Computer Vision and Pattern Recognition, Artificial Intelligence
10
Scopus Publications
159
Scholar Citations
6
Scholar h-index
5
Scholar i10-index
Scopus Publications
CBTi-YOLOv5: Improved YOLOv5 with CBAM, Transformer, and BiFPN for Real-Time Safety Helmet Detection Tio Dharmawan, Danang Setiawan, Muhamad Arief Hidayat, Vandha Pradwiyasma Widartha Journal of Information Systems Engineering and Business Intelligence, 2025 Background: Some construction workers are often in a situation where injuries can occur from negligence in the use of safety helmets. To avoid this, supervision of the use of safety helmets should be conducted continuously during the work process through the application of computer vision technology. However, the complex background of the construction environment is a challenge to detecting small and densely packed safety helmets accurately. Objective: The construction environment is complex, and the wide workspace allows workers to be in an area far from supervision. The process makes it difficult for models to detect the use of safety helmets in complex, wide, and very high object density construction environments. Therefore, this study aims to overcome the problem by modifying YOLOv5s (You Only Look Once version 5) architecture. Methods: Real-time monitoring of the use of safety helmets could be performed using YOLOv5. This study proposed a modified YOLOv5s model called CBTi-YOLOv5s. The model incorporated Convolutional Block Attention Module (CBAM), Transformer, and Bi-directional Feature Pyramid Network (BiFPN) to improve feature extraction, multi-scale object representation, as well as detection accuracy, specifically on small and high-density objects in complex construction environments. Results: The results showed the modified YOLOv5s architecture had made an improvement of 3.7% in mean average precision (mAP) compared to the base YOLOv5s model. mAP of the base YOLOv5s model was 93.6%, while the modified CBTi-YOLOv5s model achieved 97.3%. The proposed modified YOLOv5s model also achieved an inference speed of 58 frames per second (FPS), and the base model achieved 104 FPS. Conclusion: CBTi-YOLOv5s improved the accuracy, mAP, and ability to detect objects of varying scales. However, this improvement had drawbacks, namely increased model size and decreased inferential speed due to increased model architectural complexity.. Keywords: Bi-FPN, CBAM, CBTi-YOLOv5s, Helmet Detection, Transformer, YOLOv5
Gender classification performance optimization based on facial images using LBG-VQ and MB-LBP Faruq Abdul Hakim, Tio Dharmawan, Muhamad Arief Hidayat International Journal of Advances in Intelligent Informatics, 2025 In the computer vision and machine learning field, especially for gender classification based on facial images, feature extraction is one of the inseparable parts. Various features can be extracted from images, including texture features. Several prior studies show that the Linde Buzo gray vector quantization (LBG-VQ) and Multi-block local binary pattern (MB-LBP) methods can extract texture features from images. The LBG-VQ produces less optimal performance in gender classification on the FEI facial images dataset. On the other hand, the MB-LBP produces more optimal performance when applied to the FERET facial images dataset. Therefore, this study was conducted to discover the gender classification performance when the LBG-VQ and MB-LBP methods are implemented independently or in combination on the FEI facial images dataset. Three preprocessing stages are involved before extracting images' features: noise removal, illumination adjustment, and image conversion from RGB to grayscale. The extracted features are then used as training material for several classification methods, namely Naïve Bayes, SVM, KNN, Random Forest, and Logistic Regression. Then, the K-Fold Cross Validation method is used to evaluate the trained models. This study discovered that the implementation of MB-LBP tends to show a performance improvement compared to the LBG-VQ. Furthermore, the most optimal classification model, with a performance of 91.928%, was formed by implementing Logistic Regression with MB-LBP on LBG-VQ quantized images. In conclusion, this study successfully formed an optimized gender classification model based on the FEI facial images dataset.
