检索结果-内蒙古大学图书馆

2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Eric Clapten, J. Sasimekala, M.M. Rajeswari, C. Sanjay Kumar, K. Communication Engineering Department of Electronics Chennai India Department of Biomedical Engineering Chennai India Chennai Institute of Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350348910

The analysis of microarray image helps in identifying new genes that enables us to understand their functions and gene expression levels simultaneously at different conditions. This is also useful in diagnosing the various diseases and helps in develop the treatment for the required disease. In general it has 3 stages, the first one is gridding, and the second segmentation and the third one is intensity extraction. In this paper we are going to discuss various machine learning techniques in segmenting the microarray images. This proposed algorithm eliminates the noise and enhances the image quality by finding the nearest spots in segmentation and enhancing the spot using KNN algorithm. The performance can be improved further by the efficient utilization of a graphics processing unit (GPU). It is also shown that the method can be employed to produce a model on health based on a PET-MRI dataset which can be utilized to automatically detect pathology in the imaging. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Feature Selection Methods Using Swarm-Based Optimization Techniques

Comparative Analysis of Feature Selection Methods Using Swar...

引用

IoT, Communication and Automation Technology (ICICAT), International Conference on

作者： Ashish Kumar Singh Anoj Kumar Ashish Ranjan Mishra Dept. of Computer Sci. & Engineering MNNIT Allahabad Prayagraj India Dept. of Computer Sci. & Engineering Rajkiya Engineering College Sonbhadra India

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368116

Feature selection is a vital data preprocessing technique aimed at selecting informative features from a dataset, which is essential for improving classification performance. Optimization involves deriving an optimal solution from feasible options, often drawing inspiration from nature. Particle swarm optimization (PSO) is highlighted as an effective metaheuristic algorithm for feature selection, capable of achieving satisfactory results with reduced computational complexity. Techniques are categorized into evolutionary, swarm intelligence, physics-based, and human-based approaches, with swarm intelligence particularly notable for its emergent intelligent behavior from simple agents. Swarm intelligence gains traction due to its speed, adaptability, and self-organization. These optimization techniques are highly efficient for tasks like optimal feature selection. In datasets of high dimension, quantity of noisy, irrelevant, and redundant features degrade clustering performance, necessitating methods to maximize accuracy, accelerate output, and filter out irrelevant features.

关键词： Surveys Dimensionality reduction Accuracy Metaheuristics Nearest neighbor methods Filtering algorithms Feature extraction Noise measurement Particle swarm optimization Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Modified EfficientNetB3 Deep Learning Model to Classify Colour Fundus Images of Eye Diseases 5

Modified EfficientNetB3 Deep Learning Model to Classify Colo...

引用

5th IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2023

作者： Sharma, Riya Gangrade, Jayesh Gangrade, Shweta Mishra, Ashish Kumar, Gautam Kumar Gunjan, Vinit Manipal University Jaipur Dept of Computer Science & Engineering Jaipur India Learning Manipal University Jaipur Dept. of Artificial Intelligence & Machine Jaipur India Manipal University Jaipur Dept of Information Technology Jaipur India Jaypee Institute of Information Technology Dept of Computer Science & Engineering Noida India CMR Institute of Technology Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350338287

The only way to prevent blindness from eye problems is by early detection and prompt treatment. Although colour fundus photography (CFP) is useful for fundus inspection, there is a need for computer-assisted automated diagnosis tools due to the similarities between the early symptoms of many eye disorders. The suggested approach uses cutting-edge deep learning model to categorize images into several disease categories by learning distinguishing features from the input images. The high-resolution fundus photos from individuals with diabetic retinopathy (DR), glaucoma, cataract, and healthy eyes make up most of the dataset used for this research. The experimental findings show that the suggested system achieve 97% accuracy with modified efficientNetB3 model and surpasses current approaches for categorizing eye diseases. This approach may help doctors diagnose and treat eye conditions earlier, leading to better patient outcomes. © 2023 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Efficient Blind Channel Estimation for IRS-Assisted Joint Communication and Sensing in 6G Networks

Efficient Blind Channel Estimation for IRS-Assisted Joint Co...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Siddig, Ali A. Al-Dweik, Arafat Iraqi, Youssef Pandey, Anshul Giacalone, Jean-Pierre Hamila, Ridha Al-Rimawi, Ashraf Khalifa University of Science and Technology Dept. of Computer and Information Eng. PO Box 127788 Abu Dhabi United Arab Emirates Mohammed VI Polytechnic College of Computing Benguerir Morocco Secure Systems Research Center Abu Dhabi United Arab Emirates Qatar University Dept. of Electrical Eng. Doha Qatar Birzeit University Dept. of Electrical and Computer Eng. Birzeit Palestine

