检索结果-内蒙古大学图书馆

IEEE International Conference on Integrated Circuits, Technologies and applications (ICTA)

作者： Bo Li Wei Liu Yue Liu Xiao Huang Zhiyi Yu Shanlin Xiao School of Microelectronics Science and Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems

ISBN: (数字)9798331530723

ISBN: (纸本)9798331530730

Spiking neural networks (SNNs) exhibit superior energy efficiency and fault tolerance compared to artificial neural networks (ANNs). Due to their spike-based nature, input signals must be encoded into spike trains. However, traditional spiking coding schemes often encounter a trade-off between energy efficiency and fault tolerance. To overcome this limitation, we propose a novel coding scheme, Spiking Sparse Coding (SSC), which achieves both high sparsity and enhanced fault tolerance. SSC not only improves network performance but also reduces the number of spikes by 93.69%, resulting in a 76.47% increase in energy efficiency. Additionally, SSC enhances network fault tolerance, with accuracy improvements of up to 12.06% under identical noise interference conditions. We deployed the network on the ZCU102 FPGA platform, operating at a frequency of 200 MHz with a power consumption of 409 mW. On the MNIST dataset, we achieved a classification accuracy of 95.84%. The training speed and energy consumption were 12656 frames per second and 0.032 mJ per image, the inference speed and energy consumption were 19279 frames per second and 0.021 mJ per image.

关键词： Training Fault tolerance Energy consumption Accuracy Power demand Fault tolerant systems Noise Spiking neural networks Encoding Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural networks Towards Facial Skin Lesions Detection

Convolutional Neural Networks Towards Facial Skin Lesions De...

引用

International Symposium on artificial Intelligence and Signal processing (AISP)

作者： Reza Sarshar Mohammad Heydari Elham Akhondzadeh Noughabi School of Industrial and Systems Engineering Tarbiat Modares University Tehran Iran

Facial analysis has emerged as a prominent area of research with diverse applications, including cosmetic surgery programs, the beauty industry, photography, and entertainment. Manipulating patient images often necessitates professional image processing software. This study contributes by providing a model that facilitates the detection of blemishes and skin lesions on facial images through a convolutional neural network and machine learning approach. The proposed method offers advantages such as simple architecture, speed and suitability for image processing while avoiding the complexities associated with traditional methods. The model comprises four main steps: area selection, scanning the chosen region, lesion diagnosis, and marking the identified lesion. Raw data for this research were collected from a reputable clinic in Tehran specializing in skincare and beauty services. The dataset includes administrative information, clinical data, and facial and profile images. A total of 2300 patient images were extracted from this raw data. A software tool was developed to crop and label lesions, with input from two treatment experts. In the lesion preparation phase, the selected area was standardized to $50\times 50$ pixels. Subsequently, a convolutional neural network model was employed for lesion labeling. The classification model demonstrated high accuracy, with a measure of 0.98 for healthy skin and 0.97 for lesioned skin specificity. Internal validation involved performance indicators and cross-validation, while external validation compared the model’s performance indicators with those of the transfer learning method using the Vgg16 deep network model. Compared to existing studies, the results of this research showcase the efficacy and desirability of the proposed model and methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

1st International Conference on artificial Intelligence and its applications, ICAIA 2023

1st International Conference on Artificial Intelligence and ...

引用

1st International Conference on artificial Intelligence and its applications, ICAIA 2023

