JSAI (Journal Scientific and Applied Informatics)

Analysis of AI-Based Software Development (Gemini) Using ACM Code of Ethics Implementation

Rexcy Elsan — 2025-06-01

This research aims to analyze the application of the ACM Code of Ethics in the development of AI Gemini software by Google DeepMind. With the development of artificial intelligence (AI) technology, developers need to pay attention to ethical aspects in every stage of system development. This research uses a qualitative approach with a data triangulation method, which includes document analysis, interviews with AI experts, and a literature study. The results show that although Gemini AI has complied with some key ethical principles in the ACM Code of Ethics, such as data security and privacy (90%) and human well-being (85%), there are still challenges related to transparency (60%) and bias mitigation (70%). Lack of transparency in algorithms and training data as well as potential bias in results generated by AI are the main issues that need to be improved. Based on the results, overall the Gemini AI has shown fairly good ethical compliance with an average of 76.67% but still requires improvement in the aspects of transparency, bias mitigation, and usage regulation.

Optimizing Network Management with Bandwidth Limitation and Blocking Certain Access at PT Laxo Global Access by Applying the NDLC Method

Adiffanani Ramdansyah — 2025-06-01

This research focuses on optimizing network management at PT Laxo Global Akses by implementing bandwidth restrictions and restricting access to non-work related websites and applications. Internet usage in the company was previously unrestricted, resulting in decreased productivity and unstable network performance, especially during peak hours. To address these issues, this research applies the Network Development Life Cycle (NDLC) methodology and utilizes MikroTik devices for configuration. Key features such as Queue Tree for bandwidth distribution, Firewall Filtering for access control, and Hotspot User Management for user authentication were implemented. The redesigned network topology allows for more structured traffic management and real-time monitoring. The test results show that all test scenarios have succeeded as expected, so it can be concluded that the network configuration and policies implemented in the NDLC process were 100% successful at the implementation and testing stages.

Analysis of Maturity Alignment of Business Strategy with Information Technology at SAMSAT Bengkulu City Using Strategic Alignment Maturity Model (SAMM)

Kurnia Anggriani — 2025-06-01

Motor vehicle tax payments represent a substantial portion of regional income. However, recurrent delays in motorbike tax payments, notably in the Kandang Limun sub-district of Bengkulu City, pose a significant threat to regional development. This research aims to address these delays by predicting and implementing effective strategies. Using the RapidMiner application and the Artificial Neural Network (ANN) method, a delay rate of 36.14% was predicted. The study incorporates interviews to propose several strategies, including enhancing websites, improving offline and online services, implementing Drivethru services, and using SMS Blast notifications to combat delays. To evaluate the feasibility of these strategies, the research employs the Strategy Alignment Maturity Model (SAMM). The assessment at BPKD reveals a maturity level of 4, signifying an ability to improve and manage processes effectively.The maturity assessment suggests that the proposed strategies for overcoming delays are well-aligned with BPKD's capabilities. They have demonstrated a robust alignment between IT and business strategies, leveraging IT to enhance performance, and conducting thorough business and IT evaluations.In addition to the maturity assessment, the research offers suggestions and evaluation strategies. These encompass the adoption of biometrics for authentication, implementation of chatbots, Samsat self-service kiosks, real-time vehicle monitoring, and the introduction of automatic tax programs.

Implementation of NLP Election News Classification Using LSTM Algorithm

Harry Vadilan Sianturi — 2025-06-03

This study examined the application of a Long Short-Term Memory (LSTM)-based text classification method to categorize election news according to presidential and vice-presidential candidate entities. The core problem addressed was the lack of an automated classification system capable of identifying political affiliations directly within the vast volume of digital news content. In this research, news data were collected from open-access sources and automatically labeled based on the occurrence of candidate-related keywords. A supervised learning approach was implemented using the LSTM architecture to capture sequential patterns within the news text. The evaluation results demonstrated that the model achieved a validation accuracy of 95.44% and a macro-averaged F1-score of 0.95, indicating strong classification performance across all candidate categories. Furthermore, predictions on test data revealed the model’s consistency and stability in recognizing political entities. This study confirmed the effectiveness of the LSTM-based approach for entity-based election news classification and highlighted its potential for integration into automated media analytics and political discourse monitoring systems.

