检索结果-内蒙古大学图书馆

CSI-Based Human Activity Recognition using Convolutional Neural Networks 11

学校读者我要写书评

暂无评论

CSI-Based Human Activity Recognition using Convolutional Neu...

11th International Conference on computer Engineering and Knowledge, ICCKE 2021

作者： Moshiri, Parisa Fard Nabati, Mohammad Shahbazian, Reza Ghorashi, Seyed Ali Shahid Beheshti University G. C. Cognitive Telecommunication Research Group Department of Electrical Engineering Tehran Iran Standard Research Institute Faculty of Technology and Engineering Department of Electrical Engineering Alborz31745-139 Iran University of East London School of Architecture Computing and Engineering Department of Computer Science and Digital Technologies London United Kingdom

ISBN: (纸本)9781665402088

Human activity recognition (HAR) as an emerging technology can have undeniable impacts on several applications such as health monitoring, context-aware systems, transportation, robotics, and smart cities. Among the main research methods in HAR (sensor, image, and WiFi-based), the WiFi-based method has attracted considerable attention due to the ubiquity of WiFi devices. WiFi devices can be utilized to distinguish daily activities such as "walk", "run", and "sleep". These activities affect WiFi signal propagation and can be further used to recognize activities. This paper proposes a Deep Learning method for HAR tasks using channel state information (CSI). A new model is developed in which CSI data are converted to grayscale images. These images are then fed into a 2D-Convolutional Neural Network (CNN) for activity classification. We take advantage of CNN's high accuracy on image classification along with WiFi-based ubiquity. The experimental results demonstrate that our proposed approach achieves acceptable performance in HAR tasks. © 2021 IEEE.

关键词： Channel state information

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan Innovation Technology Office Research Center PASCO Corporation Tokyo Japan

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

INSTANCE SEGMENTATION AND TEETH CLASSIFICATION IN PANORAMIC X-RAYS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Budagam, Devichand Ghosh, Sayan Imanbayev, Azamat Zhanatuly Kaplun, Dmitrii Rychenkov, Artem Sinitca, Aleksandr Kumar, Ayush Shrivastav, Anuj Akhmetov, Iskander Rafailovich Antonov, Sergey Cyganov, Gleb Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Department of Chemical Engineering Indian Institute of Technology Kharagpur Kharagpur India School of IT and Engineering Kazakh-British Technical University Almaty Kazakhstan Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes St. Petersburg Electrotechnical University"LETI" St. Petersburg Russia Centre for Digital Telecommunication Technologies St. Petersburg Electrotechnical University"LETI" St. Petersburg Russia Department of Humanities and Social Sciences Indian Institute of Technology Kharagpur Kharagpur India Department of Architecture and Regional Planning Indian Institute of Technology Kharagpur Kharagpur India Faculty of Digital Transformation ITMO University St. Petersburg Russia

Teeth segmentation and recognition are critical in various dental applications and dental diagnosis. Automatic and accurate segmentation approaches have been made possible by integrating deep learning models. Although teeth segmentation has been studied in the past, only some techniques were able to effectively classify and segment teeth simultaneously. This article offers a pipeline of two deep learning models, U-Net and YOLOv8, which results in BB-UNet, a new architecture for the classification and segmentation of teeth on panoramic X-rays that is efficient and reliable. We have improved the quality and reliability of teeth segmentation by utilising the YOLOv8 and U-Net capabilities. The proposed networks have been evaluated using the mean average precision (mAP) and dice coefficient for YOLOv8 and BB-UNet, respectively. We have achieved a 3% increase in mAP score for teeth classification compared to existing methods, and a 10-15% increase in dice coefficient for teeth segmentation compared to U-Net across different categories of teeth. A new Dental dataset was created based on UFBA-UESC dataset with Bounding-Box and Polygon annotations of 425 dental panoramic X-rays. The findings of this research pave the way for a wider adoption of object detection models in the field of dental diagnosis. © 2024, CC BY.

关键词： Object detection

Energy-aware load balancing of parallel evolutionary algorithms with heavy fitness functions in heterogeneous CPU-GPU architectures

学校读者我要写书评

暂无评论

Energy-aware load balancing of parallel evolutionary algorit...

作者： Escobar, Juan José Ortega, Julio Díaz, Antonio Francisco González, Jesús Damas, Miguel Department of Computer Architecture and Technology CITIC University of Granada Spain

By means of the availability of mechanisms such as Dynamic Voltage and Frequency Scaling (DVFS) and heterogeneous architectures including processors with different power consumption profiles, it is possible to devise scheduling algorithms that are aware of both runtime and energy consumption in parallel programs. In this paper, we propose and evaluate a multi-objective (more specifically, a bi-objective) approach to distribute the workload among the processing cores in a given heterogeneous parallel CPU-GPU architecture. The aim of this distribution may be either to save energy without increasing the running time or to reach a trade-off among time and energy consumption. The parallel programs considered here are master-worker evolutionary algorithms where the evaluation of the fitness function for the individuals in the population demands the most part of the computing time. As many useful bioinformatics and data mining applications exhibit this kind of parallel profile, the proposed energy-aware approach for workload scheduling could be frequently applied. © 2018 John Wiley & Sons, Ltd.

