Providing reliable predictive maintenance is a critical industrial AI service essential for ensuring the high availability of manufacturing devices. Existing deep-learning methods present competitive results on such tasks but lack a general service-oriented framework to capture complex dependencies in industrial IoT sensor data. While Transformer-based models show strong sequence modeling capabilities, their direct deployment as robust AI services faces significant bottlenecks. Specifically, streaming sensor data collected in real-world service environments often exhibits multi-scale temporal correlations driven by machine working principles. Besides, the datasets available for training time-to-failure predictive services are typically limited in size. These issues pose significant challenges for directly applying existing models as robust predictive services. To address these challenges, we propose MsFormer, a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance. MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations across multi-streaming service data. Additionally, to accommodate data-scarce service environments, MsFormer adopts a lightweight attention mechanism with straightforward pooling operations instead of self-attention. Extensive experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods. Furthermore, MsFormer outperforms across industrial devices and operating conditions, demonstrating strong generalizability while maintaining a highly reliable Quality of Service (QoS).
The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model's ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.
Electromagnetic transient (EMT) simulation is essential for analyzing sub-cycle switching phenomena in industrial power systems; however, commercial EMT platforms present significant cost barriers for smaller utilities, consultancies, and academic institutions, particularly in developing regions. This paper validates KESTREL EMT, a free and open-source electromagnetic transient solver with Python integration, through three progressive case studies involving industrial capacitor switching transients. This work investigates energization, switching resonance and VFD interactions with capacitor banks. The results demonstrate that KESTREL, when supported by appropriate circuit modeling techniques, produces EMT responses consistent with analytical predictions and established IEEE benchmarks. This work establishes a validated and reproducible methodology for conducting industrial EMT studies using freely available, open-source tools.
Resilience non-equilibrium measurement, the ability to maintain fundamental functionality amidst failures and errors, is crucial for scientific management and engineering applications of industrial chain. The problem is particularly challenging when the number or types of multiple co-evolution of resilience (for example, randomly placed) are extremely chaos. Existing end-to-end deep learning ordinarily do not generalize well to unseen full-feld reconstruction of spatiotemporal co-evolution structure, and predict resilience of network topology, especially in multiple chaos data regimes typically seen in real-world applications. To address this challenge, here we propose industrial brain, a human-like autonomous cognitive decision-making and planning framework integrating higher-order activity-driven neuro network and CT-OODA symbolic reasoning to autonomous plan resilience directly from observational data of global variable. The industrial brain not only understands and model structure of node activity dynamics and network co-evolution topology without simplifying assumptions, and reveal the underlying laws hidden behind complex networks, but also enabling accurate resilience prediction, inference, and planning. Experimental results show that industrial brain significantly outperforms resilience prediction and planning methods, with an accurate improvement of up to 10.8\% over GoT and OlaGPT framework and 11.03\% over spectral dimension reduction. It also generalizes to unseen topologies and dynamics and maintains robust performance despite observational disturbances. Our findings suggest that industrial brain addresses an important gap in resilience prediction and planning for industrial chain.
Marcela Gonçalves dos Santos, Sylvain Hallé, Fábio Petrillo
Industrial robotic systems (IRS) are increasingly deployed in diverse environments, where failures can result in severe accidents and costly downtime. Ensuring the reliability of the software controlling these systems is therefore critical. Mutation testing, a technique widely used in software engineering, evaluates the effectiveness of test suites by introducing small faults, or mutants, into the code. However, traditional mutation operators are poorly suited to robotic programs, which involve message-based commands and interactions with the physical world. This paper explores the adaptation of mutation testing to IRS by defining domain-specific mutation operators that capture the semantics of robot actions and sensor readings. We propose a methodology for generating meaningful mutants at the level of high-level read and write operations, including movement, gripper actions, and sensor noise injection. An empirical study on a pick-and-place scenario demonstrates that our approach produces more informative mutants and reduces the number of invalid or equivalent cases compared to conventional operators. Results highlight the potential of mutation testing to enhance test suite quality and contribute to safer, more reliable industrial robotic systems.
