Claim Missing Document
Check
Articles

Go-Gallon App With A Star (A*) Algorithm Implementation Using Android Kotlin: APLIKASI GO-GALON DENGAN PENERAPAN ALGORITMA A STAR (A*) MENGGUNAKAN KOTLIN ANDROID Andesa, Khusaeri; Herwin, Herwin; Nasution, Torkis
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 5 No. 1 (2022): Jurnal Teknologi dan Open Source, June 2022
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v5i1.2066

Abstract

The need for drinking water now is not to boil water, but to buy it in the form of gallon bottles, which are available wherever it is sold, either at the refill of water or in the supermarket. In a housing estate with many heads of families, it is also difficult to find and obtain water in gallon bottles under certain conditions, and there is also the problem that there is only one brand of gallon bottles, which also makes it difficult to obtain. For this reason, the author provides a solution by creating a go-gallon application with the application of the A-Star (A*) algorithm to be able to detect the service takers of the nearest people, which is basically intended for residential environments, where with this application others can ask to find and purchase gallons and then deliver them to their homes. The A-Star algorithm is one of the distance search algorithms that has an optimal and complete ability to solve problems related to finding or determining a route with the least distance. The hope is that with this application, especially housewives, there is no need to worry when they run out of gallons of drinking water at home, enough with this application, these problems can be overcome.
Implementation of Retrieval-Augmented Generation  Method on Large Language Model for Development of Campus Service and Information Chatbot Muhammad Dzaki Salman; Rahmaddeni; Torkis Nasution; Susanti
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/3y9hy151

Abstract

Large language models have the potential to improve the quality of information services in higher education environments through responsive and natural interactions. However, LLMs are prone to generating answers that are not supported by valid knowledge sources due to knowledge cut-off limitations. This study implements Retrieval-Augmented Generation on LLMs to build an information service chatbot for the Indonesian University of Science and Technology (USTI). RAG is built using a hybrid retrieval mechanism that combines dense retrieval and sparse retrieval (BM25) through reciprocal rank fusion and is equipped with cross-encoder reranking. The knowledge base is compiled from official and public documents obtained through the USTI website. The evaluation was conducted using 13 test queries by comparing several configurations to analyze the contribution of each component. The evaluation results show that the hybrid retrieval configuration produces the best retrieval performance with Precision@3 of 71.7%, Recall@3 of 87.5%, and NDCG@3 of 96.3%. In addition, the application of RAG improved the quality of answers compared to LLM without retrieval, as shown by an increase in BERTScore-F1 from 84.8% to 89.4% and a faithfulness score of 88.8%. These findings indicate that RAG integration improves the relevance of LLM answers to source documents, with the hybrid configuration providing an optimal balance between retrieval quality and faithfulness.
The Application of Usability Testing to Analyze the Quality of Android-Based Acupressure Smart Chair Applications M. Khairul anam; Esi Tri Emerlada; Susi Erlinda; Tashid Tashid; Torkis Nasution
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 22 No. 2 (2023)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i2.2312

Abstract

A smart chair is a reflection smart chair that utilizes waste tires as an alternative to acupuncture. Smart chairs are designed for people who are phobic about acupuncture needles by replacing these needles with waste tires. Acupuncture smart chairs also make it easier for users without having to go to the acupuncture practice place. This smart chair is equipped with an application that is directly connected to android. The smart chair application is an android-based remote control where users can control the application remotely. However, this application has not been tested so it is not yet known how effective and efficient the use of the application is. Therefore, researchers would conduct testing by using the usability testing method. The usability testing method is a method carried out to measure the ease of the application that has been made. The analysis in this method used five evaluation components, namely learnability, efficiency, memorability, errors, and satisfaction. This research would make instruments based on usability testing and then distribute instruments to samples by using sampling techniques. The results of this study showed a variable learnability value was 65% while the efficiency variable got a value of 74%. In terms of memorability, its value was 59%, then the Errors variable value was 74%, and the last variable, namely satisfaction, reached a value of 74%.
Optimasi Deteksi Intrusi Jaringan Menggunakan Hybrid Model Autoencoder dan Random Forest Nanda, Afri; Nasution, Torkis
Building of Informatics, Technology and Science (BITS) Vol 7 No 4 (2026): March 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i4.9309

