检索结果-内蒙古大学图书馆

Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2021年 29卷 1827-1837页

作者： Cheng, Shihao Bolivar-Nieto, Edgar Gregg, Robert D. Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA Univ Michigan Robot Inst Ann Arbor MI 48109 USA Univ Michigan Div Elect & Comp Engn Ann Arbor MI 48109 USA

Current supervised learning or deep learning-based activity recognition classifiers can achieve high accuracy in recognizing locomotion activities. Most available techniques use a high-dimensional space of features, e.g., combinations of EMG, kinematics and kinetics, and transformations over those signals. The associated classification rules are therefore complex;the machine tries to understand the human, but the human does not understand the machine. This paper presents an activity recognition system that uses signals from a thigh-mounted IMU and a force sensitive resistor to classify transitions between sitting, walking, stair ascending, and stair descending. The system uses the thigh's orientation and velocity with foot contact information at specific moments within a given activity as the features to classify transitions to other activities. We call these Instantaneous Characteristic Features (ICFs). Because these ICFs are biomechanically intuitive, they are easy for the user to understand and thus control the activity transitions of wearable robots. We assessed our classification algorithm offline using an existing dataset with 10 able-bodied subjects and online with another 10 able-bodied subjects wearing a real-time system. The offline study analyzed the effect of subject-dependency and ramp inclinations. The real-time classification accuracy was evaluated before and after training the subjects on the ICFs. The real-time system achieved overall pre-subject-training and post-subject-training error rates of 0.59% +/- 0.24% and 0.56% +/- 0.20%, respectively. We also evaluated the feasibility of our ICFs for amputee ambulation by analyzing a public dataset with the open-source bionic leg. The simplicity of these classification rules demonstrates a new paradigm for activity recognition where the human can understand the machine and vice-versa.

关键词： Legged locomotion Stairs Thigh Real-time systems Activity recognition Prosthetics Feature extraction Activity recognition classification algorithm wearable sensors prosthetics machine learning

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC IDENTIFICATION OF ROCKS IN THIN-SECTIONS USING TEXTURE ANALYSIS

引用

MATHEMATICAL GEOLOGY 1995年第7期27卷 847-865页

作者： WANG, L 1. Centre d'applications et de recherches en télédétection (CARTEL) Université de Sherbrooke J1K 2R1 Sherbrooke Quebec Canada

This paper presents a test of the automatic identification of photomicrographs of rocks in thin sections using digital image processing and texture analysis. Three sets of textural measures derived respectively from the cooccurrence matrix, texture space, and texture spectrum have been used to identify six rock types (mylonite, diorite porphyry, diorite, gabbro, granite, and peridotite). Exploring only the texture characteristics of images, the average correct recognition rate reaches 89% for 58 photographs belonging to the sir types. The results also show the importance of using those more discriminating texture features in the classification algorithm. For the present study, the average rate of correct classification ranges from 46% to 89% depending on the set of texture measures used. The features extracted from the texture spectrum have more discriminating performance than the conventionally used Haralick measures derived from the cooccurrence matrix.

关键词： ROCK RECOGNITION IMAGE PROCESSING CRYSTAL TEXTURE classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Inferring ecological processes from population signatures: A simulation-based heuristic for the selection of sampling strategies

引用

ECOLOGICAL MODELLING 2018年 385卷 12-25页

作者： Bellot, Benoit Poggi, Sylvain Baudry, Jacques Bourhis, Yoann Parisey, Nicolas INRA UMR IGEPP 1349 Domaine MotteBP 35327 F-35653 Le Rheu France INRA UMR BAGAP 65 Rue St BrieucCS 84215 F-35042 Rennes France Rothamsted Res Dept Biointeract & Crop Protect Harpenden AL5 2JQ Herts England

