Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Implementasi Website K-Etik untuk Digitalisasi Manajemen Etik Penelitian di Universitas YARSI
No full textThe K-Etik Website was developed by Universitas YARSI as a solution to inefficiencies in research ethics management, which had previously been conducted manually, often leading to delays, inefficiencies, and a lack of transparency. This study aims to create a digital application capable of accelerating the review process and enhancing transparency in the management of ethics documents. The Scrum methodology was applied to facilitate collaboration between developers and users, integrating modern technologies such as React.js for the user interface, Node.js for the server, and MongoDB for database management. The application evaluation was conducted through black-box testing, indicating that the application meets the specified requirements, including user authentication, document submission workflows, and real-time progress tracking. System Usability Scale (SUS) testing yielded an average score of 81.1, classified as “Excellent,” signifying the application's high usability and readiness to support ethics management in research. Through digitalization via the K-Etik application, research ethics management at Universitas YARSI has become more efficient and transparent, strengthening accountability and responsiveness in the ethics document review process. The study concludes that this application provides a comprehensive digital platform to support a structured and accountable research environment at Universitas YARSI
Rancang Bangun Sistem Perpustakaan Web Universitas Esa Unggul dengan Metode Scrum untuk Pengelolaan Digital
No full textConventional library systems that are still manual-based often face various obstacles, such as delays in the transaction process, the risk of recording errors, and low efficiency in collection management. This research aims to design and build an integrated web library system at Esa Unggul University by applying the Object Oriented Programming (OOP) approach and Scrum method. The development process is carried out iteratively through the stages of Sprint Planning, Execution, Review, and Retrospective. The system was developed using Python programming language with Flask framework and MySQL database. The main features include book data management, members, loan and return transactions, automatic notifications, and time-based fine calculations. Evaluation was conducted using the Black Box Testing method on 35 scenarios, including input validation, transaction processing, and system resilience to extreme conditions. The test results showed a 100% success rate and a 60% increase in transaction efficiency compared to the manual system. End-user validation showed that the system has a responsive interface, easy to use, and supports digital library management. This research contributes to the digital transformation of libraries and opens up opportunities for development towards mobile platforms and data analytics
Optimizing Road Safety with MobileNet-Based Classification of Over-dimensioned Trucks
No full textThis study aims to automatically detect overdimension trucks using a lightweight and efficient deep learning model based on MobileNet. Overdimension trucks pose serious threats to road infrastructure, traffic safety, and contribute to increased economic costs due to road damage and congestion. The developed model utilizes MobileNet as a feature extractor without the standard fully connected layers, and is equipped with additional layers including Flatten, Batch Normalization, Dense with Leaky ReLU activation, and Dropout to enhance training stability and prevent overfitting. The dataset consists of two classes—normal trucks and overdimension trucks—with images sized 128×128 pixels, collected from internet sources and field photos. The training process employs binary crossentropy loss, the Adam optimizer with an initial learning rate of 0.0001, and an Early Stopping mechanism. Fine-tuning is performed by unfreezing layers from the 100th layer upward and lowering the learning rate to 0.00001. Evaluation results show an accuracy of 97.92%, with consistent loss and accuracy visualization, demonstrating the model's capability in classifying overdimension trucks to support automatic traffic monitoring systems. This model has the potential to be implemented in toll gate systems to automatically deny access to overdimension vehicles. Furthermore, integration with roadside CCTV allows real-time monitoring of vehicle dimension violations across various traffic checkpoints
Analisis Pengaruh Luas Area Pertanian Terhadap Prediksi Hasil Pertanian di Kebumen Menggunakan Metode Regresi Linier
No full textKebumen as an agricultural area whose people mostly play a role in agriculture has an important role in the southern part of Java. The size of the agricultural area will affect agricultural results, especially rice yields. Large agricultural areas will be beneficial for the community in their role as well as food self-sufficiency programs so that dependence on foreign agricultural production is reduced. However, agricultural conditions have not been managed maximally. It is hoped that agricultural yield predictions can help the government in making decisions on the management of agricultural areas in Kebumen. The linear regression method is one of the methods in data mining for data forecasting that relies on historical data so it requires agricultural yield data for the period from 2013 to 2019. The prediction process uses data on the area of the harvest which will influence the harvest in tons. Previous research shows that the linear regression method produces very small error values so it is very suitable for use in prediction cases. The aim of this research is to determine the predicted influence of harvested land area on the amount of harvest in Kebumen as analysis material. The stages in the linear regression method are determining the intercept and coefficient values with the a value of -317.231 and the b value of 6.0123, determining the regression equation to determine predictions, calculating the difference in predicted data, calculating the error value using MAPE with a result of 5,60%
Child Presence Detection for Child Safety with Deep Neural Networks
No full textAccidents and injuries to children often occur due to lack of supervision. This research develops a child presence detection system using Computer Vision technology and the Age Estimation method to improve child safety in dangerous areas. The system was tested with a Canon EOS M50 camera at various distances, camera heights, and light intensity. The analysis using anova obtained a data confidence level of 95% for light intensity, and the age estimation method showed performance with a success of 84.72%. This research can be applied to supervise and improve safety in children, especially outdoors
Prediksi Kesehatan Mental Remaja Berdasarkan Faktor Lingkungan Sekolah Menggunakan Machine Learning
