检索结果-内蒙古大学图书馆

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Garg, Kritika Sarker, Rahul Ahmad, Aaqib Kaur, Mehakpreet Teja, A.V. Ravi Dept. of Electrical Engineering IIT Ropar Rupnagar India Dept. of Computer Science Engineering PU Patiala India

ISBN: (纸本)9781665464543

This document is a model with an accurate estimation of the battery’s State Of Charge (SOC), which is pivotal for prime performance and optimal lifespan of the rechargeable batteries. Though traditional methods, like Open Circuit Voltage (OCV) and Coulomb Counting (CC), are advantageous, they suffer from several limitations, such as sensitivity to temperature changes, frequent calibration, ageing effects, and measurement inaccuracies. This paper proposes 1-D Kalman Filter (1-D HKF) with an approach that incorporates the OCV and CC results into the state space model for better and more accurate SOC estimation. So, the model is called 1-D HKF or Hybrid Kalman filter that, influenced the long-term stability and estimation accuracy of CC and the accuracy of OCV at specific points to get over the individual limitations. The model trained by 1-D HKF adapts itself and adjusts the gain based on the uncertainties of each measured value to ensure optimal value information. So, We evaluate the performance of the 1-D HKF versus the traditional methods Kalman Filter using examples and exploratory data. The proposed approach illustrates significantly improved accuracy and robustness across various operating conditions, including varying temperatures and discharge rates. © 2024 IEEE.

关键词： State of charge

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

Exploring the Efficacy of Modified Transfer Learning in Identifying Parkinson’s Disease Through Drawn Image Patterns 2

Exploring the Efficacy of Modified Transfer Learning in Iden...

引用

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Daiyan, Nabil Haque, Md Rakibul Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh

ISBN: (纸本)9798331508227

Parkinson’s disease (PD) is a progressive neurodegenerative condition characterized by the death of dopaminergic neurons, leading to various movement disorder symptoms. Early diagnosis of PD is crucial to prevent adverse effects, yet traditional diagnostic methods are often cumbersome and costly. In this study, a machine learning-based approach is proposed using hand-drawn spiral and wave images as potential biomarkers for PD detection. Our methodology leverages convolutional neural networks (CNNs), transfer learning, and attention mechanisms to improve model performance and resilience against overfitting. To enhance the diversity and richness of both spiral and wave categories, the training dataset undergoes augmentation to increase the number of images. The proposed architecture comprises three phases: utilizing pre-trained CNNs, incorporating custom convolutional layers, and ensemble voting. Employing hard voting further enhances performance by aggregating predictions from multiple models. Experimental results show promising accuracy rates. For spiral images, weighted average precision, recall, and F1-score are 90%, and for wave images, they are 96.67%. After combining the predictions through ensemble hard voting, the overall accuracy is 93.3%. These findings underscore the potential of machine learning in early PD diagnosis, offering a non-invasive and cost-effective solution to improve patient outcomes. ©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

Efficient Hyperspectral data Compression using 3D Convolutional Autoencoder 3

Efficient Hyperspectral Data Compression using 3D Convolutio...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Afrin, Afsana Mamun, Md. Al Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350388282

Hyperspectral image has large size due to abundance of spectral bands preventing efficient storage and transmission in real-time applications. This paper introduces a 3dimensional convolutional autoencoder (CAE) for hyperspectral data compression, utilizing CAE for both compression and subsequent decompression. Our method achieves improved Compression Ratio (CR) values of 982 and 960 on the KSC and Botswana datasets, along with better Peak Signal-to-Noise Ratio (PSNR) results of 55.29 and 52.64, surpassing existing 2D convolutional autoencoder-based HSI compression. Our approach also shows negligible differences in classification accuracy between original image and the reconstructed version of the compressed image, confirming its effectiveness in real-world applications. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Network in Remote Sensing-Based Climate Detection Using Machine Learning Algorithms

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 400-408页

作者： Srinivas, Jhade Raju, Ch VV Narasimha Sasikala, C. Bhaskar, Parumanchala Panyala, Amarendra Reddy Priya, Divya Department of Computer Science and Engineering - Data Science K G Reddy College of Engineering and Technology Moinabad Telangana Hyderabad India Information Technology Marri Laxman Reddy Institute of Technology and Management Dundigal Telangana Hyderabad 500043 India Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Santhiram Engineering College Nandyal India Department of Computer Science and Engineering (Data Science) Malla Reddy University Telangana Hyderabad India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Effective monitoring of the environment over a large area will require mobilization of a considerable amount of information. Otherwise, the use of traditional methods will prove to be costly and would take up so much time. Also, assessing the land cover changes between two times is one of the other methods which can be adopted to measure the environmental sustainability. Using ML techniques for predictive modeling in remote sensing has emerged as a useful approach in solving some of the environmental and climatic challenges. This research proposes a novel method in remote sensing image-based climate detection utilizing cloud computing and machine learning algorithms. Here, the cloud computing module is used in the collection of remote sensing images for the detection of climate changes. Then, the collected image is processed for noise removal as well as normalization. The processed image is segmented, and features are extracted utilizing a fuzzy K-clustering-based contour Gaussian model with graph cut Boltzmann CNN. Experimental analysis is carried out for various remote sensing-based climate change datasets in terms of training accuracy, random precision, AUC, recall, and F-measure. The proposed technique obtained 97% of training accuracy, 95% of random precision, 96% of recall, 93% of AUC, and 94% of F-measure. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Climate detection Cloud computing Contour Gaussian model Machine learning algorithms Remote sensing images

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

Enhancing Dietary Monitoring using Deep Learning: Food Recognition and Calorie Estimation 15

Enhancing Dietary Monitoring using Deep Learning: Food Recog...

