Muhammad Obaid Ullah

Muhammad Obaid Ullah

Auto-generated profile, based on publicly available information

Muhammad Obaid Ullah

Department of Electrical Engineering, University of Engineering and Technology, Taxila

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Advances in Civil Engineering
Verified
Journal Article
Open access
PDF file
MAMuhammad Haroon Asad
Muhammad Haroon Asad
SKSaran Khaliq
Saran Khaliq
MYMuhammad Haroon Yousaf
Muhammad Haroon Yousaf
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
Afaq AhmadAfaq Ahmad
Afaq Ahmad
Asphalt pavement distresses are the major concern of underdeveloped and developed nations for the smooth running of daily life commute. Among various pavement failures, numerous research can be found on pothole detection as they are injurious to automobiles and passengers that may turn into an accident. This work is intended to explore the potential of deep learning models and deploy three superlative deep learning models on edge devices for pothole detection. In this work, we have exploited the AI kit (OAK‐D) on a single‐board computer (Raspberry Pi) as an edge platform for pothole detection. Detailed real‐time performance comparison of state‐of‐the‐art deep learning models and object detection frameworks (YOLOv1, YOLOv2, YOLOv3, YOLOv4, Tiny‐YOLOv4, YOLOv5, and SSD‐mobilenetv2) for pothole detection is presented. The experimentation is performed on an image dataset with pothole in diverse road conditions and illumination variations as well as on real‐time video captured through a moving vehicle. The Tiny‐YOLOv4, YOLOv4, and YOLOv5 evince the highest mean average precision (mAP) of 80.04%, 85.48%, and 95%, respectively, on the image set, thus proving the strength of the proposed approach for pothole detection and deployed on OAK‐D for real‐time detection. The study corroborated Tiny‐YOLOv4 as the befitted model for real‐time pothole detection with 90% detection accuracy and 31.76 FPS.

11 March 2019 in IEEE Sensors Journal
Verified
Journal Article
Closed access
AMAqsa Mehreen
Aqsa Mehreen
SASyed Anwar
Syed Anwar
MHMuhammad Haseeb
Muhammad Haseeb
MMMuhammad Majid
Muhammad Majid
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
The problem addressed in this work is the detection of drowsiness based on signals acquired using noninvasive and wearable sensors. A combination of signals from electroencephalography (EEG) electrodes, accelerometer, and gyroscope is acquired through a commercially available off-theshelf headband to achieve this goal. The aim is to substitute the use of intrusive sensors and cameras by extracting both physiological and behavioral features for drowsiness detection using a lightweight wearable headband. A dataset is acquired from fifty volunteers using the MUSE headband for both fresh and drowsy behaviour in resting state, where subjects stare at a slow moving object on a screen and no external stimuli is used. The drowsy state is induced by sleep deprivation. The data is labelled subjectively using the Karolinska sleepiness scale. Complementary features extracted from spectral signals, head movement, and blink analysis are combined to form a feature vector for classifiers to improve the robustness and detection accuracy of the system. The implemented system is validated on the data collected in fresh and drowsy states using a leave-one-out cross-subject and 25% hold-out level testing. A detection accuracy of 92% is achieved using selected features and linear support vector machine classifier. The results show that the accuracy of drowsiness detection is improved by using a hybrid feature vector acquired from data using multiple sensors.

4 June 2021 in Energies
Verified
Journal Article
Open access
PDF file
BNBushra Nawaz
Bushra Nawaz
GAGHULAM ALI
GHULAM ALI
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
SRSarish Rehman
Sarish Rehman
FAFazal Abbas
Fazal Abbas
In this work, Ni0.5Zn0.5Fe2O4 is synthesized as binder-based (NZF) and binder-free electrodes (NZF@NF). The binder-free electrode is directly synthesized on nickel foam via facile hydrothermal techniques. The crystalline phase of both of these electrodes is examined through X-ray diffraction. Their morphology is investigated by scanning electron microscopy (SEM) and high-resolution transmission electron microscopy (TEM), which revealed the well-defined nanostructure with the shape like thin hexagonal platelets. The chemical composition is verified by energy dispersive spectroscopy (EDS). Their electrochemical properties are analyzed by cyclic voltammetry (CV), galvanostatic charge–discharge (GCD), and electrochemical impedance spectroscopy (EIS). The NZF@NF electrode has outperformed the binder-based NZF electrode in terms of electrochemical performance owing to the 3D interconnected structure of the nickel foam. The NZF@NF electrode has delivered a high specific capacity of 504 F g−1 at the current density of 1 A g−1, while its counterpart has delivered a specific capacity of 151 F g−1 at the same current density.

5 January 2023 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
ANAbdul Nasir
Abdul Nasir
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
MYMuhammad Haroon Yousaf
Muhammad Haroon Yousaf

1 June 2021 in Energies
Verified
Journal Article
Open access
PDF file
BNBushra Nawaz
Bushra Nawaz
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
GAGHULAM ALI
GHULAM ALI
Metallic oxides are considered promising candidates for supercapacitors owing to their inherent pseudocapacitive behavior and superior electrochemical properties. In this work, NiCo2O4, CuCo2O4, and CuCo2O4@NiCo2O4 composite electrodes are synthesized directly on a nickel foam substrate via the facile hydrothermal method. The phase of the prepared materials was analyzed using the X-ray diffraction method. The morphology of the prepared binder-free electrodes was observed by scanning electron microscopy. The electrochemical testing was done in a 2 M KOH solution against an Ag/AgCl reference electrode. The CuCo2O4@NiCo2O4 composite electrode demonstrated a value of specific capacitance as high as 422 F g−1 at a current density of 1 A g−1 and thus outperformed the NiCo2O4 and CuCo2O4 in terms of its electrochemical performance. The CuCo2O4@NiCo2O4 composite retained a specific capacitance of 278 F g−1 even with the increase of current density to 10 A g−1, which corresponds to a 34% loss of capacitance compared to 40% and 48% of individual NiCo2O4 and CuCo2O4 electrodes, respectively. Hence, the synergy in a composite material demonstrates it to be a potential candidate as an electrode in supercapacitors.

9 December 2022 in IEEE Access
Verified
Journal Article
Open access
KSKanwal Saeed
Kanwal Saeed
MUMuhammad Obaid Ullah
Muhammad Obaid Ullah
Software Defined Networking (SDN) makes it easy to control and manage the network due to a centralized control plane. However, this centralization also limits the scalability of SDN. To address this scalability issue, multiple controllers are deployed in the SDN. Placing multiple controllers poses several challenges, one of which is to find optimum locations for the placement of multiple controllers. The existing approaches for controller placement in a multiple-controller SDN environment overlook many aspects, like the path reliability for switch-to-controller and controller-to-controller communication, and the use of an efficient machine-learning algorithm. To address these issues, this paper proposes a novel approach, named as CMOPHA, that uses NSGA-II (a multi-objective optimization MOO algorithm) to compute the optimum placement of controllers based on the parameters of maximum switch-to-controller path reliability, and minimum value of switch-to-controller hop count, maximum controller-to-controller reliability, load-balancing among the controllers and a minimum number of controllers. We conduct simulations using real network traces. Based on the results, we show that CMOPHA improves the network performance in terms of end-to-end delay, hop count, computation time, and network availability compared to the existing state-of-the-art approach.