Beatrix-May Balaban

Mrs. Beatrix-May Balaban

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 November 2021
Verified
Conference Paper
Closed access
BBBeatrix-May Balaban
Beatrix-May Balaban
SSSacala Ioan Stefan
Sacala Ioan Stefan
PAPetrescu-Nita Alina-Claudia
Petrescu-Nita Alina-Claudia
PFPop Florin
Pop Florin
UAUdrea Andreea
Udrea Andreea
In this paper, a cyber-physical system model is proposed for usage in the medical field. The past years showed us that the challenges that the health care system is facing are becoming more and more complex. Therefore, our model aims to ease the extraction of data for each patient. For example, data like blood pressure or body temperature can be recorded and measured. The efficiency is improved by adding sensors to collect data and send it through the proposed model. The model integrates an encryption module and a machine learning module because the goal is to gather data, encrypt it to ensure privacy and train the algorithm to provide the following result: for each patient, based on their symptomatology, the algorithm will automatically analyze each variable, provide a treatment plan and predict if the health condition of a patient is getting worse. For the latter, alerts will be sent to the medical staff.

17 November 2022
Verified
Conference Paper
Closed access
BBBeatrix-May Balaban
Beatrix-May Balaban
SSSacala Ioan Stefan
Sacala Ioan Stefan
PAPetrescu-Nita Alina-Claudia
Petrescu-Nita Alina-Claudia
SRSimen Radu
Simen Radu
Considering the evolution of technology, the need to secure data is growing fast. When we turn our attention to the healthcare field, securing data and assuring privacy are critical conditions that must be accomplished. The information is sensitive and confidential, and the exchange rate is very fast. Over the years, the healthcare domain has gradually seen a growth of interest regarding the interconnectivity of different processes to optimize and improve the services that are provided. Therefore, we need intelligent complex systems that can collect and transport sensitive data in a secure way. These systems are called cyber-physical systems. In healthcare domain, these complex systems are named medical cyber physical systems. The paper presents a brief description of the above-mentioned intelligent systems. Then, we focus on wireless sensor networks and the issues and challenges that occur in securing sensitive data and what improvements we propose on this subject. In this paper we tried to provide a detailed overview about cyber-physical systems, medical cyber-physical systems, wireless sensor networks and the security issues that can appear.

1 May 2023
Verified
Conference Paper
Closed access
BBBeatrix-May Balaban
Beatrix-May Balaban
SŞSacală Ioan Ştefan
Sacală Ioan Ştefan
PAPetrescu-Niţă Alina-Claudia
Petrescu-Niţă Alina-Claudia
NRNiţă Răzvan
Niţă Răzvan
Considering the constant growth and evolution of technology, being able to secure data is a challenge. This is why researchers find this a top research topic. Cyber-Physical Systems are complex, large-scale systems that can be found in domains like healthcare, transportation, industrial controls systems or smart grids. Having many components that interact with each other, we can observe here the challenge in maintaining a secure environment for the data as data tampering or data extraction can occur, for example, in the actual transportation of data from one device to another. The main focus of this paper is to give an answer if blockchain technology provides a solution in building a secure network. We give a short review of the related work regarding blockchain integration in large-scale systems like Cyber-Physical Systems. It was also briefly analyzed the layered structure of a blockchain and discussed some solutions for each layer. We then discussed about consensus algorithms for validation and authentication process. In general, consensus algorithms are implemented to assure the validation process of the nodes in a network. In this paper we tried to analyze and propose a model that offers an extra layer of security by adding the authentication step. In this way, the nodes that are validated are also considered trusted nodes in the network.

1 May 2021
Verified
Conference Paper
Closed access
BBBeatrix-May Balaban
Beatrix-May Balaban
ISIoan Stefan Sacala
Ioan Stefan Sacala
APAlina Claudia Petrescu-Nita
Alina Claudia Petrescu-Nita
FPFlorin Pop
Florin Pop
Nowadays, intelligent vehicles are becoming more and more important in the transportation field. What makes such a vehicle vulnerable is the number of interconnected components that individually have a strong security but can cause weakness points when they are connected. The challenge is to design and build a powerful system that uses both cyber-physical components. The proposed model is a system with integrated modules for fingerprint and face recognition to certify that a driver has the right to access the vehicle. The aim is to develop a security system for intelligent vehicles that can be also a secure keyless entry system using the power of biometrics. When a driver approaches the car, a sensor will activate the recognition modules. Only after the total completion of the recognition process the driver is authenticated and has the right to use the vehicle. We simulated real-time face detection and eye tracking using Matlab 2020a. Face detection is performed using Viola-Jones algorithms and the tracking is made with bbox-es. Besides normal conditions, other tests were made to challenge the algorithm, for example: angle rotations, the use of glasses, face mask, glasses and face mask together.

18 July 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
BBBeatrix-May Balaban
Beatrix-May Balaban
Ioan SacalaIoan Sacala
Ioan Sacala
APAlina Petrescu-Nita
Alina Petrescu-Nita
Telemedicine in emergency contexts presents unique challenges, particularly in multilingual and low-resource settings where accurate, clinical understanding and triage decision support are critical. This paper introduces TriagE-NLU, a novel multilingual natural language understanding system designed to perform both semantic parsing and clinical intervention classification from emergency dialogues. The system is built on a federated learning architecture to ensure data privacy and adaptability across regions and is trained using TriageX, a synthetic, clinically grounded dataset covering five languages (English, Spanish, Romanian, Arabic, and Mandarin). TriagE-NLU integrates fine-tuned multilingual transformers with a hybrid rules-and-policy decision engine, enabling it to parse structured medical information (symptoms, risk factors, temporal markers) and recommend appropriate interventions based on recognized patterns. Evaluation against strong multilingual baselines, including mT5, mBART, and XLM-RoBERTa, demonstrates superior performance by TriagE-NLU, achieving F1 scores of 0.91 for semantic parsing and 0.89 for intervention classification, along with 0.92 accuracy and a BLEU score of 0.87. These results validate the system’s robustness in multilingual emergency telehealth and its ability to generalize across diverse input scenarios. This paper establishes a new direction for privacy-preserving, AI-assisted triage systems.

25 September 2025 in Journal of Control Engineering and Applied Informatics
Verified
Journal Article
Open access
PDF file
BBBeatrix-May Balaban
Beatrix-May Balaban
Ioan SacalaIoan Sacala
Ioan Sacala
APAlina Petrescu-Nita
Alina Petrescu-Nita
A Federated Cyber-Physical Platform for Real-Time Coordination of Emergency Medical Service via 112 Integrations