Article Per Year (5 Year)
p-Index From 2021 - 2026
4.108
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Teknik Industri J@TI (TEKNIK INDUSTRI) Jurnal Rekavasi SITEKIN: Jurnal Sains, Teknologi dan Industri JURNAL PASTI (PENELITIAN DAN APLIKASI SISTEM DAN TEKNIK INDUSTRI) Jurnal Optimasi Sistem Industri Jurnal Ilmiah Teknik Industri JOURNAL OF INDUSTRIAL AND MANUFACTURE ENGINEERING Jurnal Teknik Industri: Jurnal Keilmuan dan Aplikasi Teknik Industri Jurnal Teknik Industri : Jurnal Hasil Penelitian dan Karya Ilmiah dalam Bidang Teknik Industri Jurnal Mutu Pangan : Indonesian Journal of Food Quality International Journal of Advances in Data and Information Systems Jurnal Media Teknik dan Sistem Industri Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Optimasi Teknik Industri (JOTI) Industrika : Jurnal Ilmiah Teknik Industri Go-Integratif : Jurnal Teknik Sistem dan Industri Green Intelligent Systems and Applications Journal of Industrial Engineering and Halal Industries Spektrum Industri
Achmad Pratama Rifai
Department Of Mechanical And Industrial Engineering, Universitas Gadjah Mada
Religion Agriculture, Biological Sciences & Forestry Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering Public Health Transportation Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Optimasi Open Location Routing Problem Menggunakan Metode Metaheuristik Simulated Annealing, Large Neighborhood Search, dan Adaptive Large Neighborhood Search Muhammad, Audi Ziyad Afkar; Kafi, Mochamad Egidio Pramudya; Hasibuan, Narsico Rafael; Rahmawatie, Noor Athiea; Rifai, Achmad Pratama
Jurnal Optimasi Teknik Industri (JOTI) Vol 7, No 1 (2025)
Publisher : Teknik Industri Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/joti.v7i1.24873

Abstract

Overcoming Data Imbalance in Risk Management: A Comparative Study of Sampling Methods Astungkara, Arya Wijna; Rifai, Achmad Pratama
JTI: Jurnal Teknik Industri Vol 11, No 1 (2025): JUNI 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/jti.v11i1.37368

Abstract

Data imbalance is a significant challenge in risk management, especially in classification tasks where critical events—such as loan defaults, employee attrition, or company bankruptcy—occur less frequently than normal cases. This paper presents a comparative study of eight sampling methods—Random Undersampling (RUS), Random Oversampling (ROS), Edited Nearest Neighbor (ENN), One-Sided Selection (OSS), SMOTE, ADASYN, SMOTEENN, and SMOTETomek—across three imbalanced datasets: Taiwanese Bankruptcy Prediction, IBM HR Analytics Employee Attrition, and Loan Prediction. Using eight machine learning classifiers, the study evaluates performance using F1 Score and Negative Predictive Value (NPV), two metrics suited for imbalanced data. The results reveal that ENN achieves the highest F1 scores in high-dimensional and severely imbalanced datasets, while SMOTE-based methods perform best in large-scale datasets with moderate imbalance. Notably, RUS consistently delivers the highest NPV, highlighting its effectiveness in minimizing false negatives and supporting conservative decision-making. The findings underscore the importance of aligning sampling strategies with dataset characteristics and specific risk management objectives.
Comparative Evaluation of Convolutional Neural Network Full Learning Model with Transfer Learning (VGG-16) for Coffee Bean Roasting Level Classification Tama, Mradipta Nindya; Saptomo, Amanat Bintang; Afrido; Baroroh, Dawi Karomati; Rifai, Achmad Pratama; Tho, Nguyen Huu
International Journal of Advances in Data and Information Systems Vol. 6 No. 2 (2025): August 2025 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v6i2.1358

