A Neural Network Based Algorithm for Dynamically Adjusting Activity Targets to Sustain Exercise Engagement Among People Using Activity Trackers

Background It is well established that lack of physical activity is detrimental to the overall health of an individual. Modern-day activity trackers enable individuals to monitor their daily activities to meet and maintain targets. This is expected to promote activity encouraging behavior, but the benefits of activity trackers attenuate over time due to waning adherence. One of the key approaches to improving adherence to goals is to motivate individuals to improve on their historic performance metrics. Objective The aim of this work was to build a machine learning model to predict an achievable weekly activity target by considering (1) patterns in the user’s activity tracker data in the previous week and (2) behavior and environment characteristics. By setting realistic goals, ones that are neither too easy nor too difficult to achieve, activity tracker users can be encouraged to continue to meet these goals, and at the same time, to find utility in their activity tracker. Methods We built a neural network model that prescribes a weekly activity target for an individual that can be realistically achieved. The inputs to the model were user-specific personal, social, and environmental factors, daily step count from the previous 7 days, and an entropy measure that characterized the pattern of daily step count. Data for training and evaluating the machine learning model were collected over a duration of 9 weeks. Results Of 30 individuals who were enrolled, data from 20 participants were used. The model predicted target daily count with a mean absolute error of 1545 (95% CI 1383-1706) steps for an 8-week period. Conclusions Artificial intelligence applied to physical activity data combined with behavioral data can be used to set personalized goals in accordance with the individual’s level of activity and thereby improve adherence to a fitness tracker; this could be used to increase engagement with activity trackers. A follow-up prospective study is ongoing to determine the performance of the engagement algorithm.

Download Full-text

Neural Network–Based Algorithm for Adjusting Activity Targets to Sustain Exercise Engagement Among People Using Activity Trackers: Retrospective Observation and Algorithm Development Study (Preprint)

10.2196/preprints.18142 ◽

2020 ◽

Author(s):

Ramin Mohammadi ◽

Mursal Atif ◽

Amanda Jayne Centi ◽

Stephen Agboola ◽

Kamal Jethwani ◽

...

Keyword(s):

Neural Network ◽

Physical Activity ◽

Machine Learning ◽

Learning Model ◽

Step Count ◽

Daily Step ◽

Activity Tracker ◽

Activity Trackers ◽

Machine Learning Model ◽

Daily Step Count

BACKGROUND It is well established that lack of physical activity is detrimental to the overall health of an individual. Modern-day activity trackers enable individuals to monitor their daily activities to meet and maintain targets. This is expected to promote activity encouraging behavior, but the benefits of activity trackers attenuate over time due to waning adherence. One of the key approaches to improving adherence to goals is to motivate individuals to improve on their historic performance metrics. OBJECTIVE The aim of this work was to build a machine learning model to predict an achievable weekly activity target by considering (1) patterns in the user’s activity tracker data in the previous week and (2) behavior and environment characteristics. By setting realistic goals, ones that are neither too easy nor too difficult to achieve, activity tracker users can be encouraged to continue to meet these goals, and at the same time, to find utility in their activity tracker. METHODS We built a neural network model that prescribes a weekly activity target for an individual that can be realistically achieved. The inputs to the model were user-specific personal, social, and environmental factors, daily step count from the previous 7 days, and an entropy measure that characterized the pattern of daily step count. Data for training and evaluating the machine learning model were collected over a duration of 9 weeks. RESULTS Of 30 individuals who were enrolled, data from 20 participants were used. The model predicted target daily count with a mean absolute error of 1545 (95% CI 1383-1706) steps for an 8-week period. CONCLUSIONS Artificial intelligence applied to physical activity data combined with behavioral data can be used to set personalized goals in accordance with the individual’s level of activity and thereby improve adherence to a fitness tracker; this could be used to increase engagement with activity trackers. A follow-up prospective study is ongoing to determine the performance of the engagement algorithm.

