检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Yuhan Huang, Tianyao Liu, Yimin Wang, Xiqin The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China The EE Department Tsinghua University Beijing China

We study the problem of representing a discrete tensor that comes from finite uniform samplings of a multidimensional and multiband analog signal. Particularly, we consider two typical cases in which the shape of the subbands is cubic or parallelepipedic. For the cubic case, by examining the spectrum of its corresponding time- and band-limited operators, we obtain a low-dimensional optimal dictionary to represent the original tensor. We further prove that the optimal dictionary can be approximated by the famous discrete prolate spheroidal sequences (DPSSs) with certain modulation, leading to an efficient constructing method. For the parallelepipedic case, we show that there also exists a low-dimensional dictionary to represent the original tensor. We present rigorous proof that the numbers of atoms in both dictionaries are approximately equal to the dot of the total number of samplings and the total volume of the subbands. Our derivations are mainly focused on the 2-dimensional (2-D) scenarios but can be naturally extended to high dimensions. © 2024, CC BY.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A Frame Work For The Tuberculosis Detection Through CXR Using Deep Learning Networks

A Frame Work For The Tuberculosis Detection Through CXR Usin...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： S. Sudhakar V. P. Kolanchinathan S. Sivasaravana Babu M. Aakash B. Arunkumar V. B. Arunkumar Department of Computer Science and Engineering SSM Institute of Engineering and Technology Department of Electronics and Communication Engineering Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Mycobacterium tuberculosis, the causative agent of tuberculosis (TB), continues to be a serious worldwide health concern, killing about 1.3 million people in 2022, predominantly in low- and middle-income countries. The urgent need for automation in healthcare has spurred the development of supplementary tools. We have created a method for detecting TB in chest X-rays using advanced techniques such as pre-processing, picture segmentation, augmenting the data, along with Deep Learning model for classification. Our approach involves segmenting the lung region from X-rays using a U-Net model, followed by classification with a convolutional neural network (CNN). This optimized design enhances accuracy and efficiency, making it suitable for mobile deployment and providing a practical solution for TB detection in resource-limited settings.

关键词： Deep learning computers Automation Tuberculosis Lung X-rays Data models

来源：评论

学校读者我要写书评

暂无评论

Development of LiFi System for communication and Control in Hilly Regions

Development of LiFi System for Communication and Control in ...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Adarsh Dabral Raj Gusain Anurag Vidyarthi Rishi Prakash R. Gowri Department of Computer Science Engineering Propagation Research Lab Graphic Era (Deemed to be University) Dehradun India Department of Electronics & Communication Engineering Propagation Research Lab Graphic Era (Deemed to be University) Dehradun India Department of Electronics & Communication Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Science Engineering Graphic Era Hill University Dehradun India

In hilly regions where cable distribution is challenging and costly traditional communication systems often face difficulties. LiFi technology emerges as a promising solution in such contexts, leveraging communication through visible light. It uses light as a medium to provide data speeds that surpass those of Wi-Fi, This research paper presents an approach for a communication system specifically designed for hilly terrains using Light Fidelity (LiFi) technology. The proposed paper start with an introduction of LiFi technology and advantages of it over conventional communication methods in these regions. However, it also acknowledges the inherent limitations of Li-Fi, such as its low range, which is especially relevant in hilly topographies. The main body of the paper details the system's architecture, comprising a transmitter for sending data, a receiver to receive data, and dual operation: text for sending massage and operate devices, and audio for communication. To underscore its practicality, the system is showcased through two applications: an SOS emergency feature for hilly terrains and a device activation/deactivation application. In conclusion, the paper provides an in-depth examination of how this tailored system functions and its potential benefits for communities and operations in hilly landscapes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Prediction Using a Deep Hybrid CNN-GAN Model on EEG Data

Epileptic Seizure Prediction Using a Deep Hybrid CNN-GAN Mod...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Nowshad Hasan Md. Maskat Sharif Miskatur Rahman Md Saiful Islam Md Tohedur Rahaman Khan MD Jiabul Hoque Anamul Bahar Department of Electronics and Telecommunication Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh Department of Computer Science Enginnering International Islamic University Chittagong Chittagong Bangladesh Department of Computer and Communication Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Computer Science Enginnering University of London London United Kingdom

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

Epileptic seizure detection from EEG signals is essential for the diagnosis and treatment of neurological conditions. However, this task is difficult because of the complex and fluctuating characteristics of EEG data. To overcome these difficulties, this research employs a specialized CNN-GAN hybrid model designed to improve seizure prediction by generating realistic synthetic data. This approach addresses class imbalance and enhances feature learning. The process begins with preprocessing EEG datasets to remove noise and artifacts. Data augmentation follows, expanding the dataset and reducing the risk of overfitting. Segmentation then isolates important features to boost prediction accuracy. Feature extraction is achieved using a custom CNN model, and classification is performed with a GAN model. The model demonstrates high accuracy, with results of 99.95% on the BONN Dataset, 98.93% on the CHB-MIT Dataset and 98.80% on the SWEC-ETHZ Dataset. Overall, the custom CNN-GAN hybrid model significantly improves the accuracy of predicting epileptic seizures from EEG signals across various datasets.

