Nasir Rashid | National University of Sciences & Technology (NUST) (original) (raw)

Papers by Nasir Rashid

Computers and Electronics in Agriculture

2019 International Conference on Robotics and Automation in Industry (ICRAI)

In recent years, much progress has been made in the field of Unmanned Ground Vehicles (UGV). None... more In recent years, much progress has been made in the field of Unmanned Ground Vehicles (UGV). Nonetheless, safe mobility and traversal of a UGV on rough terrains such as snow and mountainous regions is still a daunting task. This paper discusses the increased maneuverability and robustness of a UGV by developing its control on NI myRIO. A Versatile Terrain Autonomous Mobility Platform (VTAMP) has been designed for an increase traversing capability through rough and challenging terrains. Extended maneuverability is achieved with the assistance of arm-like structures in the vehicle known as "Flippers". An open loop control system based on NI myRIO is developed with the addition of few add-ons like night vision camera. To achieve robustness, a fail-safe has been developed in both hardware and software and its reliability is experienced in various testing conditions.

2017 17th International Conference on Control, Automation and Systems (ICCAS), 2017

This paper presents an application of a novel approach for detecting and tracking an object with ... more This paper presents an application of a novel approach for detecting and tracking an object with a 2 DOF robotic manipulator which can be equipped with an array of electrically controlled actuators. The said approach utilizes the Image Based Visual Servoing (IBVS) technique. The developed system is able to determine the object pose in real time from features in the image. Object is detected using shaped based approach algorithms of image processing. The position and orientation of the world coordinates of the object being tracked are calculated from the coordinates of the object in image plane using camera's intrinsic and extrinsic parameters. Experimental results demonstrate the effectiveness of this proposed approach.

2021 International Conference on Robotics and Automation in Industry (ICRAI), 2021

Brain-computer interface (BCI) is a tool for non-muscular contact between computer and the brain,... more Brain-computer interface (BCI) is a tool for non-muscular contact between computer and the brain, used to acquire Electroencephalograms (EEG). Motor Imagery (MI) is the psychic implementation of any movement without any muscle awakening. Imagination of movement of the limbs can result in spatially noticeable brain signals that can be used to classify patterns. In this research, the application of Hilbert Transform (HT) for the classification of MI based EEG data is shown. A publicly available BCI Competition IV dataset, by Berlin BCI group, containing EEG recordings of 7 subjects performing MI task has been used for this study. Hilbert Transform has been implemented on the EEG data to draw phase plots for the detection of activity in each trial. An average accuracy of 93.6% has been achieved using the proposed methodology. Conclusions of this research manifest that better classification accuracy can be obtained using phase plots of EEG signals which would result in a more viable threshold.

2017 17th International Conference on Control, Automation and Systems (ICCAS), 2017

This paper presents the design of a stair climbing fixed flipper unmanned ground vehicle (UGV) fo... more This paper presents the design of a stair climbing fixed flipper unmanned ground vehicle (UGV) for urban search and rescue purposes. Mobile flippers are being used in certain UGVs for enhanced mobility in rough terrains, however, the control algorithm of these platforms is complex. To add this enhanced mobility in the UGV and to reduce the intricacy of the control algorithm, anterior end of the tracks are lifted up which enables the UGV to pass over obstacles with relative ease. To prevent the rollover of UGV while moving on an inclined surface, an image processing algorithm was developed which halts the motion of UGV if the calculated slope exceeds the threshold value with a maximum error of about 8%. Furthermore, left and right track velocities along with the turn radius were also calculated.

