检索结果-内蒙古大学图书馆

Geospatial Time Machine: A Generative Model to Enhance Spectral-Temporal Data Resolution

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Lopes, Felipe A. Sagan, Vasit Sarkar, Supria Stylianou, Abby Esposito, Flavio St Louis Univ Remote Sensing Lab St Louis MO 63108 USA St Louis Univ Dept Comp Sci St Louis MO 63108 USA

Geospatial artificial intelligence (GeoAI) and data processing techniques have significantly advanced object detection, prediction, and classification tasks. However, the availability of machine learning-ready, labeled data for specific applications such as plant disease detection remains the major challenge for the broader adoption of GeoAI. For instance, collecting temporal unmanned aerial vehicle (UAV) imagery of agricultural crops to track disease emergence and progress requires substantial human labor and resources, which is often limited to a small spatial scale. Recognizing the pivotal role of temporal data in pattern recognition, object detection, and scene reconstruction, we introduce an innovative approach to augment multispectral temporal datasets: the geospatial time machine (GTM). Our proposed methodology combines graph neural network (GNN) and generative adversarial network (GAN) architectures to generate comprehensive synthetic temporal data encompassing multivariate time series. The results demonstrate that imagery generated through backcasting can enhance the accuracy of downstream classification tasks by up to 53% in plant disease detection, particularly in the initial stages of analyzing a crop growth using multispectral and multitemporal datasets.

关键词： Data models Predictive models Accuracy image reconstruction Generative adversarial networks Graph neural networks Time series analysis Imputation Remote sensing Crops Data augmentation deep learning generative adversarial networks (GANs) generative artificial intelligence (GenAI) graph neural networks (GNNs) multispectral

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection using Time-Frequency Domain and Entropy Based EEG Analysis 31

Epilepsy Detection using Time-Frequency Domain and Entropy B...

引用

31st IEEE conference on Signal processing and Communications applications (SIU)

作者： Ficici, Cansel Telatar, Ziya Kocak, Onur Baskent Univ Ankara Univ Elekt Elekt Muhendisligi Bolumu Biyomed Muhendisligi Bolumu Ankara Turkiye

ISBN: (纸本)9798350343557

Abnormal electrical activities due to brain tumor, developmental anomaly, neural-atrophy in cortical/sub-cortical brain regions cause an epileptic seizure. Electroencephalography (EEG) is an important diagnostic test used for observing waveforms such as epileptic brain activities. In this study, a new method which detects epileptic seizure from EEG signals automatically is proposed. Discrete wavelet transform and time dependent entropy based statistical features of the EEG signal are used to train artificial neural networks. The proposed method has been applied on EEG signals obtained from healthy individuals and epileptic patients for epileptic seizure detection, and accuracy of 100% has been achieved. This method has also been applied on EEG signals containing normal, interictal and ictal states, and accuracy, sensitivity and specificity of 98.6%, 96.0% and 99.3% have been achieved, respectively.

关键词： epilepsy discrete wavelet transform time dependent entropy artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Pruning Deep Convolutional neural networks Using Clustering Methods: K-Means, CLIQUE, DENCLUE, and OptiGrid 24

A Comparative Study on Pruning Deep Convolutional Neural Net...

引用

9th International conference on Multimedia and image processing (ICMIP)

作者： Alqemlas, Danah Saud Jeragh, Mohammad Esmaeel Kuwait Univ Kuwait Kuwait Kuwait Oil Co Kuwait Kuwait

ISBN: (纸本)9798400716164

In the past years, machine learning (ML) and deep learning (DL) have led to the advancement of several applications, including computer vision, natural language processing, and audio processing. These complex tasks require large models, which is a challenge to deploy in devices with limited resources. These resource-constrained devices have limited computation power and memory. Hence, the neural networks must be optimized through network acceleration and compression techniques. This paper proposes a novel method to compress and accelerate neural networks from a small set of spatial convolution kernels. Firstly, a novel pruning algorithm is proposed based on the density-based clustering method that identifies and removes redundancy in CNNs while maintaining the accuracy and throughput tradeoff. Secondly, a novel pruning algorithm based on the grid-based clustering method is proposed to identify and remove redundancy in CNNs. The performance of the three pruning algorithms (density-based, grid-based, and partitional-based clustering algorithms) is evaluated against each other. The experiments were conducted using the deep CNN compression technique on the VGG-16 and ResNet models to achieve higher accuracy on image classification than the original model at a higher compression ratio and speedup.

关键词： neural Network Pruning Clustering Methods image processing

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of image Compression Methods Using artificial neural networks Based on Semi-log Quantization 23th

Comparative Study of Image Compression Methods Using Artific...

