检索结果-内蒙古大学图书馆

7th IET Smart Cities Symposium, SCS 2023

作者： Banerjee, Abhijit Gupta, Subir Dutta, P.K. El-Kenawy, El-Sayed M. Department of Electronics and Communication Engineering Dr. B C Roy Engineering College Durgapur India Department of Computer Science and Engineering Swami Vivekananda University Kolkata West Bengal 700121 School of Engineering and Technology Amity University Kolkata West Bengal India Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt

ISBN: (纸本)9781839539831

In this study, the application of NeuroEvolution-based hyperparameter tuning for reinforcement learning algorithms in the context of Software-Defined Networking (SDN) computation offloading was explored. The primary reinforcement learning algorithms investigated were Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor-Critic (A3C). These algorithms were optimized using the Gamma Levy Hybrid Metaheuristic with Conditional Evolution (GLHM-CE) and Covariance Matrix Adaptation Evolution Strategy (CMA- ES) tuning methods. The performance of the algorithms was evaluated in terms of energy efficiency and reward comparison acrossepisodes, with a focus on SDN computation offloading scenarios. The results demonstrated that NeuroEvolution-based tuning, particularly when utilizing GLHM-CE optimization, significantly improved the energy efficiency of both PPO and A3C *** was concluded that the integration of NeuroEvolution-based hyperparameter tuning methods, such as GLHM-CE, with reinforcement learning algorithms, offers a promising approach for enhancing the performance of SDN computation offloading tasks. © The Institution of engineering & technology 2023.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Endpoint detection and response using machine learning 2

Endpoint detection and response using machine learning

引用

2nd International Conference on Computational Intelligence and Energy Advancements, ICCIEA 2021

作者： Kaur, Harmionee Tiwari, Richa Computer Science Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Noida201313 India

The need for cybersecurity has increased manifold over the past decade due to an unprecedented shift towards digital. With the increase in the number and sophistication of threats, cybersecurity experts have been forced to seek out new and efficient ways to secure endpoints on a network. Machine learning provides one such solution. This paper discusses how IoT devices are threatened and the need for endpoint security. It overviews different Machine learning-based intrusion detection systems that are currently in use e.g., STAT, Haystack, etc., and other Endpoint Detection and Response Techniques. © 2021 Institute of Physics Publishing. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative study on NOMA oriented Backscatter Communication

引用

Procedia computer science 2025年 259卷 864-872页

作者： Shilpi Sachin Kumar Sudhanshu Tyagi Sudeep Tanwar Department of ECE Amity School of Engineering and Technology Lucknow Campus Uttar Pradesh India Thapar Institute of Engineering and Technology Deemed to be University Patiala Punjab India Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad Gujarat India

The recent attraction of intentness from the industry as well as academia are derived by the shoot up in 5G communication technologies, consumer electronics, healthcare, cloud computing enabled big data analytics and agriculture. There are various types of challenges in these fields such as security challenges, design challenges, deployment challenges etc. One of the considerable wide challenge is the limited lifetime of network. Reason of limited lifetime are massive devices those are being activated by the finite capacities batteries. Backscatter communications (BackCom), a technique based on the phenomena of low power and low complexity of network is a hopeful technique to tackle this challenge. BackCom technique depend on inert reflection and amendment in an incident radio frequency wave. Also the exploration of non-orthogonal multiple access (NOMA) technique became very useful in fifth and beyond fifth generation of networks to increase its capacity. The combination of the two techniques, NOMA and BackCom, gives new prospects in multi cell NOMA networks in terms of connectivity. It leads several new challenges in condensed wireless network. The significant improvements of the combination of NOMA and BackCom are mentioned in comparison with the standard technique of orthogonal multiple access (OMA) ambient BackCom.

