检索结果-内蒙古大学图书馆

International Conference on Electrical, Communication, and computer engineering (ICECCE)

作者： Ahsanul Bari Hezerul Abdul Karim Fahmid Al Farid Mina Asaduzzaman Farshid Amirabdollahian Sarina Mansor Faculty of Engineering Multimedia University Cyberjaya Malaysia Faculty of Information Science and Technology Multimedia University Melaka Malaysia Faculty of Engineering and Computer Science the University of Hertfordshire Hatfield

ISBN: (数字)9798331529437

ISBN: (纸本)9798331529444

Human Activity Recognition (HAR) is crucial for the development of intelligent assistive technologies in Ambient Assisted Living (AAL) environments. This paper proposes an innovative method for Multi-View Human Activity Recognition (MV-HAR) using lightweight deep learning models, specifically MobileNet and Cyclone-CNN (CCNet), to achieve quick and precise activity detection. Utilizing the Robot House Multi-View Human Activity Recognition (RHM-HAR) dataset, which contains four different views-front, back, ceiling (omni), and mobile robot-our models effectively address challenges related to viewpoint variation and motion dynamics. The dataset includes 14 multi-view daily living action classes, providing a balanced set of synchronized human actions suitable for multi-domain neural network learning. MobileNet and CCNet are employed for their high recognition accuracy, computational efficiency, and real-time application capabilities in AAL scenarios. We propose a Mutual Information (MI)-based method to assess the redundancy and relevance of each viewpoint, ensuring the fusion of multi-view data with minimum redundancy and maximum relevance. Benchmarking results demonstrate that multi-view combinations significantly enhance recognition performance compared to single-view models, particularly in complex activities involving high levels of movement.

关键词： Deep learning Ambient assisted living Accuracy Computational modeling Termination of employment Assistive technologies Transformers Computational efficiency Human activity recognition Robots

来源：评论

学校读者我要写书评

暂无评论

Beyond Playlists: AI-Driven Emotion-Based Music Recommendation Systems

Beyond Playlists: AI-Driven Emotion-Based Music Recommendati...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Hrishikesh Shiralaskar Sameer Mendhe Department of Computer Science & Engineering Faculty of Engineering & Technology Datta Meghe Institute of Higher Education md Research Wardha Maharashtra India Department of Computer Science & Design Faculty of Engineering & Technology Datta Meghe Institute of Higher Education and Research Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Music recommendation systems have evolved from simple playlist curation techniques to sophisticated AI-driven models capable of analyzing human emotions for personalized song suggestions. Emotion-based music recommendation systems integrate advanced machine learning, deep learning, and artificial intelligence techniques to detect users' emotional states through various input modes, including facial expressions, speech tone, text analysis, and physiological signals. These systems aim to enhance user experience by dynamically selecting music that aligns with real-time emotions, thereby improving mood regulation and mental well-being. This review explores the methodologies employed in emotion-based music recommendation systems, including deep learning architectures, facial recognition techniques, and sentiment analysis models. It also discusses the challenges associated with real-time emotion detection, data privacy concerns, cross-cultural differences in music perception, and system adaptability. Furthermore, the paper highlights emerging trends and future research directions, such as multimodal emotion detection, hybrid AI models, reinforcement learning, and ethical AI frameworks. Addressing these challenges and advancements will be crucial in developing more robust, accurate, and user-centric emotion-based music recommendation systems.

关键词： Deep learning Emotion recognition Sentiment analysis Analytical models Adaptation models Reinforcement learning Brain modeling Real-time systems Physiology Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Title-Based Fake News Detection Using LSTM

Title-Based Fake News Detection Using LSTM

引用

International Conference on computer and Information technology (ICCIT)

作者： Ratul Bhattacharjee Md Abu Sufian Md Abu Talha Md Shaikat Ahmed Faiza Tasnim Sadia Afrin Sara K.M. Nazmul Islam Department of Computer Science and Engineering (CSE) Faculty of Science & Technology (FST) American International University–Bangladesh (AIUB) Dhaka Bangladesh Department of Electrical and Electronics Engineering (EEE) Faculty of Engineering (FE) American International University–Bangladesh (AIUB) Dhaka Bangladesh Department of Computer Science and Engineering (CSE) Faculty of Engineering (FE) Ahsanullah University of Science and Technology (AUST) Dhaka Bangladesh Department of Computer Science and Engineering (CSE) Faculty of Science & Engineering (FSE) Northern University Bangladesh (NUB) Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

