- Dept. of EEE, KUET, Fulbarigate, Khulna-9203, Bangladesh
- +8801887066066
- Biosignal and Image Processing for disease diagnosis Clinical Engineering and ICT in healthcare Computer Vision and Pattern Recognition Renewable Energy and Energy Conversion, Biosignal and Image Processing for disease diagnosis, Clinical Engineering and ICT in healthcare, Computer Vision and Pattern Recognition, and Renewable Energy and Energy Conversionedit
- Professor Mohiuddin Ahmad received his BS degree with Honors Grade in Electrical and Electronic Engineering (EEE) fro... moreProfessor Mohiuddin Ahmad received his BS degree with Honors Grade in Electrical and Electronic Engineering (EEE) from Chittagong University of Engineering and Technology (CUET), Bangladesh, and his MS degree in Electronics and Information Science (EIS), major Biomedical Engineering (BME) from Kyoto Institute of Technology of Japan in 1994 and 2001, respectively. He received his Ph.D. degree in Computer Science and Engineering (CSE) from Korea University, Republic of Korea, in 2008. From November 1994 to August 1995, he served as Part-Time Lecturer in the Department of Electrical and Electronic Engineering at CUET, Bangladesh. From August 1995 to October 1998, he served as Lecturer in the Department of Electrical and Electronic Engineering at Khulna University of Engineeringedit
Research Interests:
This paper presents the economic analysis of a gridtied rooftop solar PV system with a net meter for a residential building of a university campus. The proposed PV system shows the capability to fulfill the maximum energy demand by the... more
This paper presents the economic analysis of a gridtied rooftop solar PV system with a net meter for a residential building of a university campus. The proposed PV system shows the capability to fulfill the maximum energy demand by the different flats of the building and supply overplus power to the national grid which contributes to national energy management. The methodology involves collecting the geographical site information, available useable rooftop area, solar energy resources data, load estimation, and energy consumption profile, PV module technical data, PV array sizing, calculate the profit and payback period of the system. The profit and payback period indicate the financial viability of the rooftop solar PV system. This paper also represents the amount of Carbon dioxide (CO2) reduction while generating the same amount of electrical energy from conventional fossil fuel-based power plants. The reduction of CO2 helps to preserve the environment green by reducing the production of greenhouse gases (GHGs) and global warming. The result of this analysis shows the rooftop solar PV system is economically viable and helpful to a clean environment.
Research Interests:
Support Vector Machine (SVM) is one of the most popular machine learning algorithms for pattern recognition of a specific dataset. The percentage of accuracy from a defined SVM model greatly depends on the selection of appropriate... more
Support Vector Machine (SVM) is one of the most popular machine learning algorithms for pattern recognition of a specific dataset. The percentage of accuracy from a defined SVM model greatly depends on the selection of appropriate attributes for SVM model. But the most effective attributes selection for SVM algorithm is one of the most difficult tasks for any kind of data classification. A mathematical model is proposed in this paper through which effectiveness of attributes for SVM model can be calculated. The validity of this SVM model is justified by comparing the effectiveness of a SVM model with the rate of pattern recognition for corresponding SVM model. Linear, Radial Basis Function (RBF), Polynomial Kernel SVM algorithms are used for pattern recognition. The percentage of accuracy of pattern recognition increases with the effectiveness of SVM model. The range of value of effectiveness of SVM model is 0 to <x. We have tested our proposed algorithm for noninvasive Brain Computer Interface (BCI) system. The proposed mathematical model is applicable for any other linear or nonlinear system.
Research Interests:
ABSTRACT Measurement of field permeability of asphalt pavement is affected by 3-D flow, saturation and other field boundary conditions. Therefore, field permeability testing is generally avoided for compaction quality control, mix... more
ABSTRACT Measurement of field permeability of asphalt pavement is affected by 3-D flow, saturation and other field boundary conditions. Therefore, field permeability testing is generally avoided for compaction quality control, mix evaluation, and/or moisture intrusion/damage evaluation of asphalt pavements. Rather laboratory permeability is used for asphalt mix (compaction) evaluation. Given the fact that most of the transportation agencies and paving contractors collect field cores for compaction and mix quality evaluation, an analytical model to predict field permeability can be very useful in the study of hydraulic conductivity of field pavements. To this end, this study attempts to develop an analytical model to determine field permeability of asphalt pavement using laboratory testing parameters of asphalt cores. In essence, an analytical model is developed in this study to determine field permeability from laboratory permeability and permeable pores of cores. Permeability and permeable porosity of two different sizes of asphalt cores are determined in the laboratory using a falling head permeameter modified with a salt concentration-measuring meter. These parameters are then used in the analytical model to predict field permeability. Model predicted values are found to compare reasonably well with the full scale field permeability values. The results of the analytical model are compared with the results from existing models, and the developed analytical model shows an improvement over the existing models. This model can be a useful tool in the study of asphalt’s hydraulic behavior.
