Article Per Year (5 Year)
p-Index From 2021 - 2026
1.607
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Rekayasa Perangkat Lunak E-Link: Jurnal Teknik Elektro dan Informatika Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) Journal of Artificial Intelligence and Engineering Applications (JAIEA) Jurnal Manajemen Informatika & Teknologi Jurnal Manajemen Dan Bisnis Ekonomi Sintek Kuwera
Bani Nurhakim
Unknown Affiliation
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Energy

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
CLUSTERING KEJADIAN BENCANA ALAM di JAWA BARAT BERDASARKAN JENIS BENCANA MENGGUNAKAN K-MEANS Indah Rosaliyah; Bani Nurhakim
E-Link: Jurnal Teknik Elektro dan Informatika Vol 18 No 1 (2023): Mei 2023
Publisher : Universitas Muhammadiyah Gresik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30587/e-link.v18i1.5318

Abstract

Jawa barat merupakan salah satu wilayah dengan potensi bencana alam tinggi. Hampir semua jenis bencana sudah terjadi di setiap wilayahnya, seperti gempa bumi, tanah longsor, banjir, dan masih banyak lagi. Oleh karena itu, informasi mengenai tingkat terjadinya bencana alam di berbagai wilayah harus diteliti lebih lanjut agar lebih waspada kedepannya. Penelitian ini bertujuan untuk mengelompokkan kejadian bencana alam di Jawa Barat berdasarkan jenis bencana dengan memanfaatkan teknik clustering pada data mining. Proses pengelompokan data dilakukan menggunakan metode algoritma K-Means dan tahap perancangan yang digunakan yaitu Knowledge Discovery in Database (KDD). Dengan menggunakan tools RapidMiner diperoleh 6 cluster dengan nilai Davies Bouldin Index yaitu 9.20. Cluster 3 merupakan daerah dengan kejadian bencana alam sangat rendah, cluster 1 daerah dengan kejadian bencana alam rendah, cluster 4 daerah dengan kejadian bencana alam sedang, cluster 0 daerah dengan kejadian bencana alam tinggi 1, cluster 5 daerah dengan kejadian bencana alam tinggi 2, dan cluster 2 merupakan daerah dengan kejadian bencana alam sangat tinggi.
Analisis Tingkat Penggunaan Gadget pada Anak Usia Dini dengan menggunakan K-Mean Khaerul Anam; Rizal Rusyana; Bani Nurhakim; Denni Pratama
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol 6, No 1 (2024): Maret
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jinrpl.v6i1.10317

Abstract

The use of gadget devices in early childhood has become an increasing concern in recent years. influence on human thinking patterns because devices can find data quickly for children. Research on the consequences of using gadgets in early childhood has its own significance in understanding its impact on their development. In this study, an analysis was carried out on the level of gadget use in early childhood by applying the K-Means algorithm. The K-Means algorithm is used to group the level of gadget use in children, allowing the identification of groups that have similar characteristics. The aim of this research is to evaluate and understand the level of gadget usage by young children in response to technological developments, as well as to develop an effective method or approach in classifying their gadget usage patterns by utilizing the K-Means algorithm. Thus, this research aims to provide in-depth insight into gadget use patterns in young children, which can be the basis for developing better strategies or policies regarding technology use in this age group. From a total of 332 questionnaire responses, 14 groups were found based on the best DBI scores with different category distributions, namely "very often", "often", "sometimes", "rarely", and "never" with each percentage of 1 % (2 people), 24% (80 people), 0%, 71% (235 people) and 5% (15 people).
Implementasi Data Mining FP-Growth Untuk Analisis Pola Pembelian Pada Transaksi Penjualan Komariyah, Siti; Saeful Anwar; Bani Nurhakim
JURNAL MANAJEMEN DAN BISNIS EKONOMI Vol. 1 No. 2 (2023): April : JURNAL MANAJEMEN DAN BISNIS EKONOMI
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (405.814 KB) | DOI: 10.54066/jmbe-itb.v1i2.128

