Fergus U. Onu

Bio: Fergus U. Onu is an academic researcher. The author has contributed to research in topics: Computer science & Service (business). The author has an hindex of 1, co-authored 1 publications receiving 3 citations.

Mobile and wearable sensors for data-driven health monitoring system: State-of-the-art and future prospect

Abstract: • Comprehensive review of health monitoring based sensors. • Categorize the sensors into homogeneous, dual and heterogeneous. • Discuss their strengths, drawbacks and application domains. • Outline major issues and significant solutions. • Highlights future prospect of health monitoring sensors. Mobile and wearable devices embedded with multiple sensors for health monitoring and disease diagnosis are growing fields with the potential to provide efficient means for remote health management. A sensor-based health monitoring system offers an essential mechanism for real-time diagnosis and management to detect/predict, recommend treatment and prevent the onset of diseases. This paper aims to synthesize the research efforts on mobile and wearable sensors for health monitoring. It will investigate sensors, components of health monitoring systems, major application areas, challenges, and solutions faced during the implementation of health monitoring systems by researchers and practitioners. It was observed that sensors embedded in mobile and wearable devices for health monitoring are broadly categorized into homogeneous, dual, and heterogeneous sensors. In health monitoring, heterogeneous sensor-based is widely implemented and the most effective due to its ability to combine multiple sensors from various domains. The fusion of multiple sensors provides reliability, credibility, and better accuracy for monitoring multiple health parameters. We observed that researchers follow established procedures such as data collection, data transmission, preprocessing, feature extraction and development, data analysis, and evaluation of different algorithms for implementation of the health monitoring system. Supervised machine learning algorithms such as support vector machine, decision tree, k-nearest neighbors, and deep learning methods were the most implemented methods, while accuracy was the favored evaluation measure for health monitoring. Generally, we found that a health monitoring system is implemented to resolve health issues in the areas of human activity and posture monitoring, sleep disorder, sleep stage detection, fall monitoring in the elderly, depression, and mood swing detection. Other important areas include Parkinson’s disease management, cardiac diseases monitoring, disease diagnosis, and well-being, and Corona virus detection and contact tracing to minimize infection rate. Furthermore, the review succinctly highlights various challenges impeding the development of sensor-based health monitoring systems with significant solutions that were recommended in the literature to ameliorate these challenges discussed. From the review, it can be acknowledged that various research efforts have been conducted to develop effective health monitoring systems, and many new systems have been implemented. However, there is still much work to be done which we have also discussed under future prospects.

Factors That Affect the Use of Ict in Nursing Profession in Ebonyi State Nigeria

Abstract: Information and Communication Technology (ICT) has become a major tool in the delivery of health services just as it has made a great impact on other sectors In Health, it has given birth to e-health, Health informatics, tele-health, etc The primary focus of this paper is to outline and discus the factors that affect the use of Information and Communication Technology (ICT) in Nursing profession in Ebonyi State The paper also analyzed and found out that the problems of ICT application in Nursing profession are paramount in preventing the successful implementation of health informatics in Ebonyi State It went ahead to suggest the possible solutions to the identified problems The paper concluded that nurses need to engage fully in ICT so that they contribute to shaping the care system and emerge as leaders of the new care system Keywords: ICT, e-Health, health Informatics, Nursing, Internet, computing, telephony

Prospects and Challenges of Using Machine Learning for Academic Forecasting

Abstract: The study examines the prospects and challenges of machine learning (ML) applications in academic forecasting. Predicting academic activities through machine learning algorithms presents an enhanced means to accurately forecast academic events, including the academic performances and the learning style of students. The use of machine learning algorithms such as K-nearest neighbor (KNN), random forest, bagging, artificial neural network (ANN), and Bayesian neural network (BNN) has potentials that are currently being applied in the education sector to predict future events. Many gaps in the traditional forecasting techniques have greatly been bridged by the use of artificial intelligence-based machine learning algorithms thereby aiding timely decision-making by education stakeholders. ML algorithms are deployed by educational institutions to predict students' learning behaviours and academic achievements, thereby giving them the opportunity to detect at-risk students early and then develop strategies to help them overcome their weaknesses. However, despite the benefits associated with the ML approach, there exist some limitations that could affect its correctness or deployment in forecasting academic events, e.g., proneness to errors, data acquisition, and time-consuming issues. Nonetheless, we suggest that machine learning remains one of the promising forecasting technologies with the power to enhance effective academic forecasting that would assist the education industry in planning and making better decisions to enrich the quality of education.

