Article
Green & Sustainable Science & Technology
Yasanur Kayikci, Sercan Demir, Sachin K. Mangla, Nachiappan Subramanian, Basar Koc
Summary: This study proposes a dynamic pricing model that uses real-time Internet of Things (IoT) sensor data to reduce food waste at the retailer stage of food supply chain in low and middle-income countries. The model takes into account various factors such as sale price, replenishment amount, discount rate, and freshness score to assist managers in making optimal decisions and actions. The results show the potential of using hyperspectral imaging sensors in the retailer's food supply chain.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Computer Science, Interdisciplinary Applications
Seyed Mojtaba Hosseini Bamakan, Najmeh Faregh, Ahad ZareRavasan
Summary: The paper proposes a Di-ANFIS framework based on blockchain and ANFIS techniques for evaluating service supply chain performance, featuring distributed, trustworthy, tamper-proof, and learning aspects. It presents hierarchical criteria for diagnosing root problems, a smart learning model for uncertain conditions, and a distributed blockchain framework for addressing big data and trust issues. The six-layer conceptual framework is designed to establish a performance management system utilizing the Internet of Things and smart contracts.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Wenjun Ke, Jianguo Wei, Naixue Xiong, Qingzhi Hou
Summary: Outlier detection is a challenging problem in various domains and has been well studied in the data mining community. Existing unsupervised methods for outlier detection only consider individual outliers and neglect the similarity among instances. In this paper, we propose a system based on group similarity that detects outliers by grouping similar instances and evaluating the resulting groups.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Interdisciplinary Applications
Jing Zheng, Chaher Alzaman, Ali Diabat
Summary: This study aims to improve supply chain responsiveness by expanding production capacity to cope with changes and variations in demand. Big Data Analytics helps researchers understand the current challenges of data: high volume, high velocity, and high variety. The study uses sales data and large warehouses to investigate the three characteristics of Big Data. It introduces a working architecture to handle the challenges of Big Data and applies a neural network to detect patterns in demand. The study combines deep learning with nonlinear programming to enable flexibility in responding to forecasted demand at supply chain production facilities.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Sheshadri Chatterjee, Ranjan Chaudhuri, Mahmood Shah, Pratik Maheshwari
Summary: The COVID-19 pandemic has caused an unprecedented crisis for businesses, particularly impacting small and medium enterprises (SMEs) due to their limited resources. Existing studies have not analyzed how big data driven innovation can improve supply chain management (SCM) in the post-COVID-19 era, under the moderating influence of SME technology leadership support. This study aims to examine the impact of big data driven innovation and technology capability of SMEs on their supply chain system, as well as the moderating role of SME technology leadership support on SME performance in the post-COVID-19 scenario.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Business
Jinou Xu, Margherita Pero, Margherita Fabbri
Summary: This paper investigates the link between BDA and supply chain planning (SCP) using the Delphi technique and presents 35 projections on the expected impact of BDA on SCP. The results provide insights for prioritizing BDA investment for SCP.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Computer Science, Hardware & Architecture
Mustafa Al Samara, Ismail Bennis, Abdelhafid Abouaissa, Pascal Lorenz
Summary: This paper proposes a centralised outlier detection and classification approach for Wireless Sensor Networks (WSNs), which can distinguish between errors due to a faulty sensor and those due to an event. The approach considers the spatial-temporal correlation between neighbouring sensor nodes and sensors' data values. Through a comparison study with two works from the literature, simulation results show that the proposed approach outperforms the studied techniques in terms of several metrics such as Detection Rate (DR), False Alarm Rate (FAR), Accuracy rate (ACC), F1_score and Area Under the Curve (AUC).
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Romany F. Mansour, S. Abdel-Khalek, Ines Hilali-Jaghdam, Jamel Nebhen, Woong Cho, Gyanendra Prasad Joshi
Summary: This paper designs an intelligent outlier detection with machine learning empowered big data analytics (IODML-BDA) model for mobile edge computing (MEC). The model utilizes adaptive synthetic sampling-based outlier detection techniques and oppositional swallow swarm optimization-based feature selection techniques. Experimental analysis on various datasets confirms the higher accuracy of the proposed model.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Management
Lixu Li, Yeming Gong, Zhiqiang Wang, Shan Liu
Summary: This study examines the impact of big data and supply chain integration on supply chain performance. The authors find that big data analytics technology capability and supply chain integration have a mediating effect on supply chain performance, and they can help firms develop different levels of capabilities to survive and improve performance in the context of COVID-19.
INTERNATIONAL JOURNAL OF OPERATIONS & PRODUCTION MANAGEMENT
(2023)
Article
Green & Sustainable Science & Technology
Ricardo Chalmeta, Jose-Eduardo Barqueros-Munoz
Summary: This paper proposes a framework for sustainable supply chain management composed of six dimensions and validates its practical utility, completeness, and level of detail through questionnaires.
