检索结果-内蒙古大学图书馆

6th International Congress on Human-Computer Interaction, Optimization and Robotic applications, HORA 2024

作者： Jawad Khudhur, Ali kadhim Mohammed Electrical and Computer Engineering Altinbas University Artificial Intelligence Engineering Department College of Engineering Al-Ayen University Thi-Qar Iraq

ISBN: (纸本)9798350394634

Breast cancer is a huge global health challenge, ranking as the second-largest cause of mortality worldwide. Early identification is crucial for effective treatment and better survival rates. Various screening methods, including mammography, ultrasonography, and thermography, have been developed to aid in the early diagnosis of breast cancer. Leveraging image processing techniques and deep learning algorithms, radiologists can boost the accuracy of detecting breast problems. This paper suggests the use of an upgraded Deep Convolutional neural Network (DCNN) for the early and accurate identification and diagnosis of breast cancer. Setting itself apart from earlier approaches, this work leverages a DCNN with 12 layered processing layers, leading to better detection and diagnosis accuracy. The Mini Mammographic Database (MIAS) serves as the dataset for testing the proposed system's performance. Results reveal that the Deep CNN achieves exceptional accuracy, reaching 99.1%. Furthermore, comparative analysis against related research demonstrates the advantages of the proposed DCNN-based technique. This research contributes to expanding the area of breast cancer diagnosis and emphasises the potential of deep learning to enhance diagnosis and improve. © 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

Performance Analysis of Deep Learning Algorithms Implemented Using PyTorch in image Recognition 11th

Performance Analysis of Deep Learning Algorithms Implemented...

引用

11th International Conference on applications and Techniques in Cyber Intelligence, ATCI 2023

作者： Yuan, Jie Shandong Huayu University of Technology Dezhou China

With the rapid development of artificial intelligence technology, image recognition has become a key technology in many fields. This paperaims to analyze the performance of image recognition tasks through the implementation of deep learning algorithms using PyTorch. This paperintroduces the selection and preprocessing techniques of datasets, including normalization, data augmentation, size adjustment, and batch processing, which provide high-quality input data for model training. In terms of deep learning model design, Convolutional neural Network was adopted, CNN was used as the infrastructure and the cross entropy loss function and Adam optimizer were selected for model training. The implementation details of PyTorch demonstrate the model construction, training process, and debugging, as well as how to use PyTorch's DataLoader class to improve data loading efficiency. The Results and Discussion section presents the training results of the model, where the CNN model achieves the highest accuracy of 99% in image recognition tasks, and the loss function value ultimately stabilizes at 0.02, indicating that the model has efficient learning and generalization capabilities. Performance comparison experiments show that, the CNN implemented by PyTorch outperforms MXNet and Caffe in terms of frame rate and processing delay, with a frame rate between 51FPS-79FPS and a minimum processing delay of 308ms. The analysis of practical application scenarios further explores the potential application of the model in fields such as medical image analysis, autonomous driving, retail industry, and safety monitoring, and points out challenges such as data privacy, model generalization ability, and computational resource limitations. © 2024 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Special Session: Architecture-Level DCIM Technologies for Edge AI Computing applications 37

Special Session: Architecture-Level DCIM Technologies for Ed...

引用

37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024

作者： Hsu, Chun-Lung Chen, Hsuan-Yu Chen, Yi-Lin Taoyuan320317 Taiwan

ISBN: (纸本)9798350366884

Nowadays, deep neural networks (DNNs) and artificial intelligence (AI) are widely used in image recognition, autonomous vehicles, speech recognition, and natural language processing. However, the Von-Neumann bottleneck slows down data retrieval from memory, consuming significant time and energy. The technique of computing in memory (CIM) (including analog CIM (ACIM) and digital CIM (DCIM)) has emerged as a solution, integrating computing logic into memory to improve power efficiency by reducing data movement. Despite CIM's advantages, it still faces challenges like accuracy, adaptability and dataflow flexibility due to the computing complexity. This paper addresses the architecture-level digital computing in memory (DCIM) framework to discuss the abovementioned issues, ensuring the features of low-power, high-precision, reconfigurability, and repairability across diverse DNN applications. Additionally, for large-scale language model applications like LLMs and Transformers, a scalable DCIM chiplet architecture is introduced, leveraging 2.5D/3D heterogeneous packaging technologies to achieve flexible scalability, meeting various edge AI computing requirements. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigation for the Need of Traditional Data-Preprocessing when Applying artificial neural networks to FMCW-Radar Data 29

Investigation for the Need of Traditional Data-Preprocessing...

