Sinkron : jurnal dan penelitian teknik informatika

Evaluation of Cluster Models for Creating Profiles of Home Buyers

2024-07-26T05:14:41+00:00

The property industry in Indonesia is currently a dynamic and continuously evolving field, in line with rapid economic growth and urbanization. Shifts in lifestyle patterns, infrastructure development, and changes in government policies have had a significant impact on how properties are marketed in Indonesia. With a growing population and increasing purchasing power, the Indonesian property market is becoming more complex. Therefore, strategies are needed to segment consumer groups for effective marketing in the housing sector. This research will delve deeper into consumer segmentation in home selection, a technique that divides consumer diversity into distinct groups based on characteristics and behavior. By using an extensive dataset involving demographic data such as location, age, gender, occupation, and many other variables, clustering algorithms can uncover complex patterns to determine consumer segments in their home selection. The algorithms to be used for this study are K-Means clustering, the Gaussian Mixture model, and Hierarchical clustering. By using these three data clustering models, we can determine which algorithm produces the most ideal results for customer profiling. The results demonstrate that the K-Means algorithm outperforms the others in accurately identifying distinct consumer segments, hence producing customer profiles. Therefore, customer profiling can also be used by the marketing division as a tool to aid in promotions in order to better understand their target audience, hence creating a successful marketing campaign.

A Comparative Study of Alternative Automatic Labeling Using AI Assistant

2024-08-05T17:15:00+00:00

The development of AI assistants has become increasingly sophisticated, as evidenced by their growing adoption in assisting humans with various tasks. In particular, AI assistants have demonstrated potential in the field of sentiment analysis, where they can automate the labeling of text data. Traditionally, this labeling process has been performed manually by humans or using tools like the VADER Lexicon. This study is imperative to evaluate the performance of AI Assistants in sentiment labeling, as compared to traditional human-based labeling and the application of the VADER sentiment analysis algorithm. The methodology involves comparing the labeling results of Gemini and You AI with those of human labeling and VADER. Performance is evaluated using the Naive Bayes and K- Nearest Neighbour algorithms, and K-Fold Cross Validation is employed for evaluation. The results indicate that the performance of both AI assistants can closely approximate the performance of human labeling. Gemini's best accuracy is achieved with the k-NN algorithm at 53.71%, while You AI's best accuracy is achieved with the Naive Bayes algorithm at 48.30%. These results are close to the accuracy of human labeling (61.12%) using the k-NN algorithm and VADER (54.29%) using the Naive Bayes algorithm. This suggests that AI assistants can serve as an alternative for text data labeling, as the differences in performance are not statistically significant.

Application of the Arima Method to Prediction Maximum Rainfall at Central Java Climatological Station

2024-09-03T02:39:24+00:00

The existence of extreme weather that is difficult to predict results in frequent hydrometeorological disasters. ARIMA is a prediction method that can capture trend patterns, seasonal cycles, and random fluctuations that are often found in patterned data. Although many samples of rain data collection points are needed to produce denser data, one point can be considered to represent an area that is not too large, such as Semarang City. This method is quite accurate for short-term forecasts, with the results of monthly maximum rainfall forecasts in 2023 showing varying MAPE values. For the 12-month forecast, prediction results range from fair to very accurate. The 7-month forecast also shows decent to very accurate results. However, the 5-month forecast shows less accurate results. This shows that ARIMA can be a useful method in forecasting monthly maximum rainfall, especially during the dry season. The application of ARIMA in Semarang City can help in planning hydrometeorological disaster mitigation, considering that the Semarang City area often experiences extreme weather that is difficult to predict. Thus, the use of ARIMA can provide significant benefits in preparing for and reducing the impact of hydrometeorological disasters in the region. In addition, with more accurate forecasts, the government and society can take preventative steps earlier, such as better water management, creating an adequate drainage system, and increasing public awareness of the threat of disasters. Therefore, this research emphasizes the importance of using reliable prediction methods such as ARIMA to improve preparedness in dealing with hydrometeorological disasters.

An IT Governance Analysis in Interior Contracting Industry: A COBIT 2019 Approach

2024-08-06T04:14:48+00:00

The very rapid development of technology is currently having an impact on every industry, which must adapt by carrying out technological transformation to survive and have added value for customers. Many businesses, including interior contractors, use a variety of hardware and software, as well as information systems, to streamline their business processes. Under these conditions, the importance of strong IT governance to ensure that the implementation of IT investments continues to provide great benefits for the company's progress has been considered a top priority. This research explores how IT governance functions in this industry using COBIT 2019, a leading evaluation framework. The main areas of COBIT 2019 will be used to assess a company's IT capabilities. This study focused on an interior contractor company in Serpong, Indonesia, which was already using enterprise resource planning (ERP) and project management software. The analysis identified 12 out of 40 domains that need improvement to achieve certain target levels. These agreed targets aim to improve IT capabilities, such as reducing dependence on external vendors for system development and creating clear standards for managing technological change. Despite these recommendations, further investigation revealed a gap between the desired and current conditions. This research proposes solutions to bridge this gap, including achieving greater IT system independence and establishing clear guidelines for navigating technological advances.

Retail Marketing Strategy Optimization: Customer Segmentation with Artificial Intelligence Integration and K-Means Clustering

2024-08-27T07:23:18+00:00

This study aims to optimize retail marketing strategies through customer segmentation using the K-Means clustering method and RFM (Recency, Frequency, Monetary) analysis. By utilizing transaction data from a large retail company, customers are categorized into six segments: VIP Customers, Loyal Customers, Potential Loyalists, New Customers, At-Risk Customers, and Dormant Customers. This segmentation allows for the implementation of more targeted marketing strategies for each customer group. For example, VIP Customers who represent 3.0% of total customers are very active with significant spending, so they deserve exclusive offers and premium services. Loyal Customers, which account for 7.0% of total customers, show high transaction frequency and loyalty, suitable for loyalty programs and recurring discounts. Potential Loyalists, which comprise 15.0%, show the potential for increased loyalty through retention campaigns. New customers representing 16.3% need a brand recognition and promotion strategy to increase their initial engagement. At-Risk Customers covering 30.7% indicated a decrease in transaction activity and required intervention to prevent churn, while Dormant Customers covering 28.1% required a strong reactivation strategy. The clustering evaluation showed an average Silhouette score of 0.3115, which indicates that the clusters that are formed are quite well defined, although there is still room for improvement. This research provides valuable insights to develop more effective and efficient marketing strategies, as well as increase customer satisfaction and loyalty.

Application of the C4.5 Algorithm for Predicting Students' Learning Styles Based on Somatic, Auditory, Visual, and Intellectual Models

2024-09-01T08:16:49+00:00

Education in Indonesia has seen significant development over the past few decades, with government efforts to improve access and quality of education throughout the country. Programs such as the 12-Year Compulsory Education and curriculum revitalization have driven an increase in school participation rates. However, challenges such as the quality gap between urban and rural areas and the low competence of teachers remain key issues in achieving more equitable and high-quality education for all segments of society. This study aims to apply the C4.5 algorithm to predict students' learning styles based on the Somatic, Auditory, Visual, and Intellectual (SAVI) model. Learning styles are an important aspect of education that affects the effectiveness of learning. By understanding individual learning styles, educators can optimize teaching methods according to students' needs. In this study, student learning style data was collected and analyzed using the C4.5 algorithm, an effective decision tree method for data classification. The results of this algorithm are decision trees that categorize students into one of four learning styles based on specific features. This study shows that the C4.5 algorithm has good accuracy in predicting learning styles, with an entropy value of 1.55 and a gain of 0.156. The implementation of the results of this study is expected to help teachers develop more optimal teaching strategies in preparing learning materials according to students' learning styles.

