检索结果-内蒙古大学图书馆

2nd International Conference in Civil engineering for a Sustainable Planet, ICCESP 2024

作者： Abhijith, R.P. Christy, Freeda Simi, M.R. Renju, C.M. Dept. of Civil Engineering Kalasalingam Academy of Research and Education India Dept. of Civil Engineering Mahaguru Institute of Technology India Dept. of Civil Engineering Marian Engineering College India

ISBN: (数字)9780784486047

ISBN: (纸本)9780784486047

The integrated use of Internet of Things (IoT) and machine learning (ML) in automated traffic signal systems marks a significant leap forward in optimizing urban traffic flows. By leveraging real-time data gathered from interconnected devices and applying advanced machine learning algorithms, these systems can dynamically adjust traffic signals to enhance efficiency and alleviate congestion. This technological innovation underscores the transformative potential of incorporating state-of-the-art technologies into urban traffic management practices. However, despite the promising advantages offered by IoT and machine learning, several implementation challenges are also be addressed. That includes ensuring the secure and reliable transmission of the data across interconnected devices, managing the scalability of the system to accommodate varying traffic volumes and urban environments, and effectively handling the complexity of real-time decision-making processes. Going through these types of challenges is very severe for the widespread adoption and successful deployment of automated traffic signal systems powered by IoT and machine learning. Continuous research and development efforts are essential to refine algorithms, improve data integration capabilities, and validate system performance in diverse real-world conditions. By overcoming these hurdles, cities can unlock the full potential of automated traffic signal systems to create more efficient, sustainable, and liveable urban environments. © ASCE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Spiking Attention Recurrent Neural Network for EEG-Based Motor Imagery Classification

Spatio-Temporal Spiking Attention Recurrent Neural Network f...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Lim, Jin-Gyo Kim, Seong-Eun Seoul National University of Science and Technology Dept. Defence AI Convergence Engineering Seoul Korea Republic of Seoul National University of Science and Technology Dept. Applied Artificial Intelligence Dept. Defence AI Convergence Engineering Seoul Korea Republic of

ISBN: (纸本)9798331510756

Motor Imagery (MI), a primary research domain of brain-computer interface (BCI) studies, focuses on the recording and analysis of brain activity related to imagined movements, primarily using electroencephalography (EEG). Recent advance-ments in deep learning have significantly enhanced EEG-based MI classification. New challenges, raised with increasing interest in developing low-power neuromorphic devices, brought the demand for spiking neural networks (SNNs), which promise efficient MI classification with reduced energy requirements. However, the application of SNNs to EEG-based MI classification remains relatively unexplored. In this study, we propose a novel approach that integrates spatio-temporal spike encoding with an attention recurrent neural network (ARNN), referred to as spiking ARNN (SARNN). This architecture is designed to capture both the spatial dependencies across EEG channels and the temporal dynamics within the EEG signals, enabling more robust feature extraction and classification. Our method achieved an accuracy of 78.46% on the benchmark BCI Competition IV 2a dataset, demonstrating substantial improvements in MI classification performance and emphasizing the potential of SNNs in BCI applications. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Algorithm for the Travelling Sales Man problem 3

An Evolutionary Algorithm for the Travelling Sales Man probl...

引用

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

作者： Waseem, Shaik Mohammad Jeshwanth, N.L. Lingesh, A. Jayanth, Matta Bhargavi, C.H. Dhanwanth, Batini Dept. of Computer Science and Engineering Chennai India Dept. of Artificial Intelligence and Data Science Chennai India Sai Spurthi Institute of Technology Dept. of Computer Science and Engineering Gangaram Sathuaplly India Jönköping University Dept. of Ai Engineering Jönköping Sweden

ISBN: (纸本)9798331509675

This study explores the use of Genetic Algorithms (GA) to solve the NP-hard combinatorial optimization problem known as the Travelling Salesman Problem (TSP). The suggested GA, called GA-P, performs better than conventional techniques because it uses a new randomized crossover threshold. According to experimental assessments, GA-P outperforms a normal Genetic Algorithm with fixed crossover (GA-N, 628.6) and approaches the best Branch and Bound solutions (B&B, 560.6) with an average cost of 617.4 for 16-node graphs. With average execution times of 0.1347 seconds for 16 nodes, GA-P also demonstrates constant computational efficiency, outperforming B&B's exponentially growing temporal complexity (169.37 seconds for 16 nodes). In order to balance solution quality and computational cost, hyperparameter tweaking revealed the ideal values of population percentage (pp = 1.1), crossover proportion (cp = 0.8), mutation threshold (mt = 0.3), and exploration probability (ep = 0.2). The results show that GA-P is a scalable and efficient substitute for TSP, with room for improvement via parallelization and exploratory techniques. © 2025 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Optimizing Crop Recommendation through Stacking and Feature Analysis of Ensemble Classifiers 5

Optimizing Crop Recommendation through Stacking and Feature ...

