Jusikom : Jurnal Sistem Komputer Musirawas
JUSIKOM is a place of information in the form of research results, literature studies, ideas, application of theory and critical analysis studies in the fields of research in the fields of Computer Systems, Computer Science, and Electronics. Focus and Scope: Embedded system, Intelligent control system, Software engineering, Computer network, Mobile computing, Artificial Intelligent, Internet of Things, and Information system.
Articles
212 Documents
<![CDATA[AI-OPTIMIZATION FOR LESSON PLANNING TO ADDRESS STUDENT PSYCHOLOGY GAPS IN ELEMENTARY SCHOOLS ]]>
<![CDATA[Nurfatih, Muhammad Sulkhan]]>;
<![CDATA[Zikry, Arief]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v9i2.2393
<![CDATA[This study aims to optimize the use of artificial intelligence technology, specifically GPT (Generative Pre-trained Transformer), in creating personalized lesson plans (RPP) tailored to the psychology and learning styles of students at SD Negeri 2 Muara Enim. The use of GPT is expected to assist teachers in understanding the individual psychological needs of students, addressing the limitations of counseling services at the school. The research methodology includes three main phases: analysis, system design, and implementation. During the analysis phase, demographic, academic, psychological, and contextual data of students were collected to identify key correlations influencing academic performance. This data was then used to train a machine learning model using the k-means clustering algorithm, aimed at grouping students based on their learning characteristics. The findings indicate that GPT was successfully implemented to generate lesson plans aligned with students' psychological profiles and learning styles. The developed web-based system enables teachers to effectively personalize the learning process. Moreover, the application simplifies the lesson plan creation process by offering teaching strategy recommendations relevant to each student group. In conclusion, the use of GPT proves beneficial in enhancing the effectiveness of classroom learning and provides a solution to teachers' challenges in understanding students' psychological needs.]]>
<![CDATA[Implementasi Metode Linear Discriminant Analysis (LDA) Pada Klasifikasi Buah Kentang ]]>
<![CDATA[Puspita, Desi]]>;
<![CDATA[Setiadi, Dedi]]>;
<![CDATA[Wulandari, Robeca]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v9i2.2403
<![CDATA[Kentang merupakan salah satu jenis tanaman hortikultura yang mempunyai nilai ekonomi tinggi. Sebagai sumber karbohidrat, kentang merupakan sumber pangan yang dapat menggantikan pangan karbohidrat lain yang berasal dari nasi, jagung, dan gandum. Oleh karena itu, pada penelitian ini akan dikembangkan suatu sistem pengolahan citra digital yang dapat mengklasifikasikan jenis kentang berdasarkan nilai hue dan saturation. Gambar harus disajikan secara numerik dengan nilai-nilai diskrit agar dapat diproses dengan mudah. Dalam penelitian ini dilakukan proses segmentasi, proses ekstraksi fitur, dan proses klasifikasi. Proses ekstraksi ciri memperoleh nilai hue dan saturation dari citra HSV untuk mempermudah proses klasifikasi. Selanjutnya dengan Linear Discriminant Analysis (LDA) akan diperoleh proyeksi yang optimal untuk dapat memasuki ruang dengan dimensi yang lebih kecil. Berdasarkan pengolahan data latih yang diperoleh melalui perhitungan sistem dan perhitungan manual diperoleh dari matriks konfusi, tingkat akurasi sebesar 72,5%, dan hasil pengujian diperoleh tingkat akurasi sebesar 84%. Data pengujian memperoleh tingkat akurasi sebesar 70% dan hasil pengujian memperoleh tingkat akurasi sebesar 82%.]]>
<![CDATA[PERANCANGAN APLIKASI INVENTORY BARANG BERBASIS WEB MENGGUNAKAN METODE AGILE DEVELOPMENT di WARUNG ZULAIKHA ]]>
<![CDATA[Risma, Ry]]>;
<![CDATA[Hermawan, Arief]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v9i2.2414
<![CDATA[The inventory management system is an application specifically designed to assist in managing items in the warehouse of Warung Zulaikha. The previous item data recording system used at Warung Zulaikha was still considered ineffective as it was done manually. The process of recording stock in the warehouse was only written in a ledger, which is prone to errors and difficult to manage. Therefore, the purpose of developing this system is to provide computerized management of item data. This system is expected to make it easier for the shop owner to input, search, and manage item data more efficiently. To address this issue, this study creates an online inventory management system specifically designed for Warung Zulaikha using the Agile Development method. The system is developed using PHP, HTML, CSS, and JavaScript programming languages, with MySQL as the database. The results of this study show that this system can facilitate the shop owner in recording items and provide real-time and accurate stock reports at Warung Zulaikha.]]>
<![CDATA[Evaluasi Kinerja Algoritma Naïve ]]>
<![CDATA[Sylvia, Sylvia]]>;
<![CDATA[Purnomo, Hendri]]>;
<![CDATA[Arifin, Oki]]>;
<![CDATA[Arpan, Atika]]>;
