检索结果-内蒙古大学图书馆

Biosignal classification for human identification based on convolutional neural networks

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS 2021年第7期34卷 e4685-e4685页

作者： Siam, Ali, I Sedik, Ahmed El-Shafai, Walid Abou Elazm, Atef El-Bahnasawy, Nirmeen A. El Banby, Ghada M. Khalaf, Ashraf A. M. Abd El-Samie, Fathi E. Kafrelsheikh Univ Fac Artificial Intelligence Dept Embedded Network Syst Technol Kafr Al Sheikh Egypt Kafrelsheikh Univ Fac Artificial Intelligence Dept Robot & Intelligent Machines Kafr Al Sheikh Egypt Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia Egypt Menoufia Univ Fac Elect Engn Dept Comp Sci & Engn Menoufia Egypt Menoufia Univ Fac Elect Engn Dept Ind Elect & Control Engn Menoufia Egypt Minia Univ Fac Engn Dept Elect & Elect Commun Al Minya Egypt

Human identification is considered as a serious challenge for several applications such as cybersecurity and access control. Recently, the trend of human identification has been directed to human biometrics, which can be used to recognize persons based on some physiological or behavioral characteristics that they own, such as fingerprint, iris, and biosignals. There are several types of human biosignals including electroencephalography (EEG), electrocardiography (ECG), and photoplethysmography (PPG) signals. This paper presents a human identification system based on PPG signals. The proposed system consists of three main phases: signal acquisition, signal pre-processing, and feature extraction/classification. The pre-processing phase involves denoising of the acquired signal, transformation of the 1D signal sequence into a 2D image, and computation of the spectrogram. Feature extraction is carried out on the images obtained from the pre-processing phase. Features are extracted from the images based on convolutional neural networks (CNNs). The proposed CNN model consists of a sequence of convolutional (CNV) and pooling layers. Finally, the obtained feature maps are fed to the classifier to discriminate human identities. The proposed identification algorithm is applied on signals with and without an additive white Gaussian noise (AWGN). The simulation results reveal that the proposed algorithm achieves an accuracy of 99.5% with the spectrogram representation and 89.8% with the 2D image representation, in the absence of noise. In addition, the paper gives a discussion of the efficiency of denoising techniques such as wavelet denoising, Savitzky-Golay and Kalman filtering, when involved with the proposed algorithm. The simulation results prove that the wavelet dencoising technique has a best performance among the discussed noise reduction techniques.

关键词： Biometrics deep learning human identification photoplethysmography (PPG) signal denoising

来源：评论

学校读者我要写书评

暂无评论

An image processing-Based Tomato Leaf Disease Prediction Using Deep CNN 5th

An Image Processing-Based Tomato Leaf Disease Prediction Usi...

引用

5th International Conference on artificial Intelligence and Speech Technology, AIST 2023

作者： Vanisri, Kesana Raju, K. Srujan Laxmaiah, Bagam Department of CSE CMR Technical Campus Hyderabad India

ISBN: (纸本)9783031751660

Pest outbreaks have a significant impact on plants and crops, important to a reduction in national agricultural productivity. Conventionally, farmers and specialists rely on physical observation, and it can be timeconsuming, more expensive, and prone to errors, to classify diseases in plants. Though, by employing leading-edge image processing techniques, an instinctive detection system can be established, providing rapid and precise results. This paper aims to produce a Tomato Leaf Disease identification model with different categorizing leaf images and utilizing deep neural networks. The development of specific plant protection has the potential for substantial growth and improvement, with computer vision applications in the precision agriculture market also showing promising growth. This discussion about outlines all the critical stages for implementing the disease recognition model, initial from the image database group, assessment by agricultural specialists, and applying a deep learning framework to conduct the training of deep CNNs. By using this CNN, we will apply Max pooling layer, Multiple implementations are applied and finally we will get more accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Dataset Deep CNN Diseases neural network

来源：评论

学校读者我要写书评

暂无评论

Advanced Techniques for Geospatial Referencing in Online Media Repositories

引用

FUTURE INTERNET 2024年第3期16卷 87页

作者： Warch, Dominik Stellbauer, Patrick Neis, Pascal Mainz Univ Appl Sci Sch Technol Dept Appl Informat & Geodesy D-55128 Mainz Germany