A good knowledge about species traits variability in relation to their environment is the cornerstone of landscape-oriented species management studies. One way to infer this relationship is to compare species signatures in space and time from field data with spatially explicit population dynamics models outputs. However, the inference robustness relies on the available field data, and thus on the quality of the underlying sampling strategy. Field sampling is constrained by several factors, such as the number of landscape replicates, possible number of temporal sessions and number of sample locations, that need to be accounted for prior to field sampling. We set and illustrate a heuristic method to answer the question of optimal sampling conditioned by these landscape-induced constraints. First we studied a real agricultural landscape to determine its mean properties in terms of configuration and composition. The real landscape properties were used as constraints in a landscape model to generate a collection of landscapes with similar properties. On the other hand, we formulated population dynamics models (hereafter noted Process Models (PM)) carrying competing hypotheses about two ecological processes-population growth and dispersal-in relation to spatial covariates for Pterostichus melanarius, a carabid species involved in pest regulation. We simulated these spatially explicit models and extracted their sampling-dependent signatures, i.e. metrics computed on different population samples. We defined a sampling design quality as its ability to capture the contrasts between the PM signatures, summarised by the performance of a classification procedure. The most relevant sampling design was selected on the basis of classification performance and in situ feasibility. Finally we explored the effects of the a priori ecological hypotheses quality on classification performances, through a sensitivity analysis of the PM parameters. While some improvements remain to be achiev

关键词： Ecological traits Reaction-diffusion models Population patterns Sampling designs classification algorithm Landscape ecology

来源：评论

学校读者我要写书评

暂无评论

Shallow Versus Deep Neural Networks in Gear Fault Diagnosis

引用

IEEE TRANSACTIONS ON ENERGY CONVERSION 2020年第3期35卷 1338-1347页

作者： Cirrincione, Giansalvo Kumar, Rahul Ranjeev Mohammadi, Ali Kia, Shahin Hedayati Barbiero, Pietro Ferretti, Jacopo Univ Picardie Jules Verne Lab LTI F-80025 Amiens France Univ South Pacific Sch Engn & Phys Suva 9072 Fiji Univ Padua Dept Ind Engn I-35122 Padua Italy Univ Picardie Jules Verne Lab MIS F-80025 Amiens France Politecn Torino Dept Math Sci I-10129 Turin Italy Politecn Torino DET Dept Elect & Telecommun I-10129 Turin Italy Univ Torino Dipartimento Sci Chirurg I-10124 Turin Italy

Accurate gear defect detection in induction machine-based systems is a fundamental issue in several industrial applications. At this aim, shallow neural networks, i.e., architectures with only one hidden layer, have been used after a feature extraction step from vibration, torque, acoustic pressure and electrical signals. Their additional complexity is justified by their ability in extracting its own features and in the very high-test classification rates. These signals are here analyzed, both geometrically and topologically, in order to estimate the class manifolds and their reciprocal positioning. At this aim, the different states of the gears are studied by using linear (Pareto charts, biplots, principal angles) and nonlinear (curvilinear component analysis) techniques, while the class clusters are visualized by using the parallel coordinates. It is deduced that the class manifolds are compact and well separated. This result justifies the use of a shallow neural network, instead of a deep one, as already remarked in the literature, but with no theoretical justification. The experimental section confirms this assertion, and also compares the shallow neural network results with the other machine learning techniques used in the literature.

关键词： Gears Feature extraction Vibrations Neural networks Principal component analysis Electronic mail Fault detection classification algorithm fault detection fault diagnosis gears induction motors multilayer perceptron neural networks principal component analysis vibrations

来源：评论

学校读者我要写书评

暂无评论

A novel hyperspectral imaging and modeling method for the component identification of woven fabrics

引用

TEXTILE RESEARCH JOURNAL 2019年第18期89卷 3752-3767页

作者： Li, Jiaping Meng, Xiang Wang, Wendi Xin, Binjie Shanghai Univ Engn Sci Room A223Art Bldg333 Longteng Rd Shanghai 8621 Peoples R China

The component identification of textile materials is critical for quality control and measurement in the textile field. A novel hyperspectral imaging method and the related identification model are proposed to classify single-component textiles. Firstly, the hyperspectral data of the single-component fabrics were processed to conduct dimensionality reduction based on locally linear embedding (LLE), principal component analysis (PCA), and locally preserving projection (LPP) algorithms. Moreover, the original data of 288 wavelengths from 920 nm to 2500 nm were compressed to keep the typical wavelength regions. After that, these data were imported into two classifiers (decision tree classifier and K nearest neighbor (KNN) classifier) for training, and an identification model based on these training data was developed for the sample classification. The experimental results showed that all the samples could be identified correctly by the established identification model. The recognition rate and the stability of the classifier based on LPP model and KNN classification algorithm were proved to have the highest accuracy in our research.