<![CDATA[Permata, Rizka]]>;
<![CDATA[Handoko, Dwi]]>;
<![CDATA[Fitriyah, Fitriyah]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v9i2.2447
<![CDATA[Social media sentiment analysis has become increasingly important with the rise of platforms like Twitter and Facebook as sources of public opinion. This study evaluates the performance of three machine learning algorithms—Naïve Bayes, k-Nearest Neighbors (KNN), and Support Vector Machines (SVM)—in classifying sentiment from social media data. Using a dataset in Indonesian, we apply cross-validation techniques to measure accuracy, precision, recall, F1-score, and computation time for each algorithm. The results show that SVM achieves the highest accuracy and F1-score, while Naïve Bayes offers better computational speed. KNN demonstrates the lowest performance in terms of accuracy and efficiency. These findings provide guidance for practitioners and researchers in selecting the appropriate algorithm for sentiment analysis based on their specific needs.]]>
<![CDATA[Smart light berbasis IoT dengan menggunakan Bylnk ]]>
<![CDATA[Dwitama, Surya Hafidz]]>;
<![CDATA[Elsi, Zulhipni Reno]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v9i2.2461
<![CDATA[Abstract The Internet of Things (IoT) has become a primary focus in the development of modern technology, including in the field of home automation. This research aims to design and implement a smart lighting control system based on IoT using the Blynk application. This system enables users to turn lights on and off remotely via a smartphone, enhancing comfort and energy efficiency.In this study, the NodeMCU ESP8266 is utilized as the microcontroller module connected to a Wi-Fi network, while a relay functions to control the electrical current to the lights. The Blynk application is installed on users' smartphones as an interface to control the system. Testing is conducted to evaluate the system's functionality, including remote control, signal stability, and energy consumption monitoring.The results show that the system operates effectively, achieving a control success rate of 96.67%. Although there are challenges related to Wi-Fi signal stability and data security, the system proves to be effective in enhancing energy usage efficiency and providing ease of control for users. This research contributes significantly to the development of smart home technology and opens opportunities for further integration with other IoT devices.]]>
<![CDATA[IMPLEMENTASI METODE WATERFALL PADA PERANCANGAN APLIKASI INVENTORY BARANG ]]>
<![CDATA[Sari, Yuntari Purba]]>;
<![CDATA[Wijaya, Khana]]>;
<![CDATA[Ariansyah, Ariansyah]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 1 (2025): Jusikom : Jurnal Sistem Komputer Musirawas JUNI ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v10i1.2428
<![CDATA[Patrakom have a representative Base-base almost throughout Indonesia, where each Base has inventory. As Base Patrakom Prabumulih that they keep records of goods using a simple system that is recorded into a book and then transferred to MS EXCEL. Therefore, the amount of time required for the process of data collection items are also frequent errors and delays in making the report. Based on these problems, the required application in the processing of inventory items and reports are computerized so that the recording of the flow of goods in and out can be a rapid, precise and accurate. In this study, the method of collecting data through observation and study of literature. Applications compiled with the development stage procedure that includes needs analysis, data flow diagrams, implementation using PHP as the programming language and MySQL as the database. From research conducted, produced a system software design a web-based inventory with the ability to save data inventory of goods, goods mutation data and reports. The results of the research and manufacture of this program is expected to accelerate in data processing and delivery of reports to the Project Manager.]]>
<![CDATA[PEMANFAATAN KECERDASAN BUATAN DALAM PERSONALISASI PEMBELAJARAN MAHASISWA ]]>
<![CDATA[Falah, Miftahul]]>;
<![CDATA[Florensia, Yesinta]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 1 (2025): Jusikom : Jurnal Sistem Komputer Musirawas JUNI ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v10i1.2636
<![CDATA[The development of Artificial Intelligence technology has presented new opportunities in improving the quality of education, especially in creating adaptive and personalized learning systems. In higher education, the main challenge in the learning process is the differences in student characteristics such as learning styles, initial level of understanding, and learning motivation. This inequality often makes it difficult for lecturers to deliver material evenly and effectively. This study aims to examine the extent to which the use of AI technology can improve the personalization of student learning and its impact on learning outcomes. The research method used was a quasi-experiment with a pre-test and post-test approach to 62 students involved in AI-based learning systems. The instruments used included learning outcome tests and student perception questionnaires. The results of the study showed a significant increase in learning outcomes after the implementation of AI, with an average post-test score higher than the pre-test. These findings indicate that the application of AI in learning not only improves academic outcomes but also creates a more personalized and adaptive learning experience. The conclusion of this study emphasizes the importance of integrating AI into modern learning systems in order to address the challenges of differentiating student characteristics more effectively.]]>
