S I Khan
@sreenidhi.edu.in
Associate Professor in Electronics and Communications Engineering
Sreenidhi Institute of Science and Technology
EDUCATION
PhD Electronics and communication Engineering
RESEARCH, TEACHING, or OTHER INTERESTS
Human-Computer Interaction, Multidisciplinary, Biomedical Engineering, Artificial Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Sibghatullah Inayatullah Khan and Ram Bilas Pachori
Institute of Electrical and Electronics Engineers (IEEE)
The accurate automated eye movement classification is gaining importance in the field of human–computer interaction (HCI). The present article aims at the classification of six types of eye movements from electromyogram (EMG) of extraocular muscles (EOM) signals using the Fourier–Bessel series expansion-based empirical wavelet transform (FBSE-EWT) with time and frequency-domain (TAFD) features. The FBSE-EWT of EMG signals results in Fourier–Bessel intrinsic mode functions (FBIMFs), which correspond to the frequency contents in the signal. A hybrid approach is used to select the prominent FBIMFs followed by the statistical and signal complexity-based feature extraction. Furthermore, metaheuristic optimization algorithms are employed to reduce the feature space dimension. The discrimination ability of the reduced feature set is verified by Kruskal–Wallis statistical test. Multiclass support vector machine (MSVM) has been employed for classification. First, the classification has been performed with TAFD features followed by the combination of TAFD and FBSE-EWT-based reduced feature set. The combination of TAFD and FBSE-EWT-based feature set has provided good classification performance. This study demonstrates the efficacy of FBSE-EWT and subsequent metaheuristic feature selection algorithms in classifying the eye movements from EMG of EOM signals. The combination of TAFD and the selected features through salp swarm optimization algorithm has provided maximum classification accuracy of 98.91% with MSVM employing Gaussian and radial basis function kernels. Thus, the proposed approach has the potential to be used in HCI applications involving biomedical signals.
Sibghatullah I. Khan, Saeed Mian Qaisar, Alberto López, Humaira Nisar, and Francisco Ferrero
IEEE
Schizophrenia is a mental illness that can negatively impact a patient's mental abilities, emotional propensities, and the standard of their private and social lives. Processing EEG data has evolved into a useful tool for tracking and identifying psychological brain states. In this framework, this paper focus on developing an automated approach for recognizing schizophrenia using non-invasive EEG signals. The EEG signals are segmented and onward decomposed by using the Variational Mode Decomposition (VMD). Each mode is termed a variational mode function (VMF). Onward, features from each intended VMF are mined based on a Rose Spiral Curve (RSC). The mined features are concatenated to present an instance. Afterward, the most pertinent features are selected using the Butterfly Optimization Algorithm (BOA). The selected feature set is conveyed to the classification module. Two classification approaches are applied in this study namely, the k-nearest neighbor (k-NN) and Random Forest (RF). The applicability is tested by using a publicly available EEG schizophrenia dataset. The highest accuracy of 89.0 % is secured for the case of RF.
Manal Asrar, Joud Bawazir, Sibghatullah I. Khan, and Saeed Mian Qaisar
IEEE
This paper aims to make use of The Physionet Challenge 2016 collection of normal and abnormal heart sound recordings that were classified by automated identification of PCG sounds to help detect heart diseases earlier and prevent incidents. People with heart diseases have been increasing and most of them lead to fatalities so the detection of sound signals through PCGs can be applied in machine learning models by extracting features from data. In this study, the dataset's recordings are segmented to be used in variational mode decomposition. Once they are decomposed, those means will be fused together into a set of features given to the Butterfly Optimization Algorithm which will conduct a selection of features. As the features are selected, MATLAB was used to test various machine learning algorithms. Results from Support Vector Machines (SVM) and artificial neural networks were used in this investigation (ANN). The ANN model, which had an accuracy rate of 94.8%, was the most accurate of them.