Proposed Implementation uses TOGAF ADM and ArchiMate - Enterprise Architecture in Retail Industry

2024-08-27T07:15:06+00:00

As the growth rate of the retail industry in Indonesia continues to increase, leveraging information technology (IT) to support business operations has become increasingly crucial for achieving effectiveness and efficiency. Retail companies must manage interconnected business systems, such as inventory management, supply chain, e-commerce, and customer service. Without a clear architecture, integrating these systems becomes challenging, leading to operational inefficiencies, difficulties in decision-making, and an inability to respond quickly to market trends. A comprehensive Enterprise Architecture (EA) is therefore essential for managing all core processes within a company. Implementing EA using the TOGAF (The Open Group Architecture Framework) methodology is an optimal choice, as it is widely recognized and adopted. Technology Architecture, Data Architecture, Application Architecture, and Business Architecture are the four primary domains of TOGAF. Business Architecture improves cross-departmental integration and streamlines Business Process, while Application Architecture facilitates automation and optimizes application systems for more efficient operations. Data Architecture focuses on structured data management, ensuring accurate and accessible information for decision-making. Meanwhile, technology architecture provides a flexible and adaptable technological infrastructure that responds to business changes. By implementing Enterprise Architecture (EA) through TOGAF ADM, the retail industry can streamline Business Process, integrate various systems, adopt new technologies, and optimize the supply chain more effectively. This approach not only enhances operational efficiency but also strengthens competitiveness in the retail sector by fostering innovation and providing responsive services.

Performance Single Linkage and K-Medoids on Data with Outliers

2024-08-29T17:06:16+00:00

One way to assess the economic growth of a province is by examining its Gross Regional Domestic Product (GRDP). GRDP calculated through the production approach reflects the total value added by goods and services from various sectors within a particular region over a specified period. To determine the GRDP, 17 business sectors are considered. In 2023, the GRDP growth rate in Papua has decreased to 3.44%, down from 4.11% the previous year. To help the government improve Papua’s GRDP, an analysis is required. Clustering methods can group regencies and cities with similar characteristics. Boxplots are used to identify outliers in the data. The data contains outliers, so one method that can be used is K-Medoids. Euclidean Distance is used to calculate the distance matrix. Before calculating the distances, standardization using z-score normalization is performed to ensure that the data ranges are the same. This article aims to identify the most effective method for clustering regencies and cities in Papua using GRDP at constant price data. Both Single Linkage and K-Medoids methods are applied in this study. The DBI is used for evaluation, with lower DBI values indicating better methods. According to the DBI results, Single Linkage outperforms K-Medoids for clustering regencies and cities in Papua, with the optimal number of clusters being three.

Keywords: Euclidean Distance; Davies Bouldin Index (DBI); Gross Regional Domestic Bruto; K-Medoids; Single Linkage; z-score Normalization

Implementation Docker and Kubernetes Scaling Using Horizontal Scaler Method for Wordpress Services

2024-09-12T07:18:44+00:00

Container is a technology that has recently been widely used because of the additional features that are very easy and convenient to use, especially for web hosting service developers, with Container making it easier for system admins to manage applications including building, processing and running applications on Container. With Container the process of creating and using the system will be easier but along with too many user requests so that the service does not run optimally. Therefore, the Container must have good scalability and performance. Scalability is needed for systems that can adjust to the needs of user demand and performance is needed to maintain the quality of services provided. This research aims to implement scaling using Docker and Kubernetes in terms of scalability and performance. The parameters of comparison between Docker and Kubernetes are for scalability, scaling up and scaling down time and for performance. The method in this research uses the Action Research methodology, which is a research model that is simultaneously practiced and theorized. With the initial steps of problem identification, action planning, action implementation, observation and evaluation. Based on the results that have been obtained, Docker consumes more CPU & Memory Usage Resources, namely at 500 Users Kubernetes consumes Resources with an average of 94.47%-4.70% while in Kubernetes 89.11%-4.50 because in Kubernetes itself has a complex system, especially special component components such as APIs, Metrics Server, Kubernetes manager to run the Container. While in Docker only has Docker Manager and Docker Compose components.

Enterprise Architecture of the Basic Banking Feature for a New Challenger of Digital Banking in Indonesia

2024-09-26T17:53:51+00:00

Digital transformation has significantly impacted Indonesia's banking industry, leading to the rise of digital banks that leverage technology for their operations, posing challenges to traditional banking models. This research investigates the implementation of enterprise architecture within the core features of digital banking in Indonesia, utilizing the TOGAF framework and Archimate modeling. The study's primary objective is to identify the core processes, challenges, and opportunities associated with managing the complex architecture of digital banks. Employing a qualitative methodology, data were gathered through in-depth interviews, direct observations, and a review of pertinent literature. The research identified three central processes in digital banking operations: deposits, time deposits, and loans. These processes were then modeled using the TOGAF framework and Archimate to align business strategies with operational activities more effectively. The SWOT analysis conducted highlights digital banks' strengths in operational efficiency, strategic partnerships, and innovation capabilities, while also recognizing weaknesses such as technological dependency and challenges in serving the less tech-savvy population. The study also identifies opportunities for product innovation, market expansion, and ecosystem integration. However, threats like regulatory changes, increased competition, and cybersecurity risks must be carefully managed. The research recommends adopting emerging technologies, enhancing third-party risk management, and improving customer data security and privacy to bolster digital banks' global competitiveness, operational sustainability, and service innovation.

The Oyster Mushroom Harvesting Determination System Based On Image Processing and Multi Layer Perceptron

2024-09-26T05:29:50+00:00

Oyster mushroom cultivation in Indonesia has seen rapid growth in recent years, particularly in South Sulawesi. The demand for oyster mushrooms is increasing as they are considered a nutritious food source. However, mushroom farmers are currently unable to fulfill market demand due to limited harvest yields. The primary factor contributing to this issue is the farmers' lack of skills in oyster mushroom cultivation. Therefore, an intelligent system is needed to identify and monitor the growth of oyster mushrooms, which can help to improve harvest yields. In this research, a system for determining oyster mushroom harvest timing will be designed using image processing techniques. This system will work by analyzing images of oyster mushrooms captured using a digital camera on the mushroom growing medium and then identifying visual characteristics that indicate mushroom maturity, such as color, texture, and size. The proposed method consists of several stages: image dataset collection, image preprocessing, image segmentation, morphological operations, feature extraction, and image classification based on Multi-Layer Perceptron (MLP). The dataset obtained includes 150 images of oyster mushrooms, divided into two classes: ready for harvest and not ready for harvest. The test results show that the proposed method can accurately identify oyster mushrooms as either ready for harvest or not. The classification model achieved an accuracy rate of 96.67%. By utilizing this technology, it is expected to enhance efficiency and consistency in the harvesting process and assist farmers in making informed decisions.

Sentiment Analysis on KPU Performance Post-2024 Election via YouTube Comments Using BERT

2024-08-18T17:50:47+00:00

This research aims to analyze public sentiment regarding the performance of the General Election Commission after the 2024 presidential election using the BERT (Bidirectional Encoder Representations from Transformers) model. Given the General Election Commission's crucial role in maintaining election integrity and the importance of transparency in Indonesian democracy, understanding public opinion through sentiment analysis is essential. Data was collected from YouTube comments, a platform increasingly popular for public expression. The analysis process began with data preprocessing, including case folding, text cleaning, tokenization, and stop word removal. The BERT model was then applied to classify the sentiment of the comments, with the model's performance evaluated using 10-fold cross-validation. The evaluation results showed that the first fold (k=1) achieved the best performance with an accuracy of 96%, precision of 96%, recall of 96%, and an F1-score of 96%, indicating the model's effectiveness in accurately classifying sentiment. In contrast, the ninth fold (k=9) exhibited the lowest accuracy at 86% with other metrics also lower, suggesting performance instability potentially caused by data variability. Accuracy and loss graphs confirmed that the first fold experienced consistent accuracy improvements and significant loss reduction, while the ninth fold showed performance fluctuations. This study provides valuable insights into public sentiment regarding the General Election Commission performance, with BERT demonstrating significant potential for sentiment analysis on social media platforms like YouTube.

