Sinkron : jurnal dan penelitian teknik informatika

Implementation Of K-Nearest Neighbor Algorithm With SMOTE For Hotel Reviews Sentiment Analysis

2023-02-21T23:56:33+07:00

Indonesia has considerable tourism development potential, this phenomenon is in accordance with the number of foreign tourist visits to Indonesia from January to September 2022 recorded by Badan Pusat Statistik many as 2,397,181 visitors. This research focuses on super-priority destinations in Labuan Bajo, East Nusa Tenggara, based on the government's plan that the focus of developing this destination is to increase hotel development to meet the need for an additional 2,000 hotel rooms. Thus, the available hotel rooms are still limited. Then for need to choose a hotel based on the November 2021 survey by the Populix website, 76% of 1,012 respondents chose to book hotels online with the majority using the Traveloka website. However, making decisions in choosing hotels using the reviews feature in the Traveloka website still raises various problems, such as biased information and even the rating values given do not match the reviews submitted. So that users to know what becomes the perception of positive and negative ratings, it is necessary to do in-depth research on satisfaction factors to find out positive and negative sentiments of hotel visitors. This study uses the k-nearest neighbor algorithm with SMOTE on the research objects of the three most popular hotels in Labuan Bajo. Data testing uses a value of k = 3 so that it produces an accuracy value of 87.71% - 93.47% with a maximum error tolerance of 12.29%. In addition, the performance of accuracy results is validated by the appropriate AUC value, namely the good classification category.

Comparison of Selection for Employee Position Recommended MCDM-AHP, SMART and MAUT Method

2022-10-15T22:42:31+07:00

In a company, employees are high-value assets, therefore it is necessary to select employees for the continuity of the company, of course, by getting quality human resources. The purpose of this paper is to refute the difference in the number of rankings in selecting the best employees through a comparison of the SMART and MAUT methods. Many methods can be used in the selection process. This article describes in detail about the selection of employee promotions using the MCDM-AHP collaboration method which is used to provide an assessment of the main criteria through eigenvector values based on joint decisions by company leaders based on consistent and optimal questionnaire instrumentation which is not set based on percentages manually based on wishes leader. The SMART method is used to provide a sub-criteria assessment based on a balanced weighting utility according to the number of criteria used, with an assessment weight starting from zero as the lowest value and one as the highest value. The MAUT method will be used as a comparison against the results of the SMART method, where the MAUT method has differences in determining the weights on the sub-criteria based on the perception of understanding the criteria, so that they are arranged in an orderly manner and then determine the utility value of the criteria, so that there are similarities between the two methods. The ranking results obtained from the comparison of the two methods are that they have the same rating, so that the decision support taken also has similarities between the two SMART methods and the MAUT method. This can happen if the standard of measurement is carried out consistently through the MCDM-AHP method by not changing the assessment range in determining the interval range of each criterion.

Improved Accuracy In Data Mining Decision Tree Classification Using Adaptive Boosting (Adaboost)

2022-12-23T08:25:00+07:00

The Decision Tree algorithm is a data mining method algorithm that is often applied as a solution to a problem for a classification. The Decision Tree C5.0 algorithm has several weaknesses, including: the C5.0 algorithm and several other decision tree methods are often biased towards modeling whose features have many levels, some problems for the model can occur such as over-fit or under-fit challenges, big changes to decision logic can result in small changes to data training, C5.0 can experience modeling inconvenience, data imbalance causes low accuracy in C5.0 algorithm. The boosting algorithm is an iterative algorithm that gives different weights to the distribution of training data in each iteration. Each iteration of boosting adds weight to examples of misclassification and decreases weight to examples of correct classification, thereby effectively changing the distribution of the training data. One example of a boosting algorithm is adaboost. The purpose of this research is to improve the performance of the Decision Tree C5.0 classification method using adaptive boosting (adaboost) to predict hepatitis disease using the Confusion matrix. Tests that have been carried out with the Confusion Matrix use the Hepatitis dataset in the Decision Tree C5.0 classification which has an accuracy rate of 80.58% with a classification error rate of 19.15%. Whereas in the Decision Tree C5.0 classification Adaboost has a higher accuracy rate of 82.98%, a classification error rate of 17.02%. This difference is caused by the adaboost algorithm, because the adaboost algorithm is able to change a weak classifier into a strong classifier by increasing the weight of the observations, and adaboost is also able to reduce the classifier error rate.

Detect Fake Reviews Using Random Forest and Support Vector Machine

2023-01-10T10:17:03+07:00

With the rapid development of e-commerce, which makes it possible to
buy and sell products and services online, customers are increasingly using these
online shop sites to fulfill their needs. After purchase, customers write reviews
about their personal experiences, feelings and emotions. Reviews of a product are
the main source of information for customers to make decisions to buy or not a
product. However, reviews that should be one piece of information that can be
trusted by customers can actually be manipulated by the owner of the seller. Where
sellers can spam reviews to increase their product ratings or bring down their
competitors. Therefore this study discusses detecting fake reviews on product
reviews on Tokopedia. Where the method used is the distribution post tagging
feature to perform detection. By using the post tagging feature method the
distribution got 856 fake reviews and 4478 genuine reviews. In the fake reviews,
there were 628 reviews written with the aim of increasing product sales or brand
names from store owners, while there were 228 reviews aimed at dropping their
competitors or competitors. Furthermore, the classification is carried out using the
random forest algorithm model and the support vector machine. By dividing the
dataset for training data by 80% while 20% for data testing. Here it is known that
the support vector machine gets much higher accuracy than the random forest. The
support vector machine gets an accuracy of 98% while the random forest gets an
accuracy of 60%

Classification of Positive and Negative Sentiments Using the K-Nearest Neighbor Algorithm on iQIYI Aplication

2023-02-16T01:23:51+07:00

In the current state of the Covid pandemic, the government has implemented restrictions on community activities or PPKM, which has an impact on the number of cinemas in the country temporarily closed to reduce the spread of the virus. The number of films that have been postponed for release due to this outbreak and also the decreasing use of VCDs / DVDs have made movie streaming applications begin to be favored by the public, one of which is the iQIYI movie streaming application. iQIYI is a movie streaming app launched in April 2010, so that users can know that the iQIYI application is considered good is to do a sentiment classification on the application. Therefore, this study aims to implement sentiment classification in review data using the K-Nearest Neighbor (K-NN) algorithm. K-NN itself is an algorithm that functions to classify data based on its learning data (train data sets). The data used is iQIYI user reviews as many as 400 review data, the first stage carried out is the data cleaning process or Pre-Processing, the next step is to design a K-NN algorithm model in RapidMiner Studio software to process sentiment classification. The test results using 400 review data using the K-NN algorithm obtained an Accuracy value of 99.50% then a Precision value of 100% and a Recall value of 99.44%. Which means that this study managed to get the best and best algortima in classifying positive reviews and negative reviews against the iQIYI application.

Blockchain Technology For Circular Economy In Plastic Bank

2023-02-16T20:48:45+07:00

With the use of blockchain technology, this research sought to understand the applications, benefits, and limitations faced by circular economy-based businesses. This research was conducted at the Plastic Bank Company, which used a digital conference room to allow interviews that could not be conducted in person, as well as the researcher's residence for online data gathering and document review. Five management members of the Plastic Bank Company comprise the sample population. The information used is first-hand information derived from interview findings. In order to acquire data, several methods including interviews, document analysis, and observation were applied and tested by Triangulation. The findings of this study revealed: 1) Companies with a circular economy may employ blockchain technology to change supply chain operations, tracking, and tracing. 2) Blockchain technology has benefits for businesses based on the circular economy, including easier distribution management, less duplicate papers, increased cost effectiveness, and the ability to turn plastic trash into digital cash. 3) The general public is still unaware of the use of blockchain technology for businesses that rely on the circular economy. Furthermore, the company's success is constrained on a small scale due to the absence of finance from affiliated parties. Therefore, in order to grow the use of technology on a big scale, this circular-based economy firm for plastic banks has to strengthen its performance and efforts.

Comparison of Accuracy in Detecting Tomato Leaf Disease with GoogleNet VS EfficientNetB3

2023-02-21T09:54:46+07:00

Tomato diseases vary greatly, one of which is tomato leaf disease. Some variants of leaf diseases include late blight, septoria leaf, yellow leaf curl virus, bacteria, mosaic virus, leaf fungus, two-spotted spider mite, and powdery mildew. By knowing the disease on tomato leaves, you can find medicine for the disease. So that it can increase the production of tomatoes with good quality and a lot of quantity. The problem that often occurs is that farmers cannot determine the disease in plants, they try to find suitable herbal medicines for their plants. After being given the drug, many plants actually died due to the pesticides given to the tomato plants. This is detrimental to tomato farmers. This problem is caused by incorrect disease detection. Therefore, this study aims to solve the problem of disease detection in tomato plants, in a more specific case, namely tomato leaves. Detection in this study uses a deep learning algorithm that uses a Convolutional Neural Network, specifically GoogleNet and EfficientNetB3. The dataset used comes from kaggle and google image. Both data sets have been pre-processed to match the data set class. Image preprocessing is performed to produce appropriate image datasets and improve performance accuracy. The dataset is trained to get the model. The training using GoogleNet resulted in an accuracy of 98.10%, loss of 0.0602 and using EfficientNetB3 resulted in an accuracy of 99.94%, loss: 0.1966.