关键词： Representation learning Accuracy Predictive models Brain modeling Data augmentation Feature extraction Electroencephalography Data models Robots Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Investigating the Potential of Machine Learning for Enhancing Real-Time Data Analysis 3

Investigating the Potential of Machine Learning for Enhancin...

引用

3rd International Conference on Smart Generation Computing, communication and Networking, SMART GENCON 2023

作者： Singh, Khushboo Mahalakshmi, V. Chavhan, Pranali G. Garg, Prateek Sahoo, Girija Shankar Sukumar, R. Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Electronics and Communication Engineering Karnataka Ramnagar562112 India

ISBN: (纸本)9798350319125

This abstract discusses the capability of system learning to serve as a device for real-time facts evaluation and its ability to decorate the accuracy of the resulting insights. Specifically, it examines the advantages of computerized function engineering and the way system gaining knowledge of primarily based tools may be leveraged to offer businesses with actionable data insights extra efficaciously than conventional strategies. It additionally looks at a few rising technologies, inclusive of deep neural networks, and their capability to push the limits of information analysis in real-time, and also discusses how improvements in allotted computing can similarly supplement the impact of gadget studying gear. Eventually, this summary additionally affords some demanding situations associated with actual-time evaluation of massive volumes of facts, and some advised answers. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Scalable IoT Security Framework Leveraging Ensemble Learning for Attestation

Scalable IoT Security Framework Leveraging Ensemble Learning...

引用

International Conference on Computational Intelligence and communication Networks (CICN)

作者： Mini TT Santrupti Behera M Srikar Reddy Chittaranjan Hota Design Engineering Celestica Chennai India Department of Computer Science Birla Institute of Technology and Science Pilani India Department of Electronics & Communication Birla Institute of Technology and Science Pilani India

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

Attestation involves providing verifiable evidence to support claims about the characteristics of a target device. Devices that manage sensitive data-such as wearables, Industrial IoT devices, and servers-are vulnerable to various threats, including edge-based attacks, denial-of-service (DoS) attacks, counterfeiting, and firmware tampering. Attestation plays a crucial role in ensuring the integrity of firmware and configurations, authenticating genuine hardware, and verifying that composite device assemblies remain unaltered. However, a review of existing solutions highlights significant deficiencies, particularly in comprehensive lifecycle management and support for large-scale networks. This paper introduces a novel attestation method based on an optimized ensemble learning, which achieves a predictive accuracy of 93%, addressing these gaps and enhancing security across the entire device lifecycle.

关键词： Accuracy Runtime Reviews Predictive models Malware Hardware Ensemble learning Wearable devices Microprogramming Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Patient Context Monitoring With Wireless Networks 4

Patient Context Monitoring With Wireless Networks

引用

4th International Conference on Intelligent engineering and Management, ICIEM 2023

作者： Singh, Charanjeet Shrivastava, Anurag Pokhariya, Hemant Singh Kumar, Indradeep Sundar Ganesh, C.S. Pratap Srivastava, Arun Deenbandhu Chhotu Ram University of Science and Technology Electronics and Communication Department Murthal India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India Institute of Aeronautical Engineering Department of Aeronautical Engineering Telangana Hyderabad India Karpagam College of Engineering Coimbatore641032 India Lloyd Institute of Engineering and Technology Department of CSE Uttar Pradesh Greater Noida201308 India

ISBN: (纸本)9798350341126

It has become increasingly necessary to observe patients in the emergency room, especially in cases of failed patient verification in the clinic, as medical service application innovation advances. Patients' daily activities can be recorded by numerous devices connected to the distant institution. This framework uses the actual framework as well as the application dataset along with the clinical histories of the associated patients so that users can select how simple situations should be handled. The proposed framework makes use of the actual framework, the application dataset, and the clinical histories of the associated patients. An accuracy rate of 95% ensures that this will be a beneficial tool for the clinical office. This will be able to accurately monitor the patient's condition using connected sensor-based networks. Social events and the patient's natural practices are monitored by several sensors. Next, the cloud collects important natural data. By examining sensor data, the system may identify the patient's underlying ailment and is more advanced. This system has the advantage of enabling doctors and other medical personnel to observe patients without having to interact directly with them through pop-up messages. This system then promptly alerts the relevant professionals, carers, and clinic staff. In this context, any clinical document that has web functionality and can monitor at least one indicator of patient health is known as an 'IoT-based patient health observation framework'. A patient's condition can be recorded, communicated, and alerted if it changes unexpectedly. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Dual Random Phase Encoding Encryption Using Fractional Fourier Transform

Dual Random Phase Encoding Encryption Using Fractional Fouri...

