Institution profile

University Of Dubai

Academic institutionasia · ae
Official website
Research library19linked papers
Opportunities0open roles
Selected work

Representative Papers

Prediction of bank transaction fraud using TabNet an adaptive deep learning architecture

Jul 20, 2026

This study addresses the critical need for high accuracy, interpretability, and scalability in online banking fraud detection by leveraging real-world transaction data from India. Through exploratory data analysis and SMOTE-based oversampling to mitigate class imbalance, the authors systematically evaluate five deep learning models: DNN, GRU, LSTM, 1D-CNN, and TabNet. Notably, they harness TabNet’s intrinsic sparse feature selection mechanism to simultaneously enhance model interpretability and generalization. Experimental results demonstrate that TabNet achieves a 97.39% accuracy and a 0.9739 ROC-AUC under three-fold cross-validation, significantly outperforming baseline models. The approach effectively reduces both false positives and false negatives, supports real-time deployment, and satisfies stringent financial regulatory requirements for model transparency.

0 citationsRead paper

An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations

Jun 26, 2026

This study addresses the challenge of ineffective response to noisy energy consumption alerts in office building equipment monitoring by non-expert personnel. The authors propose an end-to-end agent pipeline that integrates hybrid SSA-LSTM time-series forecasting, attention-enhanced LSTM-VAE for variational anomaly detection, and a three-stage LangChain agent framework (Context/Diagnosis/Report). By incorporating RAG with a dynamic retrieval mechanism, the system reduces context sources from six to three–six while maintaining performance and improving inference efficiency. A novel reflective memory layer is introduced to establish a human-in-the-loop feedback cycle. Notably, the approach achieves 100% pass rates across all 16 anomaly scenarios on a local 7B large language model, with the best LLM backend scoring 90.4/100, significantly enhancing alert interpretability and maintenance prioritization capabilities.

0 citationsRead paper

DDF2Pol: A Dual-Domain Feature Fusion Network for PolSAR Image Classification

Apr 20, 2026

This study addresses the challenge of effectively integrating spatial and polarimetric information in polarimetric synthetic aperture radar (PolSAR) image classification by proposing a lightweight dual-domain convolutional network. The method introduces, for the first time, parallel real-valued and complex-valued convolutional streams to simultaneously capture complementary spatial structural and polarimetric scattering characteristics. Enhanced by depthwise convolutions and coordinate attention mechanisms, the model achieves superior feature representation with only 91,371 parameters. It attains overall classification accuracies of 98.16% and 96.12% on the Flevoland and San Francisco datasets, respectively, significantly outperforming current state-of-the-art approaches. These results demonstrate that the proposed dual-domain fusion strategy effectively boosts classification performance while maintaining a compact model architecture.

0 citationsRead paper
Recent publications

Latest Papers

Prediction of bank transaction fraud using TabNet an adaptive deep learning architecture

Jul 20, 2026

This study addresses the critical need for high accuracy, interpretability, and scalability in online banking fraud detection by leveraging real-world transaction data from India. Through exploratory data analysis and SMOTE-based oversampling to mitigate class imbalance, the authors systematically evaluate five deep learning models: DNN, GRU, LSTM, 1D-CNN, and TabNet. Notably, they harness TabNet’s intrinsic sparse feature selection mechanism to simultaneously enhance model interpretability and generalization. Experimental results demonstrate that TabNet achieves a 97.39% accuracy and a 0.9739 ROC-AUC under three-fold cross-validation, significantly outperforming baseline models. The approach effectively reduces both false positives and false negatives, supports real-time deployment, and satisfies stringent financial regulatory requirements for model transparency.

0 citationsRead paper

An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations

Jun 26, 2026

This study addresses the challenge of ineffective response to noisy energy consumption alerts in office building equipment monitoring by non-expert personnel. The authors propose an end-to-end agent pipeline that integrates hybrid SSA-LSTM time-series forecasting, attention-enhanced LSTM-VAE for variational anomaly detection, and a three-stage LangChain agent framework (Context/Diagnosis/Report). By incorporating RAG with a dynamic retrieval mechanism, the system reduces context sources from six to three–six while maintaining performance and improving inference efficiency. A novel reflective memory layer is introduced to establish a human-in-the-loop feedback cycle. Notably, the approach achieves 100% pass rates across all 16 anomaly scenarios on a local 7B large language model, with the best LLM backend scoring 90.4/100, significantly enhancing alert interpretability and maintenance prioritization capabilities.

0 citationsRead paper

DDF2Pol: A Dual-Domain Feature Fusion Network for PolSAR Image Classification

Apr 20, 2026

This study addresses the challenge of effectively integrating spatial and polarimetric information in polarimetric synthetic aperture radar (PolSAR) image classification by proposing a lightweight dual-domain convolutional network. The method introduces, for the first time, parallel real-valued and complex-valued convolutional streams to simultaneously capture complementary spatial structural and polarimetric scattering characteristics. Enhanced by depthwise convolutions and coordinate attention mechanisms, the model achieves superior feature representation with only 91,371 parameters. It attains overall classification accuracies of 98.16% and 96.12% on the Flevoland and San Francisco datasets, respectively, significantly outperforming current state-of-the-art approaches. These results demonstrate that the proposed dual-domain fusion strategy effectively boosts classification performance while maintaining a compact model architecture.

0 citationsRead paper