Decision Support System for SmartPhone Selection with AHP-VIKOR Method Recommendations

2022-10-15T22:40:15+07:00

Produce products that have various features and diverse functions, which are able to provide convenience with the reliability of their features and functions. The advantages possessed by SmartPhone become more confident for users to assess the level of product intelligence, the more trustworthy. The purpose of this research is to provide additional knowledge on the selection of SmartPhone to the user in having a product with various benefits. The more criteria that become a barometer, the more difficult it is to choose a product in the form of a SmartPhone. Thus, the right method is needed to perform the selection of the SmartPhone. There are several methods offered to carry out the selection process for SmartPhones, namely the Analytic Hierarchy Process (AHP) method combined with the VIKOR elimination method. Both of these methods are very supportive in the selection process with many types of criteria and their meanings against these criteria. A number of criteria that serve as a barometer for selecting object-based applications are Operating System, Processor, Internal Memory, External Memory, Back Camera, Front Camera, Battery, Cassing Model, Screen Size, Wight and Price. Of the eleven criteria have two different characteristics of understanding. The results of this study can be seen explicitly on the selection of SmartPhones through the acquisition of the smallest Qi index with the three highest ratings, namely the first ranked Samsung Galaxy A3 (0.00) the second is the Xiaomi Mi 4C with an index of 0.19, the third is the Lenovo Vibe K5 Plus with index 0.31. Thus it can be said that the collaboration of the AHP and VIKOR Elimination methods is able to provide optimal decision-making support.

Theoretical Analysis of Standard Selection Sort Algorithm

2023-02-16T01:14:02+07:00

Sorting algorithms plays an important role in the computer science field. Many applications use sorting algorithm. There are several sorting algorithms proposed by experts, namely bubble sort, exchange short, insertion short, heap sort, quick short, merge sort, standard selection sort. One well-known algorithm of sorting is selection sort. In this journal, discussion about standard selection sort is given with thorough analysis. Sorting is very important data structure concepts that has an important role in memory management, file management, in computer science in general, and in many real-life applications. Different sorting algorithms have differences in terms of time complexity, memory use, efficiency, and other factors. There are many sorting algorithms exist right now in the computer science field. Each algorithm has its benefits and limitations where a trade-off exists between execution time and the nature of the complexity of the algorithm itself. The method is theoretical analysis. Three theoretical analyses are given with deep explanation and analysis. Each with six index arrays, namely with six data on it. The numbers are sorted in ascending order. Pseudo code is also given, to understand this algorithm more thoroughly. It is concluded that this theoretical analysis explained the algorithm more clearly, by using process iteration by hand.

Travel Management Information System Employee Service at the Office of Industry and Trade of Provsu

2023-02-23T16:33:37+07:00

Technological developments and advances in science are currently developing rapidly, especially in the management of data that has used computers. The use of computers today is also used by individuals and groups that can facilitate their work. With the development of this information technology, there is an increasing need for an information system that can complete work in a systematic and efficient manner so as to facilitate the work of individuals or groups in the form of data management.The official trip itself is a work program at the agency in the form of a field activity that functions to find out and share experiences in accordance with the field of the program being carried out. With this official trip, every time a business trip is carried out, a trip report is needed to find out what activities have been carried out so as to produce a new work program for each existing agency. However, the BPK (Corruption Supervisory Agency) is often scrutinizing official travel itself, which is because every official trip is carried out, a budget will be given according to the stipulated budget, and the budget is quite large. Therefore every employee must also report official travel activities in a systematic and realistic manner.

Classification of Stroke Opportunities with Neural Network and K-Nearest Neighbor Approaches

2023-03-06T16:24:41+07:00

Stroke is one of the deadly diseases. This is illustrated in stroke
deaths in Indonesia which reached a death rate of 131.8 cases. Some of the
things that cause a stroke to become a disease with the highest mortality rate
are related to transitions in human life in 4 aspects, namely epidemiology,
demography, technology, and economics, socio-culture. Of the many
influencing aspects, one of the transition points of human life in the
technological aspect can be an alternative solution and prevention. Aspects
of technology with the utilization of data can be used as a preventive measure
for stroke. One approach is to use data mining techniques, which can provide
an initial picture regarding the chances of getting a stroke so that it can be
used as an early warning for patients. With so many techniques in data
mining, this study used a classification or grouping approach using 2
algorithms, namely K-Nearest Neighbor and one of the Neural Network
groups, namely Multi-Layer Perceptron. This research will focus on finding
the accuracy and best results of the two algorithms in classifying. The final
result of this study is that the K-Nearest Neighbor algorithm has a better
accuracy of 95% compared to the Multi-Layer Perceptron which produces an
accuracy of 88%

Implementation Opinion Mining For Extraction Of Opinion Learning In University

2022-12-13T18:20:35+07:00

Opinion mining is a field of Natural Language Processing (NLP) that is used to carry out the process of extracting and processing textual data which functions to obtain information through sentiment analysis from a document in the form of text, among others, to detect attitudes towards objects or people. Sub-processes in opinion mining can use documents of subjectivity, opinion orientation, and detection targets to find out the data used as sentiment analysis, sentiment analysis aims to assess emotions, attitudes, opinions, and evaluations conveyed by a speaker or writer towards a product or towards a public figure. In this study, an opinion mining system was developed to analyze learning in college. The methodology used is quantitative descriptive, while the processing of sentiment analysis data uses Azure machine learning. Sentiment analysis results are very good at assessing opinions or opinions and emotions, and attitudes conveyed by someone. The learning process is the main element that must run well so that competency and achievement in learning can be maximally conveyed to students. Documents that identified opinions were then classified into negative, neutral, and positive opinions based on the results. In general, it can be concluded that the value obtained by sentiment analysis using Azure Machine Learning tools is quite good, judging from the results of a positive class of 0.79 and a neutral class of 0.53. The use of cleaning and labeling techniques and other classifications is still very possible to use. To get a better accuracy value.

COMPARISON OF K-N EAREST NEIGHBOR AND NAÏVE BAYES ALGORITHMS FOR PREDICTION OF APTIKOM MEMBERSHIP ACTIVITY EXTENSION IN 2023

2022-12-30T11:10:57+07:00

So far APTIKOM as the Informatics and Computer Higher Education Association has provided many opportunities for registered members to participate in discussions on the development of science among fellow association members, access to various professional experts, as well as technical and non-technical guidelines in the field of education. With the various opportunities above, it is hoped that all members will support the activities of each member who has joined or has just joined so that a good association can be created. This study aims to find out about the problems that occur in APTIKOM, namely members who have registered as members but rarely renew their membership which results in data accumulation in APTIKOM. This research method uses the k-nn and naïve Bayes algorithms by using data sets from 2012 to 2022. The dataset used is APTIKOM member data and has 5 attributes namely name, gender, last education, institution and validation secret. To calculate the research test using a rapid miner. The purpose of this study is to predict whether in the following year there will be a membership renewal process for all APTIKOM members who have been recorded from 2012 to 2022. Furthermore, the results of this study have a different level of accuracy. Where for k-nn the resulting accuracy is 94.00% and for the result of naïve Bayes is 91.35%.

Web-Based Village Fund Assistance Distribution Information System Using the Quota Based Method

2023-02-17T12:15:37+07:00

The development of information technology has greatly influenced several aspects of human life in the implementation of daily activities. One of the benefits of the development of information technology is that it can help local governments provide information regarding the distribution of financial assistance through monitoring. Village fund assistance is one of the government programs aimed at economic recovery for people affected by the pandemic. Currently, assistance from village funds is often not supported by good governance in every village. Particularly in Tanah Merah Village, aid arrangements were still carried out by recording manually, so sometimes data input errors occurred which resulted in inaccurate data. Therefore, we need a computerized system that can overcome the limitations and problems that occur. In making this system using the Waterfall method, the stages are needs analysis, application design, system design, testing, and system maintenance. The tools used to design this system are UML (Unified Modeling Language), which consists of Use Case Diagrams, Activity Diagrams, and Class Diagrams. The results of this study are an information system for distributing village fund assistance at the Tanah Merah Village office. The application of this information system for distributing village fund assistance can help provide alternative solutions for the village government to problems in the data collection process so that the implementation process can achieve its objectives properly.