Performance Comparison of KNN and CNN in Classifying Balinese Gangsa Instrument Tones

2024-08-30T03:54:53+00:00

Balinese traditional music, particularly the Gamelan Gangsa, represents a unique aspect of Indonesia’s cultural heritage. Despite its cultural significance, the study and teaching of this instrument face challenges, particularly in tone standardization and the availability of effective learning tools. This research addresses these challenges by exploring the application of Artificial Intelligence (AI) technologies specifically K-Nearest Neighbors (KNN) and Convolutional Neural Networks (CNN) in the identification and classification of Gamelan Gangsa tones. The study involved the creation of a dataset comprising audio recordings of the instrument, followed by the development and evaluation of KNN and CNN models. The results indicate that KNN, with an accuracy of 90%, outperformed CNN, which achieved an accuracy of 85%. The findings suggest that KNN is particularly effective in distinguishing subtle tonal differences, making it a valuable tool for supporting traditional music education. This research not only contributes to the technical understanding of Gamelan Gangsa’s acoustic characteristics but also underscores the potential of AI in cultural preservation. The development of AI-based tone identification systems can facilitate the teaching and learning of traditional music, ensuring its transmission to future generations. The study serves as a foundation for further exploration into the integration of AI technologies with cultural heritage, demonstrating how modern innovations can enhance the appreciation and understanding of traditional arts.

Clustering Analysis of Socio-Economic Districts/Cities In East Java Province Using PCA And Hierarchical Clustering Methods

2024-09-21T07:17:44+00:00

This study aims to analyze the socio-economic conditions of districts/cities in East Java using Principal Component Analysis (PCA) and Hierarchical Clustering. Socio-economic data for 2023 from 38 districts/cities includes the percentage of poor people, regional GDP, life expectancy, average years of schooling, per capita expenditure, and unemployment rate. PCA was used to reduce the dimensionality of the data, facilitating analysis and visualization. The reduced data was then analyzed using Hierarchical Clustering to group districts based on similar socio-economic characteristics. The clustering results were evaluated with the Silhouette Index and Davies-Bouldin Index. This study identified four main clusters with different socio-economic characteristics. The best clusters have high regional GDP, life expectancy, average years of schooling, and high per capita expenditure and low unemployment rates. The worst clusters show a high percentage of poor people and high unemployment rates. These results assist the government in designing more effective policies to improve welfare in East Java.

Optimizing HEI On-Page SEO with Instagram: Owned vs. Paid Media (PMB UHW Perbanas Case)

2024-09-17T07:59:48+00:00

In today's digital age, nearly every institution, including those in education, utilizes social media. Instagram, a leading social media platform, offers a wealth of features for sharing engaging visual content. To maximize the effectiveness of new student recruitment on Instagram, UHW Perbanas needs a clear understanding and implementation of paid and owned media marketing strategies. The next step is to compare content performance before and after implementing SEO strategies, both paid and organic. Marketing strategy analysis using content on the @pmb.uhwperbanas Instagram account has demonstrably built a positive image and attracted audience attention. Relevant, informative, and engaging content fosters audience interest, creates engagement, and increases brand awareness. This research suggests that utilizing paid advertising can significantly amplify the reach and impact of existing content. The results of content with organic Instagram show insight results of 1,232 reaches, 1,626 impressions, 133 interactions and 83 profile activities. The results of content with paid Instagram show insight results of 109,173 reaches, 177 post interactions, 1,619 profile activities and 987 advertisements. This data collection platform is obtained from the features owned by Instagram Business.The conclusion of this research highlights the effectiveness of a balanced paid and organic media strategy on Instagram. By leveraging keyword analysis results from an SEO tool, UHW Perbanas can craft compelling captions that optimize search content and drive new student admissions.

Model Random Forest and Support Vector Machine for Flood Classification in Indonesia

2024-08-20T06:34:33+00:00

People, especially those living in lowland areas and along rivers. This flood phenomenon significantly affects various aspects, both in terms of economics, environment, and public safety. Flooding is a disaster that often causes problems for most people, especially those living in lowland areas and on riverbanks. This flood phenomenon significantly affects various aspects, such as the economy, environment, and community safety. This research compares the Random Forest and Support Vector Machine (SVM) methods for flood classification in Jakarta. The data used is flood data from 2016 – 2020 in Jakarta, obtained from Kaggle. Model performance evaluation is carried out using accuracy, precision, recall, and F1- Score metrics. The analysis results show that both models accurately classification floods, with Random Forest showing a more stable performance than SVM.

Application of MCDM-AHP and EDAS Methods for Selection of the Best Residential Locations Areas

2024-05-17T11:16:04+00:00

The population density has led to an expansion of the area where people live. This opportunity is exploited by housing developers to build many locations for the development of residential areas. The purpose of writing this paper is to provide proper consideration in housing selection which can be seen from various parameters as selection criteria. The method support that can be used in residential selection is the collaboration of the MCDM-AHP and EDAS methods. This method can be used as a recommendation against the concept of multi-criteria. The more criteria used, the higher the level of difficulty to support decision making. With the collaboration of the MDCM-AHP method, it can be used to provide an assessment of multi-criteria that have optimal values, while the EDAS method will be used as a strength in evaluating the selection of alternatives based on positive and negative distances for different types of criteria through normalized values. Determination of the weighting value of the criteria is obtained through the iteration stages using the mathematical algebra matrices method and proven by expert choice apps. The decision support results obtained provide a ranking value with the first priority being PR06 with an accumulative weight of 0.552 followed by the second and third ranks respectively PR04 and PR05 with a weight of 0.545 and 0.522 respectively. Thus supporting decision making with the recommendation of the MCDM-AHP and EDAS method collaboration can provide an optimal assessment of residential selection in a detailed and accurate manner.

A Mixed-Integer Programming Approach on Clustering Problems with Segmentation Application Customer

2024-09-30T07:36:00+00:00

As a marketing strategy, segmentation involves categorizing customers into specific groups based on their loyalty to a brand. This process is crucial in shaping an effective business strategy, as identifying various customer types enables businesses to target their marketing efforts more precisely. This research focuses on solving the cluster optimization problem by applying a combinatorial optimization approach to develop a cluster optimization method. The combinatorial optimization utilized here operates on a binary system, using 0s and 1s to identify the optimal cluster for each object. Specifically, a value of 1 indicates that an object is assigned to an optimal cluster, while a value of 0 signifies that the object belongs to a non-optimal cluster. By designating clusters with a value of 1, the method ensures that the best optimization value is achieved. The 0-1 non-linear problem model ensures that objects with the shortest distances between them are grouped in the same cluster. Additionally, the model guarantees that each object belongs to only one cluster and that, across k tests, every cluster contains at least one object. This model can also be used to determine the ideal number of clusters for a given dataset, ensuring optimal segmentation results for business applications.

