Applied Sciences

Research

Jump to: Other

14 pages, 1413 KiB

Open AccessArticle

Enhanced Speech Emotion Recognition Using Conditional-DCGAN-Based Data Augmentation

by Kyung-Min Roh and Seok-Pil Lee

Appl. Sci. 2024, 14(21), 9890; https://doi.org/10.3390/app14219890 - 29 Oct 2024

Viewed by 623

Abstract

With the advancement of Artificial Intelligence (AI) and the Internet of Things (IoT), research in the field of emotion detection and recognition has been actively conducted worldwide in modern society. Among this research, speech emotion recognition has gained increasing importance in various areas [...] Read more.

With the advancement of Artificial Intelligence (AI) and the Internet of Things (IoT), research in the field of emotion detection and recognition has been actively conducted worldwide in modern society. Among this research, speech emotion recognition has gained increasing importance in various areas of application such as personalized services, enhanced security, and the medical field. However, subjective emotional expressions in voice data can be perceived differently by individuals, and issues such as data imbalance and limited datasets fail to provide the diverse situations necessary for model training, thus limiting performance. To overcome these challenges, this paper proposes a novel data augmentation technique using Conditional-DCGAN, which combines CGAN and DCGAN. This study analyzes the temporal signal changes using Mel-spectrograms extracted from the Emo-DB dataset and applies a loss function calculation method borrowed from reinforcement learning to generate data that accurately reflects emotional characteristics. To validate the proposed method, experiments were conducted using a model combining CNN and Bi-LSTM. The results, including augmented data, achieved significant performance improvements, reaching WA 91.46% and UAR 91.61%, compared to using only the original data (WA 79.31%, UAR 78.16%). These results outperform similar previous studies, such as those reporting WA 84.49% and UAR 83.33%, demonstrating the positive effects of the proposed data augmentation technique. This study presents a new data augmentation method that enables effective learning even in situations with limited data, offering a progressive direction for research in speech emotion recognition. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

15 pages, 5549 KiB

Open AccessArticle

Thermal Threat Monitoring Using Thermal Image Analysis and Convolutional Neural Networks

by Mariusz Marzec and Sławomir Wilczyński

Appl. Sci. 2024, 14(19), 8878; https://doi.org/10.3390/app14198878 - 2 Oct 2024

Viewed by 732

Abstract

Monitoring of the vital signs or environment of disabled people is currently very popular because it increases their safety, improves their quality of life and facilitates remote care. The article proposes a system for automatic protection against burns based on the detection of [...] Read more.

Monitoring of the vital signs or environment of disabled people is currently very popular because it increases their safety, improves their quality of life and facilitates remote care. The article proposes a system for automatic protection against burns based on the detection of thermal threats intended for blind or visually impaired people. Deep learning methods and CNNs were used to analyze images recorded by mobile thermal cameras. The proposed algorithm analyses thermal images covering the field of view of a user for the presence of objects with high or very high temperatures. If the user’s hand appears in such an area, the procedure warning about the possibility of burns is activated and the algorithm generates an alarm. To achieve this effect, the thermal images were analyzed using the 15-layered convolutional neural network proposed in the article. The proposed solution provided the efficiency of detecting threat situations of over 99% for a set of more than 21,000 images. Tests were carried out for various network configurations, architecture and both the accuracy and precision of hand detection was 99.5%, whereas sensitivity reached 99.7%. The effectiveness of burn risk detection was 99.7%—a hot object—and the hand appeared simultaneously in the image. The presented method allows for quick, effective and automatic warning against thermal threats. The optimization of the model structure allows for its use with mobile devices such as smartphones and mobile thermal imaging cameras. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

15 pages, 2143 KiB

Open AccessArticle

A Virtual Reality-Based Simulation Tool for Assessing the Risk of Falls in Older Adults

by Muhammad Asif Ahmad, Élvio Rúbio Gouveia and Sergi Bermúdez i Badia

Appl. Sci. 2024, 14(14), 6251; https://doi.org/10.3390/app14146251 - 18 Jul 2024

Viewed by 1082

Abstract

Falls are considered a significant cause of disability, pain, and premature deaths in older adults, often due to sedentary lifestyles and various risk factors. Combining immersive virtual reality (IVR) with physical exercise, or exergames, enhances motivation and personalizes training, effectively preventing falls by [...] Read more.