Implementation of the K-Nearest Neighbor (kNN) Method to Determine Outstanding Student Classes

2023-03-20T17:23:32+07:00

Education being one factor supporting students / I to be able to
increase their knowledge. Each student has their own potential that they have
obtained in the world of education. Therefore, every school has created an
education program that functions to increase the potential of high achieving
students. The program is a flagship class program. What is meant by a
superior class program is a process of selecting and classifying students to be
placed in the classroom superior (grade student / I achievement). Therefore,
this study aims to implement classification on student data using the KNearest Neighbor (kNN) algorithm. K-Nearest Neighbor (kNN) is a method
used to classify data based on training data (data set). The data that the writer
will use is student data of 60 student data. In this classification using the kNN
method aims to classify data on students who are eligible to enter the superior
class (class of outstanding students). The first step is the process of
determining data requirements. Then cleaning or pre-processing and the next
is to design a widget model of the kNN method on the orange application to
carry out the data classification process. The test results using 60 student data
using the KNN method and using the Confusion Matrix obtained an
Accuracy value of 91.6%, then a Precision value of 89.2% and a Recall value
of 92.5%. The conclusion is that this study succeeded in obtaining a method
that the best and also get the best results for Classification of superior student
classes.

Sentiment Analysis Of Hotel Reviews On Tripadvisor With LSTM And ELECTRA

2023-03-06T16:29:05+07:00

This study examines the importance of hotel review data analysis and the use of Natural Language Processing (NLP) technology in predicting hotel review sentiment. In this study, deep learning models such as Long Short-Term Memory (LSTM) and Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA) are used to predict hotel review sentiment in Indonesian. Hotel review data was obtained through a data scraping process with webscraper.io from the Tripadvisor website and a total of 977 hotel review data were obtained from Grand Mercure Maha Cipta Medan Angkasa. Before the sentiment prediction process is carried out, hotel review data must go through the text preprocessing stage to remove punctuation marks, capital letters, stopwords, and a lemmatizer process is carried out to facilitate further data processing. In addition, sentiments that were previously unbalanced need to be balanced through the undersampling process. The data that has been cleaned and balanced is then labeled as negative (0), neutral (1) and positive (2) sentiments. The test results show that the ELECTRA model produces better performance than the LSTM with an accuracy of 47% by ELECTRA and 30% by LSTM.

Comparison of the K-Means Algorithm and C4.5 Against Sales Data

2023-03-03T00:49:16+07:00

In general, the process of collecting and grouping data requires a
long process. And if it has to be grouped manually it takes a very long time.
Therefore, data mining is a solution for clustering data - a lot of data to
classify it. In this research conducted at CV.Togu - Togu On Medan Branch,
data mining is applied using the K-Means process model and the C4.5
algorithm which provides a standard process for using data mining in various
fields used in classification because the results of this method easy to
understand and easy to interpret. . The K-means method is a non-herarical
method which is an algorithmic technique for grouping items into k clusters
by minimizing the distance of the SS (sum of square) to the cluster centroid.
In the K-means method, the number of clusters can be determined by the
researcher himself. And the testing methods used to measure cluster quality
are the Silhouette Coefficient and the Elbow Method. Based on the research
conducted, there are significant differences before and after using the two
methods. The results of the K-Means algorithm will be compared with the
results of the C4.5 algorithm in the form of rules (decision trees). This
research produces data on goods that have the highest level of
sales/behavior

Scrum Framework Implementation of Fish Mobile Auction Module in Pasar Iwak Marketplace

2023-01-04T14:49:08+07:00

Lelang Ikan mobile application is an online auction in the marketplace platform of Pasar Iwak based on Android platform. Scrum framework is applied and consists of determining the product backlog, creating sprint planning and sprint backlogs, and conducting sprint reviews and sprint retrospectives. The product backlog resulted 14 backlog items based on the results of system and user requirements for user auctioneers. Sprint planning and sprint backlog are divided into four sprints, namely front-end and back-end development, system integration process and system implementation. Sprint reviews are carried out by implementing two types of testing, namely blackbox testing and user acceptance testing (UAT). Blackbox testing emphasizes testing application functions or features, while UAT is applied to measure the level of user acceptance. The results of blackbox testing showed that the features provided by the application are in accordance with the predetermined requirements. Whereas UAT showed the result of 66.8%, which means that the application is in the appropriate category and can be accepted by users. The application development process ends at the sprint retrospective stage which is a suggestion or feedback after the application testing. The suggestions obtained are in the form of adding tracking features, payment features with payment gateways, and application development with the iOS platform.

Design of IoT-Based Tomato Plant Growth Monitoring System in The Yard

2023-03-06T16:22:33+07:00

The development of tomato plants to produce good fruit cannot
be separated from environmental factors that affect their growth and
development of tomato plants. These factors include soil moisture, soil pH,
temperature, or the amount of light received by tomato plants. The need for
water in tomato plants is also very important for their continued growth.
Monitoring the development of tomato plants in home gardens based on
IoT (Internet of Things) is a monitoring system that utilizes IoT technology
to collect, transmit, and analyze data about tomato plants in real-time. In
this system, sensors connected to the internet network will be installed on
tomato plants to measure several parameters such as soil moisture, air
temperature, light intensity, and soil nutrient / pH levels in plants. The
collected data will be sent to an IoT platform that will be able to analyze the
data. The results of the analysis will be used to make decisions regarding
plant care, such as providing water or nutrients that the plants need to grow
properly. With cameras to monitor the physical development of the plants,
plant height, and fruit development. With this system, communities and
farmers can grow tomato plants and can monitor and control plant
conditions in real-time through smartphone applications. By utilizing IoT
technology, monitoring the development of tomato plants becomes more
efficient and accurate. Communities and farmers can take preventive
measures to avoid plant disorders and diseases before it's too late, to
increase the production and quality of crops.

Users Experience Analysis of the Zoom Meeting Application

2023-03-21T13:53:42+07:00

This research aimed to analyze the User Experience analysis
of the Zoom Meeting application according to the perspectives of
lecturers and students during online learning in the new normal era
because the Zoom application is considered to have numerous
outstanding features. The population in this research were 2 lecturers
and 123 students of the Bachelor of Elementary School Teacher
Education Study Program in the 2021/2022 academic year in Bali. The
purposive sampling technique was used along with the questionnaire
and in-depth interview. As a result, the attractiveness, clarity,
efficiency, and stimulation aspects scale got the average positive
result from the questionnaire because the value obtained was more
than 0.8. Furthermore, the average questionnaire scale was neutral for
the accuracy and novelty aspects because the values obtained were
from -0.8 to 0.8. Therefore, the accuracy aspect has the lowest value
compared to other aspects. It was also verified from the data obtained
from the in-depth interview results, which showed various problems
and obstacles experienced by users in terms of the accuracy of the
Zoom Meeting application when used as an online learning medium,
i.e., difficulties in conducting disciplinary assessments and
conducting lectures that required practical skills. Although Zoom has
many benefits for online learning, it still has several limitations that
must be addressed by lecturers, students, and Zoom developers.

Short Circuit Failure Detection in Induction Motor Using Wavelet Transform and Fuzzy C-Means

2023-02-16T01:22:18+07:00

Induction motors need to be monitored regularly because it
involves the company's productivity. The induction motor monitoring
method in this study uses a motor current variable which is transformed using
the Discrete Wavelet Transform. Discrete Wavelet Transform (DWT) is used
in this study because the results are satisfactory for detecting a short circuit
in the stator winding of an induction motor. Of the many types and levels of
discrete wavelet transforms, the haar wavelet transform at the third level is
used in this study. Furthermore, the results of the discrete wavelet transform
are processed using the Fuzzy C-means method. Fuzzy C-Mean (FCM) is the
grouping approach that each part has a member degree of cluster according
to the fuzzy logic algorithm. Motor modeling is shown in this article as
normal condition, final fault current, and initial fault current. For this
analysis, a combination of wavelet transform and Fuzzy C-means is used to
classify motor currents into three motor states. The motor current is
processed by Haar DWT level 3 to generate a high frequency signal. Then
the high frequency signal is processed to get the energy signal. The energy
signal is then fed to Fuzzy C-means to identify its condition. The results show
that fuzzy C-means produces an error of 0% for the normal case, 33.3% for
the initial error case and 0% for the final error case.