Download Full-text

Feedback From Activity Trackers Improves Daily Step Count After Knee and Hip Arthroplasty: A Randomized Controlled Trial

The Journal of Arthroplasty ◽

10.1016/j.arth.2018.06.024 ◽

2018 ◽

Vol 33 (11) ◽

pp. 3422-3428 ◽

Cited By ~ 13

Author(s):

Neill Van der Walt ◽

Lucy J. Salmon ◽

Benjamin Gooden ◽

Matthew C. Lyons ◽

Michael O'Sullivan ◽

...

Keyword(s):

Randomized Controlled Trial ◽

Hip Arthroplasty ◽

Controlled Trial ◽

Step Count ◽

Daily Step ◽

Randomized Controlled ◽

Activity Trackers ◽

Daily Step Count ◽

Knee And Hip Arthroplasty

Download Full-text

BonDNet: A Graph Neural Network for the Prediction of Bond Dissociation Energies for Charged Molecules

10.26434/chemrxiv.12980774 ◽

2020 ◽

Author(s):

Mingjian Wen ◽

Samuel Blau ◽

Evan Spotte-Smith ◽

Shyam Dwaraknath ◽

Kristin Persson

Keyword(s):

Neural Network ◽

Machine Learning ◽

Chemical Reactivity ◽

Absolute Error ◽

Learning Model ◽

Chemical Processes ◽

Accurate Prediction ◽

Global Features ◽

Bond Dissociation ◽

Machine Learning Model

<div><div><div><p>A broad collection of technologies, including e.g. drug metabolism, biofuel combustion, photochemical decontamination of water, and interfacial passivation in energy production/storage systems rely on chemical processes that involve bond-breaking molecular reactions. In this context, a fundamental thermodynamic property of interest is the bond dissociation energy (BDE) which measures the strength of a chemical bond. Fast and accurate prediction of BDEs for arbitrary molecules would lay the groundwork for data-driven projections of complex reaction cascades and hence a deeper understanding of these critical chemical processes and, ultimately, how to reverse design them. In this paper, we propose a chemically inspired graph neural network machine learning model, BonDNet, for the rapid and accurate prediction of BDEs. BonDNet maps the difference between the molecular representations of the reactants and products to the reaction BDE. Because of the use of this difference representation and the introduction of global features, including molecular charge, it is the first machine learning model capable of predicting both homolytic and heterolytic BDEs for molecules of any charge. To test the model, we have constructed a dataset of both homolytic and heterolytic BDEs for neutral and charged (1 and +1) molecules. BonDNet achieves a mean absolute error (MAE) of 0.022 eV for unseen test data, significantly below chemical accuracy (0.043 eV). Besides the ability to handle complex bond dissociation reactions that no previous model could con- sider, BonDNet distinguishes itself even in only predicting homolytic BDEs for neutral molecules; it achieves an MAE of 0.020 eV on the PubChem BDE dataset, a 20% improvement over the previous best performing model. We gain additional insight into the model’s predictions by analyzing the patterns in the features representing the molecules and the bond dissociation reactions, which are qualitatively consistent with chemical rules and intuition. BonDNet is just one application of our general approach to representing and learning chemical reactivity, and it could be easily extended to the prediction of other reaction properties in the future.</p></div></div></div>

Download Full-text

BonDNet: A Graph Neural Network for the Prediction of Bond Dissociation Energies for Charged Molecules

10.26434/chemrxiv.12980774.v1 ◽

2020 ◽

Author(s):

Mingjian Wen ◽

Samuel Blau ◽

Evan Spotte-Smith ◽

Shyam Dwaraknath ◽

Kristin Persson

Keyword(s):

