cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
jurnal.josh@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josh@gmail.com
Editorial Address
Sekretariat Forum Kerjasama Pendidikan Tinggi (FKPT) Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Computer Science & IT Decision Sciences, Operations Research & Management
Artikel yang dimuat melalui proses Blind Review oleh Jurnal JOSH, dengan mempertimbangkan antara lain: terpenuhinya persyaratan baku publikasi jurnal, metodologi riset yang digunakan, dan signifikansi kontribusi hasil riset terhadap pengembangan keilmuan bidang teknologi dan informasi. Fokus Journal of Information System Research (JOSH)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 795 Documents
 56   57   58   59   60 
Penerapan Metode Time Series Analysis pada Sistem Informasi Posyandu untuk Mengetahui Pola Berat Badan Anak menggunakan Whatsapp Gateway Helmi, Elsy Shafira; Triase, Triase
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6083

Abstract

Posyandu Melati Batang Gasan has been routinely collecting children's weight data every month, but is facing difficulties in managing and analyzing the data effectively. Data recording is only done in books without in-depth analysis, causing delays in proactive actions towards abnormal child growth. This manual recording is time-consuming, prone to errors, and hinders more in-depth analysis. In addition, information regarding the schedule of posyandu activities is often received late by parents, resulting in low community participation. The purpose of this research is to build a Posyandu Information System using the Time Series Analysis method and integrate the Whatsapp Gateway feature to manage children's weight data, perform time series analysis, and send Whatsapp notifications. Based on the existing problems, this research implements the Posyandu Information System using the Time Series Analysis method with Double Exponential Smoothing to monitor and forecast children's weight development, and integrates the Whatsapp Gateway feature to enhance communication and parental participation. The research results show good accuracy, with the forecasted weight and height of children for August being 14.6 and 104.6, respectively, with a Mean Absolute Percentage Error (MAPE) of 2%, and WhatsApp Gateway notifications can be sent through the system. Overall, this method is effective in predicting children's weight with good accuracy and increasing parental attendance at the posyandu.
Evaluating the Effectiveness of Machine Learning Models for Cyberattack Detection: A Study on Model Generalization and Dataset Imbalance Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6089

Abstract

In today's rapidly evolving digital landscape, detecting and preventing cyberattacks has become crucial for securing networks and data. This study evaluates the performance of several machine learning models, including RandomForest, GradientBoosting, XGBoost, LightGBM, CatBoost, Support Vector Classifier (SVC), Logistic Regression, and an ensemble Voting Classifier, in detecting and classifying cyberattacks. The models were tested on a real-world cybersecurity dataset with significant class imbalance, where benign traffic vastly outnumbers malicious attacks. Results showed that while some models, such as RandomForest and the Voting Classifier, achieved high training accuracy, they suffered from overfitting, with test accuracies not exceeding 34%. Boosting models like XGBoost and LightGBM exhibited better generalization than RandomForest but still struggled to handle the dataset complexity. The primary limitations of this study include the dataset's imbalance, the high dimensionality of the features, and the models’ tendency to overfit. These challenges highlight the need for more robust data preprocessing techniques, hyperparameter tuning, and exploration of advanced models, such as deep learning architectures, for future work. The findings provide insights into the challenges of using machine learning for cybersecurity attack detection and point toward future directions for improving model performance in real-world settings.
Robust Fan Actuator Prediction in Smart Greenhouses Using Machine Learning: A Comparative Analysis of Ensemble and Linear Models Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6095

Abstract

The increasing demand for sustainable agriculture has driven the development of smart greenhouses equipped with automated systems for climate control. A critical component of these systems is the fan actuator, which regulates airflow and stabilizes the internal climate. This study explores the use of machine learning models for predicting the activation status of fan actuators based on environmental data collected from a smart greenhouse. We evaluate several machine learning models, including Support Vector Machine (SVM), Random Forest, Gradient Boosting, XGBoost, and Logistic Regression, under real-world conditions simulated by adding noise and label corruption to the dataset. The dataset was augmented and balanced using the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalances. Results indicate that ensemble methods, particularly XGBoost and Random Forest, outperform simpler models in terms of accuracy, precision, recall, and F1 score. XGBoost achieved the highest accuracy at 94.47%, while Random Forest followed closely with 94.29%. The study demonstrates that these models are robust to data imperfections and can be effectively employed for real-time fan actuator control. However, further validation is needed to generalize the findings to different greenhouse environments. The research highlights the potential of machine learning models to improve operational efficiency in smart farming, offering insights into how these technologies can support more sustainable agricultural practices.
Rancang Bangun Sistem Alat Ukur Heart Rate Dan Suhu Tubuh Menggunakan Esp 8266 Syhabudin, Noval Aziz; Darmawan, Budi; ‎Supriono, Supriono
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6096