2019 7th International Conference on Mechatronics Engineering (ICOM), 2019

Brain computer interface (BCI) can be defined as a pathway that enables human brain to communicat... more Brain computer interface (BCI) can be defined as a pathway that enables human brain to communicate and voluntarily command an external device and generate output instead of depending upon peripheral nerves and muscular movements. Achieving maximum classification accuracy is the greatest challenge in developing a BCI system to correctly interpret the brain signals. This paper aims at investigating various classification algorithms in combination with different pre-processing techniques and comparing their results for maximum classification accuracy. Independent component analysis (ICA), principal component analysis (PCA) and notch filters are used for artifact removal, dimension reduction and noise cancellation, respectively. Left and right hand movements were recorded from the scalp using non-invasive electrodes. Fine KNN, with independent components as feature, gives highest classification accuracy in comparison with various classification techniques used in this research.

2018 3rd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), 2018

This paper presents the design of a 3 degree of freedom manipulator which can be easily mounted o... more This paper presents the design of a 3 degree of freedom manipulator which can be easily mounted on an Unmanned Ground Vehicle (UGV). UGVs operate in closed spaces and rough terrains where human manipulation is difficult for applications involving urban search and rescue. The manipulator therefore needs to have high performance, be light-weight and compact. The proposed design of the manipulator can be easily used with different end-effectors like a camera, gripper or cutter, relevant to the application. In order to maximize the payload capacity and minimize power consumption, in-parallel actuation of the elbow joint is proposed which nullifies the load of actuator on shoulder joint. A chain mechanism is used to transfer torque from motor at base to the relevant joint. Self-locking has been achieved by using worm and gear. This approach results in an increase of 1.42 kilograms in the payload capacity of the manipulator. The results are verified through experimentation.

Journal of Emerging Trends in Engineering and Applied Sciences, 2013

Energy needs are becoming more and more complex, especially in underdeveloped countries. The sola... more Energy needs are becoming more and more complex, especially in underdeveloped countries. The solar energy is one of best solution for increasing demand of energy by mankind. Sun energy can fulfil our domestic and irrigation requirement because fossil fuels are running short day by day. Therefore, it is one of the most important source of energy to explore for its maturity. In this paper, kinematic and energy analysis of two solar trackers panel systems are studied comparatively for maximising efficiency. Structure of model 1 (single axis tracker) previously designed was bulky, causing the linear actuator to consume more electrical energy. Kinematic and force analysis of model 1 showed the drawbacks of displaced centre of gravity and excessive energy consumption due to weight of frame which supports the panel. Based on kinematic and force analysis of model 1, new model 2 has been designed in which all the above problems are addressed by shifting the centre of gravity on the axis of r...

IEEE Access, 2021

Amputees with lower limb loss need special care during daily life activities to make the movement... more Amputees with lower limb loss need special care during daily life activities to make the movement natural as before amputation. No such work exists covering the main aspects from causes of amputation to the psycho-social impact of the amputees after using the prosthetic device. This review presents for lower limb prosthesis; the study of lower limb amputation, design & development, control strategies & machine learning algorithms, the psycho-social impact of prosthetic users, and design trends in patents. Research articles, review papers, magazines, letters, study reports, surveys, and patents, etc. have been used as sources for this review. Traumatic injuries and different diseases have been found as common causes of amputation. Design & development section illustrates design mechanisms, the categories of passive, active, & semi-active prostheses, an overview of a subset of commercially available prosthetic devices, and 3D printing of the accessories. The control section provides information about control techniques, sensors used, machine learning algorithms, and their key outcomes. Quality of life, phantom limb pain, and psycho-social impact of prosthetic users have been summarized for different countries that are believed to attract the interest of the readers. We have also developed an open-source database ''FAKH-50'' for patents to emphasize the design trends and advancements in lower limb prostheses from 1970 to 2020. Overall trend analysis determined is in the descending order as the knee (48%) > ankle (28%) > foot (22%) > hip (2%) patents in the current version of our database. The forthcoming section highlights the challenges and prospects of the domain. A mutual observation demands the design of a bio-compatible, lightweight, and economic prosthesis to track the normal human gait by eliminating phantom limb pain. This will empower the amputees to live a quality life in society. This work may be beneficial for researchers, technicians, clinicians, and amputees. INDEX TERMS Causes of amputation, lower limb amputation, lower limb prosthesis, design mechanisms, semi-active prosthesis, human gait cycle.