引用

Advances in Signal Processing, Power, communication, and Computing (ASPCC), IEEE International Conference on

作者： Vanitha Kakollu Hari Kishore Neerukattu Battula Tirumala Krishna Department of Computer Science GITAM School of Science GITAM University Visakhapatnam India Department of Electronics and Communication Engineering Jawaharlal Nehru Technological University Kakinada Kakinada India

ISBN: (数字)9798350355093

ISBN: (纸本)9798350355109

A fusion-based hybrid approach to Dual Random Phase Encoding Encryption (DRPE) picture encryption and watermarking uses 2D-Fractional Fourier Transform (FrFT) invariance to prevent frequency shift alterations during encryption or transmission. Phase-only information and image FrFT magnitude are combined to rebuild images during decryption. In decryption, invariance property and fusion approach rebuild encrypted information using input picture data, ensuring reliability. The method reconstructs images well and maintains watermarks. The basic hybrid approach uses cryptography, watermarking, and steganography under low noise and few attacks to describe the prospect of better encryption and decryption with authentication, ownership, degrees of freedom, and key security. Performance analysis for the suggested strategy employs different photographs under different encryption and decryption key values for different assessment criteria to examine resilience and efficiency in all areas. The approach fails to rebuild or decrypt when the encryption and decryption keys do not match and the internal procedures use incorrect image data. Correct analysis demonstrates security and attack prevention. Inefficiency or partial satisfaction with the decrypted image shows the relevance of the fusion method in this major approach for sending the entire image data to the receiver. Due of its invariance during frequency shift changes, picture phase data can improve this method.

关键词： Steganography Fourier transforms Prevention and mitigation Noise Watermarking Receivers Encryption Performance analysis Reliability Resilience

来源：评论

学校读者我要写书评

暂无评论

ANFIS Grey Wolf Optimized And Secured Path Selection Algorithm For VANET Applications

ANFIS Grey Wolf Optimized And Secured Path Selection Algorit...

引用

2023 International Conference on Energy, Materials and communication engineering, ICEMCE 2023

作者： Sivaprakash, P. Nisha, K.S. Jagadish Vijay, R. Madhivadhani, D. Maheswari, E. Sasikumar, M. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu India Amrita College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Nagercoil India Kings Engineering College Faculty of Electronics and Communication Engineering Chennai India Sri Sai Ram Institute of Technology Department of Electrical and Electronics Engineering Chennai India C. Abdul Hakeem College of Engineering & Technology Department of Electrical and Electronics Engineering Tamil Nadu India

ISBN: (纸本)9798350393378

Vehicle ad hoc networks (VANETs) present a unique mix of challenges and opportunities for routing protocols because to the semi-organized organization of means of transportation that faces limits of road structure and laws, as well as obstructions that limit physical access in urban environments. The dependability and scalability of routing protocols in big metropolitan VANETs are actively being explored. Furthermore, ANFIS-GWO Optimization approaches are used to increase routing sustainability and availability in VANETs by clustering vehicles beside one other based on connection locations and relative velocity, resulting in the widespread building of hierarchical network topologies. The transmission range demonstrates that the ANFIS-GWO (Adaptive Neuro-Fuzzy Inference System- Grey Wolf Optimization) is significantly more efficient than the ANFIS and GWO. End to End delay, Energy Consumption, Packet Loss and Throughput evaluation is contrasted with conventional approaches like FUZZY, ANN and ANFIS GWO Respectively. Throughput evaluation is contrasted with conventional approach ANFIS GWO is 650kbps. © 2023 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Application of computer Software in Chemical Data Processing using Spider Monkey Optimization Algorithm 2

Application of Computer Software in Chemical Data Processing...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Rana Veer Samara Sihman Bharattej, R. Rupavath, Rana Veer Samara Sihman Brahmatej Hussein, Abbas Hameed Abdul Anjaneyulu, Madugula Upendra Roy, B.P. Saint Leo University Department of Computer Science St Leo United States Indiana Wesleyan University Marion United States Ahl Al Bayt University College of Pharmacy Karbala Iraq Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Department of Ai&ml Hyderabad India Channabasaveshwara Institute of Technology Gubbi Department of Electronics and Communication Engineering Tumkur India

ISBN: (纸本)9798350372892

The development of chemical-based products and functional materials is crucial for modern technologies, yet it often entails significant costs and time delays. Artificial intelligence and machine learning present novel approaches to leverage data for addressing these challenges;however, they encounter specific hurdles in the chemical domain. To address these issues, a software platform has been introduced to facilitate training and development of Recurrent Neural Networks (RNN). This platform incorporates the Spider Monkey Optimization (SMO) algorithm to optimize model's hyperparameters, including neurons number, rate of learning, and activation function. This software package goes beyond neural network training and development by encompassing design and operating-parameter optimization, essential aspects of chemical engineering processes. Within this framework, the weights that were optimized and bias obtained from neural network were stored and utilized in other SMO process for optimizing important process variables, like swiftness and temperature, according to user specifications. © 2024 IEEE.

关键词： Software packages

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：