Abstract

This research developed an Internet of Things (IoT)-based health monitoring system, which is designed to support real-time monitoring of heart rate and body temperature without the need for on-site medical personnel. The main problem identified is the need for health monitoring tools that can be used independently by the community to monitor health status simply and accurately. The device was developed using a ESP8266 microcontroller, a MAX30100 heart rate sensor, and a MLX90614 temperature sensor, allowing for the automatic collection of health data and the transmission of data through the Telegram application using a Wi-Fi network. Data sources come from many subjects with different ages and health. conditions to test the effectiveness and accuracy of the device. The method used involves testing sensors to measure heart rate and body temperature, with the data displayed on an OLED screen and transmitted in real time for remote monitoring. The results showed that the accuracy of the measurements was at a good level, with an average error of 5 to 7%. Linguistic analysis of the data showed the device's ability to detect serious health conditions such as hypoxemia (SpO2 < 95%) and hypothermia (body temperature < 36°C), requiring immediate medical attention. This solution allows individuals to easily perform health monitoring independently without the need for medical assistance.
Rancang Bangun Sistem Monitoring Suhu Air Pada Kolam Pembesaran Ikan Nila Berbasis IoT Syamsi, Hans Riadhi; Darmawan, Budi; Budiman, Djul Fikry
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6097

Abstract

The tilapia rearing process requires optimal water temperature quality for good growth. The optimal water temperature for tilapia rearing is 26°C - 32°C. Temperatures that are too low or too high can cause growth disorders and even death in tilapia. Manual monitoring of tilapia rearing pond water temperature by the pond owner is often inefficient because it requires regular visits. Based on this problem, this research aims to design an automatic tilapia water temperature monitoring system using Internet of Things (IoT) technology that can work automatically and in real-time. The data used in this research is collected through the reading of the pond water temperature by the DS18B20 temperature sensor installed in the tilapia rearing pond. This monitoring system is designed using ESP32 as the main microcontroller, DS18B20 temperature sensor, heater, relay, and LCD. The results showed that the system succeeded in maintaining the optimal water temperature for tilapia. When the water temperature is below 26°C the heater will automatically turn on to warm the pool water temperature and the heater will automatically turn off when the temperature is above 30°C. The average temperature monitored in this study is 28.90 ° C, with successful notifications sent via telegram bot every five minutes and real-time pond water temperature data via LCD.
Aplikasi Pembelajaran Al-Qur’an "Madina" Memanfaatkan Teknologi Digital Pada Anak Usia Dini Berbasis Android Menggunakan Metode Rapid Application Development KH, Musliadi; Kaharuddin, Kaharuddin; Roza, Yuni; Pernando, Yonky
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): January 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6102

Abstract

Learning the Qur'an is the most important aspect in shaping a person's personality and morality, including in early childhood, especially those who adhere to Islam. Currently, the level of interest in learning the Qur'an in early childhood has decreased in various circles due to the influence of technological developments. Technological developments have changed children's behavior and attitudes in everyday life, especially in the use of smartphones which are more often used to play and watch movies via YouTube, Instagram, and Facebook than used to learn to read the Qur'an so that knowledge about reading the Qur'an is eliminated due to playing and watching movies. Along with the increasing influence of technology among children, there needs to be a breakthrough that can be utilized in learning the Qur'an in early childhood without changing the behavior of using smartphones. To design the "Madina" Qur'an learning, an appropriate, fast, and effective method is needed as a benchmark in the design cycle. The Rapid Application Development method is one of the many methods that are most often used to design Android-based applications, this is because this method only consists of four main cycles and focuses on the use of a short time in the design process. The results of the research and evaluation conducted obtained 54 respondents who were dominated by parents as the main companions in using smartphones. Children who use this application the most are in the age range under 4 years where on average they use the application for approximately 15-30 minutes under parental supervision. The Al-Qur'an learning application "Madina" can be accepted by users and parents, this is indicated by the evaluation results being at an average percentage of 86% with very strong criteria.
Identifikasi Nilai Keacakan Berdasarkan Reposisi Fungsi XOR Pada Blok Kedua LFSR A5/1 Pallangan, Jorghie Theodore Kenzo; Wowor, Alz Danny
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6112

Abstract

This research plans a random number generation method using the Linear Feedback Shift Register (LFSR) method with the A5/1 scheme which involves three feedback functions. XOR is used to determine the new output bit value in the next iteration in the feedback mechanism. The test material produces random output for an input using Run Test, Mono Bit, and Block bit. Tests using three feedback functions were carried out to compare with previous research which generated random numbers. Testing of plaintext and ciphertext encryption shows a very small level of correlation with an average value close to 0. The use of LFSR with the A5/1 scheme which involves three XOR functions, creates random output and can be used against Stream Chipers.
Prototipe Smart Mosque System Untuk Persiapan Sarana Sebelum Waktu Shalat Berbasis IoT Kafrawi, Achmad Evin; Ch, Syafaruddin; Kanata, Bulkis
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6116

