Gabriela Ghimpeteanu, Hayat Rajani, Josep Quintana
et al.
Ensuring food safety and quality is critical in the food processing industry, where the detection of contaminants remains a persistent challenge. This study presents an automated solution for detecting foreign objects on pork belly meat using hyperspectral imaging (HSI). A hyperspectral camera was used to capture data across various bands in the near-infrared (NIR) spectrum (900-1700 nm), enabling accurate identification of contaminants that are often undetectable through traditional visual inspection methods. The proposed solution combines pre-processing techniques with a segmentation approach based on a lightweight Vision Transformer (ViT) to distinguish contaminants from meat, fat, and conveyor belt materials. The adopted strategy demonstrates high detection accuracy and training efficiency, while also addressing key industrial challenges such as inherent noise, temperature variations, and spectral similarity between contaminants and pork belly. Experimental results validate the effectiveness of hyperspectral imaging in enhancing food safety, highlighting its potential for broad real-time applications in automated quality control processes.
Kiana Jafari Meimandi, Gabriela Aránguiz-Dias, Grace Ra Kim
et al.
As industry reports claim agentic AI systems deliver double-digit productivity gains and multi-trillion dollar economic potential, the validity of these claims has become critical for investment decisions, regulatory policy, and responsible technology adoption. However, this paper demonstrates that current evaluation practices for agentic AI systems exhibit a systemic imbalance that calls into question prevailing industry productivity claims. Our systematic review of 84 papers (2023--2025) reveals an evaluation imbalance where technical metrics dominate assessments (83%), while human-centered (30%), safety (53%), and economic assessments (30%) remain peripheral, with only 15% incorporating both technical and human dimensions. This measurement gap creates a fundamental disconnect between benchmark success and deployment value. We present evidence from healthcare, finance, and retail sectors where systems excelling on technical metrics failed in real-world implementation due to unmeasured human, temporal, and contextual factors. Our position is not against agentic AI's potential, but rather that current evaluation frameworks systematically privilege narrow technical metrics while neglecting dimensions critical to real-world success. We propose a balanced four-axis evaluation model and call on the community to lead this paradigm shift because benchmark-driven optimization shapes what we build. By redefining evaluation practices, we can better align industry claims with deployment realities and ensure responsible scaling of agentic systems in high-stakes domains.
Aaron Sander, Rosaria Cercola, Andrea Capogrosso
et al.
The Quantum Entrepreneurship Lab (QEL) is a one-semester, project-based course at the Technical University of Munich (TUM), designed to bridge the gap between academic research and industrial application in the quantum sector. As part of the Munich Quantum Valley (MQV) ecosystem, the course fosters interdisciplinary collaboration between technical and business students, equipping them with the skills necessary to contribute to or lead in the emerging quantum industry. The QEL curriculum integrates two complementary tracks. First, technical students form teams where they engage in cutting-edge, industry-relevant research topics under academic supervision. Meanwhile business students in a parallel course explore commercialization strategies, risks, and opportunities within the quantum technology landscape. Midway through the semester, a selection of the business students join the technical course to form interdisciplinary teams which assess the feasibility of transforming scientific concepts into viable business solutions. The course culminates in three key deliverables: a publication-style technical report, a white paper analyzing the business potential and financial requirements, and a startup pitch presented to the quantum community at a Demo Day. This work outlines the course structure, objectives, and outcomes, providing a model for other institutions seeking to cultivate a highly skilled, innovation-driven workforce in quantum science and technology.
The swift advancement of information technology has significantly impacted the energy transition. Being the largest energy consumer globally, China’s acceleration of the urban energy transition will promote sustainable development and pave the way for future development. This study examines the impact of the digital divide between cities regarding the energy transition by using panel data for 271 Chinese cities from 2006 to 2021. We found the following results. (1) The digital divide has an inhibitory effect on the energy transition of cities, hindering their development towards green and low-carbon development. (2) Further analyses found that the negative impact of the digital divide on energy transition can be effectively mitigated by strengthening urban infrastructure construction, promoting emerging technological innovation, and cultivating and attracting talent in the digital industry. (3) The results of the subsample analyses show that the inhibitory effect of the digital divide on energy transition is more significant in densely populated cities, economically and technologically developed cities, and non-resource-based cities. The above findings hold significant practical implications for overcoming the digital divide and the stagnation of energy transition, and for the scientific implementation of China’s “Carbon Neutrality” initiative.
