检索结果-内蒙古大学图书馆

MobVGG: Ensemble technique for birds and drones prediction

Heliyon 2024年第21期10卷 e39537页

作者： Muhammad Saqib, Sheikh Mazhar, Tehseen Iqbal, Muhammad Almogren, Ahmad Shahazad, Tariq Rehman, Ateeq Ur Hamam, Habib Department of Computing and Information Technology Gomal University Dera Ismail Khan 29220 Pakistan Department of Computer Science School Education Department Government of Punjab Layyah 31200 Pakistan Chair of Cyber Security Department of Computer Science College of Computer and Information Sciences King Saud University Riyadh 11633 Saudi Arabia Department of Computer Science COMSATS University Islamabad Sahiwal Campus Sahiwal 57000 Pakistan School of Computing Gachon University Seongnam 13120 South Korea Faculty of Engineering Uni de Moncton Moncton E1A3E9 NB Canada School of Electrical Engineering University of Johannesburg Johannesburg 2006 South Africa International Institute of Technology and Management (IITG) Av. Grandes Ecoles Libreville BP 1989 Gabon Bridges for Academic Excellence - Spectrum Tunis Tunisia

Detection of aerial activities, including drones and birds, has practical implications for automating bird surveys and developing radar systems for aerial object collision detection. Convolutional neural networks (CNNs) have been extensively utilized for image recognition and classification tasks, albeit prior research predominantly focuses on single-class 'drone' classification. However, a gap persists in achieving high accuracy for multi-class classification. To address the limitations of traditional CNNs, such as vanishing gradients and the necessity for numerous layers, this study introduces a novel model termed "MobVGG.” This model combines the architectures of MobileNetV2 and VGG16 to accurately classify images as either 'bird' or 'drone'. The dataset comprises 4212 images for each category of 'bird' and 'drone'. The stringent methodology was applied for dataset preparation and model training to ensure the reliability of the findings. Comparative analysis with previous research demonstrates that the proposed MobVGG model, trained on both 'bird' and 'drone' images, achieves superior accuracy (96 %) compared to benchmark studies. Our paper targets researchers and graduate students as its primary audience. © 2024 The Authors

关键词： Convolutional neural networks (CNNs) Deep learning Ensemble technique MobileNetV2 VGG16

来源：评论

学校读者我要写书评

暂无评论

A Novel Mode Selection-Based Fast Intra Prediction Algorithm for Spatial SHVC

A Novel Mode Selection-Based Fast Intra Prediction Algorithm...

引用

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

作者： Dayong Wang Yu Sun Weisheng Li Lele Xie Xin Lu Frederic Dufaux Ce Zhu Chongqing Key Laboratory on Big Data for Bio Intelligence Department of Computer Science University of Central Arkansas Computing Chongqing Key Laboratory of Image Cognition School of Information and Communication Engineering Chongqing University of Posts and Telecommunications Faculty of Computing Engineering and Media (CEM) De Montfort University CNRS CentraleSupélec Laboratoire des Signaux et systèmes Université Paris-Saclay School of Information and Communication Engineering University of Electronic Science and Technology of China

Due to multi-layer encoding and Inter-layer prediction, Spatial Scalable High-Efficiency Video Coding (SSHVC) has extremely high coding complexity. It is very crucial to improve its coding speed so as to promote widespread and cost-effective SSHVC applications. In this paper, we have proposed a novel Mode Selection-Based Fast Intra Prediction algorithm for SSHVC. We reveal the RD costs of Inter-layer Reference (ILR) mode and Intra mode have a significant difference, and the RD costs of these two modes follow Gaussian distribution. Based on this observation, we propose to apply the classic Gaussian Mixture Model and Expectation Maximization in machine learning to determine whether ILR is the best mode so as to skip the Intra mode. Experimental results demonstrate that the proposed algorithm can significantly improve the coding speed with negligible coding efficiency loss.

关键词： Machine learning algorithms Costs Signal processing algorithms Machine learning Gaussian distribution Prediction algorithms Encoding

来源：评论

学校读者我要写书评

暂无评论

SkinSource: A Data-Driven Toolbox for Predicting Touch-Elicited Vibrations in the Upper Limb

SkinSource: A Data-Driven Toolbox for Predicting Touch-Elici...