Predicting gross domestic product to macroeconomic indicators

Abstract: Macroeconomic indicators enable countries to concentrate on goods, services, and other entities that grow their Gross Domestic Product (GDP). Often, identifying these groups of indicators poses a challenge to nations. The study considered a typical data set with two main objectives. First, to predict GDP to macroeconomic indicators by applying four machine learning methods namely, Principal Component Regression (PCR), Ridge Regression (RR), Lasso Regression (LR), and Ordinary Least Squares (OLS). Second, identify the most likely key macroeconomic variables that could affect the growth of GDP. The methods were evaluated using 5-fold cross-validation, and the estimated coefficients associated with the macroeconomic indicators were computed. The results revealed that PCR method with an accuracy of 89% and a mean square error of -7.552007365635066e+21 predicted GDP to macroeconomic indicators accurately, more than other methods. Some macroeconomic indicators did affect GDP positively, while others did not. The major contribution of the study is the use of machine learning regularization methods to predict GDP instead of the traditional statistical methods. It also identified additional macroeconomic variables to compute real GDP.

Webussd care: a multi-tenant ussd based application for improving protected health information exchange

Abstract: Quick access to patient's protected health information avails clinicians the insight to understand patient's health conditions and to make an informed treatment decisions. However, the outbreak of the Covid-19 pandemic placed serious access restriction not only to the healthcare facilities and services but also to patient's protected health information. Unstructured Supplementary Service Data (USSD) technology is an efficient tool that can easily be used to create, store, access, and share personal health data whenever the needs arise. In this study, an integrated multi-tenant USSD based application to improve patient's protected health information exchange is presented as a complementary tool for improving healthcare outcomes. Object oriented methodology with integration of USSD Application Programming Interface (API) was adopted for the system development. The prototype of multi-tenant USSD based application for improving protected health Information exchange has been developed named “WEBUSSD Care”. By dialing a selected code on the mobile phone, the system displays an interactive menu for accessing patient's protected information such as medical appointments, diagnoses, medication prescription, medical test results, report drug reactions and treatment information and so on. The adoption of the WEBUSSD Care could greatly reduce delay in accessing patient's protected health information and enhance timely and informed treatment decisions.

Types of ICT applications used and the skills’ level of nursing students in higher education: A cross-sectional survey

Abstract: Background The healthcare system is increasingly becoming technology dependent; consequently, nurses in all regions of the world are expected to develop their information and communication technology (ICT) skills, and integrating ICT in the nursing curriculum is fundamental. Aim This study aims to explore the types of ICT applications used and the skills level of nursing students at a selected university in South Africa. Methods A non-experimental, descriptive quantitative research design was used in this study, and it was conducted at a selected university in South Africa. A total number of 150 nursing students participated in this study. Data were collected using a structured questionnaire and were analysed using SPSS version 25. Findings The majority of the respondents reported being skilled in using Word processing application (Ms Word) (86.7%), Ms PowerPoint (70.7%), Moodle (81.3%), and online resources (74.7%). However, 82% reported not being skilled to use SPSS for data analysis, and 65.3% were not skilled in using reference manager applications (EndNote). Data indicated that there was a progressive increase in skills with the level of the study, with upper levels being more skilled than the lower levels (K = 22.625, p = .001). The ownership of digital devices, such as laptops and tablets, was significantly associated with the skills level of using ICT applications (p Conclusion The use of technology in nursing education is essential to prepare future nurses for the information technology-rich workplace.

Highly Efficient and Stable Self‐Powered Mixed Tin‐Lead Perovskite Photodetector Used in Remote Wearable Health Monitoring Technology

