EAI Endorsed Transactions on Pervasive Health and Technology

Visit the new journal website to submit and consult our contents: https://publications.eai.eu/index.php/phat/index

Editor(s)-in-Chief: Gonçalo Marques and Nenad Filipovic

Aims & Scope
Indexing
Editorial Board
Special Issues

EAI Endorsed Transactions on Pervasive Health and Technology is open access, a peer-reviewed scholarly journal focused on personal electronic health assistants, health crowdsourcing, data mining, knowledge management, IT applications to the needs of patients, disease prevention, and awareness, electronic and mobile health platforms including design and more. The journal publishes research articles, review articles, commentaries, editorials, technical articles, and short communications. From 2021, the journal publishes five issues per year. Authors are not charged for article submission and processing.

Knowledge Representation and Reasoning

Physiological models for interpreting medical sensor data
Sensing/Actuating Technologies and Pervasive Computing
Medicine, Nursing, and Allied Health Professions
Human-Computer Interaction and Computer Supported Cooperative Work
Hardware and Software Infrastructures
Activity recognition and fall detection
User modelling and personalization
Modelling of Pervasive Healthcare environments
Sensor-based decision support systems
Design and evaluation of patient and ambient-related sensors
Wearable and implantable sensor integration
Data fusion in pervasive healthcare environments
Data mining of medical patient records
Software architectures
Electronic Health Records

Understanding Users

Identifying and addressing stakeholder needs
Usability and acceptability
Barriers and enablers to adoption
Social implications of pervasive health technology, and social inclusion
Coverage and delivery of pervasive healthcare services
Patient and caregiver empowerment
Diversity: population and condition-specific requirements
Inclusive research and design: engaging underrepresented populations
Digital interventions and health behavior change

Applications

Autonomous systems to support independent living
Clinical applications, validation and evaluation studies
Telemedicine and mHealth solutions
Chronic disease and health risk management applications
Health/Wellbeing promotion and disease prevention
Home based health and wellness measurement and monitoring
Continuous vs event-driven monitoring of patients
Smart homes and hospitals
Using mobile devices in the storage, update, and transmission of patient data
Wellbeing and lifestyle support
Systems to support individuals with auditory, cognitive, or vision impairments
Systems to support caregivers

Pervasive Healthcare Management

Challenges surrounding data quality
Standards and interoperability in pervasive healthcare
Business cases and cost issues
Security and privacy issues
Training of healthcare professional for pervasive healthcare
Legal and regulatory issues
Staffing and resource management

Editors-in-Chief
Gonçalo Marques, Polytechnic of Coimbra, Portugal
Nenad Filipovic, University of Kragujevac, Serbia
Area Editors
Alberto Antonietti (École Polytechnique Fédérale de Lausanne, Switzerland)
Alejandro Dominguez Rodriguez (Autonomous University of Baja California)
Alessandro Ruggiero (University of Salerno, Italy)
Alexandros Tzallas (Technological Educational Institute of Epirus)
Andjela Blagojevic (University of Kragujevac, Serbia)
Anind Dey (University of Washington)
Ansar-Ul-Haque Yasar (Hasselt University, Belgium)
Antonella Carbonaro (Universita' di Bologna, Italy)
Arijit Ukil (Tata Consultancy Services)
Asimina Kiourti (The Ohio State University)
AtaUllah Ghafoor (National University of Modern Languages, Islamabad, Pakistan.)
Bert Arnrich (Boğaziçi University, Istanbul, Turkey)
Boban Stojanovic (University of Kragujevac, Serbia)
Branko Arsic (University of Kragujevac, Serbia)
Constantinos Pattichis (University of Cyprus, Cyprus)
Daojing He (South China University of Technology, China)
Djordje Jakovljevic (Coventry University, UK)
Eduard Babulak (National Science Foundation, USA)
Emilija Stojmenova (Duh University of Ljubljana)
Emilio Serrano (Technical University of Madrid, Spain)
Frank Wallhoff (Jade University of Applied Sciences)
Giorgos Giannakakis (Foundation for Research and Technology Hellas, Greece)
Honggang Wang (UMASS. USA)
Kashif Saleem (King Saud University)
Laszlo Bokor (BME, Hungary)
Lazar Dasic (University of Kragujevac, Serbia)
Marcela Deyanira Rodriguez Urrea (Autonomous University of Baja California)
Marko Robnik-Sikonja (University of Ljubljana, Slovenia)
Mauro Femminella (University of Perugia, Italy)
Melina Frenken (Jade University of Applied Sciences)
Michalis Zervakis (Technical University of Crete, Greece)
Milos Ivanovic (University of Kragujevac, Serbia)
Milos Kotlar (University of Belgrade, Serbia)
Mohammad Upal Mahfuz (University of Wisconsin-Green Bay)
Mojtaba Taherisadr (University of Michigan)
Mosabber Uddin Ahmed (University of Dhaka)
Nadeem Javaid (COMSATS Institute of Information Technology, Islamabad, Pakistan)
Netzahualcoyotl Hernandez-Cruz (Oxford University, UK)
Nikolaos Bourbakis, Wright State University in Ohio, United States
Pan Zheng, University of Canterbury, New Zealand
Pietro Cipresso (Istituto Auxologico, Milan, Italy)
Razan Hamed (New York Institute of Technology, NY, USA)
Riccardo Martoglia (University of Modena and Reggio Emilia, Italy)
Saikishor Jangiti (SASTRA Deemed University, India)
Silvia Serino (Catholic University of Milan, Italy)
Stefan Rahr Wagner (Aarhus University)
Tanvir Zia (School of Computing & Mathematics, Charles Sturt University, Australia)
Tessa Dekkers (Delft University, The Netherlands)
Tijana Sustersic (Faculty of Engineering, University of Kragujevac)
Veljko Milutinovic (University of Belgrade, Serbia)
Venet Osmani (CREATE-NET, Trento, Italy)
Wilko Heuten (OFFIS, Germany)
Zhihan Lv (Qingdao University, China)
Zoran Bosnic (University of Ljubljana, Slovenia)
Ognjen Pavic (Institute for Information Technology, University of Kragujevac, Serbia)
Analúcia Schiaffino Morales (Federal University of Santa Catarina, Brazil)