In today’s information-driven society, the rapid dissemination of fake news through digital platforms has emerged as a critical issue, undermining public trust and distorting societal discourse. As online misinformation continues to spread, there is a growing demand for advanced automated techniques to effectively detect and combat false information. This study introduces a Long Short-Term Memory (LSTM) based model tailored for fake news detection, concentrating on the analysis of news titles. The model exploits the inherent temporal dependencies and contextual clues within headlines to accurately differentiate between authentic and fabricated news. Tested on a comprehensive dataset, the model achieved an impressive accuracy of 93.5%, with precision and recall rates reaching 92.8% and 94.2%, respectively. These findings demonstrate the efficacy of leveraging news titles in the detection of fake news and underscore the potential of LSTM networks as a robust tool in the ongoing battle against misinformation.

关键词： Support vector machines Logistic regression Accuracy Text categorization Refining Focusing Natural language processing Fake news Long short term memory Context modeling

来源：评论

学校读者我要写书评

暂无评论

Risk Management in Designing and Developing Innovative, Sustainable Buildings 15th

Risk Management in Designing and Developing Innovative, Sust...

引用

15th KES International Conference on Sustainability and Energy in Buildings, SEB 2023

作者： Krechowicz, Maria Krechowicz, Adam Faculty of Management and Computer Modelling Kielce University of Technology Al. 1000-Lecia Państwa Polskiego 7 Kielce25-314 Poland Faculty of Electrical Engineering Automatic Control and Computer Science Kielce University of Technology Al. 1000-Lecia Państwa Polskiego 7 Kielce25-314 Poland

ISBN: (纸本)9789819985005

Nowadays, we can observe a growing interest in sustainable buildings. Sustainable development cannot be achieved without introducing innovations in green building;therefore, innovations are important component of sustainable engineers’ job. Innovative, sustainable buildings have numerous advantages, but it should be remembered that their design, and construction is more complex and associated with higher risk and uncertainty than traditional buildings. The goal of this work is to propose a new model of risk management which is based on fault tree analysis and Fuzzy sets theory. Sixteen unwanted events in innovative, sustainable building projects were identified, a fuzzy fault tree was developed. The application of the proposed approach was shown on one example of innovative, sustainable building in Poland. Two variants of project execution were compared: with and without introducing risk management strategy. Application of fuzzy sets by using linguistic variables by experts when assessing risks of particular unwanted events enabled to decrease uncertainty and avoid problems with obtaining the crisp values of the basic events probability. Application of the proposed model allowed us to identify the critical risks of the project, calculate top event risk, and compare the project’s risk level after introducing risk management strategies. The proposed model is helpful for designers, constructors, owners, and clients to develop successful innovative, sustainable buildings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fault tree analysis

来源：评论

学校读者我要写书评

暂无评论

Smart Aging technology with IoT and Deep Learning Analytics for Elderly Activity Patterns and Health Outcomes 9

Smart Aging Technology with IoT and Deep Learning Analytics ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Srinivasan, V.Prasanna Pandey, Pramod Muthumarilakshmi, S. Konidhala, Jothibabu. Rajmohan, M. Murugan, S. R.M.D. Engineering College Department of Information Technology Kavaraipettai Tamil Nadu Chennai India Symbiosis institute of Technology Nagpur Campus Maharashtra Pune India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India University of Technology and Applied Sciences- Al Musannah Department of Electronics and Communication Engineering South Al Batina Musanna Oman Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350377972

Innovative healthcare solutions for older people have developed from the fast progress of the Internet of Things (IoT) technology and deep learning (DL). This research proposes a smart aging system that uses IoT devices and Long Short-Term Memory (LSTM) networks to track and evaluate geriatric behavior and health. The proposed approach collects real-time health and daily activity data using a wearable, smart home, and ambient sensors. A central platform uses LSTM networks to identify and forecast activity and health variables from collected data. LSTM can capture long-term relationships and patterns in time-series data, making it ideal. By evaluating these patterns, the system may detect abnormal behavior that may indicate health difficulties like falls, chronic diseases, or cognitive impairment. Preliminary findings show that LSTM-based analytics may provide accurate and timely insights to help caregivers and healthcare providers improve health outcomes. By encouraging mobility and preventive health management, the smart aging system improves older quality of life and decreases healthcare costs. To increase predicted accuracy and system dependability, LSTM models will be refined, the dataset expanded, and more health measures will be included. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Episodic memory based continual learning without catastrophic forgetting for environmental sound classification