Implementation of Agile Scrum Method and Return On Investment (ROI) Analysis on Library Information System

Muhammad Hafiz Ar Rahman — 2025-06-03

The library is one of the important institutions that provide and manage information to support learning, teaching, and research activities. In its development, the need for an integrated and efficient library information system is increasing, along with the demands of digitizing services and managing data quickly and accurately. This research aims to implement the Agile Scrum method in the development of Library Information Systems and conduct a return-on-investment (ROI) analysis to measure the effectiveness of the investment from a business and economic perspective. Based on the research problem raised and the results of the research that has been conducted, it shows that the Scrum method is proven to be effective in increasing flexibility and responsiveness to user needs. Key features are completed on time, and user feedback can be responded to in the next sprint. Active collaboration minimizes the risk of errors and maintains system quality. The first-year ROI is positive although small (4.65%), but the system is sustainable, so the ROI will increase significantly in years 2 and 3 because costs remain low while benefits continue to grow.

Analysis of Archer.exe Malware to Identify Potential Threats on Operating Systems Using the Hybrid Analysis Method

Juan Haniful Kahfi — 2025-06-03

Cybersecurity has become a primary concern in the digital era, particularly regarding malware attacks targeting the Windows operating system. This study aims to analyze a Remote Access Trojan (RAT)-type malware named archer.exe, obtained from the Any.run platform. The method used is hybrid analysis, a combination of static analysis and dynamic analysis, to provide a comprehensive understanding of the malware's structure and behavior. Static analysis results show that archer.exe is a Portable Executable (PE) file with a size of 829.35 KB and employs packing techniques to conceal its payload. Meanwhile, dynamic analysis reveals that the malware modifies system registry keys, spawns child processes such as rundll32.exe and cmd.exe, and establishes a network connection to a Command and Control (C2) server at IP address 192.169.69.26 via the domain dominoduck2101.duckdns.org. These findings indicate that archer.exe poses a high risk of remote system access, data theft, and malicious background activity without user awareness. This study demonstrates that the hybrid analysis method is effective in identifying hidden threats and malicious behavior of RAT-type malware on Windows 10 systems.

Analysis of Canva and Gamma User Satisfaction Among Students Using the System Usability Scale (SUS) Method

Helen Anggraini — 2025-06-03

Canva and Gamma are web-based graphic design platforms widely used by students to create brochure, presentations, and social media content in a simple and efficient way. The purpose of this study is to evaluate user satisfaction. with both applications using the System Usability Scale (SUS) method. The study involved 100 students from Universitas Muhammadiyah Bengkulu who had used both platforms. The results indicate that Canva achieved a SUS score of 80.2, categorized as Excellent, while Gamma received an average score of 72.4, categorized as OK. These findings suggest that although both applications demonstrate good usability, Canva is perceived to be superior in terms of ease of use, feature integration, and learning curve. The outcomes of this study can serve as a reference for’s developers with educational institutions on selecting or developing design tools that are more responsive to user needs.

Designing a Web-based Teacher Attendance System Application Using Geo Fencing at XYZ Elementary School

Faizul Anwar Ramdhani — 2025-06-08

The web-based teacher attendance system application with Geo-Fencing technology integration is designed to improve the accuracy and efficiency of the teacher attendance recording process in the school environment. The use of Geo-Fencing allows attendance to only be done when the user is in a predetermined area, thus minimizing the potential for fraud and data manipulation. This research aims to develop a web-based attendance application and evaluate its usability level using the System Usability Scale (SUS) method. The evaluation was conducted on 20 respondents consisting of teachers and school administrators. Based on the test results, an average SUS score of 75 was obtained, which is included in the Good usability category. Thus, this application is considered quite easy to use, effective, and acceptable to users. The results of this study indicate that the web-based teacher attendance system application with Geo-Fencing has the potential to be widely implemented in the school environment, with some further development recommendations to improve user experience.

