Automatic speech recognition using optimal selection of features based on hybrid ABC-PSO

This paper describes the work done in improving the performance of Tamil speech recognition system by using Time Scale Modification (TSM) and Vocal Tract Length Normalization (VTLN) techniques. The speech recognition system for Tamil language was developed using a new approach of text independent speech segmentation, with a phoneme based language model for recognition. There is degradation in the performance of speech recognition due to variations in the speaking rate and vocal tract shape among different speakers. In order to improve the performance of speech recognition system, both TSM and VTLN normalization techniques were used in this work. The TSM was implemented using the Phase vocoder approach and the VTLN was implemented using speaker specific bark/mel scale in bark/mel domain. The performance of Tamil speech recognition system was improved by performing both TSM and VTLN normalization techniques.

Feature selection is one of the best optimization problems in human recognition, which reduces the number of features, removes noise and redundant data in images, and results in high rate of recognition. This step affects on the performance of a human recognition system. This paper presents a multimodal biometric verification system based on two features of palm and ear which has emerged as one of the most extensively studied research topics that spans multiple disciplines such as pattern recognition, signal processing and computer vision. Also, we present a novel Feature selection algorithm based on Particle Swarm Optimization (PSO). PSO is a computational paradigm based on the idea of collaborative behavior inspired by the social behavior of bird flocking or fish schooling. In this method, we used from two Feature selection techniques: the Discrete Cosine Transforms (DCT) and the Discrete Wavelet Transform (DWT). The identification process can be divided into the following phases: capturing the image; pre-processing; extracting and normalizing the palm and ear images; feature extraction; matching and fusion; and finally, a decision based on PSO and GA classifiers. The system was tested on a database of 60 people (240 palm and 180 ear images). Experimental results show that the PSO-based feature selection algorithm was found to generate excellent recognition results with the minimal set of selected features.

Combined speech enhancement and auditory modelling for robust distributed speech recognition

Due to increasing risks mainly in surveillance, security, and authentication, it has become imperative to pay more attention to Face Recognition (FR) system. Any FR system consists of three main subdivisions—Feature Extraction, Feature Selection, and Classification. This paper uses a combination of DCT (Discrete Cosine Transform) and PCA (Principal Component Analysis), i.e., DCTPCA for feature extraction followed by Bat and Cuckoo Search Algorithms for Feature Selection. The aim here is to use different classifiers such as Euclidean Distance (ED), Manhattan Distance (MD), Canberra Distance (CD), and Chebyshev Distance (ChD) for classification purpose and to compare them to find as to which, among these, suits best for a given dataset. The results not only reveal the efficiency of Bat-based feature selection algorithm over Cuckoo Search but also show how effective Euclidean Distance classifier is over other classifiers for Yale_Original database and Manhattan Distance classifier for Yale_Extended database.

Feature selection is an important task which can significantly affect the performance of a pattern recognition system. In this paper, we present a feature selection algorithm based on Ant Colony Optimization (ACO) for human activity recognition. The algorithm incorporates the classification performance into the state transition rule, and uses the pheromone of the ant colony to find the optimal feature set, then selects feature set with small size and high classification accuracy. We perform experiments on human activity dataset using four classifiers, Naive Bayes, Random Forest, K-Nearest Neighbor and Support Vector Machine(NB, RF, KNN and SVM). The results show that the proposed method can improve the recognition accuracy, and it is comparable to other feature selection methods.

The performance of the speech recognition system for English classroom teaching is largely affected by the surrounding environment. These interference signals will seriously reduce the quality and intelligibility of the speech signal, thereby greatly reducing the performance of the far-field speech recognition system. Aiming at word order detection in English classroom teaching, this paper proposes an analysis model based on block coding and improved genetic algorithm. Moreover, for DNN-based single-channel speech enhancement algorithms, this paper proposes PDNNs and PLSTMs to solve the problem of serious performance degradation of prototype DNN speech enhancement under low signal-to-noise ratio. This method decomposes the entire enhancement task into multiple subtasks to complete, and the previously completed subtasks will provide prior knowledge for the subsequent subtasks, so that the subsequent subtasks can learn its goals better. In general, the experimental results prove the reliability of the model constructed in this paper.

