Ben Rahman

Dr. Ben Rahman


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 October 2024 in IEEE Access
Verified
Journal Article
Open access
BRBen Rahman
Ben Rahman
MAMaryani
Maryani
In the era of digital transformation, customer feedback has become crucial for improving service quality. This study aims to enhance customer satisfaction through sentiment analysis utilizing machine learning techniques, with additional case studies conducted to ensure comprehensive method validation. Traditional sentiment analysis methods frequently fail to manage the complexity and volume of feedback data, yielding to less accurate insights. To address this challenge, we analyzed six machine learning models: Naïve Bayes, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Random Forest, AdaBoost, and BERT, with a particular focus on BERT. Our results demonstrate that BERT outperformed the other models in terms of both accuracy and processing speed, achieving an accuracy of up to 95%. The excellence of BERT in managing large and complex datasets provides a more precise sentiment analysis, which can significantly improve service quality and customer loyalty, while increasing company revenue by up to 15%. This research advances to the field of sentiment analysis by validating the effectiveness of BERT over traditional models through extensive comparative analysis and practical case studies.

25 October 2022 in JURNAL MEDIA INFORMATIKA BUDIDARMA
Verified
Journal Article
Open access
PDF file
WJWahid Al Jufri
Wahid Al Jufri
ATAgung Triayudi
Agung Triayudi
BRBen Rahman
Ben Rahman
Determination in choosing a supplier is one of the strategic programs and needs to be more objective, often the decision making in choosing a supplier is only based on intuition, habit and experience, until now there is no mechanism or method for this that is suitable or only according to universal select criteria. Hospital Facility Maintenance Facility (IPSRS) is a facility that oversees all maintenance and repair work on non-medical facilities at the National Brain Center Hospital, including building maintenance, electrical systems, plumbing, AC management, surveillance camera or CCTV maintenance, and motor generator repair. and telephone control generator. To select the expected spare parts supplier, it is necessary to apply the SPK Ideal Solution Similarity Order Preference Technique (TOPSIS) method and combine it with the Analytical Hierarchy Process (AHP) method to facilitate the process of selecting more than one alternative. The criteria determined in this study are S1 with Price, S2 with Quality, S3 with Speed and S4 with Completeness. With these criteria, it can be used as material to determine the Decision Support carried out by the system. In the results of this study the determination of the criteria using AHP with the results of the Consistency Ratio value of 0.004 which means if the value is above 0.01 then the results are declared consistent. As well as for the design using the Topsis method, the positive ideal solution on the criteria S1 is worth 0.13282, S2 is worth 0.07954, S3 is 0.04085 and S4 is 0.0422. Meanwhile, for the negative ideal solution, S1 is worth 0.04981, S2 is 0.02983, S3 is 0.02043 and S4 is 0.0211. The first rank is P7 with a value of 0.813 and the last order is P8 with a value of 0.13. So, from the results of the assessment carried out by the system based on the weight value for ranking using the TOPSIS method which occupies the top three positions, PT. Cipta Karya Teknik with a total of 0.813 or 81.3%, followed by PT. Karya Mandiri Indonesia with a total of 0.802 or 80.2%, and PT. Indah Harapan Nusa with a total of 0.796 or 79.6%. As for the bottom three positions are PT. Tunggal Teknik Indo with a total of 0.292 or 29.2%, then PT.Harapan Maju Bersama which has a total of 0.139 or 13.9% and the last one is PT. Forward Rise Simultaneously with a value of 0.130 or 13%.

4 April 2023 in sinkron
Verified
Journal Article
Open access
PDF file
ASAdi Dwifana Saputra
Adi Dwifana Saputra
DHDjarot Hindarto
Djarot Hindarto
BRBen Rahman
Ben Rahman
HSHandri Santoso
Handri Santoso
Tomato diseases vary greatly, one of which is tomato leaf disease. Some variants of leaf diseases include late blight, septoria leaf, yellow leaf curl virus, bacteria, mosaic virus, leaf fungus, two-spotted spider mite, and powdery mildew. By knowing the disease on tomato leaves, you can find medicine for the disease. So that it can increase the production of tomatoes with good quality and a lot of quantity. The problem that often occurs is that farmers cannot determine the disease in plants, they try to find suitable herbal medicines for their plants. After being given the drug, many plants actually died due to the pesticides given to the tomato plants. This is detrimental to tomato farmers. This problem is caused by incorrect disease detection. Therefore, this study aims to solve the problem of disease detection in tomato plants, in a more specific case, namely tomato leaves. Detection in this study uses a deep learning algorithm that uses a Convolutional Neural Network, specifically GoogleNet and EfficientNetB3. The dataset used comes from kaggle and google image. Both data sets have been pre-processed to match the data set class. Image preprocessing is performed to produce appropriate image datasets and improve performance accuracy. The dataset is trained to get the model. The training using GoogleNet resulted in an accuracy of 98.10%, loss of 0.0602 and using EfficientNetB3 resulted in an accuracy of 99.94%, loss: 0.1966.