Analysis of Canva and Slidego User Satisfaction Among Students Using the Customer Satisfaction Index (CSI) Method

melzan sabri sabri — 2025-06-08

Canva and slidego are graphic design platforms that are widely used by students. This study uses the Customer Satisfaction Index (CSI) method to measure and understand how satisfied students are with the Canva and Slidego presentation design platforms. This is based on the fact that these platforms are the main choice for students to create attractive professional presentations. This study uses a quantitative, descriptive method by collecting data from students who use both applications through an online questionnaire. To measure overall user satisfaction, but there are also important attributes that affect user satisfaction. such as ease of use, completeness of features. The results of the calculations carried out using the (CSI) method show a value of the percentage of user satisfaction of 85.4115773 Based on the CSI scale, the results are categorized as "very satisfied" with the Canva application. While the Slidego application gets a value of 80.920309% categorized as "Satisfied", so in the results of this CSI calculation, the Canva application has a value greater than the Slidego application value, so the conclusion is that the Canva application is more and more often used by users.

Classification of Matoa Fruit Ripeness Levels Using PCA and KNN Methods Based on RGB Color

Rendika Efando — 2025-06-08

Matoa fruit or in scientific language Pometia Pinnata is a fruit that is quite popular and is spread in several regions. Matoa fruit has several benefits such as for health, processed drinks, and for consumption. However, up to now, matoa fruit farmers are still sorting the quality of ripe matoa fruit using methods that are still manual, which can cause errors and mistakes in sorting the quality of matoa fruit. Based on this problem, this research developed a system that is capable of classifying the maturity level of matoa fruit using RGB feature extraction and using the Principal Component Analysis (PCA) and K-Nearest Neighbor (KNN) methods. This research uses a dataset of 67 data, namely 42 training data and 25 test data consisting of 3 classes, namely raw, mature, and fully cooked. Data classification that applies KNN with the nearest neighbor value, namely K=3, gets an accuracy result of 92%, with 23 image being classified correctly and 2 image being classified incorrectly.

E-Commerce Web Design at XYZ Store with Recommendation System Features

Hafid Roihan — 2025-06-08

This research aims to design and implement a web-based e-commerce system for XYZ Store by providing a fresh vegetable product recommendation feature, using the Apriori algorithm and the Rapid Application Development (RAD) approach. The design process begins with collecting data through interviews to find out the needs of the system. Transaction data for one month was analyzed using the Apriori algorithm to identify patterns of association between products that are often purchased together. The results of this analysis were used as the basis for creating recommendation features. The RAD approach was used because it allows the system to be developed quickly and gradually by involving users in each phase of development. This research analyzes the usability level of the platform using the System Usability Scale (SUS) method. Testing was conducted on 15 participants who had tried the platform prototype in the designed usage scenario. The measurement results indicate that the average SUS score is 78.2, placing it in the “Good” category. The recommendation system feature received a positive response, with the majority of users finding it helpful in finding relevant products. These findings suggest that integrating the recommendation system not only enriches the platform's features but also contributes to improving the overall user experience.

Evaluation of DAPODIK Information Technology Usage Using the DeLone and McLean Model

Achmad Rofiqi Arwin — 2025-06-13

This study aims to evaluate the Basic Education Data System (DAPODIK) based on the DeLone & McLean model using a descriptive statistical analysis approach. The evaluation results show that the Information Quality dimension received the highest score of 86.44%, reflecting users' positive perceptions of the system's data accuracy, completeness, and relevance. The Service Quality dimension scored 84.40%, indicating good responsiveness and technical support, although there is still room for improvement in communication and service continuity. The Use dimension reached 85.33%, suggesting that the system is extensively utilized in educational operational activities. User Satisfaction obtained a score of 82.83%, the lowest among the five dimensions, yet it still reflects a high level of satisfaction, with potential for improvement in technical and user experience aspects. Meanwhile, the Net Benefits dimension scored 85.33%, signifying that the DAPODIK system provides positive impacts on work efficiency, data accuracy, and administrative coordination. These findings indicate that overall, the DAPODIK system performs well and offers tangible benefits, but continuous improvements are needed to optimize user experience and system effectiveness.

