检索结果-内蒙古大学图书馆

International Conference on Advanced Computing and communication Systems (ICACCS)

作者： S. Malini C. Murugan G. Dency Flora Gowri Shangari E Department of Electronics and Communication Engineering Karpagam College of Engineering Tamilnadu India Department of Electronics and Communication Engineering Veltech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamilnadu India Department of Computer and Communication Engineering Sri Eshwar College of Engineering Tamilnadu India

Accidents in the world increases every day in different ways. In this scenario, 50 percent of accidents were caused by the driver's inattention. Driver play as a heart of the vehicle; therefore, the driver needs to be in steady and active state during the travel. At times, the drivers used to work for more than the usual timing, which leads to drowsiness causing the base for accident. In case of goods transportation for longer distance via road ways, drivers used to consume alcohol to overcome tiredness leads to accident. This paper explains about the pre-alert system and prevention of accidents by drowsiness and alcohol consumption. The hardware model incorporates Arduino Uno board. The pre alert system uses webcam to detect drowsiness by monitoring the face of the driver using object detection algorithm and MQ3 sensor placed in front of driver senses the alcohol consumption. If the threshold exceeds and alcohol and drowsiness is detected, immediately the proposed system uses to alert the driver until driver comes to active state. At that situation the model identifies the current location and intimates to the owner/blood hood through short message service. If the vehicle undergoes an accident, the vibration sensor detects it and sends a message to the emergency contact.

关键词： Vibrations Webcams Roads Object detection Message services Timing Safety

来源：评论

学校读者我要写书评

暂无评论

Primeval Identification and Diagnosis of Alzheimer's Disease Utilizing 3D CNN Models

Primeval Identification and Diagnosis of Alzheimer's Disease...

引用

International Conference on Advanced Computing and communication Systems (ICACCS)

作者： K. L. Sujitha Lynsha Helena Pratheeba HP Rajeshwari R Kottaimalai Ramaraj Pallikonda Rajasekaran Murugan Thilagaraj M Department of Computer Science and Engineering MVJ College of Engineering Bengaluru India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India Department of Industrial Internet of Things MVJ College of Engineering Bengaluru India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

An early-onset neurocognitive impairment, Alzheimer's disease (AD) affects individuals. The symptoms of this illness include diminished memory, strange conduct, and linguistic difficulties. Since AD is the source of 60-80% of instances of dementia, it is the single most prevalent cause of dementia. An AD that is neurodegenerative begins with moderate cognitive impairment (MCI) and progressively worsens. It damages brain tissue, impairs ability to think and remember, and makes it difficult to carry out basic duties. The development of more sophisticated therapies for AD depends on swift detection. For this reason, stopping and managing the progression of AD depends greatly on early detection. The primary goal is to create a comprehensive framework for medical image categorization according to different phases of Alzheimer's disease and early identification of the condition. This work employs a deep learning approach, more precisely convolutional neural networks (CNN). Simple CNN architectures that handle 2D and 3D structural brain magnetic resonance imaging (MRI) form the basis of the suggested methodology. The limited quantity of datasets presents the primary obstacles for medical images. Thus, in order to optimize the size of the dataset and avoid the issue of overfitting, methods to augment data are used. Techniques for resampling, such as downsampling and oversampling are employed to address imbalanced dataset collections.

关键词： Solid modeling Three-dimensional displays Parkinson's disease Magnetic resonance imaging Resonance Convolutional neural networks Proposals Alzheimer's disease Older adults Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Alzheimer's Disease based on InceptionV3 and Machine learning Classifier using Neuroimaging 3

Early Detection of Alzheimer's Disease based on InceptionV3 ...

引用

3rd International Conference on Smart electronics and communication, ICOSEC 2022

作者： Nirmala, P. Ahila, S. Sobitha Geetha, M. Ramesh, S. Senthilkumar, C. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai602105 India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

Neuroimaging is a term referring to the techniques that efficiently expose facts well about cellular structure of the human brain. These techniques have been used in clinical condition, medicinal operations, and scientific work. The challenge of classifying neuroimages is among the most important stages that healthcare experts need to take in evaluating and treating their sufferers effectively by evaluating the symptoms of different types of neuroimaging. This may be achieved by analyzing the multiple types of neuroimaging. The symptoms of Alzheimer's disease need to be recognized in their earliest stages in order to prevent the quality of medical services from deteriorating further. In the current investigation, a novel method was devised by making use of a digitally subtracted angiography scan. This method has all of the required qualities of a novel indicator for blood flow to the brain and contributed to its development. In addition, samples of normal participants and digitally removed angiograms of patients with Alzheimer's disease are included in the database that is being exploited. Due to the fact that each scan had a large number of packets for the ICAs on both the left as well as the right, from before the approaches were utilized in order to get the information ready for the future stages of object classification. The multiple frames of the scan were translated from real space to DCT space so that noise could be removed from the image. After that, the median picture was reprojected into interplanetary world, and the two halves were afterwards filtered by Meijering and blended into a single image. The suggested method extracts the features using a variety of pre-trained networks, such as InceptionV3 and DenseNet201, among others. After that, using the PCA method, it was feasible to select the attributes that had an estimated deviation ratio of 0.99. These were the attributes that could subsequently be merged and used in classification algorithm. © 2022 IEE