关键词： Energy utilization

Higher education assessment practice in the era of generative AI tools

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ogunleye, Bayode Zakariyyah, Kudirat Ibilola Ajao, Oluwaseun Sharma, Hemlata Olayinka, Olakunle School of Architecture Technology & Engineering University of Brighton BrightonBN2 4GJ United Kingdom Department of Computing & Mathematics Manchester Metropolitan University ManchesterM1 5GD United Kingdom Department of Computer Science University of Sheffield SheffieldS1 4DP United Kingdom Department of Computing Sheffield Hallam University SheffieldS1 2NU United Kingdom

The higher education (HE) sector benefits every nation’s economy and society at large. However, their contributions are challenged by advanced technologies like generative artificial intelligence (GenAI) tools. In this paper, we provide a comprehensive assessment of GenAI tools towards assessment and pedagogic practice and, subsequently, discuss the potential impacts. This study experimented using three assessment instruments from data science, data analytics, and construction management disciplines. Our findings are two-fold: first, the findings revealed that GenAI tools exhibit subject knowledge, problem-solving, analytical, critical thinking, and presentation skills and thus can limit learning when used unethically. Secondly, the design of the assessment of certain disciplines revealed the limitations of the GenAI tools. Based on our findings, we made recommendations on how AI tools can be utilised for teaching and learning in HE. © 2024, CC BY.

关键词： Project management

Unsupervised Deep Learning Approaches for Anomaly Detection in IoT Data Streams

学校读者我要写书评

暂无评论

Unsupervised Deep Learning Approaches for Anomaly Detection ...

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Helina Rajini Suresh R. Neelaveni Bonda Kiran Kumar R. Arunadevi Indhumathi G M Varun Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of CSE SRM institute of science and technology Chennai Tamilnadu India KL School of Architecture KL Deemed to be University Andhrapradesh India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamilnadu India Department of ECE Rajalakshmi Engineering College Chennai Tamilnadu India Department of ECE Saveetha Engineering College Chennai Tamilnadu India

The proliferation of IoT devices is primarily responsible for the data deluge that has engulfed multiple industries. Nevertheless, due to the high dimensionality and complexity of IoT data streams, anomaly detection remains a significant challenge. This suggests that an unsupervised deep learning strategy could be used to identify anomalies in IoT data streams. Instead of relying on labeled data, this method employs deep neural networks, which can be trained to recognize anomalies and comprehend complex patterns. Experiments are conducted on a real-world IoT dataset to evaluate the efficacy and accuracy of the proposed method. The results demonstrate its proficiency in detecting anomalies in IoT data streams, paving the way for a safer, more reliable Internet of Things. Using unsupervised deep learning techniques, the method provides a practicable solution to the age-old problem of IoT anomaly identification.

关键词：

Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sohail, Shahab Saquib Himeur, Yassine Kheddar, Hamza Amira, Abbes Fadli, Fodil Atalla, Shadi Copiaco, Abigail Mansoor, Wathiq School of Computing Science and Engineering VIT Bhopal University MP Sehore466114 India College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates LSEA Laboratory Department of Electrical Engineering University of Medea 26000 Algeria Department of Computer Science University of Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between training data and test data, and the requirement for high computational resources. To that end, deep transfer learning (DTL), which decreases dependency and costs by utilizing knowledge gained from a source data/task in training a target data/task, has been widely investigated. Numerous DTL frameworks have been suggested for aligning point clouds obtained from several scans of the same scene. Additionally, DA, which is a subset of DTL, has been modified to enhance the point cloud data’s quality by dealing with noise and missing points. Ultimately, fine-tuning and DA approaches have demonstrated their effectiveness in addressing the distinct difficulties inherent in point cloud data. This paper presents the first review shedding light on this aspect. it provides a comprehensive overview of the latest techniques for understanding 3DPC using DTL and domain adaptation (DA). Accordingly, DTL’s background is first presented along with the datasets and evaluation metrics. A well-defined taxonomy is introduced, and detailed comparisons are presented, considering different aspects such as different knowledge transfer strategies, and performance. The paper covers various applications, such as 3DPC object detection, semantic labeling, segmentation, classification, registration, downsampling/upsampling, and denoising. Furthermore, the article discusses the advantages and limitations of the presented frameworks, identifies open challenges, and suggests potential research directions. © 2024, CC BY.

关键词： Object detection

Correction: Data Integration Method of Multi-source Feedback Evaluation for Remote Teaching Quality

学校读者我要写书评

暂无评论

Mobile Networks and Applications 2023年第3期28卷 935-935页

作者： Chen, Lili Baza, Mohamed Alshahrani, Hani Development and Planning Office Jilin University of Architecture and Technology Changhun China Department of Computer Science College of Charleston Charleston USA Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia

EPRD: Exploiting prior knowledge for evidence-providing automatic rumor detection

学校读者我要写书评

暂无评论

Neurocomputing 2024年 563卷

作者： Li, Jiawen Li, Ronghui Ni, Shiwen Kao, Hung-Yu Naval Architecture and Shipping College Guangdong Ocean University Guangdong Zhanjiang524000 China Technical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province Guangdong Zhanjiang524000 China Intelligent Knowledge Management Lab National Cheng Kung University Tainan Taiwan Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

With the prevalence of social media platforms, rumors have been a serious social problem. Notably, existing rumor detection methods simply provide detection labels while ignoring their explanation. However, illustrating the reasons why a suspicious statement is a rumor is essential. To address this realistic scenario, we propose a novel Evidence-Providing Rumor Detection model called EPRD. EPRD incorporates a wide variety of information from both prior knowledge sources and current comments. It also learns bilaterally friendly representations for interpretable rumor detection. EPRD first retrieves evidence from prior knowledge sources and checks the relationship between the given statement and its evidence. Our model then constructs two heterogeneous graph objects to simulate the propagation layout of the current comments and evidence relationships. Finally, EPRD integrates the GraphSAGE component and attention mechanism to detect rumors. To the best of our knowledge, we propose the first model that incorporates prior knowledge to verify rumors and boost credibility. Experiments on two real-world Twitter datasets demonstrate that EPRD consistently exhibits the best rumor detection performance. Moreover, EPRD outperforms other baselines in the early rumor detection task. © 2023

关键词： Graph neural networks