Articles
44 Documents
Search results for
, issue
"Vol 5, No 3 (2025): September"
:
44 Documents
clear
Development of a Microservice-Based Attendance System with Face Recognition and QR Code at SMK Negeri 2 Cimahi
Riyan, Riyan;
Sugianto, Castaka Agus
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7417
Sistem absensi manual yang masih banyak digunakan di lingkungan sekolah sering menimbulkan permasalahan, seperti ketidakefisienan proses pencatatan, potensi kecurangan kehadiran, dan keterlambatan penyampaian informasi kepada pihak sekolah maupun orang tua. Penelitian ini bertujuan mengembangkan sistem absensi digital berbasis arsitektur microservice dengan mengintegrasikan teknologi pengenalan wajah (face recognition) untuk absensi harian, pemindaian kode respons cepat (quick response code) untuk absensi per mata pelajaran, serta pengiriman notifikasi otomatis melalui WhatsAppApplication Programming Interface (API). Sistem dikembangkan menggunakan metode Waterfall melalui tahapan analisis kebutuhan, perancangan sistem, implementasi, pengujian, dan pemeliharaan. Pengujian dilakukan secara langsung dengan fokus pada pengujian fungsional terhadap fitur utama yang telah dirancang. Hasil pengujian menunjukkan bahwa seluruh fitur dapat berjalan dengan baik sesuai kebutuhan pengguna, membantu proses verifikasi kehadiran menjadi lebih cepat dan akurat, serta mempercepat penyampaian informasi ketidakhadiran kepada orang tua. Penelitian ini menunjukkan bahwa implementasi arsitektur microservice efektif dalam meningkatkan kualitas sistem absensi sekolah dan memiliki prospek untuk pengembangan lebih lanjut.
Temperature, Humidity, Air Quality Monitoring System In Laying Chicken Coop Based On IoT
Firdaus, Azkha Brilliant;
Maulindar, Joni;
Muhtarom, Moh.
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7279
The health and productivity of chickens in a coop heavily depend on optimal environmental conditions, such as temperature, humidity, and air quality. The ideal temperature for laying hen coops generally ranges between 18-28℃. However, manual monitoring of coop conditions is often ineffective and requires significant resources. Therefore, this research develops a Chicken Coop Monitoring system based on the Internet of Things (IoT) to improve the efficiency of environmental supervision and maintenance within the coop. This system is designed using an ESP32 microcontroller connected to temperature, humidity, and air quality sensors, combined with an internet connection to transmit real-time data to a database storage. The collected data can be accessed via a monitoring dashboard that visually displays information on the coop's environmental conditions, including whether the temperature is within the optimal range. Testing results show that this system is capable of accurately monitoring environmental parameters, detecting non-ideal conditions, and assisting in decision-making related to coop environment regulation. By implementing this technology, chicken health and productivity can be significantly improved through more efficient and effective coop environment management.
Raw Material Stock Prediction Using the Long Short-Term Memory Algorithm
Anjarwati, Pipin;
Widyaningsih, Pipin;
Pramono, Pramono
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7199
Inaccurate management of raw material inventory leads to operational inefficiency and cost overruns in micro, small, and medium enterprises (MSMEs), particularly in the culinary industry where demand is highly fluctuating and difficult to predict. This study develops a raw material stock prediction system using the Long Short-Term Memory (LSTM) algorithm with a Waterfall system development approach, applied to the case of "Mizan and Sunan" grilled bread producers operating across seven branches. The dataset consists of nine months of historical demand data, comprising 5,142 entries with eight main attributes. Data preprocessing includes Min-Max Scaling normalization, sequential data formation using a three-day sliding window, and chronological splitting of training and testing datasets. The LSTM model is trained to predict daily stock requirements, with evaluation conducted using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results show an MSE of 403.28, MAE of 10.38, and MAPE of 10.79%, indicating good predictive accuracy. The novelty of this research lies in the application of an LSTM model based on multi-branch MSME culinary historical data characterized by fluctuating demand, along with the development of an adaptive prediction system to support precise procurement decision-making. These findings demonstrate the effectiveness of LSTM as a practical data-driven solution for inventory management in multi-branch MSME operations.
