检索结果-内蒙古大学图书馆

A Survey on Graph neural networks and its applications in Various Domains

SN Computer Science 2025年第1期6卷 1-12页

作者： Murgod, Tejaswini R. Reddy, P. Srihith Gaddam, Shamitha Sundaram, S. Meenakshi Anitha, C. Department of Artificial Intelligence & Machine Learning BNM Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering NITTE Meenakshi Institute of Technology Karnataka Bengaluru India

Graph neural networks (GNNs) are neural models that use message transmission between graph nodes to represent the dependency of graphs. Variants of Graph neural networks (GNNs), such as graph recurrent networks (GRN), graph attention networks (GAT), and graph convolutional networks (GCN), have shown remarkable results on a variety of deep learning tasks in recent years. In this study, we offer a generic design pipeline for GNN models, go over the variations of each part, classify the applications in an organized manner, and suggest four outstanding research issues. Dealing with graph data, which provides extensive connection information among pieces, is necessary for many learning tasks. A model that learns from graph inputs is required for modelling physics systems, learning molecular fingerprints, predicting protein interfaces, and identifying illnesses. Reasoning on extracted structures (such as the dependency trees of sentences and the scene graphs of photos) is an important research issue that also requires graph reasoning models in other domains, such as learning from non-structural data like texts and images. Graph neural networks (GNNs) are primarily designed for dealing with graph-structured data, where relationships between entities are modeled as edges in a graph. While GNNs are not traditionally applied to image classification problems, researchers have explored ways to leverage graph-based structures to enhance the performance of Convolutional neural networks (CNNs) in certain scenario. GNN have been increasingly applied to Natural Language processing (NLP) tasks, leveraging their ability to model structured data and capture relationships between elements in a graph. GNN are also applied for traffic related problems particularly in modeling and optimizing traffic flow, analyzing transportation networks, and addressing congestion issues. GNN can be used for traffic flow prediction, dynamic routing & navigation, Anomaly detection, public transport network

关键词： Computer vision Graph neural networks Intrusion detection Natural language processing neural networks Traffic control

来源：评论

学校读者我要写书评

暂无评论

Solution-processed self-assembling charge-transfer cocrystal/TIPS-pentacene heterojunctions for artificial synapses

引用

JOURNAL OF MATERIALS CHEMISTRY C 2025年

作者： Jin, Tao Li, Wenju Zhang, Yongyi Wang, Ruiheng Wang, Shuai Pan, Chen Wang, Guan Zhang, Jiacheng Yao, Lei Zhang, Jing Zhang, Qichun Nanjing Univ Posts & Telecommun State Key Lab Flexible Elect LoFE 9 Wenyuan Rd Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Inst Adv Mat IAM 9 Wenyuan Rd Nanjing 210023 Peoples R China City Univ Hong Kong Dept Mat Sci & Engn Hong Kong Peoples R China

artificial synapses have gained considerable attention in modeling artificial visual systems. A facile and efficient p-n heterojunction, acting as the essential component, plays a critical role in configuration optimization and processing capabilities. Herein, we introduced a novel charge-transfer cocrystal that consisted of 5,8-dihydroindolo[2,3-c]carbazole (DDCB) and 7,7,8,8-tetracyanoquinodimethane (TCNQ) via the solution-process, which demonstrated good crystallinity and typical n-type charge transport characteristics. To realize good charge storage ability, crystalline p-n heterojunctions with a phase-separated heterostructure were one-step prepared by drop-casting TIPS-pentacene and DDCB/TCNQ solutions onto the substrate. The as-prepared artificial synaptic devices exhibited remarkable paired-pulse facilitation (PPF), spike-duration dependent plasticity, spike-intensity dependent plasticity, and learning-experience behaviors similar to those of biological synapses in response to light pulses. Furthermore, based on the light potentiation and electrical depression modulation properties of these synaptic devices, we constructed artificial neural networks for image recognition, achieving a validation accuracy of over 97% on the modified national institute of standards and technology (MNIST) dataset. This work provides a new simple approach to establishing p-n heterojunction based artificial synapses for applications in light information processing, artificial vision, and memory simulation.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Heart Signal processing Using Wavelet Analysis and Deep Learning Algorithms Based on artificial Intelligence

Heart Signal Processing Using Wavelet Analysis and Deep Lear...

