JuSiTik : Jurnal Sistem dan Teknologi Informasi Komunikasi

Manajemen Risiko TI Pada BID TIK Polda Sumsel Menggunakan Framework Cobit 5

2025-07-01T01:42:44+00:00

Information technology plays an important role in supporting operational effectiveness, including in government institutions such as the Indonesian National Police. BIDTIK POLDA SUMSEL is a work unit responsible for managing and developing information and communication technology systems, supported by the Renmin Subdivision, Tekkom Subdivision, and Tekinfo Subdivision. In its implementation, BidTIK faces various information technology risks, such as human error, connection disruption, device damage, and system security incidents that have not been formally documented. To manage these risks optimally, a structured approach such as COBIT 5 is needed, especially the APO12 (Manage Risk) domain which provides systematic guidance in identifying, assessing, and mitigating information technology risks in a documented and sustainable manner. The assessment was carried out on six APO12 subprocesses through questionnaires and quantitative analysis of the current (As Is) and expected (To Be) conditions. From the results of a structured approach with COBIT 5 in the APO12 domain, the average As Is value is 2.07 (Level 2), indicating that the process is running but not yet consistently documented. While the To Be value is 3.43 (Level 3), reflecting a documented and structured process target. The difference between actual and target conditions indicates the need for improvement in documentation, coordination, and technology utilization in risk management.

Klasifikasi Kondisi Penyakit Asma Menggunakan Algoritma Naïve Bayes

2025-07-01T01:40:30+00:00

Asthma is a chronic respiratory disease characterized by symptoms such as shortness of breath, coughing, and wheezing, and can be life-threatening if not properly treated. Delayed diagnosis and difficulty in assessing symptom severity are often the main causes of serious complications. This study aims to develop a classification model for asthma conditions using the Naïve Bayes algorithm based on clinical symptoms and patient demographic data. The dataset used was obtained from the public Kaggle platform, consisting of 316,800 samples with 19 attributes. The research stages included data pre-processing, model training, application of the Synthetic Minority Oversampling Technique (SMOTE), and model performance evaluation using accuracy, precision, recall, and F1-score metrics. The initial classification results showed an accuracy of 75.19%, which increased to 83.59% after applying SMOTE. The F1-score also improved from 77% to 83%. These findings indicate that the Naïve Bayes algorithm is capable of classifying asthma conditions reliably, quickly, and efficiently. Therefore, the model is considered suitable to be implemented as an initial classification system to support timely and accurate clinical diagnosis of asthma

Business Process Reengineering Pada Delivery Order Dan Sistem Insentif Di PT.XYZ

2025-09-01T03:11:00+00:00

PT. XYZ is a company engaged in the furniture sector. This company has difficulty in carrying out delivery orders such as late deliveries and a manual driver incentive calculation system. Therefore, researchers use the Business Process Reengineering (BPR) method as a method that can re-optimize business processes to be more efficient, fast, and accurate. Business process mapping uses ASME (American Society of Mechanical Engineers) and is tested using the efficiency throughput test. In building a delivery order and driver incentive system, researchers use the RAD method and also include use cases to the UI of the application. The results of this study show that initially there were 33 business processes with a total time of 9 hours 40 minutes and an efficiency throughput test of 70% and after being re-engineered there were 14 business processes with a total time of 3 hours 55 minutes and an efficiency throughput test of 98%. This shows that business process engineering was successful by eliminating, eliminating and combining unnecessary business processes, and optimizing the use of technology.

Penggunaan Data Mining Asosiasi dalam Penjualan Produk pada PT Tiga Usaha Jaya Menggunakan Algoritma Apriori

2025-09-07T10:38:00+00:00

PT Tiga Usaha Jaya is a company engaged in the sale and installation of CCTV (Closed Circuit Television) and Security Systems accompanied by Access Control systems. The company faces the problem of being left behind in following very rapid technological developments, the arrival of the COVID-19 pandemic which has caused the company to experience a decrease in the number of product purchase transactions. In addition, the company's sales transaction data has not been utilized for in-depth information analysis. In addressing this problem, an association data mining application is designed that applies the apriori algorithm. The application is expected to help companies in obtaining information related to the relationship between products that are often purchased together with the aim of improving sales strategies and the effectiveness of product bundling due to data-based information. The rule obtained with the highest confidence value at 0.8260 (82.6%) is "The EZVIZ C6N 1080P WIFI CAMERA CCTV SMART IP - 1080P - Without Memory product tends to be purchased together with the Ezviz C6N, H6C, H7C Original CCTV Bracket product". From these results, the company can provide discounts or can package recommended products to make it easier for customers to buy products.

Klasifikasi Jenis Penyakit Tanaman Jagung Berdasarkan Citra Daun dengan Algoritma EfficientNetV2-S

2025-10-09T08:01:28+00:00

Corn is one of the important food commodities in Indonesia, which is susceptible to leaf diseases such as leaf rust, gray leaf spot, and leaf blight. These disease attacks can reduce both productivity and farmers' income. Manual classification carried out by field officers is still constrained by speed and consistency, necessitating an automated classification system based on digital images. This study proposes a corn leaf disease classification model using a Convolutional Neural Network (CNN) algorithm with the EfficientNetV2-S architecture. The dataset used consists of 2,256 corn leaf images from Kaggle, divided into four classes: Leaf Blight, Common Rust, Gray Leaf Spot, and Healthy Leaf. All images were resized to 224×224 pixels, augmented, and then split into 80% training data and 20% validation data. The training process was carried out with a batch size of 32, a learning rate of 0.000005, and 200 epochs. Performance evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The best result was obtained at the 150th epoch with 96% accuracy, with no signs of overfitting. These findings indicate that EfficientNetV2-S can serve as an effective model approach for classifying corn leaf diseases.

