检索结果-内蒙古大学图书馆

ddPG-E2E: A Novel Policy Gradient Approach for End-to-End Communication Systems

IEEE Transactions on Cognitive Communications and Networking 2024年第3期11卷 1738-1751页

作者： Zhang, Bolun Huynh, Nguyen Van Hoang, dinh Thai Nguyen, diep N. Pham, Quoc-Viet University of Warwick School of Engineering CoventryCV4 7AL United Kingdom University of Liverpool Department of Electrical Engineering and Electronics LiverpoolL69 3GJ United Kingdom University of Technology Sydney School of Electrical and Data Engineering SydneyNSW2007 Australia The University of Dublin School of Computer Science and Statistics Trinity College Dublin DublinD02 PN40 Ireland

The End-to-end (E2E) learning-based approach has great potential to reshape the existing communication systems by replacing the transceivers with deep neural networks. To this end, the E2E learning approach needs to assume the availability of prior channel information to mathematically formulate a differentiable channel layer for the back-propagation (BP) of the error gradients, thereby jointly optimizing the transmitter and the receiver. However, accurate and instantaneous channel state information is hardly obtained in practical wireless communication scenarios. Moreover, the existing E2E learning-based solutions exhibit limited performance in data transmissions with large block lengths. In this article, these practical issues are addressed by our proposed deep deterministic policy gradient-based E2E communication system. In particular, the proposed solution utilizes a reward feedback mechanism to train both the transmitter and the receiver, which alleviates the information loss of error gradients during BP. In addition, a convolutional neural network-based architecture is developed to mitigate the curse of dimensionality problem when transmitting messages with large block lengths. Extensive simulations then demonstrate that our proposed solution can not only jointly train the transmitter and the receiver simultaneously without requiring prior channel knowledge but also can obtain significant performance improvement compared to state-of-the-art solutions. © 2015 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Study of Power dynamic System and Synchronous Machine Modeling 5

Study of Power Dynamic System and Synchronous Machine Modeli...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Tirmizi, Mohammed Maahir L.D. College of Engineering Department of Electrical Engineering Gujarat Ahmedabad India

ISBN: (纸本)9798350398267

Synchronous machine research has made use of a range of models and formulations. In a wide range of applications, direct interface to external circuitry is made possible by a number of model formulations, and this work provides a coherent derivation of those multiple model formulations. Greater precision, fewer time steps, and a quicker execution time can be obtained by selecting the formulation with the best interface for the simulation scenario. Analysis of the dynamic behavior of the power system has become increasingly important recently. The demand for more flexible interchange transactions is a major driver of this trend toward the utilization of transmission networks. While dynamics and stability have been researched extensively in respect to the long-term design and planning, it is becoming increasingly apparent that similar research must also be conducted in reference to operational cycles that occur more frequently (weekly or even daily). The operating theory of synchronous machines was investigated, along with some of its important applications in power systems. © 2022 IEEE.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Predictive Management of EV Charging Stations Using Machine learning 10

Predictive Management of EV Charging Stations Using Machine ...

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Alex david, S. Begum, Almas Hemalatha, d. Senthil, K. Monikaa, R. Ruth Naveena, N. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Easwari Engineering College Department of Computer Science and Engineering Chennai India Hindustan Institute of Technology & Science Department of Mathematics Chennai India

ISBN: (纸本)9798350353778

Based on experimental results the predictive accuracy of Random Forest, decision Tree, and XGBoost was much higher than the linear Regression algorithm in EV Charging Management using machine learning models. Random Forest handled the charging station dynamics well, and the complex data relationships were managed easily with XGBoost. On the other hand, linear Regression performed better because results displayed high errors and its model fit numbers were not significant. In contrast, the decision Tree has glaring issues with overfitting and generalization. The results highlight the importance of advanced data science methods for efficient EV infrastructure management by yielding exact forecasts about demand and energy consumption behaviors. Future endeavors will continue to build upon these models, increasing the scale of analysis and providing state-of-the-art solutions towards developing an approach for both scalable development as well as a push toward more sustainable transportation with improved operational efficiencies and reliability within EV networks. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A deep reinforcement learning Approach for Early detection of tomato plant disease using CNNs and machine learning Techniques 4

A Deep reinforcement Learning Approach for Early Detection o...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Kumar, Amit Ekvitayavetchanukul, Pongkit donda, Prashanth Gupta, Anurag Sachdeva, Vrinda Singh, Bakshish Ajay Kumar Garg Engineering College Department of Information Technology Ghaziabad India The Board of Khonkaen University Affairs Khonkaen University Thailand CVR College of Engineering Department of Csit Hyderabad India Abes Engineering College Department of Computer Engineering Ghaziabad India G.L Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida India Raj Kumar Goel Institute of Technology Department of Information Technology Ghaziabad India

ISBN: (纸本)9798350364729

The present research attempts to improve tomato plant disease early detection strategies by using a variety of machine learning models, such as Recurrent Neural Networks (RNN), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Convolutional Neural Networks (CNN). Using the special advantages of these models, the major objective is to correctly diagnose diseases like Early blight, Bacterial leaf spot, Bacterial wilt, and leaf curl. The work expands the foundation for disease detection by careful dataset construction, feature extraction, and preprocessing. The accuracy of CNN is the greatest at 97.5%, followed by SVM at 92.2%), KNN at 88.4%), and RNN at 86.2%. The results show remarkable accuracy. Our research demonstrates the promise of machine learning in precision agriculture by providing a useful tool for managing and diagnosing diseases early on, increasing crop output, and encouraging environmentally friendly farming methods. © 2024 IEEE.

