patternrecognition of hand gesture is currently research hot spot. It is important for rehabilitation training, human-computer interaction, prosthetic control and sports science research etc. The brachioradialis, ext...
详细信息
ISBN:
(纸本)9783642238956
patternrecognition of hand gesture is currently research hot spot. It is important for rehabilitation training, human-computer interaction, prosthetic control and sports science research etc. The brachioradialis, extensor digitorum communis, flexor carpi ulnaris muscle and flexor carpi radialis muscle as signal acquisition points;this paper captures four channel sEMG signals. Aiming at the sEMG signals of hand gesture, this paper uses the eigenvalue processed by RMS and MOV as training data samples, which is regarded as the input of LVQ neural network. Through training and learning samples, the better training result is got. The results of the study indicate that the LVQ neural network can effectively identify three action modes, all fingers, relax and middle, by adopting the four channel sEMG signals. The simple algorithm, small calculation and more than 89 percent recognition rate shows that it is a very good method of patternrecognition.
Discriminant analysis is an important multivariate statistical analysis, and plays an important part in pattern classification, datamining, machinelearning et al. In this paper, based on principle of progressively s...
详细信息
ISBN:
(纸本)9783037850992
Discriminant analysis is an important multivariate statistical analysis, and plays an important part in pattern classification, datamining, machinelearning et al. In this paper, based on principle of progressively statistical discriminant analysis under Fisher rule, a progressively statistical discriminant model is set up. The authors analyzed the data about the occurrence of the second generation of the corn borer in 21 years from 1985 to 2006 (except 1990) at Linyi, Shandong Province, and then set up three graded recognitionpattern. The results tested the pest data showed that the fitting rate is 95.24%, 92.31% and 100% respectively, and that accuracy of forecast is satisfactory.
The two mature disciplines, namely datamining and data Warehousing have broadly the same set of objectives. Yet, they have developed largely separate from each other resulting in different techniques being used in ea...
详细信息
ISBN:
(数字)9783642221859
ISBN:
(纸本)9783642221842
The two mature disciplines, namely datamining and data Warehousing have broadly the same set of objectives. Yet, they have developed largely separate from each other resulting in different techniques being used in each discipline. It has been recognized that mining techniques developed for patternrecognition such as Clustering and Visualization can assist in designing data warehouse schema. However, a suitable methodology is required for the seamless integration of mining methods in the design of warehouse schema. In previous work, we presented a methodology that employs hierarchical clustering to derive a tree structure that can be used by a data warehouse designer to build a schema. We believe that, in order to strengthen the decision making process, there is a strong need for a method that automatically extracts knowledge present at different levels of abstraction from a warehouse. We demonstrate with examples how mining at different levels of a hierarchical warehouse schema can give new insights about the underlying data cluster which not only helps in building more meaningful dimensions and facts for data warehouse design but can also improve the decision making process.
Most feed-forward artificial neural network training algorithms for classification problems are based on an iterative steepest descent technique. Their well-known drawback is slow convergence. A fast solution is an Ex...
详细信息
Image classification poses challenges to retrieval technology. Though the Support Vector machine (SVM) has been successfully applied to patternrecognition, its performance is limited by the feature space and paramete...
详细信息
ISBN:
(纸本)9783037850190
Image classification poses challenges to retrieval technology. Though the Support Vector machine (SVM) has been successfully applied to patternrecognition, its performance is limited by the feature space and parameters in the training process. Our work thus has two central themes. Construct the optimum feature space for training SVM from image features extraction by nonlinear dimensionality reduction based on manifold learning, and meanwhile establish the RBF kernel based SVM classifier by training with the best parameters with a global search capacity of the Quantum-behaved Particle Swarm Optimization (QPSO). Experiments show that our model not only improves the learning ability, but also significantly enhances the accuracy of image classification.
Fast retrieval of relevant information from the databases has always been a significant issue. Different techniques have been developed for this purpose;one of them is datamining. Clustering analysis is a key and eas...
详细信息
ISBN:
(纸本)9781467306706;9781467306690
Fast retrieval of relevant information from the databases has always been a significant issue. Different techniques have been developed for this purpose;one of them is datamining. Clustering analysis is a key and easy tool in datamining and patternrecognition. In this paper K-Mean clustering is used for evaluating the performance of socially and economically backward group of people, self help groups (SHG's) in Kerala state, and suggestions are made to improve socioeconomic status. The necessary information about the members of SHG has been collected from 9 districts in Kerala through structured questionnaire. The Parameters considered for the study are financial status, types of loan availed, improvement in assets before and after joining the group, effect of joining in more than one group and district wise analysis.
This paper describes a new learning strategy on the problem of classification on overlapped and imbalanced training set. We devise an adaptive scheme for minority generating;with data cleaning of majority, new cluster...
详细信息
Autonomous systems gather high-dimensional sensorimotor data with their multimodal sensors. Symbol grounding is about whether these systems can, based on this data, construct symbols that serve as a vehicle for higher...
详细信息
ISBN:
(纸本)9789898425409
Autonomous systems gather high-dimensional sensorimotor data with their multimodal sensors. Symbol grounding is about whether these systems can, based on this data, construct symbols that serve as a vehicle for higher symbol-oriented cognitive processes. machinelearning and datamining techniques are geared towards finding structures and input-output relations in this data by providing appropriate interface algorithms that translate raw data into symbols. Can autonomous systems learn how to ground symbols in an unsupervised way, only with a feedback on the level of higher objectives? A target-oriented optimization procedure is suggested as a solution to the symbol grounding problem. It is demonstrated that the machinelearning perspective introduced in this paper is consistent with the philosophical perspective of constructivism. Interface optimization offers a generic way to ground symbols in machinelearning. The optimization perspective is argued to be consistent with von Glasersfeld's view of the world as a black box. A case study illustrates technical details of the machine symbol grounding approach.
An ocean turbine extracts the kinetic energy from ocean currents to generate electricity. Vibration signals from the turbine hold a wealth of information regarding its state, and detecting changes in these signals is ...
详细信息
ISBN:
(纸本)9780769545967
An ocean turbine extracts the kinetic energy from ocean currents to generate electricity. Vibration signals from the turbine hold a wealth of information regarding its state, and detecting changes in these signals is crucial to the timely detection of faults. Wavelet transforms provide a means of analyzing these complex signals and extracting features which are representative of the signal. Feature selection techniques are needed once these wavelet features are extracted to eliminate redundant or useless features before the data is presented to a machinelearning algorithm for patternrecognition and classification. This reduces the quantity of data to be processed and can often even increase the machine learner's ability to detect the current state of the machine. This paper empirically compares eight feature selection algorithms on wavelet transformed vibration data originating from an onshore test platform for an ocean turbine. A case study shows the classification performances of seven machine learners when trained on the datasets with varying numbers of features selected from the original set of all features. Our results highlight that by choosing an appropriate feature selection technique and applying it to selecting just the 3 most important features (3.33% of the original feature set), some classifiers such as the decision tree and random forest can correctly differentiate between faulty and nonfaulty states almost 100% of the time. These results also show the performance differences between different feature selection algorithms and classifier combinations.
Nowadays computer scientists are faced with fast growing and permanently evolving data, which are represented as observations made sequentially in time. A common problem in the datamining community is the recognition...
详细信息
暂无评论