引用

29th International Conference on Systems, Signals and image processing (IWSSIP)

作者： Valti, Jakob Mendez, Javier Mauro, Gianfranco Cabrera, Antonio Issakov, Vadim Infineon Technol AG Neubiberg Germany Tech Univ Carolo Wilhelmina Braunschweig Braunschweig Germany

ISBN: (数字)9781665495783

ISBN: (纸本)9781665495783

Robust functionality of autonomous driving vehicles relies on their ability to detect obstables and various scenarios on the road. This can be only achieved by applying robust, fast and efficient AI-based signal processing to radar data. In this work we present an empirical investigation on the question, whether one can apply artificial neural networks (ANNs) directly to frequency modulated continuous wave (FMCW) radar raw data. We show that preproceessing is not necessary if one has enough raw data. In our experiment we have data of 153 648 frames collected with a 60 GHz FMCW radar. We compare systematically the options of preprocessing the data using variational autoencoder, applying traditional preprocessing or omit data-preprocessing and apply ANN directly to raw data. We show that the last option results in 28% faster signal processing and highest accuracy. This is a promising result, since it enables edge computing and direct signal processing at the sensor level.

关键词： artificial neural networks Data preprocessing Radar applications

来源：评论

学校读者我要写书评

暂无评论

Generating Adversarial images in Quantized Domains

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2022年 17卷 373-385页

作者： Bonnet, Benoit Furon, Teddy Bas, Patrick Univ Rennes CNRS IRISA INRIA F-35000 Rennes France Ecole Cent Lille CRIStAL Lab CNRS UMR 9189 F-59650 Lille France

Many adversarial attacks produce floating-point tensors which are no longer adversarial when converted to raster or JPEG images due to rounding. This paper proposes a method dedicated to quantize adversarial perturbations. This "smart" quantization is conveniently implemented as versatile post-processing. It can be used on top of any white-box attack targeting any model. Its principle is tantamount to a constrained optimization problem aiming to minimize the quantization error while keeping the image adversarial after quantization. A Lagrangian formulation is proposed and an appropriate search of the Lagrangian multiplier enables to increase the success rate. We also add a control mechanism of the l(infinity)-distortion. Our method operates in both spatial and JPEG domains with little complexity. This study shows that forging adversarial images is not a hard constraint: our quantization does not introduce any extra distortion. Moreover, adversarial images quantized as JPEG also challenge defenses relying on the robustness of neural networks against JPEG compression.

关键词： Computational and artificial intelligence neural networks feedforward neural network multi-layer neural network signal processing quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

A review on weight initialization strategies for neural networks

引用

artificial INTELLIGENCE REVIEW 2022年第1期55卷 291-322页

作者： Narkhede, Meenal V. Bartakke, Prashant P. Sutaone, Mukul S. Coll Engn Dept Elect & Telecommun Pune Maharashtra India

Over the past few years, neural networks have exhibited remarkable results for various applications in machine learning and computer vision. Weight initialization is a significant step employed before training any neural network. The weights of a network are initialized and then adjusted repeatedly while training the network. This is done till the loss converges to a minimum value and an ideal weight matrix is obtained. Thus weight initialization directly drives the convergence of a network. Therefore, the selection of an appropriate weight initialization scheme becomes necessary for end-to-end training. An appropriate technique initializes the weights such that the training of the network is accelerated and the performance is improved. This paper discusses various advances in weight initialization for neural networks. The weight initialization techniques in the literature adopted for feed-forward neural network, convolutional neural network, recurrent neural network and long short term memory network have been discussed in this paper. These techniques are classified as (1) initialization techniques without pre-training, which are further classified into random initialization and data-driven initialization, (2) initialization techniques with pre-training. The different weight initialization and weight optimization techniques which select optimal weights for non-iterative training mechanism have also been discussed. We provide a close overview of different initialization schemes in these categories. This paper concludes with discussions on existing schemes and the future scope for research.

关键词： Weight initialization Random initialization Interval based Variance scaling Data-driven initialization Unsupervised pre-training

来源：评论

学校读者我要写书评

暂无评论

Research on Deep Learning-Based Liver Tumor image Segmentation Techniques 4

Research on Deep Learning-Based Liver Tumor Image Segmentati...

引用

4th IEEE International Conference on Information Technology, Big Data and artificial Intelligence, ICIBA 2024

作者： Zeng, Bohao Chen, Xingqiong Mao, Jinghan Ran, Yingmei Chongqing Jiaotong University School of Mathematics and Statistics China Yunyang County People's Hospital China Fengdu General Hospital China Fengdu CH-Medicine Hospital China

ISBN: (纸本)9798350363586

Early detection and accurate diagnosis of liver tumors are crucial for patient prognosis. In recent years, deep learning techniques have made significant advancements in the field of medical image processing, particularly in liver tumor image segmentation. This paper reviews the latest research progress on deep learning-based liver tumor image segmentation techniques, focusing on the application of various deep learning models, including Convolutional neural networks (CNNs), U-Net, and its variants. By comparing the performance and efficiency of different methods, the advantages and disadvantages of each model in liver tumor segmentation tasks are discussed. Additionally, this paper proposes a new data preprocessing method called Color Preprocessing (CP), which effectively improves the segmentation accuracy of processed data under the same methods. Finally, future research directions are envisioned, highlighting the importance of deep learning technologies in improving the accuracy of liver tumor image segmentation and their potential clinical applications. © 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

Gesture Recognition for American Sign Language Using Pytorch and Convolutional neural Network 1st

Gesture Recognition for American Sign Language Using Pytorch...