Xiaoyan Ding,1 Yuhan Wang,2 Wenhao Wang3 1Library, Shandong Normal University, Jinan, People’s Republic of China; 2Department of Public Health, Shandong Second Medical University, Weifang, People’s Republic of China; 3Department of Organization, Qilu University of Technology, Jinan, People’s Republic of ChinaCorrespondence: Xiaoyan Ding, Email dingxiaoyan92@163.comBackground: Users may develop cyberchondria if they seek information about health issues excessively in online healthcare platforms. This can lead to a decline in their subjective well-being, which is essential for overall health. From the perspective of cyberchondria, we aim to investigate the factors influencing subjective well-being within the online healthcare context. Therefore, this study focuses on users’ subjective well-being, exploring the internal mechanism linking cyberchondria and subjective well-being.Methods: This study uses Partial Least Squares Structural Equation Modelling (PLS-SEM) to explore the internal mechanism of subjective well-being. A cross-sectional survey was conducted in China. The constructs in this study were measured based on previous mature scales. Data were collected from 299 users of online healthcare platforms for analysis.Results: The findings indicate that cyberchondria can lead to information anxiety and intermittent discontinuance. Information anxiety can affect subjective well-being. Furthermore, the study reveals that information avoidance plays a significant moderating role in these relationships.Conclusion: This study is innovative in its exploration of subjective well-being, offering valuable insights for users of online health platforms. Additionally, it highlights the moderating effect of information avoidance on cyberchondria, information anxiety, and intermittent discontinuance, which could enrich research into subjective well-being in the context of healthcare. The findings of this study could be used to improve the subjective well-being among users of online health platforms.Keywords: cyberchondria, information anxiety, intermittent discontinuance, online healthcare platform, subjective well-being
The advancements in urban commuting have enabled ease of travel for commuters. However, in the underdeveloped world, commuting has become a challenge for the mental health of commuters. A commuter who travels through public transport or their vehicle can develop depression and anxiety due to traffic congestion and unwanted delays. Symptoms of depression and anxiety can be mitigated through psychotherapeutic music. However, this music requires quiet rooms where a patient could listen to them. This can be overcome by playing music available on online streaming services via the commuters’ smart devices. The data from the sensors embedded in a commuter’s smart device is gathered and is termed the current context. The context includes both the data from the sensors and deduced data that is acquired through sensor services. The current context is then processed to determine the context of the commuter. The context is a label that is the outcome of a machine learning algorithm as part of context processing. The authors have utilized Bayesian probability to classify the current context of the commuter. Based on the classification outcome, which is termed context, a suitable playlist is generated and played on the commuters’ smart devices. A feedback loop enables improvement in classification as well as playlist generation. This proposed mechanism would improve the mental health of commuters including students, workers, and passengers, traveling to work and back frequently.
Sashnavi Naidu, Musawenkosi D. Saurombe, Dikeledi V. Mogoai
Orientation: Technological advancement and the coronavirus disease 2019 (COVID-19) pandemic substantially affected organisations’ overall recruitment function, causing a substantial shift towards a virtual way of recruiting talent.
Research purpose: The aim of this research was to explore the candidate experience of virtual interviews to ascertain how this experience can be enhanced because organisations are globally increasingly adopting the virtual approach.
Motivation for the study: It is important for human resource departments and recruiters to understand whether it is sustainable to utilise technologically based means of recruitment such as asynchronous video and synchronous online interviews in the workplace, particularly beyond the COVID-19 pandemic.
Research approach/design and method: The research followed a qualitative case-study approach. Purposive sampling techniques were employed to select the 14 participants who were interviewed one-on-one. Thematic analysis was then used to generate the themes and subthemes outlined in this article.
Main findings: The findings suggest that virtual interviews are quite useful in today’s digital age and will also be advantageous in the future. Nonetheless, there are some disadvantages to utilising virtual interviews. The prevailing advantages were convenience and fairness, while the prevailing disadvantages were one-way communication and a lack of the technology required to seamlessly participate in virtual interviewing. Participants believed virtual interviews would be favourable in future, because of their time and cost efficiency and convenience. Participants further agreed that the current virtual interviewing software used would require upgrading to enhance the overall candidate experience.
Practical/managerial implications: The research provides best practices for improving the candidate experience of virtual interviews.
Contribution/value-add: The research revealed aspects that should be carefully considered when using virtual interviewing methods, to ensure that the virtual interviewing experience for candidates is as efficient as possible as face-to-face interviewing.
