Ioannis E. Livieris

VLDB 2026 Research / reviewers in the wild / expert

dblp:16/7838 · DBLP profile ↗

← Back

18ranked-venue papers

10as first author

10since 2021 · last 2026

0000-0002-3996-3301ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 17 · 10 first-author · 10 since 2021Systems, architecture and hardware · 1

Year	Publication	Venue	Position
2026	C-XGBoost model with targeted regularization for treatment effect estimation Niki Kiriakidou, Ioannis E. Livieris, Christos Diou	Neural Comput. Appl.	2
2025	Convolutional neural network framework for deepfake detection: A diffusion-based approach Emmanuel Pintelas, Ioannis E. Livieris	Comput. Vis. Image Underst.	2
2025	Researching the detection of continuous gravitational waves based on signal processing and ensemble learning Emmanuel Pintelas, Ioannis E. Livieris, Panayiotis E. Pintelas	Neural Comput. Appl.	2
2024	Adaptive augmentation framework for domain independent few shot learning Emmanuel Pintelas, Ioannis E. Livieris, Panayiotis E. Pintelas	Knowl. Based Syst.	2
2024	Mutual information-based neighbor selection method for causal effect estimation Niki Kiriakidou, Ioannis E. Livieris, Panayiotis E. Pintelas	Neural Comput. Appl.	2
2023	A multi-view-CNN framework for deep representation learning in image classification Emmanuel Pintelas, Ioannis E. Livieris, Sotiris B. Kotsiantis, Panayiotis E. Pintelas	Comput. Vis. Image Underst.	2
2023	A novel forecasting strategy for improving the performance of deep learning models Ioannis E. Livieris	Expert Syst. Appl.	1
2022	A novel multi-step forecasting strategy for enhancing deep learning models' performance Ioannis E. Livieris, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2021	Smoothing and stationarity enforcement framework for deep learning time-series forecasting Ioannis E. Livieris, Stavros Stavroyiannis, Lazaros S. Iliadis, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2021	A novel explainable image classification framework: case study on skin cancer and plant disease prediction Emmanuel Pintelas, Meletis Liaskos, Ioannis E. Livieris, Sotiris B. Kotsiantis, Panayiotis E. Pintelas	Neural Comput. Appl.	3
2020	An advanced active set L-BFGS algorithm for training weight-constrained neural networks Ioannis E. Livieris	Neural Comput. Appl.	1
2020	An improved weight-constrained neural network training algorithm Ioannis E. Livieris, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2020	A CNN-LSTM model for gold price time-series forecasting Ioannis E. Livieris, Emmanuel Pintelas, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2020	A novel validation framework to enhance deep learning models in time-series forecasting Ioannis E. Livieris, Stavros Stavroyiannis, Emmanuel Pintelas, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2019	An adaptive nonmonotone active set - weight constrained - neural network training algorithm Ioannis E. Livieris, Panayiotis E. Pintelas	Neurocomputing	1
2019	Improving the evaluation process of students' performance utilizing a decision support software Ioannis E. Livieris, Theodore Kotsilieris, Vassilis Tampakas, Panayiotis E. Pintelas	Neural Comput. Appl.	1
2017	DSS-PSP - A Decision Support Software for Evaluating Students' Performance Ioannis E. Livieris, Konstantina Drakopoulou, Theodore Kotsilieris, Vassilis Tampakas, Panayiotis E. Pintelas	EANN	1
2009	A memoryless BFGS neural network training algorithm abstract We present a new curvilinear algorithmic model for training neural networks which is based on a modifications of the memoryless BFGS method that incorporates a curvilinear search. The proposed model exploits the nonconvexity of the error surface based on information provided by the eigensystem of memoryless BFGS matrices using a pair of directions; a memoryless quasi-Newton direction and a direction of negative curvature. In addition, the computation of the negative curvature direction is accomplished by avoiding any storage and matrix factorization. Simulations results verify that the proposed modification significantly improves the efficiency of the training process. M. S. Apostolopoulou, Dimitris G. Sotiropoulos, Ioannis E. Livieris, Panayiotis E. Pintelas	INDIN	3