Health Management Applications Research Articles

Investigating the Factors Influencing the Attitudes of Workplace Employees Toward Paying to Use Technology-Based Health Care Products.

This study explored whether perceived usefulness and perceived ease-of-use generate mediating effects between personal involvement and attitudes toward paying for usage, and further examining the moderating effects of social influence and company type. Questionnaires were used. A total of 365 employees, 218 from the private sector and 147 from the municipal government in Taipei City were collected. Perceived ease-of-use mediates between personal involvement and attitude toward paying for usage. The social influences of different types of public and private employment differ significantly in terms of their moderating effects on personal involvement and perceived ease-of-use. Due to the different workplace characteristics of private sector and government employees, they have different attitudes toward paying for technology-based health management applications in the future, and social influence is also an important moderating factor.

Implementation of Nutrition based REST APIs for Health Management Applications and Testing with Automation

This work is to develop a back end of an application that provides a Nutrition API service which is a micro service and hosted on to cloud, and it exposed REST APIs which can be consume by the user (health management application).This particular application helps user to keep track of Nutrition In- take by providing in-depth nutritional and caloric information so that user can reinforce good behaviours and make changes to ones that are affecting health negatively.

Potential, challenges and future directions for deep learning in prognostics and health management applications

Deep learning applications have been thriving over the last decade in many different domains, including computer vision and natural language understanding. The drivers for the vibrant development of deep learning have been the availability of abundant data, breakthroughs of algorithms and the advancements in hardware. Despite the fact that complex industrial assets have been extensively monitored and large amounts of condition monitoring signals have been collected, the application of deep learning approaches for detecting, diagnosing and predicting faults of complex industrial assets has been limited. The current paper provides a thorough evaluation of the current developments, drivers, challenges, potential solutions and future research needs in the field of deep learning applied to Prognostics and Health Management (PHM) applications.

A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and applied to time-series data of NPP steam generators

Developing an accurate and reliable multi-step ahead prediction model is a key problem in many Prognostics and Health Management (PHM) applications. Inevitably, the further one attempts to predict into the future, the harder it is to achieve an accurate and stable prediction due to increasing uncertainty and error accumulation. In this paper, we address this problem by proposing a prediction model based on Long Short-Term Memory (LSTM), a deep neural network developed for dealing with the long-term dependencies in time-series data. Our proposed prediction model also tackles two additional issues. Firstly, the hyperparameters of the proposed model are automatically tuned by a Bayesian optimization algorithm, called Tree-structured Parzen Estimator (TPE). Secondly, the proposed model allows assessing the uncertainty on the prediction. To validate the performance of the proposed model, a case study considering steam generator data acquired from different French nuclear power plants (NPPs) is carried out. Alternative prediction models are also considered for comparison purposes.

A Possibilistic Approach for Uncertainty Representation and Propagation in Similarity-Based Prognostic Health Management Solutions

In this paper, a data-driven prognostic model capable to deal with different sources of uncertainty is proposed. The main novelty factor is the application of a mathematical framework, namely a Random Fuzzy Variable (RFV) approach, for the representation and propagation of the different uncertainty sources affecting Prognostic Health Management (PHM) applications: measurement, future and model uncertainty. In this way, it is possible to deal not only with measurement noise and model parameters uncertainty due to the stochastic nature of the degradation process, but also with systematic effects, such as systematic errors in the measurement process, incomplete knowledge of the degradation process, subjective belief about model parameters. Furthermore, the low analytical complexity of the employed prognostic model allows to easily propagate the measurement and parameters uncertainty into the RUL forecast, with no need of extensive Monte Carlo loops, so that low requirements in terms of computation power are needed. The model has been applied to two real application cases, showing high accuracy output, resulting in a potentially effective tool for predictive maintenance in different industrial sectors.

