检索结果-内蒙古大学图书馆

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： K. Suresh S Shibi Raj S Vikram Surya S Raghul Dept. of Computer Science and Engineering KPRIET Coimbatore India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Video surveillance plays a significant role in the domain of intelligent transportation systems. Intelligent transportation system aims to utilize advanced technologies to enhance the efficiency and safety of transportation system. Video surveillance has several uses, including identifying the reason behind an accident, locating a particular vehicle, and figuring out the best routes between important places. Object identification and shadow removal are the primary objectives of intelligent transportation systems. Moreover, video surveillance has other difficulties, such as text recognition. This work proposes an inner outer outline profile line (IOOPL) method for recognizing the set of objects boundary layers based on shadow elevation. It also tackles the issue of object shadows in-vehicle image segmentation not being recognized as a component of the item itself. Utilizing the delta learning algorithm, often known as the Widrow-Hoff learning rule, this work suggests a procedure for identifying and classifying cars by removing their shadow counterparts. The system is trained using a variety of vehicle kinds based on their look, colors, and construction types. Furthermore, this work employs an artificial neural networks trained approach using the high-performance delta learning technique, to classify cars and gather data on their journeys. Additionally, it introduces a strategy for license plate identification through edge dilation and text correlation. Recognizing number plates poses a challenging task in the realm of video text recognition.

关键词： Correlation Text recognition Image edge detection Video surveillance Automobiles Object recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Gender Classification from Thermal Images using CNN

Gender Classification from Thermal Images using CNN

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Harika Gurram Keerthi Kethineni Deva Harshini Kommineni Kakani Soumya Dept. Computer Science & Engineering VRSEC Vijayawada India

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

In this study, two deep learning architectures— AlexNet and InceptionV3—are used to evaluate gender categorization using thermal imagery. One of the most promising techniques for classifying gender is thermal imaging, which offers distinct insights into physiological traits. Divided into separate training and testing subsets, the dataset is made up of carefully preprocessed thermal pictures. InceptionV3, known for its complex design combining inception modules, and AlexNet, a pioneering convolutional neural network (CNN), are refined on the training data to adjust to the complexities of gender categorization. Then, in order to measure the performance of the trained models, they are rigorously evaluated on the testing set. Specifically, their accuracy is evaluated. Experimental findings show that InceptionV3 performs better than AlexNet, with an accuracy of 92.3% as opposed to 82.6% for AlexNet. This significant disparity highlights how much better InceptionV3 is at identifying subtle thermal patterns and characteristics, which improves gender categorization accuracy. The work makes a substantial contribution to the rapidly developing area of thermal imagingbased gender categorization by highlighting how crucial it is to use advanced deep learning architectures in order to improve performance and accuracy. Subsequent investigations might delve into novel methodologies, including multi-modal fusion or sophisticated methods, to enhance precision and resilience in tasks using thermal-based gender categorization.

关键词： Training Deep learning Technological innovation Accuracy Training data Imaging Physiology

来源：评论

学校读者我要写书评

暂无评论

Stomach Cancer Prediction and Detection using Deep Learning: A Review 2

Stomach Cancer Prediction and Detection using Deep Learning:...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Kaur, Sharandeep Goel, Paurav Kapoor, Nitika Chandigarh University dept. of Computer Science Engineering Mohali India

ISBN: (纸本)9798331505745

Stomach cancer, sometimes referred to as gastric cancer, is still one of the most common and widespread deadly disease worldwide offers a significant challenge in oncology due to late detection and high mortality rates. The advent of deep learning has revolutionized stomach cancer prediction by leveraging sophisticated models such as convolutional neural net-works (CNNs), multimodal learning and hybrid frameworks that integrate multiple data sources like medical imaging, histological slides, clinical records and genetic profiles and provide better performance with high accuracy. This review comprehensively ex-plores recent advances in deep learning applications for the detection of stomach cancer, highlighting their performance, accuracy, and clinical implications. Comparative analysis demonstrates that different deep learning models, such as ResNet50, DenseNet121, EfficientNetB5, and MobileNetV2, provide impressive results with accuracy up to 99% and higher sensitivity and specificity. It also indicates that the system accuracy needs to be improved to 100% in order to detect stomach cancer as early as possible. Early detection helps in the stoppage of further spreading of the disease and lowers the death rates. © 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

Autonomous Drone Control for Wireless Charging Using Power Lines

Autonomous Drone Control for Wireless Charging Using Power L...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Pengkai Wang Jonghoek Kim Husna Mutahira Mannan Saeed Muhammad Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea Dept. of Defense System Engineering Sejong University Seoul South Korea Dept. of Computer Science and Engineering Sogang University Seoul South Korea