ISBN: (纸本)9798350376715

To achieve the ultimate performance of intelligent reflecting surface (IRS), an accurate channel estimation is required, which in turns induces significant signaling overhead. This work presents a novel blind channel estimation scheme for IRS-assisted heterogeneous communications and sensing networks. The proposed scheme consists of two transmission stages, one for sensing and the other for communications. By noting that the sensing information have generally less stringent quality of service (QoS) requirements, the sensing stage is used for joint blind sensing data detection and blind channel estimation for the subsequent communications stage. Channel estimation is achieved using a specific frame structure where the modulated sensing symbols cooperate to estimate the channel coefficients for all IRS reflecting elements blindly and jointly. The simulation results obtained show that the proposed blind channel estimation accuracy is comparable to pilot-based schemes. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

A Denoising Convolutional Auto Encoder with Bi-LSTM for Corrupted ECG Signals Reduction 2

A Denoising Convolutional Auto Encoder with Bi-LSTM for Corr...

引用

2nd IEEE International Conference on Data Science and Network Security, ICDSNS 2024

作者： Alsalami, Zaid Satish, E.G. Ponnibala, M. Rajalakshmi, J. Sushama, C. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Dept. of Computer Science and Engineering Bengaluru India Velalar College of Engineering and Technology Erode India School of Computing Mohan Babu University Dept. of Cse Tirupati India

ISBN: (纸本)9798350373110

The IoT based scheme e-health uses some measurable device for to monitor the health condition of our body. The long-term measurable system like cardiovascular, electrocardiogram (ECG) are significant methods to diagnose the patient's diseases. The drawbacks of this measurable system such as high computational cost, consume more time for training and ECG signals contained some noise and corrupted signals. To addresses this kind of problem, the Denoising Convolution Auto Encoder (DCAE) with Bidirectional Long Short-Term Memory (Bi-LSTM) method is implemented. The DCAE contains encoder and decoder part to convert the ECG corrupted signals into compressed form. Bi-LSTM attached to encoder part that carries the input signals and trains that. Bi-LSTM carries double layers, which makes the training process easily. This proposed method tested on MIT-BIH databases. The advantages of this method, auto encoder easily convert the corrupted signals without using any parameters and reduce computation cost. Bi-LSTM reducing the training process, time consumption and it consisted of double layers, which increase the compression process of signals fastly. The developed DCAE-Bi-LSTM gives better output rate of 97.85% which is better than other existing methods like CNN-LSTM and SVM. © 2024 IEEE.

关键词： Signal denoising

来源：评论

学校读者我要写书评

暂无评论

Visualizing the Path of a Photo Taker from Image Metadata 4

Visualizing the Path of a Photo Taker from Image Metadata

引用

4th International Informatics and Software engineering Conference, IISEC 2023

作者： Majid, Rasty Shakhawan Varol, Cihan Varol, Asaf Nasab, Ahad Firat University Department of Software Engineering Erbil Iraq Sam Houston State University Computer Science Department HuntsvilleTX United States College of Engineering and Computer Science Dept. of Engineering Management and Technology ChattanoogaTN United States

ISBN: (纸本)9798350318036

One of the most challenging investigations in forensic analysis is the work conducted on smartphones. Specifically using smartphone data to provide evidence for a case is becoming a norm nowadays. Many Android device applications use and work with location services that assist investigators in working with log files that store valuable information. Images captured on Android devices will save geolocation information, date, and time in the properties. In this work, a tool is developed to acquire the date and geolocation for each taken photo so that the path of the photo taker can be displayed on Google Maps. The work showed that the application can take about 4 and a half seconds to process four images and display the map to the investigator. © 2023 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Validation of an Information Diffusion based Health Social Media on Yoga and Ayurveda 2

Validation of an Information Diffusion based Health Social M...

引用

2nd International Conference on computer Science, engineering and Applications, ICCSEA 2022

作者： Yadav, Rk Kumar, Girish Kumar, Naveen Varshney, Pratyaksh Jha, Natwar Amit Delhi Technological University Dept. of Computer Science & Engg. Delhi India Delhi Technological University Dept. of Mechanical Engineering Delhi India Delhi Technological University Dept. of Computer Science & Engineering Delhi India

