FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas

Article Subjects > Engineering Europe University of Atlantic > Research > Scientific Production
Fundación Universitaria Internacional de Colombia > Research > Scientific Production
Ibero-american International University > Research > Articles and books
Universidad Internacional do Cuanza > Research > Scientific Production Abierto Inglés A new artificial intelligence-based approach is proposed by developing a deep learning (DL) model for identifying the people who violate the face mask protocol in public places. To achieve this goal, a private dataset was created, including different face images with and without masks. The proposed model was trained to detect face masks from real-time surveillance videos. The proposed face mask detection (FMDNet) model achieved a promising detection of 99.0% in terms of accuracy for identifying violations (no face mask) in public places. The model presented a better detection capability compared to other recent DL models such as FSA-Net, MobileNet V2, and ResNet by 24.03%, 5.0%, and 24.10%, respectively. Meanwhile, the model is lightweight and had a confidence score of 99.0% in a resource-constrained environment. The model can perform the detection task in real-time environments at 41.72 frames per second (FPS). Thus, the developed model can be applicable and useful for governments to maintain the rules of the SOP protocol. metadata Benifa, J. V. Bibal and Chola, Channabasava and Muaad, Abdullah Y. and Hayat, Mohd Ammar Bin and Bin Heyat, Md Belal and Mehrotra, Rajat and Akhtar, Faijan and Hussein, Hany S. and Ramírez-Vargas, Debora L. and Kuc Castilla, Ángel Gabriel and Díez, Isabel de la Torre and Khan, Salabat mail UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, debora.ramirez@unini.edu.mx, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED (2023) FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas. Sensors, 23 (13). p. 6090. ISSN 1424-8220

Text
sensors-23-06090.pdf
Available under License Creative Commons Attribution.
Download (2MB)

Official URL: http://doi.org/10.3390/s23136090

Abstract

A new artificial intelligence-based approach is proposed by developing a deep learning (DL) model for identifying the people who violate the face mask protocol in public places. To achieve this goal, a private dataset was created, including different face images with and without masks. The proposed model was trained to detect face masks from real-time surveillance videos. The proposed face mask detection (FMDNet) model achieved a promising detection of 99.0% in terms of accuracy for identifying violations (no face mask) in public places. The model presented a better detection capability compared to other recent DL models such as FSA-Net, MobileNet V2, and ResNet by 24.03%, 5.0%, and 24.10%, respectively. Meanwhile, the model is lightweight and had a confidence score of 99.0% in a resource-constrained environment. The model can perform the detection task in real-time environments at 41.72 frames per second (FPS). Thus, the developed model can be applicable and useful for governments to maintain the rules of the SOP protocol.

Item Type:	Article
Uncontrolled Keywords:	artificial intelligence; COVID-19; deep learning; FaceMask; MobileNetV2; pandemic; SARS CoV-2; surveillance; World Health Organization
Subjects:	Subjects > Engineering
Divisions:	Europe University of Atlantic > Research > Scientific Production Fundación Universitaria Internacional de Colombia > Research > Scientific Production Ibero-american International University > Research > Articles and books Universidad Internacional do Cuanza > Research > Scientific Production
Date Deposited:	03 Jul 2023 23:30
Last Modified:	03 Jul 2023 23:30
URI:	https://repositorio.unini.edu.mx/id/eprint/7793

Actions (login required)

View Item

open

Detecting hate in diversity: a survey of multilingual code-mixed image and video analysis

The proliferation of damaging content on social media in today’s digital environment has increased the need for efficient hate speech identification systems. A thorough examination of hate speech detection methods in a variety of settings, such as code-mixed, multilingual, visual, audio, and textual scenarios, is presented in this paper. Unlike previous research focusing on single modalities, our study thoroughly examines hate speech identification across multiple forms. We classify the numerous types of hate speech, showing how it appears on different platforms and emphasizing the unique difficulties in multi-modal and multilingual settings. We fill research gaps by assessing a variety of methods, including deep learning, machine learning, and natural language processing, especially for complicated data like code-mixed and cross-lingual text. Additionally, we offer key technique comparisons, suggesting future research avenues that prioritize multi-modal analysis and ethical data handling, while acknowledging its benefits and drawbacks. This study attempts to promote scholarly research and real-world applications on social media platforms by acting as an essential resource for improving hate speech identification across various data sources.

