ACAlexandru Ciobotaru

Alexandru Ciobotaru

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alexandru Ciobotaru has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    End-to-End Machine Learning-Based System for Diabetes Monitoring and Prediction Using Mobile Terminals

    by Alexandra Fanca, Adela Pop, Alexandru Ciobotaru, Dan Ioan Gota, Honoriu Valean

    Diabetes mellitus is a major chronic disease that requires continuous monitoring and timely risk assessment to reduce the likelihood of severe long−term complications. Recent advances in mobile health technologies and machine learning (ML) provide new opportunities for developing intelligent systems that support diabetes self−management and early risk screening. This paper presents an end−to−end mobile health platform that integrates diabetes monitoring functionalities with an ML−based prediction service within a modular client−server architecture. The proposed system enables users to record glucose measurements, insulin injections, physical activity, and other health−related information while providing historical data visualization, automated reminder notifications, and real−time diabetes risk prediction. The prediction module was trained using the publicly available PIMA Indians Diabetes Dataset and evaluated using Decision Tree (DT), Random Forest (RF), and XGBoost classifiers. Model performance was assessed using accuracy, precision, recall, specificity, F1−score, calibration analysis, and the area under the receiver operating characteristic curve (AUC). Experimental results showed that the RF classifier achieved the highest AUC (0.925), demonstrating superior discrimination capability among the evaluated models and making it the most suitable candidate for deployment within the proposed platform. Although the current prediction model was trained on a benchmark public dataset, the proposed framework provides a practical foundation for integrating ML-driven decision support into mobile health applications and can be further extended through external clinical validation and personalized prediction models.

  • Open Access

    Multi-Task and Federated Learning for Breast and Lung Cancer Screening and Diagnosis: A Survey and Future Research Directions

    by Alexandru Ciobotaru, Cosmina Corches, Dan Gota, Liviu Miclea

    Background: Breast cancer (BrC) and lung cancer (LuC) are two forms of aggressive cancer that affect both men and women worldwide. Recently, multitask learning (MTL) and federated learning (FL) techniques have proven to be efficient in increasing the robustness of deep learning (DL)-based models by performing multiple tasks simultaneously and preserving the confidentiality of medical data. Methods: This paper presents a survey of MTL and FL methods for BrC and LuC screening and diagnosis using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. Comprehensive tables were created to highlight the performances of both MTL models and FL environments. Results: The main challenges identified were the lack of hybrid MTL models that combine hard and soft sharing, heterogeneous imaging data, and edge FL systems. Conclusions: FL environments obtain competitive performance compared with centralized MTL models, highlighting their potential to preserve medical data confidentiality without compromising performance. Future research directions could include MTL-based models incorporated in FL environments, hybrid MTL models that combine both hard- and soft-sharing parameter methods, and the use of blockchain techniques to increase the security of FL environments.


  • Open Access

    An Explainable Deep Learning-Based Predictive Maintenance Solution for Air Compressor Condition Monitoring

    by Alexandru Ciobotaru, Cosmina Corches, Dan Gota, Liviu Miclea

    Air compressors are vital across various sectors—automotive, manufacturing, buildings, and healthcare—as they provide pressurized air for air suspension systems in vehicles, supply power pneumatic machines throughout industrial production lines, and support non-clinical infrastructure within hospital environments, including pneumatic control systems, isolation room pressurization, and laboratory equipment operation. Ensuring that such components are reliable is critical, as unexpected failures can disrupt facility functions and compromise patient safety. Predictive maintenance (PdM) has emerged as a key factor in enhancing the reliability and operational efficiency of medical devices by leveraging sensor data and artificial intelligence (AI)-based algorithms to detect component degradation before functional failures occur. In this paper, a predictive maintenance solution for condition monitoring and fault prediction for the exhaust valve, bearings, water pump, and radiator of an air compressor is presented, by comparing a hybrid deep neural network (DNN) as a feature extractor and a support vector machine (SVM) for condition classification: a pure DNN classifier as well as a standalone SVM model. Additionally, each model was trained and validated on three devices—NVIDIA T4 GPU, Raspberry Pi 4 Model B, and NVIDIA Jetson Nano—and performance reports in terms of latency, energy consumption, and CO2 emissions are presented. Moreover, three model agnostic explainable AI (XAI) methods were employed to increase the transparency of the hybrid model’s final decision: Shapley additive explanations (SHAP), local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDP). The hybrid model achieves on average 98.71%, 99.25%, 98.78%, and 99.01% performance in terms of accuracy, precision, recall, and F1-score across all devices Additionally, the DNN baseline and SVM model achieve on average 93.2%, 88.33%, 90.45%, and 89.37%, as well as 93.34%, 88.11%, 95. 41%, and 91.62% performance in terms of accuracy, precision, recall, and F1-score across all devices. The integration of XAI methods within the PdM pipeline offers enhanced transparency, interpretability, and trustworthiness of predictive outcomes, thereby facilitating informed decision-making among maintenance personnel.


