Logical Representation of Sensor Data, Preferences, and Personalized Activity Recommendations in an eCoach System: An Ontology-based Proof-of-Concept Study (Preprint)

2021 ◽  
Author(s):  
Ayan Chatterjee
Keyword(s):  
Health Risk ◽  
Risk Prediction ◽  
Sparql Query ◽  
Sensor Data ◽  
Personalized Recommendation ◽  
Weather Data ◽  
Health State ◽  
Proof Of Concept ◽  
Logical Representation ◽  
Activity Recommendations

UNSTRUCTURED An automatic electronic coaching (eCoaching) can motivate individuals to lead a healthy lifestyle through early health risk prediction, customized recommendation generation, preference setting (such as, goal setting, response, and interaction), and goal evaluation. Such an eCoach system needs to collect heterogeneous health, wellness, and contextual data, and then convert them into meaningful information for health monitoring, health risk prediction, and the generation of personalized recommendations. However, data from various sources may cause a data compatibility dilemma. The proposed ontology can help in data integration, logical representation of sensory observations and customized suggestions, and discover implied knowledge. This "proof of concept (PoC)" research will help sensors, personal preferences, and recommendation data to be more organized. The research aims to design and develop an OWL-based ontology ("UiA Activity Recommendation Ontology/UiAARO") to annotate activity sensor data, contextual weather data, personal information, personal preferences, and personalized activity recommendations. The ontology was created using Protégé (V. 5.5.0) open-source software. We used the Java-based Jena Framework (V. 3.16) to build a semantic web application, which includes RDF API, OWL API, native tuple storage (TDB), and SPARQL query engine. The HermiT (V. 1.4.3.x) ontology reasoner available in Protégé 5.x has implemented the logical and structural consistency of the proposed ontology. The ontology can be visualized with OWLViz and OntoGraf, and the formal representation has been used to infer the health status of the eCoach participants with a reasoner. We have also developed an ontology verification module that behaves like a rule-based decision making (e.g., health state monitor and prediction), which can evaluate participant’s health state based on the evaluation of SPARQL query results, activity performed and predefined goal. Furthermore, the “UiAARO” has helped to represent the personalized recommendation messages beyond just “String” values, rather more meaningful with object-oriented representation. The scope of the proposed ontology is limited neither to specific sensor data nor only activity recommendations; instead, its scope can be further extended.

scholarly journals UiAeHo - an OWL-Based Ontology Modeling to Support Logical Representation of Observable and Measurable Data for Healthy Lifestyle Management Targeting Obesity as a Case Study (Preprint)

2020 ◽  
Author(s):  
Ayan Chatterjee ◽  
Andreas Prinz ◽  
Martin Gerdes ◽  
Santiago Martinez
Keyword(s):  
Health Risk ◽  
Risk Prediction ◽  
Situation Awareness ◽  
Web Application ◽  
Healthy Lifestyle ◽  
Personalized Recommendation ◽  
Health And Wellness ◽  
Contextual Data ◽  
Study Case ◽  
Lifestyle Diseases

BACKGROUND Lifestyle diseases, because of adverse health behavior, are the foremost cause of death worldwide. An eCoach system may encourage individuals to lead a healthy lifestyle with health risk prediction, personalized recommendation generation, and goal evaluation. Such an eCoach system needs to collect and transform distributed heterogenous health and wellness data into meaningful information to train an artificially intelligent health risk prediction model. But it may produce data compatibility dilemma. Our proposed eHealth ontology can increase interoperability between different heterogeneous networks, give situation awareness, help in data integration, and discover inferred knowledge. This “proof of concept (POC)” study will help sensor, questionnaire, and interview data to be more organized for health risk prediction and personalized recommendation generation targeting obesity as a study case. OBJECTIVE The aim of this study has been an OWL-based ontology (called the “UiA eHealth Ontology/UiAeHo”) to annotate personal, physiological, behavioral and contextual data from heterogeneous sources (sensor, questionnaire, and interview), and followed by, structuring and standardizing of diverse descriptions to generate meaningful, practical, personalized, and contextual lifestyle recommendations based on the defined rules. METHODS We have developed a Java-based simulator to collect dummy personal, physiological, behavioral, and contextual data related to artificial participants involved in health monitoring. We have integrated the concepts of “SSN Ontology”, and “SNOMED-CT” to develop our proposed eHealth ontology. The ontology has been created using Protégé (V. 5.x). Following, we have used the Java-based “Jena Framework” (V. 3.16) for building a semantic web application that includes RDF API, OWL API, native tuple store (TDB), and the SPARQL query engine. The logical and structural consistency of the proposed ontology has been performed with “HermiT 1.4.3.x” ontology reasoner available in Protégé 5.x. RESULTS The proposed ontology has been implemented for the study case “Obesity”. However, it can be extended further for other lifestyle diseases. “UiA eHealth Ontology” has been constructed using 623 logical axioms, 363 declaration axioms, 162 classes, 83 object properties, and 101 data properties. The ontology can be visualized with “Owl Viz”, and the formal representation has been used to infer a participant's health status using the “HermiT” reasoner. In addition, we have developed a Java-based module for ontology verification, that behaves like a rule-based decision support system (DSS) to predict the probability for health risk, based on the evaluation of the results obtained from SPARQL queries. Moreover, we have discussed the potential lifestyle recommendation generation plan against adverse behavioral risks. CONCLUSIONS This study has led to the creation of a meaningful, context-specific ontology to model massive, unintuitive raw, unstructured observations for health and wellness data (e.g., sensors, interviews, questionnaires) and to annotate them with semantic metadata to create a compact, intelligible abstraction for health risk predictions for individualized recommendation generation.