Abstract

Indonesia is the 3rd largest coffee producing country in the world in 2022-2023 with coffee production reaching 11.85 million bags per 60 kg of coffee. One of the important processes in coffee production is roasting because the roasting level of coffee beans can affect the taste and aroma of coffee. The problem faced is that the process of assessing the level of coffee roasting is traditionally carried out through visual observation by an expert (roaster). This method produces a subjective level of assessment and requires high skills and experience, making the assessment of the level of coffee roasting less efficient and prone to human error. Therefore, in this study the author aims to develop a Convolutional Neural Network (CNN) model for the classification of the level of coffee bean roasting that can achieve better and faster accuracy. In this study, the author compared two CNN architecture approaches for the classification of the level of coffee bean roasting. The first approach is full learning with an architecture consisting of three convolution layers. The second approach is transfer learning based on the VGG-16 model. From the results of the analysis, it is known that the full learning model has a better level of accuracy and a faster running time than the VGG-16 transfer learning. The CNN full learning model for coffee bean roasting level classification is able to classify the coffee bean roasting level, with an accuracy of 98.75% and a running time of 856 ms per step. The application of CNN for coffee roasting level classification can provide benefits such as improving quality control and reducing the level of subjectivity of a roaster in assessing the roasting level of coffee beans.
Classification of Metal Surface Defects Using Convolutional Neural Networks (CNN) Pratama, Dhika Wahyu; Ismail, Muchammad; Nurraudah, Restu; Rifai, Achmad Pratama; Nguyen , Huu Tho
Green Intelligent Systems and Applications Volume 5 - Issue 1 - 2025
Publisher : Tecno Scientifica Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53623/gisa.v5i1.581

Abstract

Metal surface quality inspection is an important step in ensuring that products meet predetermined industry standards. The manual methods used were often slow and prone to errors, so more efficient solutions were needed. The application of Machine Learning (ML)-based technologies, especially Convolutional Neural Networks (CNN), offered an innovative approach to overcome these challenges. CNN had the ability to automatically extract visual features from images with high accuracy, making it an effective tool in defect classification. This research used several CNN architectures, including MobileNetV2 and InceptionV3, as well as a model developed in-house, the K3 Model. Data augmentation, such as rotation and lighting adjustments, was applied to increase variation in the dataset and aid the model in generalization. The research results showed that the K3+Augmentation model achieved the highest accuracy of 100% in testing, with a very low loss of 0.0009. While MobileNetV2 offered better training speed, K3+Augmentation showed superior performance in detecting and classifying metal defects. These findings confirmed the potential of CNN in improving the efficiency of quality inspection in modern industry.
Comparative analysis of gender classification methods using convolutional neural networks Pamungkasari, Panca Dewi; Asfandima, Ilhan Alim; Rifai, Achmad Pratama; Huu Tho, Nguyen
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 5: October 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i5.pp3634-3646

Abstract

Gender classification has become an important application in the fields of system automation and artificial intelligence, having important implications across various fields. The main challenge in this classification task is the variation in illumination that affects the quality of facial images. This study presents a method for identifying genders with Convolutional Neural Networks (CNNs). To address this issue, various preprocessing methods are applied, including Self Quotient Image (SQI), Histogram Equalization, Locally Tuned Inverse Sine Nonlinear (LTISN), Gamma Intensity Correction (GIC), and Difference of Gaussian (DoG), to stabilize the effects of illumination variations before the images are processed by the CNN. The CNN architecture used consists of 5 convolutional blocks and 2 fully connected blocks, which have proven effective in image recognition. The results of the study show that the model trained with the DoG method achieved an accuracy of 91.07%, making it the best preprocessing technique compared to other methods such as SQI and HE, which achieved accuracies of 90.39% and 88.76%, respectively. These findings demonstrate that the application of SQI in CNN can improve the accuracy of gender classification on facial images, providing better performance than previous methods. These findings are expected to serve as a foundation for further developments in facial image classification and its applications in various fields.
Simulated Annealing untuk Perancangan Tata Letak Industri Furniture dengan Model Single dan Double Row Layout Kusumaningsih, Devita Ayuni; Azim, Ahmad Fadhil; Albab, Disya Amalia Ikhsani Ulil; Hans, Feishal Rey; Korin, Filbert; Pohan, Rafi Naufal Al Mochtari; Ananta, Vhysnu Satya; Rifai, Achmad Pratama
Jurnal Media Teknik dan Sistem Industri Vol 6, No 1 (2022)
Publisher : Universitas Suryakancana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/jmtsi.v6i1.1773