In the digital transformation era, video media libraries' untapped potential is immense, restricted primarily by their non-machine-readable nature and basic search functionalities limited to standard metadata. This study presents a novel multimodal methodology that utilizes advances in artificial intelligence, including neural networks, computer vision, and natural language processing, to extract and geocode geospatial references from videos. Leveraging the geospatial information from videos enables semantic searches, enhances search relevance, and allows for targeted advertising, particularly on mobile platforms. The methodology involves a comprehensive process, including data acquisition from ARD Mediathek, image and text analysis using advanced machine learning models, and audio and subtitle processing with state-of-the-art linguistic models. Despite challenges like model interpretability and the complexity of geospatial data extraction, this study's findings indicate significant potential for advancing the precision of spatial data analysis within video content, promising to enrich media libraries with more navigable, contextually rich content. This advancement has implications for user engagement, targeted services, and broader urban planning and cultural heritage applications.

关键词： natural language processing named entity recognition geocoding online media repository geospatial information extraction image-to-text audio-to-text

来源：评论

学校读者我要写书评

暂无评论

Ultralow-power spiking neural networks for 1024-ary orbital angular momentum shift keying free-space optical communication

引用

JOURNAL OF OPTICS 2023年第7期25卷 074001-074001页

作者： Li, Baoli Chen, Qinyu Su, Hang Cheng, Ke Luan, Haitao Gu, Min Fang, Xinyuan Univ Shanghai Sci & Technol Inst Photon Chips Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Ctr Artificial Intelligence Nanophoton Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China

The theoretical unbounded orbital angular momentum (OAM) states can be exploited as data bits in the OAM shift keying (OAM-SK) free-space optical (FSO) communications. In order to cope with the atmospheric turbulence (AT) and misalignment in practical applications, various machine learning algorithms, or neural networks (NNs), have been put forward to decode the OAM states. However, to recognize the hybrid spatial modes representing a large bit states, the massive learnable nodes, longer computation time and more training parameters are required to improve the capability of the NNs, resulting in energy efficiency burden to the hardware device. In this paper, the event-based spiking neural network (SNN) is utilized to recognize the hybrid spatial modes consisting of superposed coaxial Laguerre-Gaussian modes with l ranging from 0 to 9 and p = 0, which is termed as spiking OAM-recognition neural network (Spiking-ORNN). In comparison to the previous solution of running deep NNs on graphics processing units, the neuromorphic solution of running Spiking-ORNN on neuromorphic chips exhibits 4300x higher energy efficiency without obvious sacrifice of recognition accuracy (less than 0.5%). Moreover, we experimentally demonstrate a 10 m 1024-ary OAM-SK FSO communication for the transmission of an image with a 10 bit grey level, wherein the peak signal-to-noise ratio of the received image can exceed 41.4 dB under the AT of C-n(2) =10(-15) m(-2/3). We anticipate that our results can stimulate further researches on the utilization of the brain-like SNN chips to reduce the energy consumptions based on the artificial-intelligence-enhanced optoelectronic systems.

关键词： orbital angular momentum free-space optical communications ultralow-power spiking neural networks deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Analysis of a Dual Memristive Hopfield neural Network

A Dynamic Analysis of a Dual Memristive Hopfield Neural Netw...

引用

neural networks, Information and Communication Engineering (NNICE), International Conference on

作者： Na Li Zhaoxing Wang Lili Huang School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China Collaborative Innovation Center of Memristive Computing Application (CICCA) Qilu Institute of Technology Jinan China

