检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Sugunadevi, C. Maheswari, B. Uma Cmr Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India Bengaluru Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering India

ISBN: (纸本)9798350390759

Leaf disease frequently arises as pears plants mature. With a particular emphasis on categorizing the pear leaf disease, the proposed research work suggests the implementation of the CNN architecture that we use in this study to create this disease identification and classification method comprised of ResNet50, InceptionV3, VGG16, and VGG19. These neural networks have been pre-trained on the ImageNet dataset. The ensemble methodology that we describe produces final predictions for the test samples based on the recall, precision, accuracy, and f1-score scores of four standard evaluation metrics. Even though there is an increase in the amount of accuracy when the models are ensembled, the remarkable combination is InceptionV3 with VGG16 with an accuracy of 77.25%, precision of 79.34%, recall of 77.25% and F1 score of 76.50% and with the severity classification as accuracy 45.29%, precision 46.88%, recall 45.29% and F1 score 45.50% respectively. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Channel assignment and power allocation for throughput improvement with PPO in B5G heterogeneous edge networks

引用

Digital Communications and Networks 2024年第1期10卷 109-116页

作者： Xiaoming He Yingchi Mao Yinqiu Liu Ping Ping Yan Hong Han Hu The College of Computer and Information Hohai UniversityNanjingChina The Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai UniversityNanjing China The School of Computer Science and Engineering Nanyang Technological UniversitySingapore The College of Textile and Clothing Engineering Soochow UniversitySuzhouChina The College of Internet of Things Nanjing University of Posts and TelecomurunicationsNanjingChina

In Beyond the Fifth Generation(B5G)heterogeneous edge networks,numerous users are multiplexed on a channel or served on the same frequency resource block,in which case the transmitter applies coding and the receiver uses interference ***,uncoordinated radio resource allocation can reduce system throughput and lead to user inequity,for this reason,in this paper,channel allocation and power allocation problems are formulated to maximize the system sum rate and minimum user achievable *** the construction model is non-convex and the response variables are high-dimensional,a distributed Deep Reinforcement Learning(DRL)framework called distributed Proximal Policy Optimization(PPO)is proposed to allocate or assign ***,several simulated agents are trained in a heterogeneous environment to find robust behaviors that perform well in channel assignment and power ***,agents in the collection stage slow down,which hinders the learning of other ***,a preemption strategy is further proposed in this paper to optimize the distributed PPO,form DP-PPO and successfully mitigate the straggler *** experimental results show that our mechanism named DP-PPO improves the performance over other DRL methods.

关键词： B5G Heterogeneous edge networks PPO Channel assignment Power allocation Throughput

来源：评论

学校读者我要写书评

暂无评论

Integrating Entropy-Based Classification into Hyper Spectral Images for Improved Object Identification

Integrating Entropy-Based Classification into Hyper Spectral...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Singh, Vishvendra Pawar, Rahul Chaudhary, Pavan Vivekananda Global University Department of Agriculture Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

this paper gives a method to integrate entropy-primarily based type, a device mastering technique, into hyperspectral images for advanced item identity. Entropy-based total classification utilizes entropy, a degree of uncertainty or unpredictability in a gadget, to categorize facts into one-of-a-kind sub-categories. By combining entropy-based categories with hyperspectral photos, the accuracy of item identity can be improved because of the accelerated decision of the facts. The paper outlines the steps to use the entropy-based type in the hyperspectral images and then discusses the consequences. In the experiments performed, a massive improvement in the accuracy of object identity turned into location. It indicates the effectiveness of the proposed method and, in addition, demonstrates its capacity for use in diverse applications. © 2024 IEEE.

关键词： categories improvement integrate entropy uncertainty unpredictability

来源：评论

学校读者我要写书评

暂无评论

Secure Energy-Efficient Resource Allocation and Relay Selection for Cooperative Communications in Wireless Sensor Networks

Secure Energy-Efficient Resource Allocation and Relay Select...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Bargavi, Manju Singh, Akhilendra Pratap Lora, Chandra Prakash Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Chemistry Jaipur India

ISBN: (纸本)9798350383348

Wireless sensor networks (WSNs) are extensively used for diverse programs, environmental tracking, healthcare, and industrial automation. The constrained electricity assets of sensor nodes in WSNs pose an undertaking to prolong the community lifetime and ensure dependable verbal exchange, specifically in harsh environments. To address this venture, cooperative communications were proposed where neighboring sensor nodes collaborate to transmit records to a base station, lowering the strength consumption of character nodes. But, security issues arise because of the capability of malicious assaults in Wesson this technical summary, we endorse a at ease electricity-efficient aid allocation and relay selection scheme for cooperative communications in WSNs. Our proposed scheme goals to acquire fundamental objectives: 1) maximizing the community lifetime via balancing the electricity consumption amongst sensor nodes, and 2) improving the safety of the community through selecting the most trusted relay node for facts transmission. We formulate an optimization hassle to collectively optimize the energy consumption and security of the network and suggest a heuristic set of rules to resolve it. © 2024 IEEE.