Performance Analysis of AODV and DSDV Routing Protocols for UDP Communication in VANET

2024-07-27T08:59:43+00:00

In high-mobility Vehicular Ad hoc Networks (VANETs), maintaining a low Packet Loss Ratio and a high Packet Delivery Ratio (PDR) under UDP communication is crucial. This study compares the performance of Ad hoc On-Demand Distance Vector (AODV) and Destination-Sequenced Distance-Vector (DSDV) routing protocols in vehicular communications and networking using Network Simulator 3 (NS3) simulations. The research employs a simulation-based approach, leveraging NS3 and SUMO to analyze these protocols across different VANET scenarios, including free flow, steady flow, and traffic jams over varying time intervals (300 to 700 seconds). Our findings demonstrate that AODV outperforms DSDV. AODV maintained an average Packet Loss Ratio of 98% and achieved higher throughput, while DSDV experienced higher packet loss and lower throughput. Additionally, AODV exhibited lower end-to-end delay and a higher Packet Delivery Ratio compared to DSDV. These results indicate that AODV is better suited for UDP communication in VANETs, offering lower packet loss, higher throughput, and reduced delays. The study further emphasizes that AODV is preferable for UDP communication in VANETs due to its superior performance metrics. There is potential for further research in vehicular communications, such as integrating advanced hybrid routing protocols and exploring the effects of different traffic densities, vehicle types, and real-world environmental conditions. By investigating these factors, future studies can enhance the reliability and efficiency of VANET communications, contributing to the advancement of intelligent transportation systems.

Extreme Learning Machine and Multilayer Perceptron Methods for Predicting COVID-19

2024-08-18T17:50:20+00:00

The number of positive COVID-19 cases in Semarang City has increased over the last year. In anticipating and preparing proper health facilities, the government must predict the number of cases. This research applies Extreme Learning Machine (ELM) and Multilayer Perceptron (MLP) to indicate the number of positive COVID-19 cases. These newly developed methods are part of Artificial Neural Network (ANN). The type of data used in the study is secondary data. Covid-19 patient data was taken from the Semarang City Health Office. The data on the number of positive Covid-19 cases used is data from April 9, 2020 to December 15, 2022. The prediction results of the ELM and MLP methods were then compared to determine which method was more effective in predicting the number of positive Covid-19 cases. The results of the study showed that both methods had an error of less than 10%, meaning that both methods were feasible for predicting the number of positive Covid-19 cases. However, based on the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) values, the MLP method had a smaller error rate than the ELM method. In predicting the number of COVID-19 positive cases, ELM has 93.436331% accuracy, and MLP has 97.055838% accuracy. The best method for predicting the number of COVID-19 positive cases in Semarang City is Multilayer Perceptron (MLP).

Comparison of Tubercolosis Detection Using CNN Models (AlexNet and ResNet)

2024-08-27T07:19:13+00:00

The bacterial infection caused by Mycobacterium tubercolosis, leading to tubercolosis is a prevalent contagious disease. This bacterium commonly targets the primary respiratory organs, particularly the lungs. Tuberculosis poses a significant global health challenge and necessitates early detection for effective management. In this context, to facilitate healthcare professionals in the early detection of patients, a technology capable of accurately identifying lung conditions is required. Therefore, CNN (Convolutional Neural Network) will be employed as the algorithm for detecting lung images. The research will utilize Convolutional Neural Network models, namely AlexNet and ResNet. The study aims to compare the performance of these two models in detecting TB through the analysis of chest X-ray images. The dataset comprises X-rays from both normal patients and TB patients, totaling 4.200 data points. The training process involves dividing the data into training and validation sets, with an 80% allocation for training and 20% for validation. The evaluation results indicate that the AlexNet model demonstrates higher detection accuracy, reaching 88.33% on the validation data, while ResNet achieves 83.10%. These findings suggest that the use of CNN models, especially AlexNet, can be an effective approach to enhancing early tuberculosis detection through the interpretation of chest X-ray images, with potential implications for improving global TB management and prevention efforts.

Analysis of Malnutrition Status in Toddlers Using the K-MEANS Algorithm Case Study in DKI Jakarta Province

2024-09-03T19:12:50+00:00

Malnutrition in children is a serious health issue in various regions, including DKI Jakarta Province, which affects the physical and cognitive development of children. This research aims to classify malnutrition status in children using the K-Means algorithm, focusing on cases in DKI Jakarta. The objective is to identify patterns of malnutrition prevalence across different regions, serving as a basis for more effective interventions. The data used in this study includes the percentage of children with severely stunted, stunted, and normal nutritional status across six districts/cities in DKI Jakarta. The results of K-Means clustering show that Central Jakarta has the highest prevalence of severely stunted (10.50%) and stunted (13.01%) status, while West Jakarta has the lowest prevalence of severely stunted (4.62%) and stunted (10.22%) status. The solution offered by this research is the grouping of regions based on malnutrition prevalence, allowing for the identification of areas requiring priority intervention. The analysis results indicate that DKI Jakarta can be classified into several clusters based on malnutrition prevalence. The cluster with the highest malnutrition prevalence includes Central Jakarta, while the cluster with the lowest malnutrition prevalence includes West Jakarta and the Thousand Islands. The implementation of K-Means in this research provides an efficient approach to identifying groups of regions that need more attention in combating malnutrition in children. In conclusion, this research can serve as an important reference for policymakers in formulating more effective and efficient intervention strategies in DKI Jakarta, as well as inspire similar studies in other regions with different population characteristics

Designing an Used Goods Donation System to Reduce Waste Accumulation Using the WASPAS Method

2024-09-17T07:54:31+00:00

This research aims to build a website application-based selection system for recipients of used goods donations using the WASPAS method. This system is designed to assist in the efficient and fair distribution of used goods to recipients in need. The WASPAS method is applied to calculate the preference value (Q_i) for each alternative donation recipient based on predetermined criteria. The analysis results show that "Alternative-01" is the best alternative with the highest Q_i value (1.866), while "Alternative-02" has the lowest Q_i value (1.713). The significant difference in Q_i values between these two alternatives indicates a clear difference in preferences. The weight (w) given to each criterion plays an important role in forming the preference value (Q_i). Therefore, careful consideration needs to be taken in determining the weight of each criterion to ensure that the final decision is in line with expectations. The WASPAS method has proven to be effective in the selection system for recipients of used goods donations. The advantage of this method lies in its ability to handle multi-criteria problems and uncertain data. By applying the WASPAS method, the decision-making process can be carried out more quickly, accurately and objectively. Although the WASPAS method provides a strong basis for decision making, it is also necessary to consider other relevant factors, both quantitative and qualitative. This will ensure that the final decision taken is the best decision and in accordance with the research objectives.

Integrated MCDM-AHP and MABAC for Selection Head of Branch Offices

2024-05-02T03:14:13+00:00

Leadership changes are very urgent in maintaining organizational stability. A good relay can build significant strength in carrying out organizational operational activities, of course this must be done with good selection. The purpose of this writing is to provide a consistent picture of the selection of branch heads in carrying out business competition which is measured based on the competencies possessed by the selected employees. The barometer is determined based on eight criteria as an assessment that is declared objective by the leadership, namely critical thinking, communication, analyzing, creative and innovation, leadership, adaptation, cooperation, and public speaking. The method used will be implemented in an integrated manner from the two MCDM-AHP methods and the MABAC method. These two methods have similar applications to the selection process. MCDM-AHP is used to select eight criteria as determinants of weighting and the MABAC method is used to determine the ranking process assessment for integrated decision making. The results obtained based on the weighted matrices of the branch head office selection process were measurably obtained, namely that the first priority was held by A11 with a weight of 1,406. The results of the integrity of both methods can provide evidence of decision support for the branch head selection process consistently with optimal results. The ranking system can be regulated and utilized for the purposes of selecting leaders to be placed in other positions.