Recently Published
Most Popular

Masked GANs for Face Completion: A Novel Deep Learning Approach
Appears in:
phat 24(1):

Authors:
Anshuman Sharma, Biswaroop Nath, Tejaswini Kar, D Khasim

Published:
15th Jan 2024

Abstract:
INTRODUCTION: Recent deep learning based image editing methods have achieved promising results for removing object in an image but fail to generate appreciable performance for removing large objects of complex nature, especially mask from facial images. Towards this goal the objective of this work …INTRODUCTION: Recent deep learning based image editing methods have achieved promising results for removing object in an image but fail to generate appreciable performance for removing large objects of complex nature, especially mask from facial images. Towards this goal the objective of this work is to remove mask objects in facial images. In this study, authors propose a novel approach for face completion using Generative Adversarial Networks (GANs) that utilize masked data. This technology can help in image restoration and preservation, thus enabling us to cherish those memories that are held dear to our hearts.
OBJECTIVES: Train a GAN to learn the mapping from incomplete to complete face images by utilizing a masked input image.
METHODS: The discriminator is trained to distinguish between face images and full ground truth images. Our results indicate that our technique generates high-quality, realistic facial images that are visually comparable to the ground truth and that it can generalise to new faces that were not encountered during training.
RESULTS: Our findings indicate that GANs with masked inputs are a good approach for generating whole face images from partial or masked data.
CONCLUSION: Our experimental findings show that our method produces facial images of great quality and realism that are visually equivalent to the actual thing. Our proposed approach can also be applied to fresh faces that weren’t seen. The performance can still be improved further using larger dataset. Also, further investigation into adversial attacks may help in improving performance. This technology can be further utilized for developing realtime mask removal software as well.
more »
Role of biodentine in endodontics: a bibliometric and scientometric analysis
Appears in:
phat 24(1):

Authors:
Maria Mihaela Iuga, Rafael Romero-Carazas, Fernando Espada-Salgado, Bogdan Oprea, Stefan Vasile Stefanescu, Mayra Lavado-García