关键词： hyperspectral imaging spectral analysis component identification dimension reduction classification algorithm

来源：评论

学校读者我要写书评

暂无评论

An Approach to Recognize and Classify Arm Activities Using Wearable Ultra Wide Band Antennas

引用

WIRELESS PERSONAL COMMUNICATIONS 2024年第2期139卷 1303-1318页

作者： Tiwari, Bhawna Gupta, Sindhu Hak Balyan, Vipin Amity Univ Dept Elect & Commun Noida Uttar Pradesh India GL Bajaj Inst Technol & Management Greater Noida Uttar Pradesh India Cape Peninsula Univ Technol Dept Elect Elect & Comp Engn Cape Town South Africa

Continuous observation, recognition and classification of various body movements and activities is essential for the implementation of Wireless Body Area Networks (WBAN) to discern the status of body parts functionalities or abnormalities if any. WBAN can continuously observe various movements of human body parts and human body activities. Recognition and classification of arm activities plays an important role in fitness monitoring, assisted living, and sports tracking, etc. In the presented work, Ultra Wide Band antennas are designed and employed on human body to observe datasets of antenna performance parameters associated with various arm movements and activities. The classification of three arm activities i.e. boxing, rowing, and clapping are implemented using Support Vector Machine, K-Nearest Neighbor, Random Forest and Decision Tree machine learning algorithms. Performance of classification depends on accuracy of implemented algorithm. The highest classification accuracies are found to be 99% in case of Decision Tree algorithm.

关键词： Arm activity recognition and classification Health monitoring WBAN UWB antenna S-11 S-21 VSWR Machine learning classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Feature selection and classifier performance on diverse bio- logical datasets

引用

BMC BIOINFORMATICS 2014年第13-Sup期15卷 S4-S4页

作者： Hemphill, Edward Lindsay, James Lee, Chih Mandoiu, Ion I. Nelson, Craig E. Dept Mol & Cellular Biol Storrs CT 06269 USA Univ Connecticut Dept Comp Sci & Engn Storrs CT 06269 USA

Background: There is an ever-expanding range of technologies that generate very large numbers of biomarkers for research and clinical applications. Choosing the most informative biomarkers from a high-dimensional data set, combined with identifying the most reliable and accurate classification algorithms to use with that biomarker set, can be a daunting task. Existing surveys of feature selection and classification algorithms typically focus on a single data type, such as gene expression microarrays, and rarely explore the model's performance across multiple biological data types. Results: This paper presents the results of a large scale empirical study whereby a large number of popular feature selection and classification algorithms are used to identify the tissue of origin for the NCI-60 cancer cell lines. A computational pipeline was implemented to maximize predictive accuracy of all models at all parameters on five different data types available for the NCI-60 cell lines. A validation experiment was conducted using external data in order to demonstrate robustness. Conclusions: As expected, the data type and number of biomarkers have a significant effect on the performance of the predictive models. Although no model or data type uniformly outperforms the others across the entire range of tested numbers of markers, several clear trends are visible. At low numbers of biomarkers gene and protein expression data types are able to differentiate between cancer cell lines significantly better than the other three data types, namely SNP, array comparative genome hybridization (aCGH), and microRNA data. Interestingly, as the number of selected biomarkers increases best performing classifiers based on SNP data match or slightly outperform those based on gene and protein expression, while those based on aCGH and microRNA data continue to perform the worst. It is observed that one class of feature selection and classifier are consistently top performers across data types and

关键词： Feature Selection Data Type Random Forest classification algorithm Feature Selection Method

来源：评论

学校读者我要写书评

暂无评论

Methodology and application of digital twin-driven diesel engine fault diagnosis and virtual fault model acquisition

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 131卷

作者： Bo, Yaqing Wu, Han Che, Weifan Zhang, Zeyu Li, Xiangrong Myagkov, Leonid Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China Bauman Moscow State Tech Univ Dept Piston Engines Moscow 105005 Russia

Digital real-time fault diagnosis is an effective way to ensure the reliable long-term operation of the diesel engine, but there is still a lack of systematic methods with high integrity and practicability. Therefore, a digital twindriven diesel engine fault diagnosis method based on the combination of the classification algorithm and the optimization algorithm is proposed and a case study of fuel injection system fault diagnosis is used to illustrate and verify the proposed method. This method closely links the physical system, virtual model, database, and diagnosis system through data transmission and the diagnostic process consists of three parts: classification, diagnosis, and decision. The fault classification part can preliminarily lock the possible types and degrees of faults, and point out the key classification features for each fault type by using classification algorithms such as Random Forest. The fault diagnosis part can diagnose and reproduce the diesel engine faults by using an optimization-simulation joint calculation model, where the virtual model variables and optimization algorithm are determined according to the possible fault types, and the optimization target depends on the importance of classification features. Then the maintenance decision can be made according to the fault detailed information. The proposed method reduces the requirement of covering the fault degree of the database, and the obtained fault model provides the possibility for subsequent online optimization and also facilitates the development of intelligent engine management.