ISBN: (纸本)9783031843969

The proceedings contain 37 papers. The special focus in this conference is on artificial Intelligence and its applications. The topics include: The Hybrid Cardiac Risk Assessment and Prediction Model Using Convolutional neural networks;deep Learning applications for Malaria Detection and Diagnosis: A Review;Environmental Considerations in the Ethics of AI Adoption in Healthcare: Striving for Sustainable and Responsible Practices;harnessing the Power of Cognitive Computing: Assessing Point-of-Care Decision Support Tools in Oncology Practice;Critical Analysis in Use of AI in Health Care Management;classification and Prediction of Spinal Tuberculosis Disease Using Optimization of Convolution neural Network Using Spatial and Temporal Constraints;artificial Intelligence for Remote Healthcare in Underserved Areas: Enhancing Access and Quality of Healthcare Delivery;machine Learning Based Skin Cancer Detection and Recognitions Techniques in IoT Environment;validation of a Chronic Kidney Disease Prediction System Using Machine Learning Techniques;real-Time Feedback Detection Using Emotion Detection and Facial Recognition;revolutionizing Vision Tasks: Unlocking Potential Through Patch-Based Approaches;automated Knee Implant Identification from 2D Templates Using image processing and artificial Intelligence – An Experimental Approach;crop Analysis and Classification Based on Phenotype Using Ensemble Learning;Classification and Identification with Health Benefit Assessment and Nutrient Profile of Brewed Tea Utilizing Computer Vision with ML and DL and Sensory Approaches;enhancing Industrial Automation Flexibility Through neural Network-Empowered Machine Vision applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online classification of soybean seeds based on deep learning

引用

ENGINEERING applications OF artificial INTELLIGENCE 2023年第PartC期123卷

作者： Lin, Wei Shu, Lei Zhong, Weibo Lu, Wei Ma, Daoyi Meng, Yizhen Nanjing Agr Univ Coll Artificial Intelligence Nanjing 210031 Peoples R China Jiangsu Univ Sci & Technol Ocean Coll Zhenjiang 212003 Peoples R China Shanghai Aerosp Control Technol Inst Shanghai 201109 Peoples R China

To quickly evaluate soybean quality, we proposed a deep learning-based method for online classification of soybean seeds. Firstly, images of soybean seeds with uneven illumination were segmented based on the multiscale Retinex with color restoration (MSRCR). Then, a convolutional neural network (CNN) was constructed to achieve soybean seed four-classification with appropriate parameters. The F-score of the normal, damaged, abnormal, and non-classifiable soybeans reached about 95.97%, 97.41%, 97.25%, and 96.14%, respectively. Finally, the method was successfully applied in NVIDIA Jetson TX2 with an accuracy of 95.63% and an average classification time of 4.92 ms for a soybean seed, which can meet the requirement of online soybean quality assessment.

关键词： Computer vision image processing Online soybean quality assessment Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AI - ISP Accelerator with RISC-VISA Extension for image Signal processing

AI - ISP Accelerator with RISC-VISA Extension for Image Sign...

引用

Technology, Systems and applications (VLSI-TSA/VLSI-DAT), International VLSI Symposium on

作者： Zong-Mao Wu Yu-Chi Lin Chih-Wei Liu Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Industrial Technology Research Institute Hsinchu Taiwan

ISBN: (数字)9798350360349

ISBN: (纸本)9798350360356

This paper focuses on the hardware acceleration of an AI-ISP (image signal processing) neural network, namely CSANet, which computes images from raw data to RGB format. To design a flexible, high-performance, and low-power AI-ISP accelerator on FPGA, we apply the RISC-VISA extension with the CFU-Playground framework specified for tiny-ML. The proposed RISC-V custom instructions support normal convolution, transposed convolution, depth-wise convolution, and partial element-wise operations, which can accelerate the computation hotspots of the CSANet. Applying with the FPGA implementation, on the Digilent Nexys Video development board (Artix-7 XC7A200T), the proposed CSANet accelerator achieves a $79.7\times$ speedup and demonstrates a $27.8\times$ improvement in energy efficiency on average compared to RISC-V CPU-only.