Research Interests:
Research Interests:
This study evaluates the effects of moisture conditioning on chemical composition and mechanical properties of asphalt concrete. In addition, how chemical changes affect the mechanical properties of asphalt is evaluated. Moisture... more
This study evaluates the effects of moisture conditioning on chemical composition and mechanical properties of asphalt concrete. In addition, how chemical changes affect the mechanical properties of asphalt is evaluated. Moisture conditioning is conducted using the AASHTO T 283 procedure and recently developed Moisture Induced Sensitivity Testing (MIST) device. Chemical analysis is performed using the Fourier Transform Infrared (FTIR) device and the mechanical testing is performed by beam fatigue testing, and a Dynamic Shear Rheometer (DSR). Results show that binder aging occurs while moisture conditioning. Moisture conditioning causes changes in six functional molecular groups of an asphalt binder. These changes are different for different conditioning procedures as well as degree of conditioning. It is observed that aging due to Sulfonate group (S=O) causes an increase in modulus and fatigue life. However, aging due to Carbonyl group (C=O) causes an increase in modulus but a decrease in fatigue life. It is also observed that Saturate (C-C) has the highest impacts on the asphalt binder properties.
Research Interests:
Research Interests: Cognitive Science, Computer Science, Artificial Intelligence, FPGA, Neural Networks, and 15 moreProsthesis, Software, Artificial Neural Networks, EMG, Biomedical Signal Processing, Hardware, Electromyography, FPGA-based systems design, Biomedical electronics, Estimator, EMG signal processing, Artificial Neural Network, Biomedical Equipment, Mean Squared Error, and Field programmable gate arrays
Electromyography is a method for recording electrical activities of the muscle for different clinical and nonclinical tasks. For extracting more information, integrated electromyography is commonly used than the raw electromyography. This... more
Electromyography is a method for recording electrical activities of the muscle for different clinical and nonclinical tasks. For extracting more information, integrated electromyography is commonly used than the raw electromyography. This paper presents the design and implementation of integrated electromyography both in software and hardware. Software was implemented in Matlab due to easier implementation whereas hardware was designed on Field Programmable Gate Array (FPGA) due to low cost and flexibility. It can be seen that, the integrator works like a moving average window filter and a hundred-point window size is chosen in the integrator design. To verify the method, real surface electromyography data was collected and used. The mean error between software (Matlab) and hardware is 5.8288e-08 and the correlation coefficient is 1.
Research Interests:
Research Interests:
Research Interests:
In this paper, a new security system is proposed based on human computer interface by using Electrooculography (EOG) signal keeping concentration on physically disabled people. Nowadays security is the main concern in every sector of our... more
In this paper, a new security system is proposed based on human computer interface by using Electrooculography (EOG) signal keeping concentration on physically disabled people. Nowadays security is the main concern in every sector of our life. Most of the system requires a secret password to get access of the system under protection. In our work, a password based security system is proposed where password can be given by eye via EOG signal. The EOG interface detects the eye movement through electrodes placed on the face around the eyes. A unique pattern of EOG signal obtained by eye movement in certain directions can give the most secure password. An algorithm is proposed to detect the eye movement and extract the features of EOG signal. These features are further used to recognize the pattern for password using string matching technique. This system can be used as an added feature of EOG based assistive system. This is an offline approach which is highly accurate and reliable.
