Modern electronic household devices often function as black boxes, limiting user interactions to basic operations. When these products break down, the lack of agency leads to frustration and disposal, contributing to ...
详细信息
ISBN:
(纸本)9798400711978
Modern electronic household devices often function as black boxes, limiting user interactions to basic operations. When these products break down, the lack of agency leads to frustration and disposal, contributing to 51 million tonnes of e-waste annually in Europe, of which 35 million tonnes arise from still-usable consumer goods being discarded. In this study, I explored how Tangible User Interfaces (TUI) can affect user engagement in maintenance and repair processes to lengthen the lifetime of electronic household devices. three rounds of user testing were conducted with 15 participants along with qualitative interviews, observation, and visual documentation. the preliminary findings suggest that color and ergonomic coding, along with practical affordances can significantly aid users and reduce the stress associated with repair processes. these insights highlight the potential of TUIs to promote sustainable practices in electronic product usage in the future.
Emotion semantic inconsistency is a ubiquitous challenge in multi-modal sentiment analysis (MSA). MSA involves analyzing sentiment expressed across various modalities like text, audio, and videos. Each modality may co...
详细信息
ISBN:
(纸本)9789819610440;9789819610457
Emotion semantic inconsistency is a ubiquitous challenge in multi-modal sentiment analysis (MSA). MSA involves analyzing sentiment expressed across various modalities like text, audio, and videos. Each modality may convey distinct aspects of sentiment, due to the subtle and nuanced expression of human beings, leading to inconsistency, which may hinder the prediction of artificial agents. In this work, we introduce a modality-conflicting test set and assess the performance of both traditional multi-modal sentiment analysis models and multi-modal large language models (MLLMs). Our findings reveal significant performance degradation across traditional models when confronted with semantically conflicting data and point out the drawbacks of MLLMs when handling multi-modal emotion analysis. Our research presents a new challenge and offers valuable insights for the future development of sentiment analysis systems.
the proceedings contain 18 papers. the special focus in this conference is on Artificial Intelligence: Methodology, Systems, and Applications. the topics include: Cross-Lingual Style Transfer TTS for High-Quality...
ISBN:
(纸本)9783031815416
the proceedings contain 18 papers. the special focus in this conference is on Artificial Intelligence: Methodology, Systems, and Applications. the topics include: Cross-Lingual Style Transfer TTS for High-Quality Machine Dubbing;an Approach to Discovering, Tracking Over Time, and Summarizing Publicly Available Information on a Given Topic;reinforcement Learning Control of Cart Pole System with Spike Timing Neural Network Actor-Critic Architecture;Predictive and Explainable Modelling in Economics on the Case Study of Remittance Prediction Using the NeuDen AI Computational Architecture;deep Learning for Multi-class Diagnosis of thyroid Disorders Using Selective Features;Advanced CNN-SVM Machine Learning Techniques for Facial Skin Ultrasound Image Analysis;Testing the NEAT Algorithm on a PSPACE-Complete Problem;investigating the Regularization of Deep Neural Networks for Affect Recognition with Relevance-Guided Local Explanations;Layered data-Centric AI to Streamline data Quality Practices for Enhanced Automation;Combining Graph NN and LLM for Improved Text-Based Emotion Recognition;a Novel Study on Modelling and Adaptive Optimal Control of a Tubular Reactor Based on Gaussian Processes;converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion;enhancing Question Answering in Lecture Videos with a Multimodal Retrieval-Augmented Generation Framework;agent-Based Simulation Leveraging Declarative Modeling for Efficient Resource Allocation in Emergency Scenarios;enhancing Security in Federated Learning: Detection of Synchronized data Poisoning Attacks;Clinical and Acquisition data for Optimizing MGMT Methylation Status Prediction: A Comprehensive Ensemble Strategy Emphasizing Non-invasive Approaches.
Federated Learning (FL) offers a privacy-preserving solution by enabling multiple clients to train a shared model collaboratively without centralizing data. However, the decentralized nature of FL presents challenges,...
详细信息
there is a growing interest in representing data physically across various domains. However, our understanding of the physicalization design process is minimal, posing barriers to supporting designers and wider utiliz...
详细信息
ISBN:
(纸本)9798400711978
there is a growing interest in representing data physically across various domains. However, our understanding of the physicalization design process is minimal, posing barriers to supporting designers and wider utilization of physicalization. In this work, we studied the dynamics of the physicalization design process, through the lens of KiriPhys, a Kirigami-inspired technique, to understand how physicalization designers navigate, iterate, and make decisions throughout their creative workflows. We conducted an exploratory qualitative study, observing physicalization/visualization experts design KiriPhys both freely and using a technology probe. From analysing the gathered data, we discovered an interactive data physicalization design process formed of six activities, characterized by non-linear and highly iterative movements between them, quite different from the predominately linear models currently in use. A key observed activity within this process is the concept of feedforward, which highlights the designer's proactive forward-thinking when making design choices, considering the physical aspects of the results. Our findings suggest strategies for digitally supporting the interactive data physicalization process.
this study examines the essential importance of security in contemporary network settings, emphasizing the increasing dependence on Virtual Private Networks (VPNs) for safe data transfer. the emphasis is on assessing ...
详细信息
Acoustic echo cancellation (AEC) has gained prominence due to increasing commercial demand and diverse application scenarios. Apart from professional fields like audio processing, AEC finds more use in daily scenarios...
