cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Safriadi
Contact Email
safriadi@pnl.ac.id
Phone
+6285262485087
Journal Mail Official
jaise@pnl.ac.id
Editorial Address
Jl. Banda Aceh-Medan Km. 280,3, Buketrata, Mesjid Punteut, Blang Mangat, Kota Lhokseumawe, 24301
Location
Kota lhokseumawe,
Aceh
INDONESIA
Journal Of Artificial Intelligence And Software Engineering
Published by Politeknik Negeri Lhokseumawe
ISSN : 2797054X     EISSN : 2777001X     DOI : http://dx.doi.org/10.30811/jaise
Core Subject : Science,
Computer Science & IT
Artificial Intelligence Natural Language Processing Computer Vision Robotics and Navigation Systems Decision Support System Implementation of Algorithms Expert System Data Mining Enterprise Architecture Design & Management Software & Networking Engineering IoT
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 44 Documents
 1   2   3   4   5 
Search results for , issue "Vol 5, No 3 (2025): September" : 44 Documents clear
Sentiment Analysis Of Reading Difficulties In Grade 7 Secondary School Students Using The Support Vector Machine (SVM) Algorithm Algipari, Rasyid Zanuar; Tresnawati, Shandy
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.v5i3.7289

Abstract

The reading ability of junior high school students in Indonesia is still relatively low, as evidenced by the results of the National Assessment and the viral case of 29 grade VII junior high school students in Pangandaran who are not yet fluent in reading. This study aims to analyze public perception of this phenomenon through a sentiment analysis approach based on YouTube comment text and using the Support Vector Machine (SVM) algorithm. The steps of the SEMMA method are applied, starting with collecting comment data, preprocessing the text using dictionary-based methods and TF-IDF, and finally classification using SVM. The dataset used includes 1,055 comments. The results of the study show that the SVM algorithm is able to classify sentiment into three categories (positive, negative, and neutral) with an accuracy of 87%. These results indicate that the majority of people care about the quality of basic education. This study contributes to the computational understanding of public perception and can be used as a reference for data-based literacy guidelines.
Implementation of a Food Menu Recommendation System at Ndalem Uti Restaurant Using Collaborative Filtering Based on User Preferences Rhemadanu, Andreas; Susanto, Rudi; Asri, Anindhiasti Ayu Kusuma
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.v5i3.7119

Abstract

This study aims to implement a menu recommendation system at Ndalem Uti Restaurant using a Collaborative Filtering approach based on user preferences. The main problem faced is that customers have difficulty choosing the best-selling menu because of the many choices and minimal information regarding the popularity of each menu. To overcome this, the Collaborative Filtering method is used with the User-Based Cosine Similarity calculation to measure the similarity of preferences between users. The test results show that the recommendation accuracy level reaches 96%, including for new users. This system is able to provide more personalized menu recommendations based on customer order history and ratings. This implementation is expected to improve user experience, optimize sales, and be a solution for the development of culinary businesses in the future.
Sentiment Analysis of Netizen Opinions on TikTok Towards iPhone Using Naïve Bayes Algorithm and Support Vector Machine (SVM) Pebriana, Sela; 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.v5i3.7011

Abstract

This study aims to analyze TikTok users’ sentiment toward the iPhone by utilizing TikTok comments as the primary data source. TikTok was chosen due to its high user engagement and ease of access to spontaneous public opinions. A total of 964 comments were collected and processed through a data cleaning stage. The sentiments were classified into positive and negative categories using two popular machine learning algorithms: Naïve Bayes and Support Vector Machine (SVM). This comparison was conducted to evaluate the effectiveness of each algorithm in handling local social media data, which is typically brief and unstructured. The results show that Naïve Bayes achieved an accuracy of 74%, while SVM reached 71%. These findings indicate that Naïve Bayes performs better in fast sentiment analysis of short-text public opinions and has practical potential for monitoring consumer perception and supporting efficient digital marketing strategies.
Analysis Of Customer Understanding Level Of The E-Policy System In The Sinar Mas Online Insurance Application In The Lhokseumawe Branch Work Area Muliana, Syarifah; Nurdin, Nurdin; Alqhifari, Azka; Khaidar, Al; Jessika, Jessika
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.v5i3.7824

