检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Vidhya, K. Nagarajan, B. Jenefa, A. Catherine Joy, R. Cherian, Minu Franz Kingstein, N. School of CST Karunya Institute of Tech. and Sci Coimbatore India Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India Division of ECE Karunya Institute of Tech. and Sci Coimbatore India Computer science and engineering department Amal Jyothi college of engineering kanjirapally Kottayam India

ISBN: (纸本)9798331527549

Advances in echocardiography have significantly improved the diagnostic processes for heart function analysis. However, traditional imaging techniques often struggle with the dynamic complexities of cardiac activities. Existing methods fail to capture detailed variations in cardiac function over time, leading to suboptimal clinical decision-making and patient outcomes. Traditional echocardiography relies heavily on manual interpretation, which can be subjective and varies significantly between observers. This research presents EchoNet Dynamic, a novel method for improving echocardiographic data analysis and interpretation based on deep learning and the Transformer model. The EchoNet Dynamic dataset used in this study comprises 15,000 B-mode echocardiographic images from 750 patients, divided into training, validation, and testing sets for comprehensive model evaluation. The Transformer model demonstrated remarkable effectiveness, achieving an accuracy of 98.5%, an AUC of 0.992, and an F1 score of 0.972, surpassing traditional diagnostic tools by a significant margin. The EchoNet Dynamic model demonstrates a promising enhancement in detecting and diagnosing cardiac functions, offering substantial improvements over conventional echocardiographic methods and setting a new benchmark in cardiac healthcare. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Block Chain technology: Anomaly Detection in Bitcoin Using RFMLPAlgorithm 4

Block Chain Technology: Anomaly Detection in Bitcoin Using R...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Elangovan, V.R. Revathi, S. Nusrat Jabeen, T. Obaid, Ahmed J. Kumar, Rahul SRM Institute of Science and Technology Kattankulathur Faculty of Science and Humanities Department of Computer Applications Chennai India City University Faculty Cybersecurity Ajman United Arab Emirates University of Kufa College Al-Ayen University Computer Science and Mathematics Department of Computer Technical Engineering Technical Engineering Thi-Qar Iraq Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR Institute of Technology and Sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

Block chain technology has been used in many different fields, including banking, logistics, healthcare, and government. However, billions have been lost to cyber attacks on block chain apps in the last several years. An efficient approach for identifying malicious behavior in block chain networks is urgently required. Anomaly detection is a well-studied issue with a lengthy history of research. Anomalies are, in a nutshell, unusual or improbable occurrences. Theft and other illicit activity in financial networks are often outliers. Participants in the network want to spot anomalies as soon as possible to safeguard the overall safety and security of the system. However, fraud and anomaly detection techniques are constantly developing along with the financial industry. Furthermore, the most secure approach being brought into money is block chain technology. The number of scams, however, increases every year alongside these innovative technology. This is why we suggested a safe Anomaly detection technique that combines Machine Learning with Deep Learning. For the purpose of classifying Anomaly transactions, we used a unique hybrid RFMLP approach. For Bitcoin transaction anomaly detection, the RFMLP combines Random Forest (RF) with multilayer perceptron (MLP). We found that our RFMLP was more accurate than competing algorithms. © 2024 IEEE.

关键词： Bitcoin

来源：评论

学校读者我要写书评

暂无评论

Learning orientation detection system and its application to RGB images

Learning orientation detection system and its application to...

引用

2024 International Conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Chen, Tianqi Qiu, Zhiyu Hua, Yuxiao Todo, Yuki Tang, Zheng Division of Electrical Engineering and Computer Science Graduate School of Natural Science & Technology Kanazawa University Ishikawa Kanazawa920-1152 Japan Faculty of Electrical Information and Communication Engineering Kanazawa University Ishikawa Kanazawa920-1192 Japan Faculty of Engineering University of Toyama Toyama930-8555 Japan

ISBN: (纸本)9781510685437

Our previous research showed that emulating dendritic neuron structure effectively addresses orientation detection challenges in learning tasks, reducing both learning time and costs compared to alternative neural network approaches. Our simulation model incorporates an On-Off Response mechanism in bipolar cells (BCs) and horizontal cells (HCs) for processing grayscale input images. To overcome limitations with single-channel input, we introduce color-selective cells. By integrating these cells, we enhance and select outputs of local orientation detection dendritic neurons, generating specific feature maps. These feature maps are generated using a biologically-inspired model that mimics the mechanism of color-selective cells. Additionally, global neurons are used to capture overall image features by aggregating outputs from local dendritic neurons. Our system utilizes backpropagation to update parameters of local orientation detection dendritic neurons. Furthermore, we integrate a learnable orientation detection neural network after the dendritic neuron stage. © 2024 SPIE.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Real-time Human Action Recognition using Deep Convolutional Neural Networks 15