The human brain, as a large and highly complex nonlinear dynamical system, has a close connection with human intelligence activities. The artificial neural network based on memristors has shown excellent performance in simulating the working mechanism of the human brain. Therefore, in the HNN neural network, both hyperbolic tangent memristors and quadratic nonlinear memristors are introduced to couple with it. Using basic dynamical analysis methods, the paper discusses the dynamical behavior of the system under different coupling strengths and studies the behavior of attractor symmetry under different initial values. The experimental results show that under different memristor parameters, by observing the changes in the phase trajectory diagram, Lyapunov exponent, and bifurcation diagram of the system, it is found that it has periodic doubling bifurcation, chaos, periodic window, and double vortex attractor symmetry behavior. At the same time, it also emphasizes its full sensitivity to initial values. At the same time, its complex dynamical characteristics also provide research support for applications in data processing, image encryption, biomedical, and other fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Learning on Medical image Analysis

引用

MOBILE networks & applications 2021年第1期26卷 351-380页

作者： Wang, Jian Zhu, Hengde Wang, Shui-Hua Zhang, Yu-Dong Univ Leicester Sch Informat Leicester LE1 7RH Leics England Loughborough Univ Sch Architecture Bldg & Civil Engn Loughborough LE11 3TU Leics England Univ Leicester Sch Math & Actuarial Sci Leicester LE1 7RH Leics England King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Syst Jeddah 21589 Saudi Arabia

Compared with common deep learning methods (e.g., convolutional neural networks), transfer learning is characterized by simplicity, efficiency and its low training cost, breaking the curse of small datasets. Medical image analysis plays an indispensable role in both scientific research and clinical diagnosis. Common medical image acquisition methods include Computer Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound (US), X-Ray, etc. Although these medical imaging methods can be applied for non-invasive qualitative and quantitative analysis of patients-compared with image datasets in other computer vision fields such like faces-medical images, especially its labeling, is still scarce and insufficient. Therefore, more and more researchers adopted transfer learning for medical image processing. In this study, after reviewing one hundred representative papers from IEEE, Elsevier, Google Scholar, Web of Science and various sources published from 2000 to 2020, a comprehensive review is presented, including (i) structure of CNN, (ii) background knowledge of transfer learning, (iii) different types of strategies performing transfer learning, (iv) application of transfer learning in various sub-fields of medical image analysis, and (v) discussion on the future prospect of transfer learning in the field of medical image analysis. Through this review paper, beginners could receive an overall and systematic knowledge of transfer learning application in medical image analysis. And policymaker of related realm will benefit from the summary of the trend of transfer learning in medical imaging field and may be encouraged to make policy positive to the future development of transfer learning in the field of medical image analysis.

关键词： Transfer learning Medical image analysis CT Deep learning MRI Convolutional neural networks Fine-tuning Feature extractor artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Enhancing image Classification with Bayesian neural networks: Improved Training Techniques and Decision Strategies for Reliable AI Support in Uncertainty-Sensitive Tasks

Enhancing Image Classification with Bayesian Neural Networks...

引用

Computer, Big Data and artificial Intelligence (ICCBD+AI), International Conference on

作者： Yan.Cheng. Liu Hua.Jun Huang Yi.Wen Wang School of Information Technology and Management Hunan University of Finance and Economics Changsha China

ISBN: (数字)9798350373233

ISBN: (纸本)9798350373240

Bayesian theory is a probabilistic statistical framework for dealing with uncertainty and incomplete information, while neural networks are widely applied in deep learning fields such as image processing. Bayesian neural networks (BNNs) combine Bayesian theory and neural networks to provide more comprehensive predictive results. Although BNNs have significant advantages in expressing model uncertainty, their training methods and network structure design are still to be explored. Effectively training BNNs and exploring their network structure design to enhance predictive performance and computational efficiency are the core of this research. The study aims to improve the performance of BNNs in image classification tasks, specifically including the quantification and utilization of uncertainty to enhance model reliability and decision support capabilities. We use efficient training methods such as variational inference to redesign Bayesian neural networks and conduct deep image recognition training on the CIFAR-10 dataset. The improved training method allows for the rapid and accurate estimation of model weight uncertainty, while the proposed decision strategy utilizes uncertainty information to make reliable decisions. This study demonstrates that BNNs have tremendous potential in addressing real-world uncertainty issues, with the results expected to provide safer AI decision support for risk-sensitive tasks and promote the reliability and practicality of deep learning technology in various critical applications.

