检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Nisha, A.V. Rajeev, S.K. Soorya, M. Shaheer, S. Dept. of Electronics and Communication Engineering Younus College of Engineering and Technology Kerala Kollam India

ISBN: (纸本)9798331522667

Alzheimer’s Disease (AD) is an escalating neurodegenerative disorder and the leading cause of dementia, with early detection being essential for prompt action and slowing disease progression. However, due to subtle and overlapping brain deterioration patterns, early AD diagnosis is difficult. This study proposes a hybrid deep learning model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to automatically detect and classify AD from axial brain magnetic resonance imaging (MRI) images. The model uses VGG16, pre-trained on ImageNet, for feature extraction, with an LSTM layer to capture temporal dependencies in MRI slices. The dataset includes three categories: AD, Cognitively Impaired (CI), and Normal Control (NC) subjects. To improve generalization, data augmentation techniques such as median blurring and horizontal flipping were used. The model, which was trained with the Adam optimizer, achieved a test accuracy of 0.9942 and a loss of 0.030. High sensitivity and specificity were shown by the performance evaluation which included a classification report and evaluation matrix, particularly in distinguishing AD from CI cases. This hybrid CNN-LSTM model effectively leverages spatial and temporal information for early AD detection, highlighting its potential to improve automated diagnostic tools and enable timely intervention. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cryptosight: Decrypting Future Trends with LSTM, PyCaret and Jinja 2.0 1

Cryptosight: Decrypting Future Trends with LSTM, PyCaret and...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Mhatre, Soham Motiram Mishra, Brajesh Kumar Raja, Ishan Kumar Goswami, Bigit Krishna Agrawal, Sneha Upadhyay, Pranjal National Institute of Technology Dept. of Electronics and Communication Engineering Nagaland Dimapur India National Institute of Technology Dept. of Mechanical Engineering Nagaland Dimapur India National Institute of Technology Dept. of Electrical & Electronics Engineering Nagaland Dimapur India National Institute of Technology Dept. of Computer Science and Engineering Nagaland Dimapur India

ISBN: (纸本)9798350377002

The primary objective of this research is to develop and evaluate combined cryptocurrency price prediction models using Long Short-Term Memory (LSTM) neural networks along with traditional time series models and machine learning techniques like Random Forest and Linear Regression. The LSTM models will capture long-term dependencies in sequential cryptocurrency price data, while the other models provide complementary predictive capabilities. This multi-model approach aims to leverage the strengths of different techniques to improve overall prediction accuracy. Additionally, this research seeks to explore the practical application of these predictions in real-world cryptocurrency trading scenarios. The study will collect historical price data and relevant news for major cryptocurrencies from reputable sources. Data preprocessing, feature engineering, model training, hyper-parameter tuning, and evaluation using metrics like RMSE, MAE, and R-squared will be performed. The predictive performance of the LSTM-based models will be compared against baseline models, with statistical significance testing. Interpretability analysis will provide insights into the factors driving price movements. Furthermore, the research will investigate integrating the predictions into trading algorithms and evaluate their efficacy through back-testing on historical data. Limitations, challenges, and future research directions in cryptocurrency price prediction will also be discussed. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Reducing the maximum scour dept. downstream of the sluice gate using a combination of two buried plates with a sill

引用

ISH Journal of Hydraulic engineering 2024年第2期30卷 196-204页

作者： Elshahat, Elsayed M. AbdelAal, Gamal M. EL-Saiad, Atef A. Tantawy, Rana F. Water and Water Structures Eng. Dept. Faculty of Engineering Zagazig University Zagazig Egypt Civil dept Higher Institute of Engineering and Technology in Zagazig Zagazig Egypt

One of the main interests of researchers is the local scour downstream hydraulic structures due to free hydraulic jump, which can cause massive damage or collapse for hydraulic structures. In this study, a new countermeasure was developed to reduce the maximum scour dept. by using two buried plates and a sill downstream of the sluice gate. The results showed that the two buried plates were a very effective tool in reducing the maximum scour dept. downstream of the fixed apron. It was found that when the two plates were buried at (LP1/LB = 0.07 with LP2/LB = 0.14) with a sill installed at (LS/LB = 0.1 with hS/LS = 0.14), the maximum scour dept. upstream and downstream of the first plate (Ds1 and Ds2) was reduced by 57% and 64%, respectively, and the maximum scour dept. downstream of the second plate (Ds3) was reduced by 35% compared to the maximum scour dept. for the no-plate condition. An empirical formula was developed to determine the maximum scour dept.. The study results may be applied in the area of protection design for the fixed apron. © 2024 Indian Society for Hydraulics.