Real-time Human Action Recognition using Deep Convolutional ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vignesh, R. Balaraju, J. Poongothai, P. Rajput, Vaishali Rajkumar, N. Pratheep, V.G. Karunya Institute of Technology and Sciences Division of Artificial Intelligence and Machine Learning Karunya Nagar Coimbatore India Anuraag University Department of Cse Hyderabad India Department of Computer Science Bangalore India Vishwakarma Institute o Technology Computer engineering Pune India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Cse Thiruvalluvar Tamil Nadu Avadi India Kongu Engineering College Department of Mechatronics Engineering Tamil Nadu Perundurai638060 India

ISBN: (纸本)9798350370249

current advances in deep gaining knowledge of have enabled automated systems to understand human moves from movies in actual-time. Deep convolutional neural networks (DCNNs) had been used to allow accurate and efficient real-time movement reputation. with the aid of leveraging the statistics-driven illustration mastering capability of DCNNs, movement popularity has become a powerful device for video analysis applications including robotics, surveillance, entertainment, augmented truth, and healthcare. DCNNs use an aggregate of densely connected convolutional layers and in addition completely linked layers for function extraction from films. The proposed architectures are usually skilled using supervised learning. Convolutional layers are used to understand nearby abstractions in motion pictures, which in turn are used to research worldwide features. diverse techniques together with temporal segmentation, movement-based characteristic extraction, and feature switch gaining knowledge of are also hired by means of DCNNs for achieving higher performance. recent works have investigated exceptional techniques to enhance the accuracy and speed of action reputation the use of DCNNs. This consists of techniques which includes model compression, decoupled inference networks, and efficient convolutional networks. By using combining those strategies, it's far viable to acquire higher popularity accuracy at the same time as at the equal time preserving an excessive computational speed. © 2024 IEEE.

关键词： Computational Equal Excessive Gaining Research Speed

来源：评论

学校读者我要写书评

暂无评论

Assistive Object Recognition and Obstacle Detection System for the Visually Impaired Using YOLO 13

Assistive Object Recognition and Obstacle Detection System f...

引用

13th International Conference on Cloud Computing, Data Science and engineering, Confluence 2023

作者： Chaudhary, Divyansh Mathur, Anubhav Chauhan, Ayush Gupta, Aakanshi Suraj Logistix Pvt. Ltd. Tuffplast Division Jamshedpur India Cognizant Faridabad India Cognizant Gurugram India Amity School of Engineering and Technology Dept. of Computer Science and Engineering Noida India

ISBN: (纸本)9781665462631

Human vision provides us with information that is irreplaceable and indispensable. Accessible visual data for humans is of utmost importance for their safety, navigation, identification, and many other activities. Therefore, to aid the visually hindered, the need of the hour is to develop a smart, automated system to gain characteristic information about the area around them and help them navigate an unknown and unmapped environment. With massive developments in machine learning and computer vision, various devices and applications have been developed to assist the visually impaired. The limitations of these techniques are their usability in a real-world scenario and affordability in third-world and developing countries. Thus, this paper comprehensively compares various state-of-the-art (SOTA) algorithms for detection and classification and outlines an application to assist the visually impaired by utilizing a handheld gadget. It incorporates different strategies to assemble a model that will classify and recognize the objects and provide an estimated distance from the nearest obstacle through an auditory medium. The model takes advantage of Raspberry Pi's portability, computational power, and modularity, creating a cost-effective handheld. It uses the YOLOv3 algorithm to perform object recognition in near real-time scenarios, which provides the best overall ratio of mAP to Time Taken and utilizes the robust dataset of MS COCO. As a result, the proposed device provides the best performance in a real-time environment, computing results within 50ms with mAP comparable to other SOTA algorithms. It aims to provide an alternative to the walking stick and other external help required by the visually challenged. © 2023 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

RiskMap: A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment

RiskMap: A Unified Driving Context Representation for Autono...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Xin, Ren Wang, Sheng Chen, Yingbing Cheng, Jie Liu, Ming Ma, Jun The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong Hong Kong Robotics and Autonomous Systems Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong

ISBN: (纸本)9781665481090

Motion planning is a complicated task that requires the combination of perception, map information integration and prediction, particularly when driving in heavy traffic. Developing an extensible and efficient representation that visualizes sensor noise and provides basis to real-time planning tasks is desirable. We aim to develop an interpretable map representation, which offers prior of driving cost in planning tasks. In this way, we can simplify the planning process for dealing with complex driving scenarios and visualize sensor noise. Specifically, we propose a unified context representation empowered by deep neural networks. The unified representation is a differentiable risk field, which is an analytical representation of statistical cognition regarding traffic participants for downstream planning tasks. This representation method is nominated as RiskMap. A sampling-based planner is adopted to train and compare RiskMap generation methods. In this paper, the RiskMap generation tools and model structures are explored, the results illustrate that our method can improve driving safety and smoothness, and the limitation of our method is also discussed. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

RetiGAN: A Hybrid Image Enhancement Method for Medical Images 5

RetiGAN: A Hybrid Image Enhancement Method for Medical Image...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Huang, Zhen Wang, Shiyuan Hu, Huijie Xu, Yiyao University of Science and Technology of China School of Computer Science and Technology Anhui Hefei230027 China University of Science and Technology of China Biomedical Engineering. Division of Life Sciences and Medicine Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu215123 China University of Science and Technology of China School of the Gifted Young Hefei230027 China University of Science and Technology of China School of Computer Science and Technology Hefei230027 China

