Hasil untuk "Industrial psychology"

Xueying Du, Jiayi Feng, Yi Zou et al.

Static analysis tools (SATs) are widely adopted in both academia and industry for improving software quality, yet their practical use is often hindered by high false positive rates, especially in large-scale enterprise systems. These false alarms demand substantial manual inspection, creating severe inefficiencies in industrial code review. While recent work has demonstrated the potential of large language models (LLMs) for false alarm reduction on open-source benchmarks, their effectiveness in real-world enterprise settings remains unclear. To bridge this gap, we conduct the first comprehensive empirical study of diverse LLM-based false alarm reduction techniques in an industrial context at Tencent, one of the largest IT companies in China. Using data from Tencent's enterprise-customized SAT on its large-scale Advertising and Marketing Services software, we construct a dataset of 433 alarms (328 false positives, 105 true positives) covering three common bug types. Through interviewing developers and analyzing the data, our results highlight the prevalence of false positives, which wastes substantial manual effort (e.g., 10-20 minutes of manual inspection per alarm). Meanwhile, our results show the huge potential of LLMs for reducing false alarms in industrial settings (e.g., hybrid techniques of LLM and static analysis eliminate 94-98% of false positives with high recall). Furthermore, LLM-based techniques are cost-effective, with per-alarm costs as low as 2.1-109.5 seconds and $0.0011-$0.12, representing orders-of-magnitude savings compared to manual review. Finally, our case analysis further identifies key limitations of LLM-based false alarm reduction in industrial settings.

Wahyu Rahmaniar, Kenji Suzuki

Traditional deep learning models often lack annotated data, especially in cross-domain applications such as anomaly detection, which is critical for early disease diagnosis in medicine and defect detection in industry. To address this challenge, we propose Multi-AD, a convolutional neural network (CNN) model for robust unsupervised anomaly detection across medical and industrial images. Our approach employs the squeeze-and-excitation (SE) block to enhance feature extraction via channel-wise attention, enabling the model to focus on the most relevant features and detect subtle anomalies. Knowledge distillation (KD) transfers informative features from the teacher to the student model, enabling effective learning of the differences between normal and anomalous data. Then, the discriminator network further enhances the model's capacity to distinguish between normal and anomalous data. At the inference stage, by integrating multi-scale features, the student model can detect anomalies of varying sizes. The teacher-student (T-S) architecture ensures consistent representation of high-dimensional features while adapting them to enhance anomaly detection. Multi-AD was evaluated on several medical datasets, including brain MRI, liver CT, and retina OCT, as well as industrial datasets, such as MVTec AD, demonstrating strong generalization across multiple domains. Experimental results demonstrated that our approach consistently outperformed state-of-the-art models, achieving the best average AUROC for both image-level (81.4% for medical and 99.6% for industrial) and pixel-level (97.0% for medical and 98.4% for industrial) tasks, making it effective for real-world applications.

Yuzhan Hang, Zhenhua Ling, Quan Liu et al.

As artificial intelligence (AI) systems increasingly enter trust-dependent domains, questions arise about whether their behaviour reflects genuine trustworthiness or merely the illusion of it. This study examined how humans and large language models (LLMs) establish and adjust trust in dynamic social interactions using a 50-round trust game. Across 100 human participants and three leading LLMs—ChatGPT-3.5, ChatGPT-4o and DeepSeek-V3—we compared trust trajectories, responsiveness to partner behaviour and reactions to unexpected outcomes. Human participants adjusted trust in line with partner trustworthiness and exhibited symmetrical responses to unexpected gains and violations. In contrast, LLMs showed fixed, model-specific behaviour with little to no adaptation based on interaction history. Despite their cooperative appearance, AI agents lacked mechanisms for social learning and trust calibration. These findings highlight a fundamental disconnect between perceived and actual AI behaviour and underscore the need for cautious interpretation of AI trust signals in socially sensitive contexts.

Dhaval Patel, Shuxin Lin, James Rayfield et al.

AI for Industrial Asset Lifecycle Management aims to automate complex operational workflows, such as condition monitoring and maintenance scheduling, to minimize system downtime. While traditional AI/ML approaches solve narrow tasks in isolation, Large Language Model (LLM) agents offer a next-generation opportunity for end-to-end automation. In this paper, we introduce AssetOpsBench, a unified framework for orchestrating and evaluating domain-specific agents for Industry 4.0. AssetOpsBench provides a multimodal ecosystem comprising a catalog of four domain-specific agents, a curated dataset of 140+ human-authored natural-language queries grounded in real industrial scenarios, and a simulated, CouchDB-backed IoT environment. We introduce an automated evaluation framework that uses three key metrics to analyze architectural trade-offs between the Tool-As-Agent and Plan-Executor paradigms, along with a systematic procedure for the automated discovery of emerging failure modes. The practical relevance of AssetOpsBench is demonstrated by its broad community adoption, with 250+ users and over 500 agents submitted to our public benchmarking platform, supporting reproducible and scalable research for real-world industrial operations. The code is accesible at https://github.com/IBM/AssetOpsBench .