Neural Network ◽

Machine Learning ◽

Chemical Reactivity ◽

Absolute Error ◽

Learning Model ◽

Chemical Processes ◽

Accurate Prediction ◽

Global Features ◽

Bond Dissociation ◽

Machine Learning Model

<div><div><div><p>A broad collection of technologies, including e.g. drug metabolism, biofuel combustion, photochemical decontamination of water, and interfacial passivation in energy production/storage systems rely on chemical processes that involve bond-breaking molecular reactions. In this context, a fundamental thermodynamic property of interest is the bond dissociation energy (BDE) which measures the strength of a chemical bond. Fast and accurate prediction of BDEs for arbitrary molecules would lay the groundwork for data-driven projections of complex reaction cascades and hence a deeper understanding of these critical chemical processes and, ultimately, how to reverse design them. In this paper, we propose a chemically inspired graph neural network machine learning model, BonDNet, for the rapid and accurate prediction of BDEs. BonDNet maps the difference between the molecular representations of the reactants and products to the reaction BDE. Because of the use of this difference representation and the introduction of global features, including molecular charge, it is the first machine learning model capable of predicting both homolytic and heterolytic BDEs for molecules of any charge. To test the model, we have constructed a dataset of both homolytic and heterolytic BDEs for neutral and charged (1 and +1) molecules. BonDNet achieves a mean absolute error (MAE) of 0.022 eV for unseen test data, significantly below chemical accuracy (0.043 eV). Besides the ability to handle complex bond dissociation reactions that no previous model could con- sider, BonDNet distinguishes itself even in only predicting homolytic BDEs for neutral molecules; it achieves an MAE of 0.020 eV on the PubChem BDE dataset, a 20% improvement over the previous best performing model. We gain additional insight into the model’s predictions by analyzing the patterns in the features representing the molecules and the bond dissociation reactions, which are qualitatively consistent with chemical rules and intuition. BonDNet is just one application of our general approach to representing and learning chemical reactivity, and it could be easily extended to the prediction of other reaction properties in the future.</p></div></div></div>

Download Full-text

BonDNet: A Graph Neural Network for the Prediction of Bond Dissociation Energies for Charged Molecules

10.26434/chemrxiv.12980774.v2 ◽

2020 ◽

Author(s):

Mingjian Wen ◽

Samuel Blau ◽

Evan Spotte-Smith ◽

Shyam Dwaraknath ◽

Kristin Persson

Keyword(s):

Neural Network ◽

Machine Learning ◽

Chemical Reactivity ◽

Absolute Error ◽

Learning Model ◽

Chemical Processes ◽

Accurate Prediction ◽

Global Features ◽

Bond Dissociation ◽

Machine Learning Model

<div><div><div><p>A broad collection of technologies, including e.g. drug metabolism, biofuel combustion, photochemical decontamination of water, and interfacial passivation in energy production/storage systems rely on chemical processes that involve bond-breaking molecular reactions. In this context, a fundamental thermodynamic property of interest is the bond dissociation energy (BDE) which measures the strength of a chemical bond. Fast and accurate prediction of BDEs for arbitrary molecules would lay the groundwork for data-driven projections of complex reaction cascades and hence a deeper understanding of these critical chemical processes and, ultimately, how to reverse design them. In this paper, we propose a chemically inspired graph neural network machine learning model, BonDNet, for the rapid and accurate prediction of BDEs. BonDNet maps the difference between the molecular representations of the reactants and products to the reaction BDE. Because of the use of this difference representation and the introduction of global features, including molecular charge, it is the first machine learning model capable of predicting both homolytic and heterolytic BDEs for molecules of any charge. To test the model, we have constructed a dataset of both homolytic and heterolytic BDEs for neutral and charged (1 and +1) molecules. BonDNet achieves a mean absolute error (MAE) of 0.022 eV for unseen test data, significantly below chemical accuracy (0.043 eV). Besides the ability to handle complex bond dissociation reactions that no previous model could con- sider, BonDNet distinguishes itself even in only predicting homolytic BDEs for neutral molecules; it achieves an MAE of 0.020 eV on the PubChem BDE dataset, a 20% improvement over the previous best performing model. We gain additional insight into the model’s predictions by analyzing the patterns in the features representing the molecules and the bond dissociation reactions, which are qualitatively consistent with chemical rules and intuition. BonDNet is just one application of our general approach to representing and learning chemical reactivity, and it could be easily extended to the prediction of other reaction properties in the future.</p></div></div></div>

Download Full-text

Combining Activity Trackers With Motivational Interviewing and Mutual Support to Increase Physical Activity in Parent-Adolescent Dyads: Longitudinal Observational Feasibility Study (Preprint)

10.2196/preprints.8878 ◽

2017 ◽

Author(s):

Josette Bianchi-Hayes ◽

Elinor Schoenfeld ◽

Rosa Cataldo ◽

Wei Hou ◽

Catherine Messina ◽

...