Irrelevant feature in heart disease dataset affects the performance of binary classification model. Consequently, eliminating irrelevant and redundant feature (s) from training set with feature selection algorithm significantly improves the performance of classification model on heart disease detection. Sequential feature selection (SFS) is successful algorithm to improve the performance of classification model on heart disease detection and reduces the computational time complexity. In this study, sequential feature selection (SFS) algorithm is implemented for improving the classifier performance on heart disease detection by removing irrelevant features and training a model on optimal features. Furthermore, exhaustive and permutation based feature selection algorithm are implemented and compared with SFS algorithm. The implemented and existing feature selection algorithms are evaluated using real world Pima Indian heart disease dataset and result appears to prove that the SFS algorithm outperforms as compared to exhaustive and permutation based feature selection algorithm. Overall, the result looks promising and more effective heart disease detection model is developed with accuracy of 99.3%.

In feature-level fusion recognition system, there are two main missions. One is improving the recognition correct rate as soon as possible; the other is optimizing system sensor design to get outstanding cost performance. So feature selection become usually necessary to reduce dimensionality of the combination of multi-sensor features and improve system performance in system design. In general, the optimization is usually applied to feature selection because of its computational feasibility and validity. For further improving recognition accuracy and reducing selected feature dimensions, this paper presents a more rational and accurate optimization, bidirectional binary particle swarm optimization (BBPSO) algorithm for feature selection in feature level fusion target recognition system. In addition, we introduce a new evaluating function as criterion function in BBPSO feature selection method. At the last, we utilized leave-one-out method to validate the proposed method. The experiment results show that the proposed algorithm improves classification accuracy by two percentage points, while the selected feature dimensions are less one dimension than original particle swarm optimization approach with 16 original feature dimensions.

Speech recognition in noisy environments is one of the long-standing research themes but remains a very important challenge nowadays. Therefore, there is much research into all techniques and approaches to improve the performance of speech recognition systems, even in poor conditions. This paper presents a comparative study under various conditions based on two architectures (GMM-HMM and DNN-HMM), the Hybrid GMM-HMM models using the CMU Sphinx tools and the Hybrid DNN-HMM using the KALDI toolkit in noise environment. In this study, we compare the Hybrid GMM-HMM models and the Hybrid DNN-HMM models to evaluate the performance of the proposed system. The novelty of this paper is to test if the presented tools could be, with good accuracy, recognize the Arabic speech principally in noisy environment. In addition, we adopted the noisy training theory in this paper based on GMM-HMM and DNN-HMM model. We use the public Arabic Speech Corpus for Isolated Words (20 words), three noise levels, and three noise types. The implementation of our system consists of two phases: Features extraction using Mel-frequency Cepstral Coefficient (MFCC) and the classification phase will use separately the previous two models. In order to test the performance of these methods a simulation will presented for different SNR and for different district type of noise.

<p>Classification problems often have a large number of features, but not all of them are useful for classification. Irrelevant and redundant features may even reduce the classification accuracy. Feature selection is a process of selecting a subset of relevant features, which can decrease the dimensionality, shorten the running time, and/or improve the classification accuracy. There are two types of feature selection approaches, i.e. wrapper and filter approaches. Their main difference is that wrappers use a classification algorithm to evaluate the goodness of the features during the feature selection process while filters are independent of any classification algorithm. Feature selection is a difficult task because of feature interactions and the large search space. Existing feature selection methods suffer from different problems, such as stagnation in local optima and high computational cost. Evolutionary computation (EC) techniques are well-known global search algorithms. Particle swarm optimisation (PSO) is an EC technique that is computationally less expensive and can converge faster than other methods. PSO has been successfully applied to many areas, but its potential for feature selection has not been fully investigated. The overall goal of this thesis is to investigate and improve the capability of PSO for feature selection to select a smaller number of features and achieve similar or better classification performance than using all features. This thesis investigates the use of PSO for both wrapper and filter, and for both single objective and multi-objective feature selection, and also investigates the differences between wrappers and filters. This thesis proposes a new PSO based wrapper, single objective feature selection approach by developing new initialisation and updating mechanisms. The results show that by considering the number of features in the initialisation and updating procedures, the new algorithm can improve the classification performance, reduce the number of features and decrease computational time. This thesis develops the first PSO based wrapper multi-objective feature selection approach, which aims to maximise the classification accuracy and simultaneously minimise the number of features. The results show that the proposed multi-objective algorithm can obtain more and better feature subsets than single objective algorithms, and outperform other well-known EC based multi-objective feature selection algorithms. This thesis develops a filter, single objective feature selection approach based on PSO and information theory. Two measures are proposed to evaluate the relevance of the selected features based on each pair of features and a group of features, respectively. The results show that PSO and information based algorithms can successfully address feature selection tasks. The group based method achieves higher classification accuracies, but the pair based method is faster and selects smaller feature subsets. This thesis proposes the first PSO based multi-objective filter feature selection approach using information based measures. This work is also the first work using other two well-known multi-objective EC algorithms in filter feature selection, which are also used to compare the performance of the PSO based approach. The results show that the PSO based multiobjective filter approach can successfully address feature selection problems, outperform single objective filter algorithms and achieve better classification performance than other multi-objective algorithms. This thesis investigates the difference between wrapper and filter approaches in terms of the classification performance and computational time, and also examines the generality of wrappers. The results show that wrappers generally achieve better or similar classification performance than filters, but do not always need longer computational time than filters. The results also show that wrappers built with simple classification algorithms can be general to other classification algorithms.</p>