Kadhim Z. Naser, Abdulamir Atalla Almayah, Abdulnasser M. Abbas
The use of efficient and environmentally friendly materials is a priority in the construction industry. In this study, the behavior of reinforced concrete corbels made of recycled concrete aggregate (RCA) was investigated. Twenty models were created and categorized into five Groups to examine various factors influencing the characteristics of the corbels. These factors included the replacement ratio of natural coarse aggregate with varying proportions of RCA, with a replacement ratio of 0 % designed for the reference mixture; the other mixtures had replacement ratios of 20 %,40 %, and 60 %. Additionally, the study assesses the amount of main and secondary reinforcement, the shear span-effective depth ratio (a/d), and compressive strength. The influence of these variables on ultimate load capacity, load-deflection curves, crack pattern, initial stiffness, and energy dissipation was investigated. The results indicated that the use of recycled concrete aggregate did not significantly affect the pattern of cracks, type of failure, and energy dissipation capabilities. At the same time, it had a modest impact on the ultimate load capacity, with a decrease of 4.4 %, 8.6 %, and 16 % at a replacement ratio of 20 %,40 %, and 60 %, respectively. Correspondingly, deflection increased from 3.63 mm to 4.27, 4.92, and 5.61 mm at the same replacement ratio. Furthermore, it was also noted that increasing replacement ratios resulted in a slight decrease in initial stiffness. The ultimate load capacity of the corbels was predicted using the theoretical equations proposed by the provisions of the ACI 318 code and the equations proposed by previous literature. The results indicated that using the equations proposed by Hwang et al. and Chetchotisak et al. provided more accurate estimates compared to the other models, yielding a coefficient of variations (COVs) of 4.8 and 5.1 %, respectively. In contrast, the values derived from the code equations were significantly more conservative.
Anna C. Schomberg, Wolf von Tümpling, Ellen Kynast
Uncontrolled mine site leakage poses massive indirect environmental pollution, particularly when harmful substances, like arsenic, infiltrate water bodies, affecting humans. Arsenic contamination, recognized as a severe environmental catastrophe, exemplifies the water quality footprint from a Moroccan cobalt mine supplying electric car construction. Applying the water quality footprint method, we determined that 30–615 m3 of virtual dilution water per electric car would be needed to reduce arsenic pollution below natural background levels in a scenario that assumes that 49 % of the cobalt from the respective mine enters the production of battery materials aligning with recent global cobalt demand and use figures. In such a scenario, this single mine's water quality footprint would constitute up to 0.15 % of Morocco's annual water availability, concerning all electric cars produced annually with cobalt from this mine, and would take up half the annual capacity of one seawater desalination plant. While the databasis ouf our analysis is limited and uncertainties are high, our findings underscore the need to avoid problem shifting so that climate-friendly technologies can develop their potential, prompt reflection on due diligence in supply chains under German and upcoming European legislation and highlight the shared responsibility of industry, society and politics.
High-strength bolts are widely used in construction machinery, steel structures, bridges, automobiles, and other industrial sectors owing to their high load-bearing capacity and connection efficiency. With the advancement of modern industry, there is a growing demand to further enhance the strength of high-strength bolt steel without significantly compromising its resistance to hydrogen embrittlement or hydrogen-induced delayed fracture (HIDF). To investigate the potential of microstructural control in improving the HIDF resistance of high-strength bolt steel, a V+Nb-microalloyed Cr–Ni–Mo high-strength bolt steel was subjected to low-temperature ausforming (i.e., controlled forging starting at ～950 ℃ and finishing at ～625 ℃), followed by direct water quenching and tempering at 450 ℃ for 2 h. The HIDF behavior was evaluated using slow strain rate tensile (SSRT) tests on pre-electrochemically hydrogen-charged notched round bar tensile specimens, along with hydrogen thermal analysis. The microstructural features were examined and their influence on HIDF was discussed. For comparison, the same steel was also processed by conventional forging (starting at ～1170 ℃ and finishing above 900 ℃, followed by air cooling), quenching, and tempering (austenitized at 945 ℃, oil-quenched, and tempered at 450 ℃ for 2 h, air-cooled). The results show that low-temperature-controlled forging produced a fine-banded microstructure with pronounced grain elongation along the forging direction and a grain size reduction of ～53%. The prior austenite grain boundaries were serrated and lacked coarse cementite film precipitation, while ～7.7% polygonal ferrite formed along these boundaries. Both the