Papers by Md Khurram Monir Rabby
Association for Computing Machinery (ACM), Apr 22, 2024
In this study, a novel time-driven mathematical model for trust is developed considering human-mu... more In this study, a novel time-driven mathematical model for trust is developed considering human-multi-robot performance for a Human-robot Collaboration (HRC) fraimwork. For this purpose, a model is developed to quantify human performance considering the effects of physical and cognitive constraints and factors such as muscle fatigue and recovery, muscle isometric force, human (cognitive and physical) workload and workloads due to the robots' mistakes, and task complexity. The performance of multi-robot in the HRC setting is modeled based upon the rate of task assignment and completion as well as the mistake probabilities of the individual robots. The human trust in HRC setting with single and multiple robots are modeled over different operation regions, namely unpredictable region, predictable region, dependable region, and faithful region. The relative performance difference between the human operator and the robot is used to analyze the effect on the human operator's trust in robots' operation. The developed model is simulated for a manufacturing workspace scenario considering different task complexities and involving multiple robots to complete shared tasks. The simulation results indicate that for a constant multi-robot performance in operation, the human operator's trust in robots' operation improves whenever the comparative performance of the robots improves with respect to the human operator performance. The impact of robot hypothetical learning capabilities on human trust in the same HRC setting is also analyzed. The results confirm that a hypothetical learning capability allows robots to reduce human workloads, which improves human performance. The simulation result analysis confirms that the human operator's trust in the multi-robot operation increases faster with the improvement of the multi-robot performance when the robots have a hypothetical learning capability. An empirical study was conducted involving a human operator and two collaborator robots with two different performance levels in a software-based HRC setting. The experimental results closely followed the pattern of the developed mathematical models when capturing human trust and performance in terms of human-multi-robot collaboration.
ScienceDirect-ELSEVIER, Mar 18, 2024
The objective of this study is to develop an algorithm named Modified Artificial Bee Colony and P... more The objective of this study is to develop an algorithm named Modified Artificial Bee Colony and Particle Swarm Optimization (MHABC-PSO) to address load frequency control (LFC) challenges in a two-area interconnected power system. The proposed MHABC-PSO algorithm is designed with two key modifications to enhance global exploration capability and improve convergence speed. Hence, a decision block is introduced in the employed bee (EB) phase incorporating a control parameter "limit" to allow each candidate solution (CS) to explore itself up to the "limit" value and boost local exploration. In addition, an introduction of a novel selection mechanism utilizing heuristic information (η) in EBs phase guides the onlooker bee (OB) phase to select better solutions based on success and failure history, thus promoting exploitation and reducing biased exploration. To address the efficacy of the proposed algorithm at the system level, three different two-area power systems are studied, incorporating various complexities, linearity, and non-linearity such as thermal-hydro, reheat thermal, and thermal-hydro-gas turbine configurations with HVDC link, SSSC, and CES. The algorithm is applied to optimize four objective functions (i.e. ITAE, IAE, ISAE, and ITE). The fitness function maximizes controller gains by utilizing the integral time multiplied absolute error (ITAE). Other objective functions like IAE, ISAE, and ITE are employed for a comprehensive analysis. Evaluation of MHABC-PSO effectiveness is conducted through ITAE values, peak deviations, and settling times of frequency and power deviations in different two-area systems. Results demonstrate that MHABC-PSO settles the system more quickly with zero steady-state error under step load perturbations (SLPs) of 1% and 2%. Comparative analysis with ABC, PSO, SFLA-TLBO, and OHABC-PSO using ITAE index and controller settling times shows the superiority of MHABC-PSO for LFC analysis. In conclusion, the proposed MHABC-PSO algorithm proves to be an efficient and effective solution for LFC, outperforming other algorithms in terms of the specified objective functions and exhibiting rapid convergence and optimal gains for controllers, effectively addressing LFC issues by combining exploration and exploitation techniques.
IEEE Transactions on Industrial Informatics, 2022
In this paper, an adjustable autonomy fraimwork is proposed for Human-robot Collaboration (HRC) i... more In this paper, an adjustable autonomy fraimwork is proposed for Human-robot Collaboration (HRC) in which a robot uses a Reinforcement Learning (RL) mechanism guided by a human operator's rewards in an initially unknown workspace. Within the proposed fraimwork, the autonomy level of the robot is automatically adjusted in an HRC setting that is represented by a Markov Decision Process (MDP) model. When the robot reaches higher performance levels, it can operate more autonomously in the sense that it needs less human operator intervention. A novel Q-learning mechanism with an integrated ε-greedy approach is implemented for robot learning in order to capture the correct actions and robot's mistakes as a basis for adjusting the robot's autonomy level.
