检索结果-内蒙古大学图书馆

2024 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2024

作者： Fikirie, Tenagne Azmeraw, Emiyamrew Tesfay, Wakjira Debasu, Abrham Bahir Dar University Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology P.O.Box 26 Bahir Dar Ethiopia University of Gondar College of Engineering Department of Computer Engineering Gondar Ethiopia Assosa University Department of Computer Engineering Assosa Ethiopia Bahir Dar University Faculty of Computing Bahir Dar Institute of Technology P.O.Box 26 Bahir Dar Ethiopia

ISBN: (纸本)9798331527792

Human action recognition (HAR) is a computer vision technique used to understand the activity of the action performed in the scene. computer vision technology has become popular and is applied in various areas like surveillance systems, robot vision, satellite imaging, etc. However, using computer vision in human activity recognition is still challenging due to the dynamic movement of human motion, noise, occlusion, complex background, variable dressing style, varying illumination, and others. Various research has been conducted to address these problems, yet they remain challenging. In this study, we applied human action recognition techniques to interpret the meaning of Tekele Zemamie's actions in the Ethiopian Orthodox Tewahedo Church. Tekele Zemamie is church choirs' most common activity during stage ceremonies and other events. To carry out the research experimental work we have prepared 900 video clip datasets. The dataset was recorded in a 2.5-meter distance using a 48MP Camera. From the dataset, 80% was used for training and the remaining 20% was used to test the model's performance. We applied skip frame selection techniques to a single video by selecting 30 frames and we applied spatial and temporal feature extraction techniques. To overcome the stated problems and to develop the recognition model experimental works have been examined using two deep-learning models CNN-LSTM and CNN-Bi-LSTM, and we achieved 95% and 97% recognition accuracy respectively. From the proposed models, CNN-Bi-LSTM works better than the other model. © 2024 IEEE.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Sensors, Signals, and Imaging Informatics: Best contributions from 2023

引用

Yearbook of Medical Informatics 2025年第1期33卷 277-279页

作者： Rittner, Leticia Baumgartner, Christian Deserno, Thomas M. Medical Imaging Computing Lab (MICLab) School of Electrical and Computer Engineering University of Campinas Brazil Institute of Health Care Engineering with European Testing Center of Medical Devices Graz University of Technology Austria Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Braunschweig Germany

OBJECTIVES: To identify and highlight research papers that represent the advances and trends in the field of sensors, signals, and imaging informatics in 2023. METHOD: We performed a bibliographic search on Scopus and PubMed databases using Medical Sub-ject Heading (MeSH) terms combined with keywords. Our aim was to build specific queries for sen-sors, signals, and imaging informatics. We disregarded journals that returned less than three papers on the query and then evaluated titles and abstracts of the papers using a 3-point Likert scale, ranging from 1 (do not include) to 3 (should be included). Only the papers with a total score of 8 or more were re-evaluated again, this time considering the full text, and the top 14 papers with the highest scores were then reviewed by external reviewers and editors of the International Medical Informatics Association (IMIA) Yearbook. RESULTS: Among the 643 returned papers published in 2023 in the various areas of sensors, signals, and imaging informatics (SSII), we selected 58 papers with at least 8 Likert points (in total). After a comprehensive evaluation, we identified 14 papers as the best contributions and sent them to eight external reviewers. The full review process resulted in a selection of the four best papers, which were then approved by consensus by the IMIA Yearbook Editorial Board. Although the imaging informatics sub-search returned all of these four papers, one is about sensorless freehand 3D ultrasound recon-struction (representing sensors), and another deals with video-based pulse rate estimation (representing signals). CONCLUSIONS: Sensors, signals, and imaging informatics is a dynamic field of intensive research. The four best papers in 2023 represent advanced approaches focusing on DL-based image processing, analysis, and indicate a shift in the research field from sensor technology development to biosignal and image analysis. The Author(s). This is an open access article published by Thieme under the terms

关键词： Biomedical informatics Deep learning Imaging informatics International Medical Informatics Association Yearbook Machine learning Personalized medicine Sensor informatics Signal in-formatics

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study of Diverse Models and Datasets for Transfer Learning based Image Classification on Sparse Data 10

An Exploratory Study of Diverse Models and Datasets for Tran...