smooth and notched tensile strengths of the low-temperature-controlled forged samples increased by approximately 5.6% and 9.1%, respectively, compared to those of the conventionally forged samples. Notably, despite the increase in strength, the low-temperature ausformed sample exhibited excellent HIDF resistance. The notch tensile strength (indicating HIDF resistance) increased by 62.1%, and the hydrogen embrittlement sensitivity index (measured by the relative notch tensile strength loss rate) decreased by 27.6% after low-temperature-controlled forging. The fracture mechanism transitioned from brittle intergranular fracture along prior austenite grain boundaries (in conventionally forged samples) to transgranular quasi-cleavage fracture in low-temperature ausformed samples. The brittle zone area on the fracture surface was significantly reduced, from ～38% in the former to ～20% in the latter, despite nearly identical diffusible hydrogen content. The enhanced HIDF resistance is mainly attributed to the fine banded structure, formation of polygonal ferrite, and changes in cementite morphology along the prior austenite grain boundaries. Therefore, tailoring the microstructure and grain boundary characteristics through low-temperature deformation is an effective strategy to further improve the HIDF resistance of high-strength bolt steels.
Thomas Rosenstatter, Christian Schäfer, Olaf Saßnick
et al.
As Industry 4.0 and the Industrial Internet of Things continue to advance, industrial control systems are increasingly adopting IT solutions, including communication standards and protocols. As these systems become more decentralized and interconnected, a critical need for enhanced security measures arises. Threat modeling is traditionally performed in structured brainstorming sessions involving domain and security experts. Such sessions, however, often fail to provide an exhaustive identification of assets and interfaces due to the lack of a systematic approach. This is a major issue, as it leads to poor threat modeling, resulting in insufficient mitigation strategies and, lastly, a flawed security architecture. We propose a method for the analysis of assets in industrial systems, with special focus on physical threats. Inspired by the ISO/OSI reference model, a systematic approach is introduced to help identify and classify asset interfaces. This results in an enriched system model of the asset, offering a comprehensive overview visually represented as an interface tree, thereby laying the foundation for subsequent threat modeling steps. To demonstrate the proposed method, the results of its application to a programmable logic controller (PLC) are presented. In support of this, a study involving a group of 12 security experts was conducted. Additionally, the study offers valuable insights into the experts' general perspectives and workflows on threat modeling.
Antoine Tordeux, Tim M. Julitz, Isabelle Müller
et al.
In the era of Industry 4.0, system reliability engineering faces both challenges and opportunities. On the one hand, the complexity of cyber-physical systems, the integration of novel numerical technologies, and the handling of large amounts of data pose new difficulties for ensuring system reliability. On the other hand, innovations such as AI-driven prognostics, digital twins, and IoT-enabled systems enable the implementation of new methodologies that are transforming reliability engineering. Condition-based monitoring and predictive maintenance are examples of key advancements, leveraging real-time sensor data collection and AI to predict and prevent equipment failures. These approaches reduce failures and downtime, lower costs, and extend equipment lifespan and sustainability. However, it also brings challenges such as data management, integrating complexity, and the need for fast and accurate models and algorithms. Overall, the convergence of advanced technologies in Industry 4.0 requires a rethinking of reliability tasks, emphasising adaptability and real-time data processing. In this chapter, we propose to review recent innovations in the field, related methods and applications, as well as challenges and barriers that remain to be explored. In the red lane, we focus on smart manufacturing and automotive engineering applications with sensor-based monitoring and driver assistance systems.
Advances in Natural Language Processing (NLP) have the potential to transform HR processes, from recruitment to employee management. While recent breakthroughs in NLP have generated significant interest in its industrial applications, a comprehensive overview of how NLP can be applied across HR activities is still lacking. This paper discovers opportunities for researchers and practitioners to harness NLP's transformative potential in this domain. We analyze key fundamental tasks such as information extraction and text classification, and their roles in downstream applications like recommendation and language generation, while also discussing ethical concerns. Additionally, we identify gaps in current research and encourage future work to explore holistic approaches for achieving broader objectives in this field.
