检索结果-内蒙古大学图书馆

2023 World Symposium on Digital Intelligence for Systems and Machines, DISA 2023

作者： Vranay, Dominik Katona, Martin Sinčák, Peter Department of Cybernetics and Artificial Intelligence Technical University of Košice Slovakia Faculty of Mechanical Engineering and Informatics University of Miskolc Hungary

ISBN: (纸本)9798350343533

This paper presents a comparative analysis of the performance of convolutional and capsule neural networks on a dataset with decreasing sizes of training data. The study evaluates both normal and pre-trained models on a dataset ranging from 10 to 7500 training samples to investigate the efficacy of capsule networks in handling smaller datasets, a common challenge in real-world applications. Results indicate that convolutional networks outperform capsule networks on larger datasets, but as the dataset size decreases, capsule networks show improved performance and eventually surpass convolutional networks. But with very small sizes, capsule networks show problems with their accuracy. Pre-training surprisingly does not improve the performance of CNN, especially for smaller datasets, however, pretrained CapsNet showed some improvements for smaller datasets. These findings suggest that capsule networks are more effective than convolutional networks for datasets with a specific size, and pre-training further improves their performance for smaller sizes. The study offers insights into the practical applicability of capsule networks in real-world scenarios with limited dataset sizes, aiding in the selection of appropriate network architectures for diverse datasets and applications. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

AI-Supported Pneumonia Diagnosis: Performance of Deep Learning Models and Synthetic Data Generation 27

AI-Supported Pneumonia Diagnosis: Performance of Deep Learni...

引用

27th IEEE Signal processing: Algorithms, Architectures, Arrangements, and applications, SPA 2024

作者： Atbas, Baran Calsskan, Efe Erdem, Oguzhan Trakya University Department of Electrical and Electronics Engineering Edirne22030 Turkey

ISBN: (纸本)9788362065486

Pneumonia, a respiratory infection that affects the lungs and leads to serious health complications, is diagnosed by physicians based on symptoms, physical exam findings and imaging tests such as chest X-rays, but these methods can be time-consuming and subjective. In this study, we propose a Convolutional neural Network (CNN) based pneumonia disease detection model utilizing X-ray images for accelerating diagnosis and initiate treatment early to prevent disease progression. Due to the insufficient number of original X-ray samples, we also produced synthetic images with our developed Deep Convolutional Generative Adversarial Network (DC-GAN) model. We comparatively evaluated the performance of our models with pretrained VGG16 and ResNet50 models on synthetic and original image datasets separately and combined. Our results show that all models performed best with the synthetic dataset and also the combined set expanded with synthetic data gave better results in all cases than using the original data alone. The average test accuracy results of all models were obtained as 93%, 89% and 91% with synthetic, original and combined datasets, respectively. Thus, it proves that the good quality of the produced synthetic images that can be used to solve the problem of medical image data need, especially in artificial intelligence-based decision support systems. When the models were compared, our CNN model achieved the best performance in all scenarios with the accuracy values of 95%, 91% and 93% with synthetic, original and combined datasets, respectively. © 2024 Division of Signal processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

International Conference on artificial Intelligence and Its Practical applications in the Age of Digital Transformation, I2COMSAPP 2024

International Conference on Artificial Intelligence and Its ...

引用

International Conference on artificial Intelligence and Its Practical applications in the Age of Digital Transformation, I2COMSAPP 2024

ISBN: (纸本)9783031714283

The proceedings contain 21 papers. The special focus in this conference is on artificial Intelligence and Its Practical applications in the Age of Digital Transformation. The topics include: Enhancing Advanced Time-Series Forecasting of Electric Energy Consumption Based on RNN Augmented with LSTM Techniques;collective Intelligence for Model Transformation by Example;artificial Intelligence in Tourism Sector: Analysis Study;initial Steps Required for Archaeological image processing;digital Transformation Based on Cutting-Edge Technologies Case Study: Mauritania 4.0;hybrid Approach to Define Axioms of the Multimedia Ontology of the Archaeological Field;benchmarking Outlier Detection: Integrating Classical Methods and Deep Learning Techniques for Advanced Fault Analysis;real-Time Torque and Drag Prediction in Oilwell Drilling: A Comparative Study of Machine Learning Models;maximizing Total Net Revenue for the Identical Parallel Machines Order Acceptance and Scheduling Problem with Sequence-Dependent Setup Times;robust and Intelligent Fuzzy Logic Controllers for a Differential Mobile Robot Trajectory Tracking;face Detection Based on Deep Learning Approaches: A Comparative Study;A Novel artificial Intelligence-Based Intrusion Detection System—NAI2DS;deep and Wide neural networks for Distinguisher Attacks;using Machine Learning Techniques for Multi-agent Systems Testing;a Smart City Model Based on artificial Intelligence for Disaster Risk Management in the Arabic Countries;evaluating Naive Bayes Classifiers for Traffic Crash Prediction in Rome, Italy: A Comparative Examination;internet of Things and the Smart Building Sector;securing Smart Homes: A Cloud-Based IoT Approach to Intelligent Home Security;adaptive Model Predictive Control for Achieving Lane Tracking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