关键词： Backscatter communication NOMA OMA

来源：评论

学校读者我要写书评

暂无评论

Thyroid Health Forecaster: A Cutting-Edge Hybrid Deep Learning Framework for Early Disease Prediction 5

Thyroid Health Forecaster: A Cutting-Edge Hybrid Deep Learni...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Selvamuthu, C.M. Kartheek, G.L.N.V. Chandrashekhara, K.T. Thatipudi, Jayendra Gopal Vadar, Parashuram Shankar Bhattacharjee, Sandeep Tamil Nadu Chennai India Anurag Engineering college Department of Computer science and Engineering Telangana Suryapet India BMS Institute of Technology and Management Department of Information science and Engineering Bangalore India University of North Texas Dept. of Computer Science United States Yashwantrao Chavan School of Rural Development Shivaji University Maharashtra Kolhapur India Amity University Rajarhat Newtown West Bengal Kolkata700135 India

ISBN: (纸本)9798331530013

Detecting thyroid disease early is crucial for effective management and treatment, as conditions like hypothyroidism and hyperthyroidism can significantly impact a patient's health if left untreated. Traditional diagnostic methods, primarily based on hormone level testing, often fail to detect the disease in its initial stages. This study introduces a hybrid deep learning strategy to predict thyroid disease at an earlier stage, utilizing a combination of ResNet50 for feature extraction and Support Vector Machine (SVM) for classification. The methodology involves preprocessing thyroid image data, including resizing, normalization, augmentation, noise reduction, and enhancement, followed by feature extraction and classification. The hybrid model achieved an accuracy of 95.2%, precision of 94.5%, recall of 93.8%, F1 score of 94.1%, and ROC-AUC of 97%. This approach demonstrates superior performance compared to traditional machine learning models, indicating its potential for reliable early diagnosis of thyroid conditions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Satellite Constellations for Global Internet Coverage: A Comparative Analysis of Communication Protocols and Orbital Configuration

Optimizing Satellite Constellations for Global Internet Cove...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Pallab Banerjee Vivek Raj Biresh Kumar Kanika Thakur Dipra Mitra Purushottam Kumar Dept. of Computer Science Engineering Amity University Jharkhand Ranchi Jharkhand India Amity School of Information Technology Amity University Jharkhand Ranchi Jharkhand India Dept. of Computer Science Engineering Galgotia University Greater Noida campus Dept. of Computer Science Engineering Amity University Jharkhand Ranchi India

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

As a way to provide ubiquitous connectivity, satellite constellations are becoming more and more popular due to the growing need for worldwide internet access. In order to provide dependable and seamless worldwide internet coverage, this study investigates how satellite constellations might be optimized by comparing and contrasting communication protocols and orbital topologies. This ambitious aim involves a number of problems and complications, which are explored in the research along with the trade-offs and design considerations that must be made in order for the implementation to be effective. Two main elements form the framework of the comparative analysis. First, by considering factors like latency, data throughput, and coverage efficiency, it evaluates a range of communication protocols, including traditional geostationary satellites, Low Earth Orbit (LEO) constellations, and Medium Earth Orbit (MEO) satellites. Second, to ascertain the effect of various orbital configurations on worldwide internet coverage, the study considers satellite dispersion, orbital altitudes, and coverage patterns. By means of this study, the research endeavors to provide a valuable contribution to the current discussion on satellite constellations for worldwide internet coverage, therefore facilitating well-informed decisions about the design and implementation of these systems.

关键词： Earth Satellite constellations Adaptation models Protocols Uncertainty Low earth orbit satellites Propulsion Throughput Topology Planning

来源：评论

学校读者我要写书评

暂无评论

Detection of Lung Tumor using an efficient Quadratic Discriminant Analysis Model

Detection of Lung Tumor using an efficient Quadratic Discrim...

