Browsing by Author "Rahman, Md. Asadur"

Now showing 1 - 7 of 7

A Simple Design of a Matlab-Based Function for Topographical Presentation of FNIRS Data.
() Proceedings of the 6th International Conference on Electrical, Control and Computer Engineering. Lecture Notes in Electrical Engineering, vol 842. Springer, Singapore. https://doi.org/10.1007/978-981-16-8690-0_46, 2022-01-02) Ferdous, Talukdar Raian; Hasan, Rifath; Alam, Mohammad Khurshed; Islam, Muhammad Muinul; Rahman, Md. Asadur
Functional Near-Infrared Spectroscopy (fNIRS) has aggrandized the domain of Neurophotonics and Imaging research to reach its apex. With enhanced spatial resolution with the pre-existing temporal resolution, fNIRS can be more promising for the functional analysis of the brain. Hardware integrated software for fNIRS analysis is affluent as well as limited for users. The analysis based on MATLAB is done with the Graphical User Interface (GUI) that are difficult to use because they involve numerous steps, coefficients, and related files. This is a simple MATLAB-based study that includes the generation of the brain activation patterns based on oxygenation and de-oxygenation of hemoglobin and enhancing spatial resolution for the better identification of brain functionality. Brain activation pattern based on the recorded fNIRS data is created in the form of a color-coded map. The map is registered to the brain surface image which provides better visuality of the activation scheme of the brain with an anatomical view. This research intends to encourage prolific researchers in this research area to conduct simplified and cost-effective analyses of the fNIRS study.
Common Spatial Pattern in Frequency Domain for Feature Extraction and Classification of Multichannel EEG Signals
(SN Computer Science (2021) 2:149, 2021-03-19) Saha, Pritom Kumar; Rahman, Md. Asadur; Alam, Mohammad Khurshed; Ferdowsi, Asma; Mollah, Md. Nurunnabi
The extraction methodology of the significant features from the signals is one of the most important pre-requisite steps for EEG signal classification. Common spatial pattern (CSP) is a widely used feature extraction method for EEG signal but with a lacking of failing to maintain discriminative features between classes in the time domain, and further as a consequence, ends up in inconvenience with erroneous output. To overcome the limitations of the convention CSP, this research work proposes a novel frequency domain CSP (FCSP) method for feature extraction. This method proposes to convert the time domain EEG signal to its power spectral density (PSD) so that the event-related variation can be found in the frequency domain. After that,the CSP method is applied to the PSD values of the selected channels to extract the variation based on the spatial pattern of the channels for the events. The output of this method helps to extract simple features from the FCSP-PSD data for the classification. The proposed method is applied to motor imagery data from BCI competition IV. To check the applicability of the proposed method, a complex environment was created considering the same lobe events such as combined left and right feet (Class#1) versus right-hand (Class#2) imagery movement. To compare the performance of the proposed work, the method is also applied to the conventional classification problem (left-hand vs right-hand imagery movement) and found very promising results of 91% accuracy on average.
EEG based Brain Alertness Monitoring by Statistical and Artificial Neural Network Approach
(International Journal of Advanced Computer Science and Applications, 2019) Rahman, Md. Asadur; Rashid, Md. Mamun or; Khanam, Farzana; Alam, Mohammad Khurshed; Ahmad, Mohiuddin
Since several work requires continuous alertness like efficient driving, learning, etc. efficient measurement of the alertness states through neural activity is a crucial challenge for the researchers. This work reports a practical method to investigate the alertness state from electroencephalography (EEG) of the human brain. Here, we have proposed a novel idea to monitor the brain alertness from EEG signal that can discriminate the alertness state comparing resting state with a simple statistical threshold. We have investigated two different types of mental tasks: alphabet counting & virtual driving to monitor their alertness level. The EEG signals are acquired from several participants regarding alphabet counting and virtual motor driving tasks. A 9-channel wireless EEG system has been used to acquire their EEG signals from frontal, central, and parietal lobe of the brain. With suitable preprocessing, signal dimensions are reduced by principal component analysis and the features of the signals are extracted by the discrete wavelet transformation method. Using the features, alertness states are classified using the artificial neural network. Additionally, the relative power of responsible frequency band to alertness is analyzed with statistical inference. We have found that the beta relative power increases at a significant level due to alertness which is good enough to differentiate the alertness state from the control state. It is also found that the increment of beta relative power for virtual driving is much greater than the alphabet counting mental alertness. We hope that this work will be very helpful to monitor constant alertness for efficient driving and learning.
