检索结果-内蒙古大学图书馆

2nd International Conference on Automation, Computing and Renewab.e Systems, ICACRS 2023

作者： Pant, Suman bhat, Niyati Shobana, G. Sindhuja, R. Lekha, D. Srimathi, S. School of CA & IT Shri Guru Ram Rai University India B.E Computer engineering University of Mumbai Mumbai India Department of Computer Applications College of Science and Humanities SRM Institute of Science and Technology Kattankulathur India Department of Medical Electronics Saveetha Engineering college India CSE Department R.M.K. College of Engineering and Technology India Department of Bio Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9798350340235

Human Gait Recognition (HGR) is a biometric system that is exploited for security purpose over the past few years. The efficiency of gait detection is affected by different features namely walking surfaces, wearing clothes, and carrying a bag. Moreover, detection from divergent views is a complicated prob.em in HGR. Numerous approaches were proposed for HGR using classical and DL methods but the conventional technique is not appropriate for massive data. This study leverages ensemb.e Learning Model for Human Gait Recognition in Human computer Interface (eLMHGA-HCI) technique. The eLMHGA-HCI technique intends to recognize various kinds of human gaits to assist HCI applications. In the eLMHGA-HCI technique, Time Domain (TD) and Frequency Domain (FD) features from the input signals. For gait recognition, an ensemb.e of three DL models takes place namely bidirectional Long Short Term Memory (biLSTM), Gated Recurrent Unit (GRU) and Recurrent Neural Network (RNN). To exhibit the enhancedgait recognition results of the eLMHGA-HCI technique, a widespread simulation analysis is done. The simulation outcomes pointed out the enhanced performance of the eLMHGA-HCI approach over other existing techniques. © 2023 Ieee.

关键词： Activity recognition Deep learning ensemb.e learning Gait recognition Human computer interface

来源：评论

学校读者我要写书评

暂无评论

employing a deep learning technique to categorize Internet of Things (IoT) traffic in a smart city context

Employing a deep learning technique to categorize Internet o...

引用

2023 Ieee International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATe 2023

作者： Anu Priya, S. Rajesh kanna, b. beaulah Jeyavathana, R. bhat, Niyati Rajalakshmi, S. Srimathi, S. Chennai600117 India Department of Electronics and Communication Engineering Alagappa Chettiyar College of Engineering and Technology Karaikudi India Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai India B.E Computer Engineering University of Mumbai Mumbai India Department of Electronics and Communication Engineering RMK College of Engineering and Technology India Department of Bio Technology Saveetha School of Engineering SIMATS Tamilnadu Chennai India

ISBN: (纸本)9798350305708

The exponential increase in quantity of cars on the roads of smart cities has led to traffic jams, air contamination, and delays in the delivery of essential goods. every day road accidents continue to be a leading cause of death and serious injury. The Internet of Things-based Traffic Management System is utilized to manage traffic flow, ensure safe data transfer, and spot accidents. Autonomous vehicles and smart devices have sensors built into an IoT-based ITM system to help with identification, data collection, and transmission. Connectivity options for the Internet of Things are being severely tested by the proliferation of IoT devices and applications. This can lead to severe difficulties in the allocation of the spectrum, the resources needed to analyze the IoT data, and the allowab.e delay for important spare situations throughout the end-to-end communication chain. Therefore, accurate categorization or forecasting of the IoT devices' time-varying traffic characteristics is essential. However, the difficulty of making this sort of categorization remains open. Current approaches tend to be based on machine learning methods, which have a high computational cost despite not taking into account the traffic's fine-grained flow features. In this research, we address this issue by developing a two-stage categorization system based on deep learning for IoT devices in a smart city that draws on both connectivity and statistical information. In order to excerpt the internet and statistical characteristics set for various IoT strategies, we must do data cleaning and preprocessing. based on the results of the tests, it appears that the proposed categorization has a 99% chance of being correct. © 2023 Ieee.