引用

23rd International conference on Intelligent Systems Design and applications, ISDA 2023

作者： Rahali, Mourad Loukil, Habiba Elloumi, Nessrine Bouhlel, Med Salim SETIT Labo on Smart Systems for Engineering and E-Health High Institute of Biotechnology University of Sfax Sfax Tunisia

ISBN: (纸本)9783031647758

image compression can be carried out through the use of various methods and, here, one can cite artificial neural networks (ANN). The purpose of this paper is to compare and study three methods of image compression using neural networks. In order to improve these methods, we will apply the semi-logarithmic quantization to the original image as a pre-treatment step before its compression with different types of neural networks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Optimizing image Classification through CNNs: A Survey of Advanced Techniques

Optimizing Image Classification through CNNs: A Survey of Ad...

引用

18th IEEE Long Island Systems, applications and Technology conference

作者： Odnis, Mike Alshibli, Mohammad Fried, Matthew SUNY Farmingdale State Coll Dept Comp Syst Farmingdale NY 11735 USA

ISBN: (纸本)9798331506674;9798331506667

We explore the latest advancements in deep learning techniques for improving the precision of image classification systems. We address the challenges of accurately categorizing photos due to factors such as background clutter, object orientations, and inconsistent illumination. Through a review of ten foundational studies, we examine state-of-the-art solutions such as data augmentation, transfer learning, and Convolutional neural networks (CNNs). Our objective is to identify key trends, obstacles, and areas for future research to enhance the accuracy of image classification.

关键词： artificial Intelligence Machine Learning image Categorization Deep Learning Precision Picture Classification Data Augmentation Transfer Learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Correction of Banding Errors in Satellite images With Generative Adversarial networks (GAN)

引用

IEEE ACCESS 2023年 11卷 51960-51970页

作者： Paola, Zarate L. Jesus, Lopez S. Christian, Arroyo H. Sonia, Rincon U. Colombian AF Res Ctr Aerosp Technol CITAE Cali CO Colombia Univ Autonoma Occidente Sch Engn Cali CO760001 CO Colombia

This research proposes an innovative method for correcting banding errors in satellite images based on Generative Adversarial networks (GAN). Small satellites are frequently launched into space to obtain images that can be used in scientific or military research, commercial activities, and urban planning, among other applications. However, its small cameras are more susceptible to radiometric, geometric errors, and other distortions caused by atmospheric interference. The proposed method was compared to the conventional correction technique using experimental data, showing the similar performance (92.64% and 90.05% accuracy, respectively). These experimental results suggest that generative models utilizing artificial Intelligence (AI) techniques, specifically Deep Learning, are getting closer to achieving automatic correction close to conventional methods. Advantages of the GAN models include automating the task of correcting banding in satellite images, reducing the required time, and facilitating the processing without requiring prior technical knowledge in handling Geographic Information Systems (GIS). Potentially, this technique could represent a valuable tool for satellite image processing, improving the accuracy of the results and making the process more efficient. The research is particularly relevant to the field of remote sensing and can have practical applications in various industries.

关键词： Satellite broadcasting Generative adversarial networks Generators Training Radiometry Remote sensing image coding artificial neural network deep learning generative adversarial network satellite images radiometric error banding

来源：评论

学校读者我要写书评

暂无评论

applications of artificial intelligence in dementia

引用

GERIATRICS & GERONTOLOGY INTERNATIONAL 2024年第Sup1期24卷 25-30页

作者： Kameyama, Masashi Umeda-Kameyama, Yumi Tokyo Metropolitan Inst Geriatr & Gerontol Res Team Neuroimaging AI & Theoret Image Proc Tokyo Japan Univ Tokyo Dementia Ctr Tokyo Japan Univ Tokyo Grad Sch Med Dept Geriatr Med Tokyo Japan Tokyo Metropolitan Inst Geriatr & Gerontol Res Team Neuroimaging AI & Theoret Image Proc Tokyo 1730015 Japan

The recent evolution of artificial intelligence (AI) can be considered life-changing. In particular, there is great interest in emerging hot topics in AI such as image classification and natural language processing. Our world has been revolutionized by convolutional neural networks and transformer for image classification and natural language processing, respectively. Moreover, these techniques can be used in the field of dementia. We introduce some applications of AI systems for treating and diagnosing dementia, including image-classification AI for recognizing facial features associated with dementia, image-classification AI for classifying leukoaraiosis in MRI images, object-detection AI for detecting microbleeding in MRI images, object-detection AI for support care, natural language-processing AI for detecting dementia within conversations, and natural language-processing AI for chatbots. Such AI technologies can significantly transform the future of dementia diagnosis and treatment. Geriatr Gerontol Int 2023;center dot center dot: center dot center dot-center dot center dot. We introduce the research on AI utilization in dementia, which can lead us to a better ***

关键词： deep learning dementia machine learning technology

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multimodal Conversational AI Using Speech and image Integration 5th

Enhanced Multimodal Conversational AI Using Speech and Image...