Roosa Risto, Mohit Sethi, Mika Katara

The Cyber Resilience Act (CRA) is a new European Union (EU) regulation aimed at enhancing the security of digital products and services by ensuring they meet stringent cybersecurity requirements. This paper investigates the challenges that industrial equipment manufacturing companies anticipate while preparing for compliance with CRA through a comprehensive survey. Key findings highlight significant hurdles such as implementing secure development lifecycle practices, managing vulnerability notifications within strict timelines, and addressing gaps in cybersecurity expertise. This study provides insights into these specific challenges and offers targeted recommendations on key focus areas, such as tooling improvements, to aid industrial equipment manufacturers in their preparation for CRA compliance.

Anwar Ahmed Khan, Indrakshi Dey

Efficient medium access control (MAC) is critical for enabling low-latency and reliable communication in industrial Machine-to-Machine (M2M) net-works, where timely data delivery is essential for seamless operation. The presence of multi-priority data in high-risk industrial environments further adds to the challenges. The development of tens of MAC schemes over the past decade often makes it a tough choice to deploy the most efficient solu-tion. Therefore, a comprehensive cross-comparison of major MAC protocols across a range of performance parameters appears necessary to gain deeper insights into their relative strengths and limitations. This paper presents a comparison of Contention window-based MAC scheme BoP-MAC with a fragmentation based, FROG-MAC; both protocols focus on reducing the delay for higher priority traffic, while taking a diverse approach. BoP-MAC assigns a differentiated back-off value to the multi-priority traffic, whereas FROG-MAC enables early transmission of higher-priority packets by fragmenting lower-priority traffic. Simulations were performed on Contiki by varying the number of nodes for two traffic priorities. It has been shown that when work-ing with multi-priority heterogenous data in the industrial environment, FROG-MAC results better both in terms of delay and throughput.

Mannangatti Vijayarani, Ganesan Balamurugan, Radhakrishnan Govindan et al.

The rise of social media, while revolutionizing the way one communicates, has also produced a rampant issue of cyberbullying with severe aftermaths, including emotional harm, social exclusion, and even suicide in some cases. Efforts have been ongoing to stop this, yet cyberbullying continues its growth through anonymity and ready accessibility provided by online resources. Deep learning techniques appeared to be the most promising, as they allow for recognizing cyberbullying through analyzing textual content and images and various user behaviors, yielding more accurate and comprehensive detection procedures than the traditional ones applied. Among the models using transformer-based and recurrent neural networks, there are perfect models for detecting harassment and threats, impersonation, and cyberbullying. Multimodal data, including emojis and sentiment analysis, have been added to improve detection accuracy as they capture subtle nuances in online communication. However, challenges persist in terms of difficulties in annotating data, slang, and context-dependent interpretations of cyberbullying. The anonymity of users further complicates the identification of perpetrators. This short communication discusses the potential of deep learning in tackling cyberbullying, underlining recent progress, challenges, and the need for further research and collaboration between academia, industry, and policymakers to produce more effective, ethical, and culturally sensitive solutions for cyberbullying detection worldwide.

Benjamin Alt, Florian Stöckl, Silvan Müller et al.

Surface treatment tasks such as grinding, sanding or polishing are a vital step of the value chain in many industries, but are notoriously challenging to automate. We present RoboGrind, an integrated system for the intuitive, interactive automation of surface treatment tasks with industrial robots. It combines a sophisticated 3D perception pipeline for surface scanning and automatic defect identification, an interactive voice-controlled wizard system for the AI-assisted bootstrapping and parameterization of robot programs, and an automatic planning and execution pipeline for force-controlled robotic surface treatment. RoboGrind is evaluated both under laboratory and real-world conditions in the context of refabricating fiberglass wind turbine blades.

Ronny Müller, Claudia De Lazzari, Fernando Chirici et al.

