检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Xiaofeng Mao Yucheng Xu Ruoshi Wen Mohammadreza Kasaei Wanming Yu Efi Psomopoulou Nathan F. Lepora Zhibin Li School of Informatics University of Edinburgh UK Touchlab Limited Edinburgh U.K. Oxford Robotics Institute University of Oxford UK Department of Engineering Mathematics University of Bristol UK Department of Computer Science University College London UK

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Imitation learning for robot dexterous manipulation, especially with a real robot setup, typically requires a large number of demonstrations. In this paper, we present a data-efficient learning from demonstration framework which exploits the use of rich tactile sensing data and achieves fine bimanual pinch grasping. Specifically, we employ a convolutional autoencoder network that can effectively extract and encode high-dimensional tactile information. Further, we develop a framework that achieves efficient multi-sensor fusion for imitation learning, allowing the robot to learn contact-aware sensorimotor skills from demonstrations. The ablation studies on encoded tactile features highlighted the effectiveness of incorporating rich contact information, which enabled dexterous bimanual grasping with active contact searching. Extensive experiments demonstrated the robustness of the fine pinch grasp policy directly learned from few-shot demonstration, including grasping of the same object with different initial poses, generalizing to ten unseen new objects, robust and firm grasping against external pushes, as well as contact-aware and reactive re-grasping in case of dropping objects under very large perturbations. Furthermore, the saliency map analysis method is used to describe weight distribution across various modalities during pinch grasping, confirming the effectiveness of our framework at leveraging multimodal information. The video is available online at: https://***/BlzxGgiKfck.

关键词： Imitation learning Perturbation methods Autoencoders Grasping Robot sensing systems Feature extraction Robustness Sensors Data mining Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Stride Based Convolutional Neural Network for Speech Emotion Recognition 7

Stride Based Convolutional Neural Network for Speech Emotion...

引用

7th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2021

作者： Wani, Taiba Majid Gunawan, Teddy Surya Qadri, Syed Asif Ahmad Mansor, Hasmah Arifin, Fatchul Ahmad, Yasser Asrul International Islamic University Malaysia Electrical and Computer Engineering Dept Kuala Lumpur53100 Malaysia Universitas Negeri Yogyakarta Electronics and Informatics Eng. Dept Yogyakarta55281 Indonesia

ISBN: (纸本)9781728175225

Speech Emotion Recognition (SER) recognizes the emotional features of speech signals regardless of semantic content. Deep Learning techniques have proven superior to conventional techniques for emotion recognition due to advantages such as speed and scalability and infinitely versatile operation. However, since emotions are subjective, there is no universal agreement on evaluating or categorizing them. The main objective of this paper is to design a suitable model of Convolutional Neural Network (CNN) - Stride-based Convolutional Neural Network (SCNN) by taking a smaller number of convolutional layers and eliminate the pooling-layers to increase computational stability. This elimination tends to increase the accuracy and decrease the computational time of the SER system. Instead of pooling layers, deep strides have been used for the necessary dimension reduction. SCNN is trained on spectrograms generated from the speech signals of two different databases, Berlin (Emo-DB) and IITKGP-SEHSC. Four emotions, angry, happy, neutral, and sad, have been considered for the evaluation process, and a validation accuracy of 90.67% and 91.33% is achieved for Emo-DB and IITKGPSEHSC, respectively. This study provides new benchmarks for both datasets, demonstrating the feasibility and relevance of the presented SER technique. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Convolution Neural Network Based Research on Recognition of Mine Vehicle Head and Tail 17th

Deep Convolution Neural Network Based Research on Recognitio...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Li, Junqiang Wang, Chao Cui, Lin Zhang, Zhiwei Tian, Wenquan Pan, Zhenggao Zhang, Wanli Yang, Xiaoying Chen, Guolong School of Informatics and Engineering Suzhou University Suzhou234000 China Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai201804 China School of Computer Science and Information Engineering Bengbu University Bengbu233000 China