关键词： Autonomous Vehicle Deep Learning IoT Traffic data Smart-City Traffic Management

来源：评论

学校读者我要写书评

暂无评论

Automatic Plane Pose estimation for Cardiac Left Ventricle Coverage estimation via Deep Adversarial Regression Network

IEEE Transactions on Artificial Intelligence

引用

Ieee Transactions on Artificial Intelligence 2024年第9期5卷 4738-4752页

作者： Zhang, Le bronik, Kevin Piechnik, Stefan K. Lima, Joao A. C. Neubauer, Stefan Petersen, Steffen e. Frangi, Alejandro F. University of Birmingham School of Engineering College of Engineering and Physical Sciences BirminghamB15 2TT United Kingdom University of Oxford Department of Engineering Science OxfordOX1 3PJ United Kingdom Division of Cardiovascular Medicine OxfordOX3 9DU United Kingdom Johns Hopkins University School of Medicine Division of Cardiology BaltimoreMD21287 United States Queen Mary University of London Centre for Cardiovascular Medicine The William Harvey Research Institute LondonE1 1BB United Kingdom Barts Health Nhs Trust Barts Heart Center LondonE1 1BB United Kingdom The University of Manchester Division of Informatics Imaging and Data Science School of Health Sciences The Department of Computer Science School of Engineering ManchesterM13 9PL United Kingdom

Accurate segmentation of the ventricles plays a crucial role in determining cardiac functional parameters such as ventricular volume, ventricular mass, and ejection fraction. However, poor image quality, such as inadequate coverage of the left ventricle (LV) and right ventricle (RV) in cardiac magnetic resonance (CMR) image sequences, can significantly affect the assessment of cardiac function. This study investigates issues related to missing or corrupted imaging planes, which often lead to incomplete ventricle coverage. To address the challenge of estimating ventricle coverage in CMR images regardless of variations in imaging parameters such as device type, magnetic field strength, and protocol execution, we introduce a novel convolutional neural network (CNN) based on adversarial learning. Additionally, we integrate supplementary information (e.g., cross-view image data) as privileged information to enhance the interpretability of our model's predictions and identify potential biases or inaccuracies. This research represents the first attempt to automatically estimate ventricular coverage by identifying missing slices and plane orientations in CMR images using a dataset-agnostic approach. The effectiveness of the proposed model is demonstrated through the evaluation of datasets from three diverse and sizab.e image acquisition cohorts, demonstrating superior performance compared to existing methods. © 2020 Ieee.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Convolutional Neural Network with Representation Self-challenge for Fingerprint Liveness Detection

引用

computers, Materials & Continua 2022年第10期73卷 719-733页

作者： Jie Chen Chengsheng Yuan Chen Cui Zhihua Xia Xingming Sun Thangarajah Akilan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310053China Jiangsu Yuchi Blockchain Research Institute Nanjing210044China Department of Software Engineering Lakehead UniversityThunder BayON P7B 5E1Canada

Fingerprint identification systems have b.en widely deployed in many occasions of our daily ***,together with many advantages,they are still vulnerab.e to the presentation attack(PA)by some counterfeit *** address challenges from PA,fingerprint liveness detection(FLD)technology has b.en proposed and gradually attracted people’s *** vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the prob.em of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model *** at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint ***,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the prob.em of model over-fitting and enhances generalization of detection ***,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and *** size of the model parameters is only 548 Kb,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently availab.e.

关键词： FLD lightweight multi-scale RSC blind materials

来源：评论

学校读者我要写书评

暂无评论

Proactive Network Optimization Using Deep Learning in Predicting IoT Traffic Dynamics

Proactive Network Optimization Using Deep Learning in Predic...

引用

Innovative Practices in Technology and Management (ICIPTM), International Conference on

作者： S. Anu Priya Niyati bhat b. Rajesh Kanna S. Rajalakshmi R. beaulah Jeyavathana Srimathi S Department of Computer Applications Vels Institute of Science Technology & Advanced Studies ((VISTAS) Chennai B.E Computer Engineering University of Mumbai Mumbai Department of Electronics and Communication Engineering Alagappa Chettiyar College of Engineering and Technology Karaikudi Department of Electronics and Communication Engineering RMK College of Engineering and Technology Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

ISBN: (数字)9798350307757

ISBN: (纸本)9798350307764

Prob.ems have arisen in allocating and managing network resources effectively because of the proliferation of IoT gadgets. This study aims to provide a deep learning-based strategy for forecasting and analyzing IoT traffic patterns to solve this prob.em. The model uses recurrent neural networks (RNNs) with Long Short-Term Memory (LSTM) cells to capture the complex temporal dependencies in IoT data streams. Following careful data gathering from various IoT sources, a thorough preprocessing phase is performed to account for missing values and outliers. effective modeling is enab.ed by applying feature engineering approaches to distill meaningful information and by temporally aggregating the dataset. The heart of the study is the creation of a sequence-to-sequence architecture that allows for reliab.e forecasting of future IoT traffic trends. Mean Squared error (MSe) and other performance metrics measure the quality of the proposed model's predictions. In addition to its predictive abilities, the model's analytical section reveals interesting facts about the fundamental habits underpinning IoT traffic. This dual purpose helps network managers better comprehend the ever-changing IoT ecosystem and allocate scarce resources. The results of this study have important implications for network optimization, providing a preventative strategy for dealing with the difficulties posed by the exponential growth of IoT data traffic. Regarding accuracy and interpretability, the suggested deep learning model significantly contributes to the development of intelligent network resource management in the IoT era.

