检索结果-内蒙古大学图书馆

18th International Conference on computer Science and Education, ICCSE 2023

作者： Zhou, Yujie Yuan, Caihong Su, Chenshuang Zou, Mingdong Zhu, Xiaoke Liang, Wenjuan School of Computer and Information Engineering Henan University Henan Engineering Research Center of Intelligent Technology and Application Henan Province Spatial Information Processing Engineering Technology Research Center Kaifeng China

ISBN: (纸本)9789819707294

With the rapid development of urban transportation, vehicle re-identification has become a focal point in traffic management and vehicle tracking problems. In order to address the problem of small inter-class similarity among vehicles, previous studies utilize vehicle parsing models to extract local features. Therefore, we introduce the Squeeze-and-Excitation attention mechanism to extract important discriminative information from these local features. Furthermore, we propose a local co-occurrence attention mechanism to represent the proportion of common parts feature matching. To address the issue of large intra-class differences caused by vehicle direction change, we propose a lightweight and effective direction weighted fusion strategy. Experiments on two large datasets show that the proposed algorithm performs competitively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Emotion and Gesture Recognition System for Humans and Animals Using computer Vision and Deep Learning 5

Multi-Modal Emotion and Gesture Recognition System for Human...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Nair, Rekha R Babu, Tina Kishore, S. Shivaswamy, Smitha Aruna, S. Bhargavi, Manchikalapudi Alliance School of Advanced Computing Alliance University Department of Computer Science and Engineering Bengaluru India Department of Computer Application Karnataka Mangaluru India Acharya Institute of Technology Department of Computer Applications Bengaluru India School of Science and Computer Studies CMR University Bangalore India Hyderabad India

ISBN: (纸本)9798331518097

Emotion recognition through facial expressions and gesture analysis has emerged as a key area of research in computer vision and human-computer interaction. The ability to automatically detect and classify human emotions has wide-ranging applications, from enhancing user experiences to improving mental health monitoring and surveillance systems. This project builds on this background to develop a comprehensive system for recognizing emotions and gestures in both humans and animals. The system integrates facial emotion recognition, hand gesture interpretation, and animal emotion detection into a single platform. Using advanced deep learning models and computer vision libraries, the system classifies facial expressions into categories such as happiness, sadness, anger, fear, surprise, and neutral. The gesture recognition component interprets hand signals to convey messages like 'need help' or 'need water.' An innovative aspect of this work is the extension of emotion recognition to animals, particularly focusing on species like dogs and monkeys. Implemented primarily in Python, the system leverages libraries such as OpenCV and DeepFace. By combining these different modalities of nonverbal communication analysis, the project presents a versatile solution with potential applications in human-computer interaction, mental health monitoring, security, and animal welfare. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Prediction from MRI image using Convolutional Deep Neural Network

Alzheimer's Disease Prediction from MRI image using Convolut...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in technology, IC-SIT 2024

作者： Panda, Sanghamitra Sahu, Rekha Dash, Satya Ranjan Centurion University of Technology and Management Department of Computer Science and Engineering Odisha Bhubaneswar India Silicon University Department of Computer Science and Engineering Odisha Bhubaneswar India KIIT Deemed to Be University School of Computer Application Odisha Bhubaneswar India

ISBN: (纸本)9798350369175

Alzheimer's disease is one sort of neurological disorder which affects the daily activities and it is incurable. But, if it can be detected early, then it may be prevented or made to progress slowly. For detection, deep learning has played a great role now a days. In this paper, we have taken 6400 MRI images of both dementia and non-dementia subjects. The dataset is spilt into ${8 0 \%}$ for training a model and ${2 0 \%}$ for validating and accessing the achievement of the trained model. We have recommended a two-dimensional convolutional neural network architecture in order to apply on the MRI dataset to generate a model for classifying and predicting Alzheimer's disease patients. The model generated using the proposed two-dimensional architecture has given approximately $98 \%$ classification accuracy. Besides, we have presented roc-auc curve, f1-score, recall, support, precision and confusion matrix to show the execution of the model. Again, at training procedure, model loss and accuracy also depicted according to epoch times. The researches already performed on prediction of Alzheimer's disease has given poor performance of ${9 1 \%}$ classification accuracy in comparison to our model. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare 4.0: The Fusion of Blockchain and IoT in Medicine 11

Revolutionizing Healthcare 4.0: The Fusion of Blockchain and...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Kashyap, Vijaita Ahuja, Rakesh Gautam, Shivani Kumar, Ashok Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Chitkara University School of Engineering & Technology Chitkara University Himachal Pradesh India School of Computer Application Lovely Professional University Punjab Phagwara India