Comparison of K-Means and Self Organizing Map Algorithms for Ground Acceleration Clustering

2024-09-22T16:16:33+00:00

This study evaluates earthquake-induced ground acceleration in Indonesia, which is located in the Pacific Ring of Fire zone, using Donovan's empirical method and comparing two clustering algorithms, Self Organizing Map (SOM) and K-Means. The main problem faced is the high risk of earthquakes in Indonesia and the need for effective methods to predict potential damage to buildings and infrastructure. The research objective is to evaluate earthquake-induced ground acceleration and identify acceleration distribution patterns using clustering techniques. The solution methods used include the application of the Donovan method to calculate ground acceleration based on BMKG data, as well as the use of SOM and K-Means algorithms to cluster the ground acceleration data. GIS and Python applications are used to visualize the clustering results. The results show that the Donovan method integrated with SOM and K-Means provides significant insights into the distribution of ground acceleration, thus assisting in risk evaluation, disaster mitigation planning, and the development of more effective earthquake-resistant infrastructure development strategies in Indonesia

A Review on AMRR and Improved Round Robin Algorithms: Comparative Study

2024-03-06T03:04:54+00:00

Round Robin Algorithm is a dominant algorithm in real time system. Improved round robin and average max round robin, which is also called AMRR are two types with a breakthrough. Improved round robin is an algorithm where if the remaining burst time of the process is less than the quantum, then the running process will continue to be executed. Afterwards the next iteration will be executed as its turn. So, each iteration will have a vary of quantum. It is called a dynamic time quantum. Different with improved round robin, in AMRR, in every iteration, the quantum will be calculated. So, for every iteration, the quantum might be different, depending upon the quantum calculation of the rest burst time. The first stage of this algorithm is to calculate the average of the existing burst times. Then this average is added with the maximum existing burst time. This addition then will be divided, then we get the quantum. This calculation will be executed again after the iteration finish. Based on our analysis, with quantum 10 in these two algorithms. It is can be shown that the improved round robin is less efficient than AMRR, because its average turnaround time and average waiting time is lower. The average turnaround time is 17.25 ms for AMRR compared to 23.25 ms in improved round robin. And the average turnaround time is 9 ms for AMRR compared to 15 ms in improved round robin.

Comparison Of Machine Learning Algorithms On Stunting Detection For 'Centing' Mobile Application To Prevent Stunting

2024-08-06T04:09:52+00:00

Stunting is a growth disorder caused by chronic undernutrition, with long-term impacts on child health and development. In Indonesia, the prevalence of stunting reached 31.8% in children under five years old in 2018, indicating an urgent need for effective interventions. In an effort to address this issue, we developed a mobile application called Centing (Cegah Stunting) that utilizes machine learning for early detection and prevention of stunting. In this study, we compare the performance of four machine learning algorithms Logistic Regression, Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel, Convolutional Neural Network (CNN), and Multilayer Perceptron (MLP) in detecting children's nutritional status based on a dataset from Kaggle with 121 thousand data and four main features: age, gender, height, and nutritional status. The experimental results show that SVM with RBF kernel and CNN achieved the highest accuracy of 98%, while Logistic Regression and MLP achieved 76% and 97% accuracy respectively. SVM with RBF kernel was chosen as the best model due to its high accuracy and efficiency in computation time. These findings suggest that the Centing application, with the implementation of SVM RBF, has significant potential in early detection and prevention of stunting, and makes an important contribution to improving child health in Indonesia.

Analytical Study Forecasting Students Using Random Forest and Linear Regression Algorithms

2024-07-17T16:42:10+00:00

Forecasting new student admissions essential for higher education institutions as it helps them plan for staffing and budgetary needs. Accurate predictions are difficult due to factors like economic conditions, government policies, and University competition. This study aims to analysis forecasting at Nasional university using Random Forest and Linear Regression algorithms. By examining historical admission data, the research seeks to identify key factors influencing the number of accepted students. Methodology involves collecting data from past admissions and applying both Random Forest and Linear Regression to compare their performance. Preliminary results, based on parameters such as application form purchases from 2015 to 2023, form prices, accreditation, and leading study programs, suggest that Random Forest offers more stable and realistic predictions. Analysis for MAE, MSE, RMSE, MAPE, MAD suggests that Linear Regression is more accurate for this data. predicts closer to actual values with lower overall errors. This makes Linear Regression preferable as it provides more reliable predictions with less deviation compared to Random Forest. Looking at admissions forecasts for the next 5 years, Random Forest predicts a steady decrease from 4224 in 2024 to 4129 in 2028. In contrast, Linear Regression suggests a stable trend with slight annual dips, going from 4954 in 2024 to 4941 in 2028. Therefore, Linear Regression is a more stable and realistic choice compared to Random Forest for this forecasting task in this research.

Analysis Technique Data hiding using HPA DCO on SATA Hard Drive

2024-08-19T13:32:10+00:00

Data hiding techniques in the Host Protected Area (HPA) and Device Configuration Overlay (DCO) areas of SATA Hard Disk Drives have become a frequently used anti-forensic activity to hide data and evidence. The area is inaccessible to standard operating systems and software, making it capable of hiding data. This technique utilizes the ability of the SATA Hard Disk Drive to reconfigure the storage size so as to hide evidence. When anti-forensic data hiding Host Protected Area (HPA) and Device Configuration Overlay (DCO) activities occur, it is necessary to conduct a digital forensic investigation to find clues that are useful in solving crimes. Therefore, in this research, an assessment of data hiding techniques using Host Protected Area (HPA) and Device Configuration Overlay (DCO) on SATA Hard Disk Drives is carried out. The implementation of the HPA DCO data hiding technique on a SATA Hard Disk Drive by identifying the HPA DCO area on the SATA HDD and investigating the acquisition results on the SATA HDD is the subject of this research. It is expected that the results will provide a comprehensive overview of HPA DCO data hiding techniques on a SATA HDD as well as recommendations on how to identify and investigate SATA HDDs that have HPA DCO. This effort aims to evaluate the HPA DCO data hiding technique in various cases and provide insight into the potential use of this technique in hiding data or evidence.

Inorganic Waste Detection Application Using Smart Computing Technology with YOLOv8 Method

2024-09-17T18:45:03+00:00

Waste and renewable energy are critical issues in Indonesia, with the government aiming for renewable energy (RE) to contribute 23% to the national energy mix by 2025. This research focuses on developing a waste processing system through the TOSS (Tempat Olah Sampah Setempat) method and Peuyeumisasi technique to convert waste into biomass, such as briquettes and pellets for fuel. However, manual waste sorting remains time-consuming, prompting the need for a real-time detection system. You Only Look Once (YOLO) is an object detection approach that utilizes Convolutional Neural Networks (CNN) for object detection, making it one of the applications of intelligent computing in the field of computer vision. the latest version of YOLO is YOLO v8 offering several improvements over the previous version, can be employed in a real-time detection system to separate organic and inorganic waste. In this study, the dataset used consists of 2.000 images comprising five classes of inorganic waste: plastic bottles, plastic, glass, cans, and Styrofoam. The study demonstrates that YOLOv8 performs exceptionally well in detecting inorganic waste, with an average accuracy of 98% based on direct testing, and model evaluation showing an average accuracy of 99.33%, precision of 99.63%, recall of 96.53%, and an f1-score of 98.03%. These results indicate that the YOLOv8 method can significantly accelerate and simplify the waste sorting process, thereby supporting the conversion of waste into renewable energy. This research is expected to provide a practical solution and serve as a reference for future studies.