关键词： Deep learning Analytical models Recurrent neural networks ecosystems Predictive models Traffic control Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Analyzing, Detecting and Automatic Classification of Different Stages of brain Tumor Using Region Segmentation and Support Vector Machine

Analyzing, Detecting and Automatic Classification of Differe...

引用

2020 International Conference on electronics and Sustainab.e Communication Systems, ICeSC 2020

作者： Gayathri, S. Wise, D.C. Joy Winnie Janani, V. eleaswari, M. Hema, S. Rajalakshmi Institute of Technology Department of Cse India B.E Computer Science and Engineering Rajalakshmi Institute of Technology India

ISBN: (纸本)9781728141084

The clinical researchers found that, Magnetic Resonance Imaging is applied in various computer science applications. However, for detecting the brain tumor without human involvement is taken into account has a major space of analysis. As a result of the obtained brain tumor images need to be optimized segmentation rule that must be more silent towards noise and size of the cluster sensitivity prob.em with automatic region based segmentation property detection. Region based segmentation is used to segment the over segment and under segment of the tumor region with automatic ROI detection. After the successful detection of tumor parts that are going to classify the different classes of brain tumors such as benign and malignant. The benign tumor and malignant tumor are classified as normal stage, medium stage and severe stage. For that different feature extraction and classification methods are used for identifying the above. Without human intercession the brain tumor should be detected and analyzed. The SVM algorithm is used to classify the tumor cell. The accurate classification and giving appropriate therapy to the Patient plays a vital role in Health Care Sector. © 2020 Ieee.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Face Spoof Detection Using Gray Level Co-Occurrence Matrix and Discrete Wavelet Transform Feature extractor

Face Spoof Detection Using Gray Level Co-Occurrence Matrix a...

引用

International Conference on Computing sciences (ICCS)

作者： Amal Mathew Kaushik Daiv Polkumpally Rohan Goud Piyush Talreja Sai Sanjana Reddy Vatte B.tech Computer Science Ms Ramaiah University of Applied Sciences Bangalore Karnataka India B.E. Computer Science MIT College of Engineering Pune Maharashtra India B.E Computer Science Chaitanya Bharathi Institute of Technology Hyderabad India B.E Computer Science Maharashtra Institute of Technology Pune Maharashtra India

ISBN: (纸本)9781665494465

Face identification using ML (machine learning) is well-known. Attendance structures may benefit from this method. Using this method, you may achieve the desired area, as well as beneficial attributes and a dataset, by preparing two sets of data again for test and training phases. To distinguish between a testing set and a test sets, a photograph is used as a testing set. An ensemb.e classification method is used to sort the test images into categories like “identified” and “unidentified.” This model can't provide reliab.e findings since it simply divides data into two categories. The development of GLCM was motivated by the need to use texture properties to identify faces. The existence of the query picture is noted once face detection has taken place. In simulation findings, the new model outperforms the baseline models in terms of accuracy. Keywords—ensemb.e classifier, GLCM, Face Spoof, SVM, DWT

关键词： Training Image segmentation Face recognition Training data Machine learning Transforms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

employing a deep learning technique to categorize Internet of Things (IoT) traffic in a smart city context

Employing a deep learning technique to categorize Internet o...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATe), International Conference on

作者： S. Anu Priya b. Rajesh Kanna R. beaulah Jeyavathana Niyati bhat S. Rajalakshmi Srimathi S Department of Computer Applications (MCA) Vels Institute of Science Technology & Advanced Studies ((VISTAS) Chennai Department of Electronics and Communication Engineering Alagappa Chettiyar College of Engineering and Technology Karaikudi Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai B.E Computer Engineering University of Mumbai Mumbai Department of Electronics and Communication Engineering RMK College of Engineering and Technology Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