Seasonal meat stock demand used comparison of performance smoothing-average forecasting Tundo Tundo, Shoffan Saifullah, Tio Dharmawan, Junaidi Junaidi, Elmi Devia Indonesian Journal of Electrical Engineering and Computer Science, 2025 Seasonal patterns significantly influence the demand for beef stock, especially in rural areas that rely on natural feed. Accurate forecasting is essential for managing this demand due to beef's status as a government-regulated nutritional commodity. Food production, consumption, and income levels affect the demand for beef stocks. This research aims to identify the most precise forecasting method for predicting future beef stock needs. We evaluated multiple techniques, including single exponential smoothing (SES), double exponential smoothing (DES), single moving average (SMA), and double moving average (DMA), using the mean absolute percentage error (MAPE) metric, focusing specifically on beef supplies in Pemalang. The results indicated that the DMA method achieved the highest accuracy with a MAPE value of 5.993% at the 4th -order parameter. Additionally, increasing the data volume improved forecasting accuracy, demonstrating the effectiveness of the DMA method for beef stock prediction.
Forecasting Roof Tile Production Using SMA and SES for Alternatives to Production Management Mesra Betty Yel, Tundo, Tio Dharmawan Proceedings 2024 5th International Conference on Computational Science and Information Management Icocsim 2024, 2024 This research aims to predict roof tile production trends at one of the roof tile companies in Kebumen in order to assist the company management in determining and providing management recommendations for the tile production that occurs so that production management always runs well and is directed. Forecasting is carried out by implementing the Single Moving Average (SMA) and Single Exponential Smoothing (SES) methods on roof tile production transaction data over a 60 month period, namely January-December 2019 to January-December 2023 to produce monthly forecasts for roof tile production predictions. The total sample of training data processed is 1, 415, 987 records, which are roof tile production transaction data, as well as data in January 2024 as test data (to test the accuracy of predictions). The results of forecast testing based on MAPE (Mean Absolute Percentage Error) for SMA forecasting with n-th ordo 9 is the best n-th ordo, amounting to 9.16 %. This means that an accuracy of 90.84 % is obtained, and SES with an alpha value of 0.1 is the best alpha, with a MAPE value of 9.49 % with an accuracy of 90.51 %, which means the accuracy is very good, namely above 90 %. Based on the MAPE results obtained, the SMA method is the right method for carrying out periodic forecasting for roof tile companies in carrying out the production process in order to maintain stability and avoid unexpected things.
Enhancing Code Smell Detection Performance in Python Programming Language: A Comparative Study Windi Eka Yulia Retnani, Daniel Siahaan, Saiful Bukhori, Tio Dharmawan, Johar Bayu Iceecit 2024 Proceedings 2nd International Conference on Electrical Engineering Computer and Information Technology 2024, 2024 Code smell is one of the problems in programming which indicates that a problem has occurred, where there is something less than ideal in the code even though the code can run well. This research conducted a comparative study of the performance of Decision Tree, Random Forest, the use of the AdaBoost, CatBoost, XGBoost ensemble, and the use of SMOTEENN preprocessing to improve code smell detection in the Python programming language. Overall, the Decision Tree Pruning model hybrid with Adaboost and SMOTEEN produces the highest accuracy of 98.69% and MCC of 97.40%. Meanwhile, on the Long Method dataset, the XGBoost model with the SMOTEENN application produces the highest accuracy of 99.69% and MCC of 99.38%.
Implementation of simplex algorithm to optimize toddler's balanced nutrition needs with minimum costs Q A A Ruhimat, R J Riftana, T Dharmawan Journal of Physics Conference Series, 2020 Nutrition is an important element needed by humans, including toddlers. The unfulfilled nutritional needs can cause several diseases, such as malnutrition and stunting. It was caused because of human inability to fullfill the nutrition needs of all family members with good quality and the lack of parental knowledge about nutritious food ingredients and how to feed properly. It is necessary to optimize the fulfillment of food nutrition for infants with a minimum cost. One of the efforts is to make the right combination of food ingredients with cost minimum so that it can be reached by all levels of society. This research was analyzed using Simplex algorithm with QM for Windows software. The results was obtained in the form of the amount of food that can be consumed by user to fullfill the nutritional intake needs along with the minimum cost.
Time Frame Detection Based on Online News Documents Using Vector Space Model Ferry Wiranto, Achmad Maududie, Tio Dharmawan Proceedings 2019 International Conference on Computer Science Information Technology and Electrical Engineering Icomitee 2019, 2019 This study aims at finding an approach to identify news case duration or time frame as well as to identify the ways to find a time frame through the news document. News document used in this research refers to the previous research done by Rahim in 2018. The research uses three popular news website of Indonesia in 2018 which are tribunnews.com, detik.com and liputan6.com. However, in this research, the news website also uses as an object of analysis. The result conducted that the process to find a news time frame should define the cosine similarity minimum (threshold) between news and keyword (query). The researcher also finds that the workflow to determine the time frame uses news document based on the vector space model and combined with measurement technique if-idf and cosine similarity.