Abstract

In the business world, efforts are needed as much as possible in gaining profits. The accuracy of marketing strategies can be seen from the consumer spending pattern database obtained from sales transactions on fashion products that are usually purchased simultaneously by customers. Information about the Pattern of Purchasing Customer Shopping that is Inaccurate at the Ayu Collection Online Shop Shop has caused promotional policy to be one of the causes of the store to suffer losses. One way to get an accurate customer shopping pattern is to use data mining. One of the methods contained in data mining is the association analysis method, in the association analysis there are several algorithms, one of which is the FP-Growth algorithm. In this study several association rules were found by applying the Frequent Pattern (FP-Growth) algorithm from the transaction database Fashion sales at Ayu Collection Online Shop. This association rules will later be used as decision making material to develop successful marketing and sales strategies. The findings of this study are in the form of product recommendations, namely the proposal of two or more items based on the findings of the FP-Growth algorithm using a 50% confidence value and a minimum support of 40%, this study uses assistance from the rapidminer tools version 9.9.
Bibliometrik Analisis: Brand Awareness Program Studi Diploma 3 Pada Database Scopus Bani Nurhakim; Dadang Sudrajat
Prosiding SISFOTEK Vol 8 No 1 (2024): SISFOTEK VIII 2024
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research aims to analyze the factors influencing brand awareness in the Diploma 3 program and to develop effective marketing strategies to enhance that awareness. The background of this study is based on the importance of brand awareness in influencing prospective students' decisions and public perception of the quality and reputation of educational institutions. This research employs survey and interview methods involving students, prospective students, and marketing staff from several higher education institutions in Indonesia. The data obtained were analyzed using statistical methods to identify the main factors affecting brand awareness. The results indicate that digital marketing and social media marketing play a significant role in increasing brand awareness of the Diploma 3 program. Consistent, innovative, and effective marketing strategies through social media have been proven to enhance recognition and appeal of the study program in the eyes of prospective students. This research makes an important contribution to the development of educational marketing strategies and offers new approaches to enhancing brand awareness of the Diploma 3 program. Thus, the results of this study are expected to assist educational institutions in increasing enrollment and retaining students by improving effective brand awareness
Klasifikasi Telur Fertil dan Infertil Berbasis Hybrid MobileNetV3 dengan Mekanisme Attention dan Texture Fusion Bani Nurhakim; Dadang Sudrajat; Tati Suprapti; Ade Rizki Rinaldi; Agus Bahtiar
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Accurate fertile-infertile egg classification is crucial to improve hatching productivity and sorting efficiency. This study proposes MobileFusionV3, a MobileNetV3 architecture enriched with CBAM (Convolutional Block Attention Module) and Hybrid Texture Fusion (LBP and GLCM) to combine deep and texture features to be more robust to candling illumination variations. A dataset of 1,275 candling images (675 fertile, 600 infertile) was subjected to preprocessing (resizing, normalization, background enhancement) and realistic data augmentation (rotation, brightness/contrast changes, Gaussian noise, illumination variations). The model was trained using transfer learning, early stopping, and an evaluation scheme based on accuracy, precision, recall, F1-score, and AUC. The test results showed an accuracy of 97.2%, precision of 96.8%, recall of 97.5%, F1 of 97.1%, and AUC of 0.99, surpassing previous designs that did not use attention mechanisms and texture fusion. Grad-CAM++ analysis confirms the model's focus on physiologically relevant regions (embryonic shadow and air-cell), thus improving the reliability of interpretation. These findings indicate that lightweight, efficient designs based on attention and texture fusion have the potential to be implemented in smart hatchery systems and edge/mobile devices while maintaining high accuracy.
Klasifikasi Tingkat Kesejahteraan Masyarakat Desa Cikuya Berdasarkan Data Sosial Ekonomi Menggunakan Algoritma Nive Bayes Ramdan Irawan; Rudi Kurniawan; Bani Nurhakim; Arif Rinaldi; Fathurrahman
Jurnal Sistem Informasi dan Teknologi Vol 6 No 1 (2026): Jurnal Sistem Informasi dan Teknologi (SINTEK)
Publisher : LPPM STMIK KUWERA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56995/sintek.v6i1.203

Abstract

Penentuan tingkat kesejahteraan masyarakat memiliki peran penting dalam proses penyaluran bantuan sosial di tingkat desa. Namun, pendataan berbasis observasi manual masih menghadirkan potensi bias subjektif dan ketidakkonsistenan dalam pengambilan keputusan. Penelitian ini bertujuan mengembangkan model klasifikasi tingkat kesejahteraan masyarakat Desa Cikuya menggunakan algoritma Naïve Bayes sebagai pendekatan berbasis data yang lebih objektif. Tahapan penelitian meliputi pengumpulan data sosial ekonomi, pra-pemrosesan, encoding variabel kategorik, normalisasi variabel numerik, pelatihan model Gaussian Naïve Bayes, serta evaluasi menggunakan metrik akurasi, precision, recall, dan f1-score. Hasil penelitian menunjukkan bahwa model menghasilkan akurasi sebesar 98,33%, yang menunjukkan performa klasifikasi yang sangat baik. Analisis lebih lanjut mengindikasikan bahwa variabel pendapatan dan kondisi fisik rumah memiliki peranan paling dominan dalam membedakan kategori kesejahteraan. Model yang dikembangkan tidak hanya berfungsi sebagai alat klasifikasi, tetapi juga dapat dimanfaatkan sebagai sistem pendukung keputusan bagi pemerintah desa untuk menilai status kesejahteraan masyarakat secara lebih cepat, konsisten, dan bebas bias subjektif. Penelitian ini memberikan kontribusi pada pemanfaatan teknologi pembelajaran mesin dalam pemetaan kesejahteraan masyarakat, meskipun masih memiliki keterbatasan pada jumlah variabel dan cakupan data lokal. Temuan ini diharapkan dapat menjadi dasar pengembangan sistem penyaluran bantuan yang lebih tepat sasaran dan transparan.
Design and Construction of a Web-Based Information System for Product Performance Monitoring and Inventory Management at John Store Farras Fadhlur Rohman; Nining Rahaningsih; Bani Nurhakim
Jurnal Manajemen Informatika & Teknologi Vol. 6 No. 1 (2026): Mei : Jurnal Manajemen Informatika & Teknologi
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/q8y5kn82