关键词： Industrial Malicious Maximizing Networks Objectives Programs

来源：评论

学校读者我要写书评

暂无评论

Developing an AI-Driven Chatbot for Enhanced College Website Support Using Machine Learning 4

Developing an AI-Driven Chatbot for Enhanced College Website...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Thamilselvan, R. Natesan, P. Gothai, E. Naveenkumar, S.E. Shanthosh, J.K. Vigneshwaran, S. Kongu Engineering College Computer Science and Engineering Erode India Kongu Engineering College Information Technology Erode India

ISBN: (纸本)9798350385793

With the emerging technological revolutions, the higher education institutions are integrating Artificial Intelligence (AI) to enhance their website support and user experience. A GPT-2-based chatbot has been developed to assist students, faculty, and stakeholders in navigating the college websites easily. The objective of this research study is to support college websites by interacting with user queries and predicting the cut-off mar of the students based on their academic performance. This AI-driven chatbot employs machine learning and Natural Language Processing (NLP) techniques to address the inquiries regarding admissions, course details, academic resources, administrative procedures, and campus life. Utilizing deep learning techniques, the developed chatbot delivers comprehensive and contextually relevant responses, focusing on Q&A interactions. The chatbot, built upon the GPT -2 model by OpenAI, is skillful at generating human-like text and serves various applications, including customer support and information retrieval systems. Particularly, it specializes in predicting admission cut-off marks, employing regression models such as Linear Regression, Decision Tree Regressor, SVM Regressor, Random Forest Regressor, and XGBoost Regressor. These models consider various factors such as joining year, quotas, previous cut-off lists, department preferences, board exam difficulty, job market demands, and academic performance. The performance evaluation metrics like Mean Squared Error (MSE), Root Mean Square Error (RMSE), and R-squared are utilized to assess the predictive accuracy of the proposed chatbot. By performing a thorough analysis of historical student data, the chatbot provides users with detailed answers and accurate forecasts regarding future academic performance, thereby enhancing the overall user experience of educational websites. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Investigating the Use of Deep Learning Networks to Classify Cardiovascular Diseases

Investigating the Use of Deep Learning Networks to Classify ...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Karthikeyan, M.P. Chaudhary, Pavan Dheer, Meenakshi Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Agriculture Jaipur India

ISBN: (纸本)9798350383348

The potential of deep gaining knowledge of networks for the motive of recognizing and classifying cardiovascular diseases has been increasingly studied. Specifically, convolutional neural networks (CNNs) and different types of deep learning have been leveraged to diagnose diverse sorts of cardiovascular illnesses, inclusive of coronary artery ailment (CAD) and atrial fibrillation (AF). Recent research has proven promising outcomes for the potential of those networks to perceive sickness signatures within the electrocardiograms (ECGs) of individuals, in addition to assisting the class of coronary vein imaging (CVI) and assessing the severity of signs and symptoms. Similarly, other techniques for recognizing cardiovascular illnesses, including stroke detection from ECG signals, have shown promising outcomes. But, similarly, paintings desire to be finished to enhance the accuracy of these structures by actively exploring specific types of information, along with cardiovascular hazard and lifestyle facts, for you to enhance prediction overall performance. Similarly, research is likewise essential to evaluate the capacity of options to deep gaining knowledge consisting of machine getting to know and deep reinforcement getting to know for recognizing and classifying cardiovascular sicknesses. Overall, because the fee of deep learning networks has grown to be more and more clean inside the healthcare setting, there may be an opportunity to keep exploring them for figuring out cardiovascular illnesses and helping physicians make correct diagnoses. Deep learning networks are a promising platform for developing ailment classification models. The use of deep studying networks for classifying cardiovascular diseases has been the topic of many research studies. This research has centered on using deep neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) to build and teach models that can appropriately discover and diagnose cardiovascular il

关键词： creation engineering functions generate increasingly

来源：评论

学校读者我要写书评

暂无评论

Improved Multi-Path Routing for QoS on MANET

引用

computer Systems science & engineering 2023年第6期45卷 2521-2536页

作者： M.Vargheese Surbhi Bhatia Shakila Basheer Pankaj Dadheech Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl HasaSaudi Arabia Department of Information Systems College of Computer and Information SciencePrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&Gramothan(SKIT)Jaipur302017RajasthanIndia

