IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
Developing a Robust Multi-objective Optimization Model for Reverse Logistics of Electric Vehicle Batteries
No full textPart 6: Advances in Production Management SystemsInternational audienceIn response to the damaging impacts of greenhouse gas emissions, Electric Vehicles (EVs) have emerged as a sustainable alternative. However, the rise of EVs creates the challenge of disposing numerous retired batteries. Hence, designing and optimizing Reverse Logistics (RL) for Electric Vehicles Batteries (EVBs) can be an effective approach. Existing uncertainties, however, cause a gap between the outputs of exact optimization models and real-world conditions. Addressing this, the present study develops a robust multi-objective optimization model that incorporates uncertainty such as the return rates of retired batteries. Making it more applicable to real-world scenarios. This research compares the relative performances of deterministic and the proposed robust optimization models and validates the model by calculating violation probabilities within a robust optimization framework. This validation is conducted by allocating a specific budget for robustness to ensure that the model remains effective under various uncertain conditions. Additionally, this study explores adjusting the level of conservatism in decision-making by applying the price of robustness approach to manage conservatism in our decision-making process. Highlighting the importance of innovative sustainable practices, this work offers a practical route for stakeholders to collaboratively mitigate the challenges associated with the end-of-life management of EV batteries, thus contributing to environmental sustainability and resource efficiency in the BEV industry
Covariance Structure Analysis of the Collaboration Between Local Enterprises and Local Governments for the Creation and Communication of Value in Local Brands
No full textPart 6: Advances in Production Management SystemsInternational audienceEstablishing regional brands is indispensable for revitalizing local areas; however, advancing such initiatives requires collaboration with a diverse array of stakeholders. This study focuses on local enterprises, which are pivotal stakeholders in regional branding strategies, and aims to elucidate the impact of their collaboration with local governments and degree of brand penetration on their willingness to engage in regional branding. We define regional branding as comprising two types: “comprehensive regional branding,” which involves branding the region, and “resource-based regional branding,” which pertains to branding specific local products and services. We propose a hypothetical model suggesting that the depth of collaboration with local governments influences local enterprises’ engagement in regional branding. We conducted a questionnaire survey among local businesses in Fukuyama City, Hiroshima Prefecture, Japan, and verified the hypothetical model through covariance structure analysis using the survey data. The results revealed a moderate correlation between the willingness to participate in regional branding and the extent of collaboration with local governments. Furthermore, we identified factors that influence local enterprises’ deepening relationships with local governments and those that enhance brand penetration among local enterprises, specifically the impact of the degree of understanding of the local culture and the attractiveness of the brand
Assessing the Cross-Disciplinary Accessibility of CyBOK
No full textPart 4: Cybersecurity Programs and Career DevelopmentInternational audienceThis study assesses the applicability of Cybersecurity Body of Knowledge (CyBOK) as a reference for non-IT disciplines, aiming to ascertain its usability and accessibility beyond the realm of computing. Despite cybersecurity’s relevance across diverse fields, its integration into qualifications outside computing appears inconsistent. Through a web-based survey and subsequent online workshops involving participants from varied backgrounds, this research explores the cross-disciplinary perception of CyBOK. The survey aimed to capture participants’ perceptions of cybersecurity within their sectors, extracting Key Words and Phrases (KWoPs) relevant to their disciplines. These KWoPs were juxtaposed with CyBOK’s Knowledge Areas and Mapping Reference. Subsequent workshops, categorized by sector, aimed to gather detailed insights into CyBOK’s usability and pertinence. The findings indicate that CyBOK, in its current presentation, poses challenges for individuals from non-cyber sectors. While participants identify relevant topics, understanding and navigating CyBOK content remains problematic. This study suggests exploring a tailored “sector lens” approach to better integrate cybersecurity into diverse disciplines, using a structured and layered content segmentation to offer accessible versions for different audience groups. Such adaptations, though potentially challenging, could significantly enhance CyBOK’s usability and relevance beyond traditional IT domains
Using Visual Cues to Enhance Phishing Education for Children
No full textPart 1: Cybersecurity Training and EducationInternational audienceChildren are often viewed as digital natives, being comfortable with technology and facing less online risk. Their ability to identify phishing attacks – widely regarded as an adult-only problem – is often overlooked, which leaves children vulnerable to an increasingly common threat. This potentially puts them and their parents/guardians at risk of identity theft or financial damage. To help children learn about phishing it is proposed that visual cues can help to direct attention to key indicators. The aim of this research was to identify the impact on learning by creating a prototype phishing education website for children. Phishing education was delivered through reading material, scenario-based learning games, a matching game, and a quiz. An evaluation with 18 participants split into groups receiving education with/without visual cues show that visual cues made content more enjoyable and easier to understand. After completing the educational activities both groups improved in their ability to identify phishing attempts, with visual cue materials reflecting slightly better (avg. of 6% more) participant results. The results show that the combination of gamification, scenario-based learning, and visual cues presents a promising approach for improving children’s phishing awareness
Recognition of Signal Modulation Pattern Based on Multi-task Self-supervised Learning