关键词： Deep learning Convolution neural networks Very large scale integration Energy efficiency artificial intelligence Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with Graph Convolutional networks: An Overview and Latest applications in Computational Intelligence

引用

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS 2023年第1期2023卷

作者： Bhatti, Uzair Aslam Tang, Hao Wu, Guilu Marjan, Shah Hussain, Aamir Hainan Univ Sch Informat & Commun Engn Haikou 570100 Peoples R China Hainan Univ State Key Lab Marine Resource Utilizat South China Haikou Peoples R China Balochistan Univ Informat Technol Engn & Managemen Dept Software Engn Quetta Pakistan Muhammad Nawaz Shareef Univ Agr Multan Dept Comp Sci Multan Pakistan

Convolutional neural networks (CNNs) have received widespread attention due to their powerful modeling capabilities and have been successfully applied in natural language processing, image recognition, and other fields. On the other hand, traditional CNN can only deal with Euclidean spatial data. In contrast, many real-life scenarios, such as transportation networks, social networks, reference networks, and so on, exist in graph data. The creation of graph convolution operators and graph pooling is at the heart of migrating CNN to graph data analysis and processing. With the advancement of the Internet and technology, graph convolution network (GCN), as an innovative technology in artificial intelligence (AI), has received more and more attention. GCN has been widely used in different fields such as image processing, intelligent recommender system, knowledge-based graph, and other areas due to their excellent characteristics in processing non-European spatial data. At the same time, communication networks have also embraced AI technology in recent years, and AI serves as the brain of the future network and realizes the comprehensive intelligence of the future grid. Many complex communication network problems can be abstracted as graph-based optimization problems and solved by GCN, thus overcoming the limitations of traditional methods. This survey briefly describes the definition of graph-based machine learning, introduces different types of graph networks, summarizes the application of GCN in various research fields, analyzes the research status, and gives the future research direction.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

artificial Intelligence Research and Development for Application in Video Capsule Endoscopy

引用

Gastrointestinal Endoscopy Clinics of North America 2021年第2期31卷 387-397页

作者： Sullivan, Peter Gupta, Shradha Powers, Patrick D. Marya, Neil B. Division of Gastroenterology University of Massachusetts Medical School 55 Lake Avenue North Worcester 01655 MA United States

artificial intelligence (AI) research for medical applications has expanded quickly. Advancements in computer processing now allow for the development of complex neural network architectures (eg, convolutional neural networks) that are capable of extracting and learning complex features from massive data sets, including large image databases. Gastroenterology and endoscopy are well suited for AI research. Video capsule endoscopy is an ideal platform for AI model research given the large amount of data produced by each capsule examination and the annotated databases that are already available. Studies have demonstrated high performance for applications of capsule-based AI models developed for various pathologic conditions. © 2021 Elsevier Inc.

关键词： artificial intelligence Convolutional neural networks Deep learning Machine learning Video capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

30.2 A 22nm 0.26nW/Synapse Spike-Driven Spiking neural Network processing Unit Using Time-Step-First Dataflow and Sparsity-Adaptive In-Memory Computing

30.2 A 22nm 0.26nW/Synapse Spike-Driven Spiking Neural Netwo...

引用

2024 IEEE International Solid-State Circuits Conference, ISSCC 2024

作者： Liu, Ying Ma, Yufei Shang, Ninghui Zhao, Tianhao Chen, Peiyu Wu, Meng Ru, Jiayoon Jia, Tianyu Ye, Le Wang, Zhixuan Huang, Ru Peking University Beijing China Nano Core Chip Electronic Technology Hangzhou China Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9798350306200

Recently, brain-inspired spiking neural networks (SNNs) have demonstrated tremendous improvement in energy efficiency (EE) and low power by exploiting highly sparse spikes and event-driven design [1-2]. (top of Fig. 30.2.1) With the same spike-based information carrier, the combination of an SNN and dynamic vision sensor (DVS) [3] offers a promising solution for edge AI applications. Typically, the greater the number of synapses in an SNN can improve inference accuracy, but induce more significant power consumption and memory size. Therefore, deploying more synapses in an SNN chip while maintaining low power, memory size and high EE requires co-design of algorithm, architecture and circuits. At the algorithm level, SNN training based on conversion from an artificial NN (ANN) [1] achieves the best accuracy in static image classification, but at the cost of worse EE and higher power consumption, as it requires excessive time steps and energy arising from ANN-SNN conversion. At the architecture level, the multiple-time-step forward computation in SNNs introduces redundant data movement and storage, including input-output spikes, weights, partial sums and membrane potentials, restricting the network scale that can be accommodated by limited on-chip memory, i.e., network density (ND) [4-6]. At the circuit level, in-memory computing (IMC) is attractive to minimize data movement. However, traditional frame-based IMC circuits are incompatible with the highly sparse and fine-grained spike-driven nature of SNNs. Recent advancements in neuromorphic IMC [7] employ integrated-fire (IF) converters, which are globally triggered by power-hungry clocks even if there is no spike, resulting in high power per synapse, i.e., power density (PD). © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 18th International Conference on Soft Computing Models in Industrial and Environmental applications, SOCO 2023