Sentiment Analysis On Twitter Posts About The Russia and Ukraine War With Long Short-Term Memory

2023-03-06T16:29:40+07:00

Sentiment analysis is one method for evaluating public opinion from the received text. In this study, we evaluate the performance of the LSTM model with Sastrawi in sentiment analysis in Indonesian using a Twitter dataset totaling 2537 data collected regarding the Russo-Ukrainian war. The purpose of this study is to determine the reliability of the LSTM model with Sastrawi in sentiment analysis in Indonesian and to evaluate the performance of the model with the collected Twitter dataset regarding the Russian-Ukrainian war. The method used in this study is data pre-processing, training and validation of the LSTM model with Literature, and model evaluation using the metrics of accuracy, precision, recall, and F1 score. In the dataset collected in this study, positive, neutral and negative sentiments were 54.7%, 35% and 10.2%. The results obtained from this study indicate that the LSTM model with Literature can provide good results in sentiment analysis with a prediction accuracy of 82%. The implication of the results of this study is that the LSTM model with Sastrawi can be used for sentiment analysis on Twitter and further research needs to be carried out with a wider and more diverse dataset, especially to produce even better accuracy.

Pet Care Information System at Darussalam Pet Shop Based on Android

2023-03-06T16:26:51+07:00

Modern technology has changed people's lifestyles, including how to raise pets. Pet is an animal kept at home or in a cage and exclusively cared for by its owner. Recently, more people owning pets. This had led to questions related to the hygiene and health of pets. An unkempt pet can cause problems for the owner, so numerous pet stores have emerged to help owners provide their animals with the care they require. However, many pet shops still use a manual system, which is considered ineffective for service, and utilizing information technology will make jobs easier while improving accuracy and information quality. Based on the problems described above, an application is required to assist and facilitate the pet shop itself and customers in caring for their pets. The research goal is to design and build suitable applications. In this journal, the researcher utilized both the Quantitative research methods and the Waterfall method for application development. For testing, the researcher used the Likert Scale. The Likert Scale calculation yielded a total score of 80.3 (Satisfied). Therefore, it can be concluded that the application is operating as intended and makes it easier to obtain pet-related information for user and manage schedules and incoming orders for administrators.

Analysis of the Naïve Bayes Method for Determining Social Assistance Eligibility Public

2023-03-23T23:10:32+07:00

Economic needs are community needs that are used to meet daily
needs. Therefore, economic needs are very important for the life of every
society. There is a gap in the economic needs of the community, the
government created a social assistance program which is assistance provided
to the community in the form of cash or non-cash. The help is made for
welfare society from inequality, especially economic inequality. So
researchers will carry out a data classification of people who are eligible for
social assistance. The classification will be carried out using the Naïve Bayes
method. The Naïve Bayes method is a simple classification method for
calculating the probability of a combination of certain data. The data to be
used by researchers is community data as much as 62 community data.
research done by using the Naïve Bayes method aims to classify community
data that is feasible to forget social assistance. The first stage of this
classification is the process of collecting community data and determining
community data that will be used as a filtered sample cleaned, furthermore
preprocessing data and then designing the Naïve Bayes Algorithm model.
The results of data classification using the Naïve Bayes method show that the
number of people who are eligible for social assistance is 14 community data
and people who are not eligible for social assistance are 48 community data.
These results can be a reference for determining the eligibility of the
community to receive social assistance.

Analyzing Image Malware with OSINTs after Steganography using Symmetric Key Algorithm

2023-03-22T22:17:11+07:00

Steganography is the practice of hiding a message or information
within another file, such as an image (Singh & Singla, 2022). OSINT (Open
Source Intelligence) involves using publicly available information for
intelligence gathering purposes. In this research, the asymmetric key
algorithm will be applied to the steganography method, using 10 images with
different sizes and dimensions. Images tested for steganography are in tiff,
gif, png, jpg, and bmp format. A combination of steganography and OSINT
could involve analyzing and decoding images found on publicly available
platforms, such as social media, to uncover hidden messages. On the other
hand, steganography within OSINT can also be used to protect sensitive
information from prying eyes. Overall, the combination of Symmetric Key
Algorithm steganography and OSINT can be a powerful tool for both
intelligence gathering and secure communication. Here in this work,
malware is developed, and using that malware the victim’s machine is
exploited. Later, an analysis is done via freely available OSINTs to find out
which is the best OSINT that gives the best results. OSINTs have been very
helpful in identifying whether the URLs and files are malicious or not. But
how binding an image with the malware makes it difficult for OSINTs to
identify they are malicious or not is being analyzed in this work. The analysis
shows that the best OSINT is VirusTotal which has a greater number of
engines that could detect the malware whereas others don’t have a variety of
engines to detect the malware. Also, when it comes to malware afore binding
it with an image is easier to detect whereas for an OSINT it was difficult to
identify and detect the malware after binding with an image

Application of the K-Means Clustering Agorithm to Group Train Passengers in Labuhanbatu

2023-03-23T17:21:04+07:00

Transportation is an activity of moving things such as humans, animals, plants and goods from one place to another. To be able to implement transportation, we need a means of transportation that suits our needs. For in Indonesia, people are more inclined to land transportation. That's because land transportation already has a lot of vehicles. Land transportation already has many vehicles that can be used, both for private and for the public. Each vehicle has its uses and risks as well. Therefore we will do a data cluster from the trains. We chose the train, because the risk from using the train is very small, meaning that there is a lot of public interest in trains. So we want to do a cluster on rail passengers. The cluster that we do is to group passenger data based on the similarity of passenger data. We will do the cluster using the K-Means method. The K-Means method is very suitable when used to perform a cluster. K-Means will process widgets that are made according to the needs of the research. So after we enter the method in the widget pattern, the widget will process it to output the results from the cluster that we created. The cluster process using the K-Means method will be applied using the orange application. After we apply it, the data will later be clustered, we will cluster data as many as 3 clusters. Then the incoming data will appear in clusters 1, 2 and 3, both from business and executive classes

Analysis of the SVM Method to Determine the Level of Online Shopping Satisfaction in the Community

2023-03-23T23:52:47+07:00

Online shopping is an activity of buying goods done online
(virtual). This online shopping process is done because it doesn't waste a lot
of time. With online shopping, it is very easy for people. Just need open
mobile phone view and select the desired item and then order goods and
goods will be delivered to the house. But online shopping sometimes also has
drawbacks which are one of the reasons people don't want to shop online,
such as long shipping times, expensive shipping costs. Therefore a study was
made about the level of public satisfaction in online shopping. Researchers
will make a data classification about the level of public satisfaction in online
shopping using the SVM method. This study aims to see the level of public
satisfaction with online shopping, many or nope satisfied people when
shopping online. The first step is to collect data that will be used in the data
mining process. After that, data preprocessing will be carried out planning
the design of the SVM method and finally the prediction process to get
Classification results. Then the classification results obtained using the SVM
method in data mining show that 34 people are satisfied with online shopping
(for a representation result of 59.65%), 23 people are dissatisfied with online
shopping (for a representation result of 40.35%). These results state that there
are still many people who are satisfied with shopping online and there are
some people who are dissatisfied with online shopping

Application of Enterprise Architecture in Digital Transformation of Insurance Companies

2023-03-31T17:37:43+07:00

Implementation of enterprise architecture is a major requirement
for companies that want to develop business processes according to their
needs. Business architecture is the company's initial plan to support the
company's operations. An insurance company is a company that provides
insurance services. Insurance is a form of contract in which the guaranteed
party pays a premium to the insurance company. Insurance companies
provide payment guarantees in the event of certain risks that are guaranteed
in the insurance contract. Therefore, this company must think about
operational forms to provide the best service for its customers. Structuring
business processes starting from the sales process, administrative processes,
claims processes, to financial processes which are the most vital processes.
Insurance companies are different from other financial services companies,
such as banking companies, fintech companies and others. The insurance
company's unique process is to provide guarantees to its customers in
carrying out risk protection. Before starting to implement enterprise
architecture, the company already has a business architecture blueprint which
is the enterprise architecture of a company. The design begins with running
architectural business processes, architectural applications, architectural
databases and architectural technology. Enterprise architecture
implementation certainly cannot be separated from project management.
Because project management is a process that manages the project so that the
project becomes more organized in its implementation

IMPLEMENTATITON OF RANDOM FOREST ALGORTIHM ON SALES DATA TO PREDICT CHURN POTENTIAL IN SUZUYA SUPERMARKET PRODUCTS

2023-03-10T13:10:20+07:00

Concentration of sales that are focused on products that are in great demand and are popular is one of the supermarket sales techniques. Seasonal sales techniques like this sometimes have an impact that can be seen obviously by the imbalance in sales of existing products in supermarkets. Sales imbalance can be the initial cause for a product to lose interest and become a product that is eventually removed from store. With a classification model made to predict which products will be eliminated or churn, it can assist staff in distributing the sales of each product. The more products are churn due to lack of enthusiasts which can affect the overall sales of the supermarket. The purpose of this study is to assist staff in classifying potentially churn products. The classification model consists of 3 models with different algorithms and the results show that the application of the Random Forest algorithm is more effective for predicting data with 96% accuracy compared to 81% for the Logistic Regression algorithm and 46% for the Support Vector Machine algorithm.