关键词： deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Optimized-lSTM Models Using Tree-Structured Parzen Estimator for Traffic Flow Forecasting in Intelligent Transportation

引用

computers, Materials & Continua 2025年第5期83卷 3369-3388页

作者： Hamza Murad Khan Anwar Khan Santos Gracia Villar luis Alonso dzullopez Abdulaziz Almaleh Abdullah M.Al-Qahtani Department of Electronics University of PeshawarPeshawar25120KPKPakistan Department of Project Management(L.A.D.L) Higher Polytechnic School(S.G.V)Universidad Europea del AtlanticoSantander39011Spain Faculty of Engineering Universidad Internacional IberoamericanaCampeche24560Mexico Faculty of Engineering Universidade Internacional do CuanzaCuitoEN250BieAngola Department of Project Management Universidad Internacional IberoamericanaCampeche24560Mexico Department of Project Management Department of Management SciencesUniversid de La RomanaLa Romana22000Dominican Reublic Information Systems Department College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia Department of Electrical and Electronic Engineering College of Engineering&Computer ScienceJazan UniversityJazan45142Saudi Arabia

Traffic forecasting with high precision aids Intelligent Transport Systems(ITS)in formulating and optimizing traffic management *** algorithms used for tuning the hyperparameters of the deep learning models often have accurate results at the expense of high computational *** address this problem,this paper uses the Tree-structured Parzen Estimator(TPE)to tune the hyperparameters of the long Short-term Memory(lSTM)deep learning *** Tree-structured Parzen Estimator(TPE)uses a probabilistic approach with an adaptive searching mechanism by classifying the objective function values into good and bad *** ensures fast convergence in tuning the hyperparameter values in the deep learning model for performing prediction while still maintaining a certain degree of *** also overcomes the problem of converging to local optima and avoids timeconsuming random search and,therefore,avoids high computational complexity in prediction *** proposed scheme first performs data smoothing and normalization on the input data,which is then fed to the input of the TPE for tuning the *** traffic data is then input to the lSTM model with tuned parameters to perform the traffic *** three optimizers:Adaptive Moment Estimation(Adam),Root Mean Square Propagation(RMSProp),and Stochastic Gradient descend with Momentum(SGdM)are also evaluated for accuracy prediction and the best optimizer is then chosen for final traffic prediction in TPE-lSTM *** results verify the effectiveness of the proposed model in terms of accuracy of prediction over the benchmark schemes.

关键词： Short-term traffic prediction sequential time series prediction TPE tree-structured parzen estimator lSTM hyperparameter tuning hybrid prediction model

来源：评论

学校读者我要写书评

暂无评论

Implementing Real-Time Analytics for Enhanced Energy Efficiency in IoT-Integrated Smart Grid Systems 10

Implementing Real-Time Analytics for Enhanced Energy Efficie...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Kanimozhi, K.V. Neelaveni, P. Seethalakshmi, K. Rao, N.Venkatesvara Prabhu, M. Naganathan, Suresh Babu Thandullu Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Information Technology Chennai Thandalam India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India J.N.N.Institute of Engineering Department of Computer Science and Engineering Kannigaipair Chennai India Mohamed Sathak College of Arts and Science Department of Computer Science Tamil Nadu Chennai India Adhiparasakthi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

This paper develops the contemporary role of real-time analytics combining IOT-enabled smart grid systems in order to improve energy efficiency, strengthen grid dependability and privacy sustainability. With help of the set of sensors data analyzed in real-time coming from the smart grid environment, the study will be focused on the energy consumption patterns, demand response efficiency, decision-making ability of predictive maintenance and security threats' detection rate. The findings emphasize a pattern of energy usage which reflects the current scenario as well as the requirements to develop demand response initiatives that are effective in stabilizing energy excesses during peak demand and encourage energy economizing. Firstly, the implementations of predictive maintenance confirm that real-time data analytics effectively sets proactive maintenance appointments thereby, scheduling minimal on-and-offs leading to extended life-span of the equipment. Also, the ripple effect of the recognized cybersecurity threats emphasizes the need for an ongoing monitoring and a substitute of the strong-security system for smart grid infrastructure. This study, therefore, spotlights the importance of current data analytics in headway of smart grid systems' energy management and sustainability solutions, thus urgently calls for new and improved technologies advancement in smart grids and mitigating emerging energy problems. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Smart Ingenious Industrial Monitor for Hazardous Toxic Gas detection

Smart Ingenious Industrial Monitor for Hazardous Toxic Gas D...