Implementation Of Static Routing And Quality Of Service For Optimization Of Network Traffic Management On Cisco Routers
Hermansyah, Hermansyah;
Khaidar, Al;
Nurdin, Nurdin;
Kurnia, Sri
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7381
Di era digital, kebutuhan akan jaringan yang andal dan efisien menjadi krusial untuk mendukung pertukaran data yang lancar. Lalu lintas data yang padat dapat menurunkan kualitas layanan, menyebabkan keterlambatan transmisi, dan meningkatkan risiko kehilangan paket. Penelitian ini mengimplementasikan metode static routing dan Quality of Service (QoS) sebagai strategi manajemen lalu lintas jaringan untuk meningkatkan efisiensi dan stabilitas komunikasi pada router Cisco. Metode yang digunakan meliputi konfigurasi static routing untuk mengatur jalur data secara manual dan penerapan QoS untuk memprioritaskan jenis layanan berdasarkan parameter latency dan packet loss. Hasil pengujian melalui simulasi dua router Cisco menunjukkan konektivitas yang stabil, dengan waktu respons rendah dan tanpa kehilangan paket signifikan. Nilai latency tercatat di bawah 150 ms dan packet loss kurang dari 1%, memenuhi kategori “Sangat Bagus” menurut standar TIPHON. Kombinasi static routing dan QoS terbukti efektif dalam mengoptimalkan manajemen lalu lintas jaringan.
Application of K-Means Clustering Algorithm for Disease Grouping at Blessing Dental Care Clinic
Fransiska, Cintiya Aulya;
Dafid, Dafid
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Blessing Dental Care Clinic is a clinic that provides dental practice services and general practitioner practices located in Palembang. This clinic offers general care and dental care managed by experienced doctors in their fields. The focus of the data used is medical record data, especially from general practice. Grouping large data into several groups based on similar pattern characteristics by utilizing the K-Means Clustering algorithm in CRISP-DM data mining was chosen to be more effective in handling various complaints of various diseases through the Clustering process. The results showed that the form of cluster 1 was 220 dominant data in the respiratory disease category, cluster 2 was 335 dominant data in the cardiovascular disease category, cluster 3 was 584 dominant data in the cardiovascular disease category, cluster 4 was 363 dominant data in respiratory disease, cluster 5 was 70 dominant data in respiratory disease, cluster 6 was 254 dominant data in cardiovascular disease and cluster 7 was 165 dominant data in ENT disease. In cluster 7 with an SSE value of 3189.16, the decrease is getting smaller and the spread pattern is starting to be optimal with a tendency for the pattern to be more spread out.
Implementation of IoT-Based Soil Moisture Monitoring System for Chili Plants
Munawaroh, Maysani;
Maulindar, Joni;
Erlinawati, Mira
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7243
Unstable soil moisture is a major challenge in chili cultivation, especially with climate change and limited water resources. To address this, the study developed an Internet of Things (IoT)-based soil moisture monitoring system with automatic irrigation. The system utilizes an ESP32 microcontroller, YL-69 moisture sensor, and the Blynk app for real-time monitoring and control via smartphone. The development followed the Waterfall method, covering requirement analysis, system design, implementation, and testing. Results showed the system accurately detects soil moisture, activates the water pump automatically based on threshold levels, and provides manual control options. The Blynk interface effectively displays real-time data, watering time, duration, and historical graphs with responsive and stable performance.
Decision Support System for Employee Performance Evaluation Using SMART Method
Romly, Moh Zaini;
Hermanto, Hermanto;
Lidimilah, Lukman Fakih
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7332
In the midst of increasingly fierce industrial competition, objectively assessing employee performance is very important to support accurate managerial decision making. This research develops a web-based Decision Support System (DSS) using the SMART (Simple Multi-Attribute Rating Technique) method to assess employee performance at the CV. Hafas P2S2 Drinking Water Factory. The main innovation of this research is the integration of the SMART method with a web interface specifically designed for small industries, the application of dynamic weights according to management priorities, and the validation of assessment results through the comparison of manual and automatic calculations, which is rarely done in previous studies. The system built with PHP and MySQL through a prototyping approach is proven to be able to assess employee performance objectively, systematically, and efficiently, and reduce subjective bias by 40% compared to manual methods.
