Journal of Industrial Information Integration最新文献

{"title":"A blockchain-enabled horizontal federated learning system for fuzzy invasion detection in maintaining space security","authors":"Y.P. Tsang ,&nbsp;C.H. Wu ,&nbsp;W.H. Ip ,&nbsp;K.L. Yung","doi":"10.1016/j.jii.2024.100745","DOIUrl":"10.1016/j.jii.2024.100745","url":null,"abstract":"<div><div>Recent advances in Industry 4.0 technologies drive robotic objects' decentralisation and autonomous intelligence, raising emerging space security concerns, specifically invasion detection. Existing physical detection methods, such as vision-based and radar-based techniques, are ineffective in detecting small-scale objects moving at low speeds. Therefore, it is worth investigating and leveraging the power of artificial intelligence to discover invasion patterns through space data analytics. Additionally, fuzzy modelling is needed for invasion detection to enhance the capability of handling data uncertainty and adaptability to evolving invasion patterns. This study proposes a Blockchain-Enabled Federated Fuzzy Invasion Detection System (BFFIDS) to address these challenges and establish real-time invasion detection capabilities for edge devices in the low earth orbit. The entire model training process is performed over the blockchain and horizontal federated learning scheme, securely reaching consensus in model updates. The system's effectiveness is examined through case analyses on a publicly available dataset. The results indicate that the proposed system can effectively maintain the desired invasion detection performance, with an average Area Under Curve (AUC) value of 0.99 across experimental runs. Utilising the blockchain-based federated learning process, the total size of transmitted data is reduced by 89.5 %, supporting the development of lightweight invasion detection applications. A closed-loop mechanism for continuously updating the space invasion detection model is established to achieve high space security.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100745"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation and evaluation of a smart machine monitoring system under industry 4.0 concept","authors":"Jagmeet Singh ,&nbsp;Amandeep Singh ,&nbsp;Harwinder Singh ,&nbsp;Philippe Doyon-Poulin","doi":"10.1016/j.jii.2024.100746","DOIUrl":"10.1016/j.jii.2024.100746","url":null,"abstract":"<div><div>Production planning and control (PPC) is essential in industrial manufacturing, ensuring efficient resource allocation and process management. Industry 4.0 introduces advanced technologies like cyber physical systems (CPS), artificial intelligence (AI), and internet of things (IoT) to effectively manage and monitor manufacturing operations. However, integrating these technologies into existing machinery, particularly for small and medium-sized enterprises (SMEs), poses challenges due to complexity and cost. The present study addresses this gap by designing and implementing a Smart Machine Monitoring System (SMMS) compatible with existing machinery such as computer numerical control and special purpose machines. The SMMS integrates IoT-based systems with AI algorithms to enhance machine tool utilization through effective planning, scheduling, and real-time monitoring. Through a nine-month case study in the shackle bolt manufacturing section, it was tested and compared to an Enterprise Resource Planning (ERP)-based system to assess its performance. Results showed significant improvements in production output, machine utilization rates, labor efficiency, and overall manufacturing costs. In conclusion, this study contributes to the body of knowledge on practical Industry 4.0 implementations for SMEs, offering insights into cost-effective solutions for enhancing operational efficiency and resource utilization in manufacturing environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100746"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated end-to-end multilingual method for low-resource agglutinative languages using Cyrillic scripts","authors":"Akbayan Bekarystankyzy ,&nbsp;Abdul Razaque ,&nbsp;Orken Mamyrbayev","doi":"10.1016/j.jii.2024.100750","DOIUrl":"10.1016/j.jii.2024.100750","url":null,"abstract":"<div><div>Millions of individuals across the world use automatic speech recognition (ASR) systems every day to dictate messages, operate gadgets, begin searches, and enable data entry in tiny devices. The engagement in these circumstances is determined by the accuracy of the voice transcriptions and the system's response. A second barrier to natural engagement for multilingual users is the monolingual nature of many ASR systems, which limit users to a single predefined language. A substantial amount of transcribed audio data must be used to train an ASR model to obtain one that is trustworthy and accurate. The absence of this data type affects a large number of languages, particularly agglutinative languages. Much research has been conducted using various strategies to improve models for low-resource languages. This study presents an integrated end-to-end multi-language ASR (EMASR) architecture that allows users to choose from a variety of spoken language combinations. The proposed EMASR presents an integrated design to support low-resource