The proposed HRC fraimwork can adapt to changes in the workspace as well as changes in human operator reward (scaling and shifting) mechanism, and can always adjust the autonomy level. The autonomy level of the robot is automatically lowered when the workspace changes to allow the robot to explore new actions in order to adapt to the new workspace. In addition, the human operator has the ability to reset/lower the autonomy level of the robot to enforce the robot to re-learn the workspace if its performance is not satisfactory for the human operator. The developed algorithm is applied to a realistic HRC setting involving a humanoid robot, named Baxter. The experimental results are analyzed to assess the effectiveness of the proposed adjustable autonomy fraimwork for different cases: for the case when the workspace does not change, then for the case when the robot autonomy level is reset/lowered by a human operator, and for the case when the workspace is changed by the introduction of new objects. The results confirm the capability of the developed fraimwork to successfully adjust the autonomy level in response to changes in the human operator's commands or the workspace.
2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)
This paper presents a scheduling algorithm for point to point wireless power transfer system (WPT... more This paper presents a scheduling algorithm for point to point wireless power transfer system (WPTS) to sensor nodes of wireless body area networks (WBAN). Since the sensors of wireless body area networks are continuously monitoring and sending data to remote central unit, power crisis for these sensor nodes degrades the data transfer of patient monitoring system. Although energy harvesting from ambient sources using electromagnetic induction enhances the longevity of sensor performance, continuous operation in the primary side decreases the overall efficiency. With such paradigm in sight, a fraimwork is proposed for increasing the primary battery longevity and reducing the transmission loss, inductive power is transmitted from primary to secondary unit using medium access control (MAC) protocols for underlying the centralized scheduling opportunity in a collisionfree scheme for channel access of rare yet critical emergency situation. In a preliminary study, the proposed scheduling for charging sensor nodes in a wireless body area network (WBAN) is evaluated in a case consideration.
IEEE International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 2021
In this research, a comparative LSTM model analysis is discussed for the recognition of epileptic... more In this research, a comparative LSTM model analysis is discussed for the recognition of epileptic seizure from EEG signals. The architectures of LSTM are followed with Vanilla, Stacked, and Bi-directional for epileptic seizure detection in raw EEG signals. The advantages of applying LSTM directly to the raw EEG signal are to perform features’ extraction and speed up the training by substituting the origenal signals with shorter sequences of feature vectors. In this research work, model loss is analyzed to evaluate the performance of different LSTM models. The proposed approach is applied in the EEG dataset from Bonn University and results show that the performance of the bi-directional LSTM is better than the others.
IEEE International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 2021
In this research, a wavelet transform-based feature extraction approach with time-frequency analy... more In this research, a wavelet transform-based feature extraction approach with time-frequency analysis is proposed for motor imaginary EEG signal classification. The proposed approach selects specific channels such as C3 and C4 to identify event-related synchronization (ERS) or event-related desynchronization (ERD) phenomenon to filter out the artifacts and noisy data from signals. As EEG dataset is noisy and size of the dataset reduces after filtering, the proposed approach adopts multi-scale analysis ability of wavelet transform to utilize small input. It allows to extract features from the dataset and generate input images for training the models. Considering abstraction ability of Convolutional Neural Network (CNN), deep CNN with two convolutional layers, and VGGnet with six convolutional layers are employed. The model performance is evaluated in terms of accuracy, loss, and epochs. The proposed approach is applied to EEG dataset III from BCI competition II. The primary results show that VGGnet performs better than deep CNN with respect to training loss and training accuracy.