Keyword(s):

Physical Activity ◽

Weight Management ◽

Rank Order ◽

Adolescent Obesity ◽

Step Count ◽

Daily Step ◽

Management Interventions ◽

Phone Calls ◽

Activity Trackers ◽

Daily Step Count

BACKGROUND An essential component of any effective adolescent weight management program is physical activity (PA). PA levels drop dramatically in adolescence, contributing to the rising prevalence of adolescent obesity. Therefore, finding innovative interventions to address this decline in PA may help adolescents struggling with weight issues. The growing field of health technology provides potential solutions for addressing chronic health issues and lifestyle change, such as adolescent obesity. Activity trackers, used in conjunction with smartphone apps, can engage, motivate, and foster support among users while simultaneously providing feedback on their PA progress. OBJECTIVE The objective of our study was to evaluate the effect of a 10-week pilot study using smartphone-enabled activity tracker data to tailor motivation and goal setting on PA for overweight and obese adolescents and their parents. METHODS We queried enrolled adolescents, aged 14 to 16 years, with a body mass index at or above the 85th percentile, and 1 of their parents as to behaviors, barriers to change, and perceptions about exercise and health before and after the intervention. We captured daily step count and active minutes via activity trackers. Staff made phone calls to dyads at weeks 1, 2, 4, and 8 after enrollment to set daily personalized step-count and minutes goals based on their prior data and age-specific US national guidelines. We evaluated dyad correlations using nonparametric Spearman rank order correlations. RESULTS We enrolled 9 parent-adolescent dyads. Mean adolescent age was 15 (SD 0.9) years (range 14-16 years; 4 female and 5 male participants); mean parent age was 47 (SD 8.0) years (range 36-66 years). On average, adolescents met their personalized daily step-count goals on 35% (range 11%-62%) of the days they wore their trackers; parents did so on 39% (range 3%-68%) of the days they wore their trackers. Adolescents met their active-minutes goals on 55% (range 27%-85%) of the days they wore their trackers; parents did so on 83% (range 52%-97%) of the days. Parent and adolescent success was strongly correlated (step count: r=.36, P=.001; active minutes: r=.30, P=.007). Parental age was inversely correlated with step-count success (r=–.78, P=.01). CONCLUSIONS Our findings illustrate that parent-adolescent dyads have highly correlated PA success rates. This supports further investigation of family-centered weight management interventions for adolescents, particularly those that involve the parent and the adolescent working together.

Download Full-text

Pointer-Based Item-to-Item Collaborative Filtering Recommendation System Using a Machine Learning Model

International Journal of Information Technology & Decision Making ◽

10.1142/s0219622021500619 ◽

2021 ◽

pp. 1-22

Author(s):

Celestine Iwendi ◽

Ebuka Ibeke ◽

Harshini Eggoni ◽

Sreerajavenkatareddy Velagala ◽

Gautam Srivastava

Keyword(s):

Machine Learning ◽

Collaborative Filtering ◽

Recommendation System ◽

Absolute Error ◽

Learning Model ◽

Text Recall ◽

Machine Learning Model ◽

Similarity Algorithm ◽

Recommendation Accuracy ◽

Better Than

The creation of digital marketing has enabled companies to adopt personalized item recommendations for their customers. This process keeps them ahead of the competition. One of the techniques used in item recommendation is known as item-based recommendation system or item–item collaborative filtering. Presently, item recommendation is based completely on ratings like 1–5, which is not included in the comment section. In this context, users or customers express their feelings and thoughts about products or services. This paper proposes a machine learning model system where 0, 2, 4 are used to rate products. 0 is negative, 2 is neutral, 4 is positive. This will be in addition to the existing review system that takes care of the users’ reviews and comments, without disrupting it. We have implemented this model by using Keras, Pandas and Sci-kit Learning libraries to run the internal work. The proposed approach improved prediction with [Formula: see text] accuracy for Yelp datasets of businesses across 11 metropolitan areas in four countries, along with a mean absolute error (MAE) of [Formula: see text], precision at [Formula: see text], recall at [Formula: see text] and F1-Score at [Formula: see text]. Our model shows scalability advantage and how organizations can revolutionize their recommender systems to attract possible customers and increase patronage. Also, the proposed similarity algorithm was compared to conventional algorithms to estimate its performance and accuracy in terms of its root mean square error (RMSE), precision and recall. Results of this experiment indicate that the similarity recommendation algorithm performs better than the conventional algorithm and enhances recommendation accuracy.