Sibghatullah I. Khan and Ram Bilas Pachori
IGI Global
In the chapter, a novel yet simple method for classifying EEG signals associated with normal and epileptic seizure categories has been proposed. The proposed method is based on empirical wavelet transform (EWT). The non-stationarity in the EEG signal has been captured using EWT, and subsequently, the common minimum number of modes have been determined for each EEG signal. Features based on amplitude envelopes of EEG signals have been computed. The Kruskal-Wallis statistical test has been used to confirm the discrimination ability of feature space. For classification, various classifiers, namely K-nearest neighbor (KNN), support vector machine (SVM), and decision tree (DT), have been used. The maximum classification accuracy of 98.67% is achieved with the K-nearest neighbor (KNN) classifier. The proposed approach has utilized only two features, which makes the proposed approach simpler. The proposed approach thus can be used in real-time applications.
Saeed Mian Qaisar, Sibghatullah I. Khan, Dominique Dallet, Ryszard Tadeusiewicz, and Paweł Pławiak
Elsevier BV
Sibghatullah I. Khan, Saeed Mian Qaisar, and Ram Bilas Pachori
Elsevier BV
Sibghatullah I. Khan, Shruti Bhargava Choubey, Abhishek Choubey, Abhishek Bhatt, Pandya Vyomal Naishadhkumar, and Mohammed Mahaboob Basha
SAGE Publications
Glaucoma is a domineering and irretrievable neurodegenerative eye disease produced by the optical nerve head owed to extended intra-ocular stress inside the eye. Recognition of glaucoma is an essential job for ophthalmologists. In this paper, we propose a methodology to classify fundus images into normal and glaucoma categories. The proposed approach makes use of image denoising of digital fundus images by utilizing a non-Gaussian bivariate probability distribution function to model the statistics of wavelet coefficients of glaucoma images. The traditional image features were extracted followed by the popular feature selection algorithm. The selected features are then fed to the least square support vector machine classifier employing various kernel functions. The comparison result shows that the proposed approach offers maximum classification accuracy of nearly 91.22% over the existing best approaches.
Sibghatullah I. Khan and Ram Bilas Pachori
Elsevier BV
Sibghatullah I. Khan and Ram Bilas Pachori
Elsevier BV
Sibghatullah I. Khan, Ganjikunta Ganesh Kumar, Pandya Vyomal Naishadkumar, and Sarvade Pedda Subba Rao
International Information and Engineering Technology Association
Diagnosing chronic obstructive pulmonary disease (COPD) from lung sounds is time consuming, onerous, and subjective to the expertise of pulmonologists. The preliminary diagnosis of COPD is often based on adventitious lung sounds (ALS). This paper proposes to objectively analyze the lung sound signals associated with COPD. Specifically, empirical mode decomposition (EMD), a data adaptive signal decomposition technique suitable for analyzing non-stationary signals, was adopted to decompose non-stationary lung sound signals. The use of EMD on lung sound signal results in intrinsic mode functions (IMFs), which are symmetric and band limited. The analytic IMFs were then computed through the Hilbert transform, which reveals the instantaneous frequency content of each IMF. The Hilbert transformed signal is analytic, and has a complex representation containing real and imaginary parts. Next, the central tendency measure (CTM) was introduced to quantify the circular shape of the analytical IMF plot. The result was taken as a useful feature to distinguish normal lung sound signal with ALS. Simulation results show that the CTM of analytic IMFs has a strong ability to distinguish between normal lung sound signals and ALS.