Proceedings of the 2018 4th International Conference on Mechatronics and Robotics Engineering, 2018

Feature extraction is a pronounced method to infer the information utility which is concealed in ... more Feature extraction is a pronounced method to infer the information utility which is concealed in electromyography (EMG) signal to study the characteristic properties and behavior of signal. This study gives a comparative analysis of thirteen complete and most up-to-date EMG feature signals in Time-domain and Frequency-domain. Particularly, the EMG signals are obtained from a device MYO gesture control on an embedded system. For this purpose, four healthy male volunteers are considered to perform four different hand movements based on stationary, double tap, single finger movement and finger spread. To be a successful classification of these EMG features in both domains, we prefer attribute selected classifier as it gives the better performance and higher rate of accuracy i.e. 93.8%. The experimental results prove that features in time-domain are superfluity and redundant while features in frequency-domain (measured by statistical parameters of EMG power spectral density) show the ultimate dominance and signal characterization. The findings of this study are highly beneficial for further use in order to predict the behavior of EMG in pattern recognition and in classification of EMG signals for assistive devices or in powered human arm prosthetics.

IEEE Access

The exponential growth in road accidents has led to a need for continuous driver monitoring to en... more The exponential growth in road accidents has led to a need for continuous driver monitoring to enhance road safety. Existing techniques rely on vehicle sensor-based and behavior analysis-based approaches, where the behavior analysis-based approaches are generally considered more desirable as they enable reliable detection of a more elaborate set of driver behaviors. They are categorized as intrusive and non-intrusive approaches. Unlike intrusive approaches that generally rely on constant direct human contact with sensors (physiological signals) and are sensitive to artifacts, non-intrusive approaches offer a more effective behavior monitoring using computer vision-based techniques. This paper proposes an end-to-end non-intrusive IoT-based automated framework to monitor driver behaviors, designed specifically for logistic and public transport applications. It consists of an embedded system, edge computing and cloud computing modules, and a mobile phone application, in an attempt to provide a holistic unified solution for drowsiness detection, monitoring, as well as evaluation of drivers. Drowsiness detection is based on detecting sleeping, yawning, and distraction behaviors using an image processing-based technique. To minimize the effects of latency, throughput, and packet losses, edge computing is performed using commercial off-the-shelf embedded boards. Moreover, a cloud-hosted real-time database for remote monitoring on interactive Android mobile application has been set up, where admin can add multiple drivers to get drowsiness notifications along with other useful related information for driver evaluation. An extensive experimental testing has been performed, obtaining encouraging results. An overall accuracy of 96% is achieved along with an enhanced robustness, portability, and usability of the proposed framework.

