Alert button
Picture for Efstratios Kakaletsis

Efstratios Kakaletsis

Alert button

Deep Learning for Energy Time-Series Analysis and Forecasting

Jun 29, 2023
Maria Tzelepi, Charalampos Symeonidis, Paraskevi Nousi, Efstratios Kakaletsis, Theodoros Manousis, Pavlos Tosidis, Nikos Nikolaidis, Anastasios Tefas

Figure 1 for Deep Learning for Energy Time-Series Analysis and Forecasting
Figure 2 for Deep Learning for Energy Time-Series Analysis and Forecasting
Figure 3 for Deep Learning for Energy Time-Series Analysis and Forecasting
Figure 4 for Deep Learning for Energy Time-Series Analysis and Forecasting

Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future. Different tasks are involved in the general field of energy time-series analysis and forecasting, with electric load demand forecasting, personalized energy consumption forecasting, as well as renewable energy generation forecasting being among the most common ones. Following the exceptional performance of Deep Learning (DL) in a broad area of vision tasks, DL models have successfully been utilized in time-series forecasting tasks. This paper aims to provide insight into various DL methods geared towards improving the performance in energy time-series forecasting tasks, with special emphasis in Greek Energy Market, and equip the reader with the necessary knowledge to apply these methods in practice.

* 13 papges, 4 figures 
Viaarxiv icon

Potential UAV Landing Sites Detection through Digital Elevation Models Analysis

Jul 14, 2021
Efstratios Kakaletsis, Nikos Nikolaidis

Figure 1 for Potential UAV Landing Sites Detection through Digital Elevation Models Analysis
Figure 2 for Potential UAV Landing Sites Detection through Digital Elevation Models Analysis
Figure 3 for Potential UAV Landing Sites Detection through Digital Elevation Models Analysis
Figure 4 for Potential UAV Landing Sites Detection through Digital Elevation Models Analysis

In this paper, a simple technique for Unmanned Aerial Vehicles (UAVs) potential landing site detection using terrain information through identification of flat areas, is presented. The algorithm utilizes digital elevation models (DEM) that represent the height distribution of an area. Flat areas which constitute appropriate landing zones for UAVs in normal or emergency situations result by thresholding the image gradient magnitude of the digital surface model (DSM). The proposed technique also uses connected components evaluation on the thresholded gradient image in order to discover connected regions of sufficient size for landing. Moreover, man-made structures and vegetation areas are detected and excluded from the potential landing sites. Quantitative performance evaluation of the proposed landing site detection algorithm in a number of areas on real world and synthetic datasets, accompanied by a comparison with a state-of-the-art algorithm, proves its efficiency and superiority.

* Proceedings of the 2019 27th European Signal Processing Conference (EUSIPCO) satellite workshop "Signal Processing Computer vision and Deep Learning for Autonomous Systems" 
Viaarxiv icon