Design and Build of an NFT-based Digital Certificate Management Application on the Solana Network

Matthew Imanuel Sumita — 2025-06-13

This research aims to design and build a Non-Fungible Token (NFT) based digital certificate management application on the Solana blockchain network. This application enables users to create, verify, and transfer certificates in the form of secure and decentralized non-fungible tokens (NFTs). Testing was conducted in two main aspects: functional and performance. The functional testing results showed a 100% success rate, indicating that all the application's main features performed as expected. In terms of performance, NFT creation took an average of 29 seconds for 0.00008 SOL, NFT verification took 1.5 seconds at no cost, and NFT transfer took 19 seconds at the same cost as creation. These results show that the application is able to perform its functions efficiently and economically on top of the Solana network. This research contributes to the utilization of blockchain technology for transparent and secure digital document management.

Analysis of IT Governance Implementation using COBIT 5.0 and COBIT 2019

Denny Ganjar Purnama — 2025-06-16

The rapid development of information technology (IT) has affected many sectors, including higher education. Universitas Pembangunan Jaya (UPJ) implemented two versions of COBIT, COBIT 5.0 and COBIT 2019, to improve their IT management. This research aims to compare the effectiveness of the two versions in supporting IT management at UPJ. The research method used is a qualitative approach with a case study involving in-depth interviews, direct observation, and documentation analysis. The data obtained was analyzed using thematic and comparative approaches. The results showed that COBIT 2019 is more flexible, allows customization to the specific conditions of the university, and improves collaboration between departments. Meanwhile, COBIT 5.0 tends to be more rigid and less adaptive to rapid changes. This research concludes that COBIT 2019 is more effective in IT management at UPJ, as it provides greater flexibility in the management of IT resources and response to environmental changes.

Development of a Web-Based Point of Sale (POS) Information System Using the Agile Method

Agnes Monika Halawa — 2025-06-16

Perkembangan teknologi informasi mendorong pelaku usaha untuk mengadopsi sistem digital dalam kegiatan operasional, salah satunya dalam proses penjualan. Penelitian ini membahas perancangan dan pengembangan Sistem Informasi Penjualan (POS) berbasis website menggunakan metode Agile serta pengujian performa sistem melalui performance testing. Metode Agile dipilih karena sifatnya yang iteratif dan fleksibel, memungkinkan pengembangan sistem secara bertahap dan adaptif terhadap perubahan kebutuhan pengguna. Pengujian performa dilakukan dengan menggunakan Apache JMeter untuk mensimulasikan berbagai skenario pengguna, seperti transaksi serentak, login massal, dan beban sistem jangka panjang. Hasil pengujian menunjukkan bahwa sistem mampu menangani hingga 200 pengguna aktif secara bersamaan dengan waktu respon rata-rata di bawah 3 detik dan tingkat error yang rendah. Namun, pada skenario spike 300 pengguna, terjadi peningkatan waktu respon dan sedikit error, menunjukkan perlunya optimalisasi lebih lanjut. Secara keseluruhan, sistem dinilai layak digunakan dan cukup stabil dalam lingkungan operasional skala kecil hingga menengah.

Implementation of Myers-Briggs Type Indicator Approach in Android-Based Counseling Guidance Information System for High School

Andi Mulawati Mas Pratama — 2025-06-16

Guidance and counseling services at SMA Negeri 3 Gorontalo Utara play a crucial role in helping students recognize their potential, interests, and the problems they face. This study aims to develop an Android-based guidance and counseling information system by integrating the Myers-Briggs Type Indicator (MBTI) approach as a tool for identifying students' personality types. The system is designed to present the MBTI questionnaire, automatically analyze the results, and provide counseling recommendations that correspond to each student's personality type. Testing was conducted on 60 eleventh-grade students at SMA Negeri 3 Gorontalo Utara. The results show that the system is capable of effectively classifying personality types and delivering relevant recommendations. The most commonly found personality types were INFP, ESTJ, and ISFJ. Both students and guidance counselors responded positively to the system's usability, ease of use, and clarity. Although limitations remain in terms of advanced personalization and data integration, the approach has proven to enhance the quality of counseling services in a more adaptive and technology-based manner. This study recommends further feature development and system integration into the school's academic management