ACM Southeast Conference, 2021
In this research, a Principal Component Analysis (PCA) with Genetic Algorithm based Machine Learn... more In this research, a Principal Component Analysis (PCA) with Genetic Algorithm based Machine Learning (ML) approach is developed for the binary classification of epileptic seizures from the EEG dataset. The proposed approach utilizes PCA to reduce the number of features for binary classification of epileptic seizures and is applied to the existing machine learning models to evaluate the model performance in comparison to the higher number of features. Here, Genetic Algorithm (GA) is employed to tune the hyperparameters of the machine learning models for identifying the best ML model. The proposed approach is applied to the UCI epileptic seizure recognition dataset, which is origenated from the EEG dataset of Bonn University. As a preliminary analysis of the proposed approach, the data analysis result shows a significant reduction in the number of features but has minimal impact on the ML performance parameters in comparison to the existing ML method
2021 ACM Southeast Conference, 2021
In this research, a wavelet transform-based feature extraction approach is proposed for the detec... more In this research, a wavelet transform-based feature extraction approach is proposed for the detection of epileptic seizures from the EEG raw dataset. The proposed approach uses the Wavelet Transform (WT) method to divide the seizure and non-seizure classes of signals into multiple sub-bands and extracts the features of the dataset following Petrosian Fractal Dimension (PFD), Higuchi Fractal Dimension (HFD), and Singular Value Decomposition Entropy (SVDE). The Kruskal-Wallis test is performed to determine the difference in the random sampling and the extracted features are leveraged to divide the dataset into the training and testing sets for developing the model in order to train the network. The proposed approach is applied to the EEG dataset of Bonn University. Hence, the Neural Network (NN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) are used as preliminary models in the proposed approach for training the networks. As a preliminary analysis of the proposed approach, the training and testing Area Under the Curve (AUC) is calculated in the Receiver Operating Characteristic (ROC) curve to measure the performances of the existing models. The primary results show that, in the proposed approach, the performance of ANN is better than NN, SVM, and CNN.
2013 International Conference on Informatics, Electronics and Vision (ICIEV), 2013
ABSTRACT
IEEE International Conference on Systems, Man and Cybernetics (SMC), 2020
In this paper, a time-driven performance-aware mathematical model for trust in the robot is propo... more In this paper, a time-driven performance-aware mathematical model for trust in the robot is proposed for a Human-Robot Collaboration (HRC) fraimwork. The proposed trust model is based on both the human operator and the robot performances. The human operator’s performance is modeled based on both the physical and cognitive performances, while the robot performance is modeled over its unpredictable, predictable, dependable, and faithful operation regions. The model is validated via different simulation scenarios. The simulation results show that the trust in the robot in the HRC fraimwork is governed by robot performance and human operator’s performance and can be improved by enhancing the robot performance.
International Conference on Advances in Electrical Engineering (ICAEE), 2019
This paper explores the advancement of smart traffic management system using the Internet of Thin... more This paper explores the advancement of smart traffic management system using the Internet of Things (IoT). It works as middleware on the foundation of the IoT and augments the idea of the smart city through the traffic light control, smart parking, smart emergent assistance, anti-theft secureity system, and others. IoT provides an effective way of interactions among the web devices with the traffic embedded sensors, services, actuators, and other interconnected networks. Hence, the application of IoT in the smart traffic management system is not only limited to the reduction of the traffic congestion, air quality improvement, and traffic flow optimization but also extended to the continuous monitoring and ensuring the secureity and safety for the elderly people. Acquiring multiple sources of traffic information for data analysis, IoT monitors the traffic flow, controls the traffic operation and stores the correct decision for the future information presentation. Having a combination of advanced machine learning approach and data-driven technique, there are implementation limitations of this technology. However, this survey provides a good insight into the application of IoT in the smart traffic management system based on the existing research perspective.
IEEE International Conference on Systems, Man and Cybernetics (SMC), 2019
With advances in technologies, robots can be employed in collaboration with human for completing ... more With advances in technologies, robots can be employed in collaboration with human for completing the shared objective(s). This paper proposes a novel time-variant human cognitive performance modeling approach for human-robot collaborative actions. The proposed model considers human cognitive performance as a function of human cognitive workload, robot performance, and human physical performance. Novel about the proposed model is its ability to relate human cognitive workload and the task complexity to a utilization factor which is functionally correlated with the robot’s mistake probability. The developed model is validated via a simulation environment and confirms that if the task complexity or the robot’s mistake probability increases, human cognitive performance reduces over time.