agglutinative languages by fusing the features of the multi-identifier module, voice fusion module, and recurrent neural network module. The proposed EMSAR identifies Turkic agglutinative languages (Kazakh, Bashkir, Kyrgyz, Saha, and Tatar) to enable multilingual training through the use of Connectionist Temporal Classification (CTC) and an attention mechanism that includes a language model (LM). The cognate word, sentence construction principles, and an alphabet are all present in these languages (Cyrillic). We use recent advancements in language identification to obtain recognition accuracy and latency characteristics. Experiment results reveal that multilingual training produces superior results than monolingual training in all languages tested. The Kazakh language obtained a spectacular result: word error rate (WER) was reduced to half and character error rate (CER) was reduced to one-third, demonstrating that this strategy may be beneficial for critically low-resource languages.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100750"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maize precision seeding scheme based on multi-sensor information fusion","authors":"Chunji Xie ,&nbsp;Li Yang ,&nbsp;Xiantao He ,&nbsp;Tao Cui ,&nbsp;Dongxing Zhang ,&nbsp;Hongsheng Li ,&nbsp;Tianpu Xiao ,&nbsp;Haoyu Wang","doi":"10.1016/j.jii.2024.100758","DOIUrl":"10.1016/j.jii.2024.100758","url":null,"abstract":"<div><div>Seeding plays a crucial role in agricultural production. The traditional mechanized seeding suffers from inefficiencies, low precision, and lack of control, which makes it inadequate for the high demands of the modern precision agriculture, such as the high speed, high precision, and real-time control. Therefore, this study proposes a precision seeding scheme based on multi-sensor information fusion. The system uses a Controller Area Network bus to collect and analyze data from multiple sensors for accurately controlling the seeding and fertilization mechanisms and real-time monitoring the operational conditions. In addition, the structural design, functional development, and field testing of the proposed seeding scheme are analyzed. A dual-speed measurement method, which employs an encoder and a Global Navigation Satellite System receiver, is then used to develop the motor drive model. The test results show that the maximum average error in motor speed does not exceed 1.5 %. The system can accurately alarm for seeding and fertilization faults reaching a 100 % success rate, with no missed or false alarms. The incorporated novel features include a field headland switch and a one-click pre-seeding function. During the lifting and lowering of the seeder, the motor stop and start success rate also reach 100 %, with a system response time &lt;0.7 s. The pre-seeding time can be arbitrarily set, which allows to avoid the issue of no seeds falling at the start of the seeder. Moreover, the wind pressure measurement of the system has an average relative error of 0.83 %. The long-term operation tests show no faults, and all the functions remain normal. Furthermore, the field test results show an average qualified seeding rate of 94.81 % and an average seed spacing variation coefficient of 14.1 %, which demonstrates the high accuracy and stability of the system.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100758"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comprehensive analysis of multi-strategic RIME algorithm for UAV path planning in varied terrains","authors":"Tao Gu ,&nbsp;Yajuan Zhang ,&nbsp;Limin Wang ,&nbsp;Yufei Zhang ,&nbsp;Muhammet Deveci ,&nbsp;Xin Wen","doi":"10.1016/j.jii.2024.100742","DOIUrl":"10.1016/j.jii.2024.100742","url":null,"abstract":"<div><div>Optimizing industrial information integration is fundamental to harnessing the potential of Industry 4.0, driving data-informed decisions that enhance operational efficiency, reduce costs, and improve competitiveness in modern industrial environments. Effective unmanned aerial vehicle (UAV) path planning is crucial within this optimization framework, supporting timely and reliable data collection and transmission for smarter decision-making. This study proposes an enhanced RIME (IRIME) algorithm for three-dimensional UAV path planning in complex urban environments, formulated as a multiconstraint optimization problem aimed at discovering optimal flight paths in intricate configuration spaces. IRIME integrates three strategic innovations into the RIME algorithm: a frost crystal diffusion mechanism for improved initial population diversity, a high-altitude condensation strategy to enhance global exploration, and a lattice weaving strategy to avoid premature convergence. Evaluated on the CEC2017 test set and six realistic urban scenarios, IRIME achieves an 86.21 % win rate across 100 functions. In scenarios 4–6, IRIME uniquely identifies the globally optimal paths, outperforming other algorithms that are limited to locally optimal solutions. We believe these findings demonstrate IRIME's capacity to address complex path-planning challenges, laying a robust foundation for its future application to broader industrial optimization tasks.