关键词： Scour

来源：评论

学校读者我要写书评

暂无评论

Economic and Environmental Analysis of Power system Using Multi-Objective Dragonfly Algorithm

Economic and Environmental Analysis of Power System Using Mu...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Dasgupta, Satyaki Das, Uttara Biswas, Nabendu Gope, Sadhan University of Calcutta Dept. of Applied Physics: Electrical Engineering Kolkata India Tripura University Dept. of Electrical Engineering Agartala India Tripura Institute of Technology Dept. of Electrical Engineering Agartala India National Institute of Technology Dept. of Electrical Engineering Agartala India

ISBN: (纸本)9798331540821

As urbanization accelerates, the demand for electricity rises, leading to an increased reliance on coal-fired power generation, which contributes significantly to environmental pollution and global climate change. Renewable energy, particularly wind power, presents a cleaner alternative but is limited by inconsistent availability. The storage system helps to minimize the imbalance of power generation by wind power plants due to inconsistency. Integrating wind power plants with pumped-hydroelectric storage systems (PSS) offers a solution, providing reliable and dispatchable power. This study explores a Wind-PSS hybridized integrated system's economic feasibility and environmental benefits using the standard IEEE 30 bus system network. Employing the Multi-Objective Dragonfly Algorithm (MODA), the research aims to optimize the cost and emission reductions depending on previous work. The findings indicate that the proposed system can substantially improve financial performance and environmental impact, demonstrating the potential of Wind-PSS hybridization for sustainable power generation. © 2024 IEEE.

关键词： Cost Emission MODA PSS Wind

来源：评论

学校读者我要写书评

暂无评论

Development of a smart agricultural monitoring system 33

Development of a smart agricultural monitoring System

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Mavimbela, Mmatshwene Mogorosi, Alex Yokwana, Xolani Sumbwanyambe, Mbuyu University of South Africa Dept. of Electrical and Smart System Engineering Johannesburg South Africa

ISBN: (纸本)9798331535162

In agriculture, vegetable farming is the most dominating type of farming as it contributes 2.45% to the African GDP growth. It is central to fostering growth reducing poverty and improving food security in south Africa. With more than 70% of rural population depending on agriculture for their livelihoods. However, farmers are facing ongoing challenges over monitoring of farm produce that requires extensive physical interaction within the farm activities. Another challenge, theft and killing cases are increasing in the farming sector due to poor security system involved. The current study proposes the use of GSM sim800 module to communicate with the user. Inconsistent power supply and high energy has greatly affected the agricultural sector. In this paper a cheaper prototype that uses an Arduino microcontroller to control and monitor irrigation by eliminating water waste, and provide maximum security is proposed, it is remotely controlled. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Partial Discharge Classification With 1D Convolutional Neural Network 14

Partial Discharge Classification With 1D Convolutional Neura...

引用

14th International Conference on the Properties and Applications of Dielectric Materials, ICPADM 2024

作者： Cheypoca, Thepjit Promphanich, Wiboon Thway, Aung Ye Hankae, Angelina Phimpissada Jeenmuang, Siwakorn Pattanadech, Norasage School of Engineering King Mongkut's Institute of Technology Ladkrabang Instrumentation and Control Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Computer Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Mechatronics Engineering Dept. Bangkok Thailand

ISBN: (纸本)9798350374605

This paper introduces a novel approach for classifying with the 1D Convolutional Neural Network model for partial discharge patterns, that consists of corona discharge, surface discharge and internal discharge. The PD measuring circuit suggested in IEC 60270:2000 is used to record Partial discharge signals. Independent parameters such as phase and charge of PD patterns were recorded. The Artificial Neural Network for the classification model was constructed. Moreover, 2×1D CNN feature extraction was utilized to reduce the curse of dimensionality in the dense layer of the proposed PD classification model. 80% of the recorded data will be used as a training data and 20% recorded data was used for testing of the classification models. Impacts of neuron numbers and network architecture on the PD classification performance will be observed. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Partial Discharge Classification with Transformer Neural Networks 14

Partial Discharge Classification with Transformer Neural Net...

引用

14th International Conference on the Properties and Applications of Dielectric Materials, ICPADM 2024

ISBN: (纸本)9798350374605

This paper introduces an approach with the Transformer Neural Networks model for partial discharge patterns classification, that consists of corona discharge, internal discharge and surface discharge. The PD measuring circuit suggested in IEC 60270:2000 is used to record Partial discharge signals. Independent parameters such as phase and charge of PD patterns were recorded. The phase value will be encoded into the charge array and Transformer Neural Network is constructed using Positional Embedding and Transformer Encoder Layer. 80% of the recorded data will be used as a training data and 20% recorded data was used for testing of the classification models. Impacts of neuron numbers and network architecture on the PD classification performance will be observed © 2024 IEEE.

关键词： Electric corona

来源：评论

学校读者我要写书评

暂无评论

Analytical Study of the Transient Period of Fault Current in Inverter-Based Resources 3

Analytical Study of the Transient Period of Fault Current in...