Falls are considered a significant cause of disability, pain, and premature deaths in older adults, often due to sedentary lifestyles and various risk factors. Combining immersive virtual reality (IVR) with physical exercise, or exergames, enhances motivation and personalizes training, effectively preventing falls by improving strength and balance in older people. IVR technology may increase the ecological validity of the assessments. The main goal of our study was to assess the feasibility of using a KAVE-based VR platform combining simulations of Levadas and a cable car to perform a balanced assessment and profiling of the older adult population for high risk of falls and the related user experience. A VR-based platform using a Wii balance board and a CAVE was developed to assess balance and physical fitness. Validated by the Biodex Balance System (BBS), 25 older adults participated in this study. The usability and presence were measured through the System Usability Scale and ITC-SOPI questionnaires, respectively. The IVR system showed a high presence and a good usability score of 75. Significant effects were found in the maximum excursion of the centre of pressure (COP) on the anterior–posterior axis during the cable car simulation (CCS), correlating with BBS metrics. Multiple discriminative analysis models and the support vector machine classified fall risk with moderate to high accuracy, precision, and recall. The system accurately identified all high-risk participants using the leave-one-out method. This study suggests that an IVR-based platform based on simulations with high ecological validity can be used to assess physical fitness and identify individuals at a higher risk of falls. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

17 pages, 5957 KiB

Open AccessArticle

Inertial and Flexible Resistive Sensor Data Fusion for Wearable Breath Recognition

by Mehdi Zabihi, Bhawya, Parikshit Pandya, Brooke R. Shepley, Nicholas J. Lester, Syed Anees, Anthony R. Bain, Simon Rondeau-Gagné and Mohammed Jalal Ahamed

Appl. Sci. 2024, 14(7), 2842; https://doi.org/10.3390/app14072842 - 28 Mar 2024

Cited by 1 | Viewed by 3141

Abstract

This paper proposes a novel data fusion technique for a wearable multi-sensory patch that integrates an accelerometer and a flexible resistive pressure sensor to accurately capture breathing patterns. It utilizes an accelerometer to detect breathing-related diaphragmatic motion and other body movements, and a [...] Read more.

This paper proposes a novel data fusion technique for a wearable multi-sensory patch that integrates an accelerometer and a flexible resistive pressure sensor to accurately capture breathing patterns. It utilizes an accelerometer to detect breathing-related diaphragmatic motion and other body movements, and a flex sensor for muscle stretch detection. The proposed sensor data fusion technique combines inertial and pressure sensors to eliminate nonbreathing body motion-related artifacts, ensuring that the filtered signal exclusively conveys information pertaining to breathing. The fusion technique mitigates the limitations of relying solely on one sensor’s data, providing a more robust and reliable solution for continuous breath monitoring in clinical and home environments. The sensing system was tested against gold-standard spirometry data from multiple participants for various breathing patterns. Experimental results demonstrate the effectiveness of the proposed approach in accurately monitoring breathing rates, even in the presence of nonbreathing-related body motion. The results also demonstrate that the multi-sensor patch presented in this paper can accurately distinguish between varying breathing patterns both at rest and during body movements. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

19 pages, 3672 KiB

Open AccessArticle

Estimation of Systolic and Diastolic Blood Pressure for Hypertension Identification from Photoplethysmography Signals

by Hygo Sousa De Oliveira, Rafael Albuquerque Pinto, Eduardo James Pereira Souto and Rafael Giusti

Appl. Sci. 2024, 14(6), 2470; https://doi.org/10.3390/app14062470 - 14 Mar 2024

Cited by 1 | Viewed by 2234

Abstract

Continuous monitoring plays a crucial role in diagnosing hypertension, characterized by the increase in Arterial Blood Pressure (ABP). The gold-standard method for obtaining ABP involves the uncomfortable and invasive technique of cannulation. Conversely, ABP can be acquired non-invasively by using Photoplethysmography (PPG). This [...] Read more.