Information Reconciliation is a critical component of Quantum Key Distribution, ensuring that mismatches between Alice's and Bob's keys are corrected. In this study, we analyze, simulate, optimize, and compare the performance of two prevalent algorithms used for Information Reconciliation: Cascade and LDPC codes in combination with the Blind protocol. We focus on their applicability in practical and industrial settings, operating in realistic and application-close conditions. The results are further validated through evaluation on a live industrial QKD system.

Yehu Chen, Muchen Xi, Jacob Montgomery et al.

We develop a novel measurement framework based on a Gaussian process coregionalization model to address a long-lasting debate in psychometrics: whether psychological features like personality share a common structure across the population, vary uniquely for individuals, or some combination. We propose the idiographic personality Gaussian process (IPGP) framework, an intermediate model that accommodates both shared trait structure across a population and "idiographic" deviations for individuals. IPGP leverages the Gaussian process coregionalization model to handle the grouped nature of battery responses, but adjusted to non-Gaussian ordinal data. We further exploit stochastic variational inference for efficient latent factor estimation required for idiographic modeling at scale. Using synthetic and real data, we show that IPGP improves both prediction of actual responses and estimation of individualized factor structures relative to existing benchmarks. In a third study, we show that IPGP also identifies unique clusters of personality taxonomies in real-world data, displaying great potential in advancing individualized approaches to psychological diagnosis and treatment.

Diego Vallarino

This paper examines the impact of fiscal incentives on industrial investment in Uruguay from 1974 to 2010. Using a mixed-method approach that combines econometric models with machine learning techniques, the study investigates both the short-term and long-term effects of fiscal benefits on industrial investment. The results confirm the significant role of fiscal incentives in driving long-term industrial growth, while also highlighting the importance of a stable macroeconomic environment, public investment, and access to credit. Machine learning models provide additional insights into nonlinear interactions between fiscal benefits and other macroeconomic factors, such as exchange rates, emphasizing the need for tailored fiscal policies. The findings have important policy implications, suggesting that fiscal incentives, when combined with broader economic reforms, can effectively promote industrial development in emerging economies.

Chenhao Zhang, Renhao Li, Minghuan Tan et al.

Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun

Liu Y

Yanhan Liu School of Education, University of Glasgow, Glasgow, UKCorrespondence: Yanhan Liu, Email meigong516972@163.comIntroduction: Resilience, a pivotal construct in positive psychology, remains incompletely understood in its facilitation of learners’ online engagement. This study aims to investigate the relationship between resilience, transactional distance, and Online Mathematics Learning Engagement (OMLE) among first-year university students.Methods: Utilizing a cross-lagged path analysis approach, the study surveyed 612 first-year students. Multiple models were constructed and compared to explore the mutual predictive relationships between resilience, transactional distance, and OMLE.Results: Among the compared models, Model 4 demonstrated the best fit. The model revealed that: (1) resilience at Time 1 and Time 2 positively predicted transactional distance at Time 2 and Time 3; (2) transactional distance at Time 1 and Time 2 positively predicted OMLE at Time 2 and Time 3; (3) resilience at Time 1 significantly predicted OMLE at Time 3; and (4) transactional distance at Time 2 fully mediated the relationship between resilience at Time 1 and OMLE at Time 3. Furthermore, mediational model analysis confirmed that transactional distance played a mediating role in the longitudinal relationship between resilience and OMLE. Using a cross-lagged mediational model with 5000 bootstrap samples, the indirect effect of transactional distance on the relationship between resilience at Time 1 and OMLE at Time 3 was significant and remained stable over time.Discussion: The findings suggest that resilience, as a positive psychological resource, stimulates students to seek and utilize protective resources in online environments, leading to more active participation in interpersonal communication and classroom interactions. Additionally, resilience helps students overcome emotional and practical difficulties encountered in online learning, thereby enhancing their OMLE. These insights offer valuable implications for educators, highlighting the potential to improve students’ online learning engagement by fostering their psychological resilience.Keywords: psychological resilience, transactional distance theory, online mathematics learning engagement, cross-lag model, university students

Sylvie Chraïbi

Since the 2000s, the development programs of international organizations, and in particular the World Bank, have been encouraging rulers and ruled to adopt a “resilient” attitude in the face of disasters - natural, economic, industrial... A concept borrowed from physics and then psychology, mostly translated into Arabic in the annual reports of the financial institution by the predicative noun صمود (ṣumūd). However, we observe that in the Arabic version of the 2019 report, other translational choices have been proposed, as if to fill a semantic void. Indeed, certain aspects of resilience, such as adaptation and restoration efforts, are absent from the صمود (ṣumūd) Sememe. On the other hand, the connotative charge of this word in the context of the modern history of the Arab world in general, and Palestine in particular, gives rise to connections on the ideological level that weaken its capacities to refer to resilience. We will show in this article that the two concepts, resilience and صمود (ṣumūd) are partially convergent central notions of two distinct fields - international development and Arab management of the Palestinian question - that have been integrated into distinct founding discourses, bearers of shared values of different orders. In this context, the “narrative” of resilience according to the World Bank reported in the multilingual 2019 report could become ambiguous in the Arabic version, so much so does the word صمود (ṣumūd) circulate in discourses committed to an issue that engages, politically, Arab institutions.