Abstract

Micro, Small, and Medium Enterprises (MSMEs) are promising contributors to national economic growth. One of the significant components in a business is the layout  aspect of production facilities. This study aims to produce an optimal layout  for an MSME engaged in furniture production, namely UD Bazooka in Yogyakarta. Currently, the layout  type used by UD Bazooka is a process layout  to produce a large variety of products. The use of simple process layout  affects on inefficient material movement, thus causing longer travelled distance and higher material handling cost as relative to the total production cost. Therefore, this research aims to improve the layout  of UD Bazooka with minimizing total travelled distance as the objective. The data collection is performed by observing the production line at UD Bazooka which will be translated into relationship data or REL charts, from-to-charts, and space requirements. In this study, the layout  of the facility is modelled into single and double-row layout  problems. This study developed a Simulated Annealing (SA) algorithm to solve the two models. Furthermore, Modified Spanning Tree (MST) is used as a benchmark method. To evaluate the best layout , we use total travelled distance and adjacency weight as the objective function. The results showed that the best layout  with minimum total travelled distance was the output of the double row layout  model solved using the Simulated Annealing. Usaha Mikro Kecil dan Menengah (UMKM) merupakan kontributor yang cukup signifikan dalam pertumbuhan ekonomi suatu negara. Salah satu komponen penting dalam sebuah bisnis adalah aspek tata letak fasilitas produksi. Penelitian ini bertujuan untuk menghasilkan tata letak optimal sebuah UMKM yang bergerak dalam bidang produksi furniture yaitu UD Bazooka yang berlokasi di Yogyakarta. Jenis tata letak yang digunakan oleh UD Bazooka saat ini adalah tipe process layout . Penggunaan tata letak fasilitas berupa process layout  yang sederhana menyebabkan perpindahan material dan komponen yang tidak efisien, sehingga menyebabkan waktu dan biaya perpindahan yang relatif tinggi dibandingkan dengan total biaya produksi. Dengan demikian, penelitian ini melakukan perancangan ulang tata letak fasilitas dengan tujuan meminimasi total travelled distance. Data diperoleh dengan mengobservasi lini produksi UD Bazooka yang kemudian akan diterjemahkan dalam data relationship atau REL chart, from-to-chart, dan space requirement. Pada penelitian ini, tata letak fasilitas dimodelkan menjadi single dan double row layout  problem. Penelitian ini mengembangkan algoritma Simulated Annealing (SA) untuk menyelesaikan kedua model tersebut. Selanjutnya, Modified Spanning Tree (MST) digunakan sebagai metode pembanding. Untuk mengevaluasi tata letak terbaik, digunakan total traveled distance dan adjacency weight sebagai fungsi tujuan. Hasil eksperimen menunjukkan bahwa layout  terbaik dengan total travelled distance paling rendah adalah output model double row layout  yang diselesaikan dengan Simulated Annealing.
Facility Layout Planning of Sheet Metal Working Industry Using Metaheuristics Ludwika, Adinda Sekar; Shalehah, Mar’atus; Mohamad, Rakan Raihan Ali; Oktavia, Andiny Trie; Normasari, Nur Mayke Eka; Tho, Nguyen Huu; Rifai, Achmad Pratama
Spektrum Industri Vol. 22 No. 2 (2024): Spektrum Industri - October 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/si.v22i2.141