Continuous monitoring plays a crucial role in diagnosing hypertension, characterized by the increase in Arterial Blood Pressure (ABP). The gold-standard method for obtaining ABP involves the uncomfortable and invasive technique of cannulation. Conversely, ABP can be acquired non-invasively by using Photoplethysmography (PPG). This non-invasive approach offers the advantage of continuous BP monitoring outside a hospital setting and can be implemented in cost-effective wearable devices. PPG and ABP signals differ in scale values, which creates a non-linear relationship, opening avenues for the utilization of algorithms capable of detecting non-linear associations. In this study, we introduce Neural Model of Blood Pressure (NeuBP), which estimates systolic and diastolic values from PPG signals. The problem is treated as a binary classification task, distinguishing between Normotensive and Hypertensive categories. Furthermore, our research investigates NeuBP’s performance in classifying different BP categories, including Normotensive, Prehypertensive, Grade 1 Hypertensive, and Grade 2 Hypertensive cases. We evaluate our proposed method by using data from the publicly available MIMIC-III database. The experimental results demonstrate that NeuBP achieves results comparable to more complex models with fewer parameters. The mean absolute errors for systolic and diastolic values are 5.02 mmHg and 3.11 mmHg, respectively. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

22 pages, 1026 KiB

Open AccessArticle

Real-Time Human Activity Recognition on Embedded Equipment: A Comparative Study

by Houda Najeh, Christophe Lohr and Benoit Leduc

Appl. Sci. 2024, 14(6), 2377; https://doi.org/10.3390/app14062377 - 12 Mar 2024

Cited by 1 | Viewed by 1351

Abstract

As living standards improve, the growing demand for energy, comfort, and health monitoring drives the increased importance of innovative solutions. Real-time recognition of human activities (HAR) in smart homes is of significant relevance, offering varied applications to improve the quality of life of [...] Read more.

As living standards improve, the growing demand for energy, comfort, and health monitoring drives the increased importance of innovative solutions. Real-time recognition of human activities (HAR) in smart homes is of significant relevance, offering varied applications to improve the quality of life of fragile individuals. These applications include facilitating autonomy at home for vulnerable people, early detection of deviations or disruptions in lifestyle habits, and immediate alerting in the event of critical situations. The first objective of this work is to develop a real-time HAR algorithm in embedded equipment. The proposed approach incorporates the event dynamic windowing based on space-temporal correlation and the knowledge of activity trigger sensors to recognize activities in the case of a record of new events. The second objective is to approach the HAR task from the perspective of edge computing. In concrete terms, this involves implementing a HAR algorithm in a “home box”, a low-power, low-cost computer, while guaranteeing performance in terms of accuracy and processing time. To achieve this goal, a HAR algorithm was first developed to perform these recognition tasks in real-time. Then, the proposed algorithm is ported on three hardware architectures to be compared: (i) a NUCLEO-H753ZI microcontroller from ST-Microelectronics using two programming languages, C language and MicroPython; (ii) an ESP32 microcontroller, often used for smart-home devices; and (iii) a Raspberry-PI, optimizing it to maintain accuracy of classification of activities with a requirement of processing time, memory resources, and energy consumption. The experimental results show that the proposed algorithm can be effectively implemented on a constrained resource hardware architecture. This could allow the design of an embedded system for real-time human activity recognition. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

31 pages, 6952 KiB

Open AccessArticle

Device Position-Independent Human Activity Recognition with Wearable Sensors Using Deep Neural Networks

by Sakorn Mekruksavanich and Anuchit Jitpattanakul

Appl. Sci. 2024, 14(5), 2107; https://doi.org/10.3390/app14052107 - 3 Mar 2024

Cited by 1 | Viewed by 2464

Abstract

Human activity recognition (HAR) identifies people’s motions and actions in daily life. HAR research has grown with the popularity of internet-connected, wearable sensors that capture human movement data to detect activities. Recent deep learning advances have enabled more HAR research and applications using [...] Read more.