Abstract

Digital transformation in the insurance industry is driving companies to adopt electronic systems, including the implementation of e-policies as a replacement for physical policy documents. This study aims to analyze the level of customer understanding of the e-policy system on the Sinar Mas Online Insurance application in Lhokseumawe branch. The research method used is a quantitative approach with data collection techniques through distributing questionnaires to 100 active customers. The results show that most customers are aware of the existence of e-policies, but still face obstacles in understanding their functions, legality, and how to access documents through the Sinar Mas Online application. Factors such as age, education level, and experience using digital services have been shown to influence the level of customer understanding. This study recommends the need for continuous education and the development of a more intuitive application interface to improve digital literacy and user convenience in accessing e-policies. These findings are expected to provide evaluation material for companies in improving their information systems and digital communication strategies for customers.
Enhancement of Rivest Shamir Adleman (RSA) Key Generation Utilizing the Diffie-Hellman Algorithm for PDF File Security Murti, Maliyah; Rahmadani, Rahmadani; Puspadini, Ratih
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.v5i3.7629

Abstract

The development of digital technology poses challenges to data security, especially in frequently used PDF files. Cryptography can be used for data security. The conventional RSA algorithm with a static public key is vulnerable to attacks. This study integrates Diffie-Hellman to generate a shared key as a public exponent (e) in RSA, making key generation more dynamic and secure. The method includes system analysis, a combined implementation of Diffie-Hellman and RSA, and testing on PDF files. Data is converted to decimal numeric format before encryption and decryption. The encryption is stored in (*.txt), decryption returns the file to the original PDF. The results show that the use of a shared key improves security even though the encrypted file size increases by about 4-5 times from the original file. This system is expected to be a better solution for PDF security and modern cryptography.
Air Temperature and Humidity Monitoring System for Oyster Mushroom Cultivation Ardani, Hasby Arif; Maulindar, Joni; Indah, Ratna Puspita
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.v5i3.7348

Abstract

Oyster mushroom cultivation demands the stability of the microenvironment, especially in the aspects of temperature and humidity in the barn space. Manual monitoring methods that are still commonly used are often less responsive and inefficient in capturing real-time changes in conditions. To answer these problems, this research designs and builds an Internet of Things (IoT)-based monitoring system integrated with the Ubidots platform as a control center and data visualization. This system is able to read and send precise temperature and humidity data using the Hypertext Transfer Protocol (HTTP) protocol. This system uses the DHT22 sensor which is more accurate than previous studies that generally use the DHT11 sensor. The test results show that the system works responsively, stably, and accurately in presenting real-time environmental data, with a temperature reading error rate of about ±0.5°C and ±5% humidity. The implementation of the system at the oyster mushroom cultivation site in Jonggrangan Village, Klaten Utara, proved its effectiveness in helping farmers monitor and maintain mushroom growth conditions remotely in an efficient and sustainable manner.Oyster mushroom cultivation demands the stability of the microenvironment, especially in the aspects of temperature and humidity in the barn space. Manual monitoring methods that are still commonly used are often less responsive and inefficient in capturing real-time changes in conditions. To answer these problems, this research designs and builds an Internet of Things (IoT)-based monitoring system integrated with the Ubidots platform as a control center and data visualization. This system is able to read and send precise temperature and humidity data using the Hypertext Transfer Protocol (HTTP) protocol. This system uses the DHT22 sensor which is more accurate than previous studies that generally use the DHT11 sensor. The test results show that the system works responsively, stably, and accurately in presenting real-time environmental data, with a temperature reading error rate of about ±0.5°C and ±5% humidity. The implementation of the system at the oyster mushroom cultivation site in Jonggrangan Village, Klaten Utara, proved its effectiveness in helping farmers monitor and maintain mushroom growth conditions remotely in an efficient and sustainable manner.
Mobile Application Development For Digitalization In The Service Sector “ReHome” Alfarizi, Muhammad Fadhillah; Nasir, Muhammad
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.v5i3.7128

Abstract

This research presents the development of ReHome, an Android-based mobile application designed to support the digitalization of architectural design services. The application provides various features that enable users to access house designs, save references, and communicate directly with architects. ReHome was developed using the Rapid Application Development (RAD) methodology to ensure rapid and adaptive system development according to user needs. The application interface was designed using Figma and implemented in Android Studio environment with Java/Kotlin programming languages, integrated with Firebase for authentication and data storage. The application features include user login and registration, main dashboard with design categories and search functionality, detailed house design views, user-architect communication system, architect portfolio management, and admin dashboard for design verification. Testing was conducted using black box testing methods for functional validation. The results show that ReHome successfully achieves its main objective of supporting the digitalization of the architectural design service industry by providing an efficient, modern, and interactive platform. The application enables users to access house design services efficiently while allowing service providers to reach more clients through digital platforms. ReHome demonstrates the practical application of digitalization concepts in the Industry 4.0 era and has great potential for further development with additional features such as integrated service booking systems and more complex admin dashboards.
Comparative Analysis of Random Forest Algorithms, Artificial Neural Networks, and Logistic Regression in Breast Cancer Prediction with Machine Learning Approach M. Ali, Rahmadi; Nurdin, Nurdin; Khaidar, Al; Azzanna, Maghriza; Rusadi, Athirah
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.v5i3.7028

