Articles
Deteksi Microsleep Menggunakan Convolutional Neural Network Dengan Sensor ESP32 Pada Pengemudi
Akbar, Yuma;
Bintoro, Bayu;
Mulyana, Dadang Iskandar;
Lestari, Sri
INTECOMS: Journal of Information Technology and Computer Science Vol 7 No 5 (2024): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31539/intecoms.v7i5.12142
Microsleep merupakan kondisi berbahaya yang terjadi ketika seseorang tertidur dalam waktu sangat singkat tanpa disadari, terutama saat mengemudi. Skripsi ini bertujuan mengembangkan sistem deteksi Microsleep berbasis Convolutional Neural Network (CNN) dengan sensor ESP32 pada pengemudi. Sistem ini dirancang untuk memantau dan menganalisis pola aktivitas pengemudi secara langsung yang dikumpulkan oleh sensor ESP32. Data yang diperoleh kemudian diproses dan diklasifikasikan menggunakan model CNN untuk mendeteksi kejadian Microsleep. Implementasi sistem ini diharapkan dapat meningkatkan keselamatan berkendara, sehingga dapat mengurangi risiko kecelakaan lalu lintas. Penelitian lebih lanjut diperlukan untuk meningkatkan akurasi deteksi dan menguji sistem pada kondisi nyata di jalan raya. hasil pengolahan data dan hasil pembahasan pada penelitian ini, dapat ditunjukkan bahwa arsitektur convolutional neural network (CNN) dengan algoritma you only look once (YOLO) dapat diimplementasikan untuk melakukan deteksi pada pengemudi apakah terjaga atau tertidur. Selain itu dengan melakukan konfigurasi parameter model dengan batch size 16, network size 320x320, diperoleh nilai IoU dengan learning rate 0.01.
Classification of Customer Satisfaction with the K-Nearest Neighbor Algorithm in Relation to Employee Performance at PT. Airkon Pratama
Suprianto, Ahmad;
Surapati, Untung;
Akbar, Yuma;
Hidayat, Aditya Zakaria
International Journal Software Engineering and Computer Science (IJSECS) Vol. 4 No. 3 (2024): DECEMBER 2024
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v4i3.2948
PT. Airkon Pratama is the technical consultancy company in the field of maintenance, repair, and operate system. Among its projects are a four-building, multi-story tax office complex. PT. Airkon Pratama experience obstacles to know how its customer satisfaction with their services that is was measured by a questionnaireobtained from work order form. The purpose of this study is to determine how well K-Nearest Neighbor data classification accurately classifies customer satisfaction based on employee performance by PT. Airkon Pratama. The data used in this study is from PT. Airkon Pratama with the data processing using RapidMiner with the K-Nearest Neighbor method which produces an accuracy of 96.53%. Among them four performance indicators were rated as "good", and two as "adequate". Of the 196 that were correctly predicted to be "good," three were "adequate." Most of the 04 respondents gave a positive response indicating their satisfaction with the management of tax office facilities provided by PT. Airkon Pratama in January 2024.
2D Platformer Game Prototype on Indonesian History Using Scratch
Akbar, Yuma;
Al Ammaar, Mohammad Farroos
International Journal Software Engineering and Computer Science (IJSECS) Vol. 4 No. 3 (2024): DECEMBER 2024
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v4i3.3070
In this study, we would like to share a prototype of a 2D platformer game in Scratch centered on the development of Indonesian history that can increase students' interest and motivation in learning history. In search of a more entertaining and successful alternative to the bad lecture situation, the demand for interactive learning media. Visual programming is chosen with Scratch because it is easier to create educational games in this language. Its creation involves the implementation of visual components such as characters, background environments, UI, etc. Data Evaluation provides a positive level of acceptance to students with an average student evaluation score of 4.1/5 Positive responses were obtained for game elements, story content, and ease of operation First, the results of the evaluation of the Validation of 2D Platformer Games in Indonesian History as a Learning Tool. Through student activeness, a more active way of responding to historical material is being implemented by use. Game development has the ability to become a new educational media if it is well structured and organized.