Abstract

The design of facility layout in a production floor determines the level of effectiveness and efficiency of the production process. Errors in arranging the layout in the production floor can disrupt the continuity of the production process and prevent optimal results. Production activities that occur over a long period of time make any inaccuracies in layout planning result in significant losses. In companies with Job Shop production type, which is characterized by identical products and varied processes, the production flow changes with each product made. Based on these issues, this research aims to optimize the layout in a company engaged in sheet metal working industry using metaheuristic algorithms such as Simulated Annealing (SA), Large Neighborhood Search (LNS), Adaptive Large Neighborhood Search (ALNS), and Ant Colony Optimization (ACO). The best total distance results were obtained by the SA, LNS, and ALNS algorithms, with a total travelled distance of 897,171 meters and a facility arrangement of 7-5-6-4-3-2-1 or 1-2-3-4-6-5-7. Additionally, considering computation time, the SA algorithm is the best choice as it has the fastest computation time compared to other algorithms.
Classification of single origin Indonesian coffee beans using convolutional neural network Rifai, Achmad Pratama; Sari, Wangi Pandan; Rabbani, Haidar; Safitri, Tari Hardiani; Hajad, Makbul; Sutoyo, Edi; Nguyen, Huu-Tho
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i6.pp5140-5156

Abstract

This research aims to develop a coffee bean type detection model using convolutional neural networks (CNN), leveraging a dataset of 14,525 images from 116 types of Indonesian coffee beans. Pre-processing steps including resizing, rescaling, and augmentation were applied to improve the dataset quality. The dataset was split into training, validation, and testing sets with proportions of 80%, 10%, and 10%, respectively. Two model development approaches were used: transfer learning with Inception V3 in two scenarios and a model built from scratch. The transfer learning Inception V3 model in scenario 1 achieved the best performance, with a test accuracy of 0.87 and optimal evaluation metrics across precision, recall, and F1-score. This model was fine-tuned using pretrained weights, allowing it to adapt effectively to the coffee bean dataset. The results highlight that transfer learning, especially with Inception V3, provides a robust method for classifying coffee beans, offering potential applications in the coffee industry for improving classification efficiency and accuracy. The study demonstrates how deep learning can enhance the objectivity and precision of coffee bean classification, contributing to greater consistency in product sorting and quality assessment.
A Multi-Objective Double Row Layout Problem Considering Safety Distances and Geometrical Constraints Achmad Pratama Rifai; Setyo Tri Windras Mara; Rachmadi Norcahyo; Andri Nasution
Jurnal Optimasi Sistem Industri Vol. 24 No. 2 (2025): Published in December 2025
Publisher : The Industrial Engineering Department of Engineering Faculty at Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (621.938 KB) | DOI: 10.25077/josi.v24.n2.p174-197.2025

