Showing papers by "Goutam Saha published in 2017"

Recurrent neural network-based modeling of gene regulatory network using elephant swarm water search algorithm

Abstract: Correct inference of genetic regulations inside a cell from the biological database like time series microarray data is one of the greatest challenges in post genomic era for biologists and researchers. Recurrent Neural Network (RNN) is one of the most popular and simple approach to model the dynamics as well as to infer correct dependencies among genes. Inspired by the behavior of social elephants, we propose a new metaheuristic namely Elephant Swarm Water Search Algorithm (ESWSA) to infer Gene Regulatory Network (GRN). This algorithm is mainly based on the water search strategy of intelligent and social elephants during drought, utilizing the different types of communication techniques. Initially, the algorithm is tested against benchmark small and medium scale artificial genetic networks without and with presence of different noise levels and the efficiency was observed in term of parametric error, minimum fitness value, execution time, accuracy of prediction of true regulation, etc. Next, the proposed algorithm is tested against the real time gene expression data of Escherichia Coli SOS Network and results were also compared with others state of the art optimization methods. The experimental results suggest that ESWSA is very efficient for GRN inference problem and performs better than other methods in many ways.

Lung sound classification using local binary pattern

Abstract: Lung sounds contain vital information about pulmonary pathology. In this paper, we use short-term spectral characteristics of lung sounds to recognize associated diseases. Motivated by the success of auditory perception based techniques in speech signal classification, we represent time-frequency information of lung sounds using mel-scale warped spectral coefficients, called here as mel-frequency spectral coefficients (MFSCs). Next, we employ local binary pattern analysis (LBP) to capture texture information of the MFSCs, and the feature vectors are subsequently derived using histogram representation. The proposed features are used with three well-known classifiers in this field: k-nearest neighbor (kNN), artificial neural network (ANN), and support vector machine (SVM). Also, the performance was tested with multiple SVM kernels. We conduct extensive performance evaluation experiments using two databases which include normal and adventitious sounds. Results show that the proposed features with SVM and also with kNN classifier outperform commonly used wavelet-based features as well as our previously investigated mel-frequency cepstral coefficients (MFCCs) based statistical features, specifically in abnormal sound detection. Proposed features also yield better results than morphological features and energy features computed from rational dilation wavelet coefficients. The Bhattacharyya kernel performs considerably better than other kernels. Further, we optimize the configuration of the proposed feature extraction algorithm. Finally, we have applied mRMR (minimum-redundancy maximum-relevancy) based feature selection method to remove redundancy in the feature vector which makes the proposed method computationally more efficient without any degradation in the performance. The overall performance gain is up to 24.5% as compared to the standard wavelet feature based system.

Recurrent Neural Network Based Modeling of Gene Regulatory Network Using Bat Algorithm

Abstract: Correct inference of genetic regulations inside a cell is one of the greatest challenges in post genomic era for the biologist and researchers. Several intelligent techniques and models were already proposed to identify the regulatory relations among genes from the biological database like time series microarray data. Recurrent Neural Network (RNN) is one of the most popular and simple approach to model the dynamics as well as to infer correct dependencies among genes. In this paper, Bat Algorithm (BA) is applied to optimize the model parameters of RNN model of Gene Regulatory Network (GRN). Initially the proposed method is tested against small artificial network without any noise and the efficiency is observed in term of number of iteration, number of population and BA optimization parameters. The model is also validated in presence of different level of random noise for the small artificial network and that proved its ability to infer the correct inferences in presence of noise like real world dataset. In the next phase of this research, BA based RNN is applied to real world benchmark time series microarray dataset of E. coli. The results prove that it can able to identify the maximum number of true positive regulation but also include some false positive regulations. Therefore, BA is very suitable for identifying biological plausible GRN with the help RNN model.

Identification of Coronary Artery Disease using Cross Power Spectral Density

Abstract: Heart sounds provide important information about cardiac status either through auscultation or by processing of electronic recordings of heart sounds, termed as phonocardiogram (PCG). The current study analyzes the relation between PCG signal from four auscultation sites for diagnosis of coronary artery disease (CAD). For this purpose, data collected from four locations on chest is analysed using cross power spectral density (CPSD). The features from spectrum are derived using distribution of power and their moments in subbands. ReliefF algorithm is employed for selecting features to be used in classification framework. Performance is evaluated using five-fold cross-validation in a support vector machine (SVM) classifier. Experimental results show that multichannel analysis performs better than existing features, as well as for same CPSD based features derived from single channel power spectrum. Different subband width were experimentally analysed to find an optimal width for feature extraction. The study shows the potential of using connectivity between PCG signals from multiple sites for diagnosing CAD related abnormality.