Sibghatullah I. Khan and Ram Bilas Pachori
Institute of Electrical and Electronics Engineers (IEEE)
Posterior myocardial infarction (PMI) is a fatal condition of the human heart, wherein the posterior coronary circulation becomes disrupted. If left untreated, the PMI can cause a severe heart attack. To detect PMI, the conventional 12-lead standard electrocardiogram signals demonstrate poor detection sensitivity due to the absence of posterior sensing electrodes. Contrastingly, the three lead vectorcardiogram (VCG) signal has the sensor electrodes placed on the posterior side, thereby improving the reliability of PMI diagnosis. In this letter, we use VCG signals for the classification of PMI and healthy control (HC) subjects. The abnormalities in the electrical conduction due to PMI are captured using Fourier–Bessel series expansion based empirical wavelet transform, followed by the singular value decomposition (SVD). The resultant feature space is then utilized to classify PMI and HC segments using a support vector machine (SVM) classifier with various kernels, namely, linear, Gaussian, and radial basis function (RBF). The SVM with RBF kernel has resulted in the maximum classification accuracy, sensitivity, and specificity of 95.52, 91.08, and 97.45%, respectively, over the Physikalisch-Technische Bundesanstalt diagnostic database. Thus, the proposed method has the potential to be used in the clinical setting for accurate and robust PMI detection.
M. Mahaboob Basha, Srinivasulu Gundala, and Sibghatullah I. Khan
Inderscience Publishers
Sibghatullah Khan*, , Syed Jahangir Badashah, Mallikarjun Mudda, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
The investigations from recent studies clearly show the potential of lung sounds in detection of lung abnormalities in human subjects. This paper aims to analyze lung sounds acquired using special electronic stethoscope for detection adventitious sounds arising out of pathological lungs due to various disease like brochities especially in pediatric population. For acquisition and recording of lung sounds, 3M Littmann 3200 model is utilized. After verifying fidelity of electronic stethoscope, the analysis of lung sounds was carried out by various spectral and temporal features. The features extracted were fed to artificial neural network for classification. Various combinations of ANN with different topologies were experimented. The overall accuracy of obtained with one hidden layer GFF is 94.95%.
Ganesh Kumar G and
The World Academy of Research in Science and Engineering
This paper proposes four-parallel pipelined fast Fourier transform (FFT) architecture for the discrete Fourier transform (DFT) computation of quadrature-phase-shift-keying Orthogonal Frequency Division Multiplexing (QPSK-OFDM) signals. The first stage of the architecture is optimized with the multiplexer blocks that contain output values of QPSK as inputs. Furthermore, the proposed architecture employs a complex constant multipliers (CCMs) using adders and shifters that can reduce the total hardware of the design. The proposed 64-point pipeline architecture is modeled and implemented using UMC 65 nm CMOS technology with a supply voltage of 1.2 V. The results demonstrate that the proposed FFT architecture significantly reduces the hardware cost and power consumption in comparison to the recent FFT architecture.
Ganesh Kumar Ganjikunta, Sibghatullah I. Khan, and M. Mahaboob Basha
American Scientific Publishers
A high speed N × N bit multiplier architecture that supports signed and unsigned multiplication operations is proposed in this paper. This architecture incorporates the modified two's complement circuits and also N × N bit unsigned multiplier circuit. This unsigned multiplier circuit is based on decomposing the multiplier circuit into smaller-precision independent multipliers using Vedic Mathematics. These individual multipliers generate the partial products in parallel for high speed operation, which are combined by using high speed adders and parallel adder to generate the product output. The proposed architecture has regular-shape for the partial product tree that makes easy to implement. Finally, this multiplier architecture is implemented in UMC 65 nm technology for N = 8, 16 and 32 bits. The synthesis results shows that the proposed multiplier architecture improves in terms of speed and also reduces power-delay product (PDP), compared to the architectures in the literature.
Muzammil M. Ahmad and Sibghatullah I. Khan
IEEE
Authentication and key exchange securely over the insecure channel is a big deal these days. It plays vital role in big data applications. Mutual authentication is generally relay at the single channel between two users. An attacker performs the passive attack (traffic analysis) and switch towards the active attack Three tier authentication system checks the authenticity of the client at three independent channels and if found secure then only allow the client to get the services from the application server. Two intermediate servers will provide two-split passwords and the application server will provide the complete password. These intermediate servers will forward the split password towards the main application server which compares and finds the similarities between them. Whole communication is based on public key cryptography to achieve mutual authentication, confidentiality and integrity of the message.
