A5041531122- Advanced Control Systems Optimization
- Fault Detection and Control Systems
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Neural Networks and Applications
- Blind Source Separation Techniques
- Crystallization and Solubility Studies
- Emotion and Mood Recognition
- Advanced Neural Network Applications
- Control Systems and Identification
- Advanced Control Systems Design
- Advanced Memory and Neural Computing
- Target Tracking and Data Fusion in Sensor Networks
- Wireless Signal Modulation Classification
- Neural Networks and Reservoir Computing
- Model Reduction and Neural Networks
- Remote Sensing and LiDAR Applications
- Speech and Audio Processing
- Advanced Algorithms and Applications
- Face and Expression Recognition
- 3D Surveying and Cultural Heritage
- Archaeological Research and Protection
- Robot Manipulation and Learning
- Radar Systems and Signal Processing
- AI in cancer detection
University of Aveiro
2014-2024
Instituto de Telecomunicações
2021-2024
National University "Yuri Kondratyuk Poltava Polytechnic"
2024
University of Life Sciences in Lublin
2024
National Technical University "Kharkiv Polytechnic Institute"
2024
Institute of Electronics
2024
Institute of General and Inorganic Chemistry
2012-2018
Uppsala University
2018
Technical University of Sofia
2002-2016
Bulgarian Academy of Sciences
1999-2012
Abstract Building integrated photovoltaics is a promising strategy for solar technology, in which luminescent concentrators (LSCs) stand out. Challenges include the development of materials sunlight harvesting and conversion, an iterative optimization process with several steps: synthesis, processing, structural optical characterizations before considering energy generation figures merit that requires prototype fabrication. Thus, simulation models provide valuable, cost-effective,...
Abstract Building-integrated photovoltaics (BIPV) is an emerging technology in the solar energy field. It involves using luminescent concentrators to convert traditional windows into generators by utilizing light harvesting and conversion materials. This study investigates application of machine learning (ML) advance fundamental understanding optical material design. By leveraging accessible photoluminescent measurements, ML models estimate properties, streamlining process developing novel...
Accurate material description is crucial to achieve high-quality results in computational analysis software. Phenomenological constitutive laws generalize the behaviour observed simple mechanical tests. The resulting empirical expressions contain parameters that need be calibrated through an inverse optimization process. Advancements Digital Image Correlation (DIC) techniques have enabled extraction of non-uniform multi-axial displacement fields, facilitating development heterogeneous...
Accurate numerical simulations require constitutive models capable of providing precise material data. Several calibration methodologies have been developed to improve the accuracy models. Nevertheless, a model’s performance is always constrained by its mathematical formulation. Machine learning (ML) techniques, such as artificial neural networks (ANNs), potential overcome these limitations. use ML for modelling very recent and not fully explored. Difficulties related data requirements...
A large number of vision sensors has been proposed for enabling self-driving vehicles to perceive their surroundings. Among them, Light Detection And Ranging (LiDAR) presents the unique advantage acquiring a high resolution 3D representation vehicle surroundings, in form point clouds, which enables accurate object detection. The success first (and current) generation LiDARs motivated development second this sensor, now based on coherent Second thus enable not only estimating radial distance,...
Three adaptive neural network control structures to regulate a biological wastewater treatment process are introduced: indirect, inverse model, and direct control. The objective is keep the concentration of recycled biomass proportional influent flow rate in presence periodically acting disturbances, parameter variations, measurement noise. This achieved by so-called Jordan Canonical Recurrent Trainable Neural Network, which completely parallel parametric structure, permitting use obtained...
Electroencephalography (EEG) based affective computing is a new research field that aims to find neural correlates between human emotions and the registered EEG signals. Typically, emo- tion recognition systems are personalized, i.e. discrimination models subject-dependent. Building subject-independent harder problem due high variability be- tween individuals. In this paper we propose unified system for efficient of positive negative in group 26 users. The users were exposed arousal images...
Mesenchymal Stromal cells (MSCs) have a potential role in cell-based therapies. Foetal bovine serum (FBS) is used to supplement the basal cell culture medium but presents several disadvantages and risks. Other alternatives been studied, including human umbilical cord blood plasma (hUCBP), aiming at development of xeno-free culturing protocols. A comparative characterization multicomponent metabolic composition hUCBP commercial FBS based on Nuclear Magnetic Resonance (NMR) spectroscopy...
Free-space optics (FSO) convey an enormous potential for ultra-high-capacity seamless fiber-wireless transmission in 5G and beyond communication systems. However, its practical exploitation future deployments, FSO still requires the development of very high-precision robust optical beam alignment. In this paper, we propose two different methods to achieve tight, precise alignment between a pair transceivers, using gimbal-based setup. For scenarios where there is no information about system,...
Singular spectrum analysis (SSA) is considered from a linear invariant systems perspective.In this terminology, the extracted components are as outputs of system which corresponds to finite impulse response (FIR) filters.The number filters determined by embedding dimension.We propose explicitly define frequency each filter responsible for selection informative components.We also introduce subspace distance measure clustering models.We illustrate methodology analyzing Electroencephalograms (EEG).
The objective of this study is to explore the effectiveness three digital shopping platforms (Plain Interactive, Marker-based Augmented Reality and Markerless Reality), on impressions purchase intentions consumers. mainly interested in analysing whether intelligent with AR elements provide any added advantage an advertised product form favourable attitude or a stronger impulse. During tests platforms, quantitative data was collected via computerised questionnaire. High Low class users were...
Despite numerous successful applications of Deep Learning (DL) to large-scale image, video, speech and text data, they remain relatively unexplored in brain imaging field. In this paper, we make an overview recent DL architectures for recognizing cognitive activities from Electroencephalogram (EEG) data with particular emphasis on Brain Computer Interface(BCI) technologies Affective Neurocomputing. We discuss the use convolutional, recurrent neural nets, as well deep belief networks,...
Mapping potential archaeological sites using remote sensing and artificial intelligence can be an efficient tool to assist archaeologists during project planning fieldwork. This paper explores the use of airborne LiDAR data data-centric for identifying burial mounds. The challenge exploring landscape mapping new sites, coupled with difficulty them through visual analysis data, results in recurring issue insufficient annotations. Additionally, top-down nature hinders its search, as morphology...