A5016527260- Chemical Thermodynamics and Molecular Structure
- Thermal and Kinetic Analysis
- Free Radicals and Antioxidants
- thermodynamics and calorimetric analyses
- Radiation Effects and Dosimetry
- Muscle activation and electromyography studies
- COVID-19 diagnosis using AI
- EEG and Brain-Computer Interfaces
- Hand Gesture Recognition Systems
- Crystallization and Solubility Studies
- Crystallography and molecular interactions
- Neural Networks and Applications
- Thermochemical Biomass Conversion Processes
- Biochemical effects in animals
- Biodiesel Production and Applications
- COVID-19 Clinical Research Studies
- Protein Interaction Studies and Fluorescence Analysis
- Digital Media Forensic Detection
- Music and Audio Processing
- Luminescence Properties of Advanced Materials
- Lipid Membrane Structure and Behavior
- Radiomics and Machine Learning in Medical Imaging
- Image and Signal Denoising Methods
- Deception detection and forensic psychology
- Artificial Intelligence in Healthcare
Universitatea Națională de Știință și Tehnologie Politehnica București
2018-2025
Romanian Academy
2001-2024
Institute of Physical Chemistry
2010-2024
Romanian Educational and Research Network
2023
Université Paris-Saclay
2020-2021
CentraleSupélec
2020-2021
University of Bucharest
2010
Institutul Oncologic Bucuresti
2010
The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, chest CT scan data, from 1003 coronavirus-infected patients two French hospitals. train deep learning model based scans to predict severity. then construct the multimodal AI-severity score includes 5 variables (age, sex, oxygenation, urea, platelet) in addition model. show neural network analysis CT-scans brings...
In an attempt to create a more familiar brain-machine interaction for biometric authentication applications, we investigated the efficiency of using users' personal hobbies, interests, and memory collections. This approach creates unique pleasant experience that can be later utilized within protocol. paper presents new EEG dataset recorded while subjects watch images popular pictures with no point interest great significance. addition, propose several applications tackled our newly collected...
Abstract. Solid biomass fuels are economical and practical renewable energy sources. Exploitation of agricultural as a fuel offers considerable advantages in different domains supply far the climate is involved. In this study we intended to investigate feasibility alternative residues grape pomace corn cob pellets with addition sawdust, starch, waste rapeseed oil examine how these additives affects calorific powers physical properties. Sawdust, was 10 %. Pellets were produced by manual...
Hand gesture recognition has numerous applications in medical (e.g., prosthetics), engineering robot manipulation) and, even, military research areas UAV control applications). This paper proposes a fast and accurate method to identify hand categories based on electromyo-graphic (EMG) signals registered by commercial sensor Myo Armband developed Ontario-based Thalmic Labs), which is placed the user's forearm. The proposed extraction of time-domain features neural network architecture perform...
Abstract The recent focus in the development of novel nanosystems for biomedical applications lays firmly on their interactions with biomolecules. Thermodynamic parameters driving interaction between nanoparticles and proteins provide insights into complex processes at bio/nanointerface. present work aims to investigate binding mechanisms dominant contributions that determine adsorption during a model protein, is, bovine serum albumin, new type drug delivery systems, Vitamin E/sphingomyelin...
The SARS-COV-2 pandemic has put pressure on Intensive Care Units, and made the identification of early predictors disease severity a priority. We collected clinical, biological, chest CT scan data, radiology reports from 1,003 coronavirus-infected patients two French hospitals. Among 58 variables measured at admission, 11 clinical 3 radiological were associated with severity. Next, using 506,341 images, we trained evaluated deep learning models to segment scans reproduce radiologists’...
In biomedical applications, the Electromyographic (EMG) signal is used to record electrical activity of muscles during their contraction. EMG classification stands at core real time systems that aim discriminate between user's movements without relying on other environmental conditions (as it case with gesture based video). The signals usually translate sign language or design computer interfaces recognition. this paper, we propose a continuation our previous work, real-time automatic hand...
The current coronavirus pandemic (COVID-19) became a world-wide threat, infecting more than 42 million people since its outbreak in early 2020. Recent studies show that analyzing chest CT scans plays an essential role assessing disease progression and facilitates diagnosis. Automatic lesion segmentation constitutes useful tool to complement traditional healthcare system strategies address the COVID-19 crisis. We introduce MASC-Net, novel deep neural network automatically detects related...
The combustion energy of histidine enantiomers (L and D) their racemic mixture was measured experimentally. following values for the enthalpies formation corresponding to crystalline state were derived = −451.7, D −448.7, DL −451.5 kJ·mol −1 ), information concerning stability obtained by correlating above thermochemical quantity with structure molecules using group additivity scheme. samples characterized a simultaneous thermogravimetry (TG) coupled differential scanning calorimetry (DSC)...
This work proposes a new learning strategy for training feedforward neural network subject to spectral norm and nonnegativity constraints. Our primary goal is control the Lipschitz constant of in order make it robust against adversarial perturbations its inputs. We propose stochastic projected gradient descent algorithm which allows us adjust this process. The evaluated context designing fully connected Automatic Gesture Recognition based on EMG signals. perform comparison with same...
Thermal analysis of two dipeptides having alanine (Ala) as first term, using combustion calorimetry method and simultaneous TG-DSC measurements, have been carried out. The enthalpies formation, the quantities related to decomposition processes these compounds, were compared with those free –α-amino acids contained in dipeptides.Information about stability influence components on was obtained.