引用

International Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems (HAPTICS)

作者： Neeli Tummala Gregory Reardon Simone Fani Dustin Goetz Matteo Bianchi Yon Visell the Department of Electrical and Computer Engineering University of California Santa Barbara Santa Barbara CA USA the Media Arts and Technology Program University of California Santa Barbara Santa Barbara CA USA the School of Biological and Health Systems Engineering Arizona State University Tempe AZ USA the Soft Robotics for Human Cooperation and Rehabilitation Lab Instituto Italiano di Tecnologia Geneva GE Italy the Department of Mechanical Engineering University of California Santa Barbara Santa Barbara CA USA the Department of Information Engineering University of Pisa PI Italy the Department of Biological Engineering University of California Santa Barbara Santa Barbara CA USA

Vibrations transmitted throughout the hand and arm during touch contact play a central role in haptic science and engineering but are challenging to model or experimentally characterize. Here, we present SkinSource, a data-driven toolbox for predicting skin vibrations across the upper limb in response to user-specified input forces. The toolbox leverages impulse response measurements that encode the physics of vibration transmission across the hands and arms of four participants and provides software tools for analyzing the predicted skin responses. We show that the SkinSource predictions closely match experimental measurements and confirm the underlying assumption of linear vibration transmission in the skin. We also demonstrate through several usage examples how SkinSource can act as a versatile computational platform for haptic research applications, such as characterizing vibrotactile transmission in the skin, engineering haptic interfaces, and investigating touch perception.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Collaborative Inference on Heterogeneous Edge Devices via Adaptive Ensemble Knowledge Distillation

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Wu, Shangrui Li, Yupeng Wang, Wenhua Guo, Jianxiong Fan, Wentao Liu, Qin Jia, Weijia Yu, Shui Cao, Jiannong Wang, Tian Beijing Normal-Hong Kong Baptist University Guangdong Provincial/Zhuhai Key Laboratory of IRADS Department of Computer Science Zhuhai China Hong Kong Baptist University Hong Kong Hong Kong Hong Kong Baptist University Department of Interactive Media Hong Kong Hong Kong Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi'an China Hunan University College of Computer Science and Electronic Engineering Changsha China University of Technology Sydney School of Computer Science Sydney Australia The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

The integration of edge computing with deep neural networks (DNNs) is crucial for intelligent industrial cyber-physical systems. Typically, deploying DNNs on heterogeneous edge devices relies on methods like model compression and partitioning. However, these approaches often result in homogeneous models across devices. This homogeneity limits the collective capability of edge computing systems, particularly in terms of generalization to diverse data distributions and adaptation to dynamic industrial environments. In this work, we propose to treat each DNN on an edge device as an independent model, aggregating their capabilities via ensemble learning to enhance generalization and dynamic adaptability. To realize this, we introduce the Adaptive Ensemble Knowledge Distillation Framework (AEKDF), combining cloud-based model training with edge computing based collaborative inference. In the cloud, AEKDF develops an enhanced Born Again Network that generates diverse, lightweight models tailored to specific edge devices through knowledge distillation. This process ensures model diversity which is critical to effective ensemble learning. On the edge, AEKDF employs an adaptive ensemble technique that aggregates prediction logits across devices, enabling rapid adaptation to changing environments and maintaining inference efficiency. Our extensive evaluations conducted on a realistic prototype demonstrate the substantial boost in predictive performance achieved by our AEKDF, showcasing a 4% to 10% accuracy improvement on the CIFAR-100 compared to conventional single-model approaches, while maintaining low latency. © 1983-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Teacher-student networks with multiple decoders for solving math word problem 29

Teacher-student networks with multiple decoders for solving ...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Jipeng Lee, Roy Ka-Wei Lim, Ee-Peng Qin, Wei Wang, Lei Shao, Jie Sun, Qianru Center for Future Media University of Electronic Science and Technology of China China School of Information Systems Singapore Management University Singapore Department of Computer Science University of Saskatchewan Canada School of Computer Science and Information Engineering Hefei University of Technology China Sichuan Artificial Intelligence Research Institute China