Domain ontology development of knowledge base in cardiovascular personalized health management

In China, cardiovascular disease has become the leading killer in recent years, and mortality from cardiovascular disease is continuing to rapidly increase. Extant medical research has proven that personal health management (prevention, intervention, and recuperation) of chronic diseases, such as cardiovascular diseases, is the best strategy for their prevention and treatment. Currently, the public can obtain health management knowledge through the Internet, newspapers, books, and other channels. However, with the explosive growth of available information, the public is limited to obtain effective health management guidance due to the characteristics of multiple sources, uneven accuracy (even some contradictory knowledge) and a major paucity of personalization, especially for the general public who lack professional medical knowledge. To address these problems, this paper proposes a knowledge base framework (i.e. domain ontology library) of health management programs based on the cardiovascular disease domain, which can standardize knowledge of health management programs both logically and structurally. In order to satisfy the needs of personalized health management, the core ontology of the domain ontology library is health-management-program ontology. In addition to common ontologies (e.g. disease ontology, drug ontology, etc.), basic ontologies include the ontology of individual health characteristics (e.g. individual-health-characteristics and environmental-characteristics ontology), and ontologies comprising diet and sport (e.g. ingredients, recipes, physical exercise, etc.). We then construct the ontology library through the professional ontology tool, Protégé. With a case study, we translate a piece of text health management knowledge into instances of an ontology library. At the same time, we present a personalized health management program recommendation algorithm based on the ontology library, and a recommendation case is realized according to this algorithm. As a basic research, the results of this paper can also support other health management applications in the future.

Introduction to the Special Section on Deep Learning for Visual Surveillance

We are now living in an era of visual information where data is unceasingly generated and pushed into consumption at astounding rates. A remarkable portion of this sensory input comes in the form of videos streaming from large-scale surveillance infrastructures as well as consumer-grade monitoring systems. The sheer amount of ground-based, aerial and mobile video surveillance data demands fittingly competent, accurate, effective techniques to extract useful cues and provide assistance for detection, prevention, and intervention tasks in traffic, safety, security, defense, forensic, health, biology, ethology, and retail space management applications.

Prediction of 30-day pediatric unplanned hospitalizations using the Johns Hopkins Adjusted Clinical Groups risk adjustment system.

BackgroundThe Johns Hopkins ACG System is widely used to predict patient healthcare service use and costs. Most applications have focused on adult populations. In this study, we evaluated the use of the ACG software to predict pediatric unplanned hospital admission in a given month, based on the past year’s clinical information captured by electronic health records (EHRs).Methods and findingsEHR data from a multi-state pediatric integrated delivery system were obtained for 920,051 patients with at least one physician visit during January 2009 to December 2016. Over this interval an average of 0.36% of patients each month had an unplanned hospitalization. In a 70% training sample, we used the generalized linear mixed model (GLMM) to generate regression coefficients for demographic, clinical predictors derived from the ACG system, and prior year hospitalizations. Applying these coefficients to a 30% test sample to generate risk scores, we found that the area under the receiver operator characteristic curve (AUC) was 0.82. Omitting prior hospitalizations decreased the AUC from 0.82 to 0.80, and increased under-estimation of hospitalizations at the greater risk levels. Patients in the top 5% of risk scores accounted for 43% and the top 1% of risk scores accounted for 20% of all unplanned hospitalizations.ConclusionsA predictive model based on 12-months of demographic and clinical data using the ACG system has excellent predictive performance for 30-day pediatric unplanned hospitalization. This model may be useful in population health and care management applications targeting patients likely to be hospitalized. External validation at other institutions should be done to confirm our results.