The limited autonomy of flight has long been considered a significant constraint in drone systems. In the context of drone inspections of power lines, this study focuses on a drone equipped with a coil designed for autonomous battery charging. Positioned atop the drone is a charging coil, and on the upper surface, there is an upward-facing camera with a restricted field-of-view (FOV), serving the crucial role of aligning the drone with power lines. This research introduces a wireless power transfer strategy to facilitate the self-charging process of the drone while maintaining its position beneath power lines. To enable the drone's autonomous approach to power lines, a method is devised to guide the drone from below. As the drone approaches the power lines, it monitors the current induced by these lines and gradually adjusts its altitude until a sufficiently high induced current is achieved. The proposed approach ensures safety, as the drone avoids direct contact with high-voltage power lines, setting it apart from other existing methods that require such contact. To the best of our knowledge, this study offers a novel approach to precisely controlling drone movements, and establishing reliable wireless power transfer from power lines. The effectiveness of the developed wireless transfer strategy has been verified through MATLAB simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention-Based AdaptSepCX Network for Effective Student Action Recognition in Online Learning

引用

Procedia computer science 2024年 233卷 164-174页

作者： Arnab Dey Anubhav Anand Subhajit Samanta Bijay Kumar Sah Samit Biswas Dept. of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Howrah 711103 India

In the realm of online learning and distance education, the issue of inadequate supervision looms large, posing a significant obstacle. This paper delves into the challenges posed by the lack of supervision in online learning environments and proposes an innovative solution to understand and recognize students’ behaviors. This study's primary objective is to detect and recognize students’ actions in images captured through webcam. This task distinguishes itself from the well-established video-based student action recognition domain, which relies on temporal cues. Recognizing student actions from images intensifies the complexity of the problem. To meet this challenge, a novel deep learning model named AdaptSepCX Attention, specifically designed for student action recognition in online learning environments, is introduced. The proposed method exhibits exceptional performance with 92.73% validation accuracy on the Student Online Action Image dataset (SOAId), a carefully curated collection comprising 2029 student-centric images. The proposed model outperforms well-established models such as DenseNet121, NASNet Mobile, Con-vXNet, DELVS1 and MobileNetV2 in student action recognition. Action recognition for students has broader implications beyond the online classroom. It has the potential to revolutionize educational technology, making online learning more interactive and engaging. Enabling machines to understand and respond to student actions enhances education, personalizes learning, and supports students’ academic success and well-being. This research enhances the understanding of student involvement in online learning and offers an effective solution for recognizing actions from images.

关键词： Students Action Recognition Action Recognition Online Learning Attention Adaptive Seperable Convolution Network

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Binary Classification of Tea Leaf Diseases

Comparative Analysis of Machine Learning Algorithms for Bina...

引用

Advances in electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Nidhi Shekhar J.S Megha J.S Varsha G.P. Revathi Dept. of Computer Science and Engineering PESU - ISFCR Bengaluru India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

India stands as one of the world's largest tea exporters. This requires for an implementation of an efficient and robust system for disease detection and prevention. The most important challenge faced by the tea industry is tea leaf diseases due to continuous pathogen infestation. These diseases can cause full-size crop losses, adversely affecting the economic system and the livelihood of tea farmers. The ability to detect these diseases early is essential. Early detection can cause timely intervention that can notably reduce harm to tea plants and keep them at their best possible quality. Unfortunately, traditional diagnostic techniques often depend on visible inspection and are hence inefficient as those methods can be gradual, labour in-dept. and vulnerable to human errors, reducing the effectiveness in larger fields. This research paper aims to classify whether a leaf is diseased or healthy through a two-step process involving feature extraction using a pretrained Convolutional Neural Network (CNN) and classification using four machine learning models - LightGBM, CatBoost, Autoencoders and Self Organized Maps (SOMs). This paper utilizes a pre-trained VGG16 model, which is trained on the ImageNet dataset. This model is capable of extracting high-level features from images.

关键词： Pathogens Machine learning algorithms Biological system modeling Computational modeling Prevention and mitigation Autoencoders Machine learning Feature extraction Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Auto-Adaptive Stator Ground Fault Protection for Synchronous Generators in Diesel-Electric Locomotives 14

Auto-Adaptive Stator Ground Fault Protection for Synchronous...

引用

14th IEEE International Symposium on Diagnostics for electrical Machines, Power Electronics and Drives, SDEMPED 2023

作者： Mahtani, Kumar Guerrero, Jose M. Beites, Luis F. Platero, Carlos A. Universidad Politécnica de Madrid Automation Electrical and Electronic Engineering and Industrial Informatics Dept. Madrid Spain Mondragon Unibertsitatea Electronics and Computer Science Dept. Arrasate-Mondragon Spain Universidad Politécnica de Madrid Automation Electrical and Electronic Engineering and Industrial Informatics Department Madrid Spain