Published:
1st Jan 2024

Abstract:
Objective. Vital Pulp therapy using Biodentine has advanced, introducing and allowing new procedures and treatments, hence medical education should focus on research and publication. The aim of the study was to perform a bibliometric and scientometric analysis of the literature on the role of biode…Objective. Vital Pulp therapy using Biodentine has advanced, introducing and allowing new procedures and treatments, hence medical education should focus on research and publication. The aim of the study was to perform a bibliometric and scientometric analysis of the literature on the role of biodentine in endodontics from 2013 to 2023.
Methodology: A bibliometric and scientometric quantitative study formed the basis of the methodology. Scientific production indicators were generated from 87 documents selected from Scopus using English keywords ("Biodentine", "Endodontic").
Results: Since 2016, the number of papers published on this topic increased (69%), indicating a growing interest towards this material. Brazil is the country with the highest scientific interest (19%), and the Universidade Estadual Paulista Júlio de Mesquita Filho with the most publications (n=9). The International Endodontic Journal received 344 citations, Tanomaru-Filho M. (n=6) being the most cited.
Conclusion: It is concluded that the role of biodentine in endodontics has grown not only in production and authorship, but also in scope and medical research, incorporating these resources in various scenarios and clinical settings.
more »
An Ensemble Models for the Prediction of Sickle Cell Disease from Erythrocytes Smears
Appears in:
phat 24(1):

Authors:
Oluwafisayo Babatope Ayoade, Tinuke Omolewa Oladele, Agbotiname Lucky Imoize, Jerome Adetoye Adeloye, Joseph Bambidele Awotunde, Segun Omotayo Olorunyomi, Oulsola Theophilius Faboya, Ayorinde Oladele Idowu

Published:
1st Jan 2024

Abstract:
INTRODUCTION: The human blood as a collection of tissues containing Red Blood Cells (RBCs), circular in shape and acting as an oxygen carrier, are frequently deformed by multiple blood diseases inherited from parents. These hereditary diseases of blood involve abnormal haemoglobin (Hb) or anemia wh…INTRODUCTION: The human blood as a collection of tissues containing Red Blood Cells (RBCs), circular in shape and acting as an oxygen carrier, are frequently deformed by multiple blood diseases inherited from parents. These hereditary diseases of blood involve abnormal haemoglobin (Hb) or anemia which are major public health issues. Sickle Cell Disease (SCD) is one of the common non-communicable disease and genetic disorder due to changes in hematological conditions of the RBCs which often causes the inheritance of mutant Hb genes by the patient..
OBJECTIVES: The process of manual valuation, predictions and diagnosis of SCD necessitate for a passionate time spending and if not done properly can lead to wrong predictions and diagnosis. Machine Learning (ML), a branch of AI which emphases on building systems that improve performance based on the data they consume is appropriate. Despite previous research efforts in predicting with single ML algorithm, the existing systems still suffer from high false and wrong predictions.
METHODS: Thus, this paper aimed at performing comparative analysis of individual ML algorithms and their ensemble models for effective predictions of SCD (elongated shapes) in erythrocytes blood cells. Three ML algorithms were selected, and ensemble models were developed to perform the predictions and metrics were used to evaluate the performance of the model using accuracy, sensitivity, Receiver Operating Characteristics-Area under Curve (ROC-AUC) and F1 score metrics. The results were compared with existing literature for model(s) with the best prediction metrics performance..
RESULTS: The analysis was carried out using Python programming language. Individual ML algorithms reveals that their accuracies show MLR=87%, XGBoost=90%, and RF=93%, while hybridized RF-MLR=92% and RF-XGBoost=99%. The accuracy of RF-XGBoost of 99% outperformed other individual ML algorithms and Hybrid models.
CONCLUSION: Thus, the study concluded that involving hybridized ML algorithms in medical datasets increased predictions performance as it removed the challenges of high variance, low accuracy and feature noise and biases of medical datasets. The paper concluded that ensemble classifiers should be considered to improve sickle cell disease predictions.
more »
Statistical determination of COVID-19 mortality in age groups in the Ecuadorian Highlands
Appears in:
phat 24(1):

Authors:
Juan Santillán-Lima, Fernando Molina-Granja, Patricio Santillán-Lima, Daniela Caichug-Rivera, Raúl Lozada-Yánez, Washington Luna-Encalada

Published:
1st Jan 2024

Abstract:
INTRODUCTION: A problem plaguing humanity is the countless deaths from COVID-19. Conducting a statistical study based on deaths data during the pandemic will allow us to identify the age groups most vulnerable to death. This information can be used by public and private health organizations to take…INTRODUCTION: A problem plaguing humanity is the countless deaths from COVID-19. Conducting a statistical study based on deaths data during the pandemic will allow us to identify the age groups most vulnerable to death. This information can be used by public and private health organizations to take preventive measures in the most vulnerable population.
OBJECTIVES: To determine the age groups most vulnerable to COVID 19 in the Ecuadorian highlands during the periods 2020-2021.
METHODS: The "Bootstrap method to calculate the confidence interval for proportions" was applied to the age groups of those who died from COVID in the Ecuadorian highlands in 2020 and 2021. The method is implemented in R Studio.
RESULTS: The adjusted confidence intervals suggest that there is a 95% confidence that the age group most prone to death from COVID-19 is the Elderly with a point estimate of 72.70% in 2020 and 76.61% in 2021. The main subgroup of 80 to 90 years followed by 65 to 70 years.
CONCLUSION: Adjusted confidence intervals indicate that there is a 95% confidence that the age subgroup most prone to death from COVID-19 is 80 to 90 years with a point estimate of 16.13% in 2020 and 16.85% in 2021. And 65 to 70 years with a point estimate of 12.98% in 2020 and 12.57% in 2021.
more »
Satisfaction with Life and its Relationship with Mental Health in University Professors
Appears in:
phat 24(1):