引用

International Conference on applications in Electronics Pervading Industry, Environment and Society, APPLEPIES 2024

作者： Zilaie, Morteza Mohammadkhani, Zohreh Asrari, Keyvan Azimi Talebiyan, Seyed Reza Islamic Azad University Science and Research Branch Khorasan Razavi Mashhad Iran The University of Pavia Pavia Italy Imam Reza International University Khorasan Razavi Mashhad Iran

ISBN: (纸本)9783031840999

The electrocardiogram signal of the heart is used to monitor the health status and function of the human heart and to a doctor in diagnosing the type of disease. For this purpose, first, the scalogram of the different heart failures produces different types of this signal. In this research, the cardiac signals of the patients are analyzed by an artificial intelligence neural network, and the type of the person’s disease is diagnosed. The artificial intelligence in question can be learned and can be used as an assistant ECG signal is calculated using continuous wavelet transform and then it is subjected to learning and evaluation using a deep convolutional neural network. In the architecture of artificial intelligence, two well-known neural networks GoogLeNet and SqueezeNet are used, which have been sufficiently trained in similar applications such as image processing and machine vision. In the end, the type of heart failure is diagnosed and classified. The cardiac signals of the patients used in the simulation were extracted from the PhysioNet medical engineering standard dataset of MIT University. In the end, the simulation results of the research are given. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optoelectronic Synapse Enabled by Defect Engineering of Tellurene for Neuromorphic Computing

IEEE ELECTRON DEVICE LETTERS

引用

IEEE ELECTRON DEVICE LETTERS 2025年第1期46卷 68-71页

作者： Guo, Junxiong Huang, Junyan Gu, Shuyi Lin, Lin Zhang, Yafei Wang, Xiang Liu, Yu Gong, Tianxun Lin, Yuan Yu, Bin Huang, Wen Zhang, Xiaosheng Univ Elect Sci & Technol China Sch Integrated Circuit Sci & Engn Chengdu 611731 Peoples R China Sch Elect Informat & Elect Engn Chengdu 610106 Peoples R China Nanjing Univ Posts & Telecommun Coll Integrated Circuit Sci & Engn Nanjing 210023 Peoples R China Univ Elect Sci & Technol China Sch Mat & Energy Chengdu 610054 Peoples R China Zhejiang Univ ZJU Hangzhou Global Sci & Technol Innovat Ctr Hangzhou 311215 Peoples R China

Emerging optoelectronic synapses hold immense potential for advancing neuromorphic computing systems. However, achieving precise control over selective responses in optoelectronic memory and clarifying tunable synaptic weights has remained challenging. This study reports an optoelectronic synapse utilizing oxygen plasma-assisted defect engineering in tellurene for artificial neural networks. Through DFT calculations and experimental analyses, we demonstrate that tellurene conductance can be modulated by controlling plasma-defined defect engineering, allowing a transition from short-term to long-term synaptic plasticity, largely determined by intrinsic large-lattice-relaxation effects. Our artificial synapses exhibit high linearity, a broad dynamic range, and tunable synaptic weights. Additionally, our optoelectronic synapses display selective sensitivity to multi-spectral light and achieve a pattern recognition accuracy of up to 96.7% across five typical datasets, surpassing even the ideal synapse. These tunable spectral responses, combined with high-performance neuromorphic applications using spike coding, establish a foundation for developments in brain-inspired machine learning, robotics, and real-time data processing.

关键词： Optoelectronic synapse defect engineering image recognition neural network Optoelectronic synapse defect engineering image recognition neural network

来源：评论

学校读者我要写书评

暂无评论

image encoded time series classification of small datasets: an innovative architecture using deep learning ensembles

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年 1-16页

作者： Indrasiri, Pubudu L. Kashyap, Bipasha Pathirana, Pubudu N. Deakin Univ Sch Engn 75Pigdons Rd Waurn Ponds Vic 3216 Australia