International Conference on artificial Intelligence and Its Practical applications in the Age of Digital Transformation, I2COMSAPP 2024

International Conference on Artificial Intelligence and Its ...

引用

International Conference on artificial Intelligence and Its Practical applications in the Age of Digital Transformation, I2COMSAPP 2024

ISBN: (纸本)9783031714252

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating the dynamic optimization strategies of Adam and AdaGrad 13

Integrating the dynamic optimization strategies of Adam and ...

引用

13th International Conference on Intelligent Control and Information processing, ICICIP 2025

作者： Huang, Zhixuan Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798331516147

artificial intelligence (AI) has been a key research area since the 1950s, initially focused on using logic and reasoning to create systems that understand language, control robots, and offer expert advice. With the rise of big data and deep learning, AI has advanced in applications like recommendation systems, image recognition, and machine translation, primarily through optimizing loss functions in deep neural networks to improve accuracy and reduce training *** descent is the core optimization method but faces challenges like slow convergence and local minima. To overcome these, algorithms like Momentum, AdaGrad, RMSProp, Adadelta, Adam, and Nadam have been developed, introducing momentum and adaptive learning rates to accelerate convergence. This paper presents a new optimization algorithm that combines the strengths of Adam and AdaGrad, offering better adaptability to different learning rates. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Usage of Electroimpedance Tomography along with artificial Intelligence in Application Development in the field of Medicine 32

The Usage of Electroimpedance Tomography along with Artifici...

引用

32nd Telecommunications Forum, TELFOR 2024

作者： Musikic, Milan University of Novi Sad Faculty of Technical Sciences Department for Computer Engineering and Communications Serbia

ISBN: (数字)9798350391060

ISBN: (纸本)9798350391053

This study investigates the integration of Electroimpedance Tomography (EIT) with Machine Learning (ML) and Deep Learning (DL) for enhanced object detection and imaging in medical and robotics applications. The study encompasses data collection, processing, and image construction, along with algorithms for evaluation and classification. The validity of the system is done by assessing algorithm accuracy by comparing the system results with the physical results. The study also identifies the areas for future improvement such as measurement complexity and data collection automation, underscoring EIT's potential for advancing diagnostics. © 2024 IEEE.

关键词： Semiconductor device measurement Electrical impedance tomography Automation Machine learning algorithms Impedance measurement neural networks Real-time systems Impedance Probes Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

image Test Libraries for the on-line self-test of functional units in GPUs running CNNs 28

Image Test Libraries for the on-line self-test of functional...

引用

28th IEEE European Test Symposium (ETS)

作者： Ruospo, A. Gavarini, G. Porsia, A. Reorda, M. Sonza Sanchez, E. Mariani, R. Aribido, J. Athavale, J. Politecn Torino DAUIN Turin Italy NVIDIA Santa Clara CA USA

ISBN: (纸本)9798350336344

The widespread use of artificial intelligence (AI)based systems has raised several concerns about their deployment in safety-critical systems. Industry standards, such as ISO26262 for automotive, require detecting hardware faults during the mission of the device. Similarly, new standards are being released concerning the functional safety of AI systems (e.g., ISO/IEC CD TR 5469). Hardware solutions have been proposed for the in-field testing of the hardware executing AI applications;however, when used in applications such as Convolutional neural networks (CNNs) in image processing tasks, their usage may increase the hardware cost and affect the application performances. In this paper, for the very first time, a methodology to develop high-quality test images, to be interleaved with the normal inference process of the CNN application is proposed. An image Test Library (ITL) is developed targeting the on-line test of GPU functional units. The proposed approach does not require changing the actual CNN (thus incurring in costly memory loading operations) since it is able to exploit the actual CNN structure. Experimental results show that a 6-image ITL is able to achieve about 95% of stuck-at test coverage on the floating-point multipliers in a GPU. The obtained ITL requires a very low test application time, as well as a very low memory space for storing the test images and the golden test responses.