详细信息
ISBN:
(纸本)9789819610440;9789819610457
Acoustic echo cancellation (AEC) has gained prominence due to increasing commercial demand and diverse application scenarios. Apart from professional fields like audio processing, AEC finds more use in daily scenarios like video conferencing. However, attaining superior speech quality frequently involves intricate deep learning models and significant computational resources, thereby impeding its widespread adoption. In order to reduce model size and enhance inference speed while maintaining speech quality, in this paper, we propose a new network architecture that combines pruning and quantization with densely connected neural network called PQ-DCNN. the proposed PQ-DCNN model utilizes encoder unstructured pruning (EUP) modules and decoder structured pruning (DSP) modules to reduce model size and accelerate model inference. Static quantization (SQ) module targets convolution layers, optimizing model resources by converting less critical weights and activation values from high to low precision. Results demonstrate a 66.78% reduction in model size and a 26.46% decrease in inference time, achieving an efficient AEC model design.
the proceedings contain 95 papers. the special focus in this conference is on Sustainable Manufacturing. the topics include: Ecosystem Collaboration for Sustainability: Learnings from the Food System;business Model De...
ISBN:
(纸本)9783031774287
the proceedings contain 95 papers. the special focus in this conference is on Sustainable Manufacturing. the topics include: Ecosystem Collaboration for Sustainability: Learnings from the Food System;business Model Design in Context of Circular Economy;From Talk to Action: A Diagnosis of Drivers of Sustainable Logistics Practices in LATAM, a Collaborative Study Between Industry and Academia;aligning Strategic Priorities in Manufacturing and Sustainable Operational Practices in Firms: Exploration and Evidence in North-East Colombia;towards Circular Business Models in the Punching Industry: Leveraging Smart Sensor Technology for Sustainable Manufacturing Processes;challenges of Low-Carbon Transition of Manufacturing Industry in Developing Countries and Research on the Construction of Green Manufacturing System in China;risk Assessment for Small Manufacturing Businesses in Soweto;criteria-Driven Comparison of Hydrogen, Charcoal and Liquefied Petroleum Gas as Cooking Fuels Based on a Systematic Literature Review;bridging the Educational Gap in Circular Design and Engineering—An Educational Concept and Case Study from Austria;concept of an Integrated Information and Education Platform for Sustainable Development;innovating Blended Learning Model for Professional Education in Manufacturing;work Engineering for Sustainability: Required Education in Engineering;developing a Framework for Sustainable Education in a Production Engineering Study Program;Identification of Lightweighting Potentials Towards More Sustainable Products via the Functional Lifecycle Energy Analysis (FLCEA);sustainability data Map: Framework for data-Based Product Carbon Footprinting of Technical Products;Life Cycle Assessment (LCA) of a Circular Saw Blade for Wood Processing;a Systems-Based Framework for Product Circularity Assessment;technology Radar for a Sustainable Biological Transformation in the Manufacturing Industry.
third-party libraries (TPLs) are widely adopted in softwares for integrating special functions (e.g., compression) efficiently. However, as most TPLs are in the same process withthe invoker, attackers could exploit m...
详细信息
ISBN:
(纸本)9783031649479;9783031649486
third-party libraries (TPLs) are widely adopted in softwares for integrating special functions (e.g., compression) efficiently. However, as most TPLs are in the same process withthe invoker, attackers could exploit memory disclosure vulnerabilities in TPLs to read the sensitive memory data of the victim process. therefore, once a vulnerability found in a TPL, all softwares withthis TPL need to be patched in time, which is impractical. In this paper, we propose a cryptography-based isolation (named mShield) between the data memory of the invoker and TPLs, to prevent TPL vulnerabilities from being exploited to read the invoker's sensitive memory data. mShield performs a user-mode and lightweight memory analysis, figures out the invoker's memory space (including stack, heap, user-defined ones in BSS/data segment), encrypts them before invoking any TPL function, and automatically decrypts them once the function returns, without interrupting the normal execution. mShield performs the encryption/decryption in the trusted environment provided by Intel SGX, which prevents the attacker from reading the cryptographic key, and alerts (i.e., the invoker's decryption fails) in time once the encryption context is tampered with (e.g., by illegal invocations of decryption). We have implemented mShield, and adopted it to protect Nginx against a potentially vulnerable TPL (i.e., zlib). the experiment demonstrates mShield's effectiveness (TPLs fail to read the invoker's plaintext sensitive memory data) and acceptable efficiency (about less than 4x time cost).
Immersive visualisations, that enable spatial, embodied exploration (e.g., XR and physicalisations), have the potential to increase user engagement withdata representations. However, which mode of representation offe...
详细信息
ISBN:
(纸本)9798400711978
Immersive visualisations, that enable spatial, embodied exploration (e.g., XR and physicalisations), have the potential to increase user engagement withdata representations. However, which mode of representation offers a higher engagement, and how does the user experience differ? Our work compares a physicalisation to a mobile AR representation of energy consumption sources and CO2 emissions. In a counter-balanced study with 16 participants, we found no significant differences in perceived user engagement, except for higher scores in "perceived usability". the physicalisation was considered 'real' and intuitive, the AR representation technical and precise. Most participants preferred the physicalisation and felt more 'connected' with it. We also analysed patterns of how people moved around the representations, and found no differences between conditions. Despite people being able to touch the physicalisation, this was barely made use of-thereby turning both conditions into visual exploration. We discuss what rationale participants provided for barely touching and discuss implications.
暂无评论