ISBN: (纸本)9783030845216

The mine environmental monitoring system captures the photos of the head and the tail of the vehicle, and sometimes the system can not accurately distinct whether it is the head or the tail of the vehicle. When there are two trucks in the view of the surveillance camera, the captured image contains the head of one truck and the tail of another truck. What needs to be recognized is the head license plate number or the tail license plate number. However, because the system cannot distinguish the head and tail of the truck, it will cause more false alarms. In order to solve this problem, this paper proposes an end-to-end feature extraction and recognition model based on deep convolution neural network (Deep CNN). The Deep CNN model contains five stage CNN layer and each layer contains different kernel size to extract the features. The data set is provided by Huaibei Siyuan Technology Co., Ltd., which includes normal capture, escape and false alarm images of the trucks. The final prediction rate is 85% on the testing set, which occupied twenty percent of the whole image set. The prediction rate of our model has been higher than the prediction rate base on right-out-left-in principle, which is used in the mine environmental monitoring system. Finally, our model will be applied in the mine environmental monitoring system. © 2021, Springer Nature Switzerland AG.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Secure Outsourcing Data Integrity Auditing for Internet of Things in Cloud-edge Environment

Blockchain-based Secure Outsourcing Data Integrity Auditing ...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Yangfei Lin Celimuge Wu Yusheng Ji Jie Li Zhi Liu Graduate School of Informatics and Engineering The University of Electro-Communications Chofu-shi Tokyo Japan Information Systems Architecture Research Division National Institute of Informatics Tokyo Japan Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Internet of Things enables devices to communicate, collect and exchange data with the network. As the number of IoT devices keeps growing, the volume of data they produce is also increasing exponentially. Given the feature of limited computing and storage resources of IoT, it is inevitable to store data in the cloud for better services. However, for users to effectively and efficiently inspect those data over the cloud is a critical and open problem. Most public integrity auditing over the cloud schemes requires the user to do a sheer amount of preprocessing work on the local devices, which is unsuitable for IoT devices. With the development of edge computing extending cloud computing, it can provide computing capability for resource-constrained devices in close geographic proximity. In this paper, we design an auditing scheme based on secure computation outsourcing assisted by edge computing, in which the data preprocessing work can be offloaded to the edge server. The experiments show that it reduces the computing load on the devices and improves the efficiency of task processing.

关键词： Cloud computing Data privacy Data integrity Outsourcing Sensors Performance analysis Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Secrecy Analysis and Optimization of UAV-Assisted Communications With Hybrid SWIPT and Cooperative Jamming

IEEE Journal on Miniaturization for Air and Space Systems

引用

IEEE Journal on Miniaturization for Air and Space Systems 2025年

作者： Pandey, Gaurav K. Gurjar, Devendra S. Yadav, Suneel Solanki, Sourabh Gazda, Juraj Chatzinotas, Symeon National Institute of Technology Silchar Department of Electronics and Communication Engineering Assam Cachar788010 India Indian Institute of Information Technology Allahabad Department of Electronics and Communication Engineering Uttar Pradesh Prayagraj211015 India National Institute of Technology Department of Electronics and Communication Engineering Warangal India Technical University of Košice Department of Computer and Informatics Košice04200 Slovakia University of Luxembourg SnT Luxembourg City1855 Luxembourg

Unmanned aerial vehicles (UAVs) have emerged as a state-of-the-art solution for establishing communication in remote and obstructed areas. However, before UAVs can be integrated into existing communication infrastructure, it is essential to address the energy constraints and security concerns arising from their line-of-sight links. This paper focuses on a UAV-enabled communication system in which a UAV relay facilitates information transfer from the source to the destination nodes when the direct link is heavily shadowed or obstructed. A nearby terrestrial passive eavesdropper can intercept information transmitted through the source-to-UAV and UAV-to-destination links. To address this, we utilize destination-aided cooperative jamming. Additionally, we consider simultaneous wireless information and power transfer (SWIPT) at the UAV to provide the energy required for data transmission. In particular, the UAV utilizes a hybrid-SWIPT technique to harvest energy from the radio-frequency signals. For this setup, we derive accurate expressions of secrecy outage probability and system secrecy throughput (SST) over Beaulieu-Xie distributed channels. Using the SST expression, we formulate an SST maximization problem to jointly optimize the transmit powers, power allocation, SWIPT coefficients, and UAV’s three-dimensional position. The formulated problem is solved using the hybrid heuristic framework, combining continuous genetic and particle swarm optimization algorithms. Numerical results demonstrate the significant enhancement in information secrecy of the system with the proposed hybrid scheme and also provide valuable insights into the system’s behavior. © 2019 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

ETHACA - A Container-Based Cyber Range for Research and Education

ETHACA - A Container-Based Cyber Range for Research and Educ...

