检索结果-内蒙古大学图书馆

International Conference on computer and Communications (ICCC)

作者： Jianwei Zhang Houjia Cai Jinghu Li Liaoning Key Lab of Integrated Circuit and Biomedical Electronic System School of Biomedical Engineering Dalian University of Technology Dalian China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou China

ISBN: (纸本)9781665409513

With the rapid development of convolutional neural networks (CNN), the design of hardware accelerators for CNN calculations has become a major focus of current research. However, power consumption and resource consumption are two main limits for the application of CNN hardware accelerators. In response to these problems, a FPGA-based implementation of a CNN hardware accelerator with high energy efficiency and low resource consumption is proposed. The implementation includes zero padding, convolution, batch normalization, ReLU6, and MaxPooling. The computing performance of the network is improved by using pipeline design and layer fusion. The LeNet-5 network is to test the implementation on the Xilinx Virtex VC-707 FPGA board. The experimental result shows that when inferring the MNIST test set, the energy efficiency is 843.91 times and 228.35 times that of the CPU and GPU, respectively.

关键词： Power demand Convolution Pipelines Parallel processing Energy efficiency Table lookup Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A survey on credit card fraud detection using various machine learning and deep learning techniques

引用

AIP Conference Proceedings 2023年第1期2800卷

作者： Ashvini S. Gorte S. W. Mohod R. R. Keole T. R. Mahore Sagar Pande Computer Science & Engineer DRGIT&R Amravati Maharashtra India Information Technology HVPM Amravati Maharashtra India Intelligent System School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

There has been a substantial growth of technology and it has evolved a lot, and with the evolving technology credit cards seem to be replacing cash payments. There is no second thought about credit cards getting used on a large scale but this extensive use brings a huge number of fraudulent uses of credit cards. In this paper, discussions on different technologies and methods that are used to detect and prevent credit card fraud have been presented. In the paper discussion on the statistics of the credit card frauds detected using machine learning and deep learning has been presented. In this paper, we have presented the survey on Machine learning techniques and analyzed their accuracy and speed, also we have discussed the methods that are used in detecting credit card fraud using deep learning and artificial intelligence. Furthermore, in this paper, various types of datasets are explained in detail. Also, the paper highlights the challenges and possible solutions to detect fraud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring advanced materials: Harnessing the synergy of inverse gas chromatography and artificial vision intelligence

引用

TrAC - Trends in Analytical Chemistry 2024年 173卷

作者： Basivi, Praveen Kumar Hamieh, Tayssir Kakani, Vijay Pasupuleti, Visweswara Rao Sasikala, G. Heo, Sung Min Pasupuleti, Kedhareswara Sairam Kim, Moon-Deock Munagapati, Venkata Subbaiah Siva Kumar, Nadavala Wen, Jet-Chau Kim, Chang Woo Pukyong National University Industry-University Cooperation Foundation Pukyong National University Busan48513 Korea Republic of Faculty of Science and Engineering Maastricht University P.O. Box 616 MD Maastricht6200 Netherlands Faculty of Sciences Lebanese University Hadath Lebanon Department of Integrated System Engineering INHA University 100 Inha-ro Namgu Incheon22212 Korea Republic of Center for International Relations and Research Collaborations and School of Applied Sciences REVA University Rukmini Knowledge Park Kattigenahalli Yelahanka Karnataka Bangalore560064 India School of Computer Sciences and Applications REVA University Kattigenahalli Rukmini Knowledge Park Bangalore560064 India Department of Smart Green Technology Engineering Pukyong National University Busan48513 Korea Republic of Chungnam National University 99 Daehak-ro Yuseong-gu Daejeon34134 Korea Republic of National Yunlin University of Science and Technology Douliou Yunlin64002 Taiwan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology Douliou Yunlin64002 Taiwan Department of Chemical Engineering College of Engineering King Saud University P.O. Box - 800 Riyadh11421 Saudi Arabia Department of Nanotechnology Engineering College of Engineering Pukyong National University Busan48513 Korea Republic of

