检索结果-内蒙古大学图书馆

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Gill, Kanwarpartap Singh Anand, Vatsala Gupta, Rupesh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350308167

A frequent degenerative joint illness that damages the cartilage, the protective tissue that covers the ends of bones inside a joint, is osteoarthritis, sometimes known as OA. It can result in discomfort, stiffness, swelling, and a reduction in the range of motion in the joints that are afflicted. Osteoarthritis may affect any joint, including the hands, feet, and shoulders, although it most frequently affects weight-bearing joints like the knees, hips, and spine. Age, obesity, joint damage, repeated joint usage, genetic susceptibility, and other underlying medical issues such metabolic disorders are all risk factors for developing osteoarthritis. The categorization of osteoarthritis in this research is done using mobilenetv3 neural network architecture. In applications where computing resources are constrained, such as on mobile phones or other edge devices, mobilenetv3 is a lightweight convolutional neural network (CNN) architecture that is created to be effective and suited for deployment on mobile devices. To effectively fight osteoarthritis in its beginning stages, it is important to first determine its type or category. Our mobilenetv3 model is very good at classifying osteoarthritis, achieving an accuracy rate of over 80%. © 2023 IEEE.

关键词： CNN Confusion matrix Deep Learning mobilenetv2 model model Training Osteoarthritis

来源：评论

学校读者我要写书评

暂无评论

Investigation of interfacial debonding identification for concrete filled steel tube columns based on acoustic signals

引用

MEASUREMENT 2025年 240卷

作者： Cao, Hui Li, Jiaxin Chen, Xinghua Chongqing Univ Sch Civil Engn Chongqing Peoples R China Chongqing Univ MOE Key Lab New Technol Construct Cities Mt Area Chongqing Peoples R China China Three Gorges Univ Hubei Key Lab Disaster Prevent & Mitigat Yichang Peoples R China China Three Gorges Univ Coll Civil Engn & Architecture Yichang 443002 Hubei Peoples R China

A method was proposed to address challenges in detecting debonding in concrete-filled steel tube (CFST) columns by analyzing acoustic signals. In this approach, wavelet time-frequency diagrams are initially derived through the application of continuous wavelet transform to acoustic signals acquired from tapping on columns. The wavelet time-frequency diagrams serve as data samples for training the mobilenetv2 convolutional neural network model in order to identify concrete debonding. The laboratory test results show that the mobilenetv2 model achieved 100 % accuracy for both the training and verification sets, and 99 % accuracy for the test set. Four CFST columns in a high-rise building under construction were also measured. The findings indicate a recognition accuracy ranging from 86.7 % to 90 % and an error rate that falls within an acceptable range. These results confirm the viability of the method outlined in this paper for detecting debonding in CFST columns using acoustic signals.

关键词： Acoustic signal Debonding identification Wavelet time-frequency diagram mobilenetv2 model Concrete filled steel tube column

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Activity Recognition in Smart Surveillance Using Transfer Learning

引用

NATIONAL ACADEMY SCIENCE LETTERS-INDIA 2025年 1-5页

作者： Sharma, Kanta Prasad Jayaprakash, B. Bhosle, Nilesh Raju, S. Srinadh Chohan, Mandeep Kaur Madan, Heena Alkhayyat, Ahmed Bareja, Lakshay Amity Univ Amity Sch Engn & Technol ASET Dept CSE Greater Noida Campus Noida India JAIN Sch Sci Dept Comp Sci & IT Bangalore Karnataka India NIMS Univ Rajasthan NIMS Inst Engn & Technol Dept Comp Sci & Artificial Intelligence Jaipur India Raghu Engn Coll Dept Comp Sci & Engn Visakhapatnam Andhra Pradesh India Vivekananda Global Univ Dept Comp Sci & Engn Jaipur India Chandigarh Engn Coll Chandigarh Grp Coll Jhanjeri Dept Comp Sci & Engn Mohali Punjab India Islamic Univ Coll Tech Engn Najaf Iraq Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura Punjab India

Human activity recognition is vital in areas like healthcare, smart homes, and surveillance. With deep learning advancements, traditional handcrafted features have been replaced by more effective methods. This study applies the mobilenetv2 model, fine-tuned using transfer learning, for activity recognition in smart surveillance systems. Initially trained on the ImageNet dataset, mobilenetv2 was adapted for the UCF101 benchmark dataset, which includes 101 diverse activities like guitar playing and jumping. Our goal was to boost recognition accuracy. Evaluation metrics such as accuracy, precision, F1-score, AUC, and RMSE showed the model's exceptional performance. The fine-tuned mobilenetv2 achieved a 97.05% accuracy, demonstrating its reliability and effectiveness for human activity recognition in smart surveillance applications.