Research Interests:
Research Interests: Bioengineering, Computer Science, Artificial Intelligence, Blindness, Optical coherence tomography, and 10 moreMedicine, Tomography, Diabetes mellitus, Deep Learning, Diabetic Retinopathy, Retinal, Clinical Sciences, Optometry and Ophthalmology, Public health systems and services research, and optical coherence tomography angiography
An electrocardiogram (ECG) is the easiest and most reliable way to understand Left Ventricular Hypertrophy (LVH), which leads to many other cardiovascular diseases at the initial stage. However, LVH can develop silently over several years... more
An electrocardiogram (ECG) is the easiest and most reliable way to understand Left Ventricular Hypertrophy (LVH), which leads to many other cardiovascular diseases at the initial stage. However, LVH can develop silently over several years without any symptoms, and it is not easy to diagnose LVH even with renowned methods and many other proposed theoretical approaches because of its interrelated nature. Utilizing ECG/EKG data availability, the authors have proposed a classifier using Support Vector Machine (SVM). Here the SVM classifier is a re-fabrication of the Combine Cornell-Sokolow (CCS) methodology, and the classifier has the effectiveness of over 90% detecting LVH in complex cases. Training variation constructs different models with various accuracies, but balance training can achieve quite admissible results. The paper will delineate the training procedure and discuss the findings in it. The study will also have concerned about EGC signal pre-processing, data processing, and feature detection in its path. Any electronic diagnosis system can utilize this research’s classifier to distinguish LVH among complex cases. The classifier can identify LVH cases continuously because of its computation manner, even where an expert physician is unavailable.
Research Interests:
Research Interests:
Research Interests:
Abstract Cranial ultrasound scans are very essential part of the routine investigation of neonatal intensive care. The scan ultrasound image sequence are not only used for real-time diagnosis but also recorded for future diagnosis. In... more
Abstract Cranial ultrasound scans are very essential part of the routine investigation of neonatal intensive care. The scan ultrasound image sequence are not only used for real-time diagnosis but also recorded for future diagnosis. In this paper, we analyze and ...
Research Interests:
Research Interests:
Abstract-Pneumonia is a bacterial infection-caused life-threatening respiratory disease. About 15% all over the world kid’s loss of life is triggered via pneumonia. A new virus called COVID-19 (in which) most important indications are... more
Abstract-Pneumonia is a bacterial infection-caused life-threatening respiratory disease. About 15% all over the world kid’s loss of life is triggered via pneumonia. A new virus called COVID-19 (in which) most important indications are pneumonia. Computer-aided diagnostic (CADx) methods have been studied for decades for the diagnosis of chest X-ray images based on lung diseases. For visual recognition, these tools assess the image properties derived from CNN. CNN filters a photo to acquire information from the chest X-ray. Throughout this study, we consider the performance of a customized CNN model used as feature extractors by the way of a variety of classifiers to distinguish the unusual and pneumonic chest X-Rays. Statistical findings point out that our CADx model can assist in the evaluation of clinical images as well. The user can insert their chest radiograph to the web app and find out their pneumonia condition, whether it is present or not present. Our proposed identification method’s accuracy is 94% which is very high compared with other states of artwork.
Research Interests:
In this paper, a user independent human computer interface system using eye movement and blink feature detection is introduced. A hands free interface between computer and human can potentially replace the traditional human computer... more
In this paper, a user independent human computer interface system using eye movement and blink feature detection is introduced. A hands free interface between computer and human can potentially replace the traditional human computer interface devices like mouse, keyboard etc. This technology is intended to give functionality to peoples with severe motor disabilities to control a computer by just moving their eyes. This paper describes a method of controlling the mouse cursor on a computer screen using the electrical potentials developed by eye movements known as Electrooculography. Electrooculography (EOG) signal is used to detect eye movement and blink features. The EOG signal is recorded from electrodes placed at appropriate positions around the eyes. The captured EOG signal is then analyzed to detect and classify eye movement features of interest. The detected features were then used to generate control signals to control a mouse cursor. The cursor control application is implemented offline. The detection accuracy for blinks, horizontal and vertical saccades are 100%, 97% and 93% respectively.