Sentiment Analysis of Social Media X Users Towards Legislators Engaged in Online Gambling Using Naïve Bayes Algorithm
Nurmaylina, Vivi;
Akbar, Yuma
International Journal Software Engineering and Computer Science (IJSECS) Vol. 4 No. 3 (2024): DECEMBER 2024
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v4i3.3079
This research analyzes public feelings toward legislative members participating in online gambling applying the Naïve bayes classification technique. The collected data were processed, labeled, cleaned, preprocessed, and classified using RapidMiner Studio software, while conducting the sentiment analysis according to a systematic approach from each of those steps described above, namely, data crawling, cleaning, preprocessing, and classification of the Twitter data. Sentiment distribution yielded 286 negative and 90 positive sentiments with a prediction accuracy of 73.10%. These findings illustrate an overwhelmingly negative public response to this behavior and the expectation society has for legislators as public figures.
Analisis Clustering Penyakit Menular pada Manusia di Jakarta Timur Menggunakan Algoritma K-Means
Ramadhan, Muhammad Arya;
Poerwandono, Edhy;
Akbar, Yuma;
Hidayat, Aditya Zakaria
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/jtik.v9i1.3007
Humans are highly susceptible to various diseases without realizing their causes. The high incidence of infectious diseases in East Jakarta requires an analysis of distribution patterns to determine intervention priorities. This study aims to identify clusters of infectious diseases in East Jakarta, helping authorities plan effective prevention and treatment strategies. Data on infectious disease cases were obtained from the Central Statistics Agency of DKI Jakarta. The K-Means algorithm was used to cluster data based on variables such as period, region, type of disease, and number of cases. The results indicate several main clusters with distinct characteristics that can serve as a foundation for targeted strategies. From 2018 to 2021, diarrhea was predominant, making up 84.14% of cases in 2018 and 81.97% in 2019, pneumonia accounted for 32.92% in 2020, and TB Paru 33.63% in 2021. In conclusion, the K-Means algorithm effectively clusters infectious disease data and provides useful insights into disease distribution in East Jakarta, improving the impact of data-driven health programs.
Implementasi Game 2D Edukasi Pengetahuan Islam untuk Remaja Menggunakan Unity
Akbar, Yuma;
Albahy, Abdurrahman Asyam
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/jtik.v9i1.3019
This research aims to address the lack of interest among children in learning basic Islamic knowledge through conventional learning methods, which are often perceived as boring. The proposed solution is the development of Unity-based educational 2D games that present basic Islamic knowledge in an engaging and interactive way. The target audience for this research is children aged 12–15 years, who are expected to show greater interest and motivation to learn Islam through more enjoyable media. The methodology employed in this research is the Waterfall method, consisting of the stages of needs analysis, system design, implementation, verification, and maintenance. The tools used include Unity software for game development and Visual Studio for C# coding. The study also utilized surveys and observations to measure the game's effectiveness in enhancing children's knowledge and engagement. Through efficient project management, it is anticipated that this educational game will become an effective and engaging learning tool for children, while contributing significantly to the field of Islamic religious education.
Optimasi Gigabit Passive Optical Network dan Algoritma Naïve Bayes dalam Analisis Jaringan FTTH
Suwandi;
Akbar, Yuma;
Mulyana, Dadang Iskandar
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/jtik.v9i1.3058
Internet service users expect reliable bandwidth quality to support the communication access process. From year to year, human needs for communication services continue to increase. Humans still want convenience in daily activities such as sending messages, video and voice, and want the quality of sending and receiving messages to be fast. This encourages telecommunications service providers to focus on innovative telecommunications networks to meet the needs of all customers. Research began by taking data at Tablue and AVS regarding the distance of the fiber cable used as far as 10Km from the OLT. Manual calculations using OTDR. The results of previous measurements and data processing regarding the attenuation obtained in fiber cables are followed by calculating the total attenuation using the existing formula. The next stage is data processing using RapidMiner software with the Naive Bayes algorithm. The final results of the comparison with this test method, namely the prediction results) show an accuracy value of 99.91%. Of the 1124 test data, 1080 data were predicted as OK sentiment and 43 data as Not OK. For prediction results from Not ok. and the Naive Bayes method shows an accuracy value of 0.962% OK. Not ok 0.038% of 1124, test data.