引用

5th International conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Dixit, Deepali Tyagi, Mihul Kandoi, Raunak Singh, Raghuraj School of Engineering and Technology Sharda University Greater Noida201310 India

ISBN: (纸本)9789819773701

The development of conversational artificial intelligence (AI) is examined in this research paper, with a focus on how speech and image recognition technologies can be combined to transform and interact with systems. The emphasis is on cutting-edge developments in multimodal conversational AI, particularly the smooth fusion of sophisticated image and speech processing methods to improve user experiences. The study addresses the applications, difficulties and potential applications of multimodal conversational AI by conducting a thorough review of the existing literature and case studies. By emphasizing the significance of enhancing voice recognition algorithms and utilizing advanced image processing techniques, the study promotes contextual understanding and customization. We have developed an innovative multimodal conversational AI system that integrates speech, text and image processing capabilities for seamless human–computer interactions. This study presents an improved multimodal conversational AI system that integrates several techniques, such as Google Text-to-Speech (gtts), speech recognition, sound playback and Convolutional neural networks (CNN). Our model architecture combines RNNs for sequential data analysis, CNNs for image processing and attention mechanisms for context extraction. Trained on diverse datasets, our model is optimized for accuracy and robustness. Evaluation against existing models demonstrates superior performance in terms of accuracy, speed and resource efficiency. Our study highlights how improved multimodal conversational AI can advance the field of human–computer interaction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Driving Behavior Recognition Algorithm and Implementation Based on Convolutional neural networks 24

Research on Driving Behavior Recognition Algorithm and Imple...

引用

4th International conference on artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024

作者： Xu, Qiangqiang Guo, Junhua Chen, Xi School of Transportation Engineering East China Jiaotong University China

ISBN: (纸本)9798400710049

The technology of driver behavior recognition holds significant importance in modern traffic management and autonomous driving systems. This paper revolves around Convolutional neural networks (CNNs) as the cornerstone, delving into the design and implementation of driver behavior recognition algorithms. Initially, image preprocessing using OpenCV lays the foundation for subsequent neural network processing. Subsequently, critical components within the neural network, such as activation functions and loss functions, are elaborated upon, alongside discussions on gradient-based optimization methods and backpropagation algorithms. Furthermore, this study provides an in-depth analysis of the roles of convolutional layers and pooling layers within CNNs, emphasizing their applications in driver behavior recognition. Lastly, by detailing specific algorithmic workflows and network architectures, the development of a driver behavior detection system is achieved. This research supports advancements in autonomous driving and traffic safety, demonstrating the vast potential of convolutional neural networks in practical applications. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic devices assisted by machine learning algorithms

引用

INTERNATIONAL JOURNAL OF EXTREME MANUFACTURING 2025年第4期7卷 042007-042007页

作者： Huo, Ziwei Sun, Qijun Yu, Jinran Wei, Yichen Wang, Yifei Cho, Jeong Ho Wang, Zhong Lin Chinese Acad Sci Beijing Inst Nanoenergy & Nanosyst Beijing 101400 Peoples R China Univ Chinese Acad Sci Sch Nanosci & Engn Beijing 100049 Peoples R China Guangxi Univ Ctr Nanoenergy Res Sch Phys Sci & Technol Nanning 530004 Peoples R China Shandong Zhongke Naneng Energy Technol Co Ltd Dongying Peoples R China Yonsei Univ Dept Chem & Biomol Engn Seoul 03722 South Korea Georgia Inst Technol Atlanta GA 30332 USA

Neuromorphic computing extends beyond sequential processing modalities and outperforms traditional von Neumann architectures in implementing more complicated tasks, e.g., pattern processing, image recognition, and decision making. It features parallel interconnected neural networks, high fault tolerance, robustness, autonomous learning capability, and ultralow energy dissipation. The algorithms of artificial neural network (ANN) have also been widely used because of their facile self-organization and self-learning capabilities, which mimic those of the human brain. To some extent, ANN reflects several basic functions of the human brain and can be efficiently integrated into neuromorphic devices to perform neuromorphic computations. This review highlights recent advances in neuromorphic devices assisted by machine learning algorithms. First, the basic structure of simple neuron models inspired by biological neurons and the information processing in simple neural networks are particularly discussed. Second, the fabrication and research progress of neuromorphic devices are presented regarding to materials and structures. Furthermore, the fabrication of neuromorphic devices, including stand-alone neuromorphic devices, neuromorphic device arrays, and integrated neuromorphic systems, is discussed and demonstrated with reference to some respective studies. The applications of neuromorphic devices assisted by machine learning algorithms in different fields are categorized and investigated. Finally, perspectives, suggestions, and potential solutions to the current challenges of neuromorphic devices are provided. The review discusses the basic structure of simple neuron models inspired by biological neurons and how they process information in simple neural networks, laying the foundation for neuromorphic device *** progress in the fabrication of neuromorphic devices is highlighted, focusing on advancements in materials, structures, and the development of st

关键词： neuromorphic devices machine learning algorithms artificial synapses memristors field-effect transistors

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：