Tudor Mihai David

Mr. Tudor Mihai David

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
27 September 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Mădălin-Dorin PopMădălin-Dorin Pop
Mădălin-Dorin Pop
Octavian ProsteanOctavian Prostean
Octavian Prostean
TDTudor Mihai David
Tudor Mihai David
Gabriela ProsteanGabriela Prostean
Gabriela Prostean
Nowadays, the intelligent transportation concept has become one of the most important research fields. All of us depend on mobility, even when we talk about people, provide services, or move goods. Researchers have tried to create and test different transportation models that can optimize traffic flow through road networks and, implicitly, reduce travel times. To validate these new models, the necessity of having a calibration process defined has emerged. Calibration is mandatory in the modeling process because it ensures the achievement of a model closer to the real system. The purpose of this paper is to propose a new multidisciplinary approach combining microscopic traffic modeling theory with intelligent control systems concepts like fuzzy inference in the traffic model calibration. The chosen Takagi–Sugeno fuzzy inference system proves its adaptive capacity for real-time systems. This concept will be applied to the specific microscopic car-following model parameters in combination with a Kalman filter. The results will demonstrate how the microscopic traffic model parameters can adapt based on real data to prove the model validity.

31 August 2025 in Computers
Verified
Journal Article
Open access
PDF file
TDTudor Mihai David
Tudor Mihai David
Mihai UdrescuMihai Udrescu
Mihai Udrescu
Epidemics caused by respiratory infections have become a global and systemic threat since humankind has become highly connected via modern transportation systems. Any new pathogen with human-to-human transmission capabilities has the potential to cause public health disasters and severe disruptions of social and economic activities. During the COVID-19 pandemic, we learned that proper mask-wearing in closed, restricted areas was one of the measures that worked to mitigate the spread of respiratory infections while allowing for continuing economic activity. Previous research approached this issue by designing hardware–software systems that determine whether individuals in the surveilled restricted area are using a mask; however, most such solutions are centralized, thus requiring massive computational resources, which makes them hard to scale up. To address such issues, this paper proposes a novel decentralized, federated learning (FL) solution to mask-wearing detection that instantiates our lightweight version of the MobileNetV2 model. The FL solution also ensures individual privacy, given that images remain at the local, device level. Importantly, we obtained a mask-wearing training accuracy of 98% (i.e., similar to centralized machine learning solutions) after only eight rounds of communication with 25 clients. We rigorously proved the reliability and robustness of our approach after repeated K-fold cross-validation.

21 August 2026 in Computers
Verified
Journal Article
Open access
PDF file
TDTudor Mihai David
Tudor Mihai David
Mihai UdrescuMihai Udrescu
Mihai Udrescu
Poisoning attacks present a significant challenge for federated learning (FL), particularly when clients operate with Non-IID data and updates are transmitted through multi-tier aggregators. This paper introduces FLVaccin, a hierarchical personalized FL framework structured as an unbalanced tree. In this framework, each non-root node both hosts local clients and aggregates shared MobileNetV2 features (FedPer), whereas the root node does not possess local data. The proposed defense integrates node-level CIFAR-100 vaccination, which calibrates depth- and round-adaptive tolerances, with per-client trend quarantine and root backbone rejection. Experimental results on CIFAR-10 with 100 clients, 25 aggregators, and Dirichlet Non-IID partitioning (α=0.5) demonstrate that the clean baseline achieves 79.9% accuracy. In contrast, unconstrained mixed attacks reduce performance to near-chance levels (20.2% k-fold). When vaccination and quarantine are enabled, 535 attack events still result in a 76.5% ± 0.4% k-fold accuracy (77.3% test), remaining within 2.6 percentage points of the clean model. These findings indicate that tree-aware, vaccination-calibrated monitoring can maintain model utility under persistent multi-vector poisoning without the need to share raw data.

29 July 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
TDTudor Mihai David
Tudor Mihai David
Mihai UdrescuMihai Udrescu
Mihai Udrescu
Federated learning (FL) enables collaborative training without centralizing raw data, yet malicious clients can poison local data or updates and degrade the global model. We present FLVaccin, a hierarchical framework on an unbalanced tree in which every non-root node aggregates and hosts local clients—to our knowledge, the first design not confining all clients to the deepest level; only the root aggregates with zero local clients. All experiments use personalized federated learning (FedPer): shared feature layers are federated bottom-up, while each client keeps a private classifier head. FLVaccin combines two defenses: (i) node-level vaccination, mixing CIFAR-100 images into CIFAR-10 shards, and (ii) depth- and round-adaptive quarantine, whose per-client tolerances are set from vaccination mean-accuracy calibration (30 single-round trials across injection-intensity bands); clients exceeding allowed metric swings are temporarily excluded, while the root rejects global backbone updates with deteriorating validation trends. Implemented with MobileNetV2/FedPer and Dirichlet Non-IID partitioning (α = 0.5), 100 clients federate across 25 nodes over four levels. Without defense, 130 attacks collapse test accuracy from 77.4% to 21.0%; with our defense mechanism, 535 attacks yield 77.3% (k-fold 76.5%±0.4%), within 2.6 percentage points of the clean baseline (96.8% of clean accuracy), showing practical tree-aware robustness while preserving privacy.