I. O. Merylova, K. V. Sokolova

The purpose of the article is to research the spiritual basis and motivation of human activity in the relationships between humans and the natural environment to create various forms of recreational spaces in the socio-cultural context of the post-industrial era. Theoretical basis. The research is based on the approach of analytical psychology by C. Jung, who identified the archetypes of the collective unconscious. These archetypes help overcome the limitations of the functional and pragmatic approach, which is focused on mere survival. They make sense and provide values in the relationship between humans and nature. Originality. The article evaluates how archetypal images of the collective unconscious, with the help of the Garden of Eden image in the socio-cultural context of European civilization, influence the recreational space in contemporary urban environments. The novelty of the work is also in the interdisciplinary approach, integrating knowledge from various fields such as philosophy, sociology, cultural studies, analytical psychology, and urban planning, which contributes to the profound understanding of complex socio-cultural processes. This paradigm emphasizes the interconnection and interdependence, adaptability, and co-evolution of society and nature, as well as requires the interdisciplinary methodological approach. Additionally, the article presents a fresh perspective on nature and its elements in terms of their importance both for individuals and society. Conclusions. The article investigates the socio-cultural factors that evoke the interest of man and society in natural factors as a recreational resource and determine the latest theoretical approaches to their use. Various recreational activities to create a renewed space provide a person with a full physical, socio-psychological and cognitive development. The humanization of the natural environment becomes the embodiment of the collective memory and history of mankind. The recreational space symbolizes spiritual values, so it is transformed from physical to socio-cultural and provides theoretical approaches to its implementation in modern urban planning practices.

Dara Kiu Yi Leung, Nicole Hiu Ling Wong, Jessie Ho Yin Yau et al.

Introduction: Hybrid training mode comprising in-person and teleconferencing sessions is effective and sustainable, yet no standardized principles guide its development for older people. This study aimed to develop a set of principles for hybrid-mode psychoeducation for older people from the experiences of middle-aged and older people in two folds: (1) examining the effects of hybrid-mode community psychoeducation and (2) identifying features that could enhance participants' experience. Methods: We delivered 12-hour Older Person Mental Health First Aid and 3-hour late-life depression training to adults aged 50 and older in in-person and hybrid modes. Hybrid group participants received technology-related support, including in-advance training and on-site support. All participants completed assessments on depression literacy, depression stigma, meaning in life, social support, depressive symptoms, and anxiety pre-and post-intervention and evaluated the program in open-ended questions. Results: A total of 471 in-person and 346 hybrid group participants completed the psychoeducation and post-assessment (80.4 % female, mean age = 64.73 years, SD = 7.29). Linear mixed models revealed improvements in depression literacy, depression stigma, meaning in life, social support, and anxiety (B = −1.43 to 0.13, all p < .001), with no significant difference between in-person and hybrid groups. Thematic analysis of open-ended questions identified three themes: (1) informational content with case studies, (2) hardcopy course handouts, and (3) interactive learning environment. Discussion/conclusion: Hybrid-mode and in-person psychoeducation had comparable benefits on middle-aged and older people. The TORCH principles, an acronym for Technology provision, On-site technical support, Rehearsal, Connection with group members, and Hardcopy notes, was derived from practice wisdom and qualitative findings to support older people in online learning.

Leonhard Faubel, Thomas Woudsma, Leila Methnani et al.

Machine learning (ML) has become a popular tool in the industrial sector as it helps to improve operations, increase efficiency, and reduce costs. However, deploying and managing ML models in production environments can be complex. This is where Machine Learning Operations (MLOps) comes in. MLOps aims to streamline this deployment and management process. One of the remaining MLOps challenges is the need for explanations. These explanations are essential for understanding how ML models reason, which is key to trust and acceptance. Better identification of errors and improved model accuracy are only two resulting advantages. An often neglected fact is that deployed models are bypassed in practice when accuracy and especially explainability do not meet user expectations. We developed a novel MLOps software architecture to address the challenge of integrating explanations and feedback capabilities into the ML development and deployment processes. In the project EXPLAIN, our architecture is implemented in a series of industrial use cases. The proposed MLOps software architecture has several advantages. It provides an efficient way to manage ML models in production environments. Further, it allows for integrating explanations into the development and deployment processes.

