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

The Applications of Mamdani Fuzzy in Water Selection of Pangas Catfish Ponds

Rizki Mugi Setya Adi — 2024-03-06

In the field of fisheries, the selection of ponds water for Pangas catfish is very important because it affect the production and quality of fish. The purpose of this research is to apply the Mamdani fuzzy method in selecting suitable ponds water for Pangas catfish. The method used includes collecting data on water quality and environmental conditions, constructing the Mamdani fuzzy system and evaluating the results of selecting ponds water. The results of the study show that the Mamdani fuzzy method is able to provide a good solution in selecting ponds water for Pangas catfish by combining several factors such as temperature, pH and oxygen solubility. This concept can be used as a consideration in selecting the right ponds water for Pangas catfish so as to increase fish production and quality.

Classification of Marine Fish Based on Image Using Convolutional Neural Network Algorithm and VGG16

Dimas Adira Wibisono — 2024-06-21

Marine fish are one of the many natural resources that frequently consumed by people. However, several types of marine fish are prohibited from consumption due to being nearly extinct. Additionally, some fish species contain high levels of mercury that can be harmful to human if consumed. Because of the large number of marine fish species, it becomes challenging to identify them without knowledge of fisheries. Moreover, computers have become highly advanced devices that facilitate various human activities. This advancement allows for the creation of systems capable of processing information from images, known as image classification. There are numerous methods that can be employed in designing an image classification system, one of which is transfer learning. This study was aimed to design an image classification system using the transfer learning method with a pre-trained VGG16 model and Convolutional Neural Network algorithm. The research results showed a training data accuracy of 100% and a validation data accuracy of 99.3%, with an overall accuracy of 84% and a loss value of 0.6591.

Utilizing Design Thinking and User Experience Research for Effective Agricultural Labor Recruitment Web Application Design

Cut Luna Sabrina — 2024-06-28

The agricultural sector faces a significant challenge in recruiting a skilled workforce, with both landowners and tenant farmers struggling to find new laborers. Factors such as inadequate rural infrastructure and facilities, coupled with limited technology adoption, have diminished the appeal of working in the agricultural sector. Consequently, agricultural productivity has declined due to a shortage of adequate labor. To address this issue, a prototype web application named “Partner Tani” was designed to facilitate labor recruitment for farmers. The application design process employed the Design Thinking methodology and the User Experience Questionnaire (UEQ) to thoroughly understand user requirements. The design outcomes encompass both user interface and administrator interface components, developed using Figma. The prototype application features functionalities such as login, account registration, profile management, job posting and search, and complaint reporting. Evaluation using the UEQ revealed that the prototype application achieved exceptional scores across all user experience dimensions: Attractiveness (average score: 2,11), Perspicuity (average score: 1,42), Efficiency (average score: 2,33), Dependability (average score: 1,50), Stimulation (average score: 1,75), and Novelty (average score: 1,67). Average scores for Attractiveness, Efficiency, Stimulation, and Novelty fell within the “Excellent” range, while Perspicuity and Dependability scores were above average. These findings indicate that the “Partner Tani” application prototype holds promise in delivering a satisfying and efficient user experience for agricultural labor recruitment.

Website Based Academic Information System Design Using Extreme Programming Method

Deni Prasetyo — 2024-07-03

SMP Negeri 3 Watukumpul is a junior high school located in Bongas Village, Watukumpul District, Pemalang Regency, Central Java. This school has implemented website-based technology as a medium for conveying information, but the website is no longer usable. The data obtained from the interview results indicate the need for an academic information system website as a medium for disseminating information and managing academic data digitally. Based on the existing problems, researchers will re-create a website-based Academic Information System for SMP Negeri 3 Watukumpul as a medium for delivering information and managing academic data. This research uses the Extreme Programming method, which is one of the development methodologies of Agile Software Development Methodologies. The Extreme Programming method has several stages: Planning, Design, Coding, and Testing. The system uses black box testing on student, admin, and teacher accounts. Blackbox testing on student accounts includes login, register, profile, news, wall magazine, course material, grades, contacts, and logout menus. Blackbox testing on teacher accounts consists of login menus, course materials, grades, and grade page details. Black box testing on admin accounts consists of login menus, school profiles, teachers and employees, news, wall magazines, extracurriculars, and lesson schedules. In testing this system, researchers use black box testing to test its functionality. The black box test from the student's account got a result of 100%, the black box test result from the teacher's account got 100%, and the black box test from the admin account was 98.57%. Thus, the average black box test result from the three users was 99.52%. With the existence of this school website, it is hoped that information dissemination activities and academic data management activities will become more effective and efficient.