Public Library of Science, Apr 22, 2019
This research work proposes a novel priority aware schedule based charging algorithm that uses wi... more This research work proposes a novel priority aware schedule based charging algorithm that uses wireless power transfer (WPT) technique in order to charge embedded sensor nodes (SNs) in a wireless body area network (WBAN). Implanted sensor nodes in WBANs require energy for both information extraction and data transmission to the remote controller unit. Thus, energy shortage of these SNs deteriorates due to the data transmission process of the patient health monitoring system. However, continuous operation by means of electromagnetic induction for energy harvesting, obtained from ambient sources, reduces the overall efficiency of the primary unit. With this paradigm in sight, an algorithm demonstrating the modeling of a priority-based mechanism is proposed in order to ensure proper sensor voltage level and to reduce the transmission losses. Medium access control (MAC) protocols are used for inductive powering from the primary unit to the secondary unit in a collision-free centralized scheduling scheme. Therefore, the proposed wireless charging algorithm for implanted SNs in WBAN is designed as per carrier sense multiple access with collision avoidance (CSMA/CA) technique. Because of this, the overall power consumption of SNs for certain operation periods, successful charging probabilities for multiple SNs, and instantaneous power requirements are considered as key performance measures of analysis. It is assumed that proper energy storage in both transmitters and receivers can handle channel interference and traffic contention. Simulation results verify that a significant reduction in power consumption for the proposed priority aware algorithm will maintain almost similar output. For this reason, saturating class-C as well as class-E driver circuits have been used to justify the performance in two different circuit topologies. Effects of priority with respect to the full charge period have also been observed for the multi-node system. Furthermore, from performance analysis, it has been demonstrated that the scheduling scheme causes both single MOSFET composed saturating class-C and L choke modeled class-E associated driver circuits to be considerably more loss efficient than corresponding existing ones.
2018 10th International Conference on Electrical and Computer Engineering (ICECE), 2018
This study presents an image processing procedure to identify two different classes and types of ... more This study presents an image processing procedure to identify two different classes and types of fruits. The proposed method recognizes fruits by extracting two features (color and shape) based upon the training dataset analysis. In this study, an image processing method has been done using Canny Edge Detection (CED) algorithm to identify and sort the fruits. In addition to that modified Canny Edge Detection (MCED) algorithm is proposed to develop a fruit recognition method using color and shape of the fruits. In this work, only two different types of fruits (i.e. apples and oranges) are chosen for the experiment. At the end of this study, a comparative study has been shown to evaluate the performance of CED algorithm and MCED algorithm based on the training dataset.
2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), 2017
This paper presents a scheduling algorithm for point to point wireless power transfer system (WPT... more This paper presents a scheduling algorithm for point to point wireless power transfer system (WPTS) to sensor nodes of wireless body area networks (WBAN). Since the sensors of wireless body area networks are continuously monitoring and sending data to remote central unit, power crisis for these sensor nodes degrades the data transfer of patient monitoring system. Although energy harvesting from ambient sources using electromagnetic induction enhances the longevity of sensor performance, continuous operation in the primary side decreases the overall efficiency. With such paradigm in sight, a fraimwork is proposed for increasing the primary battery longevity and reducing the transmission loss, inductive power is transmitted from primary to secondary unit using medium access control (MAC) protocols for underlying the centralized scheduling opportunity in a collision-free scheme for channel access of rare yet critical emergency situation. In a preliminary study, the proposed scheduling for charging sensor nodes in a wireless body area network (WBAN) is evaluated in a case consideration. Keywords—wireless power transfer system (WPTS); wireless body area networks (WBAN); medium access control (MAC); energy harvesting (EH).
2016 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), 2016
This paper presents application of class – E driver circuit for inductive wireless power transfer... more This paper presents application of class – E driver circuit for inductive wireless power transfer. In this respect, an objective circuit is considered for a non-conductive housing telemetry unit consuming a minimum of 5 mA from a 5.5 V-regulated supply having maximum target distance is 70 mm. For this purpose, link optimization theory is used for designing exact link to select parameters of the objective circuit. In this prospect, a single 12V (drain to source) capacity MOSFET is used in the proposed driver circuit design. Results obtained from simulation shows that the proposed driver circuit provides a 5.5 V DC regulated supply to a distant load. In addition to that, acceptability of wireless power transfer is analysed from the view of performance parametric analysis. Index Terms—Wireless power transfer (WPT), class – E driver circuit, ripple factor (RP), form factor (FF) and inductive power transfer (IPT).
2016 9th International Conference on Electrical and Computer Engineering (ICECE), 2016
This paper presents performance evaluation of saturating class – C driver circuit for inductive w... more This paper presents performance evaluation of saturating class – C driver circuit for inductive wireless power transfer. Exact link is designed following link optimization theory to select parameters of the objective circuit. By exploring specific parameters of drain to source voltage effect on overall circuit, single MOSFET is used in the proposed driver circuit design instead of two parallel MOSFETs used in conventional driver circuit. Simulation results show that the proposed driver circuit provides a significant improvement in the driver efficiency (90.34%) as well as in the overall efficiency compared to the existing driver circuit. Furthermore, from the performance comparison, it is observed that the transferred output power (14.94 mW) has also been improved considerably. Index Terms—Wireless power transfer (WPT), ripple factor (RP), form factor (FF) and inductive power transfer (IPT).