ISBN: (纸本)9780999241165

Math word problem (MWP) is challenging due to the limitation of training data where only one "standard" solution is provided. MWP models often fit the solution rather than truly understand or solve the problem. The generalization of models (to diverse word scenarios) is thus limited. To address this problem, we propose a novel approach we call TSN-MD that leverages a teacher network to integrate the knowledge of equivalent solution expressions such as to better regularize the learning behavior of the student network. In addition, we introduce the multiple-decoder student network to generate multiple candidate solution expressions by which the final answer is voted. In experiments, we conduct extensive comparisons and ablative studies on two large-scale MWP benchmarks, and show that using TSN-MD can surpass the state-of-the-art works by large margins. Intriguingly, the visualization results demonstrate that TSN-MD not only produces correct answers but also generates diverse equivalent expressions for the solution. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Person voice recognition methods 3

Person voice recognition methods

引用

3rd IEEE International Conference on Data Stream Mining and Processing, DSMP 2020

作者： Tymchenko, Oleksandr Havrysh, Bohdana Tymchenko, Oleksandr O. Khamula, Orest Kovalskyi, Bohdan Havrysh, Kateryna University of Warmia and Mazury Department of Safety Engineering Olsztyn Poland Ukrainian Academy of Printing Department of Media Technology and Graphic Publishing Lviv Ukraine Ukrainian Academy of Printing Department of Computer Science and Information Technology Lviv Ukraine IT Step University Lviv Ukraine

ISBN: (纸本)9781728132143

This article is devoted to the selection and evaluation of language features used in the tasks of automatic text-independent speaker verification. The task of automatic speaker identification is one of the most difficult tasks in the field of language processing. The methods used in current speaker identification systems are not ideal, that imposes some restrictions on such systems. Some systems work well in good acoustic conditions, with minimal noise, but noticeably lose recognition accuracy in low signal-to-noise conditions. The requirements for the accuracy of speaker identification for such systems set a certain bar, which increases every year. Improving authentication accuracy extends the scope of such systems, including biometric multi-factor authentication systems, remote banking, access control systems, and more. Thus, to meet the needs of these systems consumers, the high requirements for the speaker recognition accuracy are required. © 2020 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Prioritizing DevOps Implementation Guidelines for Sustainable Software Projects”

引用

IEEE Access 2025年 13卷 20246-20246页

作者： Muhammad Zohaib Ahmed Alsanad Areej Abdullah Alhogail Software Engineering Department Lappeenranta-Lahti University of Technology Lappeenranta Finland Department of Information Systems College of Computer and Information Sciences STCs Artificial Intelligence Chair King Saud University Riyadh Saudi Arabia

Presents corrections to the paper, (Corrections to “Prioritizing DevOps Implementation Guidelines for Sustainable Software Projects”).

关键词： DevOps Software Guidelines

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security and Scalability of Metaverse with Blockchain-based Consensus Mechanisms

Enhancing Security and Scalability of Metaverse with Blockch...

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Anand Singh Rajawat S.B. Goyal Aarti Goyal Kavita Rajawat Maria Simona Raboaca Chaman Verma Traian Candin Mihaltan School of Computer Science & Engineering Sandip University Nashik India Faculty of Information Technology City University Petaling Jaya Malaysia Mind Intellect Technology Indore India ICSI Energy Department National Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Valcea Romania Department of Media and Educational Informatics Faculty of Informatics Eötvös Loránd University Budapest Hungary Faculty of Building Services Technical University of Cluj-Napoca Cluj-Napoca Romania

This study examines how blockchain technology and consensus mechanisms can safeguard and grow the metaverse ecosystem. Blockchain is transparent and decentralized. It is unchangeable, cryptographically verified, and runs without a central authority. Blockchain technology can secure the metaverse and users' data. This study compares blockchain-based consensus algorithms such as POW(PoW), PoS, and PBFT to ensure metaverse safety. These consensus mechanisms provide safe, decentralized transaction verification, waste reduction, and network consensus. Studying blockchain technology's metaverse scaling restrictions and scaling solutions, including sharding, sidechains, and off-chain protocols. These methods increase throughput, parallel computing, and transaction speed. They improve the metaverse's eco-system. Quantitative analysis, simulations, and experiments determine the security and scalability of blockchain-based metaverse consensus processes. Changes will be quantified by measuring transaction speed, network throughput, and resource consumption. This study enables safe, scalable metaverse environments. Blockchain-based consensus mechanisms allow the metaverse to retain user data safely, halt undesirable conduct, and allow users to join without trusting each other. Scalability solutions declutter networks, enabling the metaverse to handle more individuals and transactions. Blockchain-based consensus mechanisms could make the metaverse more secure, private, and scalable. Users will trust each other, create new apps, and be more open to this groundbreaking digital world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interweaving Artificial Intelligence and Bio-Signals in Mental Fatigue: Unveiling Dynamics and Future Pathways

Interweaving Artificial Intelligence and Bio-Signals in Ment...