2020 12th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), 2020

Computers and Electronics in Agriculture, 2022

Computers and Electronics in Agriculture, 2021

2013 IEEE 9th International Conference on Emerging Technologies (ICET), 2013

IEEE Access

Weeds affects crops health as it shares water and nutrients from the soil, as a result it decreas... more Weeds affects crops health as it shares water and nutrients from the soil, as a result it decreases crop yield. Manual weedicide spray through bag-pack is hazardous to human health. Localized autonomous weedicide spray through aerial spraying units can help save water, weedicide chemical and effect less on human health. Such systems require multi-spectral cues to classify crop, weed, and soil surface. Our focus in this paper is on the detection of weeds in the sugar beet crop, using airborne multispectral camera sensors, which is considered as an alternative crop to sugarcane to obtain sugar in Pakistan. We developed a new framework for weed identification; a patch-based classification approach as appose to semantic segmentation that is more realistic for real-time intelligent aerial spraying systems. Our approach converts 3-class pixel classification problem into a 2-class crop-weed patch classification problem which in turns improves crop and weed classification accuracy. For classification, we developed a new VGG-Beet convolutional neural network (CNN), which is based on generic CNN (VGG16) model with 11 convolutional layers. For experiments, we captured a sugar beet dataset with 3-channel multispectral sensor with a ground sampling distance (GSD) of 0.2 cm/pixel and a height of 4 meters. For better comparison, we used two publicly available sugar beet crop aerial imagery datasets, captured using a 5-channel multispectral sensor and a 4-Channel multispectral sensor with a ground sampling distance of 1cm and a height of 10 meters. We observed that patch-based method is more robust to different lighting conditions. To produce low cost weed detection system usage of Agrocam sensor is recommended, for higher accuracy Red Edge and Sequoia multispectral sensors with more channels should be deployed. We observed higher crop-weed accuracy and lower testing time for our patch-based approach as compared to state-of-the-art UNet and Deeplab semantic segmentation networks. INDEX TERMS autonomous weed detection, drone weed detection, deep learning in agriculture, multispectral image processing.

Infrared Physics & Technology

BioMed research international, 2018

Brain Computer Interface (BCI) determines the intent of the user from a variety of electrophysiol... more Brain Computer Interface (BCI) determines the intent of the user from a variety of electrophysiological signals. These signals, Slow Cortical Potentials, are recorded from scalp, and cortical neuronal activity is recorded by implanted electrodes. This paper is focused on design of an embedded system that is used to control the finger movements of an upper limb prosthesis using Electroencephalogram (EEG) signals. This is a follow-up of our previous research which explored the best method to classify three movements of fingers (thumb movement, index finger movement, and first movement). Two-stage logistic regression classifier exhibited the highest classification accuracy while Power Spectral Density (PSD) was used as a feature of the filtered signal. The EEG signal data set was recorded using a 14-channel electrode headset (a noninvasive BCI system) from right-handed, neurologically intact volunteers. Mu (commonly known as alpha waves) and Beta Rhythms (8-30 Hz) containing most of th...

BioMed research international, 2018

Background. Brain computer interface (BCI) is a combination of software and hardware communicatio... more Background. Brain computer interface (BCI) is a combination of software and hardware communication protocols that allow brain to control external devices. Main purpose of BCI controlled external devices is to provide communication medium for disabled persons. Now these devices are considered as a new way to rehabilitate patients with impunities. There are certain potentials present in electroencephalogram (EEG) that correspond to specific event. Main issue is to detect such event related potentials online in such a low signal to noise ratio (SNR). In this paper we propose a method that will facilitate the concept of online processing by providing an efficient filtering implementation in a hardware friendly environment by switching to finite impulse response (FIR). Main focus of this research is to minimize latency and computational delay of preprocessing related to any BCI application. Four different finite impulse response (FIR) implementations along with large Laplacian filter are implemented in Xilinx System Generator. Efficiency of 25% is achieved in terms of reduced number of coefficients and multiplications which in turn reduce computational delays accordingly.

2015 15th International Conference on Control, Automation and Systems (ICCAS), 2015

This paper discusses the development of a customizable FPGA based system for implementing control... more This paper discusses the development of a customizable FPGA based system for implementing control algorithms on an Unmanned Ground Vehicle (UGV) and its 5 Degree of Freedom (DOF) manipulator. The compact RIO-9012 is used as a controller which is a reconfigurable embedded control and acquisition system using LabVIEW as the programming platform. The developed system enables the control of UGV and its manipulator using a remote joystick controller via Wi-Fi communication. Apart from Joystick, the system can also be controlled optionally using a keyboard. Accuracy of Joystick control has been enhanced by using point to point mapping technique. A user friendly GUI has been developed to view live video feedback obtained from the onboard cameras to control the UGV accordingly. Different features of UGV like path tracker (tracks its path on Google Maps), variable speed modes, battery indicator, camera switch and selector etc. are also managed in the GUI. The system has been developed so that, in future, it can easily be extended to a fully autonomous system.