Abstract: Realization of remote wearable health monitoring (RWHM) technology for the flexible photodiodes is highly desirable in remote‐sensing healthcare systems used in space stations, oceans, and forecasting warning, which demands high external quantum efficiency (EQE) and detectivity in NIR region. Traditional inorganic photodetectors (PDs) are mechanically rigid and expensive while the widely reported solution‐processed mixed tin‐lead (MSP) perovskite photodetectors (PPDs) exhibit a trade‐off between EQE and detectivity in the NIR region. Herein, a novel functional passivating antioxidant (FPA) strategy has been introduced for the first time to simultaneously improve crystallization, restrain Sn2+ oxidization, and reduce defects in MSP perovskite films by multiple interactions between thiophene‐2‐carbohydrazide (TAH) molecules and cations/anions in MSP perovskite. The resultant solution‐processed rigid mixed Sn–Pb PPD simultaneously achieves high EQE (75.4% at 840 nm), detectivity (1.8 × 1012 Jones at 840 nm), ultrafast response time (trise/tfall = 94 ns/97 ns), and improved stability. This work also highlights the demonstration of the first flexible photodiode using MSP perovskite and FPA strategy with remarkably high EQE (75% at 840 nm), and operational stability. Most importantly, the RWHM is implemented for the first time in the PIN MSP perovskite photodiodes to remotely monitor the heart rate of humans at rest and after‐run conditions.

Real-time detection of freezing of gait in Parkinson's disease using multi-head convolutional neural networks and a single inertial sensor

Abstract: Freezing of gait (FOG) is one of the most disabling symptoms of Parkinson's disease (PD), contributing to poor quality of life and increased risk of falls. Wearable sensors represent a valuable means for detecting FOG in the home environment. Moreover, real-time feedback has proven to help reduce the duration of FOG episodes. This work proposes a robust real-time FOG detection algorithm, which is easy to implement in stand-alone devices working in non-supervised conditions.Data from three different data sets were used in this study, with two employed as independent test sets. Acceleration recordings from 118 PD patients and 21 healthy elderly subjects were collected while they performed simulated daily living activities. A single inertial sensor was attached to the waist of each subject. More than 17 h of valid data and a total number of 1110 FOG episodes were analyzed in this study. The implemented algorithm consisted of a multi-head convolutional neural network, which exploited different spatial resolutions in the analysis of inertial data. The architecture and the model parameters were designed to provide optimal performance while reducing computational complexity and testing time.The developed algorithm demonstrated good to excellent classification performance, with more than 50% (30%) of FOG episodes predicted on average 3.1 s (1.3 s) before the actual onset in the main (independent) data set. Around 50% of FOG was detected with an average delay of 0.8 s (1.1 s) in the main (independent) data set. Moreover, a specificity above 88% (93%) was obtained when testing the algorithm on the main (independent) test set, while 100% specificity was obtained on healthy elderly subjects.The algorithm proved robust, with low computational complexity and processing time, thus paving the way to a real-time implementation in a stand-alone device that can be used in non-supervised environments.

Enhanced use of information and communication technology by professional nurses in distance education

Abstract: The Abstract of the manuscript should not exceed 350 words and must be structured into separate sections: Background, the context and purpose of the study; Methods, how the study was performed and statistical tests used; Results, the main findings; Conclusions, brief summary and potential implications.

Integration of deep adaptation transfer learning and online sequential extreme learning machine for cross-person and cross-position activity recognition

Abstract: • Deep adaptation transfer learning combined with OS-ELM to handle cross domain HAR. • GAP and SE structure in CNN facilitate feature extraction and adapt to input data. • DANN and DDC have different effects on cross-person and cross-position transfer. • OS-ELM classifier improves HAR accuracy with a few annotated data in target domain. Deep learning (DL) has been evolving to a prevalent method in human activity recognition (HAR). However, the performance of wearable sensor based HAR models decline significantly when training data come from different persons or sensor positions, and a time-consuming data annotation is indispensible to cater for the big-data driven DL models. In this paper we proposed a fast and robust hybrid model to handle the transfer issues of wearable sensor based HAR between different persons (cross-person) and different positions (cross-position) with just a few annotated data in target domain. The model consists of three parts: (1) A convolutional neural network (CNN) with global average pooling layer to facilitate the extraction of advanced common features in source domain and target domain; (2) A domain adaptive neural network with a gradient reversal layer (DANN) and deep domain confusion network with an adaptive layer (DDC) to reduce domain shift caused by the change of persons and sensor positions; (3) An adaptive classifier based on online sequential extreme learning machine (OS-ELM) to achieve fast and accurate classification with a few annotated data in target domain. Experimental results on four public datasets verified the superiority of the proposed hybrid model over standard CNN and deep transfer learning models in adapting the classifier to new sensor locations and subjects quickly, where the HAR accuracy can be improved by at least 12% for cross-person transfer and 20% for cross-position transfer, respectively.