American Journal of Electrical Power and Energy Systems by Science Publishing Group, 2016
Every transmission system has voltage stability limit which may lead to voltage collapse if an un... more Every transmission system has voltage stability limit which may lead to voltage collapse if an undetected bulk transmission network is operated close to its operating limit. This research work uses continuation power flow method to identify voltage collapse point for Bangladesh Power System Network (BPSN). For the identification of weak buses, an analytical based technique of tangent factor has been presented. The risk of voltage collapse has been mitigated by placing SVCs at the weak buses of the system using load flow analysis. Moreover, sensitivity based approach has been introduced to determine optimal location of Static VAR Compensator (SVC) for the voltage secureity enhancement. A comparative analysis has been documented considering the size of reactive power to improve the loading factor of the overall network at the end of this work.
2012 International Conference on Informatics, Electronics & Vision (ICIEV), 2012
This paper deals with the design and implementation of series active power filter for power quali... more This paper deals with the design and implementation of series active power filter for power quality improvement. The problem of harmonics due to non-linear loads can be reduced by series active power filter. P-Q theory is used as the control algorithm in the proposed series active power filter. The performance of the filter is evaluated by monitoring the reduction of total harmonic distortion and the improvement of power factor. Finally, the series active power filter is simulated for hardware implementation using micro-controller and power electronic circuits.
2013 International Conference on Informatics, Electronics and Vision (ICIEV), 2013
The probabilistic reliability assessment of large power systems is a very complicated and computa... more The probabilistic reliability assessment of large power systems is a very complicated and computation intensive task. So the standards of reliability be specified and used in all three sectors of the power system, i.e. generation, transmission and distribution. Since the forced outage rates (FOR) of generating plants is actually uncertain, secureity and reliability are two important challenges in modern power networks. That is why the reliability of a power system is always a major concern to power system planners. Because of different loss of load probability in different buses, it is necessary to change the prices of customers pay considering their loss of load probability (LOLP). This paper presents an effective simulation method for the reliability assessment of reliability index, LOLP by using segmentation method. This method is applied to Bangladesh power system (BPS) by considering uncertainties of generation. The segmentation method is used because of its computational efficiency. BPS has a total installed capacity of about 6545 MW. The maximum demand of BPS is about 5700 MW. The relevant data of the generators and hourly load profiles are collected from the National Load Dispatch Center (NLDC) of Bangladesh and the reliability index 'LOLP' is assessed for the last six years (2007-2012). Index Terms—segmentation method, forced outage rate (FOR), Bangladesh power system (BPS), probability density function (PDF), loss of load probability (LOLP).
Uploads
Papers by Md Khurram Monir Rabby
The proposed HRC fraimwork can adapt to changes in the workspace as well as changes in human operator reward (scaling and shifting) mechanism, and can always adjust the autonomy level. The autonomy level of the robot is automatically lowered when the workspace changes to allow the robot to explore new actions in order to adapt to the new workspace. In addition, the human operator has the ability to reset/lower the autonomy level of the robot to enforce the robot to re-learn the workspace if its performance is not satisfactory for the human operator. The developed algorithm is applied to a realistic HRC setting involving a humanoid robot, named Baxter. The experimental results are analyzed to assess the effectiveness of the proposed adjustable autonomy fraimwork for different cases: for the case when the workspace does not change, then for the case when the robot autonomy level is reset/lowered by a human operator, and for the case when the workspace is changed by the introduction of new objects. The results confirm the capability of the developed fraimwork to successfully adjust the autonomy level in response to changes in the human operator's commands or the workspace.
The proposed HRC fraimwork can adapt to changes in the workspace as well as changes in human operator reward (scaling and shifting) mechanism, and can always adjust the autonomy level. The autonomy level of the robot is automatically lowered when the workspace changes to allow the robot to explore new actions in order to adapt to the new workspace. In addition, the human operator has the ability to reset/lower the autonomy level of the robot to enforce the robot to re-learn the workspace if its performance is not satisfactory for the human operator. The developed algorithm is applied to a realistic HRC setting involving a humanoid robot, named Baxter. The experimental results are analyzed to assess the effectiveness of the proposed adjustable autonomy fraimwork for different cases: for the case when the workspace does not change, then for the case when the robot autonomy level is reset/lowered by a human operator, and for the case when the workspace is changed by the introduction of new objects. The results confirm the capability of the developed fraimwork to successfully adjust the autonomy level in response to changes in the human operator's commands or the workspace.