Computers and Electronics in Agriculture

2019 International Conference on Robotics and Automation in Industry (ICRAI)

In recent years, much progress has been made in the field of Unmanned Ground Vehicles (UGV). None... more In recent years, much progress has been made in the field of Unmanned Ground Vehicles (UGV). Nonetheless, safe mobility and traversal of a UGV on rough terrains such as snow and mountainous regions is still a daunting task. This paper discusses the increased maneuverability and robustness of a UGV by developing its control on NI myRIO. A Versatile Terrain Autonomous Mobility Platform (VTAMP) has been designed for an increase traversing capability through rough and challenging terrains. Extended maneuverability is achieved with the assistance of arm-like structures in the vehicle known as "Flippers". An open loop control system based on NI myRIO is developed with the addition of few add-ons like night vision camera. To achieve robustness, a fail-safe has been developed in both hardware and software and its reliability is experienced in various testing conditions.

2017 17th International Conference on Control, Automation and Systems (ICCAS), 2017

This paper presents an application of a novel approach for detecting and tracking an object with ... more This paper presents an application of a novel approach for detecting and tracking an object with a 2 DOF robotic manipulator which can be equipped with an array of electrically controlled actuators. The said approach utilizes the Image Based Visual Servoing (IBVS) technique. The developed system is able to determine the object pose in real time from features in the image. Object is detected using shaped based approach algorithms of image processing. The position and orientation of the world coordinates of the object being tracked are calculated from the coordinates of the object in image plane using camera's intrinsic and extrinsic parameters. Experimental results demonstrate the effectiveness of this proposed approach.

2021 International Conference on Robotics and Automation in Industry (ICRAI), 2021

Brain-computer interface (BCI) is a tool for non-muscular contact between computer and the brain,... more Brain-computer interface (BCI) is a tool for non-muscular contact between computer and the brain, used to acquire Electroencephalograms (EEG). Motor Imagery (MI) is the psychic implementation of any movement without any muscle awakening. Imagination of movement of the limbs can result in spatially noticeable brain signals that can be used to classify patterns. In this research, the application of Hilbert Transform (HT) for the classification of MI based EEG data is shown. A publicly available BCI Competition IV dataset, by Berlin BCI group, containing EEG recordings of 7 subjects performing MI task has been used for this study. Hilbert Transform has been implemented on the EEG data to draw phase plots for the detection of activity in each trial. An average accuracy of 93.6% has been achieved using the proposed methodology. Conclusions of this research manifest that better classification accuracy can be obtained using phase plots of EEG signals which would result in a more viable threshold.

2017 17th International Conference on Control, Automation and Systems (ICCAS), 2017

This paper presents the design of a stair climbing fixed flipper unmanned ground vehicle (UGV) fo... more This paper presents the design of a stair climbing fixed flipper unmanned ground vehicle (UGV) for urban search and rescue purposes. Mobile flippers are being used in certain UGVs for enhanced mobility in rough terrains, however, the control algorithm of these platforms is complex. To add this enhanced mobility in the UGV and to reduce the intricacy of the control algorithm, anterior end of the tracks are lifted up which enables the UGV to pass over obstacles with relative ease. To prevent the rollover of UGV while moving on an inclined surface, an image processing algorithm was developed which halts the motion of UGV if the calculated slope exceeds the threshold value with a maximum error of about 8%. Furthermore, left and right track velocities along with the turn radius were also calculated.

