检索结果-内蒙古大学图书馆

Reconfigurable hardware architecture for faster descriptor extraction in SURF

ELECTRONICS LETTERS 2018年第4期54卷 210-212页

作者： Kim, Y. Jung, H. Sookmyung Womens Univ Dept Comp Sci Seoul South Korea

Speeded up robust features (SURFs) are considered to be the most efficient feature extraction algorithm and it has been implemented in powerful hardware for real-time operation due to its characteristics of data-intensive computation of high complexity. Especially, the computational load of the descriptor extraction procedure is very significant and the overall performance of SURF can be improved by speeding up the descriptor extraction step with increasing parallel hardware accelerators. However, simply increasing the hardware accelerators is burdensome because of causing significant area and power consumption. Therefore, a reconfigurable hardware architecture is proposed that enables achieving the maximum performance of the descriptor extraction step with making the best use of the existing accelerators without any additional ones. Experimental results show that the proposed architecture improves the performance of the descriptor extraction step by 24.77-47.45% with negligible area overheads when compared with the existing hardware implementations of the SURF algorithm.

关键词： real-time systems feature extraction reconfigurable architectures reconfigurable hardware architecture descriptor extraction procedure speeded up robust features feature extraction algorithm real-time operation data-intensive computation computational load parallel hardware accelerators SURF algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel Intrusion Detection System for Vehicular Ad Hoc Networks (VANETs) based on differences of traffic flow and position

引用

APPLIED SOFT COMPUTING 2019年 75卷 712-727页

作者： Liang, Junwei Chen, Jianyong Zhu, Yingying Yu, Richard Shenzhen Univ Sch Comp & Software Engn Shenzhen Peoples R China Carleton Univ Sch Informat Technol Ottawa ON Canada

Vehicle ad hoc networks (VANETs) have attracted great interests from both industry and academia, but a number of issues, particularly security, have not been readily addressed. Intrusion Detection System (IDS) as one of the most important approaches to protect network security has been studied adequately in previous literatures. However, the performance of IDSs still needs to be improved to adapt the scenario of VANETs which are very fast moving and highly dynamic. In this paper, we propose a novel IDS that is able to be appropriately used in the wireless and dynamic networks, like VANETs. It mainly contains a novel feature extraction algorithm and a classifier based on an improved growing hierarchical self-organizing map (I-GHSOM) for IDS in VANETs. The proposed feature extraction algorithm is used to quickly extract distinct features from vehicle messages for IDS's training and test. In the proposed algorithm, two key features including the differences of traffic flow and of position are extracted. The former feature is calculated according to the range of the distance between vehicles, while both a voting filter mechanism and a semi-cooperative mechanism are designed to get the latter feature. Furthermore, in the I-GHSOM-based classifier, for quickly attaining precise classification results, two novel mechanisms (relabeling and recalculating mechanisms) are proposed to relabel the units of GHSOM and check whether the balance of GHSOM structure is broken or not. Simulation results show that the proposed IDS is better than others in the measurement of accuracy, stability, processing efficiency and message scales. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Vehicle Ad Hoc Networks (VANETs) Intrusion detection system (IDS) feature extraction algorithm Improved growing hierarchical self-organizing map (I-GHSOM)

来源：评论

学校读者我要写书评

暂无评论

Synthetic aperture radar target configuration recognition using locality-preserving property and the Gamma distribution

引用

IET RADAR SONAR AND NAVIGATION 2016年第2期10卷 256-263页

作者： Liu, Ming Wu, Yan Zhang, Qiang Wang, Fan Li, Ming Xidian Univ Sch Elect Engn Xian 710071 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China

Taking the inevitable speckle noise in synthetic aperture radar (SAR) images into account, a feature extraction algorithm is proposed by combining the locality-preserving property and the Gamma distribution for SAR target configuration recognition in this study. To describe the essential characteristics of SAR images, the authors model the speckle noise by the Gamma distribution. Moreover, the locality-preserving property which is of great importance for recognition is fused into the statistical model to preserve the local structure of the datasets. Besides, they modify the affinity matrix that is used in the locality-preserving property to capture both the local and global structures of the datasets for configuration recognition. The coordinate descent method is carried out for parameter estimation, in which a decomposition method is presented to obtain the transformation matrix. The experimental results on the moving and stationary target acquisition and recognition database validate the effectiveness of the proposed algorithm.