引用

5th International Conference on Emerging systems and Intelligent Computing, ESIC 2025

作者： Mahapatro, Pradeep Kumar Panigrahi, Rasmita Padhy, Neelamadhab School of Engineering and Technology Dept. of Cse Odisha Gunupur India

ISBN: (纸本)9798331522100

Farming is the source to increase agricultural productivity. Modern precision farming depends on a crop recommendation system which is used by some data-driven methods to predict a suitable crop based on the environmental conditions. To improve the accuracy of forecasting the model combines feature analysis with stacking ensemble approaches. This model also integrates with random forest (RF), gradient boosting, and XGboost. Selecting feature analysis techniques, the model assesses parameters like soil type, temperature, rainfall, and pH level. Based on soil and climate conditions the stacked model provides reliable suggestions to the farmer in making decisions for environmentally friendly farming. The main objective of this paper is to optimize the crop based on the stacking Regressor as well as the ensemble classifier. Nine machine learning classifiers are used to achieve it but among all RF classifiers outperform i.e. accuracy of 0.995455, precision of 0.995671, and recall of 0.995455. Apart from these we also used the filter-based selection (correlation) and wrapper-based selection (RFE) to provide top models for crop recommendation. The top 3 performers (Random Forest, Extra Trees, and XGBoost) are used to make an ensemble for optimizing the crop. © 2025 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of the Proposed Isolated LLC Resonant Converter with PFM Control 12

Performance Analysis of the Proposed Isolated LLC Resonant C...

引用

12th Iranian Conference on Renewable Energies and Distributed Generation, ICREDG 2025

作者： Dashti, Mohammad Reza Asadi, Mehdi Ebrahimi, Faezeh Shoghy, Omid Arak University of Technology Dept. Electrical Engineering Arak Iran

ISBN: (纸本)9798331525132

This article introduces a DC-DC converter designed for various applications, including battery chargers and electric vehicles. The input stage features an EMC/EMI filter to mitigate noise. A Power Factor Correction (PFC) circuit efficiently converts 220 V AC power into 400 V DC for the DC-DC converter's input. The converter utilizes a PID controller and Pulse Frequency (PF) modulation for switching control. This modulation technique adjusts the switching frequency in response to changes in load or input voltage, ensuring output voltage stability while maintaining high system efficiency across different load conditions. Simulation results validate the proposed converter design's effectiveness, demonstrating its ability to maintain a stable output voltage under varying conditions. © 2025 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Soil Properties and Climate Conditions on Crop Yield Prediction 5

Analyzing the Impact of Soil Properties and Climate Conditio...

引用

5th International Conference on Emerging systems and Intelligent Computing, ESIC 2025

作者： Arangi, Dasaradha Panigrahi, Rasmita Padhy, Neelamadhab School of Engineering and Technology Dept. of Cse Odisha Gunupur India

ISBN: (纸本)9798331522100

In this paper, we aim to predict the suitable crop using machine learning repressors. Predicting the right crop is one of the challenging tasks because the different soil conditions can improve agricultural output. Predicting the right crop may help to increase agricultural productivity, optimize resource utilization, and promote sustainability. In this study, we considered the different features like Nitrogen (N), Phosphorus (P), Potassium (K), pH, electrical conductivity (EC), organic carbon (OC), and various micronutrients. Our model recommends a suitable crop for the given set of features. Material/Method: The machine learning Regressor classifiers (Linear Regressor, Random Forest Regressor, Support vector Regressor, XGBoost Regressor, Gradient Boosting Regressor, LightGBM, CatBoost, and stacked Regressor) are used. During implementation, we have estimated the performance of metrics like: - Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) to assess the accuracy of the model. Result: The experimental observation reveals that the Stacked Regressor performed very well compared to other classifiers. It has the lowest MAE (3.282), MSE (14.633), and RMSE (3.825) as well as the highest R-squared value of 0.170567. Other classifiers are also exhibited well but they are not up to the mark to select as the best classifiers. A stacked regressor is one of the ensemble learning approaches that enhance the model ability and choose the suitable crop based on soil properties. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust Speech Encoding system Under Noisy Environments 3

Robust Speech Encoding System Under Noisy Environments

引用

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Thimmaraja Yadava, G. Nagaraja, B.G. Monisha, C. Revanth, K.L. Siri, S. Nitte Meenakshi Institute of Technology Dept. of Electronics & Communication Engineering Karnataka Bengaluru India Vidyavardhaka College of Engineering Dept. of Electronics & Communication Engineering Karnataka Mysuru India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508456