Convolutional neural networks (CNNs) are often favored for their strong learning abilities in tackling automatic intelligent models. The classification of time series data streams spans across many applications of intelligent systems. However, the scarcity of effective Machine Learning architectures to handle limited time-series data adversely affects the realization of some crucial applications. In particular, healthcare-related applications are inherently concerned with limited time series datasets. Indeed, building effective artificial intelligence (AI) models for rare diseases using conventional techniques can pose a significant challenge. Utilizing recent advances in deep learning and signal processing techniques, this study introduces a new ensemble deep learning (DL) approach for time series categorization in the presence of limited datasets. Physiological data, such as ECG and voice, are used to demonstrate the functionality of the proposed DL architecture with data obtained from IoT and non-IoT devices. The proposed framework comprises a self-designed deep CNN-LSTM along with ResNet50 and MobileNet transfer learning approaches. The CNN-LSTM architecture includes an enhanced squeeze and excitation block that improves overall *** architecture processes time series data transformed into a 3-Channel image structure via improved recurrence plot (RP), Gramian angular field (GAF), and fuzzy recurrence plot (FRP) methods. The proposed model demonstrated superior classification accuracy on the ECG5000 and TESS datasets compared to other state-of-the-art techniques, validating its efficacy for binary and multiclass classification.

关键词： Limited datasets Healthcare time series Squeeze and excitation Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Radar Signal processing and Its Impact on Deep Learning-Driven Human Activity Recognition

引用

SENSORS 2025年第3期25卷 724-724页

作者： Ayaz, Fahad Alhumaily, Basim Hussain, Sajjad Imran, Muhammad Ali Arshad, Kamran Assaleh, Khaled Zoha, Ahmed Univ Glasgow James Watt Sch Engn Glasgow City G12 8QQ England Ajman Univ Coll Engn & Informat Technol Dept Elect & Comp Engn POB 346 Ajman U Arab Emirates Ajman Univ Artificial Intelligence Res Ctr POB 346 Ajman 346 U Arab Emirates

Human activity recognition (HAR) using radar technology is becoming increasingly valuable for applications in areas such as smart security systems, healthcare monitoring, and interactive computing. This study investigates the integration of convolutional neural networks (CNNs) with conventional radar signal processing methods to improve the accuracy and efficiency of HAR. Three distinct, two-dimensional radar processing techniques, specifically range-fast Fourier transform (FFT)-based time-range maps, time-Doppler-based short-time Fourier transform (STFT) maps, and smoothed pseudo-Wigner-Ville distribution (SPWVD) maps, are evaluated in combination with four state-of-the-art CNN architectures: VGG-16, VGG-19, ResNet-50, and MobileNetV2. This study positions radar-generated maps as a form of visual data, bridging radar signal processing and image representation domains while ensuring privacy in sensitive applications. In total, twelve CNN and preprocessing configurations are analyzed, focusing on the trade-offs between preprocessing complexity and recognition accuracy, all of which are essential for real-time applications. Among these results, MobileNetV2, combined with STFT preprocessing, showed an ideal balance, achieving high computational efficiency and an accuracy rate of 96.30%, with a spectrogram generation time of 220 ms and an inference time of 2.57 ms per sample. The comprehensive evaluation underscores the importance of interpretable visual features for resource-constrained environments, expanding the applicability of radar-based HAR systems to domains such as augmented reality, autonomous systems, and edge computing.

关键词： human activity classification radar domain representations deep learning computational cost transfer learning

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

Thor: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX

IEEE COMPUTER ARCHITECTURE LETTERS

引用

IEEE COMPUTER ARCHITECTURE LETTERS 2025年第1期24卷 69-72页

作者： Dizani, Farshad Ghanbari, Azam Kalyanapu, Joshua Asher, Darsh Ajorpaz, Samira Mirbagher North Carolina State Univ Dept Elect & Comp Engn Raleigh NC 27606 USA

The rise of on-chip accelerators signifies a major shift in computing, driven by the growing demands of artificial intelligence (AI) and specialized applications. These accelerators have gained popularity due to their ability to substantially boost performance, cut energy usage, lower total cost of ownership (TCO), and promote sustainability. Intel's Advanced Matrix Extensions (AMX) is one such on-chip accelerator, specifically designed for handling tasks involving large matrix multiplications commonly used in machine learning (ML) models, image processing, and other computational-heavy operations. In this paper, we introduce a novel value-dependent timing side-channel vulnerability in Intel AMX. By exploiting this weakness, we demonstrate a software-based, value-dependent timing side-channel attack capable of inferring the sparsity of neural network weights without requiring any knowledge of the confidence score, privileged access or physical proximity. Our attack method can fully recover the sparsity of weights assigned to 64 input elements within 50 minutes, which is 631% faster than the maximum leakage rate achieved in the Hertzbleed attack.