No full textAdolescent mental health is a crucial aspect that affects academic performance, social relationships, and overall well-being. The school environment is one of the primary factors influencing adolescents' mental conditions. This study aims to predict adolescent mental health levels based on school environmental factors using the Random Forest algorithm. Data were collected from 229 adolescents in Lhokseumawe and categorized into four classes of mental health conditions. The research methodology includes data preprocessing, model training, and performance evaluation using accuracy and other relevant metrics. The results show that the model achieved an accuracy of 80.43%, with the highest F1-score of 0.90 in the category indicating no mental health issues. Feature importance analysis identified loneliness, feelings of worthlessness, academic pressure, and home-related stress as the most influential factors in the predictions. While the model effectively classified most data, some misclassifications occurred at certain mental health levels. Thus, the Random Forest model proves to be an effective predictive tool for detecting potential adolescent mental health issues. The findings of this study can serve as a reference for educational institutions in designing more targeted intervention strategies to support adolescent mental well-being
Rancang Bangun Sistem Informasi Psikoedukasi Berbasis Web Cintadiri.id: Pencegahan dan Penanganan Self-harm
No full textSelf-harm is an intentional act of self injury without suicidal intent. In Indonesia, self-harm is becoming an increasingly serious problem, especially among teenagers. Previous studies and surveys conducted by institutions shows quite significant results with relatively high numbers. Considering that the causes of self-harm are quite complex, there is a need for education about self-harm and access to mental health services. Based on aforementioned researches, a web-based information system was developed which the author called Cintadiri.id. Cintadiri.id was designed and developed as an innovative and comprehensive information system to help prevent and deal with self-harm behavior in Indonesia. This system hopes to help people who are struggling with self-harm behavior get the information and resources they need to get help and recover. Cintadiri.id information system was developed using SDLC Waterfall method, supported with PHP programming language, MySQL database and Laravel framework. Cintadiri.id provides various information and resources that can help people who are struggling with self-harm, including information about self-harm, resources and tools to help people who are struggling with self-harm behavior. It is hoped that Cintadiri.id can be a reference for the information and resources they need to get help
Optimasi Bobot Kelas LSTM untuk Deteksi URL Phishing pada Dataset Tidak Berimbang
No full textPhishing URL detection is one of the main challenges in cybersecurity, considering the ever-increasing threats affecting internet users globally. This research aims to develop a Long Short-Term Memory (LSTM) based deep learning model to detect phishing URLs with high accuracy. The dataset used consists of 651,191 URLs, which are divided into four categories: benign, defacement, phishing, and malware. The dataset is processed through preprocessing stages, including URL cleaning and feature extraction. The LSTM model is applied with optimized hyperparameter configurations to learn patterns from the dataset. The results showed that the model was able to achieve significant accuracy during the training and validation process. Evaluation on external datasets shows that the model performs well in the benign and defacement categories, with relatively high precision and recall. However, challenges were identified in the malware and phishing categories, where recall was low due to dataset imbalance and lack of feature representation. Further analysis showed a model bias towards the majority class, as well as difficulty in detecting URLs in the minority class. This research shows the potential of using LSTM-based deep learning in phishing URL detection, but also emphasizes the importance of further optimization, such as adjusting class weights, oversampling, or using additional features. It is hoped that the resulting model can be an initial solution in improving cyber security, especially in detecting phishing threats in real-time
Menggunakan Metode Machine Learning Untuk Memprediksi Nilai Mahasiswa Dengan Model Prediksi Multiclass
No full textThis study aims to predict students' final GPA and study duration using machine learning methods. The model applied in this study is the Random Forest Regressor, which was trained using a dataset that includes various factors such as semester GPA, socio-economic background, demographics, learning activities, and the difficulty level of courses. The results of the study show that the model produces less accurate predictions, with a Mean Squared Error (MSE) of 0.34 for the final GPA and 3.83 for the study duration. Furthermore, the R² Score for the predictions of final GPA and study duration are -0.079 and -0.055, respectively, indicating that the model's prediction performance is not optimal. In the multiclass classification section, the model is able to classify students into several categories based on their final GPA, such as Cum Laude, Very Satisfactory, Satisfactory, and Fair. From the testing results, the model predicts a final GPA of 2.92 for a new student example, which is classified into the "Satisfactory" category, with a predicted study duration of 8 semesters. The conclusion of this study indicates that the regression model used requires improvement to achieve better accuracy. Other factors, such as feature optimization or the use of alternative algorithms, can be explored in future research to enhance the prediction results
Sistem Informasi Kesatuan Pengelolaan Hutan Yogyakarta Berbasis Web
No full textThe Forest Management Unit Information System (SIKPH) is a platform that integrates information technology to improve the efficiency and effectiveness of forest management. This research aims to develop a web-based SIKPH as a modern solution for the Forest Management Unit in Yogyakarta. The system development method uses the scrum methodology, which consists of requirements analysis, system design, implementation, and evaluation. Requirements analysis was conducted by understanding the demands and challenges faced by the Yogyakarta Forest Management Unit. Based on this analysis, the system design includes web architecture, user interface, database, and functionality that supports forest management processes. System implementation using the Laravel framework with performance testing shows an average response time of 1.2 seconds for 20 simultaneous users and 2.0 seconds for 30 users. User acceptance evaluation involved 30 respondents with beta testing results showing an average satisfaction level of 4.4 out of 5 for aspects of ease of use (4.3), feature compatibility (4.5), and system benefits (4.6). The system includes modules for forest sustainability monitoring, inventory management, and reporting with a 96% implementation success rate based on functional testing. The results of this research provide a positive contribution to forest management in Yogyakarta by improving process efficiency by 40% compared to the previous manual system