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第4期14卷 4439-4449页

作者： Karam, Said Ruan, Shanq-Jang Haq, Qazi Mazhar ul Li, Lieber Po-Hung Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Sec. 4 No. 43 Keelung Rd Taipei10607 Taiwan Military College of Signals National University of Sciences and Technology Islamabad Pakistan Faculty of Medicine and Institute of Brain Science National Yang-Ming Chiao-Tung University Taipei Taiwan Department of Otolaryngology Cheng Hsin General Hospital Taipei Taiwan Department of Medical Research China Medical University Hospital China Medical University Taichung Taiwan

Convolutional neural network suffers from catastrophic forgetting during continual learning. This is one of the major obstacles for artificial intelligence, to solve new problems without forgetting the previously learned information. In this article, we propose an episodic memory technique for learning sound data incrementally. The proposed method observes tasks sequentially and successfully solves the new task without forgetting the previous task. The results show that the proposed method is able to transfer backward and forward knowledge efficiently. The performance evaluation demonstrates that the proposed method achieves better performance than other benchmarks. For ESC-50 and UrbanSound8K datasets, the proposed method obtained 96.5% and 93.1% accuracy, respectively. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Tensile Testing Based on the Polarization-maintaining Fiber Powered by an SM Optical Fibre 4

Tensile Testing Based on the Polarization-maintaining Fiber ...

引用

4th International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2024

作者： Kyselak, Martin Vavra, Jiri Vylezich, Zdenek Grenar, David Slavicek, Karel University of Defense Faculty of Military Technology Department of Electrical Engineering Brno Czech Republic University of Technology Faculty of Electrical Eng. and Communication Dept. of Telecommunications Brno Czech Republic Institute of Computer Science Masaryk University IT Infrastructure Division Brno Czech Republic

ISBN: (纸本)9798350391183

Optical fibre sensors are currently used to detect many non-electrical phenomena. The latest sensors analyze the polarization properties of light inside an optical fiber. Unlike interferometric methods, this method uses the interference of two planes of polarization at the output of the optical fibre. The sensors are divided into linear polarizer sensors or multi-fibre interference sensors based on different ways of converting the polarization state into a change in the intensity of the optical radiation. These sensors are particularly suitable for low frequency vibration measurements due to the transformation of beats into the longitudinal deformation of the optical fibre. The aim of the presented measurements was to demonstrate that these polarization vibration sensors have excellent sensitivity and are thus suitable for vibration detection. This paper demonstrates that polarization sensors have excellent sensitivity, are convenient and inexpensive to install, and, due to their non-electric nature, are suitable for hazardous environments. In addition, it is possible to employ these sensors as intrusion detection and prevention systems and remotely power them at a distance of tens of kilometers. The motivation for this research was the lack of information and equipment for vibration testing of optical fibres and the associated polarization changes. © 2024 IEEE.

关键词： Tensile testing

来源：评论

学校读者我要写书评

暂无评论

Battery Refurbishment Technologies in Industry 4.0: A Review 6

Battery Refurbishment Technologies in Industry 4.0: A Review

引用

6th International Conference on Electrical, Control and Instrumentation engineering, ICECIE 2024

作者： Nguyen-Quang, Nam Nguyen-Vinh, Khuong Gono, Radomir Ho Chi Minh City University of Technology Vietnam National University Ho Chi Minh City Ho Chi Minh City Viet Nam School of Science Engineering and Technology RMIT University Ho Chi Minh City Viet Nam VSB Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Ostrava Czech Republic

ISBN: (纸本)9798350380040

The increasing demand for batteries in various industries has resulted in the problem of battery waste. An industry 4.0 will need to tackle this kind of environmental problem. With the need for a more sustainable solution, battery refurbishment technologies have emerged as a way to reduce the environmental impact of battery waste, conserve resources, and save costs. In this review, we will discuss the existing battery refurbishment technologies in the world, including their advantages and disadvantages. The authors also discussed about their current battery refurbishment project with the help of artificial intelligence. © 2024 IEEE.