Research Interests:
In this work, the effects of different caffeine doses on cardiac activity have been evaluated by frequency domain analysis of laser Doppler flowmetry signal. Using different data acquisition units, the blood perfusion on human forearm... more
In this work, the effects of different caffeine doses on cardiac activity have been evaluated by frequency domain analysis of laser Doppler flowmetry signal. Using different data acquisition units, the blood perfusion on human forearm middle finger tip has been recorded. Blood perfusion has been recorded before and immediately after the consumption of all caffeine doses. Different caffeine doses contain different amount of caffeine but approximately same amount of sugar. Recorded and pre-processed data have been analyzed using frequency spectrum within the frequency range of cardiac activity. It is found that the consumption of caffeine free dose increases the cardiac activity. Besides, the consumption of caffeinated doses decreases the cardiac activity with respect to normal condition (before consumption). As the amount of caffeine consumed increases, the cardiac activity improves. Result shows 42.9%, 32.2% and 39.4% decrement in cardiac activity due to the consumption of 27 mg, 48 mg, and 64 mg caffeine respectively. The consumption of 80 mg caffeine dose significantly increases the cardiac activity. The outcome indicates the reduction of heart functions due to the consumption of lower caffeine dose.
Research Interests:
Advances in low power electronics and the internet of things are driving the development of wearable medical devices. Innovations in this domain are imperative for individuals with amputated limbs who are willing to operate a wide range... more
Advances in low power electronics and the internet of things are driving the development of wearable medical devices. Innovations in this domain are imperative for individuals with amputated limbs who are willing to operate a wide range of practical devices and systems particularly the personal computer. In this paper, we practically demonstrate a wearable wireless mouse suitable for people with hand amputation up to the elbow. The device operates on a combination of signals from gyroscope and Electromyogram (EMG) sensors. The spatial movement is tracked by gyroscope whereas the mouse functionalities are controlled by signals from the EMG sensors. The system monitors EMG signals only from the biceps and triceps muscles reducing the device and algorithm complexities. To make the device more universal for the user, an automatic threshold calibration algorithm is implemented to determine the threshold of the working signal-to-noise-ratio (SNR). Moreover, an SNR based algorithm is introduced to make the response of the system more robust and increase its operational accuracy. The device proposed in this paper can successfully perform all the functionalities capable of a conventional computer mouse.
Research Interests:
In recent days, brain tumor detection through Magnetic Resonance Imaging (MRI) is becoming broad and current interest because it is a very challenging task even, in today's modern medical image processing research. Earlier, many... more
In recent days, brain tumor detection through Magnetic Resonance Imaging (MRI) is becoming broad and current interest because it is a very challenging task even, in today's modern medical image processing research. Earlier, many researchers used a variety of algorithms to segment the tumor from MRI images. However, this research paper outlines a hybrid approach detecting brain tumor through MRI image segmentation for better accuracy than earlier techniques, where both region-based and supervised classifiers-based techniques are combined together. The problem of over-segmentation has been minimized. The combined feature extraction technique has also added a new concept in our system. In addition, the paper concludes with the status checking of the tumor & provides a necessary diagnosis of brain tumor. Lastly, we compare our proposed model with other techniques and get a far better result.
Research Interests:
This research work firstly describes the development and estimation of raspberry pi based smart glass system to recognize the family member of a blind man by using image processing. This system helps the blind man by giving the name of... more
This research work firstly describes the development and estimation of raspberry pi based smart glass system to recognize the family member of a blind man by using image processing. This system helps the blind man by giving the name of the family member as audio information. Raspberry Pi is a very powerful processor where machine learning can be integrated very easily like SVM, KNN, and Tensor Flow, etc. Blind People can easily identify their native family members by using their voice. When family members stop talking, it's quite impossible to identify the man near the blind man. So, here we introduce a Raspberry pi based system that can easily identify the person in front of the blind man and give audio name information. In this system, we use raspberry pi face recognition, face encoding, and face database creation for family member face recognition. So this device can be a great assistive device for the blind man. Our proposed smart glass system is good, low weight, extremely economical, and highly efficient.
Research Interests:
Electroencephalogram (EEG) that measures the electrical activity of the brain has been used extensively to recognize emotion. Normally feature based emotion recognition requires a strong effort to design the perfect feature or feature set... more
Electroencephalogram (EEG) that measures the electrical activity of the brain has been used extensively to recognize emotion. Normally feature based emotion recognition requires a strong effort to design the perfect feature or feature set related to the classification of emotion. To curtail the manual human effort we designed a model by using a virtual image from EEG with Convolutional Neural Network (CNN). Initially, we calculated Pearson’s correlation coefficients form different sub-bands of EEG to formulate a virtual image. Later, this virtual image was fed into a CNN architecture to classify emotion. We made two distinct protocols; between these, protocol-1 was to classify positive and negative emotion and protocol-2 was to classify four distinct emotions. An overall maximum accuracy of 81.51% on valence and 79.42% on arousal was obtained by using internationally authorized DEAP dataset. Our proposed method is helpful in recognizing emotions efficiently.
