While image segmentation is a fundamental and general task of image processing and computer vision, the segmentation of trunks in wood can be considered as a specific, ill posed, and hard problem. However, besides the...
详细信息
ISBN:
(纸本)9781538669792
While image segmentation is a fundamental and general task of image processing and computer vision, the segmentation of trunks in wood can be considered as a specific, ill posed, and hard problem. However, besides the lots of possible applications of it, the problems to be faced are general and can be found in other areas of open-air image analysis. In our paper we discuss these problems and propose a color clustering based approach as a feature generation step for the segmentation of trunks. The results of classification can be used as features for further segmentation techniques such as MRF. The possibility to apply for angle count based volume estimation is also discussed. The performance is shown through several tests with different types of wood.
This article presents certain features and a new classification method for recognition of power quality disturbances. The proposed method uses S-transform to extract the most severable features of the power quality wa...
详细信息
This article presents certain features and a new classification method for recognition of power quality disturbances. The proposed method uses S-transform to extract the most severable features of the power quality waveforms. The disturbances decision-making scheme is performed using the logistic model tree. This new algorithm requires fewer features compared to the wavelet based approach for the identification of power quality events. Thus, the required memory space and learning logistic model tree time are substantially reduced. The most common types of disturbances, including sag, swell, interruption, harmonics, transient, and flicker, are studied. Disturbances consisting of both sag and harmonics, as well as both swell and harmonics, are also considered. The result shows that the classifier can detect and classify different power quality events correctly. Sensitivity of the proposed algorithm under noisy condition is also investigated.
A new artificial intelligence (AI) model, called Bagging-LMT - a combination of bagging ensemble and logistic model tree (LMT) - is introduced for mapping flood susceptibility. A spatial database was generated for the...
详细信息
A new artificial intelligence (AI) model, called Bagging-LMT - a combination of bagging ensemble and logistic model tree (LMT) - is introduced for mapping flood susceptibility. A spatial database was generated for the Haraz watershed, northern Iran, that included a flood inventory map and eleven flood conditioning factors based on the Information Gain Ratio (IGR). The model was evaluated using precision, sensitivity, specificity, accuracy, Root Mean Square Error, Mean Absolute Error, Kappa and area under the receiver operating characteristic curve criteria. The model was also compared with four state-of-the-art benchmark soft computing models, including LMT, logistic regression, Bayesian logistic regression, and random forest. Results revealed that the proposed model outperformed all these models and indicate that the proposed model can be used for sustainable management of flood-prone areas. (C) 2017 Elsevier Ltd. All rights reserved.
Human immunodeficiency virus-1 (HIV-1) is the etiological agent for the global concerning disease "AIDS". The virus infects 35 million people globally and after 30 years, the disease remains a challenge. Des...
详细信息
Human immunodeficiency virus-1 (HIV-1) is the etiological agent for the global concerning disease "AIDS". The virus infects 35 million people globally and after 30 years, the disease remains a challenge. Despite great efforts in finding efficient treatment strategies, the pandemic of AIDS is continuing and the rate of new infections has not been diminished. Therefore, the need for finding novel treatment strategies is still of great importance. Peptide-based therapeutics has shown promise in the treatment of many challenging diseases such as various types of cancers and also HIV. Since time and money are the two restricting factors in any experimental researches, computer-aided techniques can dramatically reduce time and costs. In the present study, we developed a method based on pseudo amino acid composition of amino acid sequences to classify the anti-HIV-1 peptides using different machine learning algorithms. The performance of each algorithm was investigated and after comparing the performance parameters, the most accurate algorithm was proposed for predicting anti-HIV-1 activity of any given peptide. Having the accuracies of 96.15 and 83.71 % respectively, multilayer perceptron (MLP) and logistic model tree algorithms were primarily shown to be the most accurate ones in classifying anti-HIV-1 peptides. Final results demonstrate that model generated by MLP can be a valuable tool for the classification and prediction of anti-HIV-1 peptides in order to have a preliminary prediction which can be further coupled with experimental assays while reducing time and costs.
This research explores the viability of a bimodal fusion of linguistic and acoustic cues in speech to help in real-time emotion recognition in a mobile application that steers the interaction dialogue in tune with use...
