检索结果-内蒙古大学图书馆

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Palvi Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Dept. of Computer Science & Engineering Punjab India Chandigarh University Dept. of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350356816

Accurate road extraction from Remote Sensing Imagery (RSI) is crucial for various applications, including urban planning, navigation, and disaster response. This study investigates automated road extraction in rural, semi-urban and urban regions using deep learning architectures, specifically UNet and Deep Residual U-Net (ResNet) models. We leverage High-Resolution Satellite Imagery (HRSI) to train and validate our models, focusing on the distinct characteristics and challenges presented by urban and rural environments. Our methodology involves comprehensive data preprocessing and augmentation techniques to enhance model robustness. We evaluate the performance of both architectures using metrics and achieved an accuracy of 90.29%, recall of 80.95%, precision of 74.89%, and F1- score of 77.80% for the Deep Residual U-Net. Experimental results demonstrates that while both models perform well, the Deep Residual U-Net exhibits superior accuracy and generalization, particularly in complex urban landscapes. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Techniques Optimised LSTM Network for Improved Weather Prediction 2

Metaheuristic Techniques Optimised LSTM Network for Improved...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Mittal, Shweta Sangwan, Om Prakash Guru Jambheshwar University of Science and Technology Dept. of Computer Science and Engineering Hisar India

ISBN: (纸本)9798350360523

Tremendous amount of meteorological data is being generated on a daily basis from a number of sources such as weather stations, balloons, satellites, sensors etc. Timely weather prediction helps people plan everyday life events. Long Short Term Memory (LSTM) networks perform extremely well for capturing dependencies in time series datasets. Number of neurons in hidden layer highly impacts the performance of the LSTM network. The hit and Trial method for selecting the neurons consumes a lot of time and resources and might not lead to a global optimum solution. In this research work, two techniques, i.e. Genetic Algorithm optimized LSTM (LSTM-GA) and Artificial Bee Colony optimized LSTM (LSTM-ABC) have been proposed and implemented to automate the selection of the hidden layer's neurons for improved weather prediction. Proposed techniques have been implemented using DeepLearning4j library making the techniques scalable on clusters of machines. For evaluating the performance of proposed techniques, 15 years Brazil's weather dataset has been used. The experimental results proved that the proposed LSTM-GA and LSTM-ABC techniques have the reduced MAE value of 0.0074 and 0.0075 respectively while the LSTM network without any optimization has a relatively higher MAE value of 0.0086. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Detecting Retinal Damage From OCT Images 15

Detecting Retinal Damage From OCT Images

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vineetha, Kundrapu Ali, Md Jaffer Prathima, Narisetty Singh, Tripty Duraisamy, Prakash Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India University of Wisconsin-Green Bay Dept. of Computer Science and Engineering Wisconsin United States

ISBN: (纸本)9798350370249

Optical coherence tomography (OCT) is a crucial imaging modality in ophthalmology, offering detailed retinal images essential for diagnosing various retinal disorders. In this study, we investigate the application of convolutional neural networks (CNNs) and transfer learning to classify retinal OCT images. We compare a custom CNN model with two pretrained models, MobileNet and VGG16, to explore their effectiveness in categorizing retinal diseases. Our study focuses on improving classification accuracy through image enhancement techniques, training methodologies, and model evaluation using confusion matrices. The results highlight the VGG16-based CNN model as the most effective, demonstrating its potential for accurate classification of retinal disorders based on OCT images. Furthermore, we delve into strategies to further enhance the performance of these models, such as data augmentation, finetuning, and hyperparameter tuning. We discuss the importance of these techniques in optimizing model performance and reducing overfitting. Additionally, we emphasize the significance of evaluating models using confusion matrices to gain insights into their performance across different classes. Overall, our findings suggest that CNNs, particularly the VGG16based model, hold promise for improving the automated diagnosis of retinal diseases using OCT imaging, which could lead to better patient outcomes in ophthalmology. © 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

Personal Exercise Trainer Using computer Vision 2

Personal Exercise Trainer Using Computer Vision

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Hari Ram, S. Ashok, A. Ramalingam, A. Dheenadhayalan, S. National Engineering College Dept. of Computer Science and Engineering Tamil Nadu Kovilpatti India

ISBN: (纸本)9798350328202

The Personal Trainer online application tracks users progress and offers realtime feedback to encourage users in their daily workout routines. To identify and analyze human body movements, the program uses the mediapipe library, which integrates opencv and machine learning methods. The Personal Trainer online app provides an engaging and immersive workout experience by incorporating these technologies. The application supports several exercises, including weightlifting, squats, bicep curls, and pull-ups. The software uses the webcam on the computer to record realtime footage of the user completing the workout after they choose it. The user's body motions are then recognized from the recorded video using opencv and mediapipe, and performance-based feedback is given. Users may quickly move through the various training modes, check their activity history, and measure their overall progress thanks to the app's user-friendly and intuitive interface. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust Line-Convex Polygon Intersection Computation in E2 using Projective Space Representation

引用

Machine Graphics and Vision 2023年第3-4期32卷 3-16页

作者： Skala, Vaclav Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

This paper describes modified robust algorithms for a line clipping by a convex polygon in E2 and a convex polyhedron in E3. The proposed algorithm is based on the Cyrus-Beck algorithm and uses homogeneous coordinates to increase the robustness of computation. The algorithm enables computation fully in the projective space using the homogeneous coordinates and the line can be given in the projective space, in general. If the result can remain in projective space, no division operation is needed. It supports the use of vector-vector operations, SSE/AVX instructions, and GPU. © 2023 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