Authors:
Djamila Gallegos-Espinoza, Carlos LaRosa-Longobardi, Livia Piñas-Rivera, Lucía Asencios-Trujillo, Lida Asencios-Trujillo, Hernan Matta-Solis

Published:
1st Jan 2024

Abstract:
Introduction: The satisfaction with the life in university professors will have an important value for the personal evaluation of themselves on the quality of their own experiences and in addition to a well-being of personal feeling. Aim: to determine Satisfaction with life and its relationship wi…Introduction: The satisfaction with the life in university professors will have an important value for the personal evaluation of themselves on the quality of their own experiences and in addition to a well-being of personal feeling.
Aim: to determine Satisfaction with life and its relationship with mental health in professors of a university in North Lima.
Methods: a quantitative, descriptive and cross-sectional study, with a population of 270 older adults, who answered a questionnaire of sociodemographic aspects and the scale of satisfaction with life.
Results: 54 (20%) of the older adults were dissatisfied with life, 32 (11.9%) slightly dissatisfied, 39 (14.4%) are neutral with respect to life satisfaction, 84 (31.1%) are satisfied, and 50 (18.5%) are very satisfied.
Conclusions: educational talks should be held for the elderly, where the experience of positive emotions during that stage of life continues to be promoted and allows them to have a better satisfaction with their lives.
more »
Artificial Intelligence in Medical Filed
Appears in:
phat 24(1):

Authors:
Iram Fatima, Veena Grover, Ihtiram Raza Khan, Naved Ahmad, Ambooj Yadav

Published:
28th Dec 2023

Abstract:
In the healthcare industry artificial intelligence (AI) has become a disruptive technology that is revolutionizing patient care, diagnostics, and research. This abstract provides an overview of the main points and findings related to AI in healthcare exploring its advancements, applications, and et…In the healthcare industry artificial intelligence (AI) has become a disruptive technology that is revolutionizing patient care, diagnostics, and research. This abstract provides an overview of the main points and findings related to AI in healthcare exploring its advancements, applications, and ethical challenges. The rapid growth of AI technologies has led to remarkable improvements in healthcare. AI algorithms have demonstrated exceptional capabilities in analyzing number of patient data, enabling early disease detection, personalized treatment plans, and improved patient outcomes. Machine learning algorithms, such as deep learning and natural language processing, have been effectively employed to analyze medical images, predict disease progression, and support clinical decision-making. AI applications in healthcare span across various domains, including radiology, pathology, genomics, drug discovery, and patient monitoring. Telemedicine and AI-driven virtual health assistants have extended healthcare access to remote areas, empowering patients with self-care tools and enabling real-time communication with healthcare professionals. While it's undeniable that AI brings significant advantages to the field of healthcare, it's vital to emphasize the importance of ethical concerns. Additionally, ensuring that AI algorithms are transparent and interpretable is essential for establishing trust and promoting the responsible use of AI technology in clinical environments.
more »
Analyzing How AI And Emotional Intelligence Affect Indian IT Professional’s Decision-Making
Appears in:
phat 24(1):

Authors:
Anita Shukla, Alka Algnihotri, Bhawna Singh

Published:
20th Dec 2023

Abstract:
Artificial intelligence (AI) is transforming how we work and make choices, but it also poses ethical and societal issues including algorithmic discrimination and dehumanization. It is critical to take into account corporate culture, emotional intelligence, cooperation, communication, and constant l…Artificial intelligence (AI) is transforming how we work and make choices, but it also poses ethical and societal issues including algorithmic discrimination and dehumanization. It is critical to take into account corporate culture, emotional intelligence, cooperation, communication, and constant learning when using AI systems in the workplace. It has been demonstrated that emotional intelligence increases AI adoption, efficacy, and performance across a variety of sectors. But ethical concerns and trouble making decisions are also important. Effective collaboration, communication, and corporate culture are crucial for successful AI adoption, and continuing learning and development are essential for enhancing decision-making abilities. AI ethics in the workplace necessitate a comprehensive strategy that considers both technical and non-technical aspects. This study looks at the benefits of emotional intelligence, moral concerns, effective stakeholder and IT specialist engagement, organisational culture, and potential threats of artificial intelligence (AI) in decision-making. The study underlines the value of continuous AI learning and development.
more »
Harnessing the Power of Ensemble Machine Learning for the Heart Stroke Classification
Appears in:
phat 24(1):