No full textPart 1: Pattern RecognitionInternational audienceIn wireless communication, the recognition of signal modulation plays an essential role. However, acquiring high-quality data in wireless communications is often prohibitively expensive and challenging. Traditional methods for modulation pattern recognition are limited by specialized knowledge, resulting in poor adaptability and generalization. Although deep neural networks demonstrate superior performance in modulation pattern recognition, they heavily depend on high-quality and accurately annotated training data. They require significant computational resources during training, rendering them unsuitable for resource-constrained devices or real-time applications. We propose a signal modulation pattern recognition method based on multi-task self-supervised learning to overcome these challenges. This approach begins by enhancing data from various unlabeled categories, then capturing the essential signal characteristics through contrastive learning to obtain a robust pre-trained model. We then fine-tune the model with a small account of labeled modulation samples to better adapt it to downstream tasks. Experimental results indicate that in scenarios with limited sample availability, our method slightly surpasses traditional recognition methods in accuracy and shows significant advantages in training efficiency
Graph Convolutional Networks for Predicting Mechanical Characteristics of 3D Lattice Structures
No full textPart 2: Image UnderstandingInternational audienceRecent advancements in deep learning methods encouraged researchers to apply them to process 3D objects. Initially, convolutional neural networks which have shown their ability in the processing of 2D images were used for 3D object processing. These methods need a complex process to convert 3D objects to 2D images. This conversion leads to increased computation cost and possible information loss during the transformation. This research introduces a Graph Convolutional Network approach for predicting mechanical properties of custom-designed 3D lattice structures for tissue engineering applications. Seventeen scaffold geometrics were generated for training while eight were used for testing. Unlike traditional preprocessing into images, this methodology reduces preprocessing by leveraging GCNs to directly process 3D geometrics in graph form. The experimental results show the efficiency of our proposed method in predicting 3D lattice structures
Adaptive Prototype Triplet Loss for Cross-Resolution Face Recognition
No full textPart 2: Image UnderstandingInternational audienceAlthough face recognition has achieved great success in many areas, cross-resolution face recognition (CRFR) still remains a challenging task due to the large domain gap between low-resolution (LR) and high-resolution (HR) images. In this paper, we propose an adaptive prototype triplet loss (APTL) for CRFR. The APTL pulls the features close to their own prototypes, and pushes them away from the prototypes of other classes. Thus, the angular distances between features and prototypes from the same class are closer than those from different classes. Furthermore, to better exploit the similarity information among different identities, we adaptively adjust the margin term in the loss. Since the proposed APTL is applied simultaneously to HR and LR features, the gap between two domains can be narrowed naturally. Experiments on LFW and SCface datasets illustrate the superiority of our method
HARFMR: Human Activity Recognition with Feature Masking and Reconstruction
No full textPart 1: Pattern RecognitionInternational audienceThe widespread adoption of deep learning in the computer science field has significantly improved the functionality of wearable sensors, such as the recognition and localization of human activities. Nevertheless, the challenge of annotating and training sensor data persists due to the high associated costs. Unlabeled sensor data is more accessible and easier to train compared to labeled data, which has led to increased interest in self-supervised learning for human activity recognition. Masked reconstruction of raw sensor data is a method commonly employed in self-supervised learning. When applied to human activity recognition, the technique involves time-centric data masking and subsequent reconstruction. However, the masking and reconstruction of raw sensor data may potentially lead to the exclusion of crucial information, resulting in representations with lower semantic levels. To address this, we present a new strategy for masking and reconstruction, called Human Activity Recognition with Feature Masking and Reconstruction (HARFMR), specifically designed for human activity recognition. This architecture includes the masking of features using a random ratio and the subsequent reconstruction of the original sensor data, compelling the encoder to emphasize the contextual correlations of the data’s features and the properties of the features during the reconstruction process. Our evaluation of the proposed masking strategy on three public datasets demonstrates that the HARFMR method surpasses existing masking reconstruction schemes under self-supervised and semi-supervised settings
Early Anomaly Detection in Hydraulic Pumps Based on LSTM Traffic Prediction Model
No full textPart 1: Pattern RecognitionInternational audienceHydraulic pumps, vital in modern industrial equipment, face the challenge of direct flow rate measurement due to their intricate internal structures. Consequently, devising predictive methods for the main pump flow is crucial for early anomaly detection and efficient maintenance. This paper introduces a predictive method for hydraulic pump flow based on Long Short-Term Memory networks (LSTM), known for their robust handling of temporal data. Utilizing LSTM, the method predicts flow rates, which are then employed to compute the volumetric efficiency under steady rotational conditions, thus evaluating the pump’s operational status. The proposed model’s experimental validation, marked by a low mean square error in flow prediction, attests to its efficacy. Moreover, the derived average volumetric efficiency value of 0.97 serves as a reliable indicator for identifying potential anomalies in hydraulic pump performance
Analysis of Critical Success Factors of Sustainable and Resilient Aioe-based Supply Chain in Industry 5.0
No full textPart 1: Smart and Sustainable Supply Chain Management in the Society 5.0 EraInternational audienceCritical success factors (CSFs) are limited components that are critical to the success of the organization. If the organization needs its presence, it should give them. Therefore, organizations should consider these factors in their operational processes. In today’s world, which is mixed with transformative technologies and business and supply chain processes have different conditions than in the past, understanding the CSFs for smart processes in the supply chain is very necessary because it can guarantee the success of smart organizations. Understanding these factors and their position can greatly help the resilience and sustainability of the supply chain, which are key indicators of Industry 5.0. Therefore, this research aims to extract and analyze the critical success factors in resilient, sustainable, and intelligent supply chains based on Artificial Intelligence is Everything (AIoE) in Industry 5.0. To evaluate the critical factors of success, this research has prioritized these factors using a fuzzy nonlinear approach based on the hierarchical analysis method and pairwise comparison tables based on linguistic variables. The results show that the existence of technical infrastructure and hardware have the highest priority in the implementation of these systems. Understanding the framework presented in this research can provide a deep insight into the effective implementation of these smart supply chain systems in the age of transformative technologies