- Metaheuristic Optimization Algorithms Research
- Autonomous Vehicle Technology and Safety
- Text and Document Classification Technologies
- Machine Learning and Data Classification
- Advanced Multi-Objective Optimization Algorithms
- Sentiment Analysis and Opinion Mining
- Service-Oriented Architecture and Web Services
- Face and Expression Recognition
- Robotics and Automated Systems
- Imbalanced Data Classification Techniques
- Mobile Health and mHealth Applications
- Hate Speech and Cyberbullying Detection
- Social Robot Interaction and HRI
- Complex Network Analysis Techniques
- Robotic Path Planning Algorithms
- Smart Parking Systems Research
- Distributed and Parallel Computing Systems
- Evolutionary Algorithms and Applications
- Data Stream Mining Techniques
- Cognitive Radio Networks and Spectrum Sensing
- Technology Use by Older Adults
- Stroke Rehabilitation and Recovery
- Video Surveillance and Tracking Methods
- Power Line Communications and Noise
- Transportation and Mobility Innovations
Mirpur University of Science and Technology
2012-2022
University of Malaya
2020-2022
National University of Computer and Emerging Sciences
2010
Purpose Research on sentiment analysis were mostly conducted product and services, resulting in scarcity of studies focusing social issues, which may require different mechanisms due to the nature issue itself. This paper aims address this gap by developing an enhanced lexicon-based approach. Design/methodology/approach An approach was employed using General Inquirer, incorporated with multi-level grammatical dependencies role verb. Data illegal immigration gathered from Twitter for a period...
Gender classification problem is an active area of research; recently it had attracted many researchers. This study presents efficient gender technique. Weighted Majority Voting (WMV) the most popular technique used to combine individual classifiers in ensemble based classification. Genetic Algorithm (GA) a global optimization and being widely by researchers last four decades. In this paper optimized combination obtained using for The proposed method tested on Stanford university medical...
Rear-end collision detection and avoidance is one of the most crucial driving tasks self-driving vehicles. Mathematical models fuzzy logic-based methods have recently been proposed to improve effectiveness rear-end systems in autonomous vehicles (AVs). However, these methodologies do not tackle real-time object response problems dense/dynamic road traffic conditions due their complex computation decision-making structures. In our previous work, we presented an affective computing-inspired...
Clustering is a popular machine learning technique used to segregate the number of objects into different classes. Locating multiple peaks multimodal problem challenging task. In this regard, clustering considered be best that divides population clusters. literature, techniques have been suggested with particle swarm optimization (PSO) algorithm. Among techniques, partition-based widely PSO solve problems. This paper provides brief survey clustering-based for solving Open problems discussed...
The discounted {0-1} knapsack problem (D{0-1}KP) is a multi-constrained optimization and an extended form of the 0-1 problem. DKP composed set item batches where each batch has three items objective to maximize profit by selecting at most one from batch. Therefore, D{0-1}KP complex found many applications in real economic problems other areas concept promotional discounts exists. As belongs binary class problem, so novel particle swarm variant with modifications proposed this paper....
Acceleration coefficients are the key parameters of particle swarm optimization (PSO) algorithm used to control movement particles by modifying its cognitive and social components. Several variants have been proposed that modify acceleration improve convergence speed PSO in continuous search space. In this regard, a few attentions paid binary (BPSO). Moreover, presence distinct position ignoring dispersion space, BPSO deals all equally. To address issue, we fitness-based Novel BPSO, called...
According to the report of world health organization (WHO), about 1.27 million people lost their lives in 2009 due road accidents and it was ninth foremost reason deaths. The vehicle-to-vehicle communication system (V2V) is one solutions dwindle accident ratios. existing V2Vs are fixed based on single radio inept erratic especially hilly areas low SNR partial coverage. Their performance degraded metropolitans crowded population over-burdened traffic routes. Keeping above disadvantages mind,...
Technology offers new opportunities in healthcare to manage chronic conditions cost-effectively. In the adoption of mHealth services, one main barriers is usability, especially for users having limitations or special needs, such as elderly. Unlike apps specifically designed elderly monitor and cardio-vascular health, diabetes, hypertension, there a lack research pain management, including usability evaluation. Moreover, comprehensive evaluation tool. This focuses on formulation assessment...
With the rapid emergence of autonomous vehicles, there is a need to build such communication systems which help passengers communicate with vehicles (AVs) robustly. In this regard, research work presents multimodal passenger system. The communica-tion system known as “buddy" for AVs. Buddy an all in one control AVs incorporates touch, speech, text, and emotion recognition methods interaction. makes it easy interact It enables between AV eventually provides safe driving experience. Moreover,...
It is worthwhile to point out the fact that nature of given data plays considerable role in classifying accurately. To select an appropriate classifier for certain type data, we are required understand behavior classifiers on different characteristics. The varying dimensions, number instances, class labels, correlation, and distribution classes, might characterize data. In this study, performance five supervised machine learning classification techniques have been investigated using six real...
Information technology has started focusing on the healthcare enterprises, for providing better medical care. There exist different enterprise standards that are used communication of information across health enterprises swift and reliable results. HL7 is one those exchange between systems. The main focus this research work to make metadata processing efficient in v3. v3 an emerging standard achieve semantic interoperability with its well defined models like reference model (RIM), domain...