Inverse gas chromatography (IGC) has emerged as a highly sensitive, adaptable, and effective technology for material analysis. Through employing thermochemical approaches, IGC provides crucial insight into physicochemical information of materials such as dispersive surface free energy, Gibbs surface energy components and Guttamann Lewis acid-base parameters. In this comprehensive review, we delve into the historical background, instrumentation, and diverse applications of IGC. Researchers and practitioners will find valuable information on the selection and description of numerous models used in IGC experiments. The applications of IGC span various domains, including polymers, medicines, minerals, surfactants, and nanomaterials. Furthermore, IGC facilitates the measurement of important parameters such as sorption enthalpy and entropy, surface energy components (dispersive and specific), co/adhesion work, glass transition temperature, surface heterogeneity, miscibility, solubility parameters, and specific surface area. These insights contribute to a deeper understanding of material behavior and aid in the design and optimization of advanced materials. Moreover, the integration of computer vision and image processing techniques with IGC has enhanced our understanding of materials intricate surface texture, roughness, and related properties. This convergence of IGC with computer vision and artificial intelligence (AI) presents exciting opportunities for future exploration of chemical materials, opening new avenues for research and discovery. This paper not only provides a comprehensive overview of IGC, its techniques, and applications but also highlights the synergistic potential of combining IGC with AI and computer vision. The informative content and insights presented here will benefit researchers, scientists, and professionals in the field of advanced materials, enabling them to leverage IGC and AI for innovative materials discovery and development. © 2024 Elsevier

关键词： Interfacial energy

来源：评论

学校读者我要写书评

暂无评论

RETRACTION: Luminescent solar concentrator efficiency enhanced via nearly lossless propagation pathways

引用

NATURE PHOTONICS 2024年第9期18卷 998-998页

作者： Park, Kyoungwon Yi, Jeongmin Yoon, Suk-Young Park, Seong Min Kim, Jiyong Shin, Hyun-Beom Biswas, Swarup Yoo, Gang Yeol Moon, Sang-Hwa Kim, Jiwan Oh, Min Suk Wedel, Armin Jeong, Sohee Kim, Hyeok Oh, Soong Ju Kang, Ho Kwan Yang, Heesun Han, Chul Jong Display Research Center Korea Electronics Technology Institute Seongnam-si Republic of Korea Department of Materials Science and Engineering Korea University Seoul Republic of Korea Department of Materials Science and Engineering Hongik University Seoul Republic of Korea Functional Materials and Devices Fraunhofer Institute for Applied Polymer Research Potsdam Germany Device Technology Division Korea Advanced Nano Fab Center Suwon-si Republic of Korea School of Electrical and Computer Engineering Center for Smart Sensor System of Seoul (CS4) University of Seoul Seoul Republic of Korea Department of Advanced Materials Engineering Kyonggi University Suwon-si Republic of Korea Department of Energy Science Sungkyunkwan Institute of Energy Science and Technology (SIEST) Artificial Atom and Quantum Materials Center Sungkyunkwan University (SKKU) Suwon Republic of Korea

来源：评论

学校读者我要写书评

暂无评论

Efficient Random Subspace Decision Forests with A Simple Probability Dimensionality Setting Scheme

SSRN

引用

SSRN 2022年

作者： Wang, Quan Wang, Fei Li, Zhongheng Jiang, Peilin Ren, Fuji Nie, Feiping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing100094 China School of Software Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Northwestern Polytechnical University Shaanxi Xi’an710072 China

The random subspace concept is widely used in decision forests. However, there is not a reasonable approach to specify the appropriate number of randomly selected features. Previous random subspace decision forests simply specify the random subspace dimensionality d s to a preset function value such as [log 2 d ] or [√ d ] where d is the number of the total feature dimensions. Actually, this preset value may be a relatively poor choice for high dimensional data sets. In this paper, a novel framework named Efficient Random Subspace decision forest (ERS) is proposed which pays attention to how to set the random subspace dimensionality for each decision tree of decision forests. Specifically, a simple discrete uniform distribution is employed to set with probability the number of randomly selected features for each tree in random subspace decision forests. The proposed Half Range Discrete Uniform distribution-based Varied Dimensionality setting (HRDUVD) method removes the hesitation of how to preset an appropriate d s for different data sets but also results in good enough classification performance along with relatively short running time. Plenty of experiments on public benchmark data sets have demonstrated the effectiveness and the efficiency of the proposed ERS. © 2022, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