关键词： Training Deep learning Uncertainty Computer network reliability neural networks Bayes methods Reliability

来源：评论

学校读者我要写书评

暂无评论

Advances in Neuromorphic Spin-Based Spiking neural networks: A review

引用

IEEE NANOTECHNOLOGY MAGAZINE 2021年第5期15卷 33-44页

作者： Verma, Gaurav Bindal, Namita Nisar, Arshid Dhull, Seema Kaushik, Brajesh Kumar Indian Inst Technol Roorkee Dept Elect & Commun Engn Roorkee 247667 Uttarakhand India

This article reviews the recent developments and challenges in spintronic based spiking neural networks (SNNs). The present CPUs and GPUs are powerful tools that are capable of computing complex artificial intelligence (AI) tasks, yet they face several challenges. The systems utilizing machine learning techniques require extensive computations including vector-matrix multiplication. The traditional von Neumann architecture is inefficient in the hardware implementation of such systems. Neuromorphic architectures are computationally more efficient that ushers the era of high-performance hardware for AI applications. This also caters to the need of hardware solutions for biologically inspired in-memory computing functionality using nonvolatile memory (NVM). These biologically inspired networks have attracted a great attention due to their inherent computational efficiency in performing pattern/speech recognition and image classification tasks. During the last decade, SNNs have emerged as one of the suitable solutions for imitating the biological brain. Information is temporarily encoded in SNNs and the spikes serve as a mode of communication between the neurons. Various NVM devices such as spin-based memories, resistive randomaccess memory (RRAM), phase change memory (PCM), and conductive-bridging RAM (CBRAM) have been explored for the hardware implementation of NNs. Spin-based memory devices demonstrate much more energy efficiency while providing superior information processing capabilities than other NVMs. These devices also provide high endurance, scalability, CMOS compatibility, and ultralow power consumption characteristics. The spiking functionality in neurons can be easily mapped to various spin devices with synaptic learning, therefore, paving the path for future AI hardware solutions.

关键词： Hardware Computer architecture Neurons artificial neural networks Nonvolatile memory Random access memory Biological information theory

来源：评论

学校读者我要写书评

暂无评论

Household Waste Classification Algorithms Based on Various Convolutional neural networks: A Review of Performance Optimization

Household Waste Classification Algorithms Based on Various C...

引用

International Conference on Wavelet Active Media Technology and Information processing (ICWAMTIP)

作者： Huang Renxiang Chen Jia Li Jianping School of Artificial Intelligence and Big Data Sichuan University of Arts and Science Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

This paper reviews the research progress of deep learning-based household waste classification algorithms. It first introduces the importance of household waste classification and the application value of deep learning in this field. Next, it outlines the theoretical foundations of deep learning technology in waste classification, including the principles of convolutional neural networks and their applications in image recognition. The article provides a detailed analysis of the application of different deep learning models in waste classification, such as MobileNetV2, ShuffleNetV1, EfficientNetV1, and YOLOV5, as well as their optimizations and innovations in practical applications. Furthermore, it discusses optimization and innovation methods for deep learning models, including learning rate adjustment, optimizer selection, attention mechanisms, data augmentation, and lightweight network design. Finally, it summarizes the current research shortcomings and challenges, and looks forward to future research directions. This review provides a systematic perspective for a deeper understanding of the application of deep learning in waste classification and offers directions for future research.

关键词： Deep learning Analytical models Technological innovation Attention mechanisms Reviews Data augmentation Data models Classification algorithms Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Edge and Cloud image Classification with Multi-Reservoir Echo State Network and Data processing Units

引用

SENSORS 2024年第11期24卷 3640页

作者： Lopez-Ortiz, E. J. Perea-Trigo, M. Soria-Morillo, L. M. Alvarez-Garcia, J. A. Vegas-Olmos, J. J. Univ Seville Dept Comp Sci & Artificial Intelligence Avda Reina Mercedes S-N Seville 41004 Spain Univ Seville Dept Languages & Comp Syst Avda Reina Mercedes S-N Seville 41004 Spain NVIDIA Corp Hermon Bldg IL-6121002 Yokneam Israel

In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms.

关键词： state network energy-efficient models image classification reservoir computing CloudCast

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：