检索结果-内蒙古大学图书馆

IOT based wearable sensor system architecture for classifying human activity

Measurement: Sensors 2025年 39卷

作者： Mahalakshmi, V. Kumar, Pramod Bhende, Manisha Keshta, Ismail Rathod, Swatiben Yashvantbhai Ramesh, Janjhyam Venkata Naga Department of Computer Science College of Engineering and computer science Jazan University Jazan45142 Saudi Arabia Computer science and Technology Ganga Institute of Technology and Management Kablana Haryana Jhajjar124104 India Dr. D. Y. Patil Vidyapeeth Pune India Dr. D. Y. Patil School of Science & Technology Tathawade Pune India Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Instrumentation And Control Department Vishwakrma Government Engineer College Chandkheda Ahmedabad382424 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Dist. Andhra Pradesh 522302 India

Human Activity Recognition (HAR) has applications in diverse fields, including sports management and behavior classification. Existing HAR methods can be categorized into three main approaches: camera-based, wearable sensor-based, and Wi-Fi sensing-based. Camera-based methods suffer from privacy concerns, while wearable sensor-based methods face limitations in battery longevity and continuous monitoring. Wi-Fi sensing methods mitigate privacy and battery issues but rely on costly Intel 5300 network cards or software-defined radio (SDR) platforms, limiting scalability. This paper presents a cost-effective IoT-based human activity recognition system using ESP32, leveraging its Wi-Fi sensing capabilities. The proposed system follows a structured workflow: (i) channel state information (CSI) is extracted from ESP32 modules, (ii) data preprocessing is performed using Hampel and Gaussian filters for noise and outlier removal, (iii) dimensionality reduction is achieved through Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT), and (iv) activity classification is conducted using Dynamic Time Warping (DTW) and the K-Nearest Neighbors (KNN) algorithm. Experimental evaluations demonstrate that the proposed system achieves an average recognition accuracy of 98.6 % across six human activities, comparable to high-end Intel 5300-based HAR systems, while significantly reducing hardware costs and improving ease of deployment. © 2025

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Ante-Hoc Generation of Task-Agnostic Interpretation Maps

Ante-Hoc Generation of Task-Agnostic Interpretation Maps

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Akash Guna R T Raul Benitez Sikha O K Department of Computer Science and Engineering Amrita School of Engineering Coimbatore India Departament of Automatic Control Universitat Politècnica de Catalunya-BarcelonaTech Spain

Existing explainability approaches for convolutional neural networks (CNNs) are mainly applied after training (post-hoc) which is generally unreliable. Ante-hoc explainers trained simultaneously with the CNN are more reliable. However, current ante-hoc explanation methods mainly generate inexplicit concept-based explanations tailored to specific tasks. To address these limitations, we propose a task-agnostic ante-hoc framework that can generate interpretation maps to visually explain any CNN. Our framework simultaneously trains the CNN and a weighting network - an explanation generation module. The generated maps are self-explanatory, eliminating the need for manual identification of concepts. We demonstrate that our method can interpret classification, facial landmark detection, and image captioning tasks. We show that our framework is explicit, faithful, and stable through experiments. To the best of our knowledge, this is the first ante-hoc CNN explanation strategy that produces visual explanations generic to CNNs for different tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Convex Potential Games for Finding Global Solutions to Sensor Network Localization

Non-Convex Potential Games for Finding Global Solutions to S...

引用

European control Conference (ECC)

作者： Gehui Xu Guanpu Chen Yiguang Hong Baris Fidan Thomas Parisini Karl H. Johansson Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Control Science and Engineering Tongji University Shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai China Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo ON Canada Department of Electrical and Electronic Engineering Imperial College London London UK Department of Engineering and Architecture University of Trieste Trieste Italy

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results.

关键词： Location awareness Coordinate measuring machines Simulation Current measurement Noise Europe Games

来源：评论

学校读者我要写书评

暂无评论

Teeth Segmentation from Bite-Wing X-Ray Images by Integrating Nested Dual UNet with Swin Transformers

Teeth Segmentation from Bite-Wing X-Ray Images by Integratin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Yubo Tian, Yibin Zhang, Zhiyuan Zhang, Xueyang Du, Bingran Zeng, Zhi School of Computer and Information Science Chongqing Normal University Chongqing401331 China College of Mechatronics and Control Engineering Shenzhen University Shenzhen518060 China Litemaze Technology Shenzhen518000 China School of Computing and Information Systems Singapore Management University Singapore487372 Singapore Shunde Hospital Department of Stomatology Foshan528000 China