Application of the Naïve Bayes Algorithm in Determining Sales Of The Month

2023-04-03T05:29:54+07:00

One important factor for creating a healthy and growing company is the existence of sales rewards for employees to achieve sales targets every month. Assessing employees is not an easy thing when there are so many employees. This will make the assessment team have to look at the criteria carefully and carefully. Data manipulation can occur because it is difficult to make decisions with such large criteria and data without automated data mining. As a result, the company will not get competitive human resources. Sales targets are one of the keys to sales success because with sales targets, the sales prediction value can be used as a guide as a reference in determining product sales. One way to make better sales predictions is by utilizing data mining processing using the Naive Bayes algorithm. The Naive Bayes algorithm calculates the probability value of each of the attributes examined including attendance, sales targets and sales returns. Research with employee absence criteria, monthly sales and monthly sales invoice returns. From the results of the research that has been done, it can be concluded that the application of the Naive Bayes classifier method to the target data set for sales of goods achieves an optimization level of 95.78%, with attendance criteria greatly affecting employee performance so that product sales targets each month can be achieved

Smartphone Application for Support Library Operations in the Internet of Things Era

2023-04-02T10:18:03+07:00

The library can be referred to as a storage place for books and other references. The reference can be in the form of digital storage media. Libraries if not managed properly will cause chaos in the library organization. Many books were lost due to the entry and exit of books that were out of control. Currently, the library is not only a place to store books but can be maximized by managing and adding other digital devices. The use of Radio Frequency Identification (RFID) in libraries adds sophistication to the management of books and library items. In addition, currently many libraries have taken advantage of Internet of Things Technology, by adding various sensors and integrating with cloud-based storage devices. It provides a service that makes it easy for library members to find and track the current whereabouts of books. This research does not only create a library by providing hardware in the form of sensors to be installed in the library. This paper also proposes the use of smartphones as an alternative in replacing sensor hardware. This study uses a QR Code sensor to match the book you are looking for and simulates dancing a book in blocks and bookcases. with augmented reality. The purpose of this research is to make a smart library prototype to make it easier for library members to find books or other references. The results of the experiment to find books and DVDs that have been carried out achieve an accuracy of 83.33%.

Performance Analysis Of The Combination Of Advanced Encryption Standard Cryptography Algorithms With Luc For Text Security

2023-02-14T11:26:16+07:00

Data security is very important as it is easy to exchange data today.

Cryptographic techniques are needed as data security techniques. Combining two cryptographic algorithms is a solution for a better level of security. The Advanced Encryption Standard (AES) cryptographic algorithm requires low computational power and is the best symmetric algorithm. The LUC algorithm is an asymmetric algorithm that was developed from the RSA algorithm and has advantages in a better level of security and processing speed. In this research, two symmetric and asymmetric cryptographic algorithms will be combined in a hybrid scheme, namely the AES and LUC algorithms to improve data security. the AES algorithm will encrypt and decrypt messages, while the LUC algorithm performs encryption and decryption of the AES key. The results showed that the combination of the two AES and LUC algorithms was successful. However, the computational time needed by the two algorithms to perform the encryption and decryption process increases. The simulation results of the brute force attack performed show that the LUC algorithm can still be attacked. The greater the value of E (the public key of the LUC algorithm), the longer it takes for the brute force attack to be successful. The value of E is also directly proportional to the computational time required by the LUC. So it can be concluded that the AES algorithm is less precise when combined with the LUC algorithm.

Analysis of Visitor Satisfaction Levels Using the K-Nearest Neighbor Method

2023-04-04T23:14:33+07:00

Visitors are people who come to a place, entertainment, shopping, and tourism. Visitors are one of the important factors for the progress and development of a place. With visitors, an entertainment, tourism and shopping area can progress and develop. Therefore researchers will make a study of the level of visitor satisfaction. This research aims to improve the quality of an entertainment venue, shopping and increase the quantity of visitors. This research was conducted using the K-Nearest Neighbor method. The K-Nearest Neighbor method is a classification method based on training data (dataset). The data used by researchers is 45 visitor data. The classification carried out using the K-Nearest Neighbor method aims to classify data of satisfied visitors and dissatisfied visitors at an entertainment or tourism place. In using the K-Nearest Neighbor method, the first stage is selecting sample data, the data to be selected, then preprocessing, then designing the widget with the K-Nearest Neighbor method and finally testing data mining using the K-Nearest Neighbor method. The K-Nearest Neighbor Method. This visitor data was obtained by researchers through a questionnaire and the results of the questionnaire that 41 visitors were satisfied. After classifying visitor data using the K-Nearest Neighbor method, the classification results were 41 satisfied visitors. The conclusion is that many visitors are satisfied.

Application Of The C4.5 Algorithm to Determine Security Guard Work Schedules

2023-03-08T23:02:57+07:00

All agencies, companies, and public spaces must employ security guards to maintain security. The problem with the security guard's schedule is that there is an imbalance in disciplinary issues, poor performance because there is no seniority that is emulated so that the guard is not optimal which results in the problem of losing employee items, working time is not according to the rules and there is a vacancy in personnel due to personnel not coming to work, suing With the existence of a policy in the placement and distribution of the right employee work schedule, it is hoped that it can synergize all elements in the institution so that the quantity and quality of the security guard's work can increase and be completed on time. One of the techniques in data mining is classification. By applying classification techniques to security guard data and work schedules, the Decision Tree method and C4.5 algorithm are developed. The results of data processing form the root node of the gender tree as the root, that those who get schedule A are men while those who get schedule B with high school and junior level education are women, besides that they get schedule A. The accuracy of all classifications of the correct number is 61, 53%.

The Black Box Testing of the "Hybrid Engine" Application Using Boundary Value Analysis Technique

2023-03-30T01:21:38+07:00

The "Hybrid Engine" application is an introduction to a hybrid engine that is packaged attractively and can be accessed online, this application is very important for conveying information about hybrid engines, if an error occurs in the functional application there can be misunderstandings about the information conveyed. Therefore it is necessary to test to ensure the quality of the application that has been produced. Testing is an evaluation process of assessing the functional quality of software to check whether the software meets the expected process or not. Functional processes that have not been maximized can cause inequalities in the data information to be displayed. Applications that have been designed must go through the testing stages to ensure the level of functional quality. Of the several types of black box testing methods, one of them is Boundary Value Analysis. The method tests the maximum and minimum number of digits to produce a valid value and is easy enough to test "hybrid engine" applications. The first stage carried out in this research is to identify the functionality to be processed and ensure that the maximum and minimum number of digits matches the predetermined system arrangement. The result of applying the method used is that the quality of the application is under its function, and can be utilized properly by the user. The results of the Boundary Value Analysis test show that the application is following the expected system and instructions with a success percentage of 78.245615%.

Comparison of Tomato Leaf Disease Classification Accuracy Using Support Vector Machine and K-Nearest Neighbor Methods

2023-02-09T14:12:52+07:00

Tomato Leaf Disease is one of the common things for farmers in growing tomatoes. Tomatoes are one of the popular crops that can grow in low and high areas but are susceptible to disease. For this reason, farmers take precautions by looking at the characteristics and texture of tomato leaves. However, this requires more time and money and a long process. One of the efforts that can be made is to classify tomato leaf diseases. This research aims to classify using the Support Vector Machine and K-Nearest Neighbor methods. The dataset used is tomato leaf image data with 4 classes of leaves affected by disease and 1 healthy leaf. We evaluate and analyze all models using 5-Fold, 10-Fold, and 20-Fold Cross Validation with accuracy, precision, and recall for the best accuracy. The best results of this study are accuracy in the SVM method of 0.953 or 95.3%, Precision of 0.953 or 95.3%, and Recall of 0.953 or 95.3% with 10-Fold Cross-Validation. Compared to the K-NN method, it only obtained an accuracy of 0.907 or 90.7%, a Precision of 0.908 or 90.8%, and a Recall of 0.907 or 90.7% with 10-Fold Cross-Validation.