Designing a Website-Based Dentist Registration Service Application Using Waterfall and Regression Methods

Siti widiyati malihah — 2025-06-16

The development of information technology has encouraged digital transformation in the health care sector, one of which is through a website-based dentist registration service application. J&J Dental Clinic is a clinic located in Jakarta and was established to support the health aspects and dental health services for the general public. This research aims to design and test the system using the Waterfall development method and Regression Testing. The Waterfall method was chosen because it is able to provide a structured and systematic development flow, while Regression Testing is used to ensure the stability of the system after adding or modifying features. Testing was conducted by 200 users on five main features of the system, including new patient registration, login/logout, reservations, financial reports, and admin data management. The test results showed that the average system success rate was above 97%, with the admin data management feature achieving 100% success and the financial report feature having the lowest success rate of 95%. These results prove that the application functions well and is stable, but still has room for improvement on some features. These findings can be the basis for further development of a reliable and user-friendly digital-based healthcare system.

Analysis and Implementation of Mikrotik-Based Access Points Using Hubs with the PPDIOO Method

rahmat rahmat azis — 2025-06-18

This research discusses the analysis and implementation of Mikrotik-based access points using hubs as a connection medium, with the PPDIOO (Prepare, Plan, Design, Implement, Operate, Optimize) methodology approach. PPDIOO was chosen because it is able to provide a systematic, efficient work structure, and can be evaluated in stages using success indicators (KPIs). Tests were conducted at the Operate and Optimize stages with a focus on throughput (Tx/Rx) metrics, average data transmission speed, and packet loss. The test results show a current Tx throughput value of 13.2 Gbps, a 10-second average of 12.9 Gbps, and a total average of 13.7 Gbps, with no packet loss (0 packet loss). Converting these results into percentages shows success above 90% across all indicators, with connection reliability reaching 100%. These findings prove that the PPDIOO method is effective in designing and managing a stable, efficient, and high-performance access point network.

Optimizing Digital Promotion Decision Making with Data-Driven Marketing

Vina Avianingsih — 2025-06-18

In today’s digital marketing landscape, organizations must optimize promotional strategies using data-driven insights. This study proposes an integrated framework combining machine learning (ML) and multi-criteria decision-making (MCDM. Using 1,200 campaigns across platforms, we applied and evaluated regression models—Linear Regression, Random Forest, and Gradient Boosting—to predict ROI from key attributes. Gradient Boosting performed best (R² = 0.82), identifying engagement score, conversion rate, and click-through rate (CTR) as top factors. Used the Analytic Hierarchy Process (AHP) to prioritize campaigns based on predicted ROI, engagement, CTR, and cost-per-click (CPC). This combined approach supports marketers in balancing data-driven accuracy with managerial judgment. A/B testing showed the model-informed group achieved a 17.6% higher ROI and lower CPCs than baseline strategies. This research advances marketing analytics by merging advanced ML with structured decision-making, providing a replicable method for enhancing promotional effectiveness. The findings highlight the significance of behavioral metrics in predicting success and the value of integrating algorithmic precision with human evaluation. This blended approach empowers marketers to move beyond single-metric optimization, enabling more informed and impactful digital marketing strategies in competitive environments.

Comparative Analysis of Desktop and Web-Based Workshop Systems Using the User Acceptance Testing Method

Muhammad Surya Affandi — 2025-06-19

This study aims to compare desktop-based and web-based workshop information systems at PT. Motoreko Mobilindo using the User Acceptance Testing (UAT) method. The evaluation was conducted based on five key indicators: ease of use, access speed, reliability, security, and user satisfaction. Data were collected through questionnaires filled out by active users who had experience with both systems. The results show that the desktop system excels in terms of access speed (96%), reliability (97%), and security (99%). Meanwhile, the web system outperforms in ease of use (97%) and user satisfaction (96%). These findings indicate that although the desktop system has more stable technical performance, the web system is more widely accepted by users due to its convenience and flexibility. This study recommends a hybrid approach as a strategic solution, by maintaining the technical strengths of the desktop system while integrating the accessibility benefits of the web system. Thus, the company can develop a balanced, adaptive information system that aligns with the needs of digital transformation.