Cardiovascular Disease (CVD) is one of the primary diseases that causes death every year. An approximation of roughly about 17.5 million people dies due to CVD, signifying about 31% of global deaths. Based on the statistics, every 34 seconds, a person dies due to heart disease. Various classification algorithms have been developed and utilized as classifiers to support doctors who are ineffectually diagnosed with heart disease. The main aim of this work is to improve the performance of the heart disease approach using image processing algorithm. To improve the effectiveness and efficiency of classification performance for heart disease diagnosis, an optimized neural network was proposed based on the feature extraction and selection approach for handling features. The objective of this investigation is to diagnose heart diseases using feature extraction, reduction based classification and image processing methods. The proposed model comprises of two subsets: Feature extraction using gray scale properties and Moth flame optimization (MFO) for effectual feature selection, followed by a classification technique using Generalized Regression Neural Network. The first system includes three stages: (i) Pre-processing of the dataset (ii) feature extraction (iii) performing MFO for efficient selection. In the second method, GRNN is proposed. The heart data set obtained from ACDC Challenge, was utilized for performing the computation. The image obtained from the MRI-scanner is in the NIfTI image format. The pre-process step used in this is to convert the image type from INT16 to uint8 to improve the quality of image viewing and for feature extraction process. In this phase, the texture properties from the pre-processed image are calculated and the value is in the numeric format. These values are the feature attributes of the dataset. The feature attributes of the image are given as input for the moth flame optimization process and output is the feature selected from the optimization process. The whole process is performed on the feature attributes of the image by determining the optimal feature for the classifier by reducing its error rate. The optimal feature from the moth flame optimization is used for training and testing the network. The classifier used in this approach is a single neural network classifier with a regression nature. Due to the regression property, the network is well trained with the feature. The Generalized regression neural network is used for classifying heart diseases. The proposed method achieves the accuracy of 96.23%, sensitivity of 95.41% and specificity of 96.75%. These values are calculated based on the confusion matrix of the classifier. In this, the feature extraction using the gray scale properties plays an important role to determine the feature attributes from the MRI heart images. The Moth flame optimization able to produce an accuracy of 97.23% using GRNN for classification with minimum single attribute mean of the image. It also outperformed the other methods, either the feature extraction based classification or the feature reduction based classification.

Texture and its analysis methods are crucial for image feature extraction and classification. Digital elevation model (DEM) is the most important data source of digital terrain analysis and landform classification, and considerable research values are gained from texture feature extraction and analysis from DEM data. In this research, on the basis of optimal texture feature extraction, the hilly area in Shandong, China, was selected as the study area, and DEM data with a resolution of 500 m were used as the experimental data for landform classification. First, second-order texture measures and texture image were extracted from DEM data by using a gray level cooccurrence matrix (GLCM). Second, the variation characteristics of each texture measure were analyzed, and the optimal feature parameters, such as direction, gray level, and texture window, were determined. Meanwhile, the texture feature value, combined with maximum information, was calculated, and the multiband texture image was obtained by resolving three optimal texture measure images. Finally, a support vector machine (SVM) method was adopted to classify landforms on the basis of the multiband texture image. Results indicated that the texture features of DEM data can be sufficiently represented and measured via the quantitative GLCM method. However, the feature parameters during the texture feature value calculation required further optimization. Based on the image texture from DEM data, efficient classification accuracy and ideal classification effect were achieved.