引用

10th International Multidisciplinary engineering Research Conference on Moratuwa engineering Research, MERCon 2024

作者： Pathmarasa, Jathurshan Wijenayake, Udaya Wijesinghe, Ruchire Eranga Silva, Bhagya Nathali University of Sri Jayewardenepura Faculty of Engineering Department of Computer Engineering Nugegoda Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798331529048

Transfer learning is a powerful technique for image classification, especially when dealing with limited data. However, selection of the best transfer learning approach and model remains challenging, since the strategy is highly influenced by the scenario. This work conducted a thorough analysis of four transfer learning approaches for binary classification, and multiclass classification using four pretrained models i.e. MobileNetV2, MobileNetV3Large, EfficientNetB0, and EfficientNetB5. The test accuracy was measured with respect to the sample size considering the effects of data augmentation and fine tuning. The key finding of the study revealed that data augmentation has improved the test accuracy by up to 11.8%. Moreover, the lightweight models marked a breakthrough by outperforming large scale models' accuracy for sparse data settings when fine tuning (FT) and data augmentation (DA) are applied appropriately. Hence, this work provides a comprehensive overview on selecting different transfer learning approaches for sparse data classification by exploring diverse models and datasets, while discussing the consequences and challenges for future real-world applications. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Simultaneous information and energy transmission through quantum channels

引用

Physical Review A 2025年第1期111卷 012609-012609页

作者： Bishal Kumar Das Lav R. Varshney Vaibhav Madhok Department of Physics Indian Institute of Technology Madras Chennai 600036 India Centre for Quantum Information Communication and Computing (CQuICC) Indian Institute of Technology Madras Chennai 600036 India Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana Illinois 61801 USA

The optimal rate at which information can be sent through a quantum channel when the transmitted signal must simultaneously carry some minimum amount of energy is characterized. To do so, we introduce the quantum-classical analog of the capacity-power function, and we generalize results in classical information theory for transmitting classical information through noisy channels. We show that the capacity-power function for a classical-quantum channel, for both unassisted and private protocol, is concave, and we also prove additivity for unentangled and uncorrelated ensembles of input signals for such channels. This implies that we do not need regularized formulas for calculation. We show that these properties also hold for all noiseless channels when we restrict the set of input states to be pure quantum states. For general channels, we geometrically prove that the capacity-power function is piecewise concave, with further support from numerical simulations. Further, we connect channel capacity to properties of random quantum states. In particular, we obtain analytical expressions for the capacity-power function for the case of noiseless channels using properties of random quantum states under an energy constraint and concentration phenomena in large Hilbert spaces.

关键词： quantum channel

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Channel Prediction in Non-Stationary Wireless Fading Environments

Deep Learning for Channel Prediction in Non-Stationary Wirel...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Upadhyay, Abhay Venu, Nookala Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India Data Science and Quantum Computing ABV Indian Institute of Information Technology and Management Gwalior India

ISBN: (纸本)9798350379525

In non-stationary wireless fading channels deep learning models are effective in predicting channel states as indicated by this study. This work compared the LSTM and GRU models with autoregressive methods or Kalman filter, implying that deep learning is indeed able to capture temporal dependence between variables and was likely more adapted than linear method when dealing with many changes in dynamics. From the perspective of pre-processing data, keys like attention mechanism and transfer learning were decisive elements in helping them to improve prediction scores and make models more robust. These results showed that these enhanced procedures allow the models to generalise over a wide range of non-stationary situations, generating consistent performance in various diverse environments. This study indicates the promise of deep learning for enhancing wireless network operation, which could lead to greater self-awareness and utilization features in emerging future-generation wireless systems. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Smart and Advanced electrical Skills: Identifying Current Gaps and Emerging Trends 5

Smart and Advanced Electrical Skills: Identifying Current Ga...