引用

3rd IEEE International Conference on Power Electronics, Intelligent Control and Energy systems, ICPEICES 2024

作者： Kunwar, Dol Raj Hossain, Shah Mohazzem Gujar, Abhilash Ioe Tribhuvan University Dept. of Electrical Engineering Nepal Military Institute of Science and Technology Dept. of Electrical Electronic and Communication Engineering Bangladesh College of Engineering Dept. of Electrical Engineering Pune India

ISBN: (纸本)9798350387193

The increasing integration of inverter-based re-sources (IBRs) in modern power systems poses challenges to traditional grid conventions due to features such as low inertia and limited fault current supply. Since IBRs exhibit distinct fault characteristics compared to synchronous generators, a reevalu-ation of existing protection schemes is necessary. Understanding the transient response of IBR during faults is crucial for both protection system design and ensuring that its outputs remain within the maximum limits of internal semiconductor materials, which is a factor heavily influenced by manufacturer-specific con-trol settings. While electromagnetic transient programs (EMTP) provide valuable insights, their application to large power systems is computationally intensive, underscoring the need for analytical fault models. This paper addresses these challenges by converting EMTP models of grid-following IBRs into transfer function models to study transient response. Additionally, it attempts to derive fault current expressions for LC-filter-based inverters and identifies the corresponding factors that influence the resulting transients. The accuracy of the developed analytical model is also evaluated against simulations in PSCAD. © 2024 IEEE.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

Power and Energy Harvesting Efficiency Under Different Environmental Sources Using Piezoelectric Mechanism for Industrial Applications 24

Power and Energy Harvesting Efficiency Under Different Envir...

引用

24th EEEIC International Conference on Environment and Electrical engineering and 8th I and CPS Industrial and Commercial Power systems Europe, EEEIC/I and CPS Europe 2024

作者： Bani-Hani, Muath Alnemrawi, Bara'a Barham, Wasim Kouritem, Sallam Jordan University of Science and Technology Dept. of Aeronautical Engineering Irbid Jordan Jordan University of Science and Technology Dept. of Civil Engineering Irbid Jordan Alexandria University Dept. of Mechanical Engineering Alexandria Egypt

ISBN: (纸本)9798350355185

engineering has evolved from perceptions of the ways natural and constructed systems respond and from the improvement of empirical formulas that give bases to design. Centuries before it was known that engineering consists of just two fields, military and civil, civil engineering remains an umbrella term including numerous related specialties. As a result of increasing the cost of non-renewable energy resources, the world trends to find other renewable and sustainable resources for supplying power to electronic devices, generators, and much more applications. It's also worth mentioning that generating electricity in traditional ways is considered a complex method. Energy harvesting is defined as scavenging energy from the environment or natural resources such as wind, rain, waves, human activities, and earthquakes for (Structural Health Monitoring) SHM purposes, Piezoelectric mechanism is chosen in this paper for energy harvesting because of its advantages compared to other mechanisms such as its smaller size, fewer moving parts, simpler design, and its higher efficiency. This paper includes the energy efficiency investigation for different energy sources of vibration such as wind, rainfall, and earthquake using MATLAB Simulink environment. The wind is considered the most efficient source due to the high power values that can be obtained, and its continuity under all circumstances. © 2024 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Modelling of Electric Vehicle and it's components on MATLAB/Simulink 1

Modelling of Electric Vehicle and it's components on MATLAB/...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Kumar, Gautam Kumar, Sanjay Sankalp, Kumar Raj, Ashish National Institute of Technology Jamshedpur Engineering Dept. Jamshedpur India National Institute of Technology Jamshedpur Electrical Engineering Dept. Jamshedpur India

ISBN: (纸本)9798350377002

This literature commences with an overview of electric vehicles, encompassing their diverse types, charging topologies, and future prospects. Subsequently, the paper delves into the dynamics of vehicle motion, elucidating the forces at play during acceleration, with simulations conducted using MATLAB/Simulink. Visual representations of electric vehicle systems are provided, serving as a precursor to forthcoming Simulink realizations. Furthermore, the paper outlines the dynamic mathematical modelling of electric vehicles in subsequent sections. The discussion transitions to the simulation and mathematical analysis of various converters utilized in electric vehicles, including rectifiers, inverters, and choppers. Battery-related calculations are then explored, addressing the requisite number of cells in series and parallel configurations for optimal vehicle operation. Finally, the project scrutinizes three potential issues - cell equalization, voltage limits violation, and thermal anomalies in the battery - during vehicle operation or charging. A simulation model is presented as a proposed solution to mitigate these challenges, underscoring the comprehensive approach of this research endeavor. © 2024 IEEE.

关键词： Equalizers

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：