A5078954154- Hate Speech and Cyberbullying Detection
- Spam and Phishing Detection
- Text and Document Classification Technologies
- Access Control and Trust
- Traffic Prediction and Management Techniques
- User Authentication and Security Systems
- Advanced Authentication Protocols Security
- IoT and Edge/Fog Computing
- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Technology and Security Systems
- Network Traffic and Congestion Control
- AI in cancer detection
- Network Security and Intrusion Detection
- Authorship Attribution and Profiling
- Advanced Text Analysis Techniques
- Natural Language Processing Techniques
- Software-Defined Networks and 5G
- Advanced Malware Detection Techniques
- Customer churn and segmentation
- Artificial Intelligence in Healthcare
- Advanced Graph Neural Networks
- Misinformation and Its Impacts
- Brain Tumor Detection and Classification
- Internet Traffic Analysis and Secure E-voting
University of Science and Technology Bannu
2018-2025
Institute of Management Sciences Peshawar
2018
National University of Modern Languages
2018
Kohat University of Science and Technology
2018
International Islamic University, Islamabad
2018
The University of Agriculture, Peshawar
2018
The growing need for facial emotion recognition in various domains, particularly online education, has driven advancements Artificial Intelligence (AI) and computer vision. Facial expressions are a vital source of nonverbal communication as they convey wide range emotions through subtle changes features. Recent developments Deep Learning (DL) Convolutional Neural Networks (CNNs) have opened new avenues analyzing interpreting human emotions. This study proposes novel CNN-based real-time...
The healthcare data are rapidly increasing, and protecting patient-sensitive information becomes challenging. This paper surveys the use of federated learning (FL) to address privacy in industry. FL is a decentralized machine (ML) approach, where ML process distributed across multiple devices, without relying on central server or coordinator. In recent years, has obtained significant attention, especially scenarios top concern. work attempts discover progress made so far regarding...
The Urdu language is spoken and written on different social media platforms like Twitter, WhatsApp, Facebook, YouTube. However, due to the lack of Language Processing (ULP) libraries, it quite challenging identify threats from textual sequential data provided in Urdu. Therefore, required preprocess as efficiently English by creating stemming cleaning libraries for data. Different lexical machine learning-based techniques are introduced literature, but all these limited unavailability online...
Internet is the most significant source of getting up thoughts, surveys for a product, and reviews any type service or activity. A Bulky amount are produced on daily basis cyberspace about online products objects. For example, many individuals share their remarks, feelings in own language utilizing social media networks such as twitter so on. Considering colossal Quantity size, it exceedingly knotty to look at with interpret specified surveys. Sentiment Analysis (SA) aims extracting people's...
Data quality is a critical aspect of data analytics since it directly influences the accuracy and effectiveness insights predictions generated from data. Artificial Intelligence (AI) schemes have grown in existing era technological advancement, which provides innovative exposure to healthcare applications. Reinforcement Learning (RL) subfield an influential Machine (ML) model aimed at optimizing decision-making by association with dynamic environments. In applications, RL can modify conduct...
The propagation of immoral content on social media poses substantial worries to online societal well-being and communication standards. While beneficial, traditional machine learning (ML) methods fall short capturing the difficulty textual sequential data. This work reports this gap by suggesting a deep learning-based technique for detecting posts media. proposed model presents fine-tuned Bidirectional Encoder representation from Transformers (BERT) with word embedding methods. Word2Vec...
The volume of data on the web is growing rapidly, due to proliferation news sources, contents, blogs and journals etc. Like other languages, Urdu language has also observed tremendous growth internet. As expanding, information retrieval (IR) becoming compli
Immoral posts detection on social media is a serious issue in this digital era. This matter wants advanced natural language processing (NLP) methods to address user-generated text's difficult semantics and context. Incorporating deep learning (DL) techniques improves the model's aptitude handle challenges such as slang, sarcasm, vague expressions. work suggests contextual analysis framework using self-attention-based transformer model detect immoral contents soil networks efficiently. The...
Opinion mining is an interesting area of research because its wide applications in the decision-making process. aims to extract user’s perception from text and create a fast accurate summary people’s opinion about anything. In this study, we have worked on target identification impact anaphora resolution extraction. Anaphora can be utilized detect sentences having prepositions instead nouns. We empirically evaluated using benchmark datasets. achieved accuracy such as precision: 88.14 recall:...
In the constantly developing realm of Internet Things (IoT), guaranteeing fast data transfer and a smooth user experience is critical. IoT contexts with limited resources, congestion control crucial for sustaining network performance. This study suggests new strategy improving by deploying Long Short-Term Memory (LSTM) networks. LSTMs are recurrent neural networks (RNN), that excel at capturing temporal relationships patterns in data. IoT-specific such as traffic patterns, device...
This study suggests a new strategy for improving congestion control by deploying Long Short-Term Memory (LSTM) networks. LSTMs are recurrent neural networks (RNN), that excel at capturing temporal relationships and patterns in data. IoT-specific data such as network traffic patterns, device interactions, occurrences gathered analyzed. The is used to create train an LSTM architecture specific the IoT environment. Then, model's predictive skills incorporated into methods. work intends optimize...