Download Full-text

Backpropagation Neural Network-Based Machine Learning Model for Prediction of Soil Friction Angle

Mathematical Problems in Engineering ◽

10.1155/2020/8845768 ◽

2020 ◽

Vol 2020 ◽

pp. 1-11

Author(s):

Thuy-Anh Nguyen ◽

Hai-Bang Ly ◽

Binh Thai Pham

Keyword(s):

Neural Network ◽

Machine Learning ◽

Pearson Correlation ◽

Field Tests ◽

Friction Angle ◽

Absolute Error ◽

Learning Model ◽

Machine Learning Techniques ◽

Backpropagation Neural Network ◽

Machine Learning Model

In the design process of foundations, pavements, retaining walls, and other geotechnical matters, estimation of soil strength-related parameters is crucial. In particular, the friction angle is a critical shear strength factor in assessing the stability and deformation of geotechnical structures. Practically, laboratory or field tests have been conducted to determine the friction angle of soil. However, these jobs are often time-consuming and quite expensive. Therefore, the prediction of geo-mechanical properties of soils using machine learning techniques has been widely applied in recent times. In this study, the Bayesian regularization backpropagation algorithm is built to predict the internal friction angle of the soil based on 145 data collected from experiments. The performance of the model is evaluated by three specific statistical criteria, such as the Pearson correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). The results show that the proposed algorithm performed well for the prediction of the friction angle of soil (R = 0.8885, RMSE = 0.0442, and MAE = 0.0328). Therefore, it can be concluded that the backpropagation neural network-based machine learning model is a reasonably accurate and useful prediction tool for engineers in the predesign phase.

Download Full-text

HOMO–LUMO Gaps and Molecular Structures of Polycyclic Aromatic Hydrocarbons in Soot Formation

Frontiers in Mechanical Engineering ◽

10.3389/fmech.2021.744001 ◽

2021 ◽

Vol 7 ◽

Author(s):

Yabei Xu ◽

Qingzhao Chu ◽

Dongping Chen ◽

Andrés Fuentes

Keyword(s):

Machine Learning ◽

Functional Groups ◽

Soot Formation ◽

Absolute Error ◽

Learning Model ◽

Molecular Structures ◽

Machine Learning Model ◽

The Impact ◽

Homo Lumo ◽

Gap Values

A large number of PAH molecules is collected from recent literature. The HOMO-LUMO gap value of PAHs was computed at the level of B3LYP/6-311+G (d,p). The gap values lie in the range of 0.64–6.59 eV. It is found that the gap values of all PAH molecules exhibit a size dependency to some extent. However, the gap values may show a big variation even at the same size due to the complexity in the molecular structure. All collected PAHs are further classified into seven groups according to features in the structures, including the types of functional groups and the molecular planarity. The impact of functional groups, including –OH, –CHO, –COOH, =O, –O– and –CnHm on the bandgap is discussed in detail. The substitution of ketone group has the greatest reduction on the HOMO-LUMO gap of PAH molecules. Besides functional groups, we found that both local structure and the position of five-member rings make critical impacts on the bandgap via a detailed analysis of featured PAHs with unexpected low and high gap values. Among all these factors, the five-member rings forming nonplanar PAHs impact the gap most. Furthermore, we developed a machine learning model to predict the HOMO-LUMO gaps of PAHs, and the average absolute error is only 0.19 eV compared with the DFT calculations. The excellent performance of the machine learning model provides us an accurate and efficient way to explore the band information of PAHs in soot formation.

Download Full-text