Industrial Internet of Things (IIoT) technologies have revolutionized industrial processes, enabling smart automation, real-time data analytics, and improved operational efficiency across diverse industry sectors. IIoT testbeds play a critical role in advancing IIoT research and development (R&D) to provide controlled environments for technology evaluation before their real-world deployment. In this article, we conduct a comprehensive literature review on existing IIoT testbeds, aiming to identify benchmark performance, research gaps and explore emerging trends in IIoT systems. We first review the state-of-the-art resource management solutions proposed for IIoT applications. We then categorize the reviewed testbeds according to their deployed communication protocols (including TSN, IEEE 802.15.4, IEEE 802.11 and 5G) and discuss the design and usage of each testbed. Driven by the knowledge gained during this study, we present suggestions and good practices for researchers and practitioners who are planning to design and develop IIoT testbeds for connectivity research.
Recent advancements in text-to-image diffusion models have significantly transformed visual content generation, yet their application in specialized fields such as interior design remains underexplored. In this paper, we present RoomDiffusion, a pioneering diffusion model meticulously tailored for the interior design industry. To begin with, we build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. Subsequently, techniques such as multiaspect training, multi-stage fine-tune and model fusion are applied to enhance both the visual appeal and precision of the generated results. Lastly, leveraging the latent consistency Distillation method, we distill and expedite the model for optimal efficiency. Unlike existing models optimized for general scenarios, RoomDiffusion addresses specific challenges in interior design, such as lack of fashion, high furniture duplication rate, and inaccurate style. Through our holistic human evaluation protocol with more than 20 professional human evaluators, RoomDiffusion demonstrates industry-leading performance in terms of aesthetics, accuracy, and efficiency, surpassing all existing open source models such as stable diffusion and SDXL.
Md Messal Monem Miah, Ulie Schnaithmann, Arushi Raghuvanshi
et al.
Detecting dialogue breakdown in real time is critical for conversational AI systems, because it enables taking corrective action to successfully complete a task. In spoken dialog systems, this breakdown can be caused by a variety of unexpected situations including high levels of background noise, causing STT mistranscriptions, or unexpected user flows. In particular, industry settings like healthcare, require high precision and high flexibility to navigate differently based on the conversation history and dialogue states. This makes it both more challenging and more critical to accurately detect dialog breakdown. To accurately detect breakdown, we found it requires processing audio inputs along with downstream NLP model inferences on transcribed text in real time. In this paper, we introduce a Multimodal Contextual Dialogue Breakdown (MultConDB) model. This model significantly outperforms other known best models by achieving an F1 of 69.27.
Purpose: Industrial robots allow manufacturing companies to increase productivity and remain competitive. For robots to be used, they must be accepted by operators on the one hand and bought by decision-makers on the other. The roles involved in such organizational processes have very different perspectives. It is therefore essential for suppliers and robot customers to understand these motives so that robots can successfully be integrated on manufacturing shopfloors. Methodology: We present findings of a qualitative study with operators and decision-makers from two Swiss manufacturing SMEs. Using laddering interviews and means-end analysis, we compare operators' and deciders' relevant elements and how these elements are linked to each other on different abstraction levels. These findings represent drivers and barriers to the acquisition, integration and acceptance of robots in the industry. Findings: We present the differing foci of operators and deciders, and how they can be used by demanders as well as suppliers of robots to achieve robot acceptance and deployment. First, we present a list of relevant attributes, consequences and values that constitute robot acceptance and/or rejection. Second, we provide quantified relevancies for these elements, and how they differ between operators and deciders. And third, we demonstrate how the elements are linked with each other on different abstraction levels, and how these links differ between the two groups.
This study investigates the impact of industrial agglomeration on land use intensification in the Yangtze River Delta (YRD) urban agglomeration. Utilizing spatial econometric models, we conduct an empirical analysis of the clustering phenomena in manufacturing and producer services. By employing the Location Quotient (LQ) and the Relative Diversification Index (RDI), we assess the degree of industrial specialization and diversification in the YRD. Additionally, Global Moran's I and Local Moran's I scatter plots are used to reveal the spatial distribution characteristics of land use intensification. Our findings indicate that industrial agglomeration has complex effects on land use intensification, showing positive, negative, and inverted U-shaped impacts. These synergistic effects exhibit significant regional variations across the YRD. The study provides both theoretical foundations and empirical support for the formulation of land management and industrial development policies. In conclusion, we propose policy recommendations aimed at optimizing industrial structures and enhancing land use efficiency to foster sustainable development in the YRD region.