She-Hui Chang,1,2,* Peng Wu,1,* Hui-Zhi Li,2 Xing-Yue Jin,2 Bao-Liang Zhong2,3 1Department of Psychology, Faculty of Education, Hubei University, Wuhan, Hubei, People’s Republic of China; 2Research Center for Psychological and Health Sciences, China University of Geosciences, Wuhan, People’s Republic of China; 3Department of Psychiatry, Wuhan Mental Health Center, Wuhan, Hubei, People’s Republic of China*These authors contributed equally to this workCorrespondence: Bao-Liang Zhong, Department of Psychiatry, Wuhan Mental Health Center, Wuhan, Hubei, People’s Republic of China, Email haizhilan@gmail.comPurpose: Existing research on mortality salience (MS) and prosocial behavior demonstrates inconsistent findings, suggesting potential moderation by psychological variables. One such potential moderator is temporal perspective, which fundamentally shapes individuals’ understanding of life course. This study examines how temporal perspective moderates the effect of MS on prosocial behavior.Patients and Methods: A 3 (blank control vs linear temporal perspective vs cyclical temporal perspective) × 2 (MS vs dental pain) between-subjects design was implemented. Participants (N=212) were randomly assigned to different groups. Prosocial behavior was measured through self-reported helping intentions. Participants’ prosocial behavior was compared across six experimental conditions defined by the combination of temporal perspective and MS manipulations.Results: MS significantly increased prosocial behavior relative to control. Temporal perspective moderated this effect: Linear priming amplified MS-induced prosociality, whereas cyclical priming attenuated the effect to non-significance. Control group showed moderate MS effects. Critically, a significant interaction emerged between temporal perspective and MS in predicting prosocial behavior.Conclusion: The findings reconcile previous inconsistencies by demonstrating temporal perspective’s critical moderating role. Linear temporal perspective strengthens MS effects through enhanced existential threat awareness, while cyclical temporal perspective helps individuals avoid the awareness of mortality’s inevitability via natural cycle conceptualizations. This suggests temporal cognition interventions could modulate prosocial outcomes in death-related contexts, with implications for terror management applications in social behavior modification.Keywords: terror management theory, mortality salience, prosocial behavior, temporal perspective, linear temporal perspective, cyclical temporal perspective
The Industrial Internet of Things (IIoT) integrates interconnected sensors and devices to support industrial applications, but its dynamic environments pose challenges related to data drift. Considering the limited resources and the need to effectively adapt models to new data distributions, this paper introduces a Continual Learning (CL) approach, i.e., Distillation-based Self-Guidance (DSG), to address challenges presented by industrial streaming data via a novel generative replay mechanism. DSG utilizes knowledge distillation to transfer knowledge from the previous diffusion-based generator to the updated one, improving both the stability of the generator and the quality of reproduced data, thereby enhancing the mitigation of catastrophic forgetting. Experimental results on CWRU, DSA, and WISDM datasets demonstrate the effectiveness of DSG. DSG outperforms the state-of-the-art baseline in accuracy, demonstrating improvements ranging from 2.9% to 5.0% on key datasets, showcasing its potential for practical industrial applications.
Recently, generative AI (GAI), with their emerging capabilities, have presented unique opportunities for augmenting and revolutionizing industrial recommender systems (Recsys). Despite growing research efforts at the intersection of these fields, the integration of GAI into industrial Recsys remains in its infancy, largely due to the intricate nature of modern industrial Recsys infrastructure, operations, and product sophistication. Drawing upon our experiences in successfully integrating GAI into several major social and e-commerce platforms, this survey aims to comprehensively examine the underlying system and AI foundations, solution frameworks, connections to key research advancements, as well as summarize the practical insights and challenges encountered in the endeavor to integrate GAI into industrial Recsys. As pioneering work in this domain, we hope outline the representative developments of relevant fields, shed lights on practical GAI adoptions in the industry, and motivate future research.
Psychological research often involves understanding psychological constructs through conducting factor analysis on data collected by a questionnaire, which can comprise hundreds of questions. Without interactive systems for interpreting factor models, researchers are frequently exposed to subjectivity, potentially leading to misinterpretations or overlooked crucial information. This paper introduces FAVis, a novel interactive visualization tool designed to aid researchers in interpreting and evaluating factor analysis results. FAVis enhances the understanding of relationships between variables and factors by supporting multiple views for visualizing factor loadings and correlations, allowing users to analyze information from various perspectives. The primary feature of FAVis is to enable users to set optimal thresholds for factor loadings to balance clarity and information retention. FAVis also allows users to assign tags to variables, enhancing the understanding of factors by linking them to their associated psychological constructs. Our user study demonstrates the utility of FAVis in various tasks.