详细信息
ISBN:
(纸本)9781479999538
This research explores the viability of a bimodal fusion of linguistic and acoustic cues in speech to help in real-time emotion recognition in a mobile application that steers the interaction dialogue in tune with user's emotions. For capturing affect at the language level, we have utilized both, machine learning and valence assessment of the words carrying emotional connotations. The indicative values of acoustic cues in speech are of special concern in this research and an optimized feature set is proposed. We highlight the results of both independent evaluations of the underlying linguistic and acoustic processing components. We present a study and ensuing discussion on the performance metrics of a logistic model tree that has outperformed the other classifiers considered for the fusion process. The results reinforce the notion that capturing the sound interplay between the diverse set of features is crucial for confronting the subtleties of affect in speech that so often elude the text- or acoustic-only approaches to emotion recognition.
The determination of HIV-1 coreceptor usage plays a major role in HIV treatment. Since Maraviroc has been used in a treatment for patients those exclusively harbor R5-tropic strains, the efficient performance of class...
详细信息
The determination of HIV-1 coreceptor usage plays a major role in HIV treatment. Since Maraviroc has been used in a treatment for patients those exclusively harbor R5-tropic strains, the efficient performance of classifying HIV-1 coreceptor usage can help choose the most advantaged HIV treatment. In general, HIV-1 variants are classified as R5-tropic and X4-tropic or dual/mixed tropic based on their coreceptor usages. The classification of the coreceptor usage has been developed by using the various computational methods or genotypic algorithms based on V3 amino acid sequences. Most genotypic tools have been designed based on a data set of the HIV-1 subtype B that seemed to be reliable only for this subtype. However, the performance of these tools decreases in non-B subtypes. In this study, the support vector machine (SVM) method has been used to classify the HIV-1 coreceptor. To develop an efficient SVM classifier, we present a feature selector using the logistic model tree (LMT) method to select the most relevant positions from the V3 amino acid sequences. Our approach achieves as high as 97.8% accuracy, 97.7% specificity, and 97.9% sensitivity measured by ten-fold cross-validation on 273 sequences. (C) 2012 Published by Elsevier Ltd.
The authors in this paper propose a statistical technique for pattern recognition of electromyogram (EMG) signals along with effective feature ensemble to achieve an improved classification performance with less proce...
详细信息
The authors in this paper propose a statistical technique for pattern recognition of electromyogram (EMG) signals along with effective feature ensemble to achieve an improved classification performance with less processing time and memory space. In this study, EMG signals from 10 healthy subjects and two transradial amputees for six motions of hand and wrist is considered for identification of the intended motion. From four channels myoelectric signals, the extracted time domain features are grouped into three ensembles to identify the effectiveness of feature ensemble in classification. The three feature ensembles obtained from multichannel continuous EMG signals are applied to the new classifiers namely simple logistic regression (SLR), J48 algorithm for decision tree (DT), logistic model tree (LMT) and feature subspace ensemble using k-nearest neighbor (kNN). Novel classifiers SLR, DT and LMT, select only the dominant features during training to develop the model for pattern recognition. This selection of features reduces the processing time as well as memory space of the controller for real-time application. The performance of SLR, DT, LMT and feature subspace ensemble using kNN classifiers are compared with other conventional classifiers, such as neural network (NN), simple kNN and linear discriminant analysis (LDA). The average classification accuracy with SLR is found to be better with feature ensemble-1 compared to the other classifiers. Also, the statistical Kruscal-Wallis test shows, the classification performance of SLR is not only better but also takes less time and memory space compared to other classifiers for classification. Also the performance of the classifier is tested in real-time with transradial amputees for actuation of drive for two intended motions with TMS320F28335eZdsp controller. The experimental results show that the SLR classifier improves the controller response in real-time.
This paper presents a new combined S-Transform and logistic model tree (ST-LMT) techniques for fault classification and fault section identification in advanced series compensated transmission system. The Thyristor Co...
详细信息
This paper presents a new combined S-Transform and logistic model tree (ST-LMT) techniques for fault classification and fault section identification in advanced series compensated transmission system. The Thyristor Controlled Series Capacitor (TCSC) is employed at the midpoint of a line. Initially, ST is utilized to extract some useful features of post fault three line currents for one cycle duration to accomplish fault diagnosis task. A key attribute of ST is that it uniquely combines a frequency dependent resolution of the time-frequency space. The features extracted are used to train a single LMT model for fault type classification and determining fault section (whether the fault occurs before or after TCSC) simultaneously. The feasibility of the proposed algorithm has been tested on transmission line with TCSC for 11 types of fault using PSCAD/EMTDC. The result indicates that the ST-LMT method reliably classifies all types of fault and detects fault section with high accuracy on a 300 km, 400 kV TCSC-based transmission line. Copyright (C) 2010 John Wiley & Sons, Ltd.
暂无评论