ISBN: (数字)9781665458344

ISBN: (纸本)9781665458344

The deadly COVID-19 coupled with other diseases has proven to be the biggest challenge humans have seen in ages. Healthcare systems, even in the most developed countries, have completely shattered during the peak of waves. Thus, leaving millions rendered helpless and alone around the globe. This proves the importance of self-care and immunity to being the best possible way for being healthy. Solutions specific to strengthening immunity are available in the Indian sciences of Yoga and Ayurveda and has been scientifically proven. These have been around in India for ages but there is an immense lack of awareness in India and around the globe regarding that. This review paper aims at filling the lack of awareness by proposing a model and validating it further by collecting and comparing the pre and post-implementation data. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Investigation of LEO-GEO Inter-satellite Scenarios basics OWC Architecture 4

Investigation of LEO-GEO Inter-satellite Scenarios basics OW...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Kumari, Meet Sharma, Neha Chauhan, Rahul Joshi, Kireet Kumar, Amit Sunil, G. Chandigarh University Dept. of Ece Uie Mohali140413 India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350307757

To use optical wireless communication (OWC) in satellite services, forwarding communication between geostationary and low-Earth orbit satellites would typically be implemented. The OWC technology is included in this study to improve the communication in an intersatellite scenario. For this a 4×10Gbps OWC system is designed and investigated for inter-satellite links. Simulation results comprise that maximum satellite range of 27000-36000km for non return to zero and 27000-32000km for return to zero is obtained in architecture. Additionally, eye patterns together with optical spectra provide the design performance for varied range of 27000-36000km. Also, it is verified that design comprises optimum performance over other satellite communication systems. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks

arXiv

引用

arXiv 2024年

作者： Hairi Fang, Minghong Zhang, Zifan Velasquez, Alvaro Liu, Jia Dept. of Computer Science University of Wisconsin-Whitewater United States Dept. of Computer Science and Engineering University of Louisville United States Dept. of Computer Science North Carolina State University United States Dept. of Computer Science University of Colorado Boulder United States Dept. of Electrical and Computer Engineering The Ohio State University United States

In this paper, we study a fully-decentralized multi-agent policy evaluation problem, which is an important sub-problem in cooperative multi-agent reinforcement learning, in the presence of up to f faulty agents. In particular, we focus on the so-called Byzantine faulty model with model poisoning setting. In general, policy evaluation is to evaluate the value function of any given policy. In cooperative multi-agent system, the system-wide rewards are usually modeled as the uniform average of rewards from all agents. We investigate the multi-agent policy evaluation problem in the presence of Byzantine agents, particularly in the setting of heterogeneous local rewards. Ideally, the goal of the agents is to evaluate the accumulated system-wide rewards, which are uniform average of rewards of the normal agents for a given policy. It means that all agents agree upon common values (the consensus part) and furthermore, the consensus values are the value functions (the convergence part). However, we prove that this goal is not achievable. Instead, we consider a relaxed version of the problem, where the goal of the agents is to evaluate accumulated system-wide reward, which is an appropriately weighted average reward of the normal agents. We further prove that there is no correct algorithm that can guarantee that the total number of positive weights exceeds |N|− f, where |N| is the number of normal agents. Towards the end, we propose a Byzantine-tolerant decentralized temporal difference algorithm that can guarantee asymptotic consensus under scalar function approximation. We then empirically test the effective of the proposed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

On the Feasibility of a 3D-Printable Conductive Filament-Based Antenna Array for Conformal Applications

On the Feasibility of a 3D-Printable Conductive Filament-Bas...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Hemachandra Konduru Benjamin Callies Dipankar Mitra Sayan Roy Shuvashis Dey Rahul Gomes Dept. of Computer Science and Computer Engineering University of Wisconsin La Crosse WI USA Dept. of Physics and Astronomy University of Wisconsin La Crosse WI USA Electrical and Computer Engineering Division of Energy Matter and Systems University of Missouri Kansas City MO USA Dept. of Electrical and Computer Engineering North Dakota State University Fargo ND USA Dept. of Computer Science University of Wisconsin Eau Claire WI USA

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

NASA is actively addressing communication challenges, particularly in developing phased array antenna systems (PAAS) within the 2-2.5 GHz frequency band. The initial stages involve designing individual flexible antenna elements and non-phased antenna arrays. To address the issues of conformal phased array antennas, this work presents design enhancements for a 3D-printable microstrip patch antenna using a conductive Electrifi filament. The modifications, informed by recent research, are evaluated for the antenna's return loss and surface current distributions. The adopted modifications demonstrated superior performances in terms of gain and input reflection (S 11 ). The investigation extends to a 1x4 antenna array based on the modified patch antenna element. Notably, the conformal antennas and the antenna array exhibit low return loss alongside high gain and directivity, suggesting substantial potential for efficient performance in conformal surface applications.

关键词： Phased arrays Microstrip antenna arrays Electric potential Patch antennas NASA Resonant frequency Microstrip antennas

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：