Human activity recognition (HAR) identifies people’s motions and actions in daily life. HAR research has grown with the popularity of internet-connected, wearable sensors that capture human movement data to detect activities. Recent deep learning advances have enabled more HAR research and applications using data from wearable devices. However, prior HAR research often focused on a few sensor locations on the body. Recognizing real-world activities poses challenges when device positioning is uncontrolled or initial user training data are unavailable. This research analyzes the feasibility of deep learning models for both position-dependent and position-independent HAR. We introduce an advanced residual deep learning model called Att-ResBiGRU, which excels at accurate position-dependent HAR and delivers excellent performance for position-independent HAR. We evaluate this model using three public HAR datasets: Opportunity, PAMAP2, and REALWORLD16. Comparisons are made to previously published deep learning architectures for addressing HAR challenges. The proposed Att-ResBiGRU model outperforms existing techniques in accuracy, cross-entropy loss, and F1-score across all three datasets. We assess the model using k-fold cross-validation. The Att-ResBiGRU achieves F1-scores of 86.69%, 96.23%, and 96.44% on the PAMAP2, REALWORLD16, and Opportunity datasets, surpassing state-of-the-art models across all datasets. Our experiments and analysis demonstrate the exceptional performance of the Att-ResBiGRU model for HAR applications. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

Other

Jump to: Research

14 pages, 3354 KiB

Open AccessStudy Protocol

Protocol for the Development of Automatic Multisensory Systems to Analyze Human Activity for Functional Evaluation: Application to the EYEFUL System

by Paula Obeso-Benítez, Marta Pérez-de-Heredia-Torres, Elisabet Huertas-Hoyas, Patricia Sánchez-Herrera-Baeza, Nuria Máximo-Bocanegra, Sergio Serrada-Tejeda, Marta Marron-Romera, Javier Macias-Guarasa, Cristina Losada-Gutierrez, Sira E. Palazuelos-Cagigas, Jose L. Martin-Sanchez and Rosa M. Martínez-Piédrola

Appl. Sci. 2024, 14(8), 3415; https://doi.org/10.3390/app14083415 - 18 Apr 2024

Viewed by 881

Abstract

The EYEFUL system represents a pioneering initiative designed to leverage multisensory systems for the automatic evaluation of functional ability and determination of dependency status in people performing activities of daily living. This interdisciplinary effort, bridging the gap between engineering and health sciences, aims [...] Read more.

The EYEFUL system represents a pioneering initiative designed to leverage multisensory systems for the automatic evaluation of functional ability and determination of dependency status in people performing activities of daily living. This interdisciplinary effort, bridging the gap between engineering and health sciences, aims to overcome the limitations of current evaluation tools, which often lack objectivity and fail to capture the full range of functional capacity. Until now, it has been derived from subjective reports and observational methods. By integrating wearable sensors and environmental technologies, EYEFUL offers an innovative approach to quantitatively assess an individual’s ability to perform activities of daily living, providing a more accurate and unbiased evaluation of functionality and personal independence. This paper describes the protocol planned for the development of the EYEFUL system, from the initial design of the methodology to the deployment of multisensory systems and the subsequent clinical validation process. The implications of this research are far-reaching, offering the potential to improve clinical evaluations of functional ability and ultimately improve the quality of life of people with varying levels of dependency. With its emphasis on technological innovation and interdisciplinary collaboration, the EYEFUL system sets a new standard for objective evaluation, highlighting the critical role of advanced screening technologies in addressing the challenges of modern healthcare. We expect that the publication of the protocol will help similar initiatives by providing a structured approach and rigorous validation process. Full article

(This article belongs to the Special Issue Human Activity Recognition (HAR) in Healthcare, 2nd Edition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Human Activity Recognition (HAR) in Healthcare, 2nd Edition

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (8 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI