Muhammad Habib Ullah

Muhammad Habib Ullah

Auto-generated profile, based on publicly available information

Muhammad Habib Ullah

National Research Council of Italy (CNR), Institute for Electromagnetic Sensing of the Environment (IREA), Naples, Italy

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
28 August 2024 in IEEE Access
Verified
Journal Article
Open access
Elio MasciariElio Masciari
Elio Masciari
AUAreeba Umair
Areeba Umair
MUMuhammad Habib Ullah
Muhammad Habib Ullah
With the rise of social media, individuals face challenges in decision-making due to the abundance of options available. Recommender Systems (RSs) leverage Artificial Intelligence (AI) to provide users with personalized suggestions aligned with their preferences and interests. This study presents a systematic review of AI-based Recommender Systems, focusing on recent advancements and primary studies published between 2019 and 2024. While several review papers have addressed various aspects of RSs, the rapid evolution of AI techniques necessitates an updated review to capture the latest trends and innovations. We systematically gathered data from five major databases: IEEE, Springer, Science Direct, ACM, and Wiley. Through the PRISMA methodology, we selected 85 relevant studies. Our analysis addresses several key research questions: the types of datasets and data sources used, major application fields, prevalent machine learning and AI techniques, overall research productivity, and the limitations and future trends in AI-based RSs. Our findings indicate that advanced AI techniques, particularly those incorporating deep learning with multiple hidden layers and transformer models like BERT, significantly enhance the accuracy and effectiveness of Recommender Systems. Furthermore, we observed a trend towards integrating contextual and real-time data to improve recommendation relevance. Additionally, we discuss ethical considerations such as privacy, data security, bias, and transparency, emphasizing the need for responsible AI development to ensure fair and equitable recommendations. These insights can guide future research and development efforts in the field.

20 November 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AUAreeba Umair
Areeba Umair
MSMuhammad Shahzad Sarfraz
Muhammad Shahzad Sarfraz
Muhammad AhmadMuhammad Ahmad
Muhammad Ahmad
UHUsman Habib
Usman Habib
MUMuhammad Habib Ullah
Muhammad Habib Ullah
Manuel MazzaraManuel Mazzara
Manuel Mazzara
In today’s world, security is the most prominent aspect which has been given higher priority. Despite the rapid growth and usage of digital devices, lucrative measurement of crimes in under-developing countries is still challenging. In this work, unstructural crime data (900 records) from the news archives of the previous eight years were extracted to predict the behavior of criminals’ networks and transform it into useful information using natural language processing (NLP). To estimate the next move of criminals in Pakistan, we performed hotspot-based spatial analysis. Later, this information is fed to two different classifiers for possible identification and prediction. We achieved the maximum accuracy of 92% using K-Nearest Neighbor (KNN) and 62% using the Random Forest algorithm. In terms of crimes, the results showed that the most prevalent crime events are robberies. Thus, the usage of digital information archives, spatial analysis, and machine learning techniques can open new ways of handling a peaceful and sustainable society in eradicating crimes for countries having paucity of financial resources.

17 April 2026 in IEEE Access
Verified
Journal Article
Open access
AUAreeba Umair
Areeba Umair
Elio MasciariElio Masciari
Elio Masciari
MUMuhammad Habib Ullah
Muhammad Habib Ullah
This paper introduces CONV_GBERT, a hybrid deep learning framework for robust sentiment classification. The model integrates the bidirectional contextual understanding of BERT, the generative capabilities of GPT, and the local feature extraction strength of convolutional neural networks. By concatenating embeddings from BERT and GPT and passing them through a convolutional layer, CONV_GBERT captures both global semantic meaning and fine-grained sentiment patterns in text. To further enhance robustness and generalization, we incorporate Improved Fast Gradient Sign Method (IMP-FGSM) for adversarial training. IMP-FGSM introduces controlled perturbations to the input embeddings and iteratively refines them using gradient-based updates. This technique improves the model’s resistance to adversarial attacks while preserving valid token boundaries. Experiments on benchmark sentiment datasets demonstrate that CONV_GBERT significantly outperforms baseline models. It achieves an accuracy of 84.89%, precision of 83.67%, recall of 82.88%, and an F1 score of 83.37%. These results highlight the potential of combining multiple transformer-based architectures and adversarial training to advance sentiment analysis in complex, noisy, and dynamic textual environments.