The construction industry’s reliance on traditional methods and fragmented workflows results in significant information loss, inefficiencies, increased costs, and errors. This study addresses these issues by integrating comprehensive urban planning with building information modeling (BIM) to create a seamless information flow throughout the building lifecycle. We propose a holistic framework that synchronizes data from planning to demolition, incorporating national and municipal digital twins. An imperative literature review and analysis of international best practices were conducted to develop a conceptual framework aimed at improving data accuracy and interoperability. Our findings underscore the importance of adopting open standards such as Industry Foundation Classes (IFC) and CityGML for effective information exchange. By implementing an information model (IM)-based approach in urban planning and public sector permit processes, project timelines can be streamlined, and regulatory compliance enhanced. This study concludes that continuous, integrated information flow facilitates more efficient, cost-effective construction practices and improved decision-making. Furthermore, this research illustrates the potential of digital twin technology to revolutionize the construction industry by enabling real-time data integration and fostering stakeholder collaboration, ultimately offering a robust framework for practitioners, and significantly enhancing the efficiency and accuracy of construction processes.
Despite the subjective and error-prone nature of manual visual inspection procedures, this type of inspection is still a common process in most construction projects. However, Automated Construction Inspection and Progress Monitoring (ACIPM) has the potential to improve inspection processes. The objective of this paper is to examine the applications, challenges, and future directions of ACIPM in a systematic review. It explores various application areas of ACIPM in two domains of (a) transportation construction inspection, and (b) building construction inspection. The review identifies key ACIPM tools and techniques including Laser Scanning (LS), Uncrewed Aerial Systems (UAS), Robots, Radio Frequency Identification (RFID), Augmented Reality (AR), Virtual Reality (VR), Computer Vision (CV), Deep Learning, and Building Information Modeling (BIM). It also explores the challenges in implementing ACIPM, including limited generalization, data quality and validity, data integration, and real-time considerations. Studying legal implications and ethical and social impacts are among the future directions in ACIPM that are pinpointed in this paper. As the main contribution, this paper provides a comprehensive understanding of ACIPM for academic researchers and industry professionals.
Rajasundaravadivel Jeya Prakash, Balu Soundara, Christian Johnson
The massive development of the construction industry demands sustainability, and the studies on No Fines Concrete (NFC) will support sustainable development in the field of transportation and highway industry. It is the key requirement of all developing countries like India in order to satisfy three main criteria namely sustainability, serviceability and feasibility in addition to its performance. Application of NFC pavement is itself a sustainable method to manage and discharge the retaining stormwater during heavy floods. Fibre Reinforced No Fine Concrete (FRNFC) was considered, with findings suggesting that the inclusion of fibres has minimal impact on strength characteristics and only marginally reduces the permeability of NFC. However, NFC pavements require regular maintenance to prevent clogging of pores with dust, sediments, and debris, which impairs water flow. A 2 m x 2 m span real-time FRNFC pavement was cast and subsequently subjected to assessment of its serviceability performance. The study examines the performance of FRNFC under clogging and suggests rehabilitation methods to reinstate infiltration capacity. Pressure wash combined with vacuum sweep shows the highest Drainage Efficiency Restoration (DER), maintaining drain ability from 99% to 90% after 12 cycles. Routine pressure wash monthly and vacuum sweep yearly are recommended for proper pavement serviceability and effective stormwater runoff mitigation.
Samuel A. Prieto, Nikolaos Giakoumidis, Borja Garcia de Soto
The construction industry has been notoriously slow to adopt new technology and embrace automation. This has resulted in lower efficiency and productivity compared to other industries where automation has been widely adopted. However, recent advancements in robotics and artificial intelligence offer a potential solution to this problem. In this study, a methodology is proposed to integrate multi-robotic systems in construction projects with the aim of increasing efficiency and productivity. The proposed approach involves the use of multiple robot and human agents working collaboratively to complete a construction task. The methodology was tested through a case study that involved 3D digitization of a small, occluded space using two robots and one human agent. The results show that integrating multi-agent robotic systems in construction can effectively overcome challenges and complete tasks efficiently. The implications of this study suggest that multi-agent robotic systems could revolutionize the industry.