Spectral Mapping Using Prior Re-Estimation of i-Vectors and System Fusion for Voice Conversion

Abstract: In this paper, we propose a new voice conversion (VC) method using i-vectors which consider low-dimensional representation of speech utterances. An attempt is made to restrict the i-vector variability in the intermediate computation of total variability ( $\mathbf {T}$ ) matrix by using a novel approach that uses modified-prior distribution of the intermediate i-vectors. This $\mathbf {T}$ -modification improves the speaker individuality conversion. For further improvement of conversion score and to keep a better balance between similarity and quality, band-wise spectrogram fusion between conventional joint density Gaussian mixture model (JDGMM) and i-vector based converted spectrograms is employed. The fused spectrogram retains more spectral details and leverages the complementary merits of each subsystem. Experiments in terms of objective and subjective evaluation are conducted extensively on CMU ARCTIC database. The results show that the proposed technique can produce a better trade-off between similarity and quality score than other state-of-the-art baseline VC methods. Furthermore, it works better than JDGMM in limited VC training data. The proposed VC performs moderately better (both objective and subjective) than mixture of factor analyzer based baseline VC. In addition, the proposed VC provides better quality converted speech as compared to maximum likelihood-GMM VC with dynamic feature constraint.

A Machine Learning Approach to Decode Mental States in Bistable Perception

Abstract: This work demonstrates the usefulness of machine learning framework in decoding mental states from recorded brain signals. Magnetoencephalogram (MEG) signals were recorded from human participants while they were presented with six different conditions of bistable stimuli. Two internal mental states, transition and maintenance, which are related to switching or maintaining a perception in bistable perception respectively, were decoded. We extracted two types of features using complex Morlet wavelet transform that capture the spatio-temporal dynamics of large scale brain oscillations at global and local scale. Principal component analysis (PCA) was employed to reduce the dimension of the feature vector as well to minimize the redundancy among the features. Support vector machine (SVM) and artificial neural network (ANN) based classifiers were used to predict the mental states on a trial-by-trial basis. We were able to decode the two mental states from pooled data of all six conditions with accuracies of 79.52% and 79.56% using SVM and ANN classifier, respectively from local features which performed better than global features. The results show the effectiveness of signal processing and machine learning based approaches to identify internal mental states.

Quantum Computing Based Inference of GRNs

Abstract: The accurate reconstruction of gene regulatory networks from temporal gene expression data is crucial for the identification of genetic inter-regulations at the cellular level. This will help us to comprehend the working of living entities properly. Here, we have proposed a novel quantum computing based technique for the reverse engineering of gene regulatory networks from time-series genetic expression datasets. The dynamics of the temporal expression profiles have been modelled using the recurrent neural network formalism. The corresponding training of model parameters has been realised with the help of the proposed quantum computing methodology based concepts. This is based on entanglement and decoherence concepts. The application of quantum computing technique in this domain of research is comparatively new. The results obtained using this technique is highly satisfactory. We have applied it to a 4-gene artificial genetic network model, which was previously studied by other researchers. Also, a 10-gene and a 20-gene genetic network have been studied using the proposed technique. The obtained results suggest that quantum computing technique significantly reduces the computational time, retaining the accuracy of the inferred gene regulatory networks to a comparatively satisfactory level.

A novel spectrogram based approach towards automatic lung sound cycle extraction

Abstract: Automatic lung sound cycle extraction is the pivotal step for automated lung status detection as well as in monitoring the chronic lung diseases. In recent works, an attempt has been made to get rid of the additional airflow sensors due to their inaccuracy, patient's discomfort, and extra cost. In this paper, we have proposed a novel signal processing based approach to automatically extract lung sound cycles. In this framework, spectrograms are used as images to get the trend of the lung sound cycles without the need for identifying the corresponding respiratory phases or use of any reference airflow signal. We have utilized the lung sounds recorded from 8 healthy and 24 diseased subjects (8 subjects each from Asthma, COPD, and DPLD) to develop and evaluate the proposed lung sound cycle extraction algorithm. We employ a 4-fold cross-validation in our study and the average accuracy of 98.62% is found.