Optimasi Jaringan Sensor Nirkabel untuk Monitoring Suhu dan Kelembaban
Akbar, Yuma;
Abror, Ikhsan
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/jtik.v9i1.3066
The development of Internet of Things (IoT) technology has provided new opportunities to improve monitoring through the integration of temperature and humidity sensors in wireless networks. This study aims to optimize a wireless sensor network for temperature and humidity monitoring. This study combines an experimental approach with network performance analysis and optimization methods. First, the selection of temperature and humidity sensors is carried out. Next, an efficient and reliable wireless sensor network architecture is designed to collect temperature and humidity data from various locations. The process of sending data from sensors to base stations and integration with IoT platforms are also studied. Furthermore, a series of experiments are conducted to test the performance of the wireless sensor network under real conditions. Analysis of the collected data is used to identify potential improvements in network performance and improve system reliability and responsiveness. The performance parameters evaluated include connection stability, data throughput, energy consumption, and communication latency. The results of this study contribute to the development of a monitoring system that is reliable, efficient, and easy to implement.
Otomasi Backup Konfigurasi Settingan Router Mikrotik Menggunakan Ansible dengan Metode Network DevOps: Automation of Mikrotik Router Setting Configuration Backup Using Ansible with Network DevOps Method
Zulfikar, Ahmad;
Akbar, Yuma
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 1 (2025): MALCOM January 2025
Publisher : Institut Riset dan Publikasi Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.57152/malcom.v5i1.1591
Di era teknologi informasi saat ini, akses data melalui jaringan komputer menjadi krusial bagi aktivitas sehari-hari dan kebutuhan perusahaan. PT Fcom Inti Teknologi, sebagai penyedia layanan jaringan, menghadapi tantangan dalam mengelola infrastruktur jaringan yang luas dan kompleks. Metode manual yang digunakan untuk backup konfigurasi perangkat jaringan tidak hanya memakan banyak waktu dan tenaga, tetapi juga rentan terhadap kesalahan manusia yang dapat menyebabkan downtime jaringan. Penelitian ini bertujuan untuk mengimplementasikan solusi automasi menggunakan Ansible dengan metode Network Development Operations (NetDevOps) guna meningkatkan efisiensi dan keandalan proses backup konfigurasi di PT Fcom Inti Teknologi. Automasi jaringan diharapkan dapat menyediakan cara yang lebih efisien dan andal dalam mengelola konfigurasi dan backup perangkat jaringan, serta mengurangi waktu dan tenaga yang dibutuhkan untuk tugas-tugas manual. Hasil penelitian menunjukkan bahwa implementasi sistem automasi untuk backup dan konfigurasi Mikrotik berhasil dilakukan, yang berdampak pada pengurangan kesalahan konfigurasi, dan meningkatkan efisiensi waktu dalam pengaturan router Mikrotik. Automasi jaringan tidak hanya meningkatkan konsistensi konfigurasi, tetapi juga meminimalkan risiko kesalahan dan downtime jaringan. Simpulan dari penelitian ini adalah bahwa dengan mengadopsi alat automasi seperti Ansible, PT Fcom Inti Teknologi berhasil meningkatkan ketersediaan dan keandalan jaringan mereka, sehingga dapat memberikan layanan yang lebih baik kepada pelanggan.
Implementation of RFM Analysis to Enhance Sales Patterns of Food and Beverages at Bonjour Café and Resto Using the Apriori Algorithm
Sibarani, Julvan Marzuki Putra;
Akbar, Yuma;
Sutisna;
Setiawan, Kiki
International Journal Software Engineering and Computer Science (IJSECS) Vol. 4 No. 3 (2024): DECEMBER 2024
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v4i3.3073
The rapid growth of the culinary business has made business competition in this field increasingly tight, so a strategy is needed to increase food and beverage sales patterns. Bonjur Cafe Resto serves many food and beverage menus, but business actors need to try to produce product innovations in order to provide satisfactory service to customers. In this condition, a data processing technique is needed to determine customer segmentation and menu recommendations at Bonjur Cafe Resto. The analysis method used is RFM Analysis by analyzing customer behavior, analyzing purchase transaction data consisting of Recency Frequency Monetary (RFM) attributes and data mining techniques with the Apriori algorithm, where this algorithm is used to determine the most frequently appearing data set (frequent itemset). The results of this study are grouped into five categories of customers based on their purchasing behavior and association rules are formed with predetermined parameters, support 28% and confidence 70%. This can later be a recommendation for a menu combination from the data that has been collected and applied using the apriori algorithm so that it is expected to be used for service evaluation and be able to increase customer satisfaction so that Bonjur Cafe Resto can develop better