Journal of Informatics Information System Software Engineering and Applications (INISTA)

Public Sentiment Analysis Against Identitas Kependudukan Digital Application Using Decision Trees

Fernanda Al Khafid Faridian — 2025-11-30

The Identitas Kependudukan Digital (IKD) application is an innovation in the government sector that is expected to facilitate public administration through electronic means. The implementation of the Identitas Kependudukan Digital application has sparked public debate regarding its application and security. This study aims to analyze public sentiment towards the Identitas Kependudukan Digital application using the Decision Tree algorithm and to present the performance of the Decision Tree algorithm in terms of positive and negative sentiment scores. The author collected review data from Google Play for the Identitas Kependudukan Digital application using web scraping techniques with Google Collaboration. Based on the analysis results, the Decision Tree algorithm predicted 240 negative and 4 positive data points out of 244 test data points. The testing and evaluation results using the Decision Tree algorithm yielded an accuracy of 89.34%, a precision of 90.00%, and a recall of 99.08%. According to the word frequency results in the word cloud, the words “Aplikasi” and “Data” had the highest word frequencies, representing the main contributors to the high percentage of negative sentiment in the analysis of public sentiment towards the Identitas Kependudukan Digital application.

Smart IoT System for Agricultural Pest Control Using Special Frequency Sound Waves

Helena Kusuma Wardhani — 2025-11-30

This research develops a prototype of an Internet of Things (IoT)-based cricket pest control system that utilizes ultrasonic waves for rice farming. Addressing global financial losses caused by pests and health risks from chemical pesticides, the main objective is to design an intelligent non-chemical solution. The methodology used is experimental Research and Development (R&D), in which the system is integrated using the ESP32 DO IT Module, a PIR Sensor for cricket detection, and a Passive Buzzer as the ultrasonic emitter (above 20 kHz). The main novelty lies in two aspects: first, the integration of IoT for automatic and targeted repellent activation through PIR Sensor detection; second, the implementation of an adaptive frequency variation mechanism on the ESP32 to periodically change waveform patterns, overcoming the cricket habituation weakness observed in static systems. Testing was conducted with 10 repetitions at 10 different frequency levels (21–30 kHz) in a controlled environment. The results show that the system successfully detects cricket presence and automatically activates the ultrasonic buzzer, achieving the highest success rate of 90% at the optimal frequency range of 25–29 kHz. The conclusion indicates that this prototype offers a smarter, more adaptive, and more efficient solution for cricket pest control in rice farming compared to simple embedded devices.

Implementation of CLAHE and CLAGAMTWO in Medical Images

Faisal Muttaqin — 2025-11-30

In the era of development of medical image processing technology, the quality of radiological images such as X-ray, CT-Scan, and MRI plays an important role in the diagnosis process, detecting diseases early, and evaluating the treatment of various medical conditions. To maximize the potential of images in the diagnostic process, effective pre-processing steps are needed so that anatomical structures are more clearly visible, pathological details are maintained, and noise and artifacts can be reduced. One of the image contrast enhancement techniques is Contrast Limited Adaptive Histogram Equalization (CLAHE) and CLAGAMTWO (Clahe-Gamma-Gamma). CLAHE is superior in ENTROPY of 7.154, while for CLAGAMTWO it is superior in SSIM value of 0.944 and CNR of 1.820. So, in terms of increasing the complexity or diversity of information CLAHE is slightly better than CLAGAMTWO. While for CLAGAMTWO it is better in the level of contrast clarity between dark and bright areas in an image, even though there is noise interference.

Website Based Ticket Ordering Application Design Using Laravel Framework (Bedegung Waterfall Tour, Muara Enim Regency)

Wawan Gunawan — 2025-11-28

Bedegung Waterfall is a well-known natural tourism destination located in Bedegung Village, Muara Enim Regency, offering beautiful scenery and a prominent waterfall. Despite its popularity, the ticket booking process is still conducted manually, resulting in long queues, slow transactions, service delays, and traffic congestion around the tourist area, which reduces visitor comfort and management efficiency. To address these issues, this study proposes developing a web-based ticket-booking application to streamline transactions and enhance tourism service quality. The system was designed and developed using the Extreme Programming (XP) software development method to ensure flexibility, rapid development, and effective collaboration. The application was implemented using the Laravel framework, PHP as the programming language, and MySQL as the database management system, due to its reliability in handling large volumes of data. System design was supported by Flowcharts, Use Case Diagrams, Class Diagrams, Activity Diagrams, and Entity-Relationship Diagrams (ERDs) to clearly describe system workflows and data relationships. The objective of this research is to design, implement, and evaluate a web-based ticket booking system that improves transaction efficiency, reduces queues, and enhances visitor convenience. The system supports three user roles: Super Admin, Tourist Staff, and Member, each with distinct access rights and functionalities. System testing was conducted using the Black-Box Testing method to evaluate functional suitability against user requirements. A total of 37 testing scenarios were executed across all user roles, and the results showed that all system functions operated as expected, achieving a 100% testing success rate, indicating that the developed application is effective and feasible for implementation at Bedegung Waterfall.

Implementation of Forward Chaining And Certainty Factor Methods for Android-Based Red Onion Diagnosis

Imam Ghozali — 2025-06-26

Shallots are one of the crucial horticultural commodities in Indonesia, used in various social layers. Brebes is one of the main shallot producing regions with a significant increase in production. However, farmers often experience reduced yields due to disease attacks and lack of guidance from experts. This researcher aims to develop an Android-based expert system that applies the Certainty Factor and Forward Chaining methods to identify diseases in shallot plants. This system uses rules to identify onion disease symptoms and calculates the confidence level for each possible diagnosis. The Forward Chaining method helps identify symptoms sequentially, while the Certainty Factor calculates confidence in the possibility of disease. The research results show that this method is effective in providing an accurate diagnosis of onion diseases from the 5 diseases tested by the recommended system with a percentage value of 100%. In conclusion, the expert system created for diagnosing shallot plants using the Android-based forward chaining and certainty factor method was successfully built. Then, for Functionality Testing based on black box testing carried out by experts, the results were obtained with 100% accuracy, which means the system is in accordance with its functional requirements.

Multi-Layer Perceptron with Advanced Acoustic Features for Speech Emotion Recognition in Education Evaluation

Muhammad Afiq Tamamul Wafa — 2026-02-11

Traditional methods for evaluating lecturer performance in education, such as student surveys, are often limited by their nature. This study explores the development of an objective, a framework to complement these evaluations through Speech Emotion Recognition (SER). This Research utilizes a specialized Indonesian speech emotion dataset, applying data augmentation techniques to enhance model generalization. A set of advanced acoustic features, including Mel Frequency Cepstral Coefficients (MFCCs), Chroma, and Spectral Contrast, along with their statistical variations, is used to create representations of the vocal expressions. A Multi Layer Perceptron (MLP) neural network was designed and trained on these features to classify five different emotions: happy, angry, sad, surprised, and neutral. The Research resulted in a model that demonstrated very good performance, achieving an overall classification accuracy of 94% with high precision, recall, and F1-scores across all emotions, indicating a balanced and reliable system. A critical feature analysis was also conducted, revealing the significance of the standard deviation of Chroma and MFCC features. This study shows that an MLP model paired with feature engineering can be used as a powerful and objective tool for providing deeper insights into student feedback, contributing a valuable new methodology for quality assurance in higher education.