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100742"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning assisted prediction of the nitric oxide (NO) solubility in various deep eutectic solvents","authors":"Hulin Jin ,&nbsp;Yong-Guk Kim ,&nbsp;Zhiran Jin ,&nbsp;Chunyang Fan","doi":"10.1016/j.jii.2024.100741","DOIUrl":"10.1016/j.jii.2024.100741","url":null,"abstract":"<div><div>Deep eutectic solvents (DESs) are recently proposed as green materials to remove nitric oxide (NO) from released streams into the atmosphere. The mathematical aspect of this process attracted less attention than it deserved. A straightforward approach in this field will help engineer DES chemistry and optimize the equilibrium conditions to maximize the amount of removed NO. This study covers this gap by constructing a reliable artificial neural network (ANN) to correlate the NO removal capacity of DES with equilibrium pressure/temperature and solvent chemistry. So, firstly, the physical meaningful features are selected to make the DES chemistry quantitative. It was found that the density is the best representative for the hydrogen-bound acceptor and hydrogen-bound donor. Also, the density and viscosity of the DESs exhibit the highest correlation with the NO solubility. Then, the hyperparameters of three famous ANN types (feedforward, recurrent, and cascade) are determined by combining trial-and-error and sensitivity analyzes. Finally, the ranking test distinguishes the ANN type with the lowest uncertainty toward estimating NO dissolution in DESs. The cascade neural network (CNN) with twelve and one neurons in the hidden and output layers equipped with the tangent hyperbolic and radial basis transfer functions is identified as the best ANN type for the given purpose. This model predicts 292 DES-NO equilibrium records collected from the literature with mean absolute errors = 0.033, relative absolute errors = 1.49 %, mean squared errors = 0.002, and coefficient of determination = 0.9998. Also, the present study helps understand the role of DES chemistry and operating conditions on the amount of removable NO by DESs. 1,3-dimethylthioureaP4444Cl (3:1) is recognized as the best DES to separate NO molecules from gaseous streams, respectively. The simulation results show that the unit mass of the best DES is capable of absorbing up to ∼27 mol of NO.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100741"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancement of industrial information systems through AI models to simulate the vibrational and acoustic behavior of machining operations","authors":"Nisar Hakam ,&nbsp;Khaled Benfriha","doi":"10.1016/j.jii.2024.100744","DOIUrl":"10.1016/j.jii.2024.100744","url":null,"abstract":"<div><div>Advanced simulation tools allow the optimization of processes prior to production implementation. Our study aims to integrate industrial information and data into a digital model based on artificial intelligence (AI) to simulate acoustic and vibration behavior during the production preparation phase. This model integrates real manufacturing conditions with generated vibrations and acoustic waves, creating a comprehensive simulation tool for acoustic and vibration behavior during the production preparation phase. By harnessing Internet of Things (IoT) sensors, Big Data, and Cyber-Physical Systems (CPS), our approach achieves a unified system that consolidates data from diverse sources, facilitating a seamless information flow within an Industry 4.0 framework. Small signal variations made it complex to model manufacturing operations using AI tools, as seen in recent studies. However, the proposed approach overcomes these challenges and has been successfully applied to a numerical lathe using sensors and advanced analytical tools, paving the way for a robust industrial information integration system to optimize and predict operational outcomes.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100744"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Empowering robotic training with kinesthetic learning and digital twins in human–centric industrial systems","authors":"Thien Tran ,&nbsp;Quang Nguyen ,&nbsp;Toan Luu ,&nbsp;Minh Tran ,&nbsp;Jonathan Kua ,&nbsp;Thuong Hoang ,&nbsp;Man Dien","doi":"10.1016/j.jii.2024.100743","DOIUrl":"10.1016/j.jii.2024.100743","url":null,"abstract":"<div><div>This paper presents a human-centric mixed reality (MR) collaborative training platform that employs a kinesthetic learning technique in industrial robotic training, specifically focusing on robot pick–and–place (RPP) operations. Collaborating with ABB Robotics Vietnam, we conducted a user study to investigate the user experiences and practical perceptions of university students and novice trainees via the human–centric training assessment. The study compares the traditional training (TT) RPP classroom as a conventional method with a new collaborative MR RPP training approach (N = 50). The MR training features a digital twin (DT) of ABB GoFa™ CRB–15000 collaborative robot in an immersive 360° Digital–Objects–Based Augmented Training Environment (360–ATE) using Microsoft HoloLens devices. The research evaluated the impact of MR and DT on human–robot interaction and collaboration, user experience, task performance, knowledge retention, and interpretation, as well as differences in perceptions between the two novice cohorts under each training condition. The primary research question explores “Whether the MR collaborative training platform with DT integration in 360–ATE can serve as an alternative approach for novice students and industrial trainees in RPP operations?”