Dropout Detection Using Non-Academic Data Tio Dharmawan, Hari Ginardi, Abdul Munif Proceedings 2018 4th International Conference on Science and Technology Icst 2018, 2018 The common problem in the university is the high dropout rate. The high dropout rate will have a bad impact on the university. Various studies have tried to determine the factors that influence the dropout. Almost all research focuses on academic factors of students as a determinant of potential dropouts. However, there are sometimes cases of dropout students who cannot be determined using academic factors. This raises the hypothesis that the potential dropout students can be determined from non-academic factors. There are 5 non-academic factors criteria that can be used as determinants of dropout, demography, social interaction, finance, motivation, and personal. These criteria give rise to 37 factors that are considered influential in determining the potential dropout. The factors processed into three phases are collecting data, preprocessing data, and modelling. The factor that are independent to other factors are the number of family, the interest in the future study, and the relationship with the lecturer. Based on the result of correlation test there are two factors had correlation, so the modelling done with two combination factors. The best model is using combination of factor the number of family and the relationship with the lecturer using Decision Tree with split criterion is Maximum Deviance Reduction and maximum split is 2 with time for training is 1.7386 seconds.
Systematic literature review: Model refactoring Tio Dharmawan, Siti Rochimah Proceedings of the 2017 4th International Conference on Computer Applications and Information Processing Technology Caipt 2017, 2017 Refactoring is the method to detecting and fixing bad smells in software. Refactoring techniques that have developed is a refactoring technique that is done on the source code. Along with the development of model driven software engineering (MDSE), it also developed the method of refactoring on the model. Refactoring method in the model is considered more effective and efficient because the detection and repair of bad smell is done at the design phase. The method of refactoring on the model evolves into a variety of techniques. Due to this, the systematic literature review is done to get the development of refactoring method on the developing model.
RECENT SCHOLAR PUBLICATIONS
Face Gender Recognition Optimization Using VGG-16 With Integration of Spatial Attention Block and Channel Attention Block T Dharmawan, LVDK Putra, MA Hidayat Jurnal Ilmu Komputer dan Informasi 19 (1), 89-97 , 2026 2026
CBTi-YOLOv5: Improved YOLOv5 with CBAM, Transformer, and BiFPN for Real-Time Safety Helmet Detection. T Dharmawan, D Setiawan, MA Hidayat, VP Widartha Journal of Information Systems Engineering & Business Intelligence 11 (3) , 2025 2025
Disease Classification in Cauliflower Plants Using Vgg19 Architecture and Support Vector Machine (SVM)+ Lime U Ardiansah, T Dharmawan Journal of Research in Artificial Intelligence for Systems and Applications … , 2025 2025 Citations: 1
Implementation of Convolutional Neural Network (CNN) for Watermelon Plant Diseases Using Lenet-5 Architecture T Dharmawan Journal of Research in Artificial Intelligence for Systems and Applications … , 2025 2025
Optimasi Model Rekomendasi Topik Skripsi berdasarkan Performa Akademik Mahasiswa menggunakan SMOTE NO Adiwijaya, MF Al Abror, T Dharmawan, MA Hidayat Prosiding Seminar Nasional Teknik Elektro, Sistem Informasi, dan Teknik … , 2025 2025
Pengaruh Penggunaan Emoji Pada Tingkat Akurasi Sentimen Di Twitter Menggunakan Metode Support Vector Machine T Dharmawan, VG Kinanti, A Maududie Prosiding Seminar Nasional Teknik Elektro, Sistem Informasi, dan Teknik … , 2025 2025