引用

2023 IEEE International Conference on Recent Trends in Electronics and Communication, ICRTEC 2023

作者： Gupta, Shashi Kant Kumar, V. Suresh Khang, Alex Hazela, Bramah Nivethitha, T. Haralayya, Bhadrappa Eudoxia Research University Department of Cse United States Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Information Technology Chennai India University of Science and Technology Department of Information Technology United States Amity School of Engineering and Technology Lucknow Amity University Computer Science and Engineering Uttar Pradesh India Hindusthan College of Engineering and Technology Department of Ece Coimbatore India Lingaraj Appa Engineering College Bidar Department of Mba Karanataka Bidar585403 India

ISBN: (纸本)9798350396195

Deep Learning has paved a way for finding solutions to numerous problems across the globe. It is one of the techniques being used widely in all the application being used worldwide. Healthcare is a field where various new innovations need to be done in order to diagnosis various new health related issues. In today's modern era, the increase in new medications is required at the most. One such application is the diagnosis of lung tumor. Tumors are the cells that do not grow as normally as other cells in the body and leads to many other side effects and if diagnosed lately could also lead to death. Hence, to diagnosis it very early need to new medications and techniques are required. Numerous types are tumors are present and they tend to occur in various parts of a human body. Sometimes they are very easily identified whereas in some cases they get detected only after a long time. Detection of tumor in very early stages is curable and hence it is very important that it needs to be identified very early. In this research, we present a model that uses the Deep Learning approach in order to identify tumors in the lungs at extremely early stages. Through there are numerous researchers working on the same domain, we have enhanced our model with the use of the Quadratic Discriminant Analysis. To detect the tumor in lung, the model initially detects and segments the tumor cells. Once the cells are segmented, the model also classifies if the tumor cells are malignant or benign. The findings illustrate how the suggested model differs from the conventional approaches in a number of ways. The comparative research was carried out, and the data reveal that the model that was presented is better to the other in terms of the amount of time it needs, clocking in at an average of 2.16 seconds. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Multi-criteria Decision-Making Approach to Analyze Python Code Smells 1

引用

International Conference on Advances in Electrical and computer Technologies, ICAECT 2021

作者： Gupta, Aakanshi Sharma, Deepanshu Phulli, Kritika Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Noida India Executive Branch-IT Indian Navy New Delhi India Application Development Associate Accenture India

ISBN: (数字)9789811911118

ISBN: (纸本)9789811911101

Frequent modifications in the software leads to the issues in the code which deteriorates software quality. The suitable approach to rectify it is to refactor it. Consequently, this research devises a ranking using the MCDM approach for prioritizing Python-based code smells. This order ranking has been studied over 10,552 classes for five generic code smells diffused in 20 Python software. The software metrics extracted over these python classes have been considered as multiple criteria which are processed using rule-based machine learning approach. In this study, an approach providing compromised solution—VIKOR have been practiced along with TOPSIS and WASPAS methods. Additionally, the MCDM approaches have utilized Shannon’s Entropy and CRITIC method as weight estimation techniques. The extracted vital software metrics achieved over 90% accuracy. The prominent outcome portrays that the most dominant smell is Collapsible "IF" which needs to be refactored at the early stage. This should be accompanied by Cognitive Complexity smell so as to attain sustainable development environment. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

A novel genetic algorithm with CDF5/3 filter-based lifting scheme for optimal sensor placement

引用

International Journal of Innovative Computing and Applications 2021年第2-3期12卷 67-76页

作者： Ganesan, T. Rajarajeswari, Pothuraju Nayak, Soumya Ranjan Bhatia, Amandeep Singh Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation VaddeswaramAP India Amity School of Engineering and Technology Amity University Uttar Pradesh Noida India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