Sibghatullah I. Khan, Vasif Ahmed, and Naresh P. Jawarkar
IEEE
Early detection of adventitious lung sounds in pediatric population is of prime importance as untreated respiratory disorders can become chronic and non-curable in adulthood. This study deals with application of signal processing methods to preliminary classify normal and adventitious lung sounds of children using electronic stethoscope. Short time Fourier transform based features were extracted and consequently singular value decomposition for feature reduction has been utilized. Performance of k-NN and SVM has been compared for classification. Classifier based on SVM turns out to provide maximum classification accuracy. The sensitivity, specificity and accuracy of the proposed method is 92.20%.
Sibghatullah I. Khan and Vasif Ahmed
IEEE
Recent research shows that the diastolic part of cardiac cycle contains very weak murmurs caused by turbulent flow in the coronary artery diseases. This paper deals with the use of electronic stethoscope for the preliminary detection of coronary artery diseases (CAD). 3M Littmann 3200 model is used for recording of cardiac sounds of CAD and non CAD category. Cardiac sounds were analyzed in both time and frequency domain. Six features including two time domain and four frequency domain were extracted from each sound. Out of these features two frequency domain features namely spectral centroid and spectral roll off were identified as the potential features for discriminating CAD and non CAD sounds.
Sibghatullah I. Khan and Vasif Ahmed
IEEE
Pulmonary crackles and plural friction rubs are adventitious lung sounds that provide valuable information on underlying lung diseases. Due to similarities in their time domain characteristics, there exists the need to distinguish these two sounds to help novice medical doctors and to aid in automated diagnosis in telemedicine applications. This paper focuses on analyzing these two sounds using Mel Frequency Cepstral Coefficients (MFCC) speech analysis technique. The MFCC's were calculated for crackles and pleural friction rub lung sound and four basic statistical parameters of MFCC were calculated. The Standard deviation of MFCC shows maximum linear separability among other parameters. Therefore, the standard deviation of MFCC can be used as potential feature for classifying adventitious lung sounds pertaining to pulmonary crackles and pleural friction rubs.
Sibghatullah I. Khan and Vasif Ahmed
IEEE
Recent studies show that in the case of coronary artery disease (CAD) patients, the diastolic part of cardiac cycle contains very weak murmurs caused by turbulent flow in the narrowed coronary arteries. This paper aims to analyze the diastolic period of heart sounds recorded with electronic stethoscope for detection of coronary artery disease. 3M Littmann 3200 model is used for recording of heart sounds of CAD and non CAD category. Cardiac sounds were analyzed with spectral and spectro-temporal features. Thirteen features including three spectral and ten spectro-temporal were extracted from each sound. Spectral features used for the study were spectral centroid, spectral roll off and spectral flatness. Spectro-temporal features include Stockwell transform with band wise kurtosis. It is observed that along with Spectral features, spectro-temporal feature provides significant discrimination between CAD and non-CAD heart sounds with sensitivity of 98.18% and specificity of 93.10%.
Sibghatullah I. Khan and Vasif Ahmed
Springer Nature Singapore
Sibghatullah I. Khan, Naresh P. Jawarkar, and Vasif Ahmed
IEEE
This work embodies the development of simple and robust technique for early detection of respiratory disorders in the children living in the rural areas of resource poor countries like India by acquisition of the lung sound recorded by cell phone based modified stethoscope by local health worker. The recorded file is transmitted along with case history to email address of health care center volunteer. The analysis of received lung sound file is done at health care centre. The analysis involves extraction of Mel frequency cepstral coefficients of lung sound. The coefficients and their statistical parameters are passed on to neural network for detection. The network was tested for 40 subjects containing equal mix of normal and bronchitis cases. The method detects the disease with an accuracy of 90% and with specificity of 95%. The overall accuracy of this method is 92.5%. The report (lung sound, analysis results and case history) is checked by medical practitioner at health-care centre on daily basis and necessary subscription is sent to designated rural local health care worker. Samsung cell phone model Galaxy Y was used for implementation. This work has great significance for evolving solutions towards rural health care of undeveloped and developing countries.