Abstract

It must be able to stand alone since abstracts are frequently given apart The utilization of information technology has developed into a vital instrument in enhancing operational efficiency and business competitiveness, particularly in the medium-scale retail sector. Accurate inventory management is the primary foundation for business sustainability to maintain consistent customer satisfaction. However, John Store currently faces complex operational obstacles as it relies entirely on manual recording methods. The absence of a structured internal database system causes significant data synchronization issues between administrative records and physical stock in the warehouse, thereby increasing the risk of sudden stockouts. The most fundamental and crucial issue lies in managing bundling category products, where a single package transaction often fails to accurately deduct the stock balance of individual components due to the high risk of human error in manual calculation. To address this inefficiency, this research aims to build the web-based John Store Information System (SIJOHNS) as an integrated internal back-office solution. System development applies the Waterfall method systematically, covering requirements analysis, system design through Flowmap, Data Flow Diagram (DFD), and Entity Relationship Diagram (ERD), to implementation using PHP programming language and MySQL database. Key system features include the automation of bundling stock mapping and multi-role access rights management. Based on Black Box Testing, the system is proven valid. The implementation of SIJOHNS successfully transforms inventory management into a digital format, ensures the accuracy of stock deduction in real-time, and presents analytical data visualization on the dashboard to facilitate the store owner in monitoring sales trends for more strategic and targeted business decision-making
Optimization of Classification of Tea Leaf Disease Images Using LBP–HOG and MobileNetV2 Ezar Qotrunnada; Odi Nurdiawan; Arif Rinaldi Dikananda; Aris Pratama Putra; Bani Nurhakim
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1861

Abstract

This study was motivated by the need for an accurate and efficient system for detecting tea leaf diseases, given that the current method Manual identification has limitations in terms of consistency, speed, and It also depends on expert labor. To address these challenges, the study It developed a classification model for detecting diseases in tea leaves using a combination of features Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG) integrated with the MobileNetV2 architecture. The research method includes the following stages: importing the dataset, data partitioning, exploratory data analysis (EDA), preprocessing, features, and training four model scenarios: baseline MobileNetV2, LBP-based model, HOG-based model, and hybrid LBP–HOG model. Evaluation is done with the metrics of accuracy, precision, recall, and F1-score. The results show that the baseline model achieved 91.67% accuracy, the LBP model achieved 60.67%, the HOG model achieved 68.67% accuracy, and the hybrid model achieved 66.67% accuracy. These findings indicate that MobileNetV2 is still the most optimal model, but the integration of texture features and gradients provides a deeper understanding of the characteristics of disease patterns. This study emphasizes the importance of exploring classic features to enriching visual representation in lightweight CNN models, as well as providing a contribution to the development of plant disease diagnosis systems that are efficient.
Comparative Analysis of Durian Leaf Disease Classification Using Transfer Learning VGG16, InceptionV3, and U-Net Nafisa Maysa Salma; Rudi Kurniawan; Bani Nurhakim; Agus Bahtiar; Riri Narasati
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1864

Abstract

Image-based durian leaf disease detection presents challenges due to high visual similarity among symptoms and the limited, imbalanced dataset. This study compares three deep learning architectures VGG16, InceptionV3, and U-Net encoder-based—using transfer learning for classifying five durian leaf conditions. The dataset of 4,437 images underwent preprocessing, augmentation, and preliminary segmentation using U-Net to enhance focus on leaf regions. Fine-tuning was applied to the upper layers of each model to adapt feature representations to tropical leaf characteristics. The results indicate that InceptionV3 achieved the most stable and accurate performance with an accuracy of approximately 0.66, while VGG16 showed balanced results but was more prone to overfitting. U-Net proved effective for segmentation but less optimal as a classifier due to loss of small-scale lesion details. Overall, the findings demonstrate that combining U-Net segmentation with CNN-based transfer learning improves disease identification performance, particularly under limited data conditions.
Co-Authors Ade Rizki Rinaldi agus bahtiar Arif Rinaldi Arif Rinaldi Dikananda Aris Pratama Putra Dadang Sudrajat Denni Pratama Ezar Qotrunnada Farras Fadhlur Rohman Fathurrahman Indah Rosaliyah Khaerul Anam Nafisa Maysa Salma Nining Rahaningsih Odi Nurdiawan Ramdan Irawan Riri Narasati Rizal Rusyana Rudi Kurniawan Saeful Anwar Siti Komariyah Tati Suprapti