- Topic Modeling
- Advanced Text Analysis Techniques
- Natural Language Processing Techniques
- Sentiment Analysis and Opinion Mining
- Expert finding and Q&A systems
- Privacy-Preserving Technologies in Data
- Complex Network Analysis Techniques
- Opportunistic and Delay-Tolerant Networks
- Internet Traffic Analysis and Secure E-voting
- Privacy, Security, and Data Protection
- Spam and Phishing Detection
- Energy and Environment Impacts
- IoT and Edge/Fog Computing
- Misinformation and Its Impacts
- Semantic Web and Ontologies
- Mobile Ad Hoc Networks
- Hate Speech and Cyberbullying Detection
- Biomedical Text Mining and Ontologies
- Wireless Body Area Networks
- Thermochemical Biomass Conversion Processes
- Data Quality and Management
- Cell Image Analysis Techniques
- Extracellular vesicles in disease
- Mobile Crowdsensing and Crowdsourcing
- Smart Systems and Machine Learning
Islamia College University
2017-2025
University of Louisiana at Lafayette
2025
Newcastle University
2022-2023
University of Engineering and Technology Lahore
2018-2023
National University of Sciences and Technology
2021
Infosys (India)
2015-2021
Gomal University
2021
University of Waterloo
2012-2020
University of Technology Malaysia
2014-2016
Mid Yorkshire Hospitals NHS Trust
2011
Agricultural food production is projected to be 70% higher by 2050 than it today, with the world population rising more 9 billion, 34% now. The farmers have been forced produce same resources. This pressure means that optimizing productivity one of main objectives producers but also in a sustainable way. Not only does agriculture face decline production, has had limitations data collection, storing, securing, and sharing, climate change, increases input prices, traditional supply chain...
Software defect prediction (SDP) in the initial period of software development life cycle (SDLC) remains a critical and important assignment. SDP is essentially studied during few last decades as it leads to assure quality systems. The quick forecast defective or imperfect artifacts may serve team use existing assets competently more effectively provide extraordinary products given narrow time. Previously, several canvassers have industrialized models for utilizing machine learning (ML)...
Acute Myeloid Leukemia (AML) is a kind of fatal blood cancer with high death rate caused by abnormal cells’ rapid growth in the human body. The usual method to detect AML manual microscopic examination sample, which tedious and time‐consuming requires skilled medical operator for accurate detection. In this work, we proposed an AlexNet‐based classification model images compared its performance LeNet‐5‐based Precision, Recall, Accuracy, Quadratic Loss. experiments are conducted on dataset...
Social media applications, such as Twitter and Facebook, allow users to communicate share their thoughts, status updates, opinions, photographs, videos around the globe. Unfortunately, some people utilize these platforms disseminate hate speech abusive language. The growth of may result in crimes, cyber violence, substantial harm cyberspace, physical security, social safety. As a result, detection is critical issue for both cyberspace society, necessitating development robust application...
The widespread use of the Internet and tremendous growth social media have enabled people to connect with each other worldwide. Individuals are free express themselves online, sharing their photos, videos, text messages globally. However, such freedom sometimes leads misuse, as some individuals exploit this platform by posting hateful abusive comments on forums. proliferation language negatively impacts groups, leading emotional distress affecting mental health. It is crucial automatically...
With the increased usage of Web 2.0 and data-affluent tools such as social media platforms web blog services, challenge extracting public sentiment disseminating personal health information has become more common than ever in last decade. This paper proposes a novel model for Dengue disease detection based on posts alone. The does not access any people or medical record. extracts presence patients infected with tweets only decides whether it is general discussion about disease, no one...
Over the last two decades, social media platforms have grown dramatically. Twitter and Facebook are most popular platforms, with millions of active users posting billions messages daily. These allow to freedom expression. However, some exploit this facility by disseminating hate speeches. Manual detection censorship such speeches impractical; thus, an automatic mechanism is required detect counter in a real-time environment. Most research speech has been carried out English language. Still,...
In the recent era, a liver syndrome that causes any damage in life capacity is exceptionally normal everywhere throughout world. It has been found disease exposed more young people as comparison with other aged people. At point when ends up, endures just up to 1 or 2 days scarcely, and it very hard predict such illness early stage. Researchers are trying project model for prediction of utilizing various machine learning approaches. However, this study compares ten classifiers including A1DE,...
Nowadays, online product reviews have been at the heart of assessment process for a company and its customers. They give feedback to on improving quality, planning, monitoring business schemes in order increase sale gain more profit. are also helpful customers select right products less effort time. Most companies make spam sales Detecting is challenging issue NLP (natural language processing). Numerous machine learning approaches attempted detect classify as or nonspam. However, improve...
Seasonal outbreaks have several different periods that occur primarily during winter in temperate regions, while influenza may throughout the year tropical triggering more irregularly. Similarly, dengue occurs star of rainy season early May and reaches its peak late June. Dengue flu brought an impact on various countries years 2017–2019 streaming Twitter data reveals status most affected regions. This research work presents Social Media Analysis (SMA) can be used as a detector epidemic...
Abstract The shear strength of reinforced concrete members with or without reinforcement is influenced by the span to effective depth and longitudinal tensile ratios. In high-strength concrete, if paste has a higher than aggregates, then propagation cracks possible through aggregates rather around may fail brittle failure, which against most guideline’s philosophies. This paper investigates experimentally influence shear-span ratio ratios on behavior HSC beams having no reinforcement. A...
Abstract Advanced technology such as gamma radiation has various applications but also poses a threat to the environment well living organisms. The development of effective methods for shielding against these radiations is crucial mitigate their intensity. Therefore, current investigation attempted enhance capability concrete by replacing normal aggregate with magnetite collected from Swat district, Pakistan. A sample (treated samples) was prepared considering seven different values...
Cement production is a major contributor to global CO2 emissions, necessitating the development of sustainable alternatives such as fiber-reinforced concrete incorporating supplementary cementing materials (SCMs) and agricultural waste. This approach keeps environment safe by reducing consumption conventional raw for production. Incorporating SCMs in can potentially improve mechanical durability properties. research evaluated behavior mixtures using different proportions natural wheat straw...
With the growing information on web, online movie review is becoming a significant resource for Internet users. However, users post thousands of reviews daily basis and it hard them to manually summarize reviews. Movie mining summarization one challenging tasks in natural language processing. Therefore, an automatic approach desirable lengthy reviews, will allow quickly recognize positive negative aspects movie. This study employs feature extraction technique called bag words (BoW) extract...
The explosive growth of social networks in recent times has presented a powerful source information to be utilized as an extra for assisting the recommendation problems. methods that are based on probabilistic matrix factorization improved accuracy and partly solved cold-start data sparsity However, these only exploited explicit relations almost completely ignored implicit relations. In this article, we firstly propose algorithm extract relation undirected graphs by exploiting link...