Optimizing DenseNet121 for Waste Classification Using Genetic Algorithm-Based Downsampling and Data Augmentation. T Dharmawan, YA Auliya, DA Retnani, S Bukhori, M Zarkasi, I Ataama Mathematical Modelling of Engineering Problems 12 (5) , 2025 2025 Citations: 1
Gender classification performance optimization based on facial images using LBG-VQ and MB-LBP FA Hakim, T Dharmawan, MA Hidayat International Journal of Advances in Intelligent Informatics 11 (1), 72-85 , 2025 2025
Optimization of Coffee Bean Maturity Classification by Segmentation on Multispectral Images Using HSV and DBSCAN MN Hidayat, T Dharmawan, MA Hidayat, NO Adiwijaya Journal of Research in Artificial Intelligence for Systems and Applications … , 2025 2025 Citations: 2
Peningkatan Produktifitas Budidaya Jamur Janggel Dengan Penggunaan Teknologi IoT Di Desa Mrawan Mayang A Andrianto, T Dharmawan, M Fitriyasari, H Soepandi, K Leba Jurnal Transformasi Digital Masyarakat (DIGIMAS) 1 (1), 29-35 , 2025 2025
PELATIHAN PENGGUNAAN PLATFORM CANVA UNTUK OPTIMALISASI DESAIN GRAFIS BAGI PENGRAJIN PAPAN BUNGA AKRILIK S BUKHORI, HA BUKHORI, T DHARMAWAN, B PRASETYO JURNAL PENGABDIAN PADA MASYARAKAT Учредители: Universitas Mathla ul Anwar … , 2025 2025
Seasonal meat stock demand used comparison of performance smoothing-average forecasting T Tundo, S Saifullah, T Dharmawan, J Junaidi, E Devia 2025 Citations: 2
Enhancing code smell detection performance in Python programming language: A comparative study WEY Retnani, D Siahaan, S Bukhori, T Dharmawan, J Bayu 2024 IEEE 2nd International Conference on Electrical Engineering, Computer … , 2024 2024 Citations: 3
Forecasting Roof Tile Production Using SMA and SES for Alternatives to Production Management MB Yel, T Dharmawan 2024 5th International Conference on Computational Science & Information … , 2024 2024
Integration of Colbp and Viola Jones Feature Extraction Methods in Gender Classification Based on Facial Image WKR Ardana, T Dharmawan, MA Hidayat International Journal of Innovation in Enterprise System 8 (1), 87-100 , 2024 2024
Manajemen Teknologi Informasi: Strategi Dan Praktik Terbaik MA Komara, MAS Ekowati, A Andrianto, T Dharmawan, B Prasetyo CV WIDINA MEDIA UTAMA , 2024 2024 Citations: 2
Analysis and design of adulteration dairy milk system M Zarkasi, DAR Wulandari, S Bukhori, YA Auliya, T Dharmawan 2nd International Conference on Neural Networks and Machine Learning 2023 … , 2024 2024 Citations: 1
Gender Classification Using Viola Jones, Orthogonal Difference Local Binary Pattern and Principal Component Analysis MA Mukminin, T Dharmawan, MA Hidayat MATRIK: Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 23 (3 … , 2024 2024
Classification of Coffee Fruit Maturity Level based on Multispectral Image Using Naïve Bayes Method ID ‘Ulhaq, MA Hidayat, T Dharmawan JIKI: Journal of Computer Sciences and Information 17 (2), 121-126 , 2024 2024 Citations: 4
Face gender classification using combination of LPQ-Self PCA T Dharmawan, DA Nugroho, MA Hidayat JUITA: Jurnal Informatika, 101-109 , 2024 2024 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
Analisis user interface terhadap website akta online banyuwangi menggunakan metode heuristic evaluation SVN Fitri, O Juwita, T Dharmawan INFORMAL: Informatics Journal 4, 103-107 , 2019 2019 Citations: 43
Dropout detection using non-academic data T Dharmawan, H Ginardi, A Munif 2018 4th international conference on science and technology (ICST), 1-4 , 2018 2018 Citations: 37
Comprehensive measurement and evaluation of modern paddy cultivation with a hydroganics system under different nutrient regimes using WSN and ground-based remote sensing BTW Putra, WNH Syahputra, K Anam, T Darmawan, B Marhaenanto Measurement 178, 109420 , 2021 2021 Citations: 12