Authors:
Purnima Pal, Manju Nandal, Srishti Dikshit, Aarushi Thusu, Harsh Vikram Singh

Published:
15th Dec 2023

Abstract:
A heart stroke, also known as a myocardial infarction or heart attack, is a critical medical condition that arises when there is an obstruction in the coronary arteries that provide blood to the heart muscles. This blockage results in a diminished flow of blood and oxygen to a specific area of the …A heart stroke, also known as a myocardial infarction or heart attack, is a critical medical condition that arises when there is an obstruction in the coronary arteries that provide blood to the heart muscles. This blockage results in a diminished flow of blood and oxygen to a specific area of the heart. This abrupt interruption initiates a gradual sequence of heart muscle damage, which can lead to varying degrees of functional impairment. The severity of these impairments is primarily determined by the precise location of the heart muscle affected. Therefore, it is of utmost importance to identify the warning signs and symptoms of a stroke as soon as possible. This is the objective of this paper is to early recognition and prompt action can significantly improve the chances of a healthy and fulfilling life following a stroke. In this research work, the Stroke dataset is pre-processed and on pre-processed dataset machine learning and ensemble machine learning techniques were employed to develop and assess several models aimed at creating a stable framework for predicting the enduring stroke risk. And various matrices like accuracy, F1 score, ROC, precision, and recall are calculated. Among all models, AdaBoost model demonstrated exceptional performance validated through multiple metrics, including Precision, AUC, recall, accuracy, and F1-measure. The results underscored superiority of the AdaBoost classification method, achieving an impressive Accuracy of 99%. AdaBoost model may serve as a stable framework for predicting enduring stroke risk, emphasizing its potential utility in clinical settings for identifying individuals at higher risk of experiencing a stroke.
more »
Blockchain-Enabled Hyperledger Fabric to Secure Data Transfer Mechanism for Medical Cyber-Physical System: Overview, Issues, and Challenges
Appears in:
phat 24(1):

Authors:
P. Vinayasree, A. Mallikarjuna Reddy

Published:
30th Nov 2023

Abstract:
This paper proposes a model to address the challenges faced by medical cyber-physical systems (MCPS) by implementing a permissioned blockchain platform. The platform incorporates the unique properties of blockchain into the network of affected systems, including decentralization, transparency, and …This paper proposes a model to address the challenges faced by medical cyber-physical systems (MCPS) by implementing a permissioned blockchain platform. The platform incorporates the unique properties of blockchain into the network of affected systems, including decentralization, transparency, and immutability. The platform also includes a novel technique to secure MCPS through an automated access-control manager. This manager allows users to control who has access to their data, and can be configured to trust a third party if desired. The paper also extends into networked medical device systems, and discusses how the platform can be used to address critical is-sues specific to this field, such as network design. Finally, the paper discusses how various security features can be integrated into ultra-small devices, enhancing the protection of embedded systems. The overall objective of this research is to develop a secure and efficient data transfer mechanism for MCPS. The proposed platform addresses the challenges faced by MCPS by incorporating the unique properties of blockchain.
more »
A Deep Survey on Human Activity Recognition Using Mobile and Wearable Sensors
Appears in:
phat 24(1):

Authors:
Shaik Jameer, Hussain Syed

Published:
27th Nov 2023

Abstract:
Activity-based wellness management is thought to be a powerful application for mobile health. It is possible to provide context-aware wellness services and track human activity thanks to accessing for multiple devices as well as gadgets that we use every day. Generally in smart gadgets like phones,…Activity-based wellness management is thought to be a powerful application for mobile health. It is possible to provide context-aware wellness services and track human activity thanks to accessing for multiple devices as well as gadgets that we use every day. Generally in smart gadgets like phones, watches, rings etc., the embedded sensors having a wealth data that can be incorporated to person task tracking identification. In a real-world setting, all researchers shown effective boosting algorithms can extract information in person task identification. Identifying basic person tasks such as talk, walk, sit along sleep. Our findings demonstrate that boosting classifiers perform better than conventional machine learning classifiers. Moreover, the feature engineering for differentiating an activity detection capability for smart phones and smart watches. For the purpose of improving the classification of fundamental human activities, upcoming mechanisms give the guidelines for identification for various sensors and wearable devices.
more »