Comprehensive Study of Information Technology Strategy Components in Global ICT Companies Utilizing PESTLE and Ansoff Matrix

2024-08-05T17:57:55+00:00

This research underscores the diversity and strategic significance of IT Strategy components in shaping the digital transformation and competitive edge of ICT companies. The formulation of IT Strategy documents is pivotal for industries, including ICT companies, as it ensures alignment with business goals and competitive positioning. This study conducts a comprehensive literature review of IT Strategy components within global ICT companies, specifically those specializing in telecommunication network infrastructure. Despite operating within the same sector, each company’s IT Strategy document comprises distinct components. The identified components include Auditor Report, Business Strategy, Leadership, Product/Service Line, Geographic Performance, Research & Development, Partnership & Acquisition, Summary Report, Corporate Governance, Vision & Mission, Financial Statement, Industry Trends, and Business Highlights. These components are essential for aiding the organization’s IT Strategic Plan and the creation of the company's roadmap. Furthermore, this study identifies PESTLE analysis and the Ansoff Matrix as crucial tools in creating strategic roadmaps tailored to each company’s unique objectives and market conditions.

Performance Comparison of ARIMA, LSTM, and Prophet Methods in Sales Forecasting

2024-08-26T08:58:08+00:00

The development of the business world that is growing rapidly today resulted in tighter competitiveness between fellow business actors. One of the businesses that has sprung up in the market today is the bakery business. Currently, bread is one of the food needs in Indonesia that is great demand by children to the elderly, which is often used as breakfast or snack. One of the companies that produces white bread is the Bandung White Bread Factory. The number of sales at this factory continues to increase every month based on total sales data recorded since 2021. With the increasing number of sales at this factory, the factory often experiences stock shortages and cannot meet customer demand. Therefore, in this study, a model has been developed to forecast the sales of white bread using the ARIMA, LSTM, and Prophet methods. The results of the study showed that the ARIMA method (1,0,2) had the best performance compared to the LSTM and Prophet methods, because the ARIMA method (1,0,2) produced the smallest error accuracy value, namely with a MAPE value of 4.548%, an MSE value of 2248.0822, and an RMSE value of 47.4139.

Summarizer Precision Value on Tribunnews Gorontalo in the Implementation of Online Discourse Sentiment Analysis

2024-08-30T03:53:51+00:00

This research investigates the precision of a summarization-based sentiment analysis framework applied to online discourses, specifically from Tribunnews Gorontalo. This study aims to develop and evaluate a sentiment analysis framework that accurately parses complex meanings and nuances in online discourse. The research process begins with summarizing the content using Python, followed by tokenization and sentiment analysis using the BERT model. The precision of the sentiment analysis was meticulously measured. Results indicate that the precision analysis demonstrates that the Python-implemented model achieved a 86% precision rate when applied to ten online discourses from Tribunnews Gorontalo. This research contributes significantly to understanding public sentiments in online content, offering deeper and more accurate insights.

Rainfall Monitoring Using Aloptama Automatic Rain Gauge And The Network Development Life Cycle Method

2024-07-21T16:22:35+00:00

Examining the role of rainfall data management in monitoring and reducing natural disasters. Between the observation post and the coordinating office of the Central Java Meteorology, Climatology and Geophysics Agency, there are problems in managing rainfall data. To increase the accuracy and efficiency of rainfall monitoring, the Central Java BMKG Coordinator has used various platforms that are considered very good, such as Grafana, Node-RED, Xampp, and MQTT. Previous research has shown that the use of the Automatic Rain Gauge (ARG) and the Network Development Life Cycle (NDLC) method is very effective in creating an accurate and reliable rainfall monitoring system. This research uses the NDLC model, which consists of analysis, design, prototype simulation, implementation, monitoring and management stages. It is hoped that the research results will help improve visual monitoring of rainfall in local areas and increase understanding of rainfall patterns, flood prediction, water resource management and mitigation measures. This will serve as a reference for governments and institutions working together to make decisions to avoid catastrophic climate change.

Cluster Analysis of Food Social Assistance in DKI Jakarta: K-Means Approach to Identify Expenditure Patterns and Beneficiaries

2024-09-11T04:50:48+00:00

This study aims to evaluate the effectiveness of the K-Means algorithm in grouping social assistance recipients in DKI Jakarta based on various demographic and economic factors, such as income, number of family members, and living conditions. The main objective of this study is to optimize resource allocation in social assistance programs by identifying different recipient clusters, so that aid distribution becomes more targeted. In this study, the K-Means algorithm was used with an optimal number of clusters of 3, and produced an accuracy rate of 85%, indicating that this algorithm is effective in grouping large-scale and complex data. However, there are challenges related to the sensitivity of K-Means to outliers and data imbalances that affect the results of the analysis. The results also show that areas such as Central Jakarta and South Jakarta receive more social assistance compared to other areas such as North Jakarta and East Jakarta, reflecting differences in needs in various regions. These findings emphasize the importance of selecting the right variables, such as access to health facilities and economic conditions, in producing more accurate groupings. Overall, this study provides valuable insights into efforts to optimize the distribution of social assistance in DKI Jakarta and recommends further research to address the limitations that exist in the use of the K-Means algorithm, especially in the context of data that is imbalanced or has large variations.

Master Stockist Customer Segmentation Using RFM Model and Self-Organizing Maps Algorithm

2024-09-17T07:55:40+00:00

Master Stockist PT SNS 21 Bali struggles to identify member performance based on purchasing behavior because the applicable system only records transactions and stock of goods without providing insight into customers. Customer segmentation can be carried out to identify and understand differences in customer purchasing behavior. Therefore, this study aims to determine customer segmentation using the RFM (Recency, Frequency, Monetary) model and the Self-Organizing Maps (SOM) algorithm. Segmentation development uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) approach. The RFM model numerically represents customer behavior through three variables, while the Self-Organizing Maps algorithm groups customers into segments with similar characteristics. In this research, the best SOM parameters are 750 iterations, learning rate 0.5, radius 0.5, and grid size 1x3, resulting in 3 clusters with a Silhouette Score of 0.647608 and a Davies-Bouldin Index of 0.536503. Cluster 1 consists of 226 new customers with low RFM values who need encouragement to be more active. Cluster 2, comprising seven members, has low recency, high frequency, and high monetary values, representing loyal customers who need to be retained. Cluster 3 consists of 239 inactive customers with high recency, low frequency, and low monetary values, requiring a reactivation strategy.

Web-Based Application Development using PHP-Native Framework on Agent of Change Integrity Zone Information System

2024-10-08T15:05:32+00:00

An Integrity Zone is an activity related to government policies and efforts to create an environment free from corruption, collusion, and nepotism (KKN). The Integrity Zone aims to encourage transparency, accountability, and clean practices in the management of a bureaucracy. To further the success of this Integrity Zone, a Agent of Change was formed who acts as a Role Model for all parties. As a role model, agents of change must be able to provide examples in attitude, behavior, and thinking. In addition, they must be able to provide creative solutions in dealing with problems in their agencies. And must be able to provide creative ideas to improve the performance of all parties. Sometimes, their ideas are not well documented. So a digital-based system is needed that can facilitate the work of these agents of change. For this reason, it is necessary to create a Web-based application for recording, reporting, and implementing change agent performance so that it is more optimal, efficient, and effective. In this study, the development of web-based applications using a framework with PHP-Native technology. Most PHP frameworks that exist today, use MVC and OOP technology but no one has utilized PHP-Native technology as a framework. This aims to facilitate the creation of applications for programmers who have not familiar with MVC or OOP concept.