关键词： Deep neural networks Reliability On-line Self-test Fault Injection Functional Safety

来源：评论

学校读者我要写书评

暂无评论

Research on EEG technology based on convolutional neural network 6

Research on EEG technology based on convolutional neural net...

引用

2023 IEEE 6th International Conference on Information Systems and Computer Aided Education, ICISCAE 2023

作者： Xun, Yuqing Tianjin University of Science and Technology Tianjin China

ISBN: (纸本)9798350313444

Convolutional neural net is an advanced neural network whose structure consists of multiple convolutional layers and pooling layers, and its application in the field of image processing is outstanding. As an electrophysiological signal characterising brain activity, EEG signal is currently of great research significance in many fields such as artificial intelligence applications, intelligent medical care and human-computer interaction. In this paper, based on the deep learning method, based on the training of convolutional neural network CNN and LSTM hybrid model, the diagnosis of EEG signals of people with mild cognitive impairment is carried out, and the diagnostic accuracy obtained is as high as 98%, which confirms the feasibility of the application of convolutional neural network in EEG signals. © 2023 IEEE.

关键词： EEG technology mild cognitive impairment,deep learning, convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Based Dual Recursive Network for image Super-Resolution

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2022年第2期33卷 707-720页

作者： Xin, Jingwei Li, Jie Jiang, Xinrui Wang, Nannan Huang, Heng Gao, Xinbo Xidian Univ State Key Lab Integrated Serv Networks Sch Elect Engn Xian 710071 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Sch Telecommun Engn Xian 710071 Peoples R China Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15261 USA Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongqing 400065 Peoples R China Xidian Univ Sch Elect Engn Xian 710071 Peoples R China

Although remarkable progress has been made on single-image super-resolution (SISR), deep learning methods cannot he easily applied to real-world applications due to the requirement of its heavy computation, especially for mobile devices. Focusing on the fewer parameters and faster inference SISR approach, we propose an efficient and time-saving wavelet transform-based network architecture, where the image super-resolution (SR) processing is carried out in the wavelet domain. Different from the existing methods that directly infer high-resolution (HR) image with the input low-resolution (LR) image, our approach first decomposes the LR image into a series of wavelet coefficients (WCs) and the network learns to predict the corresponding series of HR WCs and then reconstructs the HR image. Particularly, in order to further enhance the relationship between WCs and image deep characteristics, we propose two novel modules [wavelet feature mapping block (WFMB) and wavelet coefficients reconstruction block (WCRB)] and a dual recursive framework for joint learning strategy, thus forming a WCs prediction model to realize the efficient and accurate reconstruction of HR WCs. Experimental results show that the proposed method can outperform state-of-the-art methods with more than a 2x reduction in model parameters and computational complexity.

关键词： Computational complexity model parameters single-image super-resolution (SISR) time-saving wavelet coefficients (WCs)

来源：评论

学校读者我要写书评

暂无评论

SpikingVPR: Spiking neural Network-Based Feature Aggregation for Visual Place Recognition 5

SpikingVPR: Spiking Neural Network-Based Feature Aggregation...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of artificial Intelligence, ICSMD 2024

作者： Wang, Gulin Ren, Ziliang Zhang, Qieshi Cheng, Jun Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China School of Computer Science and Technology Dongguan University of Technology Dongguan China

ISBN: (纸本)9798331529192

Visual Place Recognition (VPR) is a crucial task in robotics and autonomous driving, where it identifies the geographic location of a query image by matching it with a reference database. VPR faces significant challenges, including appearance variations due to lighting, occlusion, weather, and seasonal changes, alongside the need for real-time processing under low computational cost and latency. To address these challenges, we introduce Spiking neural networks (SNN) into the VPR task, specifically focusing on the feature aggregation component. SNN, with their event-driven nature, offer advantages in computational efficiency and energy consumption, making them well-suited for energy-constrained environments such as drones. Our approach transforms the feature aggregation stage of VPR into a spiking, event-driven mechanism, which maintains high recall performance while integrating seamlessly with traditional ANN-based methods. Experimental results demonstrate that our SNN-based method effectively maintains high recall performance, validating its potential in autonomous driving and other related applications. © 2024 IEEE.

关键词： Event-Driven Mechanism Feature Aggregation Spiking neural Network Visual place recognition (VPR)

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：