CRB-Net: A Sign Language Recognition Deep Learning Strategy Based on Multi-modal Fusion with Attention Mechanism *

CRB-Net: A Sign Language Recognition Deep Learning Strategy ...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Feng Xiao Cong Shen Tiantian Yuan Shengyong Chen School of Computer Science and Engineering Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin P.R.China Technical College for the Deaf Tianjin University of Technology Tianjin P.R.China

ISBN: (纸本)9781665442084

At present, sign language recognition (SLR) researchers are mainly committed to establishing a sign language recognition model based on single-mode data. Nevertheless, this manipulation often leads to a defective understanding of the sign language semantics and ignoring some visual information. In a nutshell, the challenges locate redundancy removing and the alignment of the sign language data with the given tag. To solve the conundrum, this paper proposes a deep learning strategy called CRB-Net, which has used a kind of multimodal fusion attention mechanism. We first extract the features from RGB video and depth video, respectively, then conduct multi-modal fusion. Finally, the fused feature information is fed into an encoder-decoder network to achieve the goal of end-to-end continuous SLR. We verify the effectiveness of our method on three datasets, including the German dataset RWTH-Phoenix-Weather-2014, the Chinese dataset USTC-CSL and the Chinese dataset TJUT-SLRT. As shown by experimental results, the accuracy of 98.5% of our framework CRB-Net has outperformed the state-of-the-art works in the comparison, both in accuracy and algorithm execution efficiency.

关键词： Deep learning Training Visualization Shape Semantics Gesture recognition Assistive technologies

来源：评论

学校读者我要写书评

暂无评论

Global assessment of terrestrial productivity in response to water stress

引用

Science Bulletin 2024年第15期69卷 2352-2356页

作者： Qi Liu Huadong Guo Jiahua Zhang Shijie Li Ji Li Fengmei Yao Miguel D.Mahecha Jian Peng School of Computer Engineering Jiangsu University of TechnologyChangzhou 213001China College of Earth and Planetary Sciences University of Chinese Academy of SciencesBeijing 101408China Department of Remote Sensing Helmholtz Centre for Environmental ResearchUFZLeipzig 04318Germany Remote Sensing Centre for Earth System Research Leipzig UniversityLeipzig 04103Germany Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Remote Sensing and Digital Earth Center School of Computer Science and TechnologyQingdao UniversityQingdao 266071China Key Laboratory of Earth Observation of Hainan Province Hainan Aerospace Information Research InstituteChinese Academy of SciencesSanya 572000China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China Key Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China German Centre for Integrative Biodiversity Research(iDiv) Halle-Jena-Leipzig 04103Germany

In recent decades, climate warming has led to an increase in atmospheric water demand, a potential reduction in soil moisture and a rise in the frequency and intensity of droughts. This has intensified the effects of water stress on plants, leading to more vegetated areas experiencing water stress [1,2]. Soil moisture (SM)and vapor pressure deficit (VPD) are considered the two main factors that exert water stress on vegetation activity and terrestrial productivity, thereby affecting the global carbon cycle [3].

