Mocanu Bogdan-Costel

Prof. Mocanu Bogdan-Costel

Polytechnic University 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
13 August 2022 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
AAAndrea F. Abate
Andrea F. Abate
LCLuicia Cimmino
Luicia Cimmino
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
Fabio NarducciFabio Narducci
Fabio Narducci
Florin POPFlorin POP
Florin POP
Facial Expression recognition is a computer vision problem that took relevant benefit from the research in deep learning. Recent deep neural networks achieved superior results, demonstrating the feasibility of recognizing the expression of a user from a single picture or a video recording the face dynamics. Research studies reveal that the most discriminating portions of the face surfaces that contribute to the recognition of facial expressions are located on the mouth and the eyes. The restrictions for COVID pandemic reasons have also revealed that state-of-the-art solutions for the analysis of the face can severely fail due to the occlusions of using the facial masks. This study explores to what extend expression recognition can deal with occluded faces in presence of masks. To a fairer comparison, the analysis is performed in different occluded scenarios to effectively assess if the facial masks can really imply a decrease in the recognition accuracy. The experiments performed on two public datasets show that some famous top deep classifiers expose a significant reduction in accuracy in presence of masks up to half of the accuracy achieved in non-occluded conditions. Moreover, a relevant decrease in performance is also reported also in the case of occluded eyes but the overall drop in performance is not as severe as in presence of the facial masks, thus confirming that, like happens for face biometric recognition, occluded faces by facial mask still represent a challenging limitation for computer vision solutions.

26 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
IFIon-Dorinel Filip
Ion-Dorinel Filip
DUDan Ungureanu
Dan Ungureanu
Catalin NegruCatalin Negru
Catalin Negru
MDMihai Dascalu
Mihai Dascalu
Florin POPFlorin POP
Florin POP
Human interaction in natural language with computer systems has been a prime focus of research, and the field of conversational agents (including chatbots and Interactive Voice Response (IVR) systems) has evolved significantly since 2009, with a major boost in 2016, especially for industrial solutions. Emergency systems are crucial elements of today’s societies that can benefit from the advantages of intelligent human–computer interaction systems. In this paper, we present two solutions for human-to-computer emergency systems with critical deadlines that use a multi-layer FreeSwitch IVR solution and the Botpress chatbot platform. We are the pioneers in Romania who designed and implemented such a solution, which was evaluated in terms of performance and resource management concerning Quality of Service (QoS). Additionally, we assessed our Proof of Concept (PoC) with real data as part of the system for real-time Romanian transcription of speech and recognition of emotional states within emergency calls. Based on our feasibility research, we concluded that the telephony IVR best fits the requirements and specifications of the national 112 system, with the presented PoC ready to be integrated into the Romanian emergency system.

3 January 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DUDan Ungureanu
Dan Ungureanu
STStefan-Adrian Toma
Stefan-Adrian Toma
IFIon-Dorinel Filip
Ion-Dorinel Filip
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
IAIulian Aciobanitei
Iulian Aciobanitei
Florin POPFlorin POP
Florin POP
The evolution of Natural Language Processing technologies transformed them into viable choices for various accessibility features and for facilitating interactions between humans and computers. A subset of them consists of speech processing systems, such as Automatic Speech Recognition, which became more accurate and more popular as a result. In this article, we introduce an architecture built around various speech processing systems to enhance Romanian emergency services. Our system is designed to help the operator evaluate various situations with the end goal of reducing the response times of emergency services. We also release the largest high-quality speech dataset of more than 150 h for Romanian. Our architecture includes an Automatic Speech Recognition model to transcribe calls automatically and augment the operator’s notes, as well as a Speech Recognition model to classify the caller’s emotions. We achieve state-of-the-art results on both tasks, while our demonstrator is designed to be integrated with the Romanian emergency system.

27 January 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
MMMihaela Mihaiu
Mihaela Mihaiu
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
Catalin NegruCatalin Negru
Catalin Negru
APAlina Petrescu-Nita
Alina Petrescu-Nita
Florin POPFlorin POP
Florin POP
The exponential growth of Internet of Things (IoT) devices has led to massive volumes of data, challenging traditional centralized processing paradigms. The cloud–edge continuum computing model has emerged as a promising solution to address this challenge, offering a distributed approach to data processing and management and improved performances in terms of the overhead and latency of the communication network. In this paper, we present a novel resource allocation optimization solution in cloud–edge continuum architectures designed to support multiple heterogeneous mobile clients that run a set of applications in a 5G-enabled environment. Our approach is structured across three layers, mist, edge, and cloud, and introduces a set of innovative resource allocation models that addresses the limitations of the traditional bin-packing optimization problem in IoT systems. The proposed solution integrates task offloading and resource allocation strategies designed to optimize energy consumption while ensuring compliance with Service Level Agreements (SLAs) by minimizing resource consumption. The evaluation of our proposed solution shows a longer period of active time for edge servers because of the lower energy consumption. These results indicate that the proposed solution is viable and a sustainability model that prioritizes energy efficiency in alignment with current climate concerns.

10 November 2022
Verified
Conference Paper
Closed access
HRHoria-Alexandru Rusan
Horia-Alexandru Rusan
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
Despite intensive research dedicated to human machine communication, until recently only a reduced number of systems adopted vocal commands to interact with computers. With the development of deep convolutional neural networks (DCNNs) architectures promising results have been obtained in speech recognition and natural language processing, allowing people to engage in simple question-answer dialog with robots. In that regard, the goal of this paper is to introduce a novel interface designed to facilitate the human-machine interaction (HMI). The framework starts by detecting and recognizing speech messages, transforming them into spoken commands. The voice controls are further converted into operating system instructions designed to automate everyday human tasks. The experimental evaluation performed on English spoken language dataset, validates the proposed architecture with average accuracy scores superior to 89%. In addition, we have compared different DCNNs architectures and identified which model has the best performance.

1 January 2019
Verified
Conference Paper
Closed access
Mocanu Bogdan-CostelMocanu Bogdan-Costel
Mocanu Bogdan-Costel
RTRuxandra Tapu
Ruxandra Tapu
TZTitus Zaharia
Titus Zaharia
Identifying other persons is a major challenge for blinds and visually impaired people that can hinder interaction in social activities. This paper introduces a novel CNN based face detection, tacking and recognition system designed to improve users' interaction and communication in social encounters. The major contribution consists in a novel weight adaptation scheme able to determine the relevance of face instances and to create a global, fixed-size representation from all face instances tracked during the video stream, while remaining independent of the track length. The experimental evaluation performed on a large set of video streams validates the approach that returns accuracy and recognition rates superior to 90%.