Analisis Pengaruh Kesiapan Pengguna Terhadap Penerimaan SIPENPIN Menggunakan Technology Readiness Acceptance Model (Studi Kasus: Masyarakat Desa Penambangan Kecamatan Curahdami … ED Nahzdifah, F Adnan, T Dharmawan Jurnal Teknologi Informasi dan Multimedia 4 (3), 168-185 , 2022 2022 Citations: 11
Penerapan Metode User Centered Design Untuk Mengembangkan E-Learning Universitas Jember Berbasis Mobile F Adnan, MH Muttaqin, T Dharmawan INFORMAL: Informatics Journal 3 (3), 85-92 , 2018 2018 Citations: 10
Optimization of machine learning algorithms with bagging and adaboost methods for stroke disease prediction HS Mansur, NO Adiwijaya, T Dharmawan Applied Medical Informatics 45 (2) , 2023 2023 Citations: 6
Evaluasi UI/UX Pada Game Valorant Menggunakan Metode Enhanced Cognitive Walkthrough B Kusumawardana, F Adnan, T Dharmawan Jurnal Device 12, 24-31 , 2022 2022 Citations: 6
Analisis User Interface Terhadap Website Akta Online Banyuwangi Menggunakan Metode Heuristic Evaluation. INFORMAL: Informatics Journal, 4 (3), 103 SVN Fitri, O Juwita, T Dharmawan 2020 Citations: 5
Classification of Coffee Fruit Maturity Level based on Multispectral Image Using Naïve Bayes Method ID ‘Ulhaq, MA Hidayat, T Dharmawan JIKI: Journal of Computer Sciences and Information 17 (2), 121-126 , 2024 2024 Citations: 4
Feature selection methods based on mutual information for classifying heterogeneous features RE Pawening, T Darmawan, RR Bintana, AZ Arifin, D Herumurti Jurnal Ilmu Komputer Dan Informasi 9 (2), 106-112 , 2016 2016 Citations: 4
Enhancing code smell detection performance in Python programming language: A comparative study WEY Retnani, D Siahaan, S Bukhori, T Dharmawan, J Bayu 2024 IEEE 2nd International Conference on Electrical Engineering, Computer … , 2024 2024 Citations: 3
Systematic literature review: Model refactoring T Dharmawan, S Rochimah 2017 4th International Conference on Computer Applications and Information … , 2017 2017 Citations: 3
Optimization of Coffee Bean Maturity Classification by Segmentation on Multispectral Images Using HSV and DBSCAN MN Hidayat, T Dharmawan, MA Hidayat, NO Adiwijaya Journal of Research in Artificial Intelligence for Systems and Applications … , 2025 2025 Citations: 2
Seasonal meat stock demand used comparison of performance smoothing-average forecasting T Tundo, S Saifullah, T Dharmawan, J Junaidi, E Devia 2025 Citations: 2
Manajemen Teknologi Informasi: Strategi Dan Praktik Terbaik MA Komara, MAS Ekowati, A Andrianto, T Dharmawan, B Prasetyo CV WIDINA MEDIA UTAMA , 2024 2024 Citations: 2
Face gender classification using combination of LPQ-Self PCA T Dharmawan, DA Nugroho, MA Hidayat JUITA: Jurnal Informatika, 101-109 , 2024 2024 Citations: 2
Time Frame Detection Based on Online News Documents Using Vector Space Model F Wiranto, A Maududie, T Dharmawan 2019 International Conference on Computer Science, Information Technology … , 2019 2019 Citations: 2
Disease Classification in Cauliflower Plants Using Vgg19 Architecture and Support Vector Machine (SVM)+ Lime U Ardiansah, T Dharmawan Journal of Research in Artificial Intelligence for Systems and Applications … , 2025 2025 Citations: 1
Optimizing DenseNet121 for Waste Classification Using Genetic Algorithm-Based Downsampling and Data Augmentation. T Dharmawan, YA Auliya, DA Retnani, S Bukhori, M Zarkasi, I Ataama Mathematical Modelling of Engineering Problems 12 (5) , 2025 2025 Citations: 1
Analysis and design of adulteration dairy milk system M Zarkasi, DAR Wulandari, S Bukhori, YA Auliya, T Dharmawan 2nd International Conference on Neural Networks and Machine Learning 2023 … , 2024 2024 Citations: 1