引用

International Conference on Wavelet Active media technology and information Processing (ICWAMTIP)

作者： Saba Parveen Md Belal Bin Heyat Faijan Akhtar Saima Parveen Barkathulla Asrafali Bandana Singh Kazim Ali Lie Huang Xiao Peng Li Ayesha Jabbar Maimoona Asad Jian Ping Li College of Electronics and Information Engineering Shenzhen University Shenzhen China CenBRAIN Neurotech Center of Excellence School of Engineering Westlake University Hangzhou Zhejiang China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Mathematics Shah Abdul Latif University Khairpur Sindh Pakistan College of Physics and Optoelectronics Engineering Shenzhen University Shenzhen China School of Media and Communication Shenzhen University Shenzhen China

This study conducts a thorough examination of machine learning models within Artificial Intelligence (AI)- integrated mental fatigue research, focusing on their identification and assessment. Investigating various biomedical signals linked to mental fatigue-such as Electroencephalogram (EEG), Electrocardiogram (ECG), and Galvanic Skin Response (GSR) this research sheds light on their roles in deciphering cognitive states and emotional responses. Through integration, these signals facilitate the creation of network visualizations, unveiling the intricate relationship between physiological markers and cognitive aspects during mental fatigue scenarios. Additionally, this study identifies gaps in current mental fatigue research with AI, emphasizing the need for an integrated approach across diverse domains and populations. It outlines future directions, suggesting avenues like multi-domain integration, personalized interventions, ethical considerations, longitudinal studies, and interdisciplinary collaborations to propel advancements in mental fatigue research, offering promising prospects for innovative AI-driven solutions in mental health and well-being.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer for Parkinson’s Disease Classification using Multilingual Sustained Vowel Recordings

Vision Transformer for Parkinson’s Disease Classification u...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Daria Hemmerling Marek Wodzinski Juan Rafael Orozco-Arroyave David Sztaho Mateusz Daniol Pawel Jemiolo Magdalena Wojcik-Pedziwiatr Daria Hemmerling Marek Wodzinski Mateusz Daniol and Pawel Jemiolo are With the AGH University of Science and Technology Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Krakow Poland Information Systems Institute University of Applied Sciences Western Switzerland (HES-SO Valais) Sierre Switzerland Universidad de Antioquia Medellin Colombia and With the Pattern Recognition Lab at the University of Erlangen Erlangen Germany Department of Telecommunications and Media Informatics Budapest University of Technology and Economics Hungary Department of Neurology Andrzej Frycz Modrzewski Krakow University Krakow Poland

Parkinson’s disease (PD) is the 2 nd most prevalent neurodegenerative disease in the world. Thus, the early detection of PD has recently been the subject of several scientific and commercial studies. In this paper, we propose a pipeline using Vision Transformer applied to mel-spectrograms for PD classification using multilingual sustained vowel recordings. Furthermore, our proposed transformed-based model shows a great potential to use voice as a single modality biomarker for automatic PD detection without language restrictions, a wide range of vowels, with an F1-score equal to 0.78. The results of our study fall within the range of the estimated prevalence of voice and speech disorders in Parkinson’s disease, which ranges from 70-90%. Our study demonstrates a high potential for adaptation in clinical decision-making, allowing for increasingly systematic and fast diagnosis of PD with the potential for use in *** relevance— There is an urgent need to develop non invasive biomarker of Parkinson’s disease effective enough to detect the onset of the disease to introduce neuroprotective treatment at the earliest stage possible and to follow the results of that intervention. Voice disorders in PD are very frequent and are expected to be utilized as an early diagnostic biomarker. The voice analysis using deep neural networks open new opportunities to assess neurodegenerative diseases’ symptoms, for fast diagnosis-making, to guide treatment initiation, and risk prediction. The detection accuracy for voice biomarkers according to our method reached close to the maximum achievable value.

关键词：

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：