Producción Científica

Hafiz Muhammad Raza Ur Rehman mail , Mahpara Saleem mail , Muhammad Zeeshan Jhandir mail , Eduardo René Silva Alvarado mail eduardo.silva@funiber.org, Helena Garay mail helena.garay@uneatlantico.es, Imran Ashraf mail ,

Raza Ur Rehman

open

Olive Leaf Extracts With High, Medium, or Low Bioactive Compounds Content Differentially Modulate Alzheimer's Disease via Redox Biology

Alzheimer's disease (AD) involves β-amyloid plaques and tau hyperphosphorylation, driven by oxidative stress and neuroinflammation. Cyclooxygenase-2 (COX-2) and acetylcholinesterase (AChE) activities exacerbate AD pathology. Olive leaf (OL) extracts, rich in bioactive compounds, offer potential therapeutic benefits. This study aimed to assess the anti-inflammatory, anti-cholinergic, and antioxidant effects of three OL extracts (low, mid, and high bioactive content) in vitro and their protective effects against AD-related proteinopathies in Caenorhabditis elegans models. OL extracts were characterized for phenolic composition, AChE and COX-2 inhibition, as well as antioxidant capacity. Their effects on intracellular and mitochondrial reactive oxygen species (ROS) were tested in C. elegans models expressing human Aβ and tau proteins. Gene expression analyses examined transcription factors (DAF-16, skinhead [SKN]-1) and their targets (superoxide dismutase [SOD]-2, SOD-3, GST-4, and heat shock protein [HSP]-16.2). High-OL extract demonstrated superior AChE and COX-2 inhibition and antioxidant capacity. Low- and high-OL extracts reduced Aβ aggregation, ROS levels, and proteotoxicity via SKN-1/NRF-2 and DAF-16/FOXO pathways, whereas mid-OL showed moderate effects through proteostasis modulation. In tau models, low- and high-OL extracts mitigated mitochondrial ROS levels via SOD-2 but had limited effects on intracellular ROS levels. High-OL extract also increased GST-4 levels, whereas low and mid extracts enhanced GST-4 levels. OL extracts protect against AD-related proteinopathies by modulating oxidative stress, inflammation, and proteostasis. High-OL extract showed the most promise for nutraceutical development due to its robust phenolic profile and activation of key antioxidant pathways. Further research is needed to confirm long-term efficacy.

Producción Científica

Jose M. Romero‐Marquez mail , María D. Navarro‐Hortal mail , Alfonso Varela‐López mail , Rubén Calderón Iglesias mail ruben.calderon@uneatlantico.es, Juan G. Puentes mail , Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Maurizio Battino mail maurizio.battino@uneatlantico.es, Cristina Sánchez‐González mail , Jianbo Xiao mail , Roberto García‐Ruiz mail , Sebastián Sánchez mail , Tamara Y. Forbes‐Hernández mail , José L. Quiles mail jose.quiles@uneatlantico.es,

Romero‐Marquez

open

Effects of a Garlic Hydrophilic Extract Rich in Sulfur Compounds on Redox Biology and Alzheimer's Disease Markers in Caenorhabditis Elegans

Garlic is a horticultural product highly valued for its culinary and medicinal attributes. The aim of this study was to evaluate the composition of a garlic hydrophilic extract as well as the influence on redox biology, Alzheimer's Disease (AD) markers and aging, using Caenorhabditis elegans as experimental model. The extract was rich in sulfur compounds, highlighting the presence of other compounds like phenolics, and the antioxidant property was corroborated. Regarding AD markers, the acetylcholinesterase inhibitory capacity was demonstrated in vitro. Although the extract did not modify the amyloid β-induced paralysis degree, it was able to improve, in a dose-dependent manner, some locomotive parameters affected by the hyperphosphorylated tau protein in C. elegans. It could be related to the effect found on GFP-transgenic stains, mainly regarding to the increase in the gene expression of HSP-16.2. Moreover, an initial investigation into the aging process revealed that the extract successfully inhibited the accumulation of intracellular and mitochondrial reactive oxygen species in aged worms. These results provide valuable insights into the multifaceted impact of garlic extract, particularly in the context of aging and neurodegenerative processes. This study lays a foundation for further research avenues exploring the intricate molecular mechanisms underlying garlic effects and its translation into potential therapeutic interventions for age-related neurodegenerative conditions.