Building Sustainable Communities: SIMARET Development for Financial Transparency with MDALC Approach

2024-10-07T13:42:10+00:00

The increasing need for financial transparency and efficiency in community-level governance, particularly within Rukun Tetangga (RT) in Indonesia, calls for innovative solutions. This study presents the development of SIMARET, a mobile application designed to enhance the management of RT financial activities and resident participation, using the Mobile Application Development Life Cycle (MDALC) approach. The research aims to address the challenges of manual financial management, such as lack of transparency and difficulties in tracking funds and activities like neighborhood watch (Siskamling). SIMARET incorporates key features such as digital tracking of resident contributions (jimpitan), QR code-based attendance for Siskamling, and automated financial reports. The system was developed through MDALC’s structured phases: identification, design, development, testing, and deployment. Blackbox Testing and User Acceptance Testing (UAT) were conducted to ensure functionality and user satisfaction. The results show a high satisfaction rate of 97%, confirming that SIMARET simplifies financial administration and enhances community participation. The study also highlights the application’s contribution to the United Nations Sustainable Development Goals (SDG) 16 by promoting transparency and effective governance at the local level. Although SIMARET demonstrates significant potential, further research is recommended to improve its user interface design and expand its implementation in other communities.

Implementation of the Agglomerative Hierarchical Clustering Method in Ordering Hijab Products

2024-10-07T05:21:27+00:00

The ever-evolving internet technology has an impact on various sectors, including the hijab business, where the demand for hijab products is increasing through online transactions. This research was conducted at the Kinan Hijab Store in Kota Pinang, North Sumatra, with the aim of optimizing the management of hijab product stock. The problem faced is the imbalance in the stock of hijab products, where some hijab products have excess stock that are less in demand while popular hijab products often experience a shortage of stock. To solve this problem, the Agglomerative Hierarchical Clustering method is used to group hijab products based on sales data, product type, and price. This study uses hijab sales data from May to July 2024. After the clustering process, hijab products are grouped into two categories: "Popular" and "Less Desirable". The "Popular" category includes 190 products, while the "Less Desirable" category includes 983 products. Product stock in the "Popular" category will be increased by 50% of the average sales, while stock in the "Less Desirable" category will be reduced by 25%. the effectiveness of the Agglomerative Hierarchical Clustering (AHC) method in stock planning and management by showing that it improved the inventory allocation based on customer demand patterns. The clustering method categorized hijabs into two main groups: "Popular" and "Less Preferred", based on key sales metrics such as quantity sold, price, and total sales. The implementation of the stock plan is carried out based on the sales pattern of each hijab category. Overall, the application of this method not only helps stores in understanding customer purchasing patterns but also optimizes product availability, which can ultimately increase customer satisfaction.

Sentiment Analysis on BNI Mobile Application Review Using K- Nearest Neighbors Algorithm

2024-10-02T18:37:46+00:00

Advances in Science and Technology continue to evolve in response to the demands of modern times, particularly in various fields such as banking. The development of information technology has transformed the way transactions are conducted from traditional to digital, accessible flexibly through Mobile Banking. BNI has created the BNI Mobile Banking application to facilitate customers in their transactions. The objective of this study is to investigate how the use of BNI Mobile can influence the ease of customers in conducting transactions. The data collection method used in this study is the K-Nearest Neighbors method, focusing on user experience with the BNI Mobile Banking application

Optimization of Backpropagation Method with PSO to Improve Prediction of Land Area and Rice Productivity

2024-09-30T07:32:53+00:00

This research aims to optimize the Backpropagation method using Particle Swarm Optimization (PSO) optimization to improve the accuracy of prediction of harvest area and rice productivity. The results show that the best architecture for prediction of harvest area is 3-15-1, with a Mean Squared Error (MSE) value of 0.0049980 for standard Backpropagation, and 0.00092376 after being optimized with PSO. Meanwhile, for rice productivity prediction, the best architecture is also 3-15-1, with an MSE value of 0.0049998 for standard Backpropagation, and 0.000435762 after using PSO. PSO optimization significantly reduces the MSE value, which indicates that this method is more accurate than standard Backpropagation. Predictions from 2024 to 2026 show more consistent results with some provinces experiencing an increase or decrease in harvested area and rice productivity that is different from the standard Backpropagation method. Based on the prediction accuracy that reaches 100% and the lower MSE value, it can be concluded that Backpropagation with PSO optimization is a superior method. The results of this study are useful for government, farmers, researchers, and policy makers in more effective agricultural planning and better risk management

Data Visualization for Building a Cyber Attack Monitoring Dashboard Based on Honeypot

2024-10-03T08:48:39+00:00

Computer networks are essential for modern life, enabling efficient global information exchange. However, as technology advances, network security challenges grow. To enhance security, honeypots are used alongside firewalls, mimicking legitimate systems to attract hackers and analyze their attack methods. In this research, Cowrie and Dionaea honeypots are implemented. Cowrie targets brute force attacks on SSH, while Dionaea detects port scanning and denial of service (DoS) attacks. These honeypots effectively capture and log malicious activities, providing insights into attack patterns. The collected data is analyzed using the ELK Stack, which offers real-time visualization of attack trends, frequency, and methods. This analysis helps security teams quickly identify and mitigate threats. The integration of honeypots with the ELK Stack significantly enhances network defense by improving detection, analysis, and response to cyber threats. The analysis of the results shows that both honeypots effectively capture and record malicious activities entering the network, providing critical insights into the attack patterns employed by attackers. Within just minutes of deployment, the honeypots logged over 1,000 attacks, predominantly originating from botnets attempting to exploit system vulnerabilities. The captured log data is processed through the ELK Stack, allowing for real-time visualization of attack patterns, including geographic origins, attack frequency, and methods used. This enables security teams to proactively identify trends, assess risks, and implement targeted mitigation strategies more efficiently.

Optimization of Stock Forecasting in Bali Retail Businesses to Support the Digital Economy Using Weighted Moving Average (WMA) Approach

2024-10-03T08:47:51+00:00

The development of the digital economy provides new challenges for the retail sector, especially in stock management. Accurate stock management is a key factor in improving operational efficiency and minimizing the risk of overstock and understock. This research aims to optimize stock forecasting in retail businesses in Bali using the Weighted Moving Average (WMA) method. WMA gives greater weight to the most recent data in order to forecast future demand for goods. Sales data from 2017 to 2021 was collected and used as the basis for forecasting. The forecasting process was conducted for several products, including Dolphin and Dua Kelinci. The results show that WMA is able to provide accurate predictions, especially for products with stable demand patterns. For Dolphin products, the WMA forecast for January 2024 predicted a demand of 14.8 units, with a Mean Absolute Deviation (MAD) of 3.64. Dua Kelinci products, however, experienced more fluctuations in demand, with a forecasted January 2024 demand of 7.6 units and a MAD of 4.3. Despite some variations, WMA proved to be more accurate compared to simpler methods like Simple Moving Average (SMA). By using WMA, retailers can more efficiently manage stock, improve customer satisfaction, and reduce the risk of overstocking or understocking. This research confirms the importance of integrating advanced forecasting methods in supporting the competitiveness of the retail sector in the digital economy era.