引用

5th IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2024

作者： Karapidakis, Emmanuel Markaki, Marini Apostolakis, Spyridon Canizes, Bruno Androulakis, Radamanthys Castro, Fabio Hellenic Mediterranean University Electrical and Computer Engineering Department Heraklion Greece Polytechnic Institute of Porto GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Porto Portugal ECTE GECAD - Research Group on Research Department Rethymno Greece

ISBN: (纸本)9798350352863

With the rise of smart buildings, new expertise gaps and security vulnerabilities are emerging, necessitating a comprehensive understanding of their current state and proactive future planning to address these challenges. Such identification is crucial for mapping the pathway towards vocational modernization (keeping up with trends and goal alignment). To assess these gaps, this paper explores the extensive literature that draws on workshops, expert interviews, and research to identify emerging roles and training needs across seven countries: Greece, Spain, Portugal, Italy, North Macedonia, Germany, and the Netherlands. In particular, it examines the validity of its findings in critical areas such as security, privacy, and the integration of smart grids with energy markets. Additionally, the paper highlights future skills gaps emerging from advancements in IoT, automation, and renewable energy technologies. It emphasizes the growing demand for specialized electrical expertise to optimize energy production, integrate monitoring and storage systems, and manage electric vehicle charging and energy communities effectively. In conclusion, the study identifies critical gaps in expertise and training needed to keep up with the rapid evolution of smart building technologies. Emerging trends highlight the demand for interdisciplinary skills, particularly in IoT, automation, and renewable energy. As these fields advance, expertise in cybersecurity, energy management, and smart grid integration will be crucial, emphasizing the need for proactive workforce development and planning. The findings can be used to inform and direct policymakers towards the smooth reexamination of vocational training. © 2024 IEEE.

关键词： Power grids

来源：评论

学校读者我要写书评

暂无评论

CARA: A Hybrid Framework Integrating Swarm AI Agents and Knowledge Graphs for Advanced LLM Reasoning 6

CARA: A Hybrid Framework Integrating Swarm AI Agents and Kno...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Pussadeniya, Nirodya Wijesinghe, Ruchira Wijenayake, Udaya Silva, Bhagya University of Sri Jayewardenepura Faculty of Engineering Department of Computer Engineering Nugegoda Sri Lanka Sri Lanka Institute of Information Technology Faculty of Engineering Department of Electrical and Electronic Engineering Malabe Sri Lanka Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798331517878

Language models excel in linguistic processing but often face challenges with complex reasoning tasks that require real-world interaction and multi-step logic. This paper presents the Cognitive Adaptive Reasoning Architecture (CARA), a framework that enhances reasoning by integrating a modular swarm architecture with knowledge graphs (KGs) and specialized agents. These agents, equipped with diverse tools, dynamically adapt to various tasks, actively engaging with real-world data. CARA's continuous memory update cycle ensures each reasoning step is based on up-to-date, contextual KG knowledge, enhancing decision-making. Incorporating human insights further aligns outcomes with nuanced cognition. Experimental results demonstrate CARA's superior performance over larger models, advancing language models' reasoning capabilities for more context-aware, informed decision-making in dynamic environments. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Security in the World of Internet of Things (IoT): Overcoming Challenges

Security in the World of Internet of Things (IoT): Overcomin...