1 AI-Powered Facial Expression Analysis In Real Time: Unveiling Emotions 1

1 AI-Powered Facial Expression Analysis In Real Time: Unveil...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Aishwarya, D. Sandeep, Ponduru Akhilesh Varma, Penmatsa V.P.S. Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350371802

This study introduces a novel facial deconstruction method for face emotion identification. After identifying facial landmarks with the IntraFace algorithm, seven regions of interest (ROI) are extracted, representing the principal featuresof the face: the mouth, nose, an area between the eyebrows, right and left eyes, and eyebrows. Next, a variety of local descriptors, such as Local Binary Patterns, Completed Local Binary Patterns. Local Ternary Patterns, and Dynamic Local Ternary Patterns, are employed to capture distinctive features. Inputting the feature vector which represents a face image into a multi-class support vector machine completes the recognition process. The suggested method outperforms previous facial deconstruction techniques, according on experimental findings on two publicly available datasets. © 2024 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Deep Analysis of Machine Learning Techniques for the Effective Retrieval of Images Based on Content 2

Deep Analysis of Machine Learning Techniques for the Effecti...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Jain, Ashish Varshney, Sudeep Set Sharda University Dept. of Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

Our research aims to investigate how machine learning techniques can be applied for efficient image retrieval based on content. It is a very difficult process to obtain accurate images from vast digital image collections. CBIR has been particularly interested in this area. It has been shown that content- or feature-based approaches are more effective than text-based query techniques. Research has shown that the performance of these methods varies depending on the type and size of the data set analyzed, with some algorithms performing well for specific small data sets and others for larger data sets. This article provides a comprehensive and systematic review of effective methods for obtaining the image. The paper's objective is to examine different ML classifiers that are applied via the researchers and compare their results based on accuracy and performance. These algorithms include SVM, KNN, random forest, BoVW, Naive Bayes, and LDA. This review paper can assist researchers in selecting the best classifier for their research, as well as in improving existing classifiers by combining them with other algorithms. © 2024 IEEE.

关键词： CBIR classifier feature extraction Random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

BIOPHYSICAL SIGNAL PROCESSING FOR AUTOMATIC ANXIETY CLASSIFICATION IN A VIRTUAL REALITY EXPOSURE THERAPY SYSTEM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第2期86卷 73-84页

作者： Jinga, Nicolae Petrescu, Cătălin-Dumitru Mitruț, Oana Moldoveanu, Alin Moldoveanu, Florica Petrescu, Livia Dept. of Computer Science National University of Science and Technology POLITEHNICA Bucharest Romania Dept. of Automatic Control and Systems Engineering National University of Science and Technology POLITEHNICA Bucharest Romania Faculty of Biology University of Bucharest Romania

This paper presents a signal processing framework for automatic anxiety level classification in a virtual reality exposure therapy system. Two types of biophysical data (heart rate and electrodermal activity) were recorded, pre-processed and passed through a feature extraction procedure that provided input for the real-time anxiety level classification algorithm. We showcase the mathematical and engineering techniques behind the procedures and conclude with the challenges encountered in our research and future development ideas. The proposed method provides a good estimate of the level of anxiety while having at the same time a reduced level of complexity, allowing implementation on equipment with limited computing resources. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Machine Learning Algorithms for Feature Extraction and Prediction of Bacterial Leaf Blight Disease in Paddy Fields 8

Comparative Study of Machine Learning Algorithms for Feature...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Krishna, Penugonda Seetha Rama Nagarajan, S. Annamalai University Dept. of Computer Science Engineering Tamilnadu Chidambaram India Government College of Engineering Srirangam Department of Computer Science and Engineering Trichy620012 India

ISBN: (纸本)9798350386578

Paddy farming plays a critical role in global food security, yet diseases like Bacterial Leaf Blight (BLB) pose significant threats to crop yield and quality. Early detection and accurate diagnosis are essential for effective disease management. This research study investigates machine learning methods for feature extraction and prediction of BLB in paddy fields. Utilizing a comprehensive dataset of paddy leaf images, several machine learning models including Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbours (kNN), and Gradient Boosting Machine (GBM) were trained and evaluated. Performance metrics such as accuracy, precision, recall, and F1-score were employed to assess the effectiveness of each model. The comparative analysis discusses the strengths and limitations of each method, focusing on those that demonstrate superior capability in early and accurate detection of BLB. These findings provide valuable insights for agricultural scientists and practitioners to enhance disease management strategies using modern machine learning techniques. By leveraging this knowledge, specialists can optimize interventions and improve agricultural practices to mitigate the impact of diseases like BLB on paddy farming and ensure global food security. © 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

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Localization

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Loca...

引用

2023 International Conference on Power, Instrumentation, Control and Computing, PICC 2023

作者： Anoopa, S. Salim, A. Nadera Beevi, S. College of Engineering Trivandrum Dept. of Computer Science and Engineering Kerala India Government Engineering College Thrissur Dept. of Computer Science and Engineering Kerala India Tkm College of Engineering and Technology Dept. of Computer Applications Kerala India

ISBN: (纸本)9798350334463

Video Anomaly Localization techniques are interesting and emerging tasks in computer vision that is used to locate the position of an anomalous object with bounding boxes. Convolutional neural network-based object localization methods have been developed which detect and classify objects with high precision and accuracy. Many algorithms have been developed for object detection and localization with excellent outcomes. These algorithms are fast RCNN, faster RCNN, and YOLO. In this paper, a comprehensive analysis of faster RCNN and YOLO V3 algorithms for anomaly localization is performed based on the parameters FPS, mAP, Precision, Recall and F1 Score. © 2023 IEEE.

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：