引用

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

作者： Suneela, M. Sahithi, Mandadi Vamsi, Nuthalapati Naik, Nunsavathu Balaji Chowdary, Narra Sujitha Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India

ISBN: (纸本)9798350370249

The project 'Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation' introduces an innovative method aimed at improving dietary tracking and fostering healthier eating habits. By employing cutting-edge deep learning techniques, its core objective is to precisely identify various food items and rapidly estimate their caloric content, offering users advanced and personalized monitoring capabilities. Utilizing the Python programming language alongside the MobileNet architecture model, the project underwent rigorous training and evaluation using the expansive Food 101 dataset, comprising 37,046 food images distributed across 101 distinct classes. Notably, the model demonstrated exceptional performance, achieving a training accuracy of 97.02% and a validation accuracy of 98.17%, highlighting the efficacy of this approach in accurately categorizing a wide array of food items. This system provides users with several crucial functionalities. Furthermore, it furnishes users with essential insights by estimating the caloric content of recognized foods, facilitating effective monitoring of dietary intake. The intelligent diet monitoring capabilities enabled by Food Recognition and Calorie Estimation empower users to make informed choices regarding their dietary preferences. Through the continuous tracking and analysis of their daily food consumption, users can glean valuable insights into their nutritional habits, set personalized goals, and make necessary adjustments to achieve a well-balanced and healthy diet. Enhancing Dietary Monitoring Using Deep Learning:Food Recognition And Calorie Estimation stands as a prominent illustration of successful implementation of deep learning techniques, particularly with the utilization of the MobileNet architecture, for food recognition and calorie estimation. With its remarkable accuracy, real-time processing capabilities, and intelligent monitoring features, this project has the potential to revolutioni

关键词： Convolutional Neural Network (CNN) algorithm datasets MobileNet architecture Web application

来源：评论

学校读者我要写书评

暂无评论

Advancing Ophthalmology through Transfer Learning and Channel-Wise Attention for Retinal Disease Classification 6

Advancing Ophthalmology through Transfer Learning and Channe...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Islam, Sudipta Progga Alam, Ashraf Ul Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350385779

The global incidence of ocular disorders, which impacts more than 2.2 billion people, requires innovative approaches to ensure early and accurate diagnosis. This paper explores the integration of artificial intelligence (AI) in ophthal-mology, focusing on retinal diseases like cataracts, glaucoma, and diabetic retinopathy. The utilization of AI enables remote examinations and consultations, providing a crucial advantage in early disease detection. This study introduces a comparative analysis of state-of-the-art models, combining pre-trained convolutional neural networks (CNNs) and incorporating a channel-wise attention mechanism for enhanced discriminative ability. The proposed hybrid model, combining EfficientNetBO and Inception V3 with channel-wise attention mechanism, exhibits a remarkable accuracy of 98.13%, outperforming standalone models and other combinations. The findings underscore the efficacy of combined architectures and the integration of attention mechanisms in advancing the classification of retinal diseases. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Designing a Graphics Processing Unit for 2D Rendering on FPGA for Educational Purpose 3

Designing a Graphics Processing Unit for 2D Rendering on FPG...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Saha, Rupak Sadad, Nahin Ul Mondal, Md. Nazrul Islam Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798350388282

In this paper, design and implementation of a 2D graphics processing hardware unit using FPGA for educational purpose is presented. We propose a more simple & minimalist GPU architecture, which is flexible and easy to understand than existing industrial GPUs. We present a platform for understanding GPU architecture by implementing of graphics algorithms on FPGA for students to use this in laboratories. Students can be benefited from this work as it can be used as a base understanding tool in terms of GPU architecture. It can also be extended to be used in cross disciplinary applications like 3D rendering, computer vision and signal processing visualisation. This research includes descriptions of hardware realization of 2D rasterization rendering algorithms. Hardware Description Language (HDL) called verilog is utilized in designing the architecture. Xilinx Vivado Design Suite software is used for FPGA implementation, targeting Artix 7 FPGA board, which allows users to comprehend the fundamental ideas of hardware design and their applications in graphics rendering. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis using Speech Recognition for Improved Customer Operations Using Convolutional Neural Networks 2

Sentiment Analysis using Speech Recognition for Improved Cus...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Hema, D. Deva Sujith, N. Rithika, P.J. Bhavesh, S. Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Dept. of Computer Science SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9798331541217

This paper presents the application of advanced speech recognition technologies to transcribe and analyze customer interactions, enhancing both business efficiency and customer experience. Motivated by the need for human-like interaction in automated systems, our work introduces "Humanization through Automation," a system designed to retain personal touches while optimizing operational efficiency. The approach involves capturing high-quality audio, followed by noise reduction and normalization to facilitate effective feature extraction using Spectrogram Conversion and Mel-Frequency Cepstral Coefficients (MFCC). The use of Convolutional, Pooling, and Dropout Layers refines detail detection and reduces overfitting, while Fully Connected Layers integrate and analyze features, using activation functions for accurate classification and sentiment analysis. By embedding sentiment detection within Interactive Voice Response (IVR) systems via Convolutional Neural Networks (CNNs), our system can interpret emotional tones, allowing dynamic responses and connecting customers with suitable representatives based on emotional state. This integration of speech recognition and sentiment analysis not only elevates interaction quality but also strengthens customer relationships, optimizes sales strategies, and fosters organizational growth, transitioning from traditional customer service models to solutions emphasizing efficiency and personalization. © 2024 IEEE.

关键词： Sales

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：