2019 7th International Conference on Mechatronics Engineering (ICOM), 2019

Brain computer interface (BCI) can be defined as a pathway that enables human brain to communicat... more Brain computer interface (BCI) can be defined as a pathway that enables human brain to communicate and voluntarily command an external device and generate output instead of depending upon peripheral nerves and muscular movements. Achieving maximum classification accuracy is the greatest challenge in developing a BCI system to correctly interpret the brain signals. This paper aims at investigating various classification algorithms in combination with different pre-processing techniques and comparing their results for maximum classification accuracy. Independent component analysis (ICA), principal component analysis (PCA) and notch filters are used for artifact removal, dimension reduction and noise cancellation, respectively. Left and right hand movements were recorded from the scalp using non-invasive electrodes. Fine KNN, with independent components as feature, gives highest classification accuracy in comparison with various classification techniques used in this research.

2018 3rd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), 2018

This paper presents the design of a 3 degree of freedom manipulator which can be easily mounted o... more This paper presents the design of a 3 degree of freedom manipulator which can be easily mounted on an Unmanned Ground Vehicle (UGV). UGVs operate in closed spaces and rough terrains where human manipulation is difficult for applications involving urban search and rescue. The manipulator therefore needs to have high performance, be light-weight and compact. The proposed design of the manipulator can be easily used with different end-effectors like a camera, gripper or cutter, relevant to the application. In order to maximize the payload capacity and minimize power consumption, in-parallel actuation of the elbow joint is proposed which nullifies the load of actuator on shoulder joint. A chain mechanism is used to transfer torque from motor at base to the relevant joint. Self-locking has been achieved by using worm and gear. This approach results in an increase of 1.42 kilograms in the payload capacity of the manipulator. The results are verified through experimentation.

Journal of Emerging Trends in Engineering and Applied Sciences, 2013

Energy needs are becoming more and more complex, especially in underdeveloped countries. The sola... more Energy needs are becoming more and more complex, especially in underdeveloped countries. The solar energy is one of best solution for increasing demand of energy by mankind. Sun energy can fulfil our domestic and irrigation requirement because fossil fuels are running short day by day. Therefore, it is one of the most important source of energy to explore for its maturity. In this paper, kinematic and energy analysis of two solar trackers panel systems are studied comparatively for maximising efficiency. Structure of model 1 (single axis tracker) previously designed was bulky, causing the linear actuator to consume more electrical energy. Kinematic and force analysis of model 1 showed the drawbacks of displaced centre of gravity and excessive energy consumption due to weight of frame which supports the panel. Based on kinematic and force analysis of model 1, new model 2 has been designed in which all the above problems are addressed by shifting the centre of gravity on the axis of r...

IEEE Access, 2021

Amputees with lower limb loss need special care during daily life activities to make the movement... more Amputees with lower limb loss need special care during daily life activities to make the movement natural as before amputation. No such work exists covering the main aspects from causes of amputation to the psycho-social impact of the amputees after using the prosthetic device. This review presents for lower limb prosthesis; the study of lower limb amputation, design & development, control strategies & machine learning algorithms, the psycho-social impact of prosthetic users, and design trends in patents. Research articles, review papers, magazines, letters, study reports, surveys, and patents, etc. have been used as sources for this review. Traumatic injuries and different diseases have been found as common causes of amputation. Design & development section illustrates design mechanisms, the categories of passive, active, & semi-active prostheses, an overview of a subset of commercially available prosthetic devices, and 3D printing of the accessories. The control section provides information about control techniques, sensors used, machine learning algorithms, and their key outcomes. Quality of life, phantom limb pain, and psycho-social impact of prosthetic users have been summarized for different countries that are believed to attract the interest of the readers. We have also developed an open-source database ''FAKH-50'' for patents to emphasize the design trends and advancements in lower limb prostheses from 1970 to 2020. Overall trend analysis determined is in the descending order as the knee (48%) > ankle (28%) > foot (22%) > hip (2%) patents in the current version of our database. The forthcoming section highlights the challenges and prospects of the domain. A mutual observation demands the design of a bio-compatible, lightweight, and economic prosthesis to track the normal human gait by eliminating phantom limb pain. This will empower the amputees to live a quality life in society. This work may be beneficial for researchers, technicians, clinicians, and amputees. INDEX TERMS Causes of amputation, lower limb amputation, lower limb prosthesis, design mechanisms, semi-active prosthesis, human gait cycle.

Proceedings of the 2018 4th International Conference on Mechatronics and Robotics Engineering, 2018

Feature extraction is a pronounced method to infer the information utility which is concealed in ... more Feature extraction is a pronounced method to infer the information utility which is concealed in electromyography (EMG) signal to study the characteristic properties and behavior of signal. This study gives a comparative analysis of thirteen complete and most up-to-date EMG feature signals in Time-domain and Frequency-domain. Particularly, the EMG signals are obtained from a device MYO gesture control on an embedded system. For this purpose, four healthy male volunteers are considered to perform four different hand movements based on stationary, double tap, single finger movement and finger spread. To be a successful classification of these EMG features in both domains, we prefer attribute selected classifier as it gives the better performance and higher rate of accuracy i.e. 93.8%. The experimental results prove that features in time-domain are superfluity and redundant while features in frequency-domain (measured by statistical parameters of EMG power spectral density) show the ultimate dominance and signal characterization. The findings of this study are highly beneficial for further use in order to predict the behavior of EMG in pattern recognition and in classification of EMG signals for assistive devices or in powered human arm prosthetics.

IEEE Access

The exponential growth in road accidents has led to a need for continuous driver monitoring to en... more The exponential growth in road accidents has led to a need for continuous driver monitoring to enhance road safety. Existing techniques rely on vehicle sensor-based and behavior analysis-based approaches, where the behavior analysis-based approaches are generally considered more desirable as they enable reliable detection of a more elaborate set of driver behaviors. They are categorized as intrusive and non-intrusive approaches. Unlike intrusive approaches that generally rely on constant direct human contact with sensors (physiological signals) and are sensitive to artifacts, non-intrusive approaches offer a more effective behavior monitoring using computer vision-based techniques. This paper proposes an end-to-end non-intrusive IoT-based automated framework to monitor driver behaviors, designed specifically for logistic and public transport applications. It consists of an embedded system, edge computing and cloud computing modules, and a mobile phone application, in an attempt to provide a holistic unified solution for drowsiness detection, monitoring, as well as evaluation of drivers. Drowsiness detection is based on detecting sleeping, yawning, and distraction behaviors using an image processing-based technique. To minimize the effects of latency, throughput, and packet losses, edge computing is performed using commercial off-the-shelf embedded boards. Moreover, a cloud-hosted real-time database for remote monitoring on interactive Android mobile application has been set up, where admin can add multiple drivers to get drowsiness notifications along with other useful related information for driver evaluation. An extensive experimental testing has been performed, obtaining encouraging results. An overall accuracy of 96% is achieved along with an enhanced robustness, portability, and usability of the proposed framework.