31 March 2025 in PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic
Verified
Journal Article
Open access
PDF file
MSMifta Subagja
Mifta Subagja
BRBen Rahman
Ben Rahman
Object detection is one of the main tasks in computer vision, aimed at recognizing and localizing objects in images or videos. In this study, we utilize the YOLOv5 model, which is well known for its efficiency in realtime object detection. We implement this method with the help of the OpenCV library for image processing. This research aims to evaluate the performance of YOLOv5 in detecting objects in various types of images, including landscape photos, cat photos, and traffic light images with vehicles. The model is trained using optimization methods with the Adam optimizer and assessed through metrics like accuracy, precision, recall, and IoU. The results indicate that YOLOv5 can detect objects with high accuracy and fast inference time, making it an ideal solution for various applications such as security monitoring, video analysis, and automatic recognition systems. The advantage of YOLOv5 over traditional methods such as histogram equalization and thresholding lies in its ability to perform realtime detection with optimal computational efficiency. Thus, this study demonstrates that YOLOv5 is a suitable choice for implementing deep learningbased object detection systems.

25 August 2023 in Journal of Computer System and Informatics (JoSYC)
Verified
Journal Article
Open access
PDF file
DSDewi Mawarni Santika
Dewi Mawarni Santika
FFFauziah Fauziah
Fauziah Fauziah
BRBen Rahman
Ben Rahman
Dalam memenuhi kebutuhan pembelajaran yang efisien dan praktis maka pembuatan aplikasi pembelajaran sangat di butuhkan sekolah khususnya sekolah multimedia yang sangat tergantung dengan teknologi untuk proses belajar mengajar, buku memiliki keterbatasan untuk menampilkan teks dan gambar, mudah rusak jika terkena air dan mudah robek terlebih dengan adanya pembelajaran yang tidak memiliki buku Teknik Pengambilan Gambar Menggunakan Kamera untuk media pembelajaran sehingga menyulitkan bagi pelajar untuk menempuh Pendidikan yang maksimal. Dari permasalahan tersebut, penelitian ini akan membuat aplikasi Pembelajaran Teknik Pengambilan Gambar menggunakan kamera DSLR berbasis Android dalam upaya memudahkan dalam kegiatan belajar mengajar menjadi efisien dan praktis sehingga pelajar tidak perlu membawa buku, membeli buku dan aplikasi ini dilengkapi dengan unsur multimedia seperti teks dan gambar, dan video. Penelitian ini menggunakan Algoritma Fisher Yates untuk pengacakan soal yang terdiri dalam 15 soal dengan hasil dan terjadi random soal yaitu 4,1,9,11,8,6,15,2,3,5,10,13,7,12,14 pada proses algoritma fisher yates.

2 September 2024 in SaNa: Journal of Blockchain, NFTs and Metaverse Technology
Verified
Journal Article
Open access
PDF file
RSRacquel Terranova Simanungkalit
Racquel Terranova Simanungkalit
ATAgung Triayudi
Agung Triayudi
BRBen Rahman
Ben Rahman
The development of information technology, especially the internet, has significantly impacted facilitating human access to information, including the trend of society opting for frozen food as a fast food option. Meanwhile, the phenomenon of social media depicts the tendency of society to choose convenient and fast food. On the other hand, the rapid development of sales and product promotion systems through the internet is taking place, utilizing web-based technology. Recent studies also indicate that the development of web-based sales information systems for frozen food can enhance efficiency and service quality. Collaborative filtering methods in recommendation systems are also becoming increasingly popular in helping users obtain better recommendations. All of this indicates that information technology has had a positive impact on making purchasing and information management more efficient and convenient for society