The generic algorithm has been receiving significant attention due to the node placement problem in the field of sensor application in terms of machine learning. Sensor deployment is able to provide maximum coverage and maximum connectivity with less energy consumption to sustain the network lifetime. The maximum quality coverage problem has been solved successfully by an evolutionary algorithm while placing nodes in optimal position. In evolutionary algorithms, genetic algorithm (GA) plays an important technique for deploying the sensor in the form of population matrix. However, the existing techniques are unable to place sensor position perfectly. In this paper, a novel genetic algorithm with second generation wavelet transform (SGWT) is proposed for identifying optimal potential position for node placement. In order to improve the quality of population matrix, bi-orthogonal Cohen-Daubechies-Feauveau wavelet (CDF 5/3) has been employed. The proposed method is performed primarily to generate sensor position with different populations. Subsequently, it can extend to CDF5/3 filter-based lifting scheme to adjust the sensor position. The proposed method has been compared with random deployment, genetic algorithm and GA with CDF5/3 wavelets in terms of target to cover by the sensor. The result of the proposed method affirms better optimisation as compared to the state-of-art techniques. © 2021 Inderscience Enterprises Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Edge Detection Based Segmentation of Wheat Plants Diseases 7

Edge Detection Based Segmentation of Wheat Plants Diseases

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Singh, Mukesh Kumar Agrawal, Madhup Singh, Mukund Pratap Gupta, Vishan Kumar Mishra, Kunti Galgotias Collge of Engineering & Technology Department of Cse Greater Noida India Ajay Kumar Garg Engineering College Department of Information Technology Ghaziabad India Bennett University School of Computer Science Engineering And Technology Greater Noida India Amity University Punjab Department of Cse Mohali India Noida Institute of Engineering And Technology Department of Mathematics Greater Noida India

ISBN: (纸本)9798350371406

Wheat is mankind's primary food grain and the fourth most produced cereal;it is the primary food source for a lot of people, particularly in Asian and European countries. In addition to providing proteins, minerals, and carbohydrates, it also creates jobs for millions of people. Wheat plants, on the other hand, are subject to a variety of diseases that can result in significant quality and yield losses. Wheat diseases such as Leaf or Brown Rust, Stem Rust, Yellow Rust, Loose Smut, and Powdery Mildew are now contributing to these losses. To address this issue, a reliable and accurate automated disease identification system must be developed. In this study, we demonstrate the Sobel and Canny edge detection methods for segmentation, data extraction, and identifying the main properties of objects in wheat diseases. We also assess their effectiveness in terms of several established performance metrics, such as histogram, Mean Squared Error (MSE) and structural similarity index measure (SSIM) which are based on edges, slopes, and levels of ambient noise. It is possible to categorize the various edge detection systems and gain a better understanding of the value and constraints of the performance measures employed by combining the findings of the evaluation with those from other related publications. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of AI based Kisan Se Kisan Tak (KSKT) Mobile App

Design and Implementation of AI based Kisan Se Kisan Tak (KS...

引用

2022 International Mobile and Embedded technology Conference, MECON 2022

作者： Vashista, Siddharth Dubey, Ashwani Kumar Goyal, Ayush Vashisth, Rashmi Amity University Uttar Pradesh Amity School of Engineering Technology UP Noida201313 India Texas AM University Frank H. Dotterweich College of Engineering Department of Electrical Engineering and Computer Science Kingsville United States Amity Institute of Information Technology Amity University Uttar Pradesh UP Noida201313 India

ISBN: (纸本)9781665420204

AI-based technology helps increases the efficiency in all fields of the agriculture sector such as harvest, irrigation, soil content sensing, monitoring, and agricultural robots. With a jumping global population, the agricultural sector faces the crisis, but the AI has the potential to provide a very necessary solution. The proposed Kisan Se Kisan Tak (KSKT) program includes a Chatbot that can answer farmers questions and provide accurate weather forecasts so that they can plan accordingly. Agriculture is predicted to generate major part of the revenue by 2050. Agricultural monitoring is so extensive that it necessitates decreasing humans in practice. The developed application begins with the weather forecasting app. The user may input their chosen location here, and the App will use the API to give them with all weather updates. The state of the app will be saved due to shared preferences. The KSKT application's functionalities were surveyed and a feedback of over 50 people was taken. The research work for the application is to provide ease to farmers and workers based on demographic information using API's, and it can automatically analyze the soil status i.e., humidity, pH values. © 2022 IEEE.

关键词： Weather forecasting

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：