Abstract

This study addresses an enhanced version of the Double Row Layout Problem (DRLP) by incorporating two critical constraints: minimum safety distances between machines and geometric limitations on row lengths. A bi-objective mixed-integer non-linear programming (MINLP) model is formulated to simultaneously minimize material handling costs and penalties for violating safety distance requirements. To solve the problem efficiently, a novel metaheuristic called Improved Multi-Objective Variable Neighborhood Search (IMOVNS) is proposed. IMOVNS extends the standard MOVNS by integrating an adaptive archive update strategy and a probabilistic acceptance mechanism inspired by AMOSA, thereby improving both convergence and diversity in Pareto front generation. This study contributes to the layout optimization literature by proposing a tailored MOVNS variant explicitly designed for safety-aware and geometry-constrained DRLP, a challenging problem variant that has received limited attention in prior research. Extensive experiments on 27 DRLP instances show that IMOVNS demonstrates strong performance, significantly outperforming NSGA-II and showing competitive or superior results compared to AMOSA and MOVNS in terms of convergence and solution diversity. Statistical tests further confirm the significant superiority of IMOVNS, particularly over NSGA-II. Additionally, a key managerial insight reveals that layouts with unbalanced row lengths favour safety compliance, while balanced layouts minimize material handling costs. The Pareto-optimal solutions generated by IMOVNS enable decision-makers to select layout configurations that align with specific operational priorities. These findings highlight the practical relevance and robustness of IMOVNS in solving real-world multi-objective facility layout problems under complex spatial and safety constraints.
Co-Authors Afrido Ainayyah Bintang Agista Akbar, Hafizh Naufaly Al Kautsar, M. Nurudduja Albab, Disya Amalia Ikhsani Ulil Aldyno, Achmad Farhan Alfarasyied Syahrizad Amirah Meutia Noorfadila Ananta, Vhysnu Satya Andiny Trie Oktavia Andri Nasution Anom , Mauli Ardyaksa Diptya Pramudita Arista Adriani Armaisya, Dimas Dwi Arulloh Sonja Asa Pragasel Natuna Asfandima, Ilhan Alim Astungkara, Arya Wijna Astungkatara, Arya Wijna Awal, Syifa Maulvi Zainun Azim, Ahmad Fadhil Basirun, Arif Reza Briliananda, Silvyaniza Buchari, Muhammad Achirudin Dawi Karomati Baroroh Devita Ayuni Kusumaningsih Evan Alvaro Radeva Fadilah, Andara Fahreza Baskara Hediandra Fath, Hamzah Fatiha Widyanti Fauzi, Rifqi Fransisca Astri Dianswari Gopal Sakarkar Hajad, Makbul Hans Bastian Wangsa Hans, Feishal Rey Hartanti, Sri Hasibuan, Narsico Rafael Hideki Aoyama Hikam , Azka Huu Tho, Nguyen Ihsan Ramadhana Jordiva Fernanda Junaidi, Faiza Ulinnuha Kafi, Mochamad Egidio Pramudya Khania O.P.P. Nugraha Korin, Filbert Kusumaningsih, Devita Ayuni Kusumastuti, Putri Adriani Ludwika, Adinda Sekar Manalu, Haposan Vincentius Mohamad, Rakan Raihan Ali Muchammad Ismail Muhammad, Audi Ziyad Afkar Muhtar , Dini Nandila, Alisyafira Sayyidina Naufal Nur Akmal Nguyen , Huu Tho Nguyen, Huu Tho Nguyen, Huu-Tho Nur Mayke Eka Normasari Nurraudah, Restu Oda, Ahlam Nauf Oktavia, Andiny Trie Pamungkasari, Panca Dewi Penchala, Sathish Kumar Permana, Ari Pohan, Rafi Naufal Al Mochtari Pratama, Dhika Wahyu Priansyah, Adi Prihatmaja, Dhonadio Aurell Azhar Puspadewa, Paskalis Krisna Puspitasari, Afifa Putra, Dimas Zaki Alkani Putri, Oktaviana Rabbani, Haidar Rachmadi Norcahyo Radhitya Virya Paramasuri Sunarso Rahmawatie, Noor Athiea Safira, Aretha Safitri, Tari Hardiani Saifurrahman, Anas Saptomo, Amanat Bintang Sari Ningsih Sari, Dwi Kumala Sarudi As., L. M. Setiawan, Kevin Stephen Setyo Tri Windras Mara Shalehah, Mar’atus Sholihati, Ira Diana Susilo, Nazhifa Rahmi Sutoyo, Edi Syahdan Haris Abdilah Tama, Mradipta Nindya Tanaji, Irvantara Pradmaputra Thawafani, Lathiifah Tho, Nguyen Huu Valencia, Bella Renata Violita Anggraini Wangi Pandan Sari Wibisono, Ragil Aditya Windras Mara, Setyo Tri Wiraningrum, Rakyan Galuh Yana, Anak Agung Istri Anindita Nanda