ISBN: (纸本)9798350373820

Image enhancement can improve image quality and visual effects well, and there are many outstanding applications in natural images. Medical image enhancement is relatively difficult due to its particularity, such as lack of unified standards, scarce annotation, small data, high accuracy requirements, complex patterns, insufficient image contrast, fuzzy details, and large noise interference. Due to the large gap between natural and medical images, there is a lack of effective universal methods for both types of data. This paper proposes a hybrid model based on the Retinex theory and adversarial generative network to implement the RetiGAN model. Firstly, the image is processed by Gaussian filtering, inverse number transformation and image stretching, and then the data is amplified by the generative adversarial network (GAN) to realize data enhancement. In terms of experiments, nearly a thousand X-ray data based on two public and one private medical image datasets were compared with baseline, the most common image enhancement method, and adequate comparative experiments were conducted with mainstream methods such as LL-Net, Zero-DCE, PELE, etc. Experiments show that the method not only improves the image quality indexes such as PSNR, LPIPS and SSIM but also has remarkable visualization effects and enhancement effects in texture details, which shows that our method has great potential and application space in practical clinical diagnosis. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sovereign Allocation of Resources in Cloud Milieus Using a Causal Dilated Geometric Algebra Approach for Dynamic Scalability 2

Enhancing Sovereign Allocation of Resources in Cloud Milieus...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Katru, Chandrasekhar Rao Srinivasan, Sathish Kumar, Mohan Yadwad, Sunita Satish, G. Maranan, Ramya Lead Software Engineer Indian LandSC29707 United States Machine Learning & AI Development Oracle Cloud Infrastructure Division San FranciscoCA United States Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India Parul institute of Engineering and Technology Parul University Computer science and Engineering Faculty of Engineering and Technology Gujarat India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Telangana Sheriguda India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance. © 2025 IEEE.

关键词： Infrastructure as a service (IaaS)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation

arXiv

引用

arXiv 2024年

作者： Talaei, Mahtab Izadi, Iman Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran The Department of Electrical and Computer Engineering Isfahan University of Technology Iran The Division of Systems Engineering Boston University Boston United States

Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient updates of deep neural networks) transferred between clients and servers, potentially revealing sensitive local information to adversaries using model inversion attacks. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. On the other hand, heterogeneities in data structure, storage, communication, and computational capabilities of devices can cause convergence problems and delays in developing the global model. A personalized weighted averaging of local parameters based on the resources of each device can yield a better aggregated model in each round. In this paper, to efficiently preserve privacy, we propose a personalized DP framework that injects noise based on clients’ relative impact factors and aggregates parameters while considering heterogeneities and adjusting properties. To fulfill the DP requirements, we first analyze the convergence boundary of the FL algorithm when impact factors are personalized and fixed throughout the learning process. We then further study the convergence property considering time-varying (adaptive) impact factors. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

RBCET: A Reputation based Blockchain Consensus Mechanism for Fast and Secured Energy Trading in Internet of Electric Vehicles (IoEV)

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Kumar, Amritesh Mondal, Koustav Kumar Vishwakarma, Lokendra Das, Debasis Indian Institute of Technology Department of IDRP: IoT and Applications Jodhpur India Indian Institute of Technology Inter-Disciplinary Research Division: Centre for AIoT and Applications Jodhpur India Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India Indian Institute of Technology Department of Computer Science and Engineering Jodhpur India

The state-of-the-art consensus mechanisms in blockchain-based Internet of Electric Vehicles (IoEV) prove suboptimal for energy trading due to their heavy CPU workload, high bandwidth consumption, energy inefficiencies, and the backlog of pending transactions. Also, the network is susceptible to attacks such as double-spending, Distributed Denial of Service (DDoS), eclipse, Sybil, and collusion attacks. Addressing these challenges, this paper introduces RBCET, a reputation-based consensus mechanism explicitly designed for energy trading within the IoEV blockchain network. The RBCET computes the reputation score (RS) of nodes (e.g. Electric Vehicles (EVs) and Charging Stations (CSs)) in the IoEV network using a decision tree regressor (DTR) model. This model utilizes the reputation parameter dataset generated by a relational mathematical model. RBCET allows only those EVs and CSs to participate in energy trading whose RS value exceeds the average RS value. Additionally, we also propose a hardware-based incentive mechanism to calculate and store incentives to enhance the efficiency of energy trading. Security analysis shows that RBCET resists the attacks mentioned above. Furthermore, we have developed a testbed using 10 Raspberry Pi 4 devices to demonstrate the performance of RBCET compared with state-of-the-art schemes. This comparison shows that RBCET reduces CPU workload by 47%, energy consumption by 10%, bandwidth usage by 5%, the volume of pending transactions by 75%, and overall improves efficiency by 62%. © 1975-2011 IEEE.

关键词： Denial-of-service attack

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：