Four-Class Motor Imagery EEG Signal Classification using PCA, Wavelet and Two-Stage Neural Network
(International Journal of Advanced Computer Science and Applications, 2019-01-01) Rahman, Md. Asadur; Khanam, Farzana; Hossain, Md. Kazem Hossain; Alam, Mohammad Khurshed; Ahmad, Mohiuddin
Electroencephalogram (EEG) is the most significant signal for brain-computer interfaces (BCI). Nowadays, motor imagery (MI) movement based BCI is highly accepted method for. This paper proposes a novel method based on the combined utilization of principal component analysis (PCA), wavelet packet transformation (WPT), and two-stage machine learning algorithm to classify four-class MI EEG signal. This work includes four-class MI events by an imaginary lifting of the left hand, right hand, left foot, and Right Foot. The main challenge of this work is to discriminate the similar lobe EEG signal pattern such as left foot VS left hand. Another critical problem is to identify the MI movements of two different feet because their activation level is very low and show an almost similar pattern. This work firstly uses the PCA to reduce the signal dimensions of the left and right lobe of the brain. Then, WPT is used to extract the feature from the different class EEG signal. Finally, the artificial neural network is trained into two stages – 1st stage identifies the lobe from the signal pattern and the 2nd stage identifies whether the signal is of MI hand or MI foot movement. The proposed method is applied to the 4-class MI movement related EEG signals of 15 participants and found excellent classification accuracy (>74% on average). The outcomes of the proposed method prove its effectiveness in practical BCI implementation.
Investigating music algorithm in neural information processing: robust feature extraction for emotional state classification from multichannel EEG signals
(BRAC University, 2021-08) Hossain, Md. Sakib Abrar; Chakrabarty, Amitabha; Rahman, Md. Asadur
The major challenge in any electroencephalogram (EEG) classi cation task lies with in the dilemma of feature extraction, as raw time series signal provide little correlated information, yet it holds colossal varieties of hidden feature patterns. Frequency domain transformations are considered state of the art to tackle such complexity. Nevertheless such conventional feature extraction techniques for instance; discrete wavelet transformation (DWT), short time Fourier transform (STFT), di erential entropy or classical non-parametric power spectral density (PSD) estimation models are computationally expensive as they demonstrate high computational complexity and extensive run time. Consequently arti cial intelligence driven multi channel EEG based systems struggles to process neural information in real time and such barrier minimizes the dynamics of relevant human computer interaction (HCI) and brain computer interaction (BCI) applications. Multiple Signal Classi cation Algorithm (MUSIC) is an eigen decomposition based parametric PSD estimation model, which solely uses linear transformation rather than computing windowed periodigram from autocorrelted function of the targeted signal for transformation. Hence MUSIC algorithm should demonstrate lesser time complexity and run time than contemporary classical non-parametric PSD models. Nevertheless this particular model is relatively unexplored for such feature extraction task speci cally in the area of emotion recognition, as the model is di cult to implement in terms of EEG signals which demonstrate random behaviour. Our research investigates the performance of MUSIC algorithm in feature extraction task for emotion recognition from multi channel EEG signals and compares its performance with conventional classical non parametric models. It also clari es the complexity in subspace estimations for EEG waveforms through in detailed analysis, which are indispensable parameters for implementing any eigen decomposition based models in such particular cases. Our proposed model derived state of the art 5-fold cross validation accuracies of 97% and 97:4% for Multi Layer Perceptron (MLP) network and Hybrid Long Term Short Memory (LSTM)-MLP network, respectively on the SEED emotional dataset. The proposed MUSIC model optimizes 95%􀀀96% run time comparing with conventional classical non-parametric techniques for feature extraction. With exceptional 0:01 sec: machine speci c run time for feature extraction task, the proposed model shows great prospect in real time applications. Network performance and advanced visualization techniques demonstrate the MUSIC model based feature space holds signi cant superiority over non-parametric model generated feature space. Additionally the research also found extensive aws in the widely popular SEED dataset, which were ignored in previously. Over 17% trials were found to hold multiple corrupt channel resulted from external artifacts, which should have e ected previously conducted researches. Our research also discusses the e ects of such awed trial in network performance.