scholarly journals Developing a Simulated Online Model That Integrates GNSS, Accelerometer and Weather Data to Detect Parturition Events in Grazing Sheep: A Machine Learning Approach

Animals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 303
Author(s):  
Eloise S. Fogarty ◽  
David L. Swain ◽  
Greg M. Cronin ◽  
Luis E. Moraes ◽  
Derek W. Bailey ◽  
...  
Keyword(s):  
Machine Learning ◽  
Field Trials ◽  
Satellite System ◽  
False Positives ◽  
Sensor Data ◽  
Weather Data ◽  
Integrated Sensor ◽  
Detection Model ◽  
Independent Field ◽  
Grazing Sheep

In the current study, a simulated online parturition detection model is developed and reported. Using a machine learning (ML)-based approach, the model incorporates data from Global Navigation Satellite System (GNSS) tracking collars, accelerometer ear tags and local weather data, with the aim of detecting parturition events in pasture-based sheep. The specific objectives were two-fold: (i) determine which sensor systems and features provide the most useful information for lambing detection; (ii) evaluate how these data might be integrated using ML classification to alert to a parturition event as it occurs. Two independent field trials were conducted during the 2017 and 2018 lambing seasons in New Zealand, with the data from each used for ML training and independent validation, respectively. Based on objective (i), four features were identified as exerting the greatest importance for lambing detection: mean distance to peers (MDP), MDP compared to the flock mean (MDP.Mean), closest peer (CP) and posture change (PC). Using these four features, the final ML was able to detect 27% and 55% of lambing events within ±3 h of birth with no prior false positives. If the model sensitivity was manipulated such that earlier false positives were permissible, this detection increased to 91% and 82% depending on the requirement for a single alert, or two consecutive alerts occurring. To identify the potential causes of model failure, the data of three animals were investigated further. Lambing detection appeared to rely on increased social isolation behaviour in addition to increased PC behaviour. The results of the study support the use of integrated sensor data for ML-based detection of parturition events in grazing sheep. This is the first known application of ML classification for the detection of lambing in pasture-based sheep. Application of this knowledge could have significant impacts on the ability to remotely monitor animals in commercial situations, with a logical extension of the information for remote monitoring of animal welfare.

scholarly journals UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data

2021 ◽  
Author(s):  
Chacha Chen ◽  
Junjie Liang ◽  
Fenglong Ma ◽  
Lucas Glass ◽  
Jimeng Sun ◽  
...  
Keyword(s):  
Health Risk ◽  
Risk Prediction

scholarly journals StageNet: Stage-Aware Neural Networks for Health Risk Prediction

2020 ◽  
Author(s):  
Junyi Gao ◽  
Cao Xiao ◽  
Yasha Wang ◽  
Wen Tang ◽  
Lucas M. Glass ◽  
...  
Keyword(s):  
Neural Networks ◽  
Health Risk ◽  
Risk Prediction

scholarly journals Health risk prediction models incorporating personality data: Motivation, challenges, and illustration.

2019 ◽  
Vol 10 (1) ◽  
pp. 46-58 ◽  
Author(s):  
Benjamin P. Chapman ◽  
Feng Lin ◽  
Shumita Roy ◽  
Ralph H. B. Benedict ◽  
Jeffrey M. Lyness
Keyword(s):  
Health Risk ◽  
Risk Prediction ◽  
Prediction Models ◽  
Risk Prediction Models

An Effective AQI Estimation Using Sensor Data and Stacking Mechanism

2021 ◽  
Author(s):  
Dat Q. Duong ◽  
Quang M. Le ◽  
Tan-Loc Nguyen-Tai ◽  
Hien D. Nguyen ◽  
Minh-Son Dao ◽  
...  
Keyword(s):  
Air Quality ◽  
Quality Index ◽  
Research Topic ◽  
Sensor Data ◽  
Weather Data ◽  
Quality Estimation ◽  
Data Set ◽  
Adverse Health Effects ◽  
Overall Performance ◽  
Selection Of

Accurately assessing the air quality index (AQI) values and levels has become an attractive research topic during the last decades. It is a crucial aspect when studying the possible adverse health effects associated with current air quality conditions. This paper aims to utilize machine learning and an appropriate selection of attributes for the air quality estimation problem using various features, including sensor data (humidity, temperature), timestamp features, location features, and public weather data. We evaluated the performance of different learning models and features to study the problem using the data set “MNR-HCM II”. The experimental results show that adopting TLPW features with Stacking generalization yields higher overall performance than other techniques and features in RMSE, accuracy, and F1-score.

scholarly journals Mining health knowledge graph for health risk prediction

2020 ◽  
Vol 23 (4) ◽  
pp. 2341-2362 ◽  
Author(s):  
Xiaohui Tao ◽  
Thuan Pham ◽  
Ji Zhang ◽  
Jianming Yong ◽  
Wee Pheng Goh ◽  
...  
Keyword(s):  
Health Risk ◽  
Risk Prediction ◽  
Health Knowledge ◽  
Knowledge Graph
Sign in / Sign up

Export Citation Format

Share Document