Muhammad Usman Shahid Khan
YOU?
Author Swipe
View article: Factors Affecting Service Delivery System at Local Level: An Analysis of KP Local Government System
Factors Affecting Service Delivery System at Local Level: An Analysis of KP Local Government System Open
Local government system, being closer to the people, is best suited for local development, better public management and service delivery. Efficient and functional service delivery system is contingent upon many factors like conducive envir…
View article: Social Media Profiling for Political Affiliation Detection
Social Media Profiling for Political Affiliation Detection Open
The notion of discerning political affiliations from users’ social media behavior instills a sense of unease in many. Democracy necessitates that individuals’ political affiliations remain private, and social media challenges this foundati…
View article: Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos
Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos Open
We evaluated our system’s performance on the UCF101 dataset
View article: Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos
Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos Open
We evaluated our system’s performance on the UCF101 dataset
View article: Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos
Selecting Loss-function for unseen (Out-of-distribution) Action Recognition in Videos Open
We evaluated our system’s performance on the UCF101 dataset
View article: Improved Open World Object Detection Using Class-Wise Feature Space Learning
Improved Open World Object Detection Using Class-Wise Feature Space Learning Open
Open-world object detection is a challenging set of tasks in the realm of computer vision. In these tasks, the object detection model processes the input image or video and undergoes inference to identify objects or features present in the…
View article: Explainable YouTube Video Identification Using Sufficient Input Subsets
Explainable YouTube Video Identification Using Sufficient Input Subsets Open
Neural network models are black boxes in nature. The mechanics behind these black boxes are practically unexplainable. Having the insight into patterns identified by these algorithms can help unravel important properties of the subject in …
View article: E-Ensemble: A Novel Ensemble Classifier for Encrypted Video Identification
E-Ensemble: A Novel Ensemble Classifier for Encrypted Video Identification Open
In recent years, video identification within encrypted network traffic has gained popularity for many reasons. For example, a government may want to track what content is being watched by its citizens, or businesses may want to block certa…
View article: Explainable Machine Learning for API Call Sequence Analysis
Explainable Machine Learning for API Call Sequence Analysis Open
Although deep learning achieves state-of-the-art performance in tasks like vulnerability detection and classification, they have drawbacks. A significant disadvantage of deep learning methods is their inexplicability. Many deep learning mo…
View article: Explainable Machine Learning for API Call Sequence Analysis
Explainable Machine Learning for API Call Sequence Analysis Open
Although deep learning achieves state-of-the-art performance in tasks like vulnerability detection and classification, they have drawbacks. A significant disadvantage of deep learning methods is their inexplicability. Many deep learning mo…
View article: Explainable Artificial Intelligence for API Call Sequence Analysis
Explainable Artificial Intelligence for API Call Sequence Analysis Open
Although deep learning achieves state-of-the-art performance in tasks like vulnerability detection and classification, they have drawbacks. A significant disadvantage of deep learning methods is their inexplicability. Many deep learning mo…
View article: A Bucket-Based Data Pre-Processing Method for Encrypted Video Detection
A Bucket-Based Data Pre-Processing Method for Encrypted Video Detection Open
As the number of video streaming platforms is growing, the risk factor associated with illegal and inappropriate content streaming is increasing exponentially. Therefore, mon- itoring such content is essential. Many researches have been co…
View article: SCNN-Attack: A Side-Channel Attack to Identify YouTube Videos in a VPN and Non-VPN Network Traffic
SCNN-Attack: A Side-Channel Attack to Identify YouTube Videos in a VPN and Non-VPN Network Traffic Open
Encryption Protocols e.g., HTTPS is utilized to secure the traffic between servers and clients for YouTube and other video streaming services, and to further secure the communication, VPNs are used. However, these protocols are not suffici…
View article: Fingerprinting Technique for YouTube Videos Identification in Network Traffic
Fingerprinting Technique for YouTube Videos Identification in Network Traffic Open
Recently, many video streaming services, such as YouTube, Twitch, and Facebook, have contributed to video streaming traffic, leading to the possibility of streaming unwanted and inappropriate content to minors or individuals at workplaces.…
View article: Beyond the Horizon, Backhaul Connectivity for Offshore IoT Devices
Beyond the Horizon, Backhaul Connectivity for Offshore IoT Devices Open
The prevalent use of the Internet of Things (IoT) devices over the Sea, such as, on oil and gas platforms, cargo, and cruise ships, requires high-speed connectivity of these devices. Although satellite based backhaul links provide vast cov…
View article: Adadb: Adaptive Diff-Batch Optimization Technique for Gradient Descent