A Guide to Using Asynchronous Remote Communities (ARC) for Researching Distributed Populations
Appears in:
phat 17(11): e4

Authors:
Haley MacLeod, Ben Jelen, Annu Prabhakar, Lora Oehlberg, Katie Siek, Kay Connelly

Downloads:
6505

Abstract:
Existing research methods are largely intended to be conducted co-located and synchronously with a study population, but this approach is not feasible with remote or distributed populations. We describe a needs assessment study we conducted on Facebook. We report on our use of adapted versions of c…Existing research methods are largely intended to be conducted co-located and synchronously with a study population, but this approach is not feasible with remote or distributed populations. We describe a needs assessment study we conducted on Facebook. We report on our use of adapted versions of commonly used HCI research methods and lessons learned from this approach.
more »
Security and Privacy Issues with IoT in Healthcare
Appears in:
phat 18(14): e2

Authors:
Anil Chacko, Thaier Hayajneh

Downloads:
4626

Abstract:
In healthcare, the Internet of Things (IoT) oﬀers many beneﬁts, including being able to monitor patients more closely and using data for analytics. When it comes to IoT for medical device integration, the focus is shifted towards the consumer end, such as glucose meters, blood pressure cuﬀs, and ot…In healthcare, the Internet of Things (IoT) oﬀers many beneﬁts, including being able to monitor patients more closely and using data for analytics. When it comes to IoT for medical device integration, the focus is shifted towards the consumer end, such as glucose meters, blood pressure cuﬀs, and other devices designed to record data on patient vital signs. This enables healthcare providers to automatically collect information and apply decision support rules to allow for earlier intervention in the treatment process. Unfortunately, medical companies often do not consider the security risks of connecting these devices to the internet. There is a possibility that a zero-day exploit in a medical device can be used to injure or even kill someone without being detected. The rise in hackable medical devices has forced the FDA to issue formal guidance on how medical device makers should handle reports about cyber vulnerabilities. This paper aims to explore the role of IoT in healthcare, vulnerabilities, attacks, and security issues and solutions.
more »
Voice-Based Detection of Parkinson’s Disease through Ensemble Machine Learning Approach: A Performance Study
Appears in:
phat 19(19): e2

Authors:
Iqra Nissar, Danish Raza Rizvi, Sarfaraz Masood, Aqib Nazir Mir

Downloads:
3799

Abstract:
INTRODUCTION: Parkinson's disease (PD) occurs due to the deficiency of dopamine that regulates various activities of the human body. Researchers have identified that voice is an underlying symptom of PD. Recently, Machine learning (ML) has helped in solving problems of computer vision, natural la…INTRODUCTION: Parkinson's disease (PD) occurs due to the deficiency of dopamine that regulates various activities of
the human body. Researchers have identified that voice is an underlying symptom of PD. Recently, Machine learning
(ML) has helped in solving problems of computer vision, natural language processing, speech recognition etc.

OBJECTIVES: This paper aims to analyse the effect of feature type selection i.e. MFCC and TQWT on the efficiency of
voice based PD detection system along with the use an ensemble learning based classifier for this task.

METHODS: Hence, in this work, various machine learning models, including Logistic Regression, Naive Bayes, KNN,
Random Forest, Decision Tree, SVM, MLP, and XGBoost, have been employed and explored for PD detection purpose.
The task of Feature selection was also done using minimum-Redundancy and Maximum-Relevance (mRMR) and
Recursive Feature Elimination (RFE) techniques.

RESULTS: The results of the XGBoost with mRMR feature selection, outperformed all other models with a high accuracy
of 95.39% and precision, recall and F1-score of 0.95 each, when both MFCC and TQWT features were selected.