ISBN: (纸本)9798350350357

The use of Blockchain technology (BCT) has become widespread across several scientific fields and is projected to see substantial growth in the near future. Blockchain (BC) functions as a digital record-keeping system, enabling transactions to occur in a decentralized manner. BC applications are being developed in a variety of areas, including agriculture, healthcare, and the Internet of Things. BCT has recently sparked significant interest in the healthcare industry. It provides trustworthy and convenient services, and the utmost importance to recognise and address the security issues and obstacles that are linked to this innovative approach. This study introduces the Proof-of-Health (PoH) consensus method, which improves the security and efficiency of the integrated system. It also provides a contemporary analysis and overview of the numerous challenges and unresolved issues that conventional security methods have introduced to smart healthcare. Here, the analysis of loT and BC implementation with some different factors is shown. This study also explores the many components used in BC methodologies and incorporates BCT as a feasible security measure. It evaluates possible obstacles in sectors such as healthcare, agriculture, and numerous other domains. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Extrapolative Preservation Management of Medical Equipment through IoT 1

Extrapolative Preservation Management of Medical Equipment t...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Tripathi, Rajeev Mishra, Vinay Kumar Maheshwari, Himani Tiwari, Raj Gaurang Agarwal, Ambuj Kumar Gupta, Ashulekha School of Management Sciences Department of Computer Application and Sciences Lucknow India School of Computer Application Babu Banarasi das University Lucknow India School of Computing Graphic Era Hill University Uttrakhand Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350330915

The healthcare industry is primarily driven by technological innovations as they are a significant source of inspiration to provide the best patient care. To provide patients with prompt, high-quality care, medical device manufacturing has grown at an unprecedented rate. Hospitals should use the best maintenance techniques to increase the life of their equipment while trying to reduce maintenance costs and efforts as medical device usage increases. This paper proposes a predictive maintenance method (PdM) to assist in identifying critical equipment failures with diverse and frequent failure modes. The proposed method is based on the understanding of the physics of the incident, real-time data collection of relevant parameters using Internet of Things (IoT) technology, and application of machine learning algorithms to predict and classify the condition of the device as good and bad. To demonstrate the feasibility and effectiveness of moving from traditional maintenance to PdM, an economic analysis should be provided. The objective of this study was to determine the challenge of medical device maintenance using an Internet of Things (loT) enabled automated health monitoring system for devices that generate large amounts of data. real-time data, at scale, in healthcare organizations. © 2023 IEEE.

关键词： Failure Management Internet of things IoT Medical Equipment Maintenance Predictive Maintenance Sensors

来源：评论

学校读者我要写书评

暂无评论

Music conditioned 2D hand gesture dance generation with HGS

Music conditioned 2D hand gesture dance generation with HGS

引用

作者： Zhou, Dian Liu, Shiguang Xu, Qing School of Computer Science and Technology College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University Tianjin China

In recent years, the short video industry is booming. However, there are still many difficulties in the action generation of virtual characters. We observed that on the short video social platform, "hand gesture dance" is a very popular short video form. However, its development is limited by the professionalism of choreography. In order to solve these problems, we propose an intelligent choreography framework, which can generate new gesture sequences for unseen audio based on pairing data in the database. Our framework adopts multimodal method and obtains excellent results. In additional, we collected and produced the first and largest pair labeled hand gesture dance data set. Various experiments showed that our results not only generate smooth and rich action sequences, but also collect some semantic information contained in the audio. © 2023 John Wiley & Sons Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Capacitor voltage unbalance minimization for three-phase five-level diode-clamped inverter using hexagonal hysteresis space vector modulation

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第2期7卷 661-671页

作者： Ramkumar, R. Singh, Manmohan Ramkumar, R. Usha, S. Thentral, T. M. Thamizh Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Chengalpattu India Department of Computer Engineering and Application GLA University Mathura India Department of Electrical and Electronics Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Trichy India Department of Renewable Energy University of Maroua National Advanced School of Engineering of Maroua Maroua Cameroon

This article suggests a method for diminishing the voltage unbalance in a three-phase five-level diode-clamped inverter (DCI) through the use of hexagonal hysteresis space vector modulation (HHSVM). Capacitor voltage balancing leads to enhanced system efficiency, reduced stress on components, enhanced performance, abridged electromagnetic interference, and reduced total harmonic distortion. The proposed modulation technique and its implementation are thoroughly examined in this study, along with modeling and experiment data that show how efficient the method is at lowering the capacitor voltage unbalance in the proposed five-level DCI. Capacitor voltage unbalance is reduced with the use of this HHSVM approach to 0.95%, which is a superior reduction compared to traditional PWM methods. The paper also discusses the advantages of the proposed method over other existing methods, making it a promising solution for practical applications in power electronics systems.