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Exploring Vanet Routing Using A Novel Geographic Routing Protocol

Exploring Vanet Routing Using A Novel Geographic Routing Pro...

引用

Distributed Computing and Electrical Circuits and electronics (ICDCECE), IEEE International Conference on

作者： Purushothaman Ramaiah R. Narmadha Sasikumar Gurumoorthy K. Kokulavani V. Gowri Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering J. J. College of Engineering and Technology Trichy India Department of Electronics and Communication Engineering J. J. College of Engineering and Technology Trichy India

Previously, vehicular ad hoc networks (VANETs) were designed by using several geographic routing schemes. That doesn’t sustain any routing configurations in the existing geographic routing methods. Vehicular Ad hoc Network is networks which consist of mobile nodes, consequently it is very harsh to make and remain up end-to-end links. The main aim of this research work is widespread inter vehicle distance, high speed of vehicles also supports the density of vehicle is altered. The exact real time location information of vehicles is accessed with high reliability via vehicle to vehicle inter connection. Due to frequent link entrapped and rapid topology changes it is not easy to augment well-organized routing etiquettes for VANETs. To find the exact location of stirring vehicles is very difficult and may incur in the existing routing networks. Additionally, the position information about stirring vehicle accessible to other vehicles is usually time-lagged as it is always stirring over time. Luckily, we scrutinize that the interim upcoming locations of vehicles can be forecast. Anchored in the significant surveillance, we propose a novel approach for geographic routing. It uses the extrapolative locations of automobiles. The etiquettes anchored in the vehicles' positions also called as geographic routing protocols (GR) were uncovered to be the most adequate to the VANETs because of their sturdiness in making with the dynamic environment changes and the high- ceilinged mobility of the automobiles. The etiquette is incorporated with a multi-hop information delivery virtualization deal that works on the crest of the transportation stratum and gives soaring speed for multi-hop one after the other information broadcasts. We demeanor practical computer imitations to display the recital advantage of the etiquette over additional approaches at the indistinguishable time vigor efficiency will be enhanced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Methodology for Classifying Objects in High-Resolution Optical Images Using Deep Learning Techniques 7th

Methodology for Classifying Objects in High-Resolution Optic...

引用

7th International Conference on Microelectronics, Electromagnetics and Telecommunication, ICMEET 2022

作者： Lalitha Kumari, P. Das, Santanu Kannadasan, B. Sampathila, Niranjana Saravanakumar, C. Anand, Rohit Gupta, Ankur Department of Computer Science and Engineering Malla Reddy Institute of Technology Andhra Pradesh Secunderabad Maisammaguda India Department of Biotechnology Seshadripuram First Grade College Yelahanka New Town Bangalore India Department of Civil Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai India Department of Biomedical Engineering Manipal Institute of Technology Karnataka Manipal India Department of Electronics and Communication Engineering SRM Valliammai Engineering College Tamilnadu Kattankulathur India DSEU G.B.Pant Okhla-1 Campus New Delhi India Department of Computer Science and Engineering Vaish College of Engineering Haryana Rohtak India

ISBN: (纸本)9789811988646

The classification of objects that are present in the images or in the videos is being developed progressively to obtain good results because of the use of convolutional networks. In this work, we have used the convolutional networks for the detection of objects that are present in high-resolution satellite images. Tests were carried out on ships that are on the high seas and in the ports. This classification is useful for monitoring the coasts, as well as for analyzing the dynamics of the ships which can be applied in the search of ships. To cover this task of classifying ships in the spectral images, the use of high-resolution satellite images of coastal areas and with a large number of ships is used in order to build a set of images, containing images of the ships. In order to be used for training setting and testing of the convolutional network, a very particular configuration of the convolutional network caused by the particularity of high-resolution satellite images is presented. The methodology developed indicating the procedures performed is also presented in which a set of images containing 300 was built images of ships that are in the sea or are anchored in the ports. The results obtained in the classification using the convolutional networks are acceptable to be able to be used in different applications. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Predicting Groundwater Quality with Advanced Deep Learning Models: Improving Environmental Management by Addressing Pollution Issues and Obtaining More Accurate Forecasts

Predicting Groundwater Quality with Advanced Deep Learning M...