引用

1st International Conference on Intelligent Systems and applications

作者： Sethia, Devashsih Singh, Pallavi Mohapatra, B. Galgotias Univ Dept Elect Elect & Commun Engn Gr Noida 201310 India

ISBN: (纸本)9789811965814;9789811965807

Human-computer interaction (HCI) is the most prevalent topic of active research due to the demand for machine learning and computer vision. American Sign Language (ASL) is one of the most popular languages used by deaf and dumb people in the world. The deaf and dumb people use hand gestures to communicate. Hand gestures vary from person to person in shape, size, scale, and image quality. Hence, nonlinearity exists in this problem. In the area of image processing, there has been tremendous progress made recently, and it's proven that neural networks have numerous applications in interpreting sign language. The recognition of ASL in real-time motion is employed using an efficient artificial intelligence tool, and Convolutional neural Network (CNN) has been proposed in this work. The dataset of 27,455 images of 25 English alphabets has been used to train and validate our model. The model is tested on 7172 images which were divided into many classes. The maximum validation accuracy of the model with enhanced data was found to be 99.8% which is better than many existing methods in real-time motion.

关键词： Sign language CNN Gesture recognition Pytorch

来源：评论

学校读者我要写书评

暂无评论

Segmentation of skin lesions image based on U-Net plus

引用

MULTIMEDIA TOOLS AND applications 2022年第6期81卷 8691-8717页

作者： Zhao, Chen Shuai, Renjun Ma, Li Liu, Wenjia Wu, Menglin Nanjing Tech Univ Coll Comp Sci & Technol Nanjing 211816 Peoples R China Nanjing Hlth Informat Ctr Nanjing 210003 Peoples R China Nanjing Med Univ Changzhou Peoples Hosp 2 Changzhou 213003 Jiangsu Peoples R China

In the medical field, melanoma is one of the most dangerous skin cancers. However, the accuracy rate of doctors' identification of melanoma is only 60%. Diagnosis requires higher technical experience and low fault tolerance for doctors who identify melanoma and other skin lesions. Therefore, the accurate segmentation of melanoma is of vital importance for clinical diagnosis and treatment. The current segmentation of melanoma is mainly based on fully connected networks (FCNs) and U-Net. Nevertheless, these two kinds of neural networks are prone to parameter redundancy, and the gradient disappears when depth increases, which reduces the Jaccard index of the skin lesion image segmentation model. To solve the above problems and improve the survival rate of melanoma patients, this paper proposes an improved skin lesion segmentation model based on U-Net++. In particular, we introduce a new loss function, which improves the Jaccard index of skin lesion image segmentation. The experiments show that our model has excellent performance on the segmentation of the ISIC2018 Task I dataset, and achieves a Jaccard index of 84.73%. The proposed method improves the Jaccard index of segmentation of skin lesion images and could also assist dermatological doctors in determining and diagnosing the types of skin lesions and the boundary between lesions and normal skin.

关键词： U-Net plus plus Melanoma Skin lesion segmentation Biomedical image processing Convolutional neural networks Dermoscopic images artificial intelligence Jaccard index

来源：评论

学校读者我要写书评

暂无评论

Fusion of Handcrafted Features and Deep Features to Detect COVID-19 1

引用

8th International Conference on Computer Vision and image processing (CVIP)

作者： Gunda, Koushik Chakraborty, Soumendu Culibrk, Dubravko Indian Inst Informat Technol Lucknow Lucknow Uttar Pradesh India Univ Novi Sad Inst Artificial Intelligence Novi Sad Serbia

ISBN: (数字)9783031585357

ISBN: (纸本)9783031585340;9783031585357

The COVID-19 pandemic's rapid growth has made it crucial to develop reliable and efficient diagnostic methods. In this study, we incorporate deep features and handcrafted features to provide a unique method for COVID-19 identification using chest X-rays. In order to extract high-level features from the chest X-ray pictures, we first use a convolutional neural network (CNN) that has already been trained to take advantage of deep learning. The discriminative information regarding COVID-19 infection is captured by the obtained deep features. In addition to the deep features, we also use manually created features that are meant to capture the unique features of COVID-19 in chest X-rays. Based on earlier study findings and domain understanding, these characteristics were manually constructed. They consist of statistical measures, shape-based characteristics, and texture descriptors. Comparing the performance of the classification with the standalone applications of convolutional and handcrafted features, we find that combining the features in our innovative framework enhances performance.

关键词： COVID-19 LGHP Convolutional neural networks LGB classifier Feature level fusion

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：