Research Interests:
To investigate human brain activities regarding EEG signal during psychophysiological activities in Salat (Muslim Prayer), several facts have been analyzed in this study. This research work investigated relaxed condition with eyes open... more
To investigate human brain activities regarding EEG signal during psychophysiological activities in Salat (Muslim Prayer), several facts have been analyzed in this study. This research work investigated relaxed condition with eyes open and eyes closed and compared with 2 raqat (a single unit of Muslim prayer) Salat. Consequently, we have proposed that Salat provides a more relaxed state of mind than that of relaxing with either eye opened or closed. EEG data were acquired through the B-Alert system from several participants. The effects of EEG alpha band were determined using Welch's power spectral density method. Using student's t-distribution, the p-value was calculated to determine the difference between the alpha relative power of Salat and other relaxed states. During psychophysiological activities in Salat, a significant (p<0.05) increase in alpha RP has been observed in the frontal and parietal regions than other two relaxed sessions. This result reflects the relaxed condition of body and soul which raises parasympathetic activity and lessens the sympathetic activity. Therefore, this proposed work concludes that Salat can support proper relaxation and reduce anxiety than the regular relaxed situations.
Research Interests:
This work reports the potentiality of the motor imagery movement classification from prefrontal hemodynamics for the brain–computer interface (BCI) applications. Although movement-related activation correlates with the central lobe, this... more
This work reports the potentiality of the motor imagery movement classification from prefrontal hemodynamics for the brain–computer interface (BCI) applications. Although movement-related activation correlates with the central lobe, this area of a paralyzed patient is often found obsolete. Therefore, to design a BCI system for paralyzed persons, the central lobe hemodynamics cannot be considered. To overcome this problem, this work proposed an alternative approach. This research work experimentally investigates the potentiality of classifying the motor planning (imagery) activities from the prefrontal hemodynamics. The functional changes of prefrontal hemodynamics for imagery hand movements are measured by functional near-infrared spectroscopy (fNIRS) from several subjects. The fNIRS signals of imagery hand movements are classified by a k-nearest neighbor and artificial neural network algorithms. The classification accuracies were checked with the subject dependent and independent approach. Our results demonstrate that the prefrontal hemodynamics could serve as the potential biomarker for the effective BCI system.
Research Interests:
Research Interests:
Functional near-infrared spectroscopy (fNIRS) plays an imperative role for studying hemodynamic measurement of brain. Event related task measurement mostly depends on the effect size (ES) of fNIRS data. The noisy fNIR signal is an... more
Functional near-infrared spectroscopy (fNIRS) plays an imperative role for studying hemodynamic measurement of brain. Event related task measurement mostly depends on the effect size (ES) of fNIRS data. The noisy fNIR signal is an obstacle to estimate the precise ES of such measurement. Though Savitzky-Golay and Moving Average filters are often used for de-noising the fNIR signal, they have some limitations in measuring ES. In this paper, we have proposed a simple signal processing scheme which contributes to remove noise and evaluates not only proper ES but also overcome the drawback of Savitzky-Golay and Moving Average filter. By this scheme, the filtered signal becomes lower standard deviated than the raw fNIR signal. Else, the scheme maintains the mean of original and filtered signal unchanged. Since, the scheme reduces the standard deviation of the signal notably remaining the mean value unchanged; the ES of interest is improved eloquently. The numerical results and corresponding contrast to noise ratio (CNR) pattern prove the usefulness of the proposed scheme. The numerical results and corresponding contrast to noise ratio (CNR) pattern prove the effectiveness of the proposed scheme.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Motor Imagery (MI) is a highly supervised method nowadays for the disabled patients to give them hope. This paper proposes a differentiation method between imagery left and right hands movement using Daubechies wavelet of Discrete Wavelet... more
Motor Imagery (MI) is a highly supervised method nowadays for the disabled patients to give them hope. This paper proposes a differentiation method between imagery left and right hands movement using Daubechies wavelet of Discrete Wavelet Transform (DWT) and Levenberg-Marquardt back propagation training algorithm of Neural Network (NN). DWT decomposes the raw EEG data to extract significant features that provide feature vectors precisely. Levenberg-Marquardt Algorithm (LMA) based neural network uses feature vectors as input for classification of the two class data and outcomes overall classification accuracy of 92%. Previously various features and methods used but this recommended method exemplifies that statistical features provide better accuracy for EEG classification. Variation among features indicates differences between neural activities of two brain hemispheres due to two imagery hands movement. Results from the classifier are used to interface human brain with machine for better performance that requires high precision and accuracy scheme.