Development of Android-based Edutainment game on Numerical Ability

2022-12-22T17:15:39+07:00

Learning mathematic cannot be separated from the mathematical symbol and a numerical skill, which is required as ability to perform calculation and related matters with the numbers. This research is aimed to improve the numerical ability of students. The method used was based on Borg and call, which consisted of ten main stages involved. The first research result is the validation of android-based mobile games edutainment, that is, the average value of the three experts is 78.33% with valid criteria. Then the average validation results of the android mobile game test questions based on edutainment is 77.77% with valid criteria. The second is the value of simplicity, seen from the value of the questionnaire which was filled in by all fresh graduates which was accumulated so that a percentage of 85.84% was obtained with very practical criteria. Furthermore, the effectiveness is seen from the increase in scores workmanship of fresh graduate pretest and posttest which is calculated by the formula T test results obtained by increasing the pretest posttest score then ability numerical increase so that it is categorized as effective. Thus it is concluded that the development of android mobile games is based on edutainment on numerical ability is categorized valid, practical, and effective for used

Analysis of the Decision Tree Method for Determining Interest in Prospective Student College

2023-03-23T17:20:33+07:00

Education is learning science, skills that are carried out by a person or a group of people. The education level starts from Elementary School Education, Junior High School and High School. Apart from that, the highest level of education is college. Lectures are further education carried out by people to gain knowledge and degrees. In college education everyone can choose their respective majors, according to their wishes and desires. With college education, there will be many prospective students who will go to college. But the interest of prospective students to study varies, there are some prospective students who want to study in public and there are some who want to study privately. Therefore the author will make research about prospective students' interest in college. This study aims to see the college interest of prospective students. For this research a data classification of prospective students will be carried out using the Decision Tree method. For this research stage using the Decision Tree method, the first is data analysis, then data preprocessing, then the Decision Tree method design and finally data mining testing. The classification was carried out using the Decision Tree method using 65 prospective student data. From the results of the classification using the Decision Tree method, the results of the Classification of prospective students who are interested in studying are 46 prospective students. The classification results above show that many prospective students are interested in studying.

Sentiment Analysis of Beauty Product Applications using the Naïve Bayes Method

2023-03-31T18:56:02+07:00

The number of beauty products that appear on the market makes every producer compete in attracting consumers. One of the facilities provided by manufacturers to make it easier for consumers to shop is an online shopping application that can be accessed via gadgets. Where the feature of the application is the availability of user review services User reviews are often used as a recommendation for the product to be purchased. The more positive the reviews that appear, the greater the consumer's confidence to buy the product; conversely, the more negative the reviews that appear, the more reluctant consumers are to buy. This study aims to find out how much accuracy the Naïve Bayes algorithm has in conducting sentiment analysis on user reviews of beauty product applications with different combinations of training and test data. Furthermore, it is also important to know the frequency of words that often appear in the review. The sentiment class used is divided into three, namely, positive, negative, and neutral. This research method includes a number of stages, namely: data collection, data labeling, text pre-processing, data visualization, TF-IDF, sentiment analysis, etc., until the results are obtained. This research has produced the highest accuracy rate of 90.08% in the Naïve Bayes algorithm, with a composition of 90% training data and 10% test data. While the word that often appears in user reviews is "application," with a frequency of 446 occurrences, it is followed by the word "product," 444 times, and the word "price," 312 times. The greater the amount of training data used, the higher the level of accuracy resulting from the Naïve Bayes algorithm. Meanwhile, the greater the amount of test data used, the lower the resulting accuracy value.

Application Of The A-Star Algorithm On The Mapping Of Sports Team In The City Of Pematang Siantar Based On Android

2023-03-22T22:02:25+07:00

Geographic information system is a system that has the function to build, store, manage, and display information related to geography. This geographic information system is very helpful for human work in any case. This Android-based GIS application design produces complete information and can be accessed online or can download the application on our cellphones. Currently the city of Pematang Siantar is developing, especially in the field of technology. This research designs a technology that can help people to find a shortest route solution in searching for information on sports teams and their training locations in the city of Pematang Siantar using the A-Star algorithm. The A-Star algorithm is very helpful because the time to find the nearest route is faster and the routes found can be different but at the same cost, making it easier for designers to code in worksheets. The results of this study are in the form of an android application that is connected to the internet network so that it makes it easier for people to find information about sports teams and the closest location to where the user is using only a mobile phone and anywhere that is reachable by the internet network. This android application displays detailed information about sports teams, training locations, and training schedules controlled by the admin who is responsible for adding and changing sports team data so that the application runs properly.

Implementation of the Naïve Bayes Method to determine the Level of Consumer Satisfaction

2023-04-10T17:31:08+07:00

Satisfaction is a feeling of pleasure at something you like, you get it from goods and services. Satisfaction becomes an important assessment when someone sells goods or services. This is because satisfaction will be an assessment of the goods purchased by consumers or services that will be received by consumers. Therefore the authors make research about the level of consumer satisfaction in shopping. This research was made using the Naïve Bayes method and used consumer data as sample data which used 49 consumer data. By using the Naïve Bayes method, this study aims to see the level of consumer shopping satisfaction, it is made to see the results of a consumer's satisfaction, sometimes there are some consumers who are dissatisfied with the reason the product is not good and some are satisfied with the reason the product is still new and good. Therefore this research was made. This research was conducted using the naïve Bayes method with the first stage being data analysis, then data preprocessing, then naïve Bayes algorithm and finally system testing. After system testing is carried out, classification results will be obtained using the naïve Bayes method. Classification results stated that as many as 47 consumers were satisfied shopping and as many as 2 consumers were not satisfied shopping. The conclusion is that a lot of consumers are satisfied with shopping, meaning that the place is very good and liked by many consumers.

Android-Based RCSM Application for Implementation of Preventive Maintenance on CNC Production Machine

2023-03-30T01:18:00+07:00

Preventive maintenance (PM) implementation at POLMAN Bandung is scheduled to follow the lecture schedule so that the implementation of activities does not interfere with the lecture process. Even though the scheduling of preventive maintenance activities at POLMAN Bandung has been made quite well, there are problems in its implementation, including some activities that were not detected in the previous PM implementation, both in the form of activity reports and machine history updates. This can confuse subsequent pm implementers, as it can result in mishandling. As for the cause of the problem, there are two possibilities, namely the implementation of preventive maintenance is not carried out or the implementation of preventive maintenance has been carried out, but reports on the implementation of activities are not prepared and stored by procedures (human error). To overcome this, the researchers developed an Android-based application that functions as a reminder, recorder, and controller, for the pm process, named Reminder & Control System Management (RCSM). RCSM will remind, the implementers, to be on schedule, carry out a remind mechanisms, and information broadcast and validation until the completion of preventive maintenance activities is acceptable to the relevant authorities. Likewise, for reporting and recording engine history a system will be created with a similar mechanism. The results that have been achieved are the application software prototype reaching 100% and several field trials have been carried out. This application can direct pm implementers to avoid misuse of pm implementation procedures so that preventive maintenance implementation data can be recapitulated.

Safe Security System Using Face Recognition Based on IoT

2023-03-06T16:27:37+07:00

Face recognition is widely used in various applications, especially in the field of surveillance and security systems. This study aims to design and build a safe security system using face recognition via camera based on internet of things. This system uses the Raspberry Pi 3B and the OpenCV library as face recognition data processing which produces output on the Selenoid to open and close the safe, LCD 16x2 to display system status, IoT-based email delivery when smugglers occur. This study performs face recognition through the face detection stage using the Viola Jones method, feature extraction using the PCA (Principal Component Analysis) method and face recognition, then matched with the existing profile data in the directory. The results of this study indicate that the safe is open when a face is detected and will send a face capture to the e-mail address of the owner’s safe if the detected face is not recognized. Tests carried out on the safe security system using face recognition based on IoT build reach validity 90,25%.

Analysis of the Neural Network Method to Determine Interest in Buying Pertamax Fuel

2023-03-30T11:15:28+07:00

Fuel is one of the needs that is used by the community as a material to be used on motorcycles or cars. Fuel has become an important need for society, because when there is no fuel, a motorbike or car that is owned by someone cannot be used. Each vehicle has its own fuel, for motorbikes the fuel is pertalite, Pertamax, Pertamax Turbo and for cars the fuel is diesel and dexlite. For the fuel used in motorbikes, there are some people who are interested in Pertalite fuel and there are not many people who are interested in Pertamax fuel. So researchers will make a study of public interest in Pertamax fuel. This research will be made using the neural network method by classifying community data in data mining. This study aims to see the public's interest in purchasing Pertamax fuel. The research process was carried out with the initial stages of collecting and selecting data to be used, then preprocessing, then designing the neural network method and finally the testing process to obtain classification results using the neural network method. The results obtained from data classification using the neural network method state that there are 23 people who are interested in Pertamax fuel and 18 people who are not interested in Pertamax fuel. It turns out that many people are interested in Pertamax fuel.