<![CDATA[SISTEM PAKAR DIAGNOSA STUNTING BALITA MENGGUNAKAN NAIVE BAYES ]]>
<![CDATA[Andayani, Mastra]]>;
<![CDATA[Putrawansyah, Ferry]]>;
<![CDATA[Syahri, Riduan]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 1 (2025): Jusikom : Jurnal Sistem Komputer Musirawas JUNI ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v10i1.2649
<![CDATA[This study aims to develop an expert system to diagnose stunting in toddlers using the naive bayes method. Stunting is a serious health problem that is often ignored due to lack of public awareness and limited access to health services. This expert system is designed to diagnose stunting based on symptoms inputted by the user without having to consult directly with medical personnel. The naive bayes method is used to handle uncertainty in the data and provide a level of certainty in the diagnosis. Research data were obtained through observation, interviews with medical personnel at the Health Office, and literature studies. This system was developed using the PHP programming language and MySQL database, and tested using the blackbox testing technique. This system is expected to increase awareness and early detection of stunting, while supporting the Health Office in its efforts to reduce the prevalence of stunting.]]>
<![CDATA[IMPLEMENTASI CRM WEB MOBILE UNTUK EFISIENSI PERENCANAAN PEMBELIAN DAN PENYEDIAAN JASA PT. SEMESTA JARING MEDIA ]]>
<![CDATA[Setiawan, Agus]]>;
<![CDATA[Oktapriandi, Sony]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 1 (2025): Jusikom : Jurnal Sistem Komputer Musirawas JUNI ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v10i1.2654
<![CDATA[This article discusses the implementation of a mobile web-based Customer Relationship Management (CRM) system to enhance the efficiency of purchasing planning and service provision at PT. Semesta Jaring Media. In an increasingly competitive business environment, CRM serves as a strategic tool for analyzing customer interactions and managing relevant data to improve service quality and customer satisfaction [1][2]. This research employs a user-centered design approach for system development, resulting in a responsive and user-friendly design [3][4]. Data from the implementation indicates a significant increase in operational efficiency, including reduced information processing time and expedited decision-making [5]. Additionally, the integration of this CRM system contributes to improved customer loyalty through better relationship management [6][7]. The findings from this case study are expected to provide a positive contribution to the development of information technology in the service sector and strengthen the competitive position of PT. Semesta Jaring Media in the market [8][9].]]>
<![CDATA[STUDI PERFORMA DAN EXPLAINABILITY JARINGAN SYARAF TIRUAN UNTUK PERAMALAN CUACA MENGGUNAKAN METODE LIME ]]>
<![CDATA[,, Rachmansyah]]>;
<![CDATA[Fajri, Ricky Maulana]]>;
<![CDATA[Tasmi, Tasmi]]>;
<![CDATA[Hamim, Sumi Amariena]]>
<![CDATA[ Jusikom : Jurnal Sistem Komputer Musirawas Vol 10 No 1 (2025): Jusikom : Jurnal Sistem Komputer Musirawas JUNI ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS BINA INSAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32767/jusikom.v10i1.2655
<![CDATA[Accurate weather prediction is crucial to support various sectors such as agriculture, transportation, and disaster mitigation. Artificial Neural Networks have been proven to improve the accuracy of weather forecasts through their ability to capture complex nonlinear patterns in atmospheric data. However, the complexity of these artificial neural networks architectures often results in decisions that are non-transparent and difficult for end users to understand. To address this issue, this study examines the effectiveness of the Local Interpretable Model-agnostic Explanation (LIME) method in providing local explanations for weather predictions generated by the artificial neural networks. The study uses historical meteorological data and evaluates the interpretability of prediction results for several key weather variables. Experimental results show that LIME is capable of identifying the most influential features affecting the model's decisions, as well as providing human-understandable insights into the prediction logic. These findings reinforce the importance of integrating explainability methods into artificial neural network-based weather prediction systems to enhance user trust and support more informed decision-making.]]>