关键词： Transfer learning Machine learning Deep learning Activity recognition mobilenetv2 model UCF101 dataset Deep convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Music Genre Classification using Modified MobileNet Deep Learning model 2

Automated Music Genre Classification using Modified MobileNe...

引用

2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS)

作者： Bohra, Manvi Kumar, Indrajeet Shivam Graph Era Hill Univ Dehradun Dept Comp Sci & Engn Dehra Dun India Graph Era Hill Univ Dehra Dun India Graph Era Deemed Be Univ Dehra Dun 248001 Uttarakhand India

ISBN: (纸本)9798350391558;9798350379990

This research work intends to design and develop the music genre classification process for any given audio file and extract features from audios to understand the audio graph. The entire learning process has been conducted using a pre-trained Convolutional Neural Network (CNN) and the mobilenetv2 model with fine-tuning. Music Genre Classification, which categorizes music based on composition, such as the beat, is a focal point of this work. In recent years, music genre classification has become more approachable and popular with more genres emerging in the music sector that can now be automatically classified. The automated classification technology is also a suitable solution to reduce the effort involved in selecting music files manually. This work reviews a recent topic in the field of identification called music genre classification. The proposed model aids in identifying music files and creating a comprehensive playlist of songs. Manual selection of music files is not only difficult but also time-consuming. The modified mobilenetv2 model yields outstanding performance in terms of accuracy, precision, recall, and F1-score.

关键词： Music Genre Classification Fourier Transformation Spectrogram CNN model mobilenetv2 model

来源：评论

学校读者我要写书评

暂无评论

KartalOl: a new deep neural network framework based on transfer learning for iris segmentation and localization task—new dataset for iris segmentation

引用

Iran Journal of Computer Science 2023年第4期6卷 307-319页

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Ul. Nowowiejska 15/19 Warsaw 00-665 Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Faculty of Engineering Arak University Arak Iran Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Tehran Iran Stanford University Stanford United States

Iris segmentation and localization in unconstrained environments are challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature have somehow mitigated some of the above-mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture initialized with a pre-trained mobilenetv2 model. In addition, to better study the detectors in iris recognition scenarios, we have collected 1000 images. The provided dataset (KartalOl) is made publicly available for the research community. In the proposed framework, to have better generalization, we fine-tuned the mobilenetv2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Likewise, data augmentation techniques are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa, along with the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The implementation source code of KartalOl is made publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © The Author(s) 2023.

关键词： Iris segmentation Localization mobilenetv2 model Unconstrained environment

来源：评论

学校读者我要写书评

暂无评论

Pistachio Species Classification: Leveraging Machine Learning for Quality Assurance and Market Optimization

Pistachio Species Classification: Leveraging Machine Learnin...

引用

2024 International Conference on Information Science and Communications Technologies, ICISCT 2024

作者： Bhuria, Ruchika Bordoloi, Dibyahash Kumar, Bura Vijay Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Uttarakhand Dehradun 248002 India School of Computer Science & Artificial Intelligence Sr University Warangal India

ISBN: (纸本)9798331527921

Leveraging a large dataset of 2,148 high-resolution photos, this work proposes a fresh method for classifying pistachio species using a mobilenetv2 deep learning model. The suggested system seeks to automate the classification process, hence improving accuracy and efficiency over conventional hand sorting methods. The dataset consists of pictures of several pistachio varieties, so guaranteeing strong representation for good model training. After data preparation and augmentation, transfer learning was used to fine-tune the mobilenetv2 architecture producing a quite good classification model. The model had an overall accuracy of 94%;specific class measures show excellent performance. For several classes, specifically, precision and recall scores peaked around 99%;F1-scores across most species often exceeded 0.90. The classification report shows the success of the suggested model by displaying F1-scores demonstrating balanced performance in different species and accuracy values ranging from 0.81 to 0.99, so separating between various species. This study shows the possibilities of deep learning in agricultural uses, especially in optimizing pistachio processing and guaranteeing the quality of goods on the market. The results imply that the mobilenetv2 model not only simplifies classification problems but also provides a scalable solution fit for like agricultural difficulties. © 2024 IEEE.