Assessment of Deep Learning techniques for Prognosis of solar thermal systems

Solar Hot Water (SHW) systems are a sustainable and renewable alternative for domestic and low-temperature industrial applications. As solar energy is a variable resource, performance prediction methods are useful tools to increase the overall availability and effective use of these systems. Recently, data-driven techniques have been successfully used for Prognosis and Health Management applications. In the present work, Deep Learning models are trained to predict the performance of an SHW system under different meteorological conditions. Techniques such as artificial neural networks (ANN) recurrent neural networks (RNN) and long short-term memory (LSTM) are explored. A physical simulation model is developed in TRNSYS software to generate large quantities of synthetic operational data in nominal conditions. Although similar results are achieved with the tested architectures, both RNN and LSTM outperform ANN when replicating the data's temporal behavior; all of which outperform naïve predictors and other regression models such as Bayesian Ridge, Gaussian Process and Linear Regression. LSTM models achieved a low Mean Absolute Error of 0.55 °C and the lowest Root Mean Square Error scores (1.27 °C) for temperature sequence predictions, as well as the lowest variance (0.520 °C2) and relative prediction errors (3.45%) for single value predictions, indicating a more reliable prediction performance.

Application architecture and typical cases of big data technology in health management of civil aircraft system

Under the background of the big data era, the concept and technology of civil aircraft health management have been continuously innovated. This paper investigates the progress of health management technologies of mainstream manufacturers and airlines. Based on the analysis of operational data, this paper proposes a big data platform architecture for civil health management applications. Besides, the case of applying QAR data for prediction is introduced in the typical fault of air conditioning system, and the effectiveness of AR model in short-term trend prediction is verified.

Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture

In recent years, research has proposed several deep learning (DL) approaches to providing reliable remaining useful life (RUL) predictions in Prognostics and Health Management (PHM) applications. Although supervised DL techniques, such as Convolutional Neural Network and Long-Short Term Memory, have outperformed traditional prognosis algorithms, they are still dependent on large labeled training datasets. With respect to real-life PHM applications, high-quality labeled training data might be both challenging and time-consuming to acquire. Alternatively, unsupervised DL techniques introduce an initial pre-training stage to extract degradation related features from raw unlabeled training data automatically. Thus, the combination of unsupervised and supervised (semi-supervised) learning has the potential to provide high RUL prediction accuracy even with reduced amounts of labeled training data. This paper investigates the effect of unsupervised pre-training in RUL predictions utilizing a semi-supervised setup. Additionally, a Genetic Algorithm (GA) approach is applied in order to tune the diverse amount of hyper-parameters in the training procedure. The advantages of the proposed semi-supervised setup have been verified on the popular C-MAPSS dataset. The experimental study, compares this approach to purely supervised training, both when the training data is completely labeled and when the labeled training data is reduced, and to the most robust results in the literature. The results suggest that unsupervised pre-training is a promising feature in RUL predictions subjected to multiple operating conditions and fault modes.

Approximation of diffuse attenuation, Kd, for MODIS high-resolution bands

ABSTRACTA high resolution depth attenuation product (Kdhires) was developed using MODIS 500 m and 250 m spectral bands. The Kdhires was compared with Wang’s operational Kd for the Chesapeake Bay. Minimal differences were observed between the two methods, with greatest deviation occurring in areas of high turbidity in the tributaries. After tuning the new Kdhires, the mean absolute error and bias between the two algorithms was 0.22 m−1 and 0.026 m−1, indicating good agreement. Higher spatial resolution provides for improved retrievals along the coast and into the narrow sections of the tributaries, coinciding with areas of concern to estuarine health and coastal management applications.

A Framework for Prognostics and Health Management Applications toward Smart Manufacturing Systems

Prognostics and health management (PHM) has emerged as an intelligent solution to improve the availability of manufacturing systems. PHM consists of system health monitoring, feature extraction, fault diagnosis, and fault prognosis through remaining useful life estimation. However, the application of PHM to manufacturing systems is challenging because systems have become more complex and uncertain. In particular, small and medium-sized enterprises have difficulty in applying PHM due to the lack of internal expertise, time and resources for research and development. The objective of this paper is to develop a framework to provide a readily usable and accessible guideline for PHM application to manufacturing systems. A survey was performed to gather the current practices in dealing with system failures and maintenance strategies in the field. A framework was developed for giving a guideline for PHM application based on common core modules across manufacturing systems and their kinds with respect to the amount of available data and domain knowledge. A reference table was developed to track the PHM techniques for feature extraction, fault diagnosis, and fault prognosis. Finally, fault prognosis of a system was conducted as a case study, following the framework and the reference table to verify its practical use.