  • Open Access

    Deep Learning and Federated Learning in Breast Cancer Screening and Diagnosis: A Systematic Review

    by Alexandru Ciobotaru, Cosmina Corches, Dan Gota, Liviu Miclea

    Breast cancer remains one of the leading causes of death among women worldwide. Early detection and diagnosis are crucial for effective treatment and improved patient outcome. In recent years, both deep learning and federated learning have demonstrated significant advancements in terms of their ability to reliably and securely diagnose breast cancer using various imaging techniques. Consequently, a thorough summary of recent advancements in the field of breast cancer screening and diagnosis using deep learning and federated learning, along with future research directions, is imperative. This study presents a comprehensive review of recent deep learning and federated learning-based methods for breast cancer screening and diagnosis from the classification, segmentation, and detection viewpoints using ultrasonography, mammography, magnetic resonance imaging, and histopathology images. In addition, novel deep learning and federated learning architectures that are used to reliably and securely diagnose breast cancer using various imaging techniques are highlighted. Finally, a discussion of the associated challenges and future research directions are presented.


  • Open Access

    System for the Acquisition and Monitoring of Energy Consumption in the Context of Industry 4.0

    by Tudor Covrig, Alexandru Ciobotaru, Pavel-Alexandru Bejan, Lucian Farmathy-Pop, Stelian Oltean, Cristian-Dragoș Dumitru, Liviu-Cristian Miclea

    This paper examines methodologies for monitoring energy consumption and operational parameters of an industrial assembly line, with a particular emphasis on the utilization of virtual tools, augmented reality, and real-time data visualization. The research examines the integration of an interface and the implementation of a data acquisition system, employing augmented reality to facilitate interaction with the collected data. The proposed system employs the Node-RED interface to facilitate the establishment of connections between constituent elements. The data is stored in a database, which provides support for decision-making in the analysis of energy consumption and operational parameters of the industrial assembly line. The results demonstrate that the solution is effective in enhancing energy resource management, identifying inefficiencies, and optimizing the performance of industrial equipment. The findings indicate that the implementation of such a system can markedly enhance the industrial process.


  • Open Access

    Multi-Instance Classification of Breast Tumor Ultrasound Images Using Convolutional Neural Networks and Transfer Learning

    by Alexandru Ciobotaru, Maria Aurora Bota, Dan Ioan Goța, Liviu Cristian Miclea

    Background: Breast cancer is arguably one of the leading causes of death among women around the world. The automation of the early detection process and classification of breast masses has been a prominent focus for researchers in the past decade. The utilization of ultrasound imaging is prevalent in the diagnostic evaluation of breast cancer, with its predictive accuracy being dependent on the expertise of the specialist. Therefore, there is an urgent need to create fast and reliable ultrasound image detection algorithms to address this issue. Methods: This paper aims to compare the efficiency of six state-of-the-art, fine-tuned deep learning models that can classify breast tissue from ultrasound images into three classes: benign, malignant, and normal, using transfer learning. Additionally, the architecture of a custom model is introduced and trained from the ground up on a public dataset containing 780 images, which was further augmented to 3900 and 7800 images, respectively. What is more, the custom model is further validated on another private dataset containing 163 ultrasound images divided into two classes: benign and malignant. The pre-trained architectures used in this work are ResNet-50, Inception-V3, Inception-ResNet-V2, MobileNet-V2, VGG-16, and DenseNet-121. The performance evaluation metrics that are used in this study are as follows: Precision, Recall, F1-Score and Specificity. Results: The experimental results show that the models trained on the augmented dataset with 7800 images obtained the best performance on the test set, having 94.95 ± 0.64%, 97.69 ± 0.52%, 97.69 ± 0.13%, 97.77 ± 0.29%, 95.07 ± 0.41%, 98.11 ± 0.10%, and 96.75 ± 0.26% accuracy for the ResNet-50, MobileNet-V2, InceptionResNet-V2, VGG-16, Inception-V3, DenseNet-121, and our model, respectively. Conclusion: Our proposed model obtains competitive results, outperforming some state-of-the-art models in terms of accuracy and training time.