Modeling and Classification of Voluntary and Imagery Movements through fNIR & EEG Signals for Brain-Computer Interface
(Khulna University of Engineering & Technology (KUET), Khulna, Bangladesh, 2020-01) Rahman, Md. Asadur; Ahmad, Prof. Dr. Mohiuddin
Neural activation measurement regarding voluntary and imagery movement is a crucial argument for brain-computer interface. Generally, movement-related hemodynamics is measured from the central lobe of the brain which may be erroneous for the paralyzed people due to their inactiveness of this brain area. To overcome this limitation, this thesis work proposes an approach to measure the movement-related hemodynamics from the prefrontal cortex. In the proposed research work, the changes of the oxidized hemoglobin (HbO2) and deoxidized hemoglobin (dHb) concentration regarding different voluntary and imagery movement stimuli are captured by functional near-infrared spectroscopy (fNIR) from several subjects. With necessary preprocessing, the fNIR signals are statistically analyzed by ANOVA and effect size method to localize the most significantly activated regions of the prefrontal cortex regarding the voluntary and imagery stimuli. The experimental results show that voluntary and imagery movements have a strong correlation with the prefrontal cortex. The temporal pattern of HbO2 and dHb signals regarding the most activated regions are modeled by polynomial regression. Consequently, the model activation patterns are used to classify the voluntary and imagery tasks based on the maximum similarity approach. In addition, conventional classification methods are used to classify the signals. In this work, we consider two, four, and six class fNIR data of movement-related tasks for classification. The classification accuracies of the proposed method are convincing and found almost similar to the conventional procedure. The outcomes of this proposed work suggest that the prefrontal hemodynamics can be used for the modeling and classification of the voluntary and imagery movement-related tasks which will be helpful for the brain-computer interface applications. The combination of fNIR and electroencephalography (EEG) signals has become the best choice of accurate brain-computer interface (BCI) because of their finer spatiotemporal resolution. The purpose of this work is to develop an effective BCI model to classify the brain signals (fNIR and EEG) regarding the voluntary and imagery movements. For achieving the high classification accuracy from the developed BCI system, Convolutional neural network (CNN) has been used to extract the features automatically from the multiple channel fNIR and EEG signals instead of the manual feature selection. In this work, eight different movement-related stimuli (four voluntary and four imagery movements of hands and feet) have been considered. The multiple channel fNIR and EEG signals are used to prepare functional neuroimages to train and test the performance of the proposed BCI system. In addition, the proposed procedure is applied to prepare neuroimages from the individual modality (fNIR and EEG) to train and test the performance of the CNN based BCI system. The results reveal that the combined-modality approach of fNIR and EEG provides improved classification accuracy than the individual one. From the results, we found that the proposed CNN-based BCI system of bimodal (fNIR+EEG) approach outperforms the unimodal (only fNIR) methods in terms of the classification accuracy. Therefore, the outcomes of the proposed research work will be very helpful to implement the finer BCI system, in future.
QoS Provisioning Using Optimal Call Admission Control for Wireless Cellular Networks
(Khulna University of Engineering & Technology (KUET), Khulna, Bangladesh., 2014-12) Rahman, Md. Asadur; Chowdhury, Dr. Mostafa Zaman
The increasing demand for advanced services in wireless networks raises the problem for quality of service (QoS) provisioning with proper resource management. In this research, such a provisioning technique for wireless networks is performed by Call Admission Control (CAC). A new approach in CAC named by Uniform Fractional Band (UFB) is proposed in this work for the wireless networks for providing proper priority between new calls and handover calls. This UFB scheme is basically a new style of handover priority scheme. Handover priority is provided by two stages in this scheme which help the network to utilize more resources. The first priority stage is fractional priority and the second stage is integral priority. Fractional priority is provided by the uniform fractional acceptance factor that accepts new calls with the predefined acceptance ratio throughout the fractional priority stage (fractional band of channels). Integral priority is given to the handover calls by reserving some channels only for handover calls. In this work, it is shown that UFB scheme proofs itself as optimum call admission technique which is concerned about not only the QoS but also the proper channel utilization with respect to conventional guard channel and fractional channel schemes. In this thesis work, conventional fixed and fractional guard channel based CAC schemes are studied literally and presented in this paper in very easy mathematical method. In addition, the handover call rate estimation and its impact on QoS provisioning is discussed widely to attain the optimum QoS in proposed handover priority scheme. In multiple services providing wireless network, excessive call blocking of lower priority traffic is very often event at very high traffic rate which is a concerning issue for QoS provisioning. To attain such QoS provisioning for multiple services, another CAC scheme is proposed in this research work. This scheme is recognised by Uniform Band Thinning (UBT) scheme which is based on uniform thinning technique (UTT) and this is quite similar idea as UFB scheme. In this scheme, a set of channels experiences the fractionizing policy. This scheme reduces the call blocking probabilities (CBP) of lower priority traffic classes without notably increasing the CBP's of the higher priority traffic classes. The analytical functions of this scheme are deduced in general form which is useful to deduce for any number of traffic classes. In addition, numerical analysis of the proposed UBT scheme shows that the performances in terms of call blocking probability, overall call blocking probability, and channel utilization are improved and optimised compared to the conventional fixed guard channel scheme. Keywords: Call admission control, call dropping probability, call blocking probability, quality of services, thinning schemes, acceptance factor, uniform fractional band, uniform band thinning, channel utilization, and traffic class.