CONCLUSION: The results obtained strongly support the use of XGBoost model for the voice sample based detection of
PD along with mRMR feature selection technique.
more »
An Efficient Face Mask Detector with PyTorch and Deep Learning
Appears in:
phat 21(25): e4

Authors:
CMAK. Zeelan Basha, B.N. Lakshmi Pravallika, E. Bharani Shankar

Downloads:
3590

Abstract:
INTRODUCTION: The outbreak ofacoronavirus disease in 2019 (COVID-19) has created a global health epidemic that has had a major effect on the way we view our environment and our daily lives. The Covid-19 affected numbers are rising at a tremendous pace. Because of that, many countries face an econom…INTRODUCTION: The outbreak ofacoronavirus disease in 2019 (COVID-19) has created a global health epidemic that has had a major effect on the way we view our environment and our daily lives. The Covid-19 affected numbers are rising at a tremendous pace. Because of that, many countries face an economic catastrophe, recession, and much more. One thing we should do is to separate ourselves from society, remain at home, and detach ourselves from the outside world. But that's no longer a choice, people need to earn to survive, and nobody can remain indefinitely within their homes. As a precaution, people should wear masks while keeping social distance, but some ignore such things and walk around.

OBJECTIVES: To develop aFace Mask Detector with OpenCV, PyTorch, and Deep Learning that helps to detect whether or not a person wears a mask.

METHODS: A Neural Network model called ResNet is trained on the dataset. Furthermore, this work makes use of the inbuilt Face Detector after training. Finally, we predict whether or not a person is wearing a mask along with the percentage of the face covered or uncovered.

RESULTS: The validation results have been proposed to be 97% accurate when compared to applying different algorithms.

CONCLUSION: This Face Mask Detection System was found to be apt for detecting whether or not people wear masks in public places which contribute to their health and also to the health of their contacts in this COVID-19 pandemic.
more »
A Review of Medical Image Segmentation Algorithms
Appears in:
phat 21(27): e6

Authors:
K.K.D. Ramesh, G. Kiran Kumar, K. Swapna, Debabrata Datta, S. Suman Rajest

Downloads:
3111

Abstract:
INTRODUCTION: Image segmentation in medical physics plays a vital role in image analysis to identify the affected tumour. The process of subdividing an image into its constituent parts that are homogeneous in feature is called Image segmentation, and this proces…INTRODUCTION: Image segmentation in medical physics plays a vital role in image analysis to identify the affected tumour. The process of subdividing an image into its constituent parts that are homogeneous in feature is called Image segmentation, and this process concedes to extract some useful information. Numerous image segmentation techniques have been developed, and these techniques conquer different restrictions on conventional medical segmentation techniques. This paper presents a review of medical image segmentation techniques and statistical mechanics based on the novel method named as Lattice Boltzmann method (LBM). The beauty of LBM is to augment the computational speed in the process of medical image segmentation with an accuracy and specificity of more than 95% compared to traditional methods. As there is not much information on LBM in medical physics, it is intended to present a review of the research progress of LBM.

OBJECTIVE: As there is no review paper on the research progress of the LB method, this paper presents a review with an objective to give some thought regarding the different segmentation for medical image and novel LB method to advance interest for future investigation and exploration in medical image segmentation.

METHODS: This paper in attendance a short review of medical image segmentation techniques based on Thresholding, Region-based, Clustering, Edge detection, Model-based and the novel method Lattice Boltzmann method (LBM).

CONCLUSION: In this paper, we outlined various segmentation techniques applied to medical images, emphasize that none of these problem areas has been acceptably settled, and all of the algorithms depicted are available for broad improvement. Since LBM has the benefits of speed and adaptability of modelling to guarantee excellent image processing quality with a reasonable amount of computer resources, we predict that this method will become a new research hotspot in image processing.
more »
Future Prospective of Soft Computing Techniques in Psychiatric Disorder Diagnosis
Appears in:
phat 18(15): e1

Authors:
Manik Sharma, Natalia Romero

Downloads:
2634

Abstract:
more »
Overcoming Barriers to Healthcare Access and Delivery
Appears in:
phat 18(15): e2

Authors:
Foluso Ayeni, Zacchaeus Omogbadegun, Nicholas Omoregbe, Sanjay Misra, Lalit Garg

Downloads:
2591

Abstract:
Access to standard and economical health care delivery, availability of significant health information are viewed as some of the most functional public health interventions in present-day history. Despite that, current information obtained from the WHO regarding Nigeria’s health condition shows tha…Access to standard and economical health care delivery, availability of significant health information are viewed as some of the most functional public health interventions in present-day history. Despite that, current information obtained from the WHO regarding Nigeria’s health condition shows that the average existence expectancy is at 54 years and maternal mortality at 608 per 100,000 live births as a result of poor health care services. Several aspects of health informatics have been applied to solve these challenges such as the transformation of records from manual to electronic. Among these are the telemedicine and socialized healthcare, which have been barely adopted in developing nations. This work thus proposes an architectural framework for a cloud-supported socialized healthcare system. In order to achieve this; a webbased application software was designed and implemented through the use of cloud computing technology platforms and server side scripting tools. This study proves that socialized healthcare will really go a long way in defeating barriers of viable human access and delivery.
more »
Deep Medical Image Reconstruction with Autoencoders using Deep Boltzmann Machine Training
Appears in:
phat 20(24): e2