Article
Computer Science, Information Systems
Jin Peng, Lin Chen, Bo Zhang
Summary: This paper investigates an integrated transportation planning and retailing optimization problem in a supply chain network under different carbon regulatory policies using big data technology. Uncertainty theory is applied to handle the uncertainty in big data information. The research results can assist supply chain managers in decision-making and governments in formulating effective carbon regulatory policies.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Maryam Ziaee, Himanshu Kumar Shee, Amrik Sohal
Summary: This study aims to explore the application of big data analytics in pharmaceutical supply chain for better business intelligence based on information processing view theory. The findings revealed that big data analytics is more practical and beneficial in the planning, delivery and return processes of the supply chain. The study informs managers about the strategic role of big data analytics capabilities in supply chain processes for improved business intelligence.
INDUSTRIAL MANAGEMENT & DATA SYSTEMS
(2023)
Article
Business
Ghulam Qader, Muhammad Junaid, Qamar Abbas, Muhammad Shujaat Mubarik
Summary: This study investigates the impact of Industry 4.0 on supply chain performance, with the mediating role of supply chain resilience and the moderating role of supply chain visibility. The findings suggest that Industry 4.0 has a significant impact on supply chain performance and that supply chain resilience and visibility play important roles in this relationship.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2022)
Review
Green & Sustainable Science & Technology
Joash Mageto
Summary: Sustainable supply chain management has become a significant research topic due to climate change, with the introduction of sustainable development goals by the United Nations. Big data analytics can enhance SSCM in manufacturing supply chains, but challenges such as cyberattacks and information technology skills gap exist.
Article
Business
Anish Kumar, Sachin Kumar Mangla, Pradeep Kumar, Malin Song
Summary: Food Supply Chains (FSCs) are essential services during a pandemic, with Perishable Food Supply Chains (PFSC) facing higher risks. This study identifies and analyzes risk mitigation strategies for PFSC during the COVID-19 pandemic, prioritizing strategies such as collaborative management and proactive business continuity planning. The fuzzy-best worst methodology (F-BWM) is an effective approach for analyzing risk mitigation strategies in unique business contingencies.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Chemistry, Multidisciplinary
Alifia Revan Prananda, Eka Legya Frannita, Augustine Herini Tita Hutami, Muhammad Rifqi Maarif, Norma Latif Fitriyani, Muhammad Syafrudin
Summary: Recently, the development of a rapid detection approach using artificial intelligence for detecting glaucoma disease has been proposed. Cup-to-disc ratio (CDR) and disc damage likelihood scale (DDLS) are commonly used for glaucoma analysis, but their variability in individuals makes it difficult. To solve this problem, a new method of glaucoma detection based on analyzing the damage to the retinal nerve fiber layer (RNFL) is proposed, with a pre-treatment process and a glaucoma classification process. With the use of nine deep-learning architectures, the proposed method achieves a highest accuracy of 92.88% and an AUC of 89.34% in the evaluation using the ORIGA dataset, showing improved results compared to previous research works. The model is expected to contribute to the improvement of eye disease diagnosis and assessment.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Wenxiao Zhao, Muhammad Syafrudin, Norma Latif Fitriyani
Summary: In this study, a new Artificial-SAR-Vessel dataset was generated by combining the FUSAR-Ship dataset and the SimpleCopyPaste method. A novel multi-category vessel detection method called CRAS-YOLO was proposed, which integrated a convolutional block attention module (CBAM), receptive fields block (RFB), and adaptively spatial feature fusion (ASFF) based on YOLOv5s. The experiments demonstrated that the proposed CRAS-YOLO model achieved high precision, recall rate, and mean average precision (mAP) (0.5) of up to 90.4%, 88.6%, and 92.1% respectively.
Review
Computer Science, Information Systems
Muhammad Anshari, Muhammad Syafrudin, Abby Tan, Norma Latif Fitriyani, Yabit Alas
Summary: The emergence of AI and its derivative technologies, such as ML and DL, has brought about a new era of knowledge management. ML, a type of AI, requires new tools and techniques to analyze data for improved decision-making and predictions. This study aims to investigate the extent of ML applications in knowledge management.
Article
Mathematics
Norma Latif Fitriyani, Muhammad Syafrudin, Siti Maghfirotul Ulyah, Ganjar Alfian, Syifa Latif Qolbiyani, Chuan-Kai Yang, Jongtae Rhee, Muhammad Anshari
Summary: Type 2 diabetes (T2D) and non-alcoholic fatty liver disease (NAFLD) have a strong relationship and often coexist. This study analyzed T2D screening scores in people with NAFLD and proposed an early prediction model using logistic regression-based feature selection and multi-layer perceptrons. The analysis revealed a prevalence of 8.13% for prediabetes and 37.19% for diabetes among NAFLD patients. Clinical tests such as ALT, AST, ALP, GGT, and SBP were found to be significant predictors of T2D in both prediabetes and diabetes NAFLD datasets. The proposed model showed superior performance compared to other machine learning models, achieving accuracy rates of 92.11% and 83.05% in the two datasets, with improvement scores of 1.35% and 5.35% after feature selection.
