Lidia Bajenaru

Dr. Lidia Bajenaru

PRECIS, University Politehnica of Bucharest, Bucharest, Bucureşti, Romania
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2019 in Sensors
Verified
Journal Article
Open access
PDF file
RVRobert-Andrei Voicu
Robert-Andrei Voicu
CDCiprian Dobre
Ciprian Dobre
LBLidia Bajenaru
Lidia Bajenaru
RCRadu-Ioan Ciobanu
Radu-Ioan Ciobanu
Because the number of elderly people is predicted to increase quickly in the upcoming years, “aging in place” (which refers to living at home regardless of age and other factors) is becoming an important topic in the area of ambient assisted living. Therefore, in this paper, we propose a human physical activity recognition system based on data collected from smartphone sensors. The proposed approach implies developing a classifier using three sensors available on a smartphone: accelerometer, gyroscope, and gravity sensor. We have chosen to implement our solution on mobile phones because they are ubiquitous and do not require the subjects to carry additional sensors that might impede their activities. For our proposal, we target walking, running, sitting, standing, ascending, and descending stairs. We evaluate the solution against two datasets (an internal one collected by us and an external one) with great effect. Results show good accuracy for recognizing all six activities, with especially good results obtained for walking, running, sitting, and standing. The system is fully implemented on a mobile device as an Android application.

31 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MBMonica Barbu
Monica Barbu
Iordache Dragos DanielIordache Dragos Daniel
Iordache Dragos Daniel
IPIonut Petre
Ionut Petre
DBDragos Catalin Barbu
Dragos Catalin Barbu
LBLidia Bajenaru
Lidia Bajenaru
This study presents a novel approach to inclusive education by integrating augmented reality (XR) and generative artificial intelligence (AI) technologies into an immersive and adaptive learning platform designed for students with special educational needs. Building upon existing solutions, the approach uniquely combines XR and generative AI to facilitate personalized, accessible, and interactive learning experiences tailored to individual requirements. The framework incorporates an intuitive Unity XR-based interface alongside a generative AI module to enable near real-time customization of content and interactions. Additionally, the study examines related generative AI initiatives that promote inclusion through enhanced communication tools, educational support, and customizable assistive technologies. The motivation for this study arises from the pressing need to address the limitations of traditional educational methods, which often fail to meet the diverse needs of learners with special educational requirements. The integration of XR and generative AI offers transformative potential by creating adaptive, immersive, and inclusive learning environments. This approach ensures real-time adaptability to individual progress and accessibility, addressing critical barriers such as static content and lack of inclusivity in existing systems. The research outlines a pathway toward more inclusive and equitable education, significantly enhancing opportunities for learners with diverse needs and contributing to broader social integration and equity in education.

16 November 2024 in Future Internet
Verified
Journal Article
Open access
PDF file
EPElena Paraschiv
Elena Paraschiv
LBLidia Bajenaru
Lidia Bajenaru
CPCristian Petrache
Cristian Petrache
OBOvidiu Bica
Ovidiu Bica
DNDragoș-Nicolae Nicolau
Dragoș-Nicolae Nicolau
Schizophrenia is a complex neuropsychiatric disorder characterized by disruptions in brain connectivity and cognitive functioning. Continuous monitoring of neural activity is essential, as it allows for the detection of subtle changes in brain connectivity patterns, which could provide early warnings of cognitive decline or symptom exacerbation, ultimately facilitating timely therapeutic interventions. This paper proposes a novel approach for detecting schizophrenia-related abnormalities using deep learning (DL) techniques applied to electroencephalogram (EEG) data. Using an openly available EEG dataset on schizophrenia, the focus is on preprocessed event-related potentials (ERPs) from key electrode sites and applied transfer entropy (TE) analysis to quantify the directional flow of information between brain regions. TE matrices were generated to capture neural connectivity patterns, which were then used as input for a hybrid DL model, combining convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The model achieved a performant accuracy of 99.94% in classifying schizophrenia-related abnormalities, demonstrating its potential for real-time mental health monitoring. The generated TE matrices revealed significant differences in connectivity between the two groups, particularly in frontal and central brain regions, which are critical for cognitive processing. These findings were further validated by correlating the results with EEG data obtained from the Muse 2 headband, emphasizing the potential for portable, non-invasive monitoring of schizophrenia in real-world settings. The final model, integrated into the NeuroPredict platform, offers a scalable solution for continuous mental health monitoring. By incorporating EEG data, heart rate, sleep patterns, and environmental metrics, NeuroPredict facilitates early detection and personalized interventions for schizophrenia patients.

30 August 2024 in Electronics
Verified
Journal Article
Open access
PDF file
OBOvidiu-Lucian Băjenaru
Ovidiu-Lucian Băjenaru
LBLidia Bajenaru
Lidia Bajenaru
MIMarilena Ianculescu
Marilena Ianculescu
VCVictor Stefan Constantin
Victor Stefan Constantin
AGAndreea Maria Gusatu
Andreea Maria Gusatu
CNCatalina Raluca Nuta
Catalina Raluca Nuta
The aging population requires cutting-edge approaches to geriatric care, with digital health technologies playing a crucial part in meeting the challenging demands of healthcare. Current approaches frequently fall short of the goal of providing comprehensive, real-time monitoring and merging contextually complex information for use in the treatment of patients. This paper addresses these limitations by integrating the innovative approaches within the RO-SmartAgeing system and the NeuroPredict platform to boost geriatric-care outcomes. It emphasizes the multifaceted design and development processes of these digital health solutions, emphasizing a multidisciplinary approach and a meticulous choice of decision-making tools. This paper presents the inclusion of decision-making tools, namely the Medical Blackbox and Gaitband, into the RO-SmartAgeing system and the NeuroPredict platform; these tools have been developed for the purpose of gathering complex physiological data and allow for in-depth evaluations of gait patterns and vital health parameters in elderly individuals. The present research emphasizes major breakthroughs in sensing technology and decision-making capabilities, illustrating the manner in which these tools enhance patient outcomes by providing timely, data-driven insights. The results demonstrate that these tailored decision-making tools significantly improve patient outcomes, underscoring the need for such ongoing improvements able to address digital health solutions tailored to the dynamic demands of an increasingly aging population.

3 July 2019 in Studies in Informatics and Control
Verified
Journal Article
Closed access
VGVeronica Gavrilă
Veronica Gavrilă
LBLidia Bajenaru
Lidia Bajenaru
CDCiprian Dobre
Ciprian Dobre

17 December 2019 in Studies in Informatics and Control
Verified
Journal Article
Closed access
ABAlexandru Balog
Alexandru Balog
LBLidia Bajenaru
Lidia Bajenaru
ICIrina Cristescu
Irina Cristescu