Abstract

Conventional Intrusion Detection Systems often suffer from performance degradation due to their inability to handle the complexity of high-dimensional data and class imbalance in modern network traffic. This study aims to optimize the Network Intrusion Detection System (IDS) by addressing the limitations of the Random Forest algorithm in handling high-dimensional data and its lack of model transparency (black-box). The proposed method is a Hybrid model integrating an Autoencoder as a non-linear feature extractor and Random Forest as a classifier. The Autoencoder is trained using a semi-supervised strategy to generate latent features and Reconstruction Error (MSE), which serves as a robust anomaly indicator. Additionally, the Synthetic Minority Over-sampling Technique (SMOTE) is applied to address class imbalance in the NSL-KDD dataset. To address the challenge of interpretability, SHAP-based Explainable AI (XAI) is strategically implemented to elucidate the complex interactions between the Autoencoder-compressed latent features and the final classification decisions, thereby transforming this hybrid architecture into a transparent system. Evaluation results demonstrate that the Hybrid Autoencoder-Random Forest model outperforms the Random Forest Baseline, achieving an Accuracy increase of 2.54% (to 77.61%) and a Recall increase of 3.96% (to 62.31%). The significant improvement in the Recall metric empirically validates the effectiveness of hybrid features, specifically the Reconstruction Error, in detecting Zero-Day attacks characterized by unknown patterns. Furthermore, SHAP visualization successfully reveals the contribution of latent features, providing crucial transparency for network security forensic analysis.
Pengembangan Konten Multimedia Untuk Sosialisasi Strategi Pemasaran Umkm Melalui Aplikasi Grabmart Di Desa Tarai Bangun Aurelia, Zahra Nur; Nasution, Torkis; Muzawi, Rometdo; Haryono, Dwi
Journal of Authentic Research Vol. 4 No. 2 (2025): December
Publisher : LITPAM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/h4q7sw80

Abstract

Penelitian ini bertujuan untuk mengembangkan konten multimedia yang efektif untuk sosialisasi strategi pemasaran bagi pelaku UMKM di Desa Tarai Bangun melalui pemanfaatan aplikasi GrabMart. Sebelum intervensi dilakukan, kondisi UMKM di Desa Tarai Bangun menunjukkan tingkat adopsi teknologi yang masih rendah; sebagian besar pelaku UMKM belum memahami cara memanfaatkan platform digital, menghadapi hambatan seperti kurangnya literasi digital, minimnya pemahaman tentang pemasaran online, serta keterbatasan akses terhadap panduan praktis penggunaan aplikasi GrabMart. Untuk menjawab kebutuhan tersebut, penelitian ini mengembangkan beberapa jenis konten multimedia, yaitu video tutorial langkah demi langkah penggunaan GrabMart, infografis tentang strategi pemasaran digital, serta modul PDF interaktif sebagai panduan lengkap. Konten tersebut didistribusikan melalui platform yang mudah diakses oleh UMKM, seperti YouTube, WhatsApp Group komunitas UMKM, dan Google Drive. Metode penelitian menggunakan pendekatan Research and Development (R&D), dengan tahapan meliputi analisis kebutuhan, desain, pengembangan konten, serta uji coba kepada pelaku UMKM di Desa Tarai Bangun. Data diperoleh melalui wawancara, survei, dan observasi untuk menilai perubahan pemahaman peserta setelah mengikuti sosialisasi. Hasil uji coba menunjukkan peningkatan signifikan dalam pemahaman pengguna, ditunjukkan melalui skor Mean Opinion Score (MOS) sebesar 84,96%, yang menandakan bahwa konten multimedia yang dikembangkan efektif dan mudah dipahami. Penelitian ini menyimpulkan bahwa pengembangan konten multimedia dapat meningkatkan literasi digital pelaku UMKM di Desa Tarai Bangun dan membantu mereka mengimplementasikan strategi pemasaran digital secara mandiri melalui GrabMart, sehingga berpotensi meningkatkan jangkauan dan keberhasilan pemasaran produk mereka.