关键词： Diode-clamped inverter (DCI) Capacitor voltage balancing Hexagonal hysteresis space vector modulation (HHSVM) Total harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Visible and Infrared Image Fusion for Object Detection: A Survey

Visible and Infrared Image Fusion for Object Detection: A Su...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Sun, Yuxuan Meng, Yuanqin Wang, Qingbo Tang, Minghua Shen, Tao Wang, Qingwang School of Information Engineering and Automation Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China Naval Research Academy Beijing China

ISBN: (纸本)9789819708543

Thanks to the advancements of Deep Learning (DL) Algorithms. DL-based object detection models has witnessed remarkable success in the past few years. By leveraging deep convolutional neural networks (CNNs) and other deep learning models, rich feature representations can be effectively extracted from visible (RGB) images for object detection. However, for challenging scenarios such as low-light conditions and haze, the performance of object detection using visible images is often not satisfactory. On the other hand, thermal camera, which is unaffected by lighting conditions, can penetrate through low-light and hazy environments to capture object images. However, infrared images lack edge and texture information of objects. Recognizing the complementary nature of visible and infrared images, researchers have explored the fusion of visible and infrared images for object detection, yielding promising research outcomes. This paper provides an analysis of the current research status of visible and infrared image fusion for object detection. Firstly, the fusion models are categorized into three kinds: pixel-level fusion, feature-level fusion, and decision-level fusion. Several models within each category are discussed. Furthermore, this paper summarizes five datasets that can be utilized for training RGB-Infrared object detection models and compares the experimental results of selected models on the KAIST dataset. Lastly, the paper concludes with a summary of existing challenges in the field and offers some reflections on future directions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Branchy-TEE: Deep Learning Security Inference Acceleration Using Trusted Execution Environment 35

Branchy-TEE: Deep Learning Security Inference Acceleration U...

引用

35th International Conference on Software Engineering and Knowledge Engineering, SEKE 2023

作者： Wang, Yulong Deng, Kai Meng, Fanzhi Chen, Zhi Yin, Mingyong Yang, Run Institute of Computer Application China Academy of Engineering Physics Mianyang China School of Cyberspace Science Harbin Institute of Technology Harbin China

Deep Learning as a Service (DLaaS) has become a remarkable trend in modern data-driven online services. Both data holders and service providers need to build on trust in third-party cloud infrastructure platforms. However, once the trust is broken, data holders’ sensitive data and service providers’ intellectual property rights will face significant security and privacy risks. In this paper, we propose a secure and efficient inference framework for deep learning in untrustworthy cloud platforms, termed Branchy-TEE, which aims to protect the confidentiality and integrity of data and models of multiple participating actors throughout the inference process using the Trusted Execution Environment (TEE). Branchy-TEE dynamically loads the inference network into the TEE on-demand based on early-exit mechanism, expecting to break the hardware performance bottleneck of the TEE. Moreover, a joint training method based on knowledge distillation for multi-exit networks is proposed, by flowing"knowledge" from the final exit with high accuracy to the early branch exit with lower accuracy. Finally, the effectiveness and efficiency of Branchy-TEE are verified through extensive experiments in real environments, while achieving an optimal balance between performance and hardware resources. © 2023 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Data Mining for Predictive Modeling of Stroke Risk and Post-Stroke Care Management 3

Machine Learning and Data Mining for Predictive Modeling of ...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Gobi, N. Singh, B.P. Yadav, Surendra Department of Computer Science and Information Technology Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350343274

The research investigates the efficacy of a comprehensive machine learning and data mining approach in predictive modeling of stroke risk and post-stroke care management. A holistic methodology is proposed, integrating diverse datasets and advanced algorithms, including Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) networks. Data preprocessing, feature extraction, and personalized care plan generation are key components. Performance evaluation using accuracy, sensitivity, specificity, precision, F1 Score, AUC, and MAE demonstrates the superior predictive capabilities and efficiency of the proposed method compared to traditional approaches. The study highlights the potential for revolutionizing stroke care, emphasizing personalized risk assessment and post-stroke management for improved patient outcomes and healthcare delivery. © 2023 IEEE.

关键词： Data mining

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：