检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ziogas, Ioannis Hadjileontiadis, Leontios J. Khandoker, Ahsan H. Al Shehhi, Aamna Dpt. of Biomedical Eng. and Biotechnology Khalifa University of Science and Technology Abu Dhabi United Arab Emirates Dpt. of Electrical and Computer Eng. Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (纸本)9798350368741

Wearable and smartphone-based emotion recognition (WER) remains a challenging setting in affective computing, due to the notorious difficulty and bias associated with in-the-wild label collection. The high inter-and intra-subject emotional variability motivates us to explore WER modeling through graph node classification in a limited resources learning scheme powered by Self-Supervised Learning (SSL) graph masking augmentation tasks. We employ a subgraph sampling approach during training, utilizing labeled and unlabeled data, along with supervised, semi-supervised, and SSL mechanisms in a multi-task inductive graph neural network architecture. Our evaluations on K-EmoPhone through leave-one-group-out cross-validation in the binary arousal and valence tasks yield average accuracy gains of 4.3% and 7.8%, compared to the full resource setting, utilizing only 20% and 25% of the labels, respectively. Our model analysis sheds light on the relation of SSL graph augmentations to emotional arousal and valence and justifies the approach of SSL-driven subgraph training for in-the-wild WER. © 2025 IEEE.

关键词： Graph Masking Graph Neural Networks Self-Supervised Learning Wearable Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition

Self-Supervised Graph Representation Learning for In-The-Wil...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ioannis Ziogas Leontios J. Hadjileontiadis Ahsan H. Khandoker Aamna Al Shehhi Dpt. of Biomedical Eng. and Biotechnology Khalifa University of Science and Technology Abu Dhabi UAE Dpt. of Electrical and Computer Eng Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Wearable and smartphone-based emotion recognition (WER) remains a challenging setting in affective computing, due to the notorious difficulty and bias associated with in-thewild label collection. The high inter-and intra-subject emotional variability motivates us to explore WER modeling through graph node classification in a limited resources learning scheme powered by Self-Supervised Learning (SSL) graph masking augmentation tasks. We employ a subgraph sampling approach during training, utilizing labeled and unlabeled data, along with supervised, semi-supervised, and SSL mechanisms in a multi-task inductive graph neural network architecture. Our evaluations on K-EmoPhone through leave-one-group-out cross-validation in the binary arousal and valence tasks yield average accuracy gains of 4.3% and 7.8%, compared to the full resource setting, utilizing only 20% and 25% of the labels, respectively. Our model analysis sheds light on the relation of SSL graph augmentations to emotional arousal and valence and justifies the approach of SSL-driven subgraph training for in-the-wild WER.

关键词： Training Representation learning Emotion recognition Time series analysis Speech recognition Self-supervised learning Signal processing Biomedical monitoring Wearable devices Speech processing

来源：评论

学校读者我要写书评

暂无评论

AI Integration in the IT Professional Workplace: A Scoping Review and Interview Study with Implications for Education and Professional Competencies 2024

AI Integration in the IT Professional Workplace: A Scoping R...

引用

29th Working Group Reports on Innovation and Technology in computer science Education, ITiCSE WGR 2024

作者： Clear, Tony Cajander, Åsa Clear, Alison Mcdermott, Roger Daniels, Mats Divitini, Monica Forshaw, Matthew Humble, Niklas Kasinidou, Maria Kleanthous, Styliani Kultur, Can Parvini, Ghazaleh Polash, Mohammad Zhu, Tingting Department of Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand Department of Information Technology Uppsala University Uppsala Sweden School of Business Eastern Institute of Technology Auckland New Zealand School of Computing Robert Gordon University Aberdeen United Kingdom Dpt. of Computer Science Norwegian University of Science and Technology Trondheim Norway The Alan Turing Institute Newcastle Upon Tyne United Kingdom Open University of Cyprus Nicosia Cyprus The Open University of Cyprus Nicosia Cyprus School of Computer Science Carnegie Mellon University PittsburghPA United States Manning College of Information and Computer Sciences University of Massachusetts Amherst Amherst United States School of Computer Science University of Sydney Sydney Australia Department of Geography Geomatics and Environment University of Toronto Mississauga Toronto Canada School of Computer Science Newcastle University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9798400712081