Producción Científica

María D. Navarro‐Hortal mail , Jose M. Romero‐Marquez mail , Johura Ansary mail , Cristina Montalbán‐Hernández mail , Alfonso Varela‐López mail , Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Jianbo Xiao mail , Rubén Calderón Iglesias mail ruben.calderon@uneatlantico.es, Maurizio Battino mail maurizio.battino@uneatlantico.es, Cristina Sánchez‐González mail , Tamara Y. Forbes‐Hernández mail , José L. Quiles mail jose.quiles@uneatlantico.es,

Navarro‐Hortal

open

Game-based educational experience in clinical simulation and academic achievement in medical students: a retrospective study

Background In recent years, medical education has increasingly embraced gamification as a method for teaching clinical skills. In Peru, social isolation resulting from the COVID-19 pandemic forced universities and academic institutions to restructure their teaching methods, while there are no reports about the impact of this strategies in Peruvian students. In this study we evaluated the feasibility and patterns of use of a novel video game based didactic activity in undergraduate students from a School of Medicine in Peru. Method We conducted a retrospective pilot study in medical students who used the Full Code Medical Simulation platform. We retrieved scoring data obtained from this platform for selected cases of clinical courses with an appropriate number of users [clinical medicine (CM) I (7 cases), CM II (17 cases), surgery I (6 cases) and surgery II (6 cases)]. cases)]. We also evaluated patterns of use and the association between academic performance and the Full Code scores. Results A total of 590 students were included in the study. We found a direct correlation between the student’s course grade and Full Code score in all courses (CM I: p < 0.001, CM II: p < 0.05, Surgery I: p < 0.05 and Surgery II: p < 0.05). CM II course students who dedicated more time to completing cases received better grades (p < 0.05). The pattern of use of Full code were similar in students regardless their academic performance. In addition, students with higher academic performance were more likely to have higher scores in the platform (p < 0.001). Conclusion The use of gamification in clinical simulation was highly feasible in students of medicine regardless their academic performance. Prospective and interventional studies are needed to assess if the Full Code platform directly affect the learning outcomes.

Artículos y libros

Maria Amalia Salafia mail , María Elena Perez-Ochoa mail ,

Salafia

open

Novel hybrid transfer neural network for wheat crop growth stages recognition using field images

Wheat is one of the world’s most widely cultivated cereal crops and is a primary food source for a significant portion of the population. Wheat goes through several distinct developmental phases, and accurately identifying these stages is essential for precision farming. Determining wheat growth stages accurately is crucial for increasing the efficiency of agricultural yield in wheat farming. Preliminary research identified obstacles in distinguishing between these stages, negatively impacting crop yields. To address this, this study introduces an innovative approach, MobDenNet, based on data collection and real-time wheat crop stage recognition. The data collection utilized a diverse image dataset covering seven growth phases ‘Crown Root’, ‘Tillering’, ‘Mid Vegetative’, ‘Booting’, ‘Heading’, ‘Anthesis’, and ‘Milking’, comprising 4496 images. The collected image dataset underwent rigorous preprocessing and advanced data augmentation to refine and minimize biases. This study employed deep and transfer learning models, including MobileNetV2, DenseNet-121, NASNet-Large, InceptionV3, and a convolutional neural network (CNN) for performance comparison. Experimental evaluations demonstrated that the transfer model MobileNetV2 achieved 95% accuracy, DenseNet-121 achieved 94% accuracy, NASNet-Large achieved 76% accuracy, InceptionV3 achieved 74% accuracy, and the CNN achieved 68% accuracy. The proposed novel hybrid approach, MobDenNet, that synergistically merges the architectures of MobileNetV2 and DenseNet-121 neural networks, yields highly accurate results with precision, recall, and an F1 score of 99%. We validated the robustness of the proposed approach using the k-fold cross-validation. The proposed research ensures the detection of growth stages with great promise for boosting agricultural productivity and management practices, empowering farmers to optimize resource distribution and make informed decisions.

Producción Científica

Aisha Naseer mail , Madiha Amjad mail , Ali Raza mail , Kashif Munir mail , Aseel Smerat mail , Henry Fabian Gongora mail henry.gongora@uneatlantico.es, Carlos Eduardo Uc Ríos mail carlos.uc@unini.edu.mx, Imran Ashraf mail ,

Naseer

Enlaces de interés

Enlaces de interés

FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas

Abstract

Actions (login required)

TEMÁTICA

ACCESO

IDIOMA

Filtros