关键词： Diesel engine Fault diagnosis classification algorithm Optimization algorithm Digital twin

来源：评论

学校读者我要写书评

暂无评论

Multispectral digital microscopy for in vivo monitoring of oral neoplasia in the hamster cheek pouch model of carcinogenesis

引用

OPTICS EXPRESS 2005年第3期13卷 749-762页

作者： Park, SY Collier, T Aaron, J Markey, MK Richards-Kortum, R Sokolov, K Mackinnon, N MacAulay, C Coghlan, L Milbourne, A Follen, M Univ Texas Dept Biomed Engn Austin TX 78712 USA Univ Texas MD Anderson Canc Ctr Dept Imaging Phys Houston TX 77030 USA British Columbia Canc Res Ctr Dept Canc Imaging Vancouver BC V5Z 4E6 Canada Univ Texas MD Anderson Canc Ctr Div Res Smithville TX 78957 USA Univ Texas MD Anderson Canc Ctr Dept Gynecol Oncol Houston TX 77030 USA Univ Texas Hlth Sci Ctr Dept Obstet Gynecol & Reprod Sci Houston TX 77030 USA

In this study we use a multi-spectral digital microscope (MDM) to measure multi-spectral auto-fluorescence and reflectance images of the hamster cheek pouch model of DMBA ( dimethylbenz[ a] anthracene)induced oral carcinogenesis. The multi-spectral images are analyzed both in the RGB ( red, green, blue) color space as well as in the YCbCr ( luminance, chromatic minus blue, chromatic minus red) color space. Mean image intensity, standard deviation, skewness, and kurtosis are selected as features to design a classification algorithm to discriminate normal mucosa from neoplastic tissue. The best diagnostic performance is achieved using features extracted from the YCbCr space, indicating the importance of chromatic information for classification. A sensitivity of 96% and a specificity of 84% were achieved in separating normal from abnormal cheek pouch lesions. The results of this study suggest that a simple and inexpensive MDM has the potential to provide a cost-effective and accurate alternative to standard white light endoscopy. (C) 2005 Optical Society of America.

关键词： .hamster reflectance multispectral RGB image intensity Richards-Kortum Anderson Cancer Center oral neoplasia cheek pouch DMBA YCbCr chromatic standard deviation skewness kurtosis classification algorithm

来源：评论

学校读者我要写书评

暂无评论

A recursive method for the construction and enumeration of self-orthogonal and self-dual codes over the quasi-Galois ring F2r[u]/<u^e >

引用

DESIGNS CODES AND CRYPTOGRAPHY 2023年第5期91卷 1973-2003页

作者： Yadav, Monika Sharma, Anuradha IIIT Delhi Dept Math New Delhi 110020 India

In this paper, we provide a recursive method to construct self-orthogonal and self-dual codes of the type {k(1), k(2), ... , k(e)} and length n over the quasi-Galois ring F(2)r[u]/ < u(e) > from a self-orthogonal code of the same length n and dimension k(1) + k(2) + middot middot middot + k([e/2])over F(2)r and vice versa, where F2r is the finite field of order 2r, n > 1, e > 2 are integers, [e2] is the smallest integer greater than or equal to e/2, and k(1), k(2), . . . , k([e/2])are non-negative integers satisfying k(1) <= n - (k(1) + k(2) + middot middot middot + k(e)) and k(i) = k(e-i+2) for 2 <= i <= e. We further apply this recursive method to provide explicit enumeration formulae for self-orthogonal and self-dual codes of an arbitrary length over the ring F(2)r[u]/ < u(e) >. With the help of these enumeration formulae and by carrying out computations in the Magma Computational Algebra system, we classify all self-orthogonal and self-dual codes of lengths 2, 3, 4, 5 over the ring F-2[u]/ < u(3) > and of lengths 2, 3, 4 over the ring F-4[u]/ < u(2) >.

关键词： Linear codes Witt decomposition classification algorithm Chain rings

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：