As Artificial Intelligence (AI) continues transforming workplaces globally, particularly within the Information Technology (IT) industry, understanding its impact on IT professionals and computing curricula is crucial. This research builds on joint work from two countries, addressing concerns about AI's increasing influence in IT sector workplaces and its implications for tertiary education. The study focuses on AI technologies such as generative AI (GenAI) and large language models (LLMs). It examines how they are perceived and adopted and their effects on workplace dynamics, task allocation, and human-system interaction. IT professionals, noted as early adopters of AI, offer valuable insights into the interplay between AI and work engagement, highlighting the significant competencies required for digital workplaces. This study employs a dual-method approach, combining a systematic and multi-vocal literature review and qualitative research methods. These included a thematic analysis of a set of 47 interviews conducted between March and May of 2024 with IT professionals in two countries (New Zealand and Sweden). The research aimed to understand the implications for computing students, education curricula, and the assessment of emerging professional competencies. The literature review found insufficient evidence addressing comprehensive AI practice methodologies, highlighting the need to both develop and regulate professional competencies for effective AI integration. Key interview findings revealed diverse levels of GenAI adoption, ranging from individual experimentation to institutional integration. Participants generally expressed positive attitudes toward the technology and were actively pursuing self-learning despite some concerns. The themes emerging from the interviews included AI's role in augmenting human tasks, privacy and security concerns, productivity enhancements, legal and ethical challenges, and the evolving need for new competencies in the workplace.

关键词： artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Results From a Large-Scale IoT-based Intervention for Energy Saving and Sustainability Awareness via Behavior Change in 25 K-12 Schools in Europe

引用

IEEE Internet of Things Journal 2025年

作者： Mylonas, Georgios Amaxilatis, Dimitrios Paganelli, Federica Chatzigiannakis, Ioannis Koulouris, Pavlos Falkouskaya, Yelizaveta Markopoulos, Panos Athena Research Center Industrial Systems Institute Patras26504 Greece Comp. Tech. Institute and Press "Diophantus" 26504 Greece Spark Works Ltd GalwayH91 AHR1 Ireland Univ. of Pisa Dpt. of Computer Science Pisa56127 Italy CNIT Florence50134 Italy Sapienza University of Rome Dpt. of Computer Control and Management Engineering 00185 Italy Ellinogermaniki Agogi Athens Greece Eindhoven University of Technology AI Systems Institute Industrial Design Noord-Brabant Eindhoven5612 AE Netherlands

The unfolding climate crisis has resulted in a rising interest for increasing sustainability awareness and achieving energy savings worldwide. Several interventions within educational environments have been aimed at mobilizing younger audiences towards such goals. However, most of the interventions carried out so far are based on a subset of possible tools (e.g., IoT monitoring, gamification) and offer "all or nothing"approaches, which do not cope well with the uniqueness of schools and the need to adapt interventions to specific contexts (e.g. school size, building, curriculum, teacher involvement). We present a large-scale intervention in 25 school buildings in Europe over the course of two school years. Our intervention was based on the installation of a relatively low-cost IoT infrastructure in schools, that produced real-time energy-related data from the school buildings involved, and the application of a strategy combining, in a flexible and customizable way, educational activities, monitoring tools, gamification, and competition to motivate behavior change and achieve energy savings. Overall, 2983 students and 204 educators were directly involved to a variable degree of participation. Our results indicate a positive overall result in terms of short-term energy savings in most schools involved, with an average reduction of 20-25% in the energy that could be affected by end-users, as well as a 32.9% increase after the intervention in students self-reporting good or very good sustainability awareness. These findings suggest that such interventions can be a valuable step towards educating young students regarding sustainability and towards sustainable schools, if designed and implemented properly. © 2014 IEEE.

关键词： Behavior Change Education for Sustainable Development Energy Literacy Energy Saving Environmental Education Gamification Internet of Things K-12 Sustainability Sustainable Smart Schools

来源：评论

学校读者我要写书评

暂无评论

Whisper-Slu: Extending a Pretrained Speech-to-Text Transformer for Low Resource Spoken Language Understanding

Whisper-Slu: Extending a Pretrained Speech-to-Text Transform...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Meeus, Quentin Moens, Marie-Francine Van Hamme, Hugo Ku Leuven Dpt. Computer Science Belgium Ku Leuven Dpt. Electrical Engineering Belgium

ISBN: (纸本)9798350306897

Human-computer interactions require systems that work out of the box without requiring lots of data to adapt to a new task or user. In this research, we address low resource spoken language understanding tasks such as named entity recognition (NER), intent recognition (IR), and slot filling (SF) to research how a pretrained model can be modified for a new task, then finetuned with few labelled data. We propose extending the Whisper model with task-specific modules for NER, SF, and IR, leveraging a Markov network as output structure. We develop a novel approach to finetuning by removing irrelevant weights and reorganizing the embeddings to drastically improve the performance in a low-resource setting. Our approach outperforms previous models without external language models and demonstrates effective transfer learning, even with very limited training data. The models exhibit a small footprint, making them suitable for applications requiring robustness, few-shot learning, and efficiency. © 2023 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Camera calibration method for an automotive safety driving system

引用

Journal of Institute of Control, Robotics and Systems 2015年第7期21卷 621-626页

作者： Park, Jong-Seop Kim, Gi-Seok Roh, Soo-Jang Cho, Jae-Soo Dpt. of Computer Science and Engineering Korea University of Technology and Education Korea Republic of

This paper presents a camera calibration method in order to estimate the lane detection and inter-vehicle distance estimation system for an automotive safety driving system. In order to implement the lane detection and vision-based inter-vehicle distance estimation to the embedded navigations or black box systems, it is necessary to consider the computation time and algorithm complexity. The process of camera calibration estimates the horizon, the position of the car's hood and the lane width for extraction of region of interest (ROI) from input image sequences. The precision of the calibration method is very important to the lane detection and inter-vehicle distance estimation. The proposed calibration method consists of three main steps: 1) horizon area determination;2) estimation of the car's hood area;and 3) estimation of initial lane width. Various experimental results show the effectiveness of the proposed method. © ICROS 2015.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Context-sensitive content representation for static document

Context-sensitive content representation for static document

引用

11th Asia-Pacific Software engineering Conference (APSEC 2004)

作者： Chu, WC Chen, YW Chen, JN Dpt. of Computer Science and Information Engineering Tunghai University Taiwan Dpt. of Engineering Science National Cheng Kung University Taiwan

ISBN: (纸本)0769522459

Due to the convenience of pervasive information environment, many people use various computing devices to perform plenty kinds of tasks. In the field of education, there are various applications to facilitate learner, especially for e-learning. However, some computing devices suffer from the limited resources and can not accept rich information content. Therefore, the information content has to be tailored into different kinds of presentation depending on the types of computing devices. Context sensitivity is an application software system's ability to sense and analyze context from various sources. In this paper, we aim to customize static documents using context-sensitive middleware (CSM) to sense the computing device, and then using the agent-based parser to provide suitable content representation dynamically.

关键词： e-learning context-sensitive customization

来源：评论

学校读者我要写书评

暂无评论

New experimental methods for determining electromagnetic field attenuation in nanomaterials

New experimental methods for determining electromagnetic fie...

引用

15th International Symposium for Design and Technology of Electronics Packages, SIITME 2009

作者： Aciu, Lia Elena Nicolae, George Ogrutan, Petre Electrical Engineering and Computer Science Dpt. Transilvania University of Brasov Romania

ISBN: (纸本)9781424451333

The interaction between electromagnetic radiation and infinite plane shield having finite thickness d, placed in free space in the plane waves region depends on material/shield macroscopic parameters (e, fl, a), its thickness, radiation frequency and incidence angle. Lately, entirely new classes of materials have been developed. Knowing the characteristics and the behavior of nanomaterials inside different media creates wide opportunities for a variety ofindustrial applications. For that reason, a simple method to determine their electromagnetic field (EMF) attenuation properties is also necessary. This paper presents experimental methods for the investigation of nanomaterials behavior inside the EMF. ©2009 IEEE.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

ADDON: A paradigm for large-scale document discussion

ADDON: A paradigm for large-scale document discussion

引用

10th IASTED International Conference on Software engineering, SE 2011

作者： Allamanis, Miltiadis Mavrakis, Chris Electrical and Computer Engineering Dpt. Aristotle University of Thessaloniki Thessaloniki Greece Electrical and Computer Engineering Dpt. Democritus University of Thrace Xanthi Greece

ISBN: (纸本)9780889868649

Large-scale document discussion is becoming an increasingly important need for governments and organizations. To our knowledge, existing tools and methods cannot extensively support such processes. This paper proposes the issues that need to be tackled, namely discussion consistency, debate clarity, discussion evolution and conversation monitoring. After outlining the challenge of supporting such discussions, we describe addon, a prototype application implementing all such requirements. The prototype consists of a concise web application that is able to support and enhance such discussions and improve decision quality. We then proceed in evaluating addon's performance. Finally, the paper concludes proposing various extensions and applications that can derive from addon.

关键词： Intranets

来源：评论

学校读者我要写书评

暂无评论

MSNER: A Multilingual Speech Dataset for Named Entity Recognition 20

MSNER: A Multilingual Speech Dataset for Named Entity Recogn...

引用

20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation, ISA 2024

作者： Meeus, Quentin Moens, Marie-Francine Van Hamme, Hugo LIIR Lab. Computer Science Dpt. KU Leuven Belgium PSI Electrical Engineering Dpt. KU Leuven Belgium

ISBN: (纸本)9782493814326

While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing MSNER, a freely available, multilingual speech corpus annotated with named entities. It provides annotations to the VoxPopuli dataset in four languages (Dutch, French, German, and Spanish). We have also releasing an efficient annotation tool that leverages automatic pre-annotations for faster manual refinement. This results in 590 and 15 hours of silver-annotated speech for training and validation, alongside a 17-hour, manually-annotated evaluation set. We further provide an analysis comparing silver and gold annotations. Finally, we present baseline NER models to stimulate further research on this newly available dataset. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Silver

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：