Kemal Polat
17 Papers
Kemal Polat is an academic researcher. The author has contributed to research in topics: Computer science & Trajectory. The author has an hindex of 1, co-authored 2 publications.
Chat about Author
Papers
Similarity attributed knowledge graph embedding enhancement for item recommendation
TL;DR: SAGE as discussed by the authors constructs entity-relevance-based Similarity-attributed Subgraph (ESS) to remove noise from the underlying data, and simultaneously utilizes feedbacks to enhance the interactions and regularize the model to highlight influential targets (nodes).
21
Robust underwater image enhancement with cascaded multi-level sub-networks and triple attention mechanism.
TL;DR: A novel network called Cascaded Network with Multi-level Sub-nets (CNMS), which selectively cascades multiple sub-networks through triple attention modules to extract distinct features from underwater images, bolstering the network's robustness and improving generalization capabilities.
19
TANet: Transmission and atmospheric light driven enhancement of underwater images
Dehuan Zhang,Yakun Guo,Jingchun Zhou,Wei-shi Zhang,Zifan Lin,Kemal Polat,Fayadh Alenezi,Adi Alhudhaif +7 more
TL;DR: This study proposes TANet, a novel approach for enhancing underwater images by integrating transmission-driven refinement and atmospheric light removal modules, leveraging localized transmission analysis and global atmospheric light extraction to improve image quality and visibility.
6
An ensemble learning approach for resampling forgery detection using Markov process
R. Mehta,K. Kumar,Adi Alhudhaif,Fayadh Alenezi,Kemal Polat +4 more
TL;DR: This paper proposes an ensemble learning approach for resampling forgery detection using Markov features in spatial and DCT domains, achieving 99.12% accuracy with bicubic interpolation and 0.44% error probability, outperforming prior techniques with single SVM classification.
4
A knowledge-driven graph convolutional network for abnormal electrocardiograph diagnosis
Zhaoyang Ge,Huiqing Cheng,Zhuang Tong,Ziyang He,Adi Alhudhaif,Kemal Polat,Mingliang Xu +6 more
TL;DR: This study proposes a knowledge-driven graph convolutional network, ECG-KG, for abnormal electrocardiogram diagnosis, leveraging expert knowledge to improve classification accuracy and outperform existing models on benchmark datasets.
3