. The findings indicate that MR training is more engaging and effective in enhancing participant safety, confidence, and task performance, which also augments cognitive capabilities. The virtual contents on HoloLens, especially the DT, captured the attention and stimulated active learning abilities. Overall, participants in the MR cohort find the proposed training platform useful and easy to use. The platform has a positive influence on their intention to use similar 360–ATE–assisted training platforms in the future.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100743"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal-information-based optimized agricultural prescription recommendation system of crop electronic medical records","authors":"Chang Xu ,&nbsp;Junqi Ding ,&nbsp;Bo Wang ,&nbsp;Yan Qiao ,&nbsp;Lingxian Zhang ,&nbsp;Yiding Zhang","doi":"10.1016/j.jii.2024.100748","DOIUrl":"10.1016/j.jii.2024.100748","url":null,"abstract":"<div><div>Multimodal Crop Electronic Medical Records (CEMRs) contain complex information, including disease symptoms, crop conditions, environmental factors, and diagnostic prescriptions, making them crucial for intelligent prescription recommendations. However, effectively integrating complementary features from different CEMRs modalities has remained a key challenge. Current CEMRs research primarily focuses on unimodal data, and simplistic approaches like feature concatenation struggle to achieve in-depth cross-modal interactions. This study introduces a novel agricultural prescription recommendation model (named AgriPR) based on cross-modal multi-layer feature fusion. The model initially employs task-adaptive pre-trained BERT (TA-BERT) and ConvNeXt to encode text and image unimodal features respectively. Subsequently, it utilizes Bilinear Attention Networks (BAN) to bilinear features and combines them with bimodal encoding features for a multilayer fusion representation. Finally, a dual-layer Transformer performs re-interaction to emphasize key fused features, resulting in precise prescription recommendations. To evaluate AgriPR, we constructed a real CEMRs dataset containing 13 prescription categories from Beijing Plant Clinic. Experimental results demonstrate that AgriPR achieves outstanding performance, with a classification accuracy of 98.88 %, surpassing state-of-the-art models. Furthermore, the study compares and analyzes 8 encoder combinations, 6 feature fusion strategies, and 6 network layer configurations, highlighting the model's design advantages. Lastly, the model's adaptability was also tested with incomplete modality inputs (text-only or image-only) and missing information inputs (e.g., crop, environment, symptoms). The findings confirm AgriPR's practical applicability, providing a high-performance solution for agricultural management systems.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100748"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards cognitive intelligence-enabled product design: The evolution, state-of-the-art, and future of AI-enabled product design","authors":"Zuoxu Wang ,&nbsp;Xinxin Liang ,&nbsp;Mingrui Li ,&nbsp;Shufei Li ,&nbsp;Jihong Liu ,&nbsp;Lianyu Zheng","doi":"10.1016/j.jii.2024.100759","DOIUrl":"10.1016/j.jii.2024.100759","url":null,"abstract":"<div><div>Engineering design researchers have increasing interests in leveraging artificial intelligence (AI) techniques to a wide range of product design tasks, such as customer requirement analysis, product concept generation, design synthesis, and decision-making in product design. Indeed, AI techniques perform excellently on well-defined design tasks with clear problem definition, specialized solutions, and abundant training data. However, facing the ever-evolving AI techniques rapidly and radically changing the product design manner, there is still a lack of a systematic summary about the current stage of AI-enabled product design. Besides, although the current AI-enabled product design performs excellently on the well-defined tasks, the other advanced design tasks that need cognitive capability can still hardly be satisfyingly completed by the current product design system. This study systematically reviewed the literature on AI-enabled product design to understand its evolution and state-of-the-arts. To bridge the semantic gap between humans and systems, a novel cognitive intelligence-enabled product design (CIPD) framework is proposed, in which cognitive intelligence is the key enabler. The CIPD's key aspects, including its system architecture, human-like capabilities, enabling technologies, and potential applications, are also systematically discussed. It is hoped that this study could contribute to the future directions of the product design field and offer insightful guidance to the practitioners and researchers in their product design process.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"43 ","pages":"Article 100759"},"PeriodicalIF":10.4,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}