引用

International conference of electronics, communication and Aerospace Technology (ICECA)

作者： K. Selvakumarasamy R Mahaveerakannan D. N.S Ravi Kumar R Balamanigandan T. Rajesh Kumar Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India School of Electronics Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

To ensure clean water for consumption in the future, it is imperative to understand the pollutants and the quality of the existing groundwater. Controlling water pollution and enhancing water management both depend on the ability to predict the water’s purity with high accuracy. Previous studies have shown that when it comes to deep learning models, extreme gradient boosting (XGBoost) performs better in terms of accuracy and precision than random forest (RF). This study explores the field of water quality assessment by creating a novel method that combines state-of-the-art deep learning algorithms such as artificial neural networks (ANN), long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), gated recurrent units (GRU), convolutional neural networks (CNN), recurrent neural networks (RNN), and backpropagation neural networks (BPNN). Utilising deep learning techniques to enhance the index’s prediction capacity and accuracy, as well as computing WQI utilising comprehensive water quality metrics, are our main research objectives. Through the use of deep learning models in conjunction with WQI, we hope to uncover patterns and connections in information on water quality that are not visible through conventional means. Plans for groundwater development will benefit from the study’s findings, which will also enhance DL applications for better groundwater quality.

关键词： Deep learning Radio frequency Accuracy Groundwater Water quality Predictive models Prediction algorithms Water pollution Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

An Analytical Review of Underwater Image Enhancement Techniques

An Analytical Review of Underwater Image Enhancement Techniq...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Gogoi, Kaveri Baruah, Swagat Kumar Konwar, Utkarsh Mahanta, Rajpratim Boruah, Abhijit Sarma, Debajit Kakoty, Nayan M. Department of Computer Science and Engineering DUIET Dibrugarh University Assam Dibrugarh786004 India Department of Electronics and Telecommunication Engineering Barak Valley Engineering College Assam Karimganj788710 India Department of Electronics and Communication Engineering Tezpur University Assam Napaam Tezpur784028 India

Underwater images are integral parts for both terrestrial and aerial environments. Due to the environmental conditions in the deep-sea, poor visibility, haziness, and low contrast causes the distortion of the underwater images and hence image enhancement techniques are significant. Effects of color also plays a major role as refection, refraction, and scattering occurs. The water quality is controlled and influenced by the filtering properties of the water. Researchers proposed Underwater Image Enhancement (UIE) methods to solve these problems. In this paper, analysis has been done for five state of the art Underwater Image Enhancement models namely FUnIEGAN model, U-Shape Transformer model, DeepSeeColor model, Waternet model, and SRCNN model. To improve the quality of the image in terms of noise levels, Peak Signal-to-Noise Ratio (PSNR) is used and to compare images based on characteristics such as luminance, contrast, and structure, Structural Similarity Index (SSIM)is used. Results shows an analytical comparision among the enhancement models, and suggests one among them as superior based on the evaluation metrices. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Fault Detection in Smart Grids

AI-Driven Fault Detection in Smart Grids

引用

Electrical Power engineering, communication and Computing Technology(ODICON), Odisha International Conference on

作者： S. Pradeep C. R. Edwin Selva Rex D. Kalaiyarasi Ramya Dhandapani M. Sakthivel K. Vijaipriya Department of Electronics and Communication Engineering S. A. Engineering College Tamil Nadu India Department of Electrical and Electronic Engineering Vignana Bharathi Institute of Technology Hyderabad Telangana India Department of Electronics and Communication Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Madurai Tamil Nadu India Department of Electronics and Communication Engineering Sri Sai Ranganathan Engineering College Coimbatore Tamil Nadu India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

The use of artificial intelligence (AI) for fault finding in smart grids, with the end goal of improving the reliability and efficiency of ultramodern power systems. Smart grids, which are distinguished by their intricate architectural design and massive data collection, are equipped with cutting-edge approaches for the quick and precise identification of breakdowns. Through the utilization of artificial intelligence techniques, such as Deep Reinforcement Learning (DRL) method can analyze big datasets, identify anomalies, and accurately predict implicit errors with a high degree of precision. In this research, artificial intelligence algorithms that are colorful are investigated, along with their effectiveness in real-time monitoring and defect finding within smart grids. The advantages of AI-driven defect discovery over traditional methods are demonstrated through case studies and simulations. These advantages include important breakthroughs in response time, delicacy, and functional adaptability. The incorporation of artificial intelligence into the management of smart grids holds the potential to bring about substantial breakthroughs in the areas of grid stability maintenance, time-out reduction, and energy distribution optimization. The purpose of this research is to provide a complete analysis of the role that artificial intelligence plays in defect finding. It also offers insight into future advances and practical applications in smart grid systems.