Abstract

Perkembangan teknologi informasi khususnya kecerdasan buatan dan machine learning, telah meningkatkan efektivitas deteksi dini penyakit seperti kanker payudara. Namun, tingginya angka kejadian dan kematian akibat kanker payudara di Indonesia masih menjadi tantangan besar, terutama karena rendahnya tingkat deteksi dini dan banyak pasien datang dalam stadium lanjut. Penelitian ini membandingkan performa tiga algoritma machine learning, yaitu Random Forest, Artificial Neural Network (ANN), dan Logistic Regression, dalam memprediksi diagnosis kanker payudara berdasarkan akurasi, efisiensi komputasi, dan kestabilan kinerja. Evaluasi dilakukan dengan classification report dan validasi silang 10-Fold Cross Validation. Hasil menunjukkan Logistic Regression memiliki akurasi rata-rata tertinggi sebesar 77,56% dan waktu eksekusi tercepat, yaitu 0,024897 detik, menandakan efisiensi dan kestabilan yang baik. Random Forest memberikan akurasi classification report 80% dan nilai AUC tertinggi 0,89, menunjukkan keunggulan dalam diskriminasi kelas. ANN memiliki performa terendah dengan akurasi validasi silang 74,64% dan recall rendah untuk kelas positif. Logistic Regression direkomendasikan sebagai model paling seimbang, sementara Random Forest sebagai alternatif akurasi tinggi.Kata Kunci: Random Forest, Artificial Neural Networks, Logistic Regression, Breast Cancer Prediction, Machine Learning
Implementation of the Analytic Hierarchy Process Method for Performance-Based Rewards for Lecturers Ruskan, Endang Lestari; Seprina, Iin; Ariani, Ardina; Indah, Dwi Rosa; Athalina, Githa
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.v5i3.7600

Abstract

Rewards are carried out by the faculty as an effort to motivate lecturer performance. The obstacle is that the system has not accommodated all lecturer performance on the required indicators, the supporting files are also a problem, and the final results of many performance scores are the same, potentially due to subjective decision-making. There is no scientific formulation, no common standard, and no direct file collection system as the cause. The research method used is identifying problems and collecting data, analyzing data, designing decision support systems, and making prototypes. The research objective is to apply the analytical hierarchical process method to the application of a decision support system for determining lecturer rewards.  The contribution of research on performance-based criteria instruments applied to dynamic applications in determining indicators, so that they can be adjusted to the performance report indicators of higher education institutions. The results are in the form of lecturer performance criteria weights based on key performance. The highest lecturer performance ranking is 0.0880, the second is 0.067, and the third is 0.0663, with detailed lecturer performance scores for each criterion. These digital files can be used at any time, helping management make objective and transparent decisions.
IoT-Based Real-Time Security System Implementation at Kaka Game Center Internet Café Prastya, Alvian Bagus; Maulindar, Joni; Purwanto, Eko
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.v5i3.7327

Abstract

Security in public spaces such as internet cafés (warnet) is a major concern, especially during non-operational hours. This study develops a real-time security system based on the Internet of Things (IoT) by integrating the ESP32 and ESP32-CAM microcontrollers to enhance surveillance effectiveness in warnet environments. The system uses a PIR sensor to detect motion, then automatically sends a notification to the Telegram application and triggers image capture via the ESP32-CAM. In addition to automatic detection, users can also manually control the system via Telegram, such as activating the buzzer, requesting snapshots, or accessing real-time video streaming using ngrok. The system was developed using the Waterfall method, which includes requirement analysis, design, implementation, and testing. The results show that all system features operate properly, are responsive, and support efficient remote monitoring. With its low cost and optimal technology integration, the system is a viable alternative to conventional security systems for small-scale businesses.

Page 4 of 5 | Total Record : 44

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 5, No 4 (2025): Desember (On Progress) Vol 5, No 3 (2025): September Vol 5, No 2 (2025): Juni On-Progress Vol 5, No 2 (2025): June Vol 5, No 1 (2025): March Vol 5, No 1 (2025): Maret Vol 4, No 2 (2024) Vol 4, No 1 (2024) Vol 3, No 2 (2023) Vol 3, No 1 (2023) Vol 2, No 2 (2022) Vol 2, No 1 (2022) Vol 1, No 2 (2021) Vol 1, No 1 (2021) More Issue