Abstract

The advancement of technology in the modern era has driven the development of innovations that facilitate human activities, one of which is through the concept of the Internet of Things (IoT). This research aims to develop a smart mosque prototype based on IoT to prepare facilities before prayer times. The issue faced by several mosques is the lack of a permanent caretaker, which often leads to delays in preparing for worship, such as filling the ablution water or playing the Quran recitation before the call to prayer, as well as the management of facilities like lighting and fans that are not well controlled. The proposed solution in this research utilizes the NodeMCU ESP32 microcontroller, an ultrasonic sensor to detect the water tank capacity to ensure water is available, a DFPlayer Mini to automatically play the Quran recitation before the call to prayer, the MyQur’an API to retrieve prayer times, and the NTP (Network Time Protocol) server to synchronize the system time accurately. Additionally, the Blynk application is used to control the facilities within the mosque. Based on the test results, this prototype system demonstrates good performance in controlling mosque facilities, automatic water filling, and timely Quran recitation playback. However, in the automatic water filling, there is a limitation regarding the high filling threshold, where water overflows at 90% and 95% levels. The DS1307 RTC system has also proven capable of synchronizing time accurately with the prayer schedule from the MyQur’an API, with minimal time difference.
Penerapan Metode CNN (Convulution Neural Network) Dalam Klasifikasi Buah Putra, Fathan Aldira; Irawan, Davit; Wulandari, Cindi
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6121

Abstract

Fruit type classification plays an important role in supporting the efficiency of distribution, sorting, and stock management processes in the agriculture and food industry. The use of technology in various aspects of life is growing rapidly, including in agriculture and agro-processing. Fruit type classification is an important stage in the fruit supply chain, starting from farmers to consumers. Traditionally, fruit type classification is done manually by human labor, which can be error-prone and time-consuming. With the advancement of technology, especially the development of Convolutional Neural Network (CNN) in deep learning, there is an opportunity to automate and improve the accuracy of the fruit type classification process based on images. Convolutional Neural Network (CNN) is one of the methods in deep learning that has proven effective in image processing and pattern recognition. This method has provided impressive results in various applications, including object classification in images. The purpose of this research is to find out how the architecture and results of the Convolutional Neural Networks (CNN) algorithm for image classification of fruit types. The method used is CNN with different epoch values on each training data. Training data is 9000 and testing data is 100, and validation data is 1000 data. The results obtained quite high accuracy training which reached 82.42% and accuracy validation reached 87.50%. from these results it can be concluded that the model is included in good accuracy and succeeded in identifying types of fruit when testing with test data.
Rancang Bangun Sistem Kontrol Ph Air dan Pemberian Pakan Ikan Otomatis Pada Akuaponik Berbasis Mikrokontroler Pradana, Ersa Satria; Ch, Syafaruddin; Suksmadana, I Made Budi
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.6122

Abstract

Aquaponics is an integrated system that combines fish farming and plant cultivation in a mutually beneficial ecosystem. In this system, plants utilize nutrients produced from fish waste, while also helping to maintain water quality. However, farmers often face difficulties in managing water pH and feeding fish due to their busy schedules or other activities. And also excess feeding can accelerate changes in pond pH. This is because the remaining uneaten feed will decompose in the water, resulting in ammonia compounds that have the potential to increase the pH in the pond. Therefore, this research aims to design an automated device to regulate feeding and control water pH. Arduino is used as the central controller to manage sensors and automate the system. Water quality is measured using a pH sensor with an accuracy level of 95%. The pH control system in fish ponds functions to maintain water quality at the optimal range for fish health. Feeding is carried out according to a set schedule, and the feed throwing distance is adjusted based on voltage. The results of this system show that water pH remains stable, fish and plants are in good condition, and it helps farmers easily maintain water quality and nutrients for both fish and plants. Thus, this device can provide a practical solution for farmers needing automation in the aquaponics process.

Page 58 of 80 | Total Record : 795

 56   57   58   59   60 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol 7 No 2 (2026): January 2026 Vol 7 No 1 (2025): October 2025 Vol 6 No 4 (2025): July 2025 Vol 6 No 3 (2025): April 2025 Vol 6 No 2 (2025): January 2025 Vol 6 No 1 (2024): Oktober 2024 Vol 5 No 4 (2024): Juli 2024 Vol 5 No 3 (2024): April 2024 Vol 5 No 2 (2024): Januari 2024 Vol 5 No 1 (2023): Oktober 2023 Vol 4 No 4 (2023): Juli 2023 Vol 4 No 3 (2023): April 2023 Vol 4 No 2 (2023): January 2023 Vol 4 No 1 (2022): October 2022 Vol 3 No 4 (2022): Juli 2022 Vol 3 No 3 (2022): April 2022 Vol 3 No 2 (2022): Januari 2022 Vol 3 No 1 (2021): Oktober 2021 Vol 2 No 4 (2021): Juli 2021 Vol 2 No 3 (2021): April 2021 Vol 2 No 2 (2021): Januari 2021 Vol 2 No 1 (2020): Oktober 2020 Vol 1 No 4 (2020): JULI 2020 Vol 1 No 3 (2020): April 2020 Vol 1 No 2 (2020): Januari 2020 Vol 1 No 1 (2019): Oktober 2019 More Issue