关键词： Battery Refurbishment Environmental Impact Industry 4.0 Sustainable

来源：评论

学校读者我要写书评

暂无评论

PAPR Reduction in MIMO-OFDM using Nonlinear Inertia Weight Factor of Whale Optimization Algorithm 2

PAPR Reduction in MIMO-OFDM using Nonlinear Inertia Weight F...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Habelalmateen, Mohammed I. Archana Reddy, R. Reddy, Chetana Nagarjuna, N. Pradeep Kumar, S. Universiti Tun Hussein Onn Malaysia Parit Raja Faculty of Electrical and Electronic Engineering Johor Batu Pahat Malaysia The Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf Iraq Sr University School of Computer Science and Artificial Intelligence Telangana India Oxford College of Engineering Department of Electronics and Communication Bangalore India Cvr College of Engineering Department of Csit Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350317558

In the landscape of optimization for mitigating the Peak-to-Average Power Ratio (PAPR) in Multiple-Input Multiple-Output and Orthogonal Frequency Division Multiplexing (MIMO-OFDM) systems, prevalent techniques like the tone reservation scheme and l-norm Cyclic Algorithm (LNCA) algorithm grapple with inherent challenges linked to computational complexity and iterative algorithm derivation. While strides have been made with models such as Twin Symbol Hybrid Optimization by the premise of Partial Transmit Sequence (TSHO-PTS) and Advanced Switching Differential Evolution (ASDE), persistent concerns related to symbol overlaps and algorithmic limitations underscore the need for further refinement in computational efficiency within OFDM-based communication systems. In response to these challenges, the proposed Nonlinear Inertia Weight Factor within the Whale Optimization Algorithm (NIWF-WOA) emerges as a solution. Comparative analysis against existing methods like LCNA, Modified Dragonfly Optimization algorithm (MDOA), TSHO-PTS, and ASDE reveals the superior performance of NIWF-WOA. Numerical validation affirms its efficacy, with a recorded in Bit Error Rate (BER) of 10-2.5, SNR 10-3.4 and PAPR of.10-4.2, underscoring the substantial improvement achieved by NIWF-WOA in optimizing PAPR reduction for MIMO-OFDM systems. © 2024 IEEE.

关键词： Landscape of optimization MIMO-OFDM system Non-linear weight factor Peak to Average Power Ratio Whale optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Literary Analysis through Artificial Intelligence and Machine Learning: Insights from 'The Alchemist' 2

Enhancing Literary Analysis through Artificial Intelligence ...

引用

2nd IEEE International Conference on Recent Advances in Information technology for Sustainable Development, ICRAIS 2024

作者： Vinodini, S. Adithya Pothan Raj, V. Sathyabama Institute of Science and Technology Faculty of Arts Dept. of English Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Dept. of CSE Chennai India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354461

The rapid growth of digital literature has necessitated the advancement of analytical tools to extract valuable insights from extensive textual data. This paper investigates the application of Artificial Intelligence (AI) and Machine Learning (ML) in literary analysis, presenting innovative methods to understand and interpret complex narratives and themes in literary works. Traditional literary analysis relies on human interpretation, which, while insightful, is often subjective and labor-intensive. The advent of digital humanities has sparked interest in computational methods to enhance traditional literary analysis. AI and ML, especially through Natural Language Processing (NLP), offer powerful solutions to analyze literary themes. Techniques such as sentiment analysis, topic modeling, and named entity recognition can dissect thematic elements, emotional tones, and character dynamics in texts. For example, sentiment analysis reveals underlying themes related to mood and character psychology, while topic modeling uncovers hidden thematic structures. Machine learning algorithms, through supervised and unsupervised learning, can recognize and classify themes across different literary works. Despite challenges like the complexity of human language and contextual nuances, AI and ML significantly enhance the speed and scale of literary analysis, uncovering subtle themes often overlooked by human readers. The Flair tool, developed by Zalando Research, exemplifies a robust NLP library that enhances literary analysis through pre-trained models for tasks such as Named Entity Recognition (NER), sentiment analysis, text classification, and Part-of-Speech (POS) tagging. Applying Flair to Paulo Coelho's "The Alchemist"demonstrates its potential to analyze genres, themes, and stylistic categories, showcasing the transformative capabilities of AI and ML in the digital humanities. © 2024 IEEE.

关键词： Natural language processing systems

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：