Article
Computer Science, Information Systems
Muhammad Rifqi Maarif, Arif Rahman Saleh, Muhammad Habibi, Norma Latif Fitriyani, Muhammad Syafrudin
Summary: In this study, an energy usage forecasting model using LSTM and parameter analysis using XAI were proposed. The models were evaluated using a public energy usage dataset from a steel company, and achieved the lowest RMSE scores for single-layer LSTM, double-layer LSTM, and bi-directional LSTM. Interpretability analysis revealed the strong influence of two parameters on the model output. This study is expected to provide industry practitioners with accurate energy forecasting LSTM models and insight for policymakers and industry leaders to support sustainable development.
Article
Computer Science, Information Systems
Ganjar Alfian, Muhammad Syafrudin, Norma Latif Fitriyani, Sahirul Alam, Dinar Nugroho Pratomo, Lukman Subekti, Muhammad Qois Huzyan Octava, Ninis Dyah Yulianingsih, Fransiskus Tatas Dwi Atmaji, Filip Benes
Summary: In recent years, RFID technology has been used to monitor product movements within a supply chain in real time. This study investigates the performance of machine learning algorithms in detecting the movement and direction of passive RFID tags. The proposed model achieved an accuracy of up to 94.251% in detecting the movement and direction of RFID tags and can be applied to a web-based monitoring system.
Article
Computer Science, Artificial Intelligence
Inzamam Mashood Nasir, Mudassar Raza, Siti Maghfirotul Ulyah, Jamal Hussain Shah, Norma Latif Fitriyani, Muhammad Syafrudin
Summary: This study proposes a network-level fusion method that extracts unique features by combining multiple pre-trained models effectively. Five fusion strategies, including sum, max, concatenation, convolutional, and bilinear fusion, are used to fuse three pre-trained models. Finally, an optimization method is used to extract descriptors, and the proposed model is evaluated on four publicly available datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Green & Sustainable Science & Technology
Ismallianto Isia, Tony Hadibarata, Muhammad Noor Hazwan Jusoh, Rajib Kumar Bhattacharjya, Noor Fifinatasha Shahedan, Norma Latif Fitriyani, Muhammad Syafrudin
Summary: This paper systematically studies 11 flood disaster case studies from 2010 to 2022 using databases from Springer Link, Science Direct, JSTOR, and Web of Science. The findings reveal that demographic characteristics, socioeconomic status, and access to healthcare crucially determine social vulnerability to adverse flood events. However, many social vulnerability indicators fail to adequately consider the influence of these factors. The article emphasizes the importance of considering specific situations and locations when understanding vulnerability and concludes by offering recommendations to customize quantitative indicators of social vulnerability to flood contexts.
Article
Green & Sustainable Science & Technology
Zahra Ahanin, Maizatul Akmar Ismail, Narinderjit Singh Sawaran Singh, Ammar AL-Ashmori, Muhammad Syafrudin, Ganjar Alfian, Norma Latif Fitriyani, Muhammad Anshari
Summary: Emotions are crucial for identifying an individual's attitude and mental state. Detecting and classifying emotions can enhance Human-Computer Interaction systems in Natural Language Processing applications, leading to more effective decision-making in organizations. This paper proposes a hybrid feature extraction model that combines engineered features with deep learning based features for emotion classification in English text.
Article
Computer Science, Interdisciplinary Applications
Nehad T. A. Ramaha, Ruaa M. Mahmood, Alaa Ali Hameed, Norma Latif Fitriyani, Ganjar Alfian, Muhammad Syafrudin
Summary: A brain tumor is a collection of aberrant tissues, so it is crucial to classify tumors of the brain using MRI before beginning therapy. Tumor segmentation and classification from brain MRI scans using machine learning techniques are widely recognized as challenging and important tasks. The potential applications of machine learning in diagnostics, preoperative planning, and postoperative evaluations are substantial.
Article
Computer Science, Information Systems
Ganjar Alfian, Muhammad Qois Huzyan Octava, Farhan Mufti Hilmy, Rachma Aurya Nurhaliza, Yuris Mulya Saputra, Divi Galih Prasetyo Putri, Firma Syahrian, Norma Latif Fitriyani, Fransiskus Tatas Dwi Atmaji, Umar Farooq, Dat Tien Nguyen, Muhammad Syafrudin
Summary: This study proposes a method to analyze customer browsing activity in retail stores using RFID technology and machine learning models. The method accurately identifies different customer shopping activities and improves the performance of the model. The results can assist managers in understanding customer preferences and improve product placement, promotions, and customer recommendations.