Design of Monitoring System Gryllus Mitratus Cricket Cultivation Based Internet of Things

Aulia Desy Aulia Nur Utomo — 2024-07-04

Crickets have various types, one of which is Gryllus Mitratus. Gryllus Mitratus crickets in Penolih village are cultivated by 16 cricket breeders, with individuals having at least 6 boxes with a size of 200 x 120 x 65 cm and a cage foot height of 25 cm. Cricket cultivation in Penolih village, Kaligondang sub-district, Purbalingga district, is still not optimal due to several factors, such as temperature, humidity, and light intensity, which are not suitable for crickets and cause stress and death. The temperature that crickets can accept is 20 ^oC to 32 ^oC, humidity is 65% to 80%, and light intensity is 0 lux. A tool is needed to monitor temperature conditions using DHT11, humidity using BME280, and light intensity using BH1750, which is installed in the cricket cage to determine its value and be followed up by cricket breeders. These sensors will send the input data to NodeMCU to be sent to the cloud so that it can be displayed in the Android application. The research method used is waterfall, namely the development of a systematic and sequential information system. Based on testing for 7 days, the average temperature of the cricket cage was 28.26 ^oC, the humidity of the cricket cage was 74.72%, and the light intensity of the cricket cage was 5.1 lux.

Analysis of User Satisfaction with the Cards Application Using the End User Computing Satisfaction Method

Xenaya Hawa Eldita — 2024-07-04

The rapid development of technology has significantly facilitated daily activities and brought about numerous changes in society. This swift technological advancement has had a profound impact on the development of payment systems in transactions. Various applications like CARDS have become well-known and widely utilized by many individuals to streamline their day-to-day transactions. CARDS application is also popular within school environments, making it easier for students and cooperative employees to conduct transactions for purchasing food, beverages, and other school necessities. However, there are challenges that need to be addressed regarding the use of the CARDS application. One of them is the lack of understanding among some parents in operating the application and loading credits. End User Computing Satisfaction can be used as a method to measure the level of satisfaction of a system application's users. This method compares user expectations with the reality provided by the application, thereby identifying how well the application meets user expectations. The research results will provide recommendations for improving the application, taking into account the End User Computing Satisfaction method.

Analysis of NSL-KDD for the Implementation of Machine Learning in Network Intrusion Detection System

Yuliana Yuliana — 2024-02-29

In the world of network data communication, anomaly detection is a crucial element in identifying abnormal behavior among the flowing data packets. Research in the field of intrusion detection often focuses on the search and analysis of anomalous patterns and the misuse of communication data. The research methodology in this study adopts CRISP-DM (Cross-Industry Standard Process for Data Mining) as the framework. The primary goal of this research is to conduct a comparative analysis of classification techniques to identify normal and anomaly records within network data. For this purpose, a publicly available standard dataset, NSL-KDD, is used. The NSL-KDD dataset consists of 41 attributes with relevance, and the 42nd attribute is used to identify normal class and four attack classes. The results of the analysis using the NSL-KDD dataset, applying the CRISP-DM methodology and machine learning techniques in the Network Intrusion Detection System, reveal that the Decision Tree model has the highest accuracy, achieving 100% on the training data and 80% on the testing data. These findings are compared with the results of using other models such as Random Forest, Logistic Regression, and K-Nearest Neighbor. This discovery has significant implications for enhancing NIDS's ability to recognize network threats and improve network system security.

Sentiment Analysis Using Transformer Method

Andi Aljabar — 2024-02-29

This research delves into sentiment analysis, employing the transformative capabilities of transformer method. Specifically, leveraging BERT Models, the study aims to advance sentiment classification accuracy by intricately capturing contextual nuances and positive or negative comment on IMDB movies reviews. The transformer architecture's distinctive attention mechanism proves pivotal in comprehending intricate relationships between words, facilitating a profound understanding of sentiment in textual data. Through extensive experimentation, the study establishes the transformative prowess of these methods, showcasing their effectiveness in achieving state-of-the-art results in sentiment analysis tasks. This investigation not only contributes to the evolving landscape of sentiment analysis but also underscores the significance of transformer-based approaches in deciphering the subtleties of human expression within textual data specially for Bert models. This research will predict sentiment analysis on comment of IMDB movies and shows some results which are 3% of loss, 60% off loss validation, 98% of accuracy and 90% of validation accuracy

Exploration of the Dempster-Shafer Theory for Diagnosing Hardware Damage: Comparative Study with the Certainty Factor Method

Koidah Koidah — 2024-03-05

Comparative research is a research method that compares two or more research objects to expand understanding of them. In this context, we compare the Certainty Factor method and the Dempster-Shafer method in diagnosing computer hardware damage. The Certainty Factor method measures an expert's confidence in the solution that will be provided. On the other hand, the Dempster-Shafer method is a useful theory in situations where uncertainty dominates. This research focuses on comparing the effectiveness of the two methods in detecting computer hardware damage. An experimental approach is used to look for causal relationships between variables controlled by the researcher. The research results show that the Certainty Factor method has an average success rate of 14.51%, while the Dempster-Shafer method reaches 84.27% in terms of error difference. From these results, it can be concluded that the Certainty Factor method is more effective in diagnosing computer hardware damage.

Keywords: INISTA, journal, MS.Word template