DSS Using MABAC,MOORA For Selection of Majors According to Students' Interests

2023-04-06T08:56:09+07:00

In the current digital era, individual abilities are needed to be more creative and innovative in various fields, so that vocational students must better prepare their competencies. In this case the competence is related to the major they choose. On average, students take the wrong major about 35%, follow friends around 50%, for students who really choose the right major 15%. For this, the MABAC and MOORA decision support system methods are needed in terms of determining majors according to student interests and talents. System development uses the Waterfall method. The purpose of this study is to design a decision support system that can be used for selecting majors according to student interests by utilizing the results of a comparison of the MABAC and MOORA methods. The results of this study illustrate the MOORA calculation for major selection, so prospective students get the decision to choose the Multimedia major because it has the highest score. From the MABAC calculations for the selection of majors, prospective students get the decision to choose the Accounting major because it has the highest score. The comparison of the mabac and moora methods is where mabac has the highest decision outcome value compared to the decision outcome value of the moora method so that the mabac method is used to assist decision making in selecting majors according to interests.

Information Systems UI/UX Design of Online Tickets for Situ Pasir Maung Tourism in Dago Village Using the Figma Application

2023-02-28T21:51:02+07:00

has several interesting tours, one of which is Situ Pasir Maung, a place in the form of a natural tourism park located in Dago Village, Parung Panjang District, Bogor Regency. However, ticket purchases can only be made by buying directly on the spot when entering the tourist spot. This can make it difficult to order tickets due to the large number of visitors. So here a design for an e-ticket application will be made using the design thinking method to analyze and design a mobile application for online ticket ordering at Dago Tourism. In this design the editing software used is Figma, and in this study will only make UI/UX designs related to online ticket purchases. UI/UX design of the Design Thinking method for Situ Pasir. The Maung tourist ticket application was created and a prototype of the application was tested by sending a questionnaire to 20 respondents with an average score of 4.021 and most of the responses from potential users said that the tour ticket prototype was easy to understand and use. So here we will try to make an e-ticket application design. E-tickets can make it easier for buyers or visitors to get them because there is no need to come directly to tourist attractions. Ticket purchases can be made through easy-to-use online ordering

Modeling Digital Image Segmentation with Canny Method

2023-03-23T23:30:10+07:00

In general, the segmentation process is divided into three parts. classification, by edge, and by area. The digital image segmentation process divides an object whose surface or background maintains the RGB value of all pixels of a digital image so that the object can be processed for other purposes. This system aims to execute drawing objects using intelligent methods. In the Canny method, the process begins with taking digital images and continues with the grayscale process. In addition, technique selection starts with performing a complex operator or Laplacian edge detection and finally unlocks it. Successful segmentation results using edge detection with intelligent operators to separate objects. This system uses the Matlab 2017 application.

Optic Disc Detection on Retina Image using Extreme Learning Machine

2023-01-12T09:02:23+07:00

Optic disk detection on retina image has become one of many initial steps in evaluation of Diabetic Macular Edema (DME) severity. As much as early the step is, the result of the step is extremely essential. This article discusses the optic disk detection on retina image based on the color histogram value. The detection is done by using color histogram value which is taken from window sliding process with the size of 50x50 pixels. First, the candidates of optic disc were detected using Extreme Learning Machine towards the histogram value. Then the optic disc was selected form the candidates of optic which has highest average intensity. 4 retina image datasets were employed in the evaluation, including Drions dataset, DRIVE dataset, DiaretDB1 dataset, and Messidor dataset. The result of evaluation then validated by medical expert. The model outcome reaches the accuracy as much as 85,39 % for DiaretDB1 dataset, 95% for DRIVE dataset, 98,18% for Drions and 99% for Messidor dataset.

Implementation of Cyber-Security Enterprise Architecture Food Industry in Society 5.0 Era

2023-04-24T19:51:59+07:00

The application of Enterprise Architecture is an important topic in the development of the food industry in the Society 5.0 Era. Enterprise Architecture is used to integrate and optimize corporate information systems so as to generate higher business value. This study aims to evaluate the effectiveness of Enterprise Architecture implementation in improving the performance of the food industry in Era Society 5.0 and implementing Cyber-Security as a defense against the system to be implemented. This study uses a case study method by collecting data from several companies in the food industry. The data collected includes information about the implementation of Enterprise Architecture, business performance, and factors that influence the successful implementation of Enterprise Architecture. The results of the study show that the implementation of Enterprise Architecture has helped companies improve their business performance, especially in terms of operational efficiency, better decision making, and the ability to adapt to changes in the business environment. Factors that influence the successful implementation of Enterprise Architecture include management support, involvement of business users, and availability of resources. In conclusion, the application of Enterprise Architecture can help the food industry in Era Society 5.0 improve its business performance. However, the implementation of Enterprise Architecture must be accompanied by strong management support, greater involvement of business users, availability of adequate resources and adequate Cyber-Security. The novelty of this research is implementing Cyber-Security as protection in implementing Enterprise Architecture.

Implementation of ResNet-50 on End-to-End Object Detection (DETR) on Objects

2023-04-24T19:48:12+07:00

Object recognition in images is one of the problems that continues to be faced in the world of computer vision. Various approaches have been developed to address this problem, and end-to-end object detection is one relatively new approach. End-to-end object detection involves using the CNN and Transformer architectures to learn object information directly from the image and can produce very good results in object detection. In this research, we implemented ResNet-50 in an End-to-End Object Detection system to improve object detection performance in images. ResNet-50 is a CNN architecture that is well-known for its effectiveness in image recognition tasks, while DETR utilizes Transformers to study object representations directly from images. We tested our system performance on the COCO dataset and demonstrated that ResNet-50 + DETR achieves a better level of accuracy than DETR models that do not use ResNet-50. In addition, we also show that ResNet-50 + DETR can detect objects more quickly than similar traditional CNN models. The results of our research show that the use of ResNet-50 in the DETR system can improve object detection performance in images by about 90%. We also show that using ResNet-50 in DETR systems can improve object detection speed, which is a huge advantage in real-time applications. We hope that the results of this research can contribute to the development of object detection technology in images in the world of computer vision.

Drowsy Detection in the Eye Area using the Convolutional Neural Network

2023-04-28T14:19:41+07:00

Detection of a drowsy driver is an important aspect of driving safety. For this reason, it is necessary to have technology to carry out early detection before fatigue occurs. Mainly focused on driver fatigue that occurs at night. Analysis can be done quickly and accurately. These conditions can be sent via data so that they can be monitored and analyzed in real time. The results of the analysis can be sent by communication via the internet network. In addition, it functions as an early warning and can be used as logging or records that can be stored. This research does not discuss data communication but makes a prototype for detecting sleepy drivers. Prototype created using the Convolutional Neural Network Algorithm. The detection area is in the eye and testing is carried out with the brightness level of the light. In this study, building a prototype to detect signs of driver fatigue using the Convolutional Neural Network algorithm. The detection area used is in the eye, by testing at different light brightness levels. The dataset used in this study consists of a series of eye images, which are divided into two classes, namely open eyes, and closed eyes. After conducting the training process on Convolutional Neural Network, we get results of detection accuracy reaching 90%.

Implementation of IPv6 using 6RD Method on Power Line Communication Network

2023-04-07T20:31:27+07:00

The development of computer network technology is rapidly advancing in response to society's increasing demand for network services. Currently, the most widely used network protocol is IPv4, but it has some limitations. To address these limitations, a new network protocol, IPv6, has been developed. More and more new network devices are using IPv6 as their IP address, while many existing technologies and internet devices still use IPv4. Therefore, a mechanism is required to transition from IPv4 to IPv6. The 6RD tunneling method is used in Power Line Communication networks to connect two or more network devices using electrical wiring as a data transmission medium. The Power Line is equipped with a charger for a laptop and a drill, creating a load to test the performance of the Quality of Service(QoS) with the throughput parameter. The measured Rerate throughput upload was 11800 Kbit/s without any additional electrical load, 9377.8 Kbit/s with a laptop charger as an additional load, and 6082.2 Kbit/s with a drill as an additional load. The Rerate throughput download was 8098.8 Kbit/s without any additional electrical load, 7782.8 Kbit/s with a laptop charger as an additional load, and 5996 Kbit/s with a laptop charger and a drill as additional loads. With this transition mechanism, IPv4 can communicate with IPv6, allowing for more efficient network communication.

Proposed Enterprise Architecture on System Fleet Management: PT. Integrasia Utama

2023-04-29T14:43:31+07:00

An information technology consulting firm that specializes in Global Positioning Systems provides fleet management services for many of its clients. The systems currently used by companies require more advanced modernization to ensure optimal service delivery. To overcome this challenge, a proposed enterprise architecture on system fleet management is presented in this paper. The proposed enterprise architecture is a comprehensive solution that includes the necessary hardware, software and operational processes to improve fleet management services. The proposed architecture is based on the Enterprise Architecture, which enables the integration of various systems and applications used by companies. The proposed architecture includes modules for vehicle tracking, fuel management, maintenance scheduling and driver performance monitoring. These modules work together to provide real-time data on fleet operations, enabling companies to make informed decisions regarding their fleet management services. The proposed architecture also incorporates an easy-to-use interface that simplifies the fleet management process and enhances customer satisfaction. The proposed system is scalable and easily adaptable to meet service requirements across multiple customers. In conclusion, the proposed enterprise architecture for system fleet management provides a comprehensive solution to the current challenges faced by companies as a corporate fleet service provider. The proposed architecture will improve service, reduce costs, and increase customer satisfaction.

