19684 research outputs found
Sort by
Harnessing Deep Learning for Fault Detection in Industry 4.0:A Multimodal Approach
No full textThe advent of Industry 4.0 has reshaped the modern industries (e.g., Manufacturing, Automotive, Aerospace and Defense), driven by the rapid development of artificial intelligence, smart sensing technologies, and interconnected cyber-physical systems. One of the most important goal for Industry 4.0 is the improvement and enhancement in productivity, reduction of production losses, and operational efficiency. High quality fault detection within different environments is the foundation to achieve these goals. Industry 4.0 emphasizes the use of interconnected systems, smart sensors, and advanced analytics, which generate large volumes of data from production environments. The data complexity and scale, product by the widespread deployment of sensors and IoT devices, demands sophisticated Machine Learning (ML) and data-driven methods. In this paper, we argue that the future of accurate and reliable fault detection lies in the seamless fusion of edge-cloud computing, explainable AI, and adaptive machine learning algorithms capable of processing high-frequency, multimodal data streams in real time. Different kinds of advantages for multimondal learning and core enabling techniques are also discussed and revise. This vision paper outlines the future trajectory of multimodal learning based fault detection, via identifying critical research gaps and promising directions for future study.</p
Managing Technological Innovation for Social Good:A Systematic Literature Review
No full textThe past decades have seen a growing recognition of a need to develop novel solutions to effectively and efficiently deliver in-clusive values to society. However, the evolving literature in innovation management, for example, in the discourse of socialinnovation or responsible innovation, has yet to produce a consolidated knowledge base for how technologies could be managedfor social good. Hence, this systematic review attempts to synthesize relevant literature regarding managing innovation for socialgood with a particular focus on the critical role technologies play. By doing so, two contributions to knowledge are presented.First, we identify three streams of conceptualization describing managing technological innovation for social good that requirefurther synergies. Second, the findings indicate that the social consequences of technology and technological advancements re-main unclear, which we call for a more evident discourse of social impacts and social good in the innovation management field
Molecular dynamics investigation of polyvinylidene difluoride dipole movement in electromechanical stretching:A key impact on the polymer’s piezoelectric phenomenon
No full textThe transition from α-phase to β-phase is critical for the piezoelectric functionality of polyvinylidene difluoride (PVDF), with the dynamical behaviors of polymer molecular during this transition playing the key role in determining the piezoelectric performance. A molecular dynamics simulation was used to investigate the effects of the duration and direction of an applied electric field during external stretching on enhancing the β-phase content in PVDF. A simulation scheme, aligned with the electrospinning process, was designed, and phase transition simulations were conducted. The results show that mechanically stretched PVDF fibers form a disorder structure β phase lacking piezoelectric properties due to internal dipole cancellation. However, applying an electric field perpendicular to the stretching direction during stretching aids in dipole alignment, creating overall polarity. When an electric field with varying direction is applied during stretching, polymer's polarity direction shifts rapidly, with the electric field strength playing a positive role in the process. The variation in electric field direction is crucial in differentiating the piezoelectric coefficients of near-field and far-field electrospun films. This work provides a theoretical foundation for optimizing nanofibrous fabrication processes for high-performance piezoelectric applications.</p
Further study of heave plate designs for enhancing motion control of floating offshore wind turbines
No full textTo enhance the motion control of floating offshore wind turbines in complex wave conditions, this paper further investigates heave plate designs, with a novel focus on the effects of perforation depth, hexagonal design, and combined perforation-hexagonal design on hydrodynamic damping and motion stability of the floating platform. Using numerical simulations and experimental testing methods, the research systematically analyzed the platform’s hydrodynamic characteristics and response amplitude operators (RAOs) under various heave plate designs and wave and wind conditions. Key findings reveal that increasing the perforation depth in heave plates significantly reduces RAO values for heave and pitch motions, with optimal stability achieved under the through perforation condition, where perforation depth equals heave plate thickness. Additionally, the introduction of a hexagonal design enhances vortex generation and force distribution, further reducing rotational motions, particularly at longer wave periods. The combined perforation-hexagonal design demonstrates superior damping performance, improving platform stability during motion. These findings highlight a novel, practical approach to enhancing the performance of floating wind turbine platforms under challenging marine conditions
Paddy Plant Stress Identification Using Few-Shot Learning Framework
No full textThe efficient identification of stress in paddy plant leaves is paramount for optimizing agricultural resources and ensuring robust crop yields in smart agriculture practices. This research explores the potential of few-shot learning (FSL) to address the inherent challenges posed by limited training data in stress identification. Three distinct FSL approaches - Siamese network, Matching network, and Model-Agnostic Meta Learning (MAML) - are evaluated for their accuracy in stress detection. The study introduces the importance of stress detection in smart agriculture and the challenges of limited training data. It then covers the methodology in five stages: dataset description, data pre-processing, FSL implementation, accuracy evaluation, and reporting. Among the FSL models, the Matching Network stands out with an impressive accuracy of 86% for 6-way 1-shot learning. This surpasses the performance of a Convolutional Neural Network (CNN) tested with a larger shot size (270-shots), which achieved an accuracy of 81%. These comparative results underscore the potential of FSL techniques in achieving precise stress identification, even when working with limited data. The objective of this research is to contribute valuable insights towards enhancing the efficiency of stress prediction in paddy leaves, thereby fostering healthier and more productive paddy crop production in smart agriculture. The findings presented here aim to inform the development of effective stress detection systems and advance the field of precision agriculture.</p
Using MOOCs for professional development purposes by education professionals in Cambodia:A qualitative study
No full textMassive Open Online Courses (MOOCs) have become an effective learning approach for continuing professional development (PD) and there is an increasing body of literature on MOOC learners’ perspectives drawing from a range of the global contexts. However, in developing countries like Cambodia, relatively little research on this phenomenon has been carried out. This study therefore aims to address this knowledge gap by exploring the perspectives of the Cambodian education professionals towards taking MOOCs, centering around motivations for enrolment, challenges of MOOC completion, and suggestions for promoting MOOCs in Cambodia for teachers’ PD. Drawing on evidence gathered from semi-structured interviews with English program leaders and coordinators, and teachers of English, our study reveals that Cambodian education professionals perceive a range of perspectives of taking MOOCs in terms of motivations and challenges. We highlight some steps that would promote the use of MOOCs for teachers’ PD in the Cambodian context, and might also be applicable to other developing countries with similar geographical and socioeconomic status, especially the significance of using mother tongue (Khmer) as the language of education and the importance of teachers’ mindset in undertaking PD
The relationship of NDVI and GVI, and the effect of building heights:A case study in Athens, Greece
No full textUrban green spaces play a crucial role in enhancing the sustainability of cities, making it a necessity for their measurement methods to be precise and reliable. Mapping of urban green has been standardized with multiple data sources, such as the Normalized Difference Vegetation Index (NDVI) derived from satellite imagery, and the Green View Index (GVI), derived from street-level imagery. Both are popular, complementary methods for quantifying urban green. This case study, in Athens, Greece, aims to investigate the strength of their relationship for different resolutions of NDVI. In addition, as NDVI is sensitive to height variations of the imaged area, this relationship was also quantified in terms of the effect of building heights. Results show a strong relationship between the two indices, but not linear. Incorporating building heights into proper models is a method that could support a more comprehensive approach.</p
Access Repository Dashboard
Do you manage Huddersfield Research Portal? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!