关键词： Power engineering Power system stability Prediction algorithms Stability analysis Real-time systems Smart grids Power system reliability Time factors Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Connectivity Disturbances in Self-Limited Epilepsy with Centrotemporal Spikes: A Partial Directed Coherence Analysis of Electroencephalogram

引用

Clinical EEG and Neuroscience 2024年第2期55卷 257-264页

作者： Chiang, Ching-Tai Yang, Rei-Cheng Kao, Yu-Chia Wu, Rong-Ching Ouyang, Chen-Sen Lin, Lung-Chang Department of Computer and Communication National Pingtung University Pingtung Taiwan Departments of Pediatrics Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung Taiwan Departments of Pediatrics E-Da Hospital Kaohsiung Taiwan Department of Electrical Engineering I-Shou University Kaohsiung Taiwan Department of Information Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Pediatrics School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan

Although the remission of self-limited epilepsy with centrotemporal spikes (SeLECTS) usually occurs by adolescence, deficits in cognition and behavior are not uncommon. Several functional magnetic resonance imaging (fMRI) studies have revealed connectivity disturbances in patients with SeLECTS associated with cognitive impairment. However, the disadvantages of fMRI are expensive, time-consuming, and motion sensitive. In the current study, we used a partial directed coherence (PDC) method to analyze electroencephalogram (EEG) for exploring brain connectivity in patients with SeLECTS. This study enrolled 38 participants (19 patients with SeLECTS and 19 healthy controls) for PDC analysis. Our results demonstrated that the controls had significantly higher PDC inflow connectivity in the F7, T3, FP1, and F8 channels than patients with SeLECTS. By contrast, the patients with SeLECTS demonstrated significantly higher PDC inflow connectivity than did the controls in the T5, Pz, and P4 channels. We also compared the PDC connectivity in different Brodmann areas between the patients with SeLECTS and the controls. The results revealed that the inflow connectivity in the BA9_46_L area was significantly higher in the controls than in the patients with SeLECTS, whereas the inflow connectivity in the MIF_L area 4 was significantly higher in the patients with SeLECTS than in the controls. Our proposed approach of combining EEG with PDC provides a convenient and useful tool for investigating functional connectivity in patients with SeLECTS. This approach is time-saving and inexpensive compared with fMRI, but it achieves similar results to fMRI. © EEG and Clinical Neuroscience Society (ECNS) 2023.

关键词： cognition EEG fMRI partial directed coherence self-limited epilepsy with centrotemporal spikes

来源：评论

学校读者我要写书评

暂无评论

Augmented Insights: A Qualified Evaluation of Deep Learning Representations for Enhancing Banana Leaf Spot Disease Detection

Augmented Insights: A Qualified Evaluation of Deep Learning ...

引用

Social and Sustainable Innovations in Technology and engineering (SASI-ITE), International Conference on

作者： P Kanaga Priya M S Vinu M S V Jeevitha N Rathina Kumar N Kanimozhi S Jayachitra Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Coimbatore India Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Erode India Department of Computer Technology UG Kongu Engineering College Erode India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798350360790

ISBN: (纸本)9798350360806

The manufacturing of bananas is tough due to a wide variety of diseases that reduce crop yields extensively. This proposed research advances the sector of banana leaf spot disorder detection through a detailed qualifying or comparative evaluation of Deep gaining knowledge of Deep Learning (DL) representations. Examining the performance of important methods consisting of ResNet, VGG19, and EfficientNetB0 in diagnosing banana leaf spot diseases. With picture photograph or image augmentation as an essential step, the studies conduct a comprehensive assessment among unique original and augmented pics, clarifying their impact on version performance. The proposed work reports accuracy rates for authentic photos as $78.82\%$ for ResNet, $77.65 \%$ for VGG19, and a surprising $85.88 \%$ for EfficientNetB0. For augmented photographs ResNet showed a $90.24 \%$ accuracy rate, VGG19 $74.74 \%$, and EfficientNetB0 $94.43 \%$. Because of this dual assessment approach, EfficientNetB0 is found to be powerful in identifying banana leaf diseases as well as highlighting the vital function photograph augmentation performs. The reason for this work is to offer precious insight into the comparative performance of banana farming strategies via the incorporation of pioneering technology. This research lays specific significance on the augmentation of image databases, highlighting its significance in attaining improved accuracy. Through a dual approach, model robustness is highly improved throughout multiple datasets, giving us a normal angle on how they carry out below real-world conditions.

关键词： Deep learning Precision agriculture Technological innovation Accuracy Image databases Oral communication Robustness

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：