Diagnostic on Car Internal Combustion Engine through Noise

2023-05-01T13:35:45+07:00

Internal Combustion Engines are known for their unique sound characteristics. Through these sound characteristics, an experienced car mechanic will be able to diagnose the type of engine damage just by listening to the sound. This reduces the need to disassemble components to pinpoint machine faults which also contributes to a significant reduction in overall repair time. The main aim of this paper is to build a process to identify faulty machines through engine noise analysis with visual data to determine machine faults at an early stage. By capturing various types of engine sounds, data visualization uses healthy engine sounds and broken engine sounds obtained from cars as well as various types of broken engine sounds that are usually found in vehicles. This audio data will be used in audio signal processing combined with a linear regression classification algorithm. Visualization data can distinguish various types of sounds that are commonly found in damaged or damaged engines such as clicks, ticks, knocks and other types of sounds to determine the types of damage that are usually found in internal combustion engines. The data used comes from Kaggle, which is public data which is widely used as general data for data science activities. Visually, data from vehicle engines can be seen from the data on which car brand is the best in terms of sound. The results using linear regression show the R-squared score (R^2) or also called the coefficient of determination reaching 91.95%.

TOGAF Framework For an AI-enabled Software House

2023-05-01T14:00:27+07:00

The integration of artificial intelligence (AI) in software development has revolutionized the industry, leading to faster and more accurate results. However, the implementation of AI requires a robust framework to ensure effective planning, design, implementation, and maintenance of AI-enabled software systems. The Open Group Architecture Framework (TOGAF) provides such a framework, enabling organizations to develop a structured and integrated approach to AI-enabled software development. In this journal, we present a case study of how a software house utilized the TOGAF framework to integrate AI in their software development processes. We discuss the challenges faced by the organization in the integration process and how the TOGAF framework provided a structured approach to overcome these challenges. We also highlight the benefits that the organization realized through the implementation of AI-enabled software systems. The case study presented in this journal demonstrates the applicability of the TOGAF framework in AI-enabled software development, and its potential to enhance the capabilities and competitiveness of software houses. The TOGAF framework provides a structured approach to the integration of AI in software development, ensuring that organizations can effectively leverage the benefits of AI while minimizing the associated risks and challenges.

Detects Damage Car Body using YOLO Deep Learning Algorithm

2023-05-01T13:34:43+07:00

This journal presents a technique for detecting scratches, cracks and other damage to car bodies using machine learning methods. This method is used to improve process efficiency and checking accuracy and can also reduce the cost and time required for manual inspection. The method includes collecting image datasets of cars in good and damaged condition, followed by preprocessing and segmentation to separate damaged or damaged car parts. not broken. Then, it is followed by a deep learning algorithm, namely You Only Look Once, or Faster Region-based Convolutional Neural Networks, which is used to build a detection model. The model is trained and tuned using the collected data, then evaluated using the test data to measure the accuracy and precision of the detection results. The experimental results show that the proposed method achieves high accuracy and efficiency in detecting scratches, cracks, and other defects on the car body, with precision of an average of more than 70%. This method provides a promising approach to improving the car body inspection process which can be used by taxi companies to help inspect and maintain vehicles more quickly and accurately, to help with insurance, avoid accidents and so on.

Securing Messages Using AES Algorithm and Blockchain Technology on Mobile Devices

2023-05-01T04:52:15+07:00

In recent years, there has been a rapid increase in the use of mobile devices and messaging applications for communication, leading to a growing concern about the security of text messages exchanged through these platforms. This study proposes a novel method that uses the AES algorithm and Blockchain to secure text messages in messaging applications on mobile devices. The AES algorithm is selected due to its faster encryption and decryption processes, which are superior to asymmetric cryptography algorithms. On the other hand, Blockchain is chosen for its inherent security properties that only allow data addition and cannot be altered. This study aims to achieve both speed and security to prevent cybercrime in text messages. The Avalanche Effect calculation and Processing Time measurement are used as the analysis methods to evaluate the proposed approach. The results show that the computation time of the message delivery process using Blockchain and AES algorithm has an average total process time of 33.59 milliseconds. Additionally, the testing results of the Avalanche Effect value show that the AES algorithm has a value of 50% for character lengths up to 16 characters and below 50% for character lengths greater than 16 characters. Based on these testing results, the proposed combination of the AES algorithm and Blockchain is an effective method for securing text messages in messaging applications. This method can offer a secure and efficient way of exchanging text messages on mobile devices and can adopt as a standard approach for messaging applications.

Usability Evaluation of Mobile USSD-SMS Interactive Result Checking System for Resource-Constrained Settings (MIRCS) using System Usability Score (SUS).

2023-05-01T04:57:24+07:00

Mobile phones, especially smartphones have impacted the way we access information related to education. For instance, students are now able to view their results using a smartphone on a browser. However, these result systems that make it possible for students to view their exam results through web browsers or emails on their mobile devices need an internet connection for the process to work as expected. Also, given the indigent nature of most students in developing countries, this creates a digital divide for students that do not own smartphones. With many students coming from rural and often low economic status homes, not many can afford smartphones. Hence, leveraging on the potentials of Unstructured Supplementary Service Data (USSD) and Short Message Service (SMS), a Mobile USSD-SMS Interactive Result Checking System for Resource-Constrained Settings (MIRCS) was developed to provide a device agnostic accessible Result Checking System. This study evaluated MIRCS using System Usability Scale (SUS) to verify the effectiveness from a usability point of view. The result of the evaluation shows that the MIRCS is usable which received grade C (66.21), although it does not meet the acceptable level specified by SUS. Further analysis of the interaction with respondents suggests some areas of improvement to include cost of service, high availability and accuracy.

Analysis of Public Interest in Telkomsel Cards Using the Decision Tree Method

2023-04-18T00:03:54+07:00

SIM card (Subscriber Identification Module) card is a physical electronic device that is the integrated circuit of the internet. Sim cards are used by the public as a place to store quotas for internet, phone calls and SMS. There are many types of SIM cards that are used by the public, such as Telkomsel cards, XL cards, Exis cards and Smartfren cards. There are some people who are interested and use Telkomsel cards, because the network is good. But there are some people who don't use Telkomsel cards, because the quota price is quite expensive. Therefore, the Penlus will make research about people's interest in Telkomsel cards. This study aims to determine the amount of public interest in the Telkomsel card. To conduct this research, the authors used 42 community data which would be classified using the decision tree method. The data used by the author was obtained by distributing a questionnaire to the public. After classifying using the decision tree method, the result is that the people who are interested in the Telkomsel card are 33 people who are interested in the Telkomsel card (for the representation results it is 78.5%) and the results obtained are that the people who are not interested in the Telkomsel card are 9 people (for its representation results of 21.4%). From the results of the study, many people are interested in Telkomsel cards, even though the internet, call and SMS quota prices are quite expensive.

Class Balancing Methods Comparison for Software Requirements Classification on Support Vector Machines

2023-05-12T11:33:07+07:00

Cost, time, and development effort can increase due to errors in analyzing functional and non-functional software requirements. To minimize these errors, previous research has tried to classify software requirements, especially non-functional requirements, on the PROMISE dataset using the Bag of Words (BoW) feature extraction and the Support Vector Machine (SVM) classification algorithm. On the other hand, the unbalanced distribution of class labels tends to decrease the evaluation result. Moreover, most software requirements are usually functional requirements. Therefore, there is a tendency for classifier models to classify test data as functional requirements. Previous research has performed class balancing on a dataset to handle unbalanced data. The study can achieve better classification evaluation results. Based on the previous research, this study proposes to combine the class balancing method and the SVM algorithm. K-fold cross-validation is used to optimize the training and test data to be more consistent in developing the SVM model. Tests were carried out on the value of K in k-fold, i.e., 5, 10, and 15. Results are measured by accuracy, f1-score, precision, and recall. The Public Requirements (PURE) dataset has been used in this research. Results show that SVM with class balancing can classify software requirements more accurately than SVM without class balancing. Random Over Sampling is the class balancing method with the highest evaluation score for classifying software requirements on SVM. The results showed an improvement in the average value of accuracy, f1 score, precision, and recall in SVM by 22.07%, 19.67%, 17.73%, and 19.67%, respectively.