Mirko Duradoni, Veronica Spadoni, Mustafa Can Gursesli
et al.
With the growing prevalence of online social interactions, it is crucial to understand how the social dimension affects well-being. This study investigates the relationship between the Need for Online Social Feedback (NfOSF) and individuals’ well-being, considering the moderating role of perceived online reputation. A total of 1398 participants, predominantly female, aged 14 to 61, completed an online questionnaire. The results revealed an M-shaped pattern, indicating that both dissatisfaction and excessive satisfaction with online reputation were associated with lower well-being. For those dissatisfied with their reputation, a high desire for social feedback correlated with reduced well-being, as validation from the social environment, was lacking. Similarly, individuals with fully satisfying reputations experienced frustration in their pursuit of online social feedback. In this case, the “Fame” dimension of the NfOSF scale exhibited a negative association with well-being, highlighting the impact of grandiose expectations. The findings underscore the subjective nature of this relationship, emphasizing the role of individual characteristics and social context.
Fabian Sturm, Elke Hergenroether, Julian Reinhardt
et al.
This work presents the Industrial Hand Action Dataset V1, an industrial assembly dataset consisting of 12 classes with 459,180 images in the basic version and 2,295,900 images after spatial augmentation. Compared to other freely available datasets tested, it has an above-average duration and, in addition, meets the technical and legal requirements for industrial assembly lines. Furthermore, the dataset contains occlusions, hand-object interaction, and various fine-grained human hand actions for industrial assembly tasks that were not found in combination in examined datasets. The recorded ground truth assembly classes were selected after extensive observation of real-world use cases. A Gated Transformer Network, a state-of-the-art model from the transformer domain was adapted, and proved with a test accuracy of 86.25% before hyperparameter tuning by 18,269,959 trainable parameters, that it is possible to train sequential deep learning models with this dataset.
Federated Learning (FL), as a rapidly evolving privacy-preserving collaborative machine learning paradigm, is a promising approach to enable edge intelligence in the emerging Industrial Metaverse. Even though many successful use cases have proved the feasibility of FL in theory, in the industrial practice of Metaverse, the problems of non-independent and identically distributed (non-i.i.d.) data, learning forgetting caused by streaming industrial data, and scarce communication bandwidth remain key barriers to realize practical FL. Facing the above three challenges simultaneously, this paper presents a high-performance and efficient system named HFEDMS for incorporating practical FL into Industrial Metaverse. HFEDMS reduces data heterogeneity through dynamic grouping and training mode conversion (Dynamic Sequential-to-Parallel Training, STP). Then, it compensates for the forgotten knowledge by fusing compressed historical data semantics and calibrates classifier parameters (Semantic Compression and Compensation, SCC). Finally, the network parameters of the feature extractor and classifier are synchronized in different frequencies (Layer-wiseAlternative Synchronization Protocol, LASP) to reduce communication costs. These techniques make FL more adaptable to the heterogeneous streaming data continuously generated by industrial equipment, and are also more efficient in communication than traditional methods (e.g., Federated Averaging). Extensive experiments have been conducted on the streamed non-i.i.d. FEMNIST dataset using 368 simulated devices. Numerical results show that HFEDMS improves the classification accuracy by at least 6.4% compared with 8 benchmarks and saves both the overall runtime and transfer bytes by up to 98%, proving its superiority in precision and efficiency.
In 2017 a definition of spiral tilings was given, thereby answering a question posed by Grünbaum and Shephard in the late 1970s. The author had the pleasure to discuss the topic via e-mail with Branko Grünbaum in his 87th year. During this correspondence the question arose whether a spiral structure (given a certain definition of it) could be recognized automatically or whether "to some extent, at least, the spiral effect is psychological", as Grünbaum and Shephard had conjectured in 1987 (see exercise section of chapter 9.5 in "Tilings and Patterns"). In this paper, an algorithm for automatic detection of such a tiling's spiral structure and its first implementation results will be discussed. Finally, the definitions for several types of spiral tilings are refined based on this investigation.
In this essay, we will defend the thesis that the multi-computational paradigm is a natural way of thinking about the fourth industrial revolution. This will be done considering the geometry that emerges as the continuum limit of multiway systems.