Performance Comparison of Random Tree, K-NN, and A-NN Algorithms for DDoS Attack Detection on Software Defined Network (SDN)

Akbar Pandu Segara — 2025-06-19

Software-Defined Networks (SDNs) with a centralized architecture are vulnerable to Distributed Denial of Service (DDoS) attacks, which can cause widespread network service failures. This study aims to compare the performance of three Machine Learning algorithms—K-Nearest Neighbor (K-NN), Artificial Neural Network (ANN), and Random Tree—in detecting DDoS attacks in an SDN environment. The DDoS-SDN dataset, consisting of 104,345 rows and 23 columns, was used with a data split of 70% for training and 30% for testing. Evaluation was conducted using accuracy, precision, recall, F1-score, and AUC-ROC metrics. The results showed that ANN achieved the best performance with an accuracy of 96.85%, precision of 94.35%, recall of 97.79%, F1-score of 96.04%, and AUC of 0.994, followed by K-NN with an accuracy of 88.89% and Random Tree with the lowest accuracy of 86.49%. The superiority of ANN is attributed to its ability to capture complex non-linear patterns, perform automatic feature extraction, and adapt to the heterogeneity of data from the 22 features used. These findings indicate that ANN is the optimal choice for implementing a real-time DDoS attack detection system in an SDN environment, providing a strong foundation for the development of intelligent and adaptive Machine Learning-based network security systems

Integration of Multi-criteria Decision Making Methods for Tobacco Land Assessment: A Case Study Using SMART, TOPSIS, and AHP

Dony Bahtera Firmawan — 2025-06-21

The results of decision making play an important role in achieving a goal in solving certain problems. Decision making process requires data or supporting evidence that can be used as a guide for the selection of solutions based on available alternatives, to produce choices that can increase productivity. Multi Criteria Decision Making (MCDM) method for the analysis of research data namely SMART, TOPSIS, and AHP. The three methods are tested, because each MCDM method has a different way of working or algorithm, so it is necessary to experiment with certain cases. This study aims to determine the performance of the SMART, TOPSIS, and AHP methods with a case study of selecting of tobacco land recommendations. The application of three MCDM methods for alternative analysts of prospective tobacco land based on testing to determine the accuracy of comparing the results/output of the system with expert recommendation solutions using a sample of 10 tobacco land that produce priority/ranking for tobacco land recommendations, shows that the performance of the three methods produces priority selection results different, with an accuracy of SMART 80

Application of Optical Character Recognition (OCR) in Retrieving Book Title Text for Library Archives Digitization

Julian Mulyadi — 2025-06-21

The advancement of information technology requires libraries to transform into digital services. One important step in this process is the digitization of book titles, which has previously been carried out manually and is prone to errors. This study aims to develop a system for extracting book title text from cover images using the Optical Character Recognition (OCR) method based on MATLAB 2017b. The OCR method used in this research applies a template matching and feature extraction approach, where characters are recognized by matching them against built-in character templates in the system after going through an image preprocessing phase. The preprocessing stages include Region of Interest (ROI) selection, grayscale conversion, contrast enhancement, noise removal, and image resizing. After preprocessing, the text is extracted using OCR and stored in digital format. The system was tested using 60 book cover images from the Regional Library of Bengkulu Province, featuring various font types, colors, and lighting conditions. The test results, evaluated using a confusion matrix, show good system performance with an accuracy of 81.67%, precision of 83.05%, and recall of 98.00%. The high recall value indicates that the system is capable of accurately recognizing most of the book title text. Therefore, this system can serve as an initial solution to support the automatic, fast, and efficient digitization of library archives.