关键词： statistical analysis decomposition method parameter estimation affinity matrix Optical, image and video signal processing matrix algebra Gamma distribution feature extraction Algebra Radar equipment, systems and applications statistical model feature extraction algorithm SAR images SAR target configuration recognition synthetic aperture radar target configuration recognition synthetic aperture radar image denoising locality preserving property Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Prediction of TNM stage in head and neck cancer using hybrid machine learning systems and radiomics features

Prediction of TNM stage in head and neck cancer using hybrid...

引用

Conference on Medical Imaging - Computer-Aided Diagnosis

作者： Salmanpour, Mohammadreza R. Hosseinzadeh, Mahdi Akbari, Azizeh Borazjani, Kasra Mojallal, Kasra Askari, Dariush Hajianfar, Ghasem Rezaeijo, Seyed Masoud Ghaemi, Mohammad M. Nabizadeh, Amir Hossein Rahmim, Arman Univ British Columbia Vancouver BC Canada BC Canc Res Inst Vancouver BC Canada Technol Virtual Collaborat TECVICO Corp Vancouver BC Canada Tarbiat Modares Univ Tehran Iran Hakim Sabzevari Univ Sab Zevar Iran Univ Tehran Tehran Iran Amirkabir Univ Technol Tehran Iran Shahid Beheshti Univ Med Dept Radiol Technol Tehran Iran Iran Univ Med Sci Rajaie Cardiovasc Med & Res Ctr Tehran Iran Ahvaz Jundishapur Univ Med Sci Sch Med Dept Med Phys Ahvaz Iran Kerman Univ Med Sci Kerman Iran IST Univ Lisbon P-1000029 Lisbon Portugal

ISBN: (数字)9781510649422

ISBN: (纸本)9781510649422;9781510649415

The tumor, node, metastasis (TNM) staging system enables clinicians to describe the spread of head-and-neck-squamous-cell-carcinoma (HNSCC) cancer in a specific manner to assist with the assessment of disease status, prognosis, and management. This study aims to predict TNM staging for HNSCC cancer via Hybrid Machine Learning Systems (HMLSs) and radiomics features. In our study, 408 patients were included from the Cancer Imaging Archive (TCIA) database, included in a multi-center setting. PET images were registered to CT, enhanced, and cropped. We created 9 sets including CT-only, PET-only, and 7 PET-CT fusion sets. Next, 215 radiomics features were extracted from HNSCC tumor segmented by the physician via our standardized SERA radiomics package. We employed multiple HMLSs, including 16 feature-extraction (FEA) + 9 feature selection algorithms (FSA) linked with 8 classifiers optimized by grid-search approach, with model training, fine-tuning, and selection (5-fold cross-validation;319 patients), followed by external-testing of selected model (89 patients). Datasets were normalized by z-score-technique, with accuracy reported to compare models. We first applied datasets with all features to classifiers only;accuracy of 0.69 +/- 0.06 was achieved via PET applied to Random Forest classifier (RFC);performance of external testing (similar to 0.62) confirmed our finding. Subsequently, we employed FSAs/FEAs prior to the application of classifiers. We achieved accuracy of 0.70 +/- 0.03 for Curvelet transform (fusion) + Correlation-based feature Selection (FSA) + K-Nearest Neighbor (classifier), and 0.70 +/- 0.05 for PET + LASSO (FSA) + RFC (classifier). Accuracy of external testing (0.65 & 0.64) also confirmed these findings. Other HMLSs, applied on some fused datasets, also resulted in close performances. We demonstrate that classifiers or HMLSs linked with PET only and PET-CT fusion techniques enabled relatively low improved accuracy in predicting TNM stage. Meanwhile, th

关键词： prediction of TNM Stage hybrid machine learning system radiomics feature fusion techniques head and neck squamous cell carcinoma feature extraction algorithm feature selection algorithm classifier

来源：评论

学校读者我要写书评

暂无评论

Research on Motion Posture Based on Convolutional Neural Network algorithm

Research on Motion Posture Based on Convolutional Neural Net...