Fleet PHM for Critical Systems

Data-driven approaches are highly relying on the representativeness of the dataset used for training the algorithms. For Prognostics and Health Management (PHM) applications, a lack of representativeness will result in detecting new operating conditions (that have not yet been observed during the period used for training) as faults. This is particularly a challenge for PHM in critical systems, for which long and consistent datasets with all operating conditions are generally not available. Among the many data-driven approaches applied to PHM, Deep Learning has recently brought promising results, enabling an automation of traditional PHM tasks, including signal processing, feature engineering and signal monitoring. Yet, as the parameters to optimize in a Deep Neural Networks are numerous, the training requires also huge datasets: another quality that critical system datasets are often missing. When a fleet of systems is monitored, however, a solution to compose more representative and bigger training datasets is to combine condition monitoring data from systems with similar operating conditions. Identifying similar operating conditions would, traditionally, require comparing the distances and the distributions of multi-dimensional time series, a computationally intensive task worsened by the curse of dimensionality. In this paper, we propose to use a deep neural network, designed for measuring similarities between the training and the testing datasets: a Hierarchical Extreme Learning Machine (HELM). HELM have demonstrated excellent abilities to jointly learn features and monitor deviations from the training data. Training first this network on individual systems, HELM can be used to identify other systems with similar operating conditions. Afterwards, the same network can be trained again with this representative dataset composed of condition monitoring data of several systems, to monitor more efficiently the health of the individual systems. Any deviation in the algorithm output would signify that the system is not anymore in operating conditions seen in the training fleet, and is likely experiencing a fault. The novelty of the proposed approach lies in the usage of the same architecture twice in a bi-level framework: first, for selecting the representative datasets from a fleet of systems and second, using the selected datasets to train the health monitoring algorithm. This approach achieves good performances on both tasks. Learning from the fleet attenuates the impact of changing operating conditions (\eg summer/winter trends), and improves the quality of the fault detection. The approach is tested on a fleet of 112 power plants, some of which experienced a stator vane failure.

Monitoring and learning algorithms for dynamic hybrid Bayesian network in on-line system health management applications

This paper presents a new modeling approach, computational algorithm, and an example application for health monitoring and learning in on-line System Health Management (SHM). A hybrid Dynamic Bayesian Network (DBN) is introduced to represent complex engineering systems with underlying physics of failure by modeling a theoretical or empirical degradation model with continuous variables. The methodology is designed to be flexible and intuitive, and scalable from small, localized functionality to large complex dynamic systems. Markov Chain Monte Carlo (MCMC) inference is optimized using a pre-computation strategy and dynamic programming for on-line monitoring of system health. Proposed Monitoring and Anomaly Detection algorithm uses pattern recognition to improve failure detection and estimation of Remaining Useful Life (RUL). Pre-computation inference database enables efficient on-line learning and maintenance decision-making. The proposed methodology and algorithm are demonstrated with an Unmanned Aerial Vehicle (UAV) application.

A review on the application of deep learning in system health management

Abstract Given the advancements in modern technological capabilities, having an integrated health management and diagnostic strategy becomes an important part of a system’s operational life-cycle. This is because it can be used to detect anomalies, analyse failures and predict the future state based on up-to-date information. By utilising condition data and on-site feedback, data models can be trained using machine learning and statistical concepts. Once trained, the logic for data processing can be embedded on on-board controllers whilst enabling real-time health assessment and analysis. However, this integration inevitably faces several difficulties and challenges for the community; indicating the need for novel approaches to address this vexing issue. Deep learning has gained increasing attention due to its potential advantages with data classification and feature extraction problems. It is an evolving research area with diverse application domains and hence its use for system health management applications must been researched if it can be used to increase overall system resilience or potential cost benefits for maintenance, repair, and overhaul activities. This article presents a systematic review of artificial intelligence based system health management with an emphasis on recent trends of deep learning within the field. Various architectures and related theories are discussed to clarify its potential. Based on the reviewed work, deep learning demonstrates plausible benefits for fault diagnosis and prognostics. However, there are a number of limitations that hinder its widespread adoption and require further development. Attention is paid to overcoming these challenges, with future opportunities being enumerated.