The exponential increase in quantity of cars on the roads of smart cities has led to traffic jams, air contamination, and delays in the delivery of essential goods. every day road accidents continue to be a leading cause of death and serious injury. The Internet of Things-based Traffic Management System is utilized to manage traffic flow, ensure safe data transfer, and spot accidents. Autonomous vehicles and smart devices have sensors built into an IoT-based ITM system to help with identification, data collection, and transmission. Connectivity options for the Internet of Things are being severely tested by the proliferation of IoT devices and applications. This can lead to severe difficulties in the allocation of the spectrum, the resources needed to analyze the IoT data, and the allowab.e delay for important spare situations throughout the end-to-end communication chain. Therefore, accurate categorization or forecasting of the IoT devices' time-varying traffic characteristics is essential. However, the difficulty of making this sort of categorization remains open. Current approaches tend to be based on machine learning methods, which have a high computational cost despite not taking into account the traffic's fine-grained flow features. In this research, we address this issue by developing a two-stage categorization system based on deep learning for IoT devices in a smart city that draws on both connectivity and statistical information. In order to excerpt the internet and statistical characteristics set for various IoT strategies, we must do data cleaning and pre-processing. based on the results of the tests, it appears that the proposed categorization has a 99% chance of being correct.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging ensemb.e Learning Model for Human Gait Recognition in Human computer Interface

Leveraging Ensemble Learning Model for Human Gait Recognitio...

引用

Automation, Computing and Renewab.e Systems (ICACRS), International Conference on

作者： Suman Pant Niyati bhat G Shobana R. Sindhuja D Lekha S Srimathi School of CA & IT Shri Guru Ram Rai University B.E Computer engineering University of Mumbai Mumbai Department of Computer Applications College of Science and Humanities SRM Institute of Science and Technology Kattankulathur India Department of Medical Electronics Saveetha Engineering college CSE Department R.M.K. College of Engineering and Technology Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

Human Gait Recognition (HGR) is a biometric system that is exploited for security purpose over the past few years. The efficiency of gait detection is affected by different features namely walking surfaces, wearing clothes, and carrying a bag. Moreover, detection from divergent views is a complicated prob.em in HGR. Numerous approaches were proposed for HGR using classical and DL methods but the conventional technique is not appropriate for massive data. This study leverages ensemb.e Learning Model for Human Gait Recognition in Human computer Interface (eLMHGA-HCI) technique. The eLMHGAHCI technique intends to recognize various kinds of human gaits to assist HCI applications. In the eLMHGA-HCI technique, Time Domain (TD) and Frequency Domain (FD) features from the input signals. For gait recognition, an ensemb.e of three DL models takes place namely bidirectional Long Short Term Memory (biLSTM), Gated Recurrent Unit (GRU) and Recurrent Neural Network (RNN). To exhibit the enhanced gait recognition results of the eLMHGA-HCI technique, a widespread simulation analysis is done. The simulation outcomes pointed out the enhanced performance of the eLMHGA-HCI approach over other existing techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Sample-efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review

arXiv

引用

arXiv 2024年

作者： Hassani, Hossein Razavi-Far, Roozbeh Saif, Mehrdad Lin, Liang Department of Electrical and Computer Engineering Western University LondonONN6A 3K7 Canada Faculty of Computer Science Canadian Institute for Cybersecurity University of New Brunswick FrederictonNBE3B 5A3 Canada Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China

Reinforcement learning (RL) is a sub-domain of machine learning, mainly concerned with solving sequential decision-making prob.ems by a learning agent that interacts with the decision environment to improve its behavior through the reward it receives from the environment. This learning paradigm is, however, well-known for being time-consuming due to the necessity of collecting a large amount of data, making RL suffer from sample inefficiency and difficult generalization. Furthermore, the construction of an explicit reward function that accounts for the trade-off between multiple desiderata of a decision prob.em is often a laborious task. These challenges have b.en recently addressed utilizing transfer and inverse reinforcement learning (T-IRL). In this regard, this paper is devoted to a comprehensive review of realizing the sample efficiency and generalization of RL algorithms through T-IRL. Following a brief introduction to RL, the fundamental T-IRL methods are presented and the most recent advancements in each research field have b.en extensively reviewed. Our findings denote that a majority of recent research works have dealt with the aforementioned challenges by utilizing human-in-the-loop and sim-to-real strategies for the efficient transfer of knowledge from source domains to the target domain under the transfer learning scheme. Under the IRL structure, training schemes that require a low number of experience transitions and extension of such frameworks to multi-agent and multi-intention prob.ems have b.en the priority of researchers in recent years. © 2024, CC bY.

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：