ISBN: (纸本)9798350320770

Diesel-electric locomotives are equipped with one or more synchronous generators driven by diesel engines, that provide the necessary electrical energy for their operation. These generators are usually provided with some protection relays, depending on their rated power and their type of service. Standard stator-ground fault protection has a setting for rated conditions. In case of variable speed and voltage operation, the protection does not cover all the operation range of the machine. In addition, unwanted tripping may occur due to incorrect filtering of the third harmonic. In this paper, an auto-adaptative stator ground protection function is presented, for the operation of synchronous machines at variable voltage and frequency. A specific case study is tackled, focused on the main generators of a diesel-electric locomotive. Numerous simulations are carried out to verify the proposed protection method. The obtained results are promising, and they can be used in other synchronous machines operating at variable speed. © 2023 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection using Image Processing and Generative Adversarial Network 14

Plant Disease Detection using Image Processing and Generativ...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Teresha, Y. Shaji, Nikhil John Jarial, Manav Mirjankar, Ved Vishal Patil, Swetha Computer Science Engineering Dept. PES University Bengaluru India

ISBN: (纸本)9798331531935

Agriculture is a key contributor to the GDP of our country, India. Plants play a very important role in the ecosystem and plant diseases can negatively impact the agricultural industry by causing huge losses to the food supply. Plant leaves are prone to a variety of diseases, including blights, leaf spots, and other infections. Therefore, identifying diseases efficiently is crucial to pave the way for sustainable agriculture. In the field of agriculture, traditional and manual methods for detecting diseases in plants have sometimes been found to be inefficient and error prone. We therefore present a novel solution to these issues by introducing a method to automate plant disease detection in the Tomato plant leaf by using advanced Convolutional Neural Network (CNN) frameworks, image processing libraries and Generative Adversarial Networks (GANs). The pipeline of our work involves preprocessing plant image datasets, generating synthetic images using GANs, segmenting region of interests via a U-Net model, and classifying diseases with a CNN-based classifier. A deployed model ensures accurate disease identification from user input. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

First-Year engineering Students' Expertise and Trust in GenAl 54

First-Year Engineering Students' Expertise and Trust in GenA...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Bego, Campbell R. Crockett, Cenetria L. Danovitch, Judith H. Martinez, Liliana G. Rajkumar, Alwin K. Thomas, Elisabeth L. Thompson, Angela K. Tran, Alvin Valavala, Benarji J. B. Speed School of Engineering University of Louisville Dept. of Engineering Fundamentals United States School of Arts & Sciences University of Louisville Dept. of Anthropology United States School of Arts & Sciences University of Louisville Dept. of Brain and Psychological Sciences United States J B. Speed School of Engineering University of Louisville Dept. of Bioengineering United States J.B.Speed School of Engineering University of Louisville Dept. of Computer Engineering and Computer Science United States J B. Speed School of Engineering University of Louisville Dept. of Industrial Engineering United States

ISBN: (纸本)9798350351507

This full-length research study investigated first-year engineering students 'trust in generative artificial intelligence (GenAl) before and after course instruction. Pre-and post-surveys were conducted with questions on students' experience with GenAl tools as well as trust in GenAl. The trust questions had students evaluate the likelihood of GenAl generating a correct response to various prompts such as 'explain the unit circle' (correct response likely) to 'solving this system of equations...' (correct response unlikely for tools available in Fall 2023). Within-subjects analyses indicated that lessons in the course significantly increased trust in ChatGPT for correct-response-likely items. In addition, the lessons significantly decreased students 'trust in ChatGPT for correct-response-unlikely items. There were no significant interactions between prior experience level and change in trust. These results show that guided exposure to GenAl helped first-year engineering students begin to understand capabilities and limitations of GenAl. These results are promising because student trust in GenAl output will directly impact decisions to engage with it for different tasks. More work is needed to optimize instruction and understand students' use of the tool beyond the classroom integration, including their full ethical decision-making process, but the malleability of trust at this level is an indication that engineering educators can impact student perspectives of GenAl. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

IoT Botnet Detection Using an Economic Deep Learning Model

IoT Botnet Detection Using an Economic Deep Learning Model

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Elsayed, Nelly Elsayed, Zag Bayoumi, Magdy Univesity of Cincinnati School of Information Technology Ohio United States University of Louisiana at Lafayette Dept. of Electrical and Computer Engineering Louisiana United States

ISBN: (纸本)9798350337617

The rapid progress in technology innovation usage and distribution has increased in the last decade. The rapid growth of the Internet of Things (IoT) systems worldwide has increased network security challenges created by malicious third parties. Thus, reliable intrusion detection and network forensics systems that consider security concerns and IoT systems limitations are essential to protect such systems. IoT botnet attacks are one of the significant threats to enterprises and individuals. Thus, this paper proposed an economic deep learning-based model for detecting IoT botnet attacks along with different types of attacks. The proposed model achieved higher accuracy than the state-of-the-art detection models using a smaller implementation budget and accelerating the training and detecting processes. © 2023 IEEE.

关键词： Internet of things

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：