Research Interests:
A biosignal is a human body variable that can be measured and monitored continuously and provide information about the health status. Among them well known bioelectrical signals are Electrocardiograph (ECG), Electromyography (EMG),... more
A biosignal is a human body variable that can be measured and monitored continuously and provide information about the health status. Among them well known bioelectrical signals are Electrocardiograph (ECG), Electromyography (EMG), Electroencephalogram (EEG) and Electrooculogram (EOG). Those signals are useful for different applications like disease diagnosis, human machine interface, entertainment. This paper presents a low cost, wireless biosignal acquisition system specialized for ECG, EMG and EOG. In this system, Arduino Uno in used and an application is developed for visualizing and storing the signal in real-time. This application is developed by processing. It stores the signal data in a text file, which can be used in MATLAB for analysis. In this system, biosignal is transferred by Bluetooth serial communication, which ensures safety and reduces noise interference. This system can be used either Windows, Linux, Mac OS and suitable for both laptop and desktop computer.
Research Interests:
This paper presents a cognitive state estimation system focused on some effective feature extraction based on temporal and spectral analysis of electroencephalogram (EEG) signal and the proper channel selection of the BIOPAC automated EEG... more
This paper presents a cognitive state estimation system focused on some effective feature extraction based on temporal and spectral analysis of electroencephalogram (EEG) signal and the proper channel selection of the BIOPAC automated EEG analysis system. In the proposed approach, different frequency components (i) real value; (ii) imaginary value; (iii) magnitude; (iv) phase angle and (v) power spectral density of the EEG data samples during different mental task performed to assess seven types of human cognitive states — relax, mental task, memory related task, motor action, pleasant, fear and enjoying music on the three channels of BIOPAC EEG data acquisition system — EEG, Alpha and Alpha RMS signal. Also the time and time-frequency-based features were extracted to compare the performance of the system. After feature extraction, the channel efficacy is evaluated by support vector machine (SVM) based on the classification rate in different cognitive states. From the experimental results and classification accuracy, it is determined that the overall accuracy for alpha channel shows much improved result for power spectral density than the other frequency based features and other channels. The classification rate is 69.17% for alpha channel whereas for EEG and alpha RMS channel it is found 47.22% and 32.21%, respectively. For statistical analysis standard deviation shows better result for alpha channel and it is found 65.4%. The time-frequency analysis shows much improved result for alpha channel also. For the mean value of DWT coefficients the accuracy is highest and it is 81.3%. Besides the classification accuracy, SVM shows better performance in compare with kNN classifier.
Research Interests:
Practical brain–computer interface (BCI) demands the learning-based adaptive model that can handle diverse problems. To implement a BCI, usually functional near-infrared spectroscopy (fNIR) is used for measuring functional changes in... more
Practical brain–computer interface (BCI) demands the learning-based adaptive model that can handle diverse problems. To implement a BCI, usually functional near-infrared spectroscopy (fNIR) is used for measuring functional changes in brain oxygenation and electroencephalography (EEG) for evaluating the neuronal electric potential regarding the psychophysiological activity. Since the fNIR modality has an issue of temporal resolution, fNIR alone is not enough to achieve satisfactory classification accuracy as multiple neural stimuli are produced by voluntary and imagery movements. This leads us to make a combination of fNIR and EEG with a view to developing a BCI model for the classification of the brain signals of the voluntary and imagery movements. This work proposes a novel approach to prepare functional neuroimages from the fNIR and EEG using eight different movement-related stimuli. The neuroimages are used to train a convolutional neural network (CNN) to formulate a predictive model for classifying the combined fNIR–EEG data. The results reveal that the combined fNIR–EEG modality approach along with a CNN provides improved classification accuracy compared to a single modality and conventional classifiers. So, the outcomes of the proposed research work will be very helpful in the implementation of the finer BCI system.