关键词： Timing artificial neural networks Vectors Servers Program processors Microarchitecture Computational modeling Time-frequency analysis Side-channel attacks Privacy Intel advanced matrix extensions (AMX) value-dependent timing side-channel ML privacy NN sparsity

来源：评论

学校读者我要写书评

暂无评论

Deep Residual Learning for Fruits of Ceremonial Plants Recognition 2

Deep Residual Learning for Fruits of Ceremonial Plants Recog...

引用

2nd International Conference on Data, Information and Computing Science, CDICS 2024

作者： Negara, Ida Bagus Kade Dwi Suta Putra, I. Ketut Gede Darma Sudarma, Made Sukarsa, I. Made Udayana University Denpasar Indonesia

ISBN: (纸本)9781643685762

Fruit detection refers to a method within image processing and computer vision that focuses on automatically recognizing and distinguishing different types of fruits using advanced algorithms and techniques. Fruits are essential and widely used in ceremonial offerings (Banten). They are pivotal in ensuring the completeness of ceremonial offerings. The main goal of fruit detection is to recognize fruits in image form, making it applicable in various applications, including inventory management, automatic classification in the agricultural industry, and medical applications for monitoring dietary patterns. Commonly used methods include artificial neural networks (deep learning), digital image processing, and feature extraction techniques to distinguish between shapes, colours, textures, and other visual features of different types of fruits. In this research, the deep learning algorithm CNN (Convolutional neural Network) is employed. This technique, a deep learning algorithm, excels in accurate image recognition and classification. A total of 500 fruit images are used for five types of ceremonial fruits commonly used in religious activities, namely coconut, banana, candlenut, nutmeg, and areca nut. The residual learning method RESNET152 is used as the CNN algorithm architecture. According to the test findings, the highest accuracy rate achieved was 93% in correctly identifying ceremonial fruit images. © 2025 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Large Language Models (such as ChatGPT) as Tools for Machine Learning-Based Data Insights in Analytical Chemistry

引用

ANALYTICAL CHEMISTRY 2025年第13期97卷 6956-6961页

作者： Duponchel, Ludovic de Oliveira, Rodrigo Rocha Motto-Ros, Vincent Univ Lille CNRS UMR 8516 LASIRE Lab Spect Interact Re?activite? & Environm F-59000 Lille France Univ Barcelona Fac Chem Chemometr Grp Barcelona 08028 Spain Univ Claude Bernard Lyon 1 Inst Lumiere Matiere CNRS UMR 5306 F-69622 Villeurbanne France

artificial intelligence (AI), especially through the development of deep learning techniques like convolutional neural networks (CNNs), has revolutionized numerous fields. CNNs, introduced by Yann LeCun in the 1990s (Hubbard, W.;Jackel, L. D. Backpropagation Applied to Handwritten Zip Code Recognition. neural Comput. 1989, 1 (4), 541- 551. https://***/10.1162/neco.1989.1.4.541), have found applications in healthcare for medical diagnostics, autonomous vehicles in transportation, stock market prediction in finance, and image recognition in computer vision to name just a few. Similarly, in analytical chemistry, deep learning has enhanced data analysis from techniques like MS spectrometry, NMR, fluorescence spectroscopy, and chromatography. Another AI branch, Natural Language processing (NLP), has surged recently with the advent of Large Language Models (LLMs), such as OpenAI's ChatGPT. This paper demonstrates the application of an LLM via a smartphone to conduct multivariate data analyses, in an interactive conversational manner, of a hyper-spectral imaging data set from laser-induced breakdown spectroscopy (LIBS). We demonstrate the potential of LLMs to process and analyze data sets, which automatically generate and execute code in response to user queries, and anticipate their growing role in the future of analytical chemistry.

关键词： Convolutional neural networks

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：