Authors:
Saravanan. S, Sujitha Juliet

Downloads:
2543

Abstract:
INTRODUCTION: Deep learning-based Image compression achieves a promising result in recent years as compared with the traditional transform coding methodology. Autoencoder, an unsupervised learning algorithm with the input value as same as that of the output value, is considered in this research wo…INTRODUCTION: Deep learning-based Image compression achieves a promising result in recent years as compared with the traditional transform coding methodology. Autoencoder, an unsupervised learning algorithm with the input value as same as that of the output value, is considered in this research work for effective medical image reconstruction.

OBJECTIVES: Medical data needs to be reconstructed without distorting the details present over it. A deep neural network that accepts the data and processes it to the other several layers and reconstructs that data is achieved by autoencoder.

METHODS: Deep Autoencoder is implemented in this methodology as it has been considered for high dimensionality reduction. Layer by layer pretraining is achieved using an approximate inference algorithm called Deep Boltzmann Machine.

RESULTS: The proposed method proves to be efficient when compared with the performance of the other autoencoders such as Deep Autoencoder with multiple Backpropagation (DA-MBP), Deep Autoencoder with RBM (DA-RBM) and Deep Convolutional Autoencoder with RBM (DCA-RBM).

CONCLUSION: Performance metrics are measured in terms of Mean Square Error, Structural similarity Index and PSNR.
more »
Ear-Lead Multiple Smart Bio Sensor System in M-health
Appears in:
phat 16(6): e5

Authors:
Numan Celik, Wamadeva Balachandran, Nadarajah Manivannan

Downloads:
2435

Abstract:
In this paper, we present a multi-parameter wearable sensor system in conjunction with a smartphone to enable a real-time unobtrusive monitoring of core body temperature, electrocardiogram (ear-lead ECG), and blood oxygen saturation (SpO2) on ambulatory patients. Clinical research illustrating that…In this paper, we present a multi-parameter wearable sensor system in conjunction with a smartphone to enable a real-time unobtrusive monitoring of core body temperature, electrocardiogram (ear-lead ECG), and blood oxygen saturation (SpO2) on ambulatory patients. Clinical research illustrating that continuing accurate measurements of core body temperature (CBT) are crucial to investigate human thermoregulation in ambulatory environment and during activity. On the other hand, ECG remains the mainstay test for primary diagnosis and survival analysis of heart diseases. We implement a wireless multisensory system that measures both the tympanic temperature inside the ear and ECG data from an ear and an arm. The behind-the-Ear device makes desirable to measure ECG data without any chest belt and allow the patient to move around freely. The proposed Bluetooth device has similarity of a hearing aid and is wirelessly connected to a smartphone for data transmission and displaying. This device not only gives access to the core temperature and ECG data in real time, but also the device can be controlled – removed and reapplied – by the patient at any time, thus increasing the performance of personal health applications.
more »
Low-threshold CMOS Rectifier Design for Energy Harvesting in Biomedical Sensors
Appears in:
phat 16(6): e4

Authors:
Mehmet Yuce, Ali Mohammadi, Jean-Michel Redoute

Downloads:
2197

Abstract:
The power transfer efficiency of energy harvesting systems is strongly dependent on the power conditioning circuits, especially rectifiers. The voltage drop across rectifier and its leakage current can drastically influence the efficiency. The hybrid energy harvesters impose even more severe co…The power transfer efficiency of energy harvesting systems
is strongly dependent on the power conditioning circuits,
especially rectifiers. The voltage drop across rectifier and
its leakage current can drastically influence the efficiency.
The hybrid energy harvesters impose even more severe constraints on the rectifier. The low Vth transistors and bulk
regulation technique are used in this work to mitigated the
voltage drop and leakage current, respectively. It has been
shown that the bulk regulation stops the current leakage
through body of PMOS transistor. A near zero threshold
cross connected CMOS rectifier is presented in this work using the standard 180nm UMC technology and experimental
analysis are carried out to evaluate the circuit performance.
more »

Publisher: EAI
ISSN: 2411-7145
Number of Volumes: 8

Last Published: 2022-12-20