A Mobile Ad hoc NETwork(MANET)is a self-configuring network that is not reliant on *** paper introduces a new multipath routing method based on the Multi-Hop Routing(MHR)*** is the consecutive selection of suitable relay nodes to send information across nodes that are not within direct range of each *** to ensure good MHR leads to several negative consequences,ultimately causing unsuccessful data transmission in a *** research work consists of three *** first to attempt to propose an efficient MHR protocol is the design of Priority Based Dynamic Routing(PBDR)to adapt to the dynamic MANET environment by reducing Node Link Failures(NLF)in the *** is achieved by dynamically considering a node’s mobility parameters like relative velocity and link duration,which enable the next-hop *** method works more efficiently than the traditional *** the second stage is the Improved Multi-Path Dynamic Routing(IMPDR).The enhancement is mainly focused on further improving the Quality of Service(QoS)in MANETs by introducing a QoS timer at every node to help in the QoS routing of *** QoS is the most vital metric that assesses a protocol,its dynamic estimation has improved network performance *** method uses distance,linkability,trust,and QoS as the four parameters for the next-hop *** is compared against traditional routing *** Network Simulator-2(NS2)is used to conduct a simulation analysis of the protocols under *** proposed tests are assessed for the Packet Delivery Ratio(PDR),Packet Loss Rate(PLR),End-to-End Delay(EED),and Network Throughput(NT).

关键词： Multi-path routing quality of service node-link failure packet delivery ratio

来源：评论

学校读者我要写书评

暂无评论

Classification Inconsistency Alignment Network for Cross-corpus Speech Emotion Recognition

Classification Inconsistency Alignment Network for Cross-cor...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhou, Xiaoyan Li, Jiajie Yu, Qida Wu, Quan School of Electronics and Information Engineering Nanjing University of Information Science and Technology Nanjing China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9798350368741

Cross-corpus speech emotion recognition (SER) aims to transfer emotional information from a labeled source corpus to an unlabeled target corpus. Due to the characteristics of each corpus, models trained on source domain may classify target samples into incorrect categories, resulting in classification inconsistency problem. Therefore, this paper proposes classification inconsistency alignment network (CIAN). The core idea of CIAN is to construct two complementary and adversarial classifiers to optimize the decision boundary. Herein, primary classifier extracts discriminative emotional features by bridging source samples and corresponding labels. Then, the auxiliary classifier focuses on misclassified samples arising from domain discrepancy. Through the interaction of two classifiers, CIAN can identify all samples prone to inconsistent classification, thereby enhancing classification consistency while domain adaptation. Extensive experiments based on three public emotion corpora demonstrate that CIAN outperforms existing advanced methods in cross-corpus SER tasks. © 2025 IEEE.

关键词： Cross-corpus speech emotion recognition deep learning speech emotion recognition (SER) transfer learning unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Domain-Adversarial Training (DANN) with Invariant Risk Minimization (IRM) Hybrid Approach 3

Breast Cancer Detection using Domain-Adversarial Training (D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Akash, K.V. Daniel, Esther Seetha, S. Durga, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India Cmr Institute of Technology Department of Information Science & Engineering India Amrita Vishwa Vidyapeetham Tifac Core in Cyber Security Amrita School of Engineering India

ISBN: (纸本)9798331509675

The breast cancer detection performs a key function in the health care network. The precise and early detection of cancer in the breast could aid to save life of the sufferer. The traditional machine learning methods struggle due to the data used to train is different from data used later this is known as Domain shifts. This project uses a hybrid model known as Domain-Adversarial Training of Neural Networks (DANN) with Invariant Risk Minimization (IRM) Hybrid Method to identification of the tumor in the breast. Through integrating the (DANN) and IRM works perfectly among the various type of data and also with the various image from the various sources. This model is more precise and reliable than any other older *** that this model act as an effective tool for detecting the breast cancer in the early stages. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-Model Gradient Boosting Techniques for Workforce Enablement: A Transparent Framework for Task Management and Issue Resolution

Leveraging Multi-Model Gradient Boosting Techniques for Work...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Rithani, M. Kumar, Mahendira S. Kumar, Sudeesh V. Kumar, Praveen S. Priyadharshan, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Information and Technology SRM Institute Of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9798350374933

In the rapidly shifting workplace environment, fostering an inspiring and dynamic atmosphere is essential for organizational success. This paper introduces an innovative Workforce Enhancement Platform designed to improve transparency, teamwork, and communication within the team. The platform employs state-of-the-art techniques for analyzing textual data, utilizing Gradient Boosting Machines (GBM) such as XGBoost, LightGBM, and CatBoost, to evaluate and categorize worker-submitted issues. It features a comprehensive data cleaning procedure to remove extraneous elements like markup and special symbols, followed by converting the processed text into actionable features using methods such as term frequency and inverse document frequency. Central to the system is the application of GBM algorithms, which detect and classify the emotional tone of the reports, distinguishing between positive and negative sentiments. Furthermore, the platform incorporates advanced data visualization tools to provide an in-depth analysis of model performance, including accuracy metrics, confusion matrices, and feature importance evaluations. By optimizing the identification and classification of workplace issues, the platform facilitates effective resolution, fostering a setting of innovation and teamwork. The main goal of the platform is to boost staff engagement and support by addressing challenges proactively, thereby promoting both individual growth and collective progress. This comprehensive approach ensures that team members’ feedback is acknowledged and valued, ultimately contributing to a more positive and productive organizational environment. © 2024 IEEE.

关键词： Empowerment of personnel

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：