Speech encoding systems serve as fundamental components of wireless communication systems. Linear predictive coding (LPC)-based encoding is the most popular technique, primarily due to its simplicity. However, while LPC performs well in noise-free conditions, its performance deteriorates significantly in noisy environments. Over the years, numerous algorithms have been proposed to address real-time encoding issues, but their effectiveness diminishes considerably in the presence of background noise. In this work, we first analyze four state-of the-art enhancement techniques based on estimators of the signal magnitude spectrum. Subsequently, we propose a novel technique designed to enhance the robustness of speech encoding systems under noisy conditions. Our proposed system incorporates a background noise suppression module utilizing the soft mask estimator with a priori SNR uncertainty (SMPR). This module is integrated into the system prior to LPC-based encoding. The effectiveness of the proposed encoding system is evaluated using NOIZEUS speech data across four noise types and varying noise levels. Experimental results demonstrate significant improvements in encoding performance, highlighting the system's ability to maintain robustness in noisy environments. © 2025 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

COMPARATIVE ANALISIS OF DIFFERENT CONFIGURATION OF HEAT PUMPS OPERATING WITH NATURAL REFRIGERANTS

引用

UPB Scientific Bulletin, Series D: Mechanical engineering 2025年第1期87卷 47-58页

作者： Talaba, Ovidiu Serban, Alexandru Doctoral School of Mechanical Engineering and Mechatronics National University of Science and Technology POLITEHNICA Bucharest Romania Dept. of Applied Thermodynamics National University of Science and Technology POLITEHNICA Bucharest Romania

The article compares, based on the exergetic analysis, the performances of a cogeneration system for heating and air conditioning that works with CO2 or NH3. The analyzed refrigeration schemes are in two stages. The most efficient scheme for NH3 was the one with flash intermediary cooling (COPNH3=5.79, ɳexNH3=0.42) and for CO2, the one with intermediary cooling through the injection of saturated gas at intermediate pressure in the gas stream discharged by the first compression stage (COPCO2 =3.56 and ɳexCO2=0.29). © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Smart Vehicle Procurement system using Blockchain technology 3

Smart Vehicle Procurement System using Blockchain Technology

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kumar, Boddu Manoj Rajeswari, G. Duraipandian, Kavitha David, Shiela Dept. of Computer Science and Engineering with specialization in Blockchain Technology Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India

ISBN: (纸本)9798331527549

Blockchain technology has become more widespread in our lives revolutionizing various industries through improved security, transparency, and operational efficiency. Its decentralized ledger system is particularly effective in areas like finance and supply chain management ensuring data integrity and reducing the need for middlemen. This study explores how blockchain technology is used in the process of buying vehicles highlighting its benefits compared to methods. Traditional vehicle purchases involve a network of dealers, banks and regulators leading to inefficiencies, higher costs and potential fraud. The usual process involves steps like financing checking vehicle history and changing ownership. Each requiring extensive paperwork and third-party intervention. In contrast using blockchain for vehicle purchases can simplify things through contracts that automate tasks like verifying history securely transferring ownership instantly settling payments. The unchangeable nature of records ensures that all transaction data remains secure against tampering fostering trust between buyers and sellers. Furthermore, blockchain can cut costs significantly by removing the need for middlemen such, as escrow services and title companies while reducing burdens. The advanced security elements built into technology help reduce the chances of fraudulent actions like altering odometer readings or selling stolen cars. This study showcases a comparison illustrating how blockchain can simplify the process of buying vehicles offering an economical and secure experience. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Interactions of Viral Pathogenic Waste with Clays for Containment Applications

Interactions of Viral Pathogenic Waste with Clays for Contai...

引用

Geo-EnvironMeet 2025: Geoenvironmental Contamination and Waste Containment

作者： Yadav, Himanshu Bharat, T.V. Kumar, Sachin Dept. of Civil Engineering Indian Institute of Technology Guwahati Guwahati India Dept. of Biosciences and Bioengineering Indian Institute of Technology Guwahati Guwahati India

ISBN: (数字)9780784485699

Pathogenic waste generated during pandemics creates large quantities of biomedical waste (BMW) in the form of masks, personal protective kits, etc. This waste is generally disposed of municipal solid waste (MSW) landfills in the absence of exclusive BMW disposal facilities. The geosynthetic clay liners (GCLs) contain macro-voids in granular bentonite (GB), which do not seal in a salt environment from leachate due to loss in osmotic potential. Such behaviour of the GB might lead to the advection-controlled movement of viral pathogens through GCLs in the presence of leachates. Safe disposal of viral-infected waste in MSW landfills requires an understanding of the interactions of viral pathogens with the clays. The present study evaluated the interaction energy profiles of virus-clay system by considering sphere plate-type arrangement. Furthermore, the study also evaluated the sorption characteristics of coronavirus surrogate with different clays. Factors controlling virus-clay interactions such as interaction period, clay dosage, and clay type were investigated. The viruses were greatly attenuated by both clays (Bentonite and Kaolin). The virus sorption kinetics of these clays were evaluated to understand how fast viruses attenuate to studied clays. Batch sorption studies were conducted to evaluate the percentage reduction in the viral load of samples. Furthermore, the maximum sorption ability and retardation factor of the clays for the studied virus were evaluated and presented. © ASCE.

关键词： Municipal solid waste

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：