关键词： soil moisture terrestrial

来源：评论

学校读者我要写书评

暂无评论

Rail-5k: A real-world dataset for rail surface defects detection

arXiv

引用

arXiv 2021年

作者： Zhang, Zihao Yu, Shaozuo Yang, Siwei Zhou, Yu Zhao, Bingchen The Key Laboratory of Road and Traffic Engineering Ministry of Education Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety Tongji University Shanghai China Department of Computer Science Tongji University Shanghai China

This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real world application scenario, namely the rail surface defects detection task. We collected over 5k high quality images from railways across China, and annotated 1100 images with the help from railway experts to identify the most common 13 types of rail defects. The dataset can be used for two settings both with unique challenges, the first is the fully-supervised setting using the 1k+ labeled images for training, fine-grained nature and long-tailed distribution of defect classes makes it hard for visual algorithms to tackle. The second is the semi-supervised learning setting facilitated by the 4k unlabeled images, these 4k images are uncurated containing possible image corruptions and domain shift with the labeled images, which can not be easily tackle by previous semi-supervised learning methods. We believe our dataset could be a valuable benchmark for evaluating robustness and reliability of visual algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Rails

来源：评论

学校读者我要写书评

暂无评论

GraphEye: A Novel Solution for Detecting Vulnerable Functions Based on Graph Attention Network

GraphEye: A Novel Solution for Detecting Vulnerable Function...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Li Zhou Minhuan Huang Yujun Li Yuanping Nie Jin Li Yiwei Liu School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Science and Technology on Information System Security BeijingChina School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665418164

With the continuous extension of the Industrial Internet, cyber incidents caused by software vulnerabilities have been increasing in recent years. However, software vulnerabilities detection is still heavily relying on code review done by experts, and how to automatically detect software vulnerabilities is an open problem so far. In this paper, we propose a novel solution named GraphEye to identify whether a function of C/C++ code has vulnerabilities, which can greatly alleviate the burden of code auditors. GraphEye is originated from the observation that the code property graph of a non-vulnerable function naturally differs from the code property graph of a vulnerable function with the same functionality. Hence, detecting vulnerable functions is attributed to the graph classification problem. GraphEye is comprised of VecCPG and GcGAT. VecCPG is a vectorization for the code property graph, which is proposed to characterize the key syntax and semantic features of the corresponding source code. GcGAT is a deep learning model based on the graph attention networks, which is proposed to solve the graph classification problem according to VecCPG. Finally, GraphEye is verified by the SARD Stack-based Buffer Overflow, Divide-Zero, Null Pointer Deference, Buffer Error, and Resource Error datasets, the corresponding F1 scores are 95.6%, 95.6%, 96.1%, 92.6%, and 96.1% respectively, which validate the effectiveness of the proposed solution.

关键词： Deep learning Codes Conferences Semantics Cyberspace Syntactics Data science

来源：评论

学校读者我要写书评

暂无评论

Examining the Fourier Spectrum of Speech Signal from a Time-Frequency Perspective for Automatic Depression Level Prediction

引用

IEEE Transactions on Affective Computing 2025年

作者： Niu, Mingyue Tao, Jianhua He, Yongjun Zhang, Shiqing Li, Ming YanShan University School of Information Science and Engineering Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Taizhou University Institute of Intelligent Information Processing Taizhou318000 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China

Currently, many studies use Fourier amplitude spectra of speech signals to predict depression levels. However, those works often treat Fourier amplitude spectra as images or sequences to capture depression cues using convolutional neural networks or multilayer perceptrons. Therefore, they ignore the complex element composition and time-frequency attributes of Fourier spectra, which is not conducive to capturing the differences among individuals with different depression levels. For this reason, we construct a Time-Frequency Self-Embedding (TFSE) module, which not only stores the correlation relationship among real (imaginary) parts of Fourier spectra of different subjects from the time-frequency perspective, but also maintain the physical properties of data through the weight embedding process. Besides, Global Average Pooling (GAP) or linear layers are difficult to balance both temporal and frequency dimensions in the vectorization process. Therefore, we construct a Time-Frequency Tensor Vectorization (TFTV) module, which summarizes each channel along time and frequency dimensions, and then generates the vectorization result by integrating various channels. In this way, we combine TFSE and TFTV modules to form our SpectrumFormer model for predicting depression levels. Evaluation indicators on AVEC 2013 and AVEC 2014 depression databases imply the progressiveness of our model. © 2010-2012 IEEE.

关键词： Depression level prediction Real and imaginary parts Tensor vectorization Time-frequency attributes

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：