2020 12th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), 2020

Computers and Electronics in Agriculture, 2022

Computers and Electronics in Agriculture, 2021

2013 IEEE 9th International Conference on Emerging Technologies (ICET), 2013

IEEE Access

Weeds affects crops health as it shares water and nutrients from the soil, as a result it decreas... more Weeds affects crops health as it shares water and nutrients from the soil, as a result it decreases crop yield. Manual weedicide spray through bag-pack is hazardous to human health. Localized autonomous weedicide spray through aerial spraying units can help save water, weedicide chemical and effect less on human health. Such systems require multi-spectral cues to classify crop, weed, and soil surface. Our focus in this paper is on the detection of weeds in the sugar beet crop, using airborne multispectral camera sensors, which is considered as an alternative crop to sugarcane to obtain sugar in Pakistan. We developed a new framework for weed identification; a patch-based classification approach as appose to semantic segmentation that is more realistic for real-time intelligent aerial spraying systems. Our approach converts 3-class pixel classification problem into a 2-class crop-weed patch classification problem which in turns improves crop and weed classification accuracy. For classification, we developed a new VGG-Beet convolutional neural network (CNN), which is based on generic CNN (VGG16) model with 11 convolutional layers. For experiments, we captured a sugar beet dataset with 3-channel multispectral sensor with a ground sampling distance (GSD) of 0.2 cm/pixel and a height of 4 meters. For better comparison, we used two publicly available sugar beet crop aerial imagery datasets, captured using a 5-channel multispectral sensor and a 4-Channel multispectral sensor with a ground sampling distance of 1cm and a height of 10 meters. We observed that patch-based method is more robust to different lighting conditions. To produce low cost weed detection system usage of Agrocam sensor is recommended, for higher accuracy Red Edge and Sequoia multispectral sensors with more channels should be deployed. We observed higher crop-weed accuracy and lower testing time for our patch-based approach as compared to state-of-the-art UNet and Deeplab semantic segmentation networks. INDEX TERMS autonomous weed detection, drone weed detection, deep learning in agriculture, multispectral image processing.

Infrared Physics & Technology

BioMed research international, 2018

Brain Computer Interface (BCI) determines the intent of the user from a variety of electrophysiol... more Brain Computer Interface (BCI) determines the intent of the user from a variety of electrophysiological signals. These signals, Slow Cortical Potentials, are recorded from scalp, and cortical neuronal activity is recorded by implanted electrodes. This paper is focused on design of an embedded system that is used to control the finger movements of an upper limb prosthesis using Electroencephalogram (EEG) signals. This is a follow-up of our previous research which explored the best method to classify three movements of fingers (thumb movement, index finger movement, and first movement). Two-stage logistic regression classifier exhibited the highest classification accuracy while Power Spectral Density (PSD) was used as a feature of the filtered signal. The EEG signal data set was recorded using a 14-channel electrode headset (a noninvasive BCI system) from right-handed, neurologically intact volunteers. Mu (commonly known as alpha waves) and Beta Rhythms (8-30 Hz) containing most of th...

BioMed research international, 2018

Background. Brain computer interface (BCI) is a combination of software and hardware communicatio... more Background. Brain computer interface (BCI) is a combination of software and hardware communication protocols that allow brain to control external devices. Main purpose of BCI controlled external devices is to provide communication medium for disabled persons. Now these devices are considered as a new way to rehabilitate patients with impunities. There are certain potentials present in electroencephalogram (EEG) that correspond to specific event. Main issue is to detect such event related potentials online in such a low signal to noise ratio (SNR). In this paper we propose a method that will facilitate the concept of online processing by providing an efficient filtering implementation in a hardware friendly environment by switching to finite impulse response (FIR). Main focus of this research is to minimize latency and computational delay of preprocessing related to any BCI application. Four different finite impulse response (FIR) implementations along with large Laplacian filter are implemented in Xilinx System Generator. Efficiency of 25% is achieved in terms of reduced number of coefficients and multiplications which in turn reduce computational delays accordingly.

2015 15th International Conference on Control, Automation and Systems (ICCAS), 2015

This paper discusses the development of a customizable FPGA based system for implementing control... more This paper discusses the development of a customizable FPGA based system for implementing control algorithms on an Unmanned Ground Vehicle (UGV) and its 5 Degree of Freedom (DOF) manipulator. The compact RIO-9012 is used as a controller which is a reconfigurable embedded control and acquisition system using LabVIEW as the programming platform. The developed system enables the control of UGV and its manipulator using a remote joystick controller via Wi-Fi communication. Apart from Joystick, the system can also be controlled optionally using a keyboard. Accuracy of Joystick control has been enhanced by using point to point mapping technique. A user friendly GUI has been developed to view live video feedback obtained from the onboard cameras to control the UGV accordingly. Different features of UGV like path tracker (tracks its path on Google Maps), variable speed modes, battery indicator, camera switch and selector etc. are also managed in the GUI. The system has been developed so that, in future, it can easily be extended to a fully autonomous system.