ISBN: (纸本)9781665410205

In medical practice, the precision of image segmentation is crucial for diagnosis and treatment evaluations. Specifically, in dentistry, accurate teeth segmentation from bite-wing images is important for automatic and objective evaluations of root canal treatments. This study introduces Swin-U2 Net, a model merging the nested dual UNet with residual U-block and Swin Transformers. It combines the local feature extraction capability of the former and the global attention and context understanding of the latter. It has been evaluated for tooth root segmentation using 500 bite-wing dental x-ray images obtained from a root canal treatment clinic. It achieved the best segmentation outcome in terms of Intersection over Union (IOU) and the third best result in terms of Dice Similarity Coefficient (DSC) with the second least amount of network parameters among six UNet-like models, thus it is effective and efficient. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Poisson Process for Bayesian Optimization

arXiv

引用

arXiv 2024年

作者： Wang, Xiaoxing Li, Jiaxing Xue, Chao Liu, Wei Liu, Weifeng Yang, Xiaokang Yan, Junchi Tao, Dacheng Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China College of Control Science and Engineering China University of Petroleum China JD Explore Academy The University of Sydney Australia

Bayesian Optimization (BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP). However, few methods have been explored to estimate the relative rankings of candidates, which can be more robust to noise and have better practicality than absolute function responses, especially when the function responses are intractable but preferences can be acquired. To this end, we propose a novel ranking-based surrogate model based on the Poisson process and introduce an efficient BO framework, namely Poisson Process Bayesian Optimization (PoPBO). Two tailored acquisition functions are further derived from classic LCB and EI to accommodate it. Compared to the classic GP-BO method, our PoPBO has lower computation costs and better robustness to noise, which is verified by abundant experiments. The results on both simulated and real-world benchmarks, including hyperparameter optimization (HPO) and neural architecture search (NAS), show the effectiveness of PoPBO. Copyright © 2024, The Authors. All rights reserved.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

DialogNTM: Context Reconstruction in Multi-Turn Dialogue Generation using Neural Turing Machines

DialogNTM: Context Reconstruction in Multi-Turn Dialogue Gen...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Haohao Zhao Meiling Liu Jiyun Zhou Kaiquan Fu College of Computer and Control Engineering Northeast Forestry University Harbin China Lieber Institute Johns Hopkins University Baltimore USA Department of Electrical Engineering and Computer Science South Dakota State University Brookings South Dakota USA

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In actual conversational scenarios, we can often determine which parts of the previous dialogue are more critical based on the current inquiry. However, the existing contextual modeling methods often encode the query sentence and the dialogue history in a unified manner, which fails to effectively highlight the inference effect of the query sentence. Moreover, these methods typically process the dialogue history only at the information extraction level, neglecting the treatment of the context itself. In this paper, we propose a novel conversational context modeling technique called DialogNTM. Based on the guidance of the query sentence, the technology can effectively eliminate redundant information by reconstructing the representation of the context. Specifically, we have tweaked the memory and input flow of the Neural Turing Machine (NTM) to encode contextual information in memory and guide the read, write, and erase operations of memory through query sentence. This design simulates the human brain's dynamic retrieval and renewal mechanism of previous memories when dealing with current problems. We have conducted extensive experiments on three publicly available datasets to verify the effectiveness of the DialogNTM model. Compared to the benchmark model, DialogNTM showed significant performance improvements ranging from 11% to 73% across multiple automated evaluation metrics (3.52% to 8.68% in absolute terms).

关键词： Adaptation models Turing machines Text summarization Benchmark testing Brain modeling Information retrieval Distance measurement History Cybernetics Context modeling

来源：评论

学校读者我要写书评

暂无评论

Delayed dynamic-feedback controller design for multi-frequency vibration suppression

引用

IFAC-PapersOnLine 2024年第27期58卷 196-201页

作者： Adrian Saldanha Adam Peichl Wim Michiels Tomas Vyhlidal Department of Computer Science KU Leuven Celestijnenlaan 200A 3001 Leuven Belgium Dept. Instrumentation and Control Engineering Faculty of Mechanical Engineering and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6 Czechia

We present a methodology for designing a dynamic controller with delayed output feedback for achieving non-collocated vibration suppression with a focus on the multi-frequency case. To synthesize the delay-based controller, we first remodel the system of equations as a delay-differential algebraic equation (DDAE) in such a way that existing tools for design of a static output feedback controller can be easily adapted. The problem of achieving non-collocated vibration suppression with sufficient damping is formulated as a constrained optimization problem of minimizing the spectral abscissa in the presence of zero-location constraints, with the constraints exhibiting polynomial dependence on its parameters. We transform the problem into an unconstrained one using elimination, following which we solve the resulting non-convex, non-smooth optimization problem.