Research Interests:
Research Interests:
Research Interests: Computer Science, Artificial Intelligence, Computer Vision, Support Vector Machines, Image Analysis (Mathematics), and 9 moreImage Representation, Human Body, Action Recognition, Human Performance, Human Action Recognition, Action (Physics), Electrical And Electronic Engineering, Silhouette, and Representation Politics
Research Interests: Computer Science, Artificial Intelligence, Computer Vision, Principal Component Analysis, Gesture Recognition, and 15 moreImage Analysis (Mathematics), Proceedings, Motion estimation, Optical Flow, Hidden Markov Models, Human Body, Action Recognition, hidden Markov model, Feature Extraction, Image recognition, Shape, Human Action Recognition, Image Sequence, Feature Space, and Feature vector
Research Interests:
Research Interests:
Magnetic resonance imaging is one of the best methods for detecting brain tumors. But the images captured by this method may contain different kinds of noises. So it is very essential to remove the noises for properly identifying the... more
Magnetic resonance imaging is one of the best methods for detecting brain tumors. But the images captured by this method may contain different kinds of noises. So it is very essential to remove the noises for properly identifying the specific brain tumor. A filter is usually used to remove the noises. This paper illustrates different image filtering methods, such as low pass filter, high pass filter, and median filter, to improve the image quality by removing the noises from magnetic resonance images to identify the brain tumor. The MSE, RMSE, and the PSNR is used for understanding the quality of the filtered images. A graphical user interface is developed in MATLAB to implement all the filtering process and performance analysis for magnetic resonance images used to detect brain tumor.
Research Interests:
Research Interests:
In the past few decades, the healthcare technology management performance comes under the clinical engineering for enhancing the healthcare delivery performance of hospital. For this reasons, most of the countries established clinical... more
In the past few decades, the healthcare technology management performance comes under the clinical engineering for enhancing the healthcare delivery performance of hospital. For this reasons, most of the countries established clinical engineering department in their healthcare delivery organizations such hospitals and clinics. This study explores clinical engineering intermediation to measure the performance of present healthcare delivery and advises to introduce the CED in the healthcare delivery organization. In this paper, we propose a model of CED for 250 bedded hospital in Bangladesh. The study describes the necessity of CE to enhance the present unpleasant healthcare delivery performance in Bangladesh as well as describes the result to introduce CED model in the healthcare delivery organization in Bangladesh. Moreover, the benefit of introduced CE and CED in healthcare delivery organizations in Bangladesh is described. Expected results of this study will enrich the conceptions of the present health care management team on CE and CED for the healthcare delivery performance. We firmly believe that our study will enhance the present unfamiliarity conception of healthcare management team.
Research Interests:
Research Interests:
Korotkoff method is the most used method for blood pressure measurement. In this method, sphygmomanometer and a stethoscope are required. A trained person is required for properly measuring blood pressure. In this paper, an easy approach... more
Korotkoff method is the most used method for blood pressure measurement. In this method, sphygmomanometer and a stethoscope are required. A trained person is required for properly measuring blood pressure. In this paper, an easy approach has been introduced to develop a non-invasive digital blood pressure meter that will enable people to measure their blood pressure at home without the help of a trained person. This design consists of a simple circuit. The pressure signal is collected by a pressure sensor, which consists of the valuable signal for blood pressure measurement along with many noise signals. So, it is processed by using a two-stage bandpass filter and an analog to digital converter. The signal obtained after filtering is suitable for calculating systolic and diastolic blood pressure values using simple software design. Then calculated values of systolic and diastolic blood pressure can be shown on a liquid crystal display. In this system, no digital filtering is required. Therefore, this system is easy to implement and by using this system, it is possible to convert an analog sphygmomanometer into a digital blood pressure monitor easily. As this system provides an opportunity for measuring blood pressure at home without a trained person, it will be very helpful for early diagnosing of problems related to blood pressure.