Comparison of Container Orchestration (Local Kubernetes) and Virtualization Environment (Local Docker) in Node.js Application Management
Satria, Chiko Gita;
Krishna Yudistira, Bagus Gede
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7266
Penelitian ini membandingkan efisiensi orkestrasi container (Kubernetes lokal) dan lingkungan virtualisasi (container lokal Docker) dalam manajemen aplikasi Node.js. Dengan memanfaatkan Minikube untuk Kubernetes dan Docker langsung untuk virtualisasi berbasis container, penelitian ini mereplikasi dan menganalisis perilaku fundamental teknologi cloud-native di lingkungan lokal. Tujuan utama adalah menganalisis efisiensi orkestrasi container dibandingkan dengan implementasi virtualisasi berbasis container langsung, dengan fokus pada latensi dan throughput. Aplikasi Node.js diuji dengan tiga endpoint yang merepresentasikan beban ringan (/hello), beban CPU intensif (/load), dan latensi I/O (/sleep). Pengujian beban dilakukan menggunakan Apache JMeter dengan 1000–1500 request per menit selama 10 menit untuk setiap endpoint dan diulang lima kali. Hasil menunjukkan bahwa Docker secara umum memberikan latensi yang lebih rendah dan throughput yang lebih tinggi dibandingkan Minikube, terutama pada endpoint /hello dan /load. Hal ini mengindikasikan bahwa tanpa overhead tambahan dari lapisan orkestrasi, Docker lebih efisien untuk skenario beban ringan hingga sedang. Meskipun Minikube menyediakan fitur orkestrasi yang lengkap, ia memiliki dampak pada efisiensi. Penelitian ini menegaskan bahwa untuk pengujian lokal atau pengelolaan aplikasi skala kecil-menengah tanpa kebutuhan orkestrasi kompleks, Docker dapat menjadi pilihan yang lebih efisien.
Evaluating LMS Usability by Integrating Nielsen and Budd Principles
Maulidati, Zuli;
Meilani, Budanis Dwi;
Sodik, Anwar
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7401
ABSTRACTLearning Management Systems (LMS) are integral to modern education, supporting course delivery, student engagement, and administrative functions. Usability challenges often divert users’ focus from learning content to navigating system complexities. Heuristic evaluation (HE) has revealed persistent design and usability issues in LMS interfaces, such as poor error prevention and inadequate documentation. To address the usability issues in the LMS, this study aims to evaluate the usability of the classroom ITATS using a dual-framework approach: Jakob Nielsen’s Heuristics and Andy Budd’s Heuristics. This combined approach aims to identify interface flaws and enhance usability. Nielsen’s heuristics address universal usability principles, while Budd’s guidelines emphasize modern web design elements like responsiveness and visual hierarchy. The study is evaluated by novice evaluators who are the end users of LMS. Involving novice evaluators in this study reveals a fresh perspective which cannot be shown by the experts. The study revealed about 158 issues found by 23 novice evaluators. Those were found according to Nielsen’s and Budd’s HE within the average of severity rating about 2.52 and 2.51, respectively. Nielsen’s heuristics highlight core principles such as feedback, visibility, and error prevention, while Budd’s heuristics emphasize simplicity, consistency, and user enjoyment.
Internet of Things-Based Automation System for Watering Cayenne Pepper Plants
Akbar, Reza Maulana;
Maulindar, Joni;
Muhammad, Nibras Faiq
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30811/jaise.v5i3.7359
This study aims to build an Internet of Things (IoT)-based automatic watering system intended for cayenne pepper farmers in rural areas. The system is designed to irrigate plants automatically based on environmental parameters obtained in real-time. The hardware components consist of an ESP32 microcontroller, a DHT22 temperature and humidity sensor, a soil moisture sensor, a relay module, and a DC water pump. Sensor data are processed by the ESP32 and transmitted to a Supabase database using the HTTP protocol, then visualized through a local web-based interface. Testing results show that the system functions automatically and responsively when the soil moisture value falls below the predetermined threshold. The monitoring interface displays real-time temperature, soil moisture, and a history of recent watering activities. This system is considered effective in reducing labor and optimizing water usage, while also providing a digital solution that aligns with small-scale precision agriculture practices. Based on the results, the system is deemed feasible for implementation and further development.