Forward Selection as a Feature Selection Method in the SVM Kernel for Student Graduation Data

2024-10-09T01:43:41+00:00

In the era of information technology development, accurate graduation predictions are important to improve the quality of higher education in Indonesia. This research evaluates the effectiveness of Support Vector Machine (SVM) with various kernels, including Radial Basis Function (RBF), linear, and polynomial, as well as the application of FS as an optimization method. The dataset used consists of student graduation data which includes nine independent attributes and one label. This research aims to increase the accuracy of student graduation predictions using the SVM method which is optimized through Forward Selection (FS). The SVM method is applied using 10-fold cross validation to predict on-time graduation. The results show that the combination of SVM and FS improves prediction accuracy significantly. The SVM model with an RBF kernel optimized with FS achieved the highest accuracy of 87.06% and recall of 53.68%, showing increased sensitivity in identifying student graduation cases compared to SVM without FS. Although there is a trade-off between precision and recall, the model optimized with FS shows better performance overall. This research contributes to the development of a more efficient graduation prediction method, which can help universities in planning strategies to improve academic quality. Further studies are recommended to overcome weaknesses in the recall value by using other optimization methods or combinations of other optimization algorithms

Implementation Of Technology Towards The Merdeka Curricullum Doing Diagnostic Assessment For Student with Autism Spectrum Disorder In Preschool Level

2024-07-14T15:45:22+00:00

This research aims to developing an effective and applicable diagnostic assessment instrument that has been prepared based on the requirements of competency standards for graduates at the preschool institute. The instrument functions is to separate mild and moderate levels of the autism spectrum, for students with learning disabilities resembling autism spectrum symptoms in early childhood. This research used R and D methode from Borg and Gall with result is this application product containing a 23-item questionnaires that has been validated by material, language and media experts. Subject of this research is teachers of preschool institutions, and the objek is the instrument of diagnostic assessment wich researcher build. The practicality test results of this instrument have a percentage level of 92.52% in the 'very practical' category, with a validity test level of 84%, on the Likert scale showing the instrument is 'very feasible'.

Comparative Study of XGBoost, Random Forest, and Logistic Regression Models for Predicting Customer Interest in Vehicle Insurance

2024-10-24T09:25:03+00:00

In today’s competitive insurance market, accurately predicting customer interest in additional products, such as vehicle insurance, is crucial for optimizing marketing strategies and maximizing sales. This study presents a comparative analysis of three machine learning models such as XGBoost, RandomForest, and Logistic Regression to predict customer interest in vehicle insurance based on a dataset that includes demographic, vehicle, and policy-related features. The dataset was analyzed using five-fold cross-validation, and the performance of the models was evaluated using AUC-ROC, precision, recall, and F1-score. XGBoost demonstrated the highest recall (0.9525) and AUC-ROC (0.7854), making it the most effective model for identifying customers interested in vehicle insurance, though at the expense of lower precision (0.2585). RandomForest showed a more balanced trade-off between precision (0.3064) and recall (0.5341) but performed lower overall. Logistic Regression, while the most interpretable model, exhibited high variability in performance across different folds, with a lower average precision (0.2372). The findings of this research highlight that XGBoost is ideal for maximizing recall in high-volume campaigns, while RandomForest may be better suited for applications requiring fewer false positives. These results offer valuable insights into model selection based on business objectives and resource allocation.

Clustering Analysis of Cadet Profiles Using Age, Recency, Frequency and Monetary Methods Using K-Means and K-Medoids Algorithms

2024-10-10T16:55:22+00:00

Banten Maritime Polytechnic is a new academic school established in 2019 so that the formulation of data management is still being sought to be suitable and optimal, there are many obstacles if the data is not managed properly, starting from the recruitment of prospective cadets in taking sailor competency training such as not optimal socialization. According to data from the 2021 Transportation Human Resource Development Agency, it explains that there are still few enthusiasts, especially at the Banten Maritime Polytechnic. The purpose of this study is to analyze the profile of cadets in taking sailor competency training using the age, recency, frequency and monetary methods in categorizing data and clustering with the k-means and k-medoids algorithms so that the data can be used for cadet services and related parties in the Banten Maritime Polytechnic database. This analysis can also be used for mapping in recruiting prospective cadets in taking sailor competency training so that they can see opportunities and optimize target markets. This research was conducted in 2023 based on the latest data on the 2022-2023 academic year cadet profile at the Banten Maritime Polytechnic. The results of this analysis data can be used for cadets who have not graduated and have graduated in finding work partners and channeling cadets to the shipping industry. So it is very important to manage and cluster cadet profile data in taking this sailor competency training. The use of the K-means and K-medoids algorithms helps in compiling data groupings that have large data. It works by looking at the number of small groups or groups whose numbers are represented by the variable K. To be able to group the existing data, the K-means algorithm runs iteratively from each existing data point to the K group that has been created. The results of the study are cadet profile grouping data that can be managed again for strategies and management formulations at the Banten Maritime Polytechnic, especially in increasing the recruitment of prospective cadets in taking sailor competency training.

Complete Kernel Fisher Discriminant (CKFD) and Color Difference Histogram for Palm Disease

2024-10-02T18:35:57+00:00

Palm oil plantations play a significant role in the economy of Indonesia, supporting 16.2 million people. However, plant diseases pose a major threat to the productivity and health of palm oil crops. Early detection of these diseases is essential to prevent yield losses and mitigate damage. This study proposes the application of the Complete Kernel Fisher Discriminant (CKFD) method combined with Color Difference Histogram to classify diseases affecting oil palm fronds and leaves. The CKFD method uses a non-linear kernel transformation to improve the performance of Fisher Linear Discriminant Analysis (FLDA), while the Color Difference Histogram enhances sensitivity to color variations in different lighting conditions. Experimental results demonstrate that the CKFD method achieves superior accuracy in disease detection compared to traditional Convolutional Neural Networks (CNN) and Support Vector Machines (SVM). The proposed approach showed an average accuracy of 94.5% for detecting diseases like Curvularia sp and Cochliobolus carbonus. The combination of CKFD with Color Difference Histogram significantly reduces the impact of lighting variations on the classification results, making it a robust solution for practical deployment in palm oil plantations. This research provides an effective tool for early disease detection and management in the palm oil industry.

Implementation of Deep Learning Model for Classification of Household Trash Image

2024-10-28T17:27:48+00:00

The problem of household waste management is a very important issue today, where the rapid urbanization, consumptive culture, and the tendency to dispose of waste without sorting it first from home, makes the volume of waste in landfills increase. Therefore, household waste management needs to be managed quickly and appropriately, so as not to have a major impact on environmental, hygiene, and health problems. Although some environmental communities and local governments have made efforts to manage waste through recycling systems, the long-term use of human labor is inefficient, expensive, and harmful to workers' health. Therefore, utilizing artificial intelligence technology is the best solution to classify waste types quickly and accurately. This research tries to test several pre-trained convolutional neural network (CNN) models to perform classification. The results of testing pre-trained CNN models, such as AlexNet, VGG16, VGG19, ResNet50, and ResNeXt50, found that the pre-trained model ResNext50 is better with 100% accuracy, while the training loss and validation loss are 0.0414 and 0.0304, respectively. Then the second best model is the pre-trained ResNet50 model with 100% accuracy with training loss and validation loss of 0.0832 and 0.1077, respectively.

E-Homestay Application Based on Decision Support System for Optimizing Tourism

2024-10-21T04:48:20+00:00

Pagar Alam City, a growing tourist destination, has seen a steady increase in visitors each year, driving greater demand for accommodations, especially homestays. Homestays are often favored by tourists due to their affordability compared to hotels. However, many tourists face challenges in selecting a suitable homestay that meets their preferences and needs. To address this issue, this study proposes the development of a web-based Decision Support System (DSS) integrated into the e-homestay platform. The system utilizes the Simple Additive Weighting (SAW) method, chosen for its capability to assess multiple alternatives based on specific weighted criteria, including price, facilities, location, distance, and guest ratings. This approach is designed to assist tourists in identifying the optimal homestay that aligns with their preferences and budget, thereby enhancing their overall travel experience in Pagar Alam City. Moreover, the platform has the potential to promote local economic growth by supporting digital marketing of homestays, while also contributing to sustainable tourism development and management.