引用

IEEE International Workshop on computer-Aided Modeling, Analysis, and Design of Communication Links and Networks, CAMAD

作者： Nestoras Chouliaras Ioanna Kantzavelou Grammati Pantziou Leandros Maglaras Panagiota Chouliara-Sidera Antonis Adamakos Panagiotis Chalatsakos Department of Informatics and Computer Engineering University of West Attica Athens Greece School of Computing Edinburgh Napier University Edinburgh UK Department of Computer Science and Biomedical Infromatics University of Thessaly Lamia Greece Senior Software Engineer at *** Athens Greece Faculty of Pure and Applied Sciences Open University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350377644

ISBN: (纸本)9798350377651

The advent of Industry 4.0 and the Industrial Internet of Things (IIoT) has revolutionized manufacturing and production systems, enhancing efficiency and communication through the integration of advanced technologies such as IoT devices and AI. However, this increased digitization has also led to heightened cybersecurity risks, with a notable rise in the frequency and complexity of cyber-attacks. Cyber Ranges emerges as a critical solution in addressing these challenges, offering a controlled environment for simulating cyber-attack scenarios, training cybersecurity teams, and developing robust defense strategies. The escalating demand for cybersecurity professionals has highlighted the crucial need for effective training solutions. This article presents an open-source Cyber Range constructed on container-based architecture, meticulously engineered for efficient operation with minimal resource consumption. In response to the scarcity of cybersecurity experts, this platform prioritizes extensive scalability and robust isolation between exercises, ensuring secure learning environments, and also integrates a complex developed exercise series aimed at strengthening cybersecurity learning experiences. These exercises encompass a variety of scenarios and challenges, catering to professionals at different skill levels. Each exercise replicates real-world cyber threats, offering practical, hands-on learning opportunities. Additionally, a comprehensive questionnaire accompanies these exercises, designed to gather feedback on participants' experiences.

关键词： Training Production systems Scalability Conferences Computational modeling computer architecture Fourth Industrial Revolution Complexity theory Cyberattack Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

PheME: A deep ensemble framework for improving phenotype prediction from multi-modal data

PheME: A deep ensemble framework for improving phenotype pre...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Shenghan Zhang Haoxuan Li Ruixiang Tang Sirui Ding Laila Rasmy Degui Zhi Na Zou Xia Hu Department of Computer Science Xi’an Jiaotong-Liverpool University Xi’An China Department of Computer Science Wuhan University Wuhan China Department of Computer Science Rice University Houston USA Department of Computer Science and Engineering Texas A&M University College Station USA UTHealth Houston School of Biomedical Informatics Houston USA Department of Engineering Technology & Industrial Distribution Texas A&M Univerisity College Station USA

Detailed phenotype information is fundamental to accurate diagnosis and risk estimation of diseases. As a rich source of phenotype information, electronic health records (EHRs) promise to empower diagnostic variant interpretation. However, how to accurately and efficiently extract phenotypes from the heterogeneous EHR data remains a challenge. In this work, we present PheME, an Ensemble framework using Multi-modality data of structured EHRs and unstructured clinical notes for accurate Phenotype prediction. Firstly, we employ multiple deep neural networks to learn reliable representations from the sparse structured EHR data and redundant clinical notes. A multi-modal model then aligns multi-modal features onto the same latent space to predict phenotypes. Secondly, we leverage ensemble learning to combine outputs from single-modal models and multi-modal models to improve phenotype predictions. We chose seven diseases to evaluate the phenotyping performance of the proposed framework. Experimental results show that using multi-modal data significantly improves phenotype prediction in all diseases, the proposed ensemble learning framework can further boost the performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic melanoma detection using discrete cosine transform features and metadata on dermoscopic images

引用

Journal of King Saud University - computer and Information Sciences 2024年第2期36卷

作者： Yousefi, Shamim Najjar-Ghabel, Samad Danehchin, Ramin Band, Shahab S. Hsu, Chung-Chian Mosavi, Amir Department of Computer Engineering University of Mohaghegh Ardabili Ardabil Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