关键词： Accuracy Agriculture Artificial intelligence Deep learning Education Empowerment Health Innovation mobilenetv2 model Partnership Pistachio species classification Resilience Sustainable Technology

来源：评论

学校读者我要写书评

暂无评论

Classification of skin diseases based on improved mobilenetv2 33

Classification of skin diseases based on improved MobileNetV...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Cheng Yu Jia Lin Wei Liu Yuan Zhen Sun Lu Shanghai Inst Technol Shanghai 201418 Peoples R China

ISBN: (纸本)9781665440899

In order to realize the classification research of skin diseases on portable devices, the neural network model can be better applied to embedded and mobile devices. This article explores the impact of ECA module on the model complexity and accuracy. By embedding ECA module into the mobilenetv2 model, the accuracy of the model is significantly improved without increasing the complexity of the model. Due to the complex network structure of neural network, it has a high requirement on hardware equipment and has a great amount of calculation, which cannot be run on mobile and embedded devices, and cannot deal with the problem of portable identification of skin lesion images on mobile devices. In this article, a deep learning model based on improved mobilenetv2 is proposed, which has higher accuracy and faster recognition rate, and can realize the classification and recognition of skin lesion images on portable devices. By comparing with the current advanced network model, it is verified that this model can improve the network performance without increasing the complexity of the model and at the same time improving the recognition rate.

关键词： Classification of skin diseases Neural network ECA module mobilenetv2 model

来源：评论

学校读者我要写书评

暂无评论

Classification of skin diseases based on improved mobilenetv2

Classification of skin diseases based on improved MobileNetV...

引用

第33届中国控制与决策会议

作者： CHENG Yu Jia LIN Wei LIU Yuan Zhen SUN Lu Shanghai Institute of Technology

In order to realize the classification research of skin diseases on portable devices,the neural network model can be better applied to embedded and mobile *** article explores the impact of ECA module on the model complexity and *** embedding ECA module into the mobilenetv2 model,the accuracy of the model is significantly improved without increasing the complexity of the *** to the complex network structure of neural network,it has a high requirement on hardware equipment and has a great amount of calculation,which cannot be run on mobile and embedded devices,and cannot deal with the problem of portable identification of skin lesion images on mobile *** this article,a deep learning model based on improved mobilenetv2 is proposed,which has higher accuracy and faster recognition rate,and can realize the classification and recognition of skin lesion images on portable *** comparing with the current advanced network model,it is verified that this model can improve the network performance without increasing the complexity of the model and at the same time improving the recognition rate.

关键词： Classification of skin diseases Neural network ECA module mobilenetv2 model

来源：评论

学校读者我要写书评

暂无评论

The Design of Lightweight and Multi Parallel CNN Accelerator Based on FPGA 8

The Design of Lightweight and Multi Parallel CNN Accelerator...

引用

IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Li Zong-ling Wang Lu-yuan Yu Ji-yang Cheng Bo-wen Hao Liang China Acad Space Technol Beijing Inst Spacecraft Syst Engn Beijing 100094 Peoples R China

ISBN: (纸本)9781538681787

In this paper, a lightweight, parallel computing and storage, high energy efficiency CNN accelerator based on FPGA was designed. According to the characteristics of forward inference structure of deep convolution neural network, the parallel characteristics of convolution operation are analyzed from two aspects of computational efficiency and data reuse rate, and the full parallel pipeline implementation of full connection layer is studied. The accelerator has adopted full parallel pipeline structure to improve the computational efficiency, and making full use of various convolution parallel computing architectures to balance the requirements of computing efficiency, parameters and data load bandwidth, a lightweight and tightly coupled accelerator architecture is designed based on the characteristics of hardware resources such as internal computing, logic and storage in FPGA. In the validation test of open data set based on ImageNet, the accelerator is deployed on Xilinx Virtex7-690T FPGA with 28nm technology, under the working frequency of 200MHz, the maximum number of multiplication and addition operation is 1728 times per cycle, the peak operation rate is 691.2Gops, the energy ratio is 138.24Gops/w. In the end, the classification results are consistent with the processing results using double-precision floating-point data format.

关键词： Convolution neural network mobilenetv2 model Lightweight Parallel compute and storage High energy efficiency ratio FPGA

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：