Digitalisasi Ekosistem Riset dan Inovasi Daerah Purwakarta: Analisis Kesiapan SDM Kolaborasi Pemerintahan

2025-10-14T02:43:40+00:00

This study investigates the digital transformation of the research and innovation ecosystem in Purwakarta Regency, emphasizing the readiness of human resources, inter-agency collaboration, and data governance. Using a descriptive qualitative approach, data were collected through in-depth interviews with three key local government offices: the Department of Industry, the Department of Trade, and the Department of Cooperatives and MSMEs. Thematic analysis following the Miles and Huberman model was employed to identify patterns within the ecosystem. Results indicate five structural challenges: (1) limited research and digital literacy among civil servants, (2) fragmented research databases, (3) lack of transparent digital funding mechanisms, (4) weak inter-agency collaboration, and (5) low innovation culture among MSMEs. Based on these findings, this study proposes the LINKRASI (Link and Integration of Research and Collaborative Internship) digital model as a governance framework to connect stakeholders through an integrated research management system. This study contributes to the understanding of local digital governance by proposing an integrated model that bridges research management and collaborative innovation.

Sistem Informasi Repository Penjamin Mutu Internal Universitas Indo Global Mandiri

2025-11-21T02:20:58+00:00

The advancement of information technology plays a vital role in enhancing the effectiveness of implementing the Internal Quality Assurance System (SPMI) in higher education institutions. This study designed and developed a web-based information system to support the implementation of SPMI at Universitas Indo Global Mandiri (UIGM) using the Web Engineering method, which includes the stages of planning, design, coding, and testing. The system provides features for uploading, reviewing, and reporting quality assurance documents for management staff and administrators. The implementation results show that the system improves the efficiency of quality document management and enhances the transparency of quality assurance processes at UIGM.

A Systematic Review of Random Forest and Logistic Regression Algorithms for Predicting Student Readiness in LSP-P1 Competency Certification at Vocational High Schools

2025-11-29T00:09:15+00:00

Assessing student readiness for LSP-P1 Competency Certification in Indonesian vocational schools is still commonly performed manually, resulting in subjective and potentially inaccurate decisions. Although existing studies have applied machine learning algorithms such as Random Forest and Logistic Regression to predict academic performance, limited research specifically focuses on vocational certification readiness within the Indonesian LSP-P1 context. This study applies a Systematic Literature Review (SLR) following Kitchenham and Charters guidelines to examine research trends, predictor variables, and key findings from previous studies. The review reveals that both algorithms are promising for readiness prediction; however, no study has explicitly addressed their application for LSP-P1 readiness at the SMK level. This work identifies research gaps and highlights opportunities for future development of data-driven decision support systems.

Sistem Informasi Pemeliharaan Kendaraan Operasional Untuk Meningkatkan Kegiatan Operasional Di PT Sinar Anugrah Nusantara Mas

2025-12-01T11:29:12+00:00

This study develops a web-based operational vehicle maintenance information system to improve the efficiency and effectiveness of operational activities at PT Sinar Anugrah Nusantara Mas. The system is designed as a solution to issues arising from manual documentation, which often leads to data inaccuracies, delays in maintenance scheduling, and insufficient monitoring of vehicle conditions. Through the digitalization of maintenance processes, the system provides features such as vehicle data management, automated maintenance scheduling, service history recording, and real-time condition reporting. The development process applies the Waterfall model within the System Development Life Cycle (SDLC), covering requirement analysis, system design, development, testing, and maintenance stages. The results indicate that the system enhances data accuracy, accelerates administrative processes, reduces operational costs caused by unexpected breakdowns, and supports data-driven decision-making. The implementation of this system is expected to optimize fleet management and improve the overall operational performance of the company

Prediction of Daily Ice Crystal Demand Using Modified Bi-xLSTM

2025-12-04T04:30:47+00:00

In this study, in addition to developing a predictive model based on Extended Long Short-Term Memory (xLSTM), an in-depth analysis was also conducted on the factors that can influence daily demand for crystal ice. Weather factors such as temperature, rainfall, and humidity, as well as Google search trends for “crystal ice,” were used as additional variables that are expected to improve the model’s prediction accuracy. The historical data collected consists of crystal ice sales over the past several months, including relevant external variables. Furthermore, this data was processed and cleaned using data preprocessing techniques such as normalization and handling of missing values to ensure it was ready for the model training stage.The implementation of the model involved splitting the data into training and validation sets, which provided an overview of how well the model is able to generalize to previously unseen data. The training process was carried out iteratively by tuning hyperparameters, such as the number of LSTM units, learning rate, and number of epochs, to achieve optimal model performance. Additionally, the binary classification feature integrated into this model allows SMEs to quickly decide whether additional production capacity for crystal ice is needed for the following day, based on the latest demand trends.Model evaluation was conducted not only based on accuracy values but also using a confusion matrix to gain deeper insight into the recall and precision rates. In this study, an accuracy of up to 90% was achieved, indicating that this model can be applied by various SMEs producing crystal ice to help increase their profits.