Adadb: Adaptive Diff-Batch Optimization Technique for Gradient Descent Open
Gradient descent is the workhorse of deep neural networks. Gradient descent has the disadvantage of slow convergence. The famous way to overcome slow convergence is to use momentum. Momentum effectively increases the learning factor of gra…
View article: HateClassify: A Service Framework for Hate Speech Identification on Social Media
HateClassify: A Service Framework for Hate Speech Identification on Social Media Open
It is indeed a challenge for the existing machine learning approaches to segregate the hateful content from the one that is merely offensive. One prevalent reason for low accuracy of hate detection with the current methodologies is that th…
View article: A Cost-Effective Electric Vehicle Intelligent Charge Scheduling Method for Commercial Smart Parking Lots Using a Simplified Convex Relaxation Technique
A Cost-Effective Electric Vehicle Intelligent Charge Scheduling Method for Commercial Smart Parking Lots Using a Simplified Convex Relaxation Technique Open
Deployment of efficient and cost-effective parking lots is a known bottleneck for the electric vehicles (EVs) sector. A comprehensive solution incorporating the requirements of all key stakeholders is required. Taking up the challenge, we …
View article: Machine Learning Based Energy Management Model for Smart Grid and Renewable Energy Districts
Machine Learning Based Energy Management Model for Smart Grid and Renewable Energy Districts Open
The combination of renewable energy sources and prosumer-based smart grid is a sustainable solution to cater to the problem of energy demand management. A pressing need is to develop an efficient Energy Management Model (EMM) that integrat…
View article: Requirement Validation for Embedded Systems in Automotive Industry Through Modeling
Requirement Validation for Embedded Systems in Automotive Industry Through Modeling Open
Requirement validation contributes significantly toward the success of software projects. Validating requirements is also essential to ensure the correctness of embedded systems in the auto industry. The auto industry emphasizes a lot on t…
View article: An Adaptive Distributed Averaging Integral Control Scheme for Micro-Grids With Renewable Intermittency and Varying Operating Cost
An Adaptive Distributed Averaging Integral Control Scheme for Micro-Grids With Renewable Intermittency and Varying Operating Cost Open
The increasing penetration of intermittent renewable energy resources in micro-grids poses several issues, such as stochastic power generation, demand and supply miss-match, frequency fluctuation, and economic dispatch problems. To address…
View article: Adaptive Filtering on GPS-Aided MEMS-IMU for Optimal Estimation of Ground Vehicle Trajectory
Adaptive Filtering on GPS-Aided MEMS-IMU for Optimal Estimation of Ground Vehicle Trajectory Open
Fusion of the Global Positioning System (GPS) and Inertial Navigation System (INS) for navigation of ground vehicles is an extensively researched topic for military and civilian applications. Micro-electro-mechanical-systems-based inertial…
View article: Emergency Auxiliary Services: A Bi-Directional Mutual Beneficial Framework for Power Systems and Data Centers
Emergency Auxiliary Services: A Bi-Directional Mutual Beneficial Framework for Power Systems and Data Centers Open
The power transmission networks face an increased electrical load at times and locations. This situation gives rise to the problem of demand/supply mismanagement. Therefore, the power systems need fast auxiliary services to keep power mana…
View article: Towards Achieving Machine Comprehension Using Deep Learning on Non-GPU Machines
Towards Achieving Machine Comprehension Using Deep Learning on Non-GPU Machines Open
Long efforts have been made to enable machines to understand human language. Nowadays such activities fall under the broad umbrella of machine comprehension. The results are optimistic due to the recent advancements in the field of machine…
View article: Student Feedback Sentiment Analysis Model Using Various Machine Learning Schemes A Review
Student Feedback Sentiment Analysis Model Using Various Machine Learning Schemes A Review Open
Objectives: The study has been carried out to present the sentiment analysis model for improving the quality of teaching in academic institutions, particularly at universities. The purpose of this study is to explore the different machine …
View article: Towards a Fog Enabled Efficient Car Parking Architecture
Towards a Fog Enabled Efficient Car Parking Architecture Open
The automotive industry is growing day by day and personal vehicles have become a significant transportation resource now. With the rise in private transportation vehicles, getting a free space for parking one's car, especially in populate…
View article: SocialRec: A Context-Aware Recommendation Framework With Explicit Sentiment Analysis
SocialRec: A Context-Aware Recommendation Framework With Explicit Sentiment Analysis Open
In recent years, recommendation systems have seen significant evolution in the field of knowledge engineering. Usually, the recommendation systems match users' preferences based on the star ratings provided by the users for various product…
View article: An Optimal Ride Sharing Recommendation Framework for Carpooling Services
An Optimal Ride Sharing Recommendation Framework for Carpooling Services Open
Carpooling services allow drivers to share rides with other passengers. This helps in reducing the passengers' fares and time, as well as traffic congestion and increases the income for drivers. In recent years, several carpooling-based re…