关键词： vibration suppression time-delay DDAE

来源：评论

学校读者我要写书评

暂无评论

Cooperative Reinforcement Learning for Military Drones over Large-Scale Battlefields

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年

作者： Kim, Gyu Seon Lee, Sungjoon Woo, Taejin Park, Soohyun Department of Electrical and Computer Engineering Korea University Seoul Korea Republic of LIG Nex1 Ground Control System Team 3 Korea Republic of Division of Computer Science Sookmyung Women’s University Seoul Korea Republic of

The development of autonomous systems in military drone operations signifies a paradigm shift in modern warfare strategies, and modern warfare emphasizes the crucial role of military drones to the extent that it is called drone war. Despite the importance of these military drones, the efficiency of such operations hinges on the swarm military drones’ ability to operate cooperatively in complex battlefield environments where the target changes dynamically. The proposed algorithm for robust and reliable military drones needs to consider a total of three objectives, i.e., (i) cooperative swarm flight maintenance, (ii) target bombing zone maximization, and (iii) energy efficiency optimization. For this objective, multi-agent deep reinforcement learning (MARL) is utilized for the cooperation of military drones to achieve these objectives optimally. Lastly, this paper considers ‘Shahed-136’ which is one of well-known military drones for realistic battlefield evaluation. Additionally, the military drones employing the proposed algorithm are evaluated in a large-scale battlefield environment spanning 4×104 km3. This paper assesses the efficacy of the proposed approach through simulations that evaluate the swarm flight, success rate of bombing, and energy efficiency of drones, particularly under dynamic target conditions. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Detection of Intracranial Hematoma Using Window-Based Stacking and YOLOv5 Framework 2

An Efficient Detection of Intracranial Hematoma Using Window...

引用

2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2023

作者： Vidhya, V. Gudigar, Anjan Raghavendra, U. Basak, Sudipta Mallappa, Sankalp Hegde, Ajay Menon, Girish Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal576104 India Manipal Institute of Technology Manipal Academy of Higher Education Instrumentation and Control Engineering Manipal576104 India Department of Neurosurgery Manipal Hospitals Karnataka India Department of Neurosurgery Manipal Academy of Higher Education Kasturba Medical College Manipal576104 India

ISBN: (纸本)9798350306811

Traumatic brain injury (TBI) is a burgeoning medical disorder across the world particularly among young adults and children. TBI can cause intracranial hematoma (ICH), a lethal condition which requires prompt and accurate interpretation of computed tomography (CT) images for timely diagnosis and treatment. Since manual detection of CT images is a tedious and operator-dependent task, a deep learning framework is proposed for locating and categorizing ICH for improved diagnostic performance. Firstly, the input images are processed by using various techniques such as local directional pattern, local binary pattern, and windowing. Then the single stage YOLOv5 object detection model with faster spatial pyramid pooling is applied to detect hematoma regions of various types in the brain. The proposed model using windowing approach realized an overall mAP of 0.969, precision of 0.945 and recall of 0.943. The experimental results from the research study demonstrated that the suggested framework can help radiologists in strategic decision-making and improve quality care to the patients. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptively Feature Extracting Network for Cervical Squamous Lesion Cell Detection 4th

Deep Adaptively Feature Extracting Network for Cervical Squ...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Peng, Zhonghua Hu, Rong Wang, Fuen Fan, Haoyi Eng, Yee Wei Li, Zuoyong Zhou, Liwei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China Department of Nutrition The First Affiliated Hospital of Zhengzhou University Henan Zhengzhou450052 China

ISBN: (纸本)9783031200984

Cervical cancer is one of the most widespread malignancies affecting women’s health worldwide today. However, the task of detection is particularly difficult due to the complex background of the cervical smear, where cells are previously stacked in clusters. To address this problem, we utilize the YOLOv5 as the baseline and build on YOLOv5 by using the simple Transformer Block which only combines with multi-head self attention layers and MLP to better extract cell features as well as to obtain global information. In addition, we allow the model to refine features adaptively to assist with detection by using Convolutional Block Attention Module (CBAM), an attention module being simple and effective for feed-forward convolutional neural networks, in the complex background information. Finally, we compare the model with YOLOv5 as baseline. In CDetector dataset, our model obtains 52.5% mAP@.5, which is 6% better than baseline. In transfer learning, it is 62.2%, which outperforms baseline by 3.2%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cells

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：