Proceedings of the 18th International Conference on Soft Com...

引用

Proceedings of the 18th International Conference on Soft Computing Models in Industrial and Environmental applications, SOCO 2023

ISBN: (纸本)9783031425288

The proceedings contain 61 papers. The special focus in this conference is on Soft Computing Models in Industrial and Environmental applications. The topics include: Missing Values Imputation for Visualizing the Air Quality Evolution During the COVID-19 Pandemic in Madrid;Comparative Study of Wastewater Treatment Plant Feature Selection for COD Prediction;effectiveness of Quantum Computing in image processing for Burr Detection;hyperspectral Technology for Oil Spills Detection by Using artificial neural Network Classifier;Model-Based Design of the IMO-NMPC Strategy: Real-Time Implementation;first Approach of an Intelligent Automatic System for Aircraft Flap/Slat Positioning;multi-scale neural Model for Tool-Narayanaswamy-Moynihan Model Parameter Extraction;comparative Study of Open Source Database Management Systems to Enable Predictive Maintenance of Autonomous Guided Vehicles;deep Learning and Metaheuristic for Multivariate Time-Series Forecasting;forecasting Greenhouse Temperature Using Machine Learning Models: Optimizing Crop Production in Andalucia;extended Rank-Based Ant Colony Optimization Algorithm for Traveling Salesman Problem;Managing Pandemics Through Agent-Based Simulation: A Case Study Based on COVID-19;leveraging Smart Meter Data for Adaptive Consumer Profiling;Categorization of CoAP DoS Attack Based on One-Class Boundary Methods;text Classification for Automatic Distribution of Review Notes in Movie Production;fault Detection in Biological Methanation Process Using Machine Learning: A Comparative Study of Different Algorithms;machine Learning Approaches for Predicting Tree Growth Trends Based on Basal Area Increment;integrated Forecast and Optimization for Retailer Allocation in a Two-Echelon Inventory System;application of Fuzzy Logic to the Risk Assessment of Production Machines Failures;Neuron Characterization in Complex Cultures Using a Combined YOLO and U-Net Segmentation Approach;neuroevolutionary Transfer Learning for Time Series Forecasting;f

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Recommender Systems Through Multimodal Large Language Models and neural Matrix Factorization

Enhancing Recommender Systems Through Multimodal Large Langu...

引用

Electronic Communication and artificial Intelligence (IWECAI), International Workshop on

作者： Yizhuo Jiang School of Management Shanghai University Shanghai China

ISBN: (数字)9798350386943

ISBN: (纸本)9798350386950

This This study proposes a new recommendation system model that integrates multimodal data, large language models (LLM), and neural matrix factorization techniques. By using Vision Transformer (ViT) and the BERT model, we deeply mine the image and text information of users and products, and combine unstructured data with neural network technology for evaluation prediction and recommendation, showing excellent prediction performance. This study also verified the performance advantages of this method compared with traditional recommendation system methods through various ablation experiments. The results highlight the importance of text data in capturing user preferences and improving recommendation accuracy. In addition, the study found that in practical applications, more detailed segmentation processing of visual data is needed to accurately evaluate the specific contribution of visual data to multi-modal recommendation systems. These findings provide important theoretical and practical guidance for further optimizing recommendation systems.

关键词： Visualization Accuracy Large language models Splicing neural networks Predictive models Speech enhancement

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：