NPK (Nitrogen, Phosporus and Potassium) Level Detection Tool in Palm Leaf Organic Fertilizer based on Internet of Things (IoT) using Soil NPK SensorIntegration of Multi-criteria Decision Making Methods for Tobacco Land Assessment: A Case Study Using SMART, TOPSIS, and AHP

Hesmi_Aria Yanti — 2025-06-23

Significant decline in palm oil production; this is due to the termination of fertilizer subsidies and price increases, especially NPK fertilizers. To test the nitrogen (N), phosphorus (P), and potassium (K) content and water content in organic fertilizers made from oil palm leaves, cow dung, water, and other materials. Laboratory testing using chemical analysis and a composting process for 3 months is required. The results of the analysis of N content were 1.63%, P₂O₅ was 0.16%, K₂O was 0.12%, and water content was 12.71%. These results are in accordance with the quality standards of organic fertilizers. The implementation of the NPK content detection tool in oil palm leaves uses these results as a reference. Then the implementation is carried out directly at the location by taking samples of oil palm leaves, cow dung, and water, and then testing is carried out using an integrated NPK detection tool in real time. Where the test results are N = 97 mg/kg, P = 28 mg/kg, and K = 113 mg/kg, these values have not met the minimum threshold for organic fertilizer quality, so it is necessary to add other materials and incubate composting for 3 months or use EM-4 as a liquid that can help accelerate composting. The tool has an accuracy of ±2% and a resolution of up to 1 mg/kg, so the tool is suitable for use as a tool for detecting NPK levels.

Application of Artificial Intelligence for Course Information Chatbot SMK Informatika Komputer Ampana Kota

Anisa Yulandari — 2025-06-24

Ampana City Computer Informatics Vocational School students have problems with enthusiasm for learning at school due to the lack of motivation provided. As a result, many students are lazy to listen or follow class subjects. From the description of the existing problem, the researcher tried to create information media to provide motivation to students which is related to the benefits and goals of learning, using Artificial Intelligence which is formed in a subject information chatbot. The Naïve Bayes Classifier method is used to build chatbots. Assuming independence between features, Naive Bayes is able to work well on text-based classification such as processing questions and answers in chatbots. So you can answer students' questions accurately. The research results show that the use of chatbots contributes significantly to increasing learning motivation, as shown by the Paired Sample T-test of 0.05, indicating that there is a significant increase in student interest in learning. In addition, system testing shows an accuracy rate of 100% in providing responses to student questions. Artificial intelligence-based chatbots can be an effective innovation in supporting learning and increasing students' interest in learning in technology-based educational institutions.

Wireless Local Area Network Analysis Using Quality Of Service and Reliability Maintainability Availability (RMA) Parameters

Ester Agung Natanael — 2025-06-30

Wireless Local Area Network (WLAN) has become an important infrastructure in supporting connectivity in various sectors, but its quality and reliability often experience problems. This study aims to analyze the performance of WLAN networks using two main approaches, namely Quality of Service (QoS) parameters which include throughput, jitter, and packet loss, and the Reliability, Maintainability, and Availability (RMA) method. Tests were conducted before and after network improvements using analysis tools such as Wireshark and iPerf. The results showed that after the repair, throughput increased significantly from an unstable value to an average of 5-5.5 Mbps, jitter decreased consistently, and packet loss reduced from a maximum of 8% to below 2%. In addition, the network availability value increased along with a decrease in repair time (MTTR) and an increase in time between failures (MTBF). This study concludes that the combination of QoS and RMA evaluation provides a comprehensive overview of network performance and reliability, and is effective in supporting decision making for continuous improvement of network systems.

Application of Zachman Framework in the Design of Drug Management Information System Architecture of Purbalingga Health Office

Annisa Dwi Risqi — 2025-06-30

The application of the right information system architecture framework is very important in ensuring efficiency and consistency in data management, especially in drug management information systems in the government sector. This study aims to evaluate the maturity level of the application of the Zachman Framework in the design of the Drug Management Information System at the Purbalingga Health Office using the Capability Maturity Model (CMM) approach. The evaluation was conducted on six main perspectives of Zachman: Planner, Owner, Designer, Builder, Subcontractor, and Functioning System. The measurement results showed the following maturity percentage values: Planner (60%), Owner (40%), Designer (60%), Builder (40%), Subcontractor (20%), and Functioning System (60%), with an average maturity level of 46.67% or equivalent to Level 2 (Repeatable). These results indicate that the design process already has a basic pattern but has not been thoroughly documented or standardized. The main recommendation in this research is to improve technical documentation, HR training, and integration between architecture perspectives to achieve a higher level of maturity.