引用

2024 IEEE International Conference on Cognitive Computing and Complex Data

作者： Tang, Yunpeng Zou, Yu Guizhou Business Sch Phys Educ Teaching Dept Guiyang 550014 Peoples R China Guizhou Kangsitian Sci & Technol Dev Co Ltd Guiyang 550002 Peoples R China

ISBN: (纸本)9798350352900;9798350352894

Recognition of motion postures has been a highly popular research field, aiming to analyze and identify human movements and behavior patterns through observations and description using natural language and other methods. This study introduces a posture motion feature extraction algorithm that incorporates spatiotemporal weighting and utilizes a deep convolutional neural network (CNN) approach. The algorithm extracts spatiotemporal motion key frames from selected motion samples and presents them as static images. It then performs initial motion image preprocessing, such as motion target detection and image enhancement, and vectorizes motion features using CNN. The spatiotemporal weighted adaptive interpolation method is employed to minimize errors in motion edge detection, enabling the extraction of posture motion features by combining posture edge features and spatiotemporal features. The extraction results are presented as the output. Comparative experiments with traditional algorithms demonstrate that the proposed neural network intelligent recognition algorithm not only achieves intelligent recognition of motion postures but also improves overall accuracy and reduces computational load compared to some other algorithms.

关键词： Convolutional neural networks Temporal and spatial weights Sports posture Movement characteristics feature extraction algorithm

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machine based Handwritten Numeral Recognition of Kannada Script

Support Vector Machine based Handwritten Numeral Recognition...

引用

IEEE International Advance Computing Conference

作者： Rajashekararadhya, S. V. Ranjan, P. Vanaja Anna Univ Coll Engn Dept Elect & Elect Engn Chennai 600025 Tamil Nadu India

ISBN: (纸本)9781424429271

Character recognition is the important area in image processing and pattern recognition fields. Handwritten character recognition has received extensive attention in academic and production fields. The recognition system can be either on-line or off-line. Off-line handwriting recognition is the subfield of optical character recognition. India is a multi-lingual and multi-script country, where eighteen official scripts are accepted and have over hundred regional languages. In this paper we present Zone and Distance metric based feature extraction system. The character centroid is computed and the image is further divided in to n equal zones. Average distance from the character centroid to the each pixel present in the zone is computed. This procedure is repeated for all the zones present in the numeral image. Finally n such features are extracted for classification and recognition. Support vector machine is used for subsequent classification and recognition purpose. We obtained 97.75% recognition rate for Kannada numerals.

关键词： Handwritten character recognition feature extraction algorithm Support Vector Machine Kannada Script

来源：评论

学校读者我要写书评

暂无评论

On-Chip Spike Clustering & Classification using Self Organizing Map for Neural Recording Implants

On-Chip Spike Clustering & Classification using Self Organiz...

引用

Annual IEEE Biomedical Circuits and Systems Conference (BioCAS) - Engineering Tomorrow's Healthcare

作者： Yang, Yuning Mason, Andrew J. Michigan State Univ Dept Elect & Comp Engn E Lansing MI 48824 USA

ISBN: (纸本)9781457714702

Spike sorting plays a vital role in recording neural signals using microelectrode arrays for neuroscience research. The bandwidth bottleneck is greatly eased for data transmission of hundreds of channels in neuroprosthetic application through on-chip spike sorting. Our previous work on feature extraction algorithm called Zero-Crossing features (ZCF) shows good performance for data reduction and spike classification while requiring minimal hardware resources. In this paper, a new spike clustering & classification method based on ZCF feature extraction is presented. The method is shown to perform well in identifying the number of neurons in a spike channel and classifying spikes into correct neurons. An implant-compatible VLSI hardware architecture to cluster and classify spikes in the ZCF feature space is also presented.

关键词： Accuracy Classification algorithms Clustering algorithms feature extraction Neurons Signal to noise ratio Sorting VLSI VLSI hardware architecture ZCF feature extraction bandwidth bottleneck data transmission feature extraction feature extraction algorithm

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC HAND GESTURE RECOGNITION

DYNAMIC HAND GESTURE RECOGNITION

引用

International Conference on Signal and Information Processing (IConSIP)

作者： Rokade-Shinde, Rajeshree Sonawane, Jayashree Lokmanya Tilak Callege Engn Koperkhairne Navi Mumbai India

ISBN: (纸本)9781509015221

Recognition of dynamic gesture is one of the most challenging tasks in the computer vision. This paper deals with dynamic hand gesture (digits) recognition. The method consist of three fold novel contributions: firstly finding the flow of hand, secondly recognition technique of signs (Dynamic digits) and thirdly classification of gesture. We worked on 11 to 20 (digits) gestures. Spatiotemporal volume is not always sufficient to grasp the flow of hand movement. We proposed new method to find flow of hand for special signs. features are extracted using proposed feature extraction algorithm and gestures are recognized. Proposed algorithm shows recognition efficiency of 94% for dynamic gestures. Time complexity of the given method is less as compared to some traditional methods.