Gurjot Singh Bhatia, Yoann Corre, Marco Di Renzo

This paper presents an innovative method that can be used to produce deterministic channel models for 5G industrial internet-of-things (IIoT) scenarios. Ray-tracing (RT) channel emulation can capture many of the specific properties of a propagation scenario, which is incredibly beneficial when facing various industrial environments and deployment setups. But the environment's complexity, composed of many metallic objects of different sizes and shapes, pushes the RT tool to its limits. In particular, the scattering or diffusion phenomena can bring significant components. Thus, in this article, the Volcano RT channel simulation is tuned and benchmarked against field measurements found in the literature at two frequencies relevant to 5G industrial networks: 3.7 GHz (mid-band) and 28 GHz (millimeter-wave (mmWave) band), to produce calibrated ray-based channel model. Both specular and diffuse scattering contributions are calculated. Finally, the tuned RT data is compared to measured large-scale parameters, such as the power delay profile (PDP), the cumulative distribution function (CDF) of delay spreads (DSs), both in line-of-sight (LoS) and non-LoS (NLoS) situations and relevant IIoT channel properties are further explored.

Yunpeng Ma, Khalil Younis, Bestoun S. Ahmed et al.

Digital twins (DT) of industrial processes have become increasingly important. They aim to digitally represent the physical world to help evaluate, optimize, and predict physical processes and behaviors. Therefore, DT is a vital tool to improve production automation through digitalization and becomes more sophisticated due to rapidly evolving simulation and modeling capabilities, integration of IoT sensors with DT, and high-capacity cloud/edge computing infrastructure. However, the fidelity and reliability of DT software are essential to represent the physical world. This paper shows an automated and systematic test architecture for DT that correlates DT states with real-time sensor data from a production line in the forging industry. Our evaluation shows that the architecture can significantly accelerate the automatic DT testing process and improve its reliability. A systematic online DT testing method can significantly detect the performance shift and continuously improve the DT's fidelity. The snapshot creation methodology and testing agent architecture can be an inspiration and can be generally applicable to other industrial processes that use DT to generalize their automated testing.

Zhang C, Ma X, Liu L

Chunyu Zhang, Xiao Ma, Liping Liu School of Economics and Management, Guangxi Normal University, Guilin, 541006, People’s Republic of ChinaCorrespondence: Xiao Ma; Liping Liu, School of Economics and Management, Guangxi Normal University, No. 1 Yanzhong Road, Yanshan District, Guilin, 541006, People’s Republic of China, Email mxsawyer@163.com; 865248131@qq.comPurpose: Although prior research has found outdoor activities to be an important effect on employee well-being, the mechanisms of their effect are understudied. This study integrated the Broaden-and-Build Theory, Attention Restoration Theory and Cognitive Assessment Theory to examine the relation between passion for outdoor activities (two dimensions, namely, harmonious passion, obsessive passion) and employee well-being (three dimensions, namely, life well-being, workplace well-being, psychological well-being) by the mediating role of nature connectedness and the moderating role of environmental identity.Participants and Methods: Data were collected from 403 employees of Guangxi enterprises in China. The structural equation model was constructed using AMOS and SmartPLS to test the hypotheses proposed in this study.Results: Our results confirm that harmonious passion for outdoor activities had a positive effect on employee nature connectedness, workplace well-being and psychological well-being. Obsessive passion for outdoor activities had a negative effect on employee nature connectedness, life well-being and psychological well-being. Natural connectedness has a positive effect on all three dimensions of employee well-being. Nature connectedness mediates between harmonious passion for outdoor activities and all three dimensions of employee well-being. Environmental identity positively moderated the relationship between nature connectedness and the three dimensions of employee well-being. Harmonious passion for outdoor activities has no direct effect on employee life well-being. Obsessive passion for outdoor activities had no direct effect on employee workplace well-being.Conclusion: This study reveals the mechanism of passion for outdoor activities on employee well-being from a new perspective and unveils that the two dimensions of passion for outdoor activities have different effects on employees’ life well-being, workplace well-being, and psychological well-being. Business managers should give attention to the benefits of outdoor activities and nature connectedness for their employees, through which they can relieve stress at work, recover attention and improve well-being.Keywords: Passion for Outdoor Activities, Employee Well-being, Broaden-and-Build Theory, Attention Restoration Theory, Cognitive Assessment Theory