引用

2023 International Conference for Technological engineering and its Applications in Sustainable development, ICTEASd 2023

作者： Muthusundari, S. Srujan, Chandra Siva durga Prasad, Gorrela Mohan Pathi, lakshmi Mahima, M. Alsalami, Zaid Prasanna, Yeluri lakshmi R.M.D. Engineering College Dept of Computer Science and Engineering Tamil Nadu Kavaraipettai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq GRIET Telangana Hyderabad India

ISBN: (纸本)9798350336474

Air pollution and health-related issues are closely linked, accounting for approximately 7 million premature deaths annually, along with numerous hospitalizations and sick leave days. A significant portion of these deaths occur among industrial workers exposed to high levels of various pollutants. Regular monitoring of worker health and workplace safety is crucial, especially for employees in chemical, metallurgy, and petrochemical industries who are at higher risk of illness due to constant exposure to harmful gases. This study aims to quantify and monitor toxic gases, such as carbon dioxide and carbon monoxide, released in industries using a detector device to identify gas leaks and prevent poisoning. The approach utilizes an Arduino UNO board and ESP8266 chip, along with gas and temperature sensors, to provide a continuous monitoring system and prevent unpredictable incidents. This study focuses on providing a safe environment for workers in chemical, steel, and petroleum industries by predicting toxic gas levels early. The system enabled live monitoring of temperature and toxic gas levels in the equipped industries. Industrial disasters contribute significantly to workplace uncertainties and risks. Establishing a safe workplace is crucial for all professionals in the industry. © 2023 IEEE.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Simple Network Simulator: Web based simulator for creating and visualizing computer Networks and related algorithms 7

Simple Network Simulator: Web based simulator for creating a...

引用

7th IEEE International conference for Convergence in Technology, I2CT 2022

作者： Joshi, Yashodhan Vyas, Yatharth Ghone, Tejas Soni, Vatsal Kanani, Pratik D.J. Sanghvi College of Engineering Computer Engineering Maharashtra Mumbai India

ISBN: (纸本)9781665421683

Network visualization is used widely and the existing network simulators severely are esoteric to intellects that possess a technical understanding of complex programming languages. Simple Network Simulators bridges the prerequisite knowledge gap by facilitating a web interface that demands no setup. It is easy to understand, custom-tailored and requires minimal operating knowledge. This software can be used to simulate concepts involving network protocols, packet sniffing attacks and key exchange algorithms in a visual manner that is simple to comprehend by a dilettante. This simulator also allows tracing of a packet from source to destination using colour marking, so can be used to develop and test new algorithms, and see how they process the packets. © 2022 IEEE.

关键词： Simulators

来源：评论

学校读者我要写书评

暂无评论

Revivify: A depression detection and Control System using Tweets and Automated Chatbot

Revivify: A Depression Detection and Control System using Tw...

引用

2022 IEEE World Conference on Applied Intelligence and Computing, AIC 2022

作者： Hakani, Riddhi Patil, Samiksha Patil, Sakshi Jhunjhunwala, Siddhi deulkar, Khushali Computer Engineering D. J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9781665479882

ISBN: (纸本)9781509050017

Mental Health is a stigma in India and on a global scale. Ignorance of mental health on our part has created a world where those suffering from it cannot talk about it openly and often feel uncomfortable disclosing it to others or even professional therapists. To address this problem, we propose a digital system that detects signs of anxiety and also suggests methods for depression control. Revivify performs a comprehensive analysis of a user's mental state using different techniques. We have used tweets, patient health questionnaires, depression anxiety stress scale (dASS), and personalized responses as our dataset. Our system uses Feed Forward Neural Networks, latent dirichlet Allocation, and Random Forest Classifier algorithm to classify the user responses and tweets into one of the nine levels of anxiety and depression. Random Forest Classifier gives the highest accuracy. Further, the chatbot also suggests various blogs and provides helpline numbers for damage control. This system is a cost-effective solution to detect depression. © 2022 IEEE.

关键词： decision trees

来源：评论

学校读者我要写书评

暂无评论

Enhancing face recognition performance: a comprehensive evaluation of deep learning models and a novel ensemble approach with hyperparameter tuning

引用

Soft Computing 2024年第20期28卷 12399-12424页

作者： Selvaganesan, Jana Sudharani, B. Shekhar, S. N. Chandra Vaishnavi, K. Priyadarsini, K. Raju, K. Srujan Rao, T. Srinivasa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Avadi Tamil Nadu Chennai600062 India Guntur Dist. Andhra Pradesh Vadlamudi India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and Technology Telangana Hyderabad501301 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering CMR Technical Campus Medchal Telangana Hyderabad501401 India Department of Electronics and Communication Engineering Aditya Engineering College Surampalem533437 India

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—denseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (lFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate

关键词： Convolutional neural networks

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：