Linking Health Web Services as Resource Graph by Semantic REST Resource Tagging

Various health Web services host a huge amount of health data about patients. The heterogeneity of the services hinders the collaborative utilization of these health data, which can provide a valuable support for the self-management of chronic diseases. The combination of REST Web services and Semantic Web technologies has proven to be a viable approach to address the problem. This paper proposes a method to add semantic annotations to the REST Web services. The service descriptions and the resource representations with semantic annotations can be transformed into a resource graph. It integrates health data from different services, and can link to the health-domain ontologies and Linked Open Health Data to support health management and imaginative applications. The feasibility of our method is demonstrated by realizing with OpenAPI service description and JSON-LD representation in an example use case.

Implementation of Behavioural and Medical Health Management Applications: Reducing High Intensity Medicaid Services Utilization for Individuals with Serious Mental Illness

Health challenges for persons with serious mental illness and comorbid medical conditions are related to application design and usability. An application suite to improve community care was deployed in the community services division of South Beach Psychiatric Center, a large state-run facility in New York, USA. The association between the use of the Medicaid utilization application and changes in the use of Medicaid publicly paid medical inpatient and emergency services was evaluated. A Generalized Linear Mixed Model (GLMM) was developed and applied to assess for longitudinal (5-year) reductions in utilization, the impact of colocation of behavioural and medical health services, and the effects of intra subject correlation, zero inflation, and over-dispersion in the data. Significant reductions in the use of Medicaid paid inpatient and emergency services were observed. Colocation of services was not significant. Significant effects for intra subject correlation and zero inflation were obtained and accounted for in the model.

Framework for a Uniform Description of Prognostics and Health Management

The successful application of Prognostics and Health Management (PHM) systems is increasing steadily worldwide. One reason for this is the increasing number of smart products entering the market. Mirroring smart products, PHM systems are now developed and applied in avariety of engineering disciplines, all using different models and methods. Model, method, and product type diversity all lead to highly complex systems. To handle the complexity in an efficient way, this paper introduces a common base for PHM systems, in the form of a framework – the goal being a generic model with clear formalization of both notation and semantics. Accordingly, the PHM System is separated into both a RUL-Health model and a context model. Both are described and connected through a roles and relation model of their modules. Diagnosis and prognosis modules – estimating the components’ health using lifetime models – are RUL-Health based. For a holistic description, the general lifetime model (GLM) is introduced. This allows different measures of component health to be represented in a single model and reduces the complexity to two metrics – remaining useful life (RUL) and health index (HI). These metrics – combined with internal/external requirements & targets – arethe input for the context modules’ optimization and decision making.

Health structure monitoring for the design of an innovative UAS fixed wing through inverse finite element method (iFEM)

The structural health monitoring (SHM) plays an essential role in system health management applications for aeronautic and space transportation vehicles, manned and unmanned. The unmanned aircraft systems (UAS) are also extremely needed in various fields of interest, from military to civilian (search and rescue, environmental surveillance and monitoring, entertainment). This work presents an innovative UAS fixed-wing design and control through an inverse finite element method-based, which compute the full-field displacements reconstruction of a three-dimensional shell/plate deformations from experimentally measured surface strains. The full-field displacements are useful for the preliminary design and inspections of the UAS loads, caused by maneuvers or gusts. Goal of this paper was to validate the high accuracy predictions of deformations afforded due to the inverse finite element method (iFEM). Overall formulation was based on the minimization of a least-squares functional that uses and compares the strains extracted due to embedded sensors with the strains of linear, first order shear-deformation theory. The test article was a thin plate equipped with embedded sensors (strain gauge sensors) which permit to extract surface strains in real-time, used as input data for shape sensing. The plate was used to approximate an UAS wing box section, in further work analyzed.