Diabetes Mellitus (DM) is a global health challenge, and accurate early detection is critical for effective management. The study explores the potential of machine learning for improved diabetes prediction using microarray gene expression data and PIMA data set. Researchers utilizing a hybrid feature extraction method such as Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO) followed by metaheuristic feature selection algorithms as Harmonic Search (HS), Dragonfly Algorithm (DFA), Elephant Herding Algorithm (EHA). Evaluated the performance of a system by using the following classifiers as Non-Linear Regression—NLR, Linear Regression—LR, Gaussian Mixture Model—GMM, Expectation Maximization—EM, Bayesian Linear Discriminant Analysis—BLDA, Softmax Discriminant Classifier—SDC, and Support Vector Machine with Radial Basis Function kernel—SVM-RBF classifier on two publicly available datasets namely the Nordic Islet Transplant Program (NITP) and the PIMA Indian Diabetes Dataset (PIDD). The findings demonstrate significant improvement in classification accuracy compared to using all genes. On the Nordic islet transplant dataset, the combined ABC-PSO feature extraction with EHO feature selection achieved the highest accuracy of 97.14%, surpassing the 94.28% accuracy obtained with ABC alone and EHO selection. Similarly, on the PIMA Indian diabetes dataset, the ABC-PSO and EHO combination achieved the best accuracy of 98.13%, exceeding the 95.45% accuracy with ABC and DFA selection. These results highlight the effectiveness of our proposed approach in identifying the most informative features for accurate diabetes prediction. It is observed that the parametric values attained for the datasets are almost similar. Therefore, this research indicates the robustness of the FE and FS along with classifier techniques with two different datasets.

<p>Classification aims to identify a class label of an instance according to the information from its characteristics or features. Unfortunately, many classification problems have a large feature set containing irrelevant and redundant features, which reduce the classification performance. In order to address the above problem, feature selection is proposed to select a small subset of relevant features. There are three main types of feature selection methods, i.e. wrapper, embedded and filter approaches. Wrappers use a classification algorithm to evaluate candidate feature subsets. In embedded approaches, the selection process is embedded in the training process of a classification algorithm. Different from the other two approaches, filters do not involve any classification algorithm during the selection process. Feature selection is an important process but it is not an easy task due to its large search space and complex feature interactions. Because of the potential global search ability, Evolutionary Computation (EC), especially Particle Swarm Optimization (PSO), has been widely and successfully applied to feature selection. However, there is potential to improve the effectiveness and efficiency of EC-based feature selection. The overall goal of this thesis is to investigate and improve the capability of EC for feature selection to select small feature subsets while maintaining or even improving the classification performance compared to using all features. Different aspects of feature selection are considered in this thesis such as the number of objectives (single-objective/multi-objective), the fitness function (filter/wrapper), and the searching mechanism. This thesis introduces a new fitness function based on mutual information which is calculated by an estimation approach instead of the traditional counting approach. Results show that the estimation approach works well on both continuous and discrete data. More importantly, mutual information calculated by the estimation approach can capture feature interactions better than the traditional counting approach. This thesis develops a novel binary PSO algorithm, which is the first work to redefine some core concepts of PSO such as velocity and momentum to suit the characteristics of binary search spaces. Experimental results show that the proposed binary PSO algorithm evolve better solutions than other binary EC algorithms when the search spaces are large and complex. Specifically, on feature selection, the proposed binary PSO algorithm can select smaller feature subsets with similar or better classification accuracies, especially when there are a large number of features. This thesis proposes surrogate models for wrapper-based feature selection. The surrogate models use surrogate training sets which are subsets of informative instances selected from the training set. Experimental results show that the proposed surrogate models assist PSO to reduce the computational cost while maintaining or even improving the classification performance compared to using only the original training set. The thesis develops the first wrapper-based multi-objective feature selection algorithm using MOEA/D. A new decomposition strategy using multiple reference points for MOEA/D is designed, which can deal with different characteristics of multi-objective feature selection such as highly discontinuous Pareto fronts and complex relationships between objectives. The experimental results show that the proposed algorithm can evolve more diverse non-dominated sets than other multi-objective algorithms. This thesis introduces the first PSO-based feature selection algorithm for transfer learning. In the proposed algorithm, the fitness function uses classification performance to reduce the differences between domains while maintaining the discriminative ability on the target domain. The experimental results show that the proposed algorithm can select feature subsets which achieve better classification performance than four state-of-the-art feature-based transfer learning algorithms.</p>

An improved feature selection approach using global best guided Gaussian artificial bee colony for EMG classification