引用

2024 International Conference on Sustainable computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Gannavaram, Venkat Tulasi Krishna Desu, Sravya Jujjuru, Venkata Rohith Renikunta, Sri Vatsa Venkata Tejaswi Gajula, Arun Kumar Reddy, Ganta Raghotham School of Electrical Computer and Energy Engineering Arizona State University Tempe United States School of Computing and Augmented Intelligence Arizona State University Tempe United States Department of Electronics and Communication Engineering Kakatiya Institute of Technology and Science Warangal India

ISBN: (纸本)9798350355338

Internet of Things (IoT) is turning out to be more prominent in our everyday existence, with smart home appliances and industrial control systems serving as examples. But the proliferation of IoT devices and internet connectivity increased the potential of security breaches. Botnet attacks, injection attacks, Domain Name Systems (DNS) spoofing attacks, firmware assaults, zero-day attacks, brute-force attacks, and cryptographic attacks may be used against IoT devices. These assaults may result in the loss of data, illegal access, and even physical damage to infrastructure and people. There are various potential courses of action. Machine Learning subpart of Artificial Intelligence have the capacity for finding and prevent dangers in real time. With blockchain technology, an IoT network can have a secure and unbreakable a record of every exchange and data transfers. Hardware-based security techniques, such as secure boot and trusted execution environments, may protect IoT devices against attacks that seek to compromise the underlying hardware or firmware. Standardizing security procedures may ensure that all devices can work together safely and achieve a given degree of security. The use of privacy-enhancing technology, IoT data may be kept confidential and sensitive information disguised. © 2024 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Secrecy Capacity Optimization in RF/FSO Systems: Impact of Mixed Rayleigh and Log-Normal Fading with Atmospheric Turbulence

Secrecy Capacity Optimization in RF/FSO Systems: Impact of M...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Upadhyay, Abhay Venu, Nookala Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India ABV Indian Institute of Information Technology and Management Data Science and Quantum Computing Gwalior India

ISBN: (纸本)9798350379525

This paper investigates the secrecy capacity optimization in RF/FSO systems with mixed Rayleigh and log-normal fading, while masking eavesdroppers channel state information () as well as suffering from atmospheric turbulence. We explore the impact of several parameters including beamforming angles, modulation schemes and hybrid RF/FSO link configurations through a combination of simulations as well as analytical models. Secrecy capacity is enhanced for an improved SNR and vice versa under higher turbulence conditions and cooler influents eavesdropped scenarios. Performance of the hybrid RF/FSO systems dominates considerably over single-link solutions, especially at longer distances. All these mechanisms appreciably increase the secrecy capacity, while beamforming and advanced modulation techniques offer most of the improvement. The study also demonstrates the interdependencies of system parameters, providing guidelines for designing secure communication systems under different environmental and operational conditions. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Partitioning-Based Filtering Technique for Accelerated Speckle Reduction in SAR Images 15

Partitioning-Based Filtering Technique for Accelerated Speck...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Garg, Avni Nirmala, D. Goyal, Dinesh Savitha, R. Deshpande, Leena A. Kuppuraj, T. Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Quantum University Research Center Quantum University India School of Engineering and Technology Electrical and Electronics Engineering Karnataka Bangalore India Vishwakarma Institute of Technology Department of Computer Engineering Pune India Karpagam Academy of Higher Education Department of Computer Applications Coimbatore641021 India

ISBN: (纸本)9798350370249

Partitioning-based total filtering is a way to lower speckle noise in synthetic Aperture Radar (SAR) pics. This technique uses a brand-new mass-spring analogy to partition a photograph into present-day homogenous areas. A hard and fast state-of-the-art policy is then hooked up to pick out the speckle-loose pixels' present-day place and build a statistical model of today's speckle-free pixels from them. This statistical version is applied to the alternative pixels within every region to generate a speckle-decreased picture. This approach ends in an improved noise reduction effect compared to SAR denoising strategies while keeping the edge features inside the picture. Additionally, it requires no prior information approximately the speckles and, therefore, can be used for any SAR image without tuning the parameters. As a result, this technique can boost the denoising procedure and convey proper consequences with much less computational complexity. © 2024 IEEE.

关键词： Complexity Computational Consequences Filtering Partitioning Synthetic

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：