关键词： Hand segmentation hand flow detection using chain code feature extraction algorithm classification

来源：评论

学校读者我要写书评

暂无评论

Systematic investigation of keywords selection and processing strategy on search engine forecasting: a case of tourist volume in Beijing

引用

INFORMATION TECHNOLOGY & TOURISM 2022年第4期24卷 547-580页

作者： Yuan, Ziqi Jia, Guozhu Sichuan Normal Univ Coll Phys & Elect Engn Chengdu 610000 Peoples R China

The timeliness, precision, and low cost of search data have great potential for projecting tourist volume. Obtaining valuable information for decision-making, particularly for predicting, is hampered by the vast amount of search data. A systematic investigation of keyword selection and processing has been conducted. Using Beijing tourist volume as an example, 11 different feature extraction algorithms were selected and combined with long short-term memory (LSTM), random forest (RF) and fuzzy time series (FTS) for forecasting tourist volume. A total of 1612 keywords were retrieved from Baidu Index demand mapping using the direct word extraction method, range word extraction method and empirical selection method. The remaining 813 keywords were subjected to feature extraction. Based on the forecasting results of medium and short-term (1-day, 7-days and 10-days), the forecasting results of Kernel principal component analysis (KPCA) and locally linear embedding (LLE) are relatively stable when the dimensionality is reduced to 5 dimensions. The forecasting results of t-stochastic neighbor embedding (t-SNE), isometric mapping (IsoMap) and locally linear embedding (LLE), locality preserving projections (LPP), independent component correlation (ICA) are relatively stable when the dimensionality is reduced to 10 dimensions. Accurately forecasting many factors (transportation, attraction, food, lodging, travel, tips, tickets, and weather) provides a solid foundation for tourism demand optimization and scientific management and a resource for tourists' holistic vacation planning.

关键词： Tourist volume forecasting Search engine data feature extraction algorithm LSTM FTS RF

来源：评论

学校读者我要写书评

暂无评论

Security Analysis of Sports Injury Medical System Based on Internet of Health Things Technology

引用

IEEE ACCESS 2020年 8卷 211358-211370页

作者： Xia, Yunping Fan, Yunxiang Hunan Normal Univ Coll Phys Educ Changsha 410000 Peoples R China

In the absence of physical movement, the dynamic process of rehearsing specific actions in the mind based on memory is called motor imagination (MI). Motor imaging brain-computer interface (BCI) refers to communicating with a computer or controlling external devices by imagining specific movements in the brain, while the Internet of health things technology helps to convey the rehabilitation of the limbs of patients with paralysis and stroke in time. Studies have shown that with the increase of motor imaging tasks, the classification accuracy rate will also decrease. It is necessary to study the construction and security of sports injury rehabilitation systems under the Internet of health things. Based on the study of the feature extraction algorithm, this paper starts with the infusion monitoring in the clinical medical care work, and through the construction of the Internet of health things smart care management system. It could provide application modules such as "infusion monitoring", "disease call interconnection", and "PDA interconnection" to realize the closed-loop path management of the whole process of basic nursing work in the ward. The sports rehabilitation training system receives the EEG data collected by the UE-16B EEG amplifier through the socket, and calls MATLAB to perform feature extraction and classification of the EEG data, and feedback the processing results to the sports rehabilitation training system and subjects. On this basis, the system has designed and completed a non-feedback training module, a feedback training module and related BCI game modules to promote users to perform sports imagination training and successfully complete sports rehabilitation training.

关键词： Electroencephalography feature extraction Internet Biomedical imaging Licenses Brain-computer interfaces Training feature extraction algorithm sports injury medical system optimization the Internet of Health Things internet security

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：