Machine learning contributes in improving the accuracy of melanoma detection. There are extensive studies in classic and deep learning-based approaches for melanoma detection in the literature. Still, they are not accurate or require high learning data. This paper proposes a hybrid mechanism for automated melanoma detection on dermoscopic images based on Discrete Cosine Transform features and metadata. It is composed of three steps. First, extra information/artifacts are deleted;the remaining pixels are standardized for accurate processing. Second, the reliability of the mechanism is improved by the Radon transform, extra data is removed using the Top-hat filter, and the detection rate is increased by Discrete Wavelet Transform and Discrete Cosine Transform. Then, the number of features is reduced by Locality Sensitive Discriminant Analysis. The third step divides the images into learning and test ones to create image-based models using learning data. Finally, the best model is selected based on test data and improved by a metadata-based model. Simulation results show that the decision tree provides the most practical image-based model by improving accuracy and sensitivity. Besides, the comparison results demonstrate that our model improves the F-Value to detect melanoma superior to other approaches. © 2024 The Author(s)

关键词： Artificial intelligence Big data Data science Dermoscopic image Discrete cosine transform features Machine learning Melanoma detection Metadata

来源：评论

学校读者我要写书评

暂无评论

A Development of Object Detection System based on Deep Learning Approach to Support the Laparoscope Manipulating Robot (LMR)

A Development of Object Detection System based on Deep Learn...

引用

2022 International Electrical engineering Congress, iEECON 2022

作者： Sonsilphong, Suphachoke Sonsilphong, Amornthep Hormdee, Daranee Khampitak, Kovit Khon Kaen University Data Science Health Informatics Program Academic Affairs Faculty of Medicine Khon Kaen Thailand Rajamangala University of Technology Isan Department of Electrical Engineering Khon Kean Thailand Khon Kaen University Embedded System RD Group Department of Computer Engineering Faculty of Engineering Khon Kean Thailand Khon Kean University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kean Thailand

ISBN: (纸本)9781665402064

This paper presents the development of an object detection system based on the deep learning approach of computer vision to support the laparoscopic surgical robotic position control system. The system comprises two main phases, the training phase, and the real-time operating phase. In the training phase, a modified YOLOv4 algorithm is proposed to be adopted within the Darknet framework for training the weights of detection models. The best detection model is then selected to be assigned to the object detector in the real-time operating phase. The validation result of the detection model across the experiment datasets is 90% accuracy on average during the training phase. To validate the viability of real-time object detection, the proposed system was implemented in two test-cases of gynecologic surgery with the soft-body cadavers. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

Real-Time Outdoor Air Quality Monitoring System 7

Real-Time Outdoor Air Quality Monitoring System

引用

7th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2021

作者： Abiduzzaman, S.M. Mansor, Hasmah Gunawan, Teddy Surya Ahmad, Robiah International Islamic University Malaysia Electrical and Computer Engineering Department Kuala Lumpur53100 Malaysia Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Kuala Lumpur54100 Malaysia

ISBN: (纸本)9781728175225

Air pollution has harmed human health as a human cannot live without breathing. Even more worrying is that air pollution seems to be increasing day by day due to man-made pollution or natural pollution like a massive forest fire. Due to no real-time monitoring device being implemented, the authorities are unaware of the real-time conditions of air quality. Therefore, this project is aimed to give real-time air quality and location data by designing and developing a portable device and mobile app capable of producing and broadcasting real-time Air Pollutant Index (API) and GPS coordinates. In this work, various air pollutant gases and problems of the present air quality monitoring system have been reviewed. Two different pollutant gas sensors, i.e., Carbon Monoxide (CO) and Nitrogen Dioxide (NO2) sensors, and NEO-6M Global Positioning System (GPS) module, have been proposed. Air Pollutant Index (API) value and location data are determined by the system and uploaded to the cloud database. The developed mobile app retrieves the data, and anyone with the mobile app can get information about the location and its air quality in real-time. The system has been tested at two different places, and the results were compared with existing air-quality websites that were available online. Results showed that the system provides a 92.3% accuracy that is 5.1% more accurate than other systems. The proposed system could provide an important building block for smart city development. © 2021 IEEE.

关键词： Air quality

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：