scholarly journals Development and validation of an interpretable Conditional RNN for weight change prediction an obesity management mobile app (Preprint)

2020 ◽  
Author(s):  
Ho Heon Kim ◽  
Young In Kim ◽  
Yu Rang Park
Keyword(s):  
Weight Loss ◽  
Predictive Model ◽  
Mobile App ◽  
Percentage Error ◽  
Obesity Management ◽  
Contributing Factors ◽  
Negative Contribution ◽  
Actual Weight ◽  
Average Percentage ◽  
Time Invariant

BACKGROUND As an alternative to on-site obesity management, a mobile-based intervention has been given more attention. Despite the rise of mobile interventions for obesity, there are lost opportunities to achieve better outcomes due to the lack of a predictive model using currently existing health data collected longitudinally and cross-sectionally. OBJECTIVE This study aimed to develop a predictive model for weight to be used in mobile-based interventions using interpretable AI, and to explore the contributing factors to weight loss. METHODS Using lifelong of mobile application users (Noom) who used a weight loss program for 16 weeks in the U.S., an interpretable recurrent neural network for the prediction of weight after intervention considering both time-variant variables and time-invariant variables was developed. This interpretable model was trained and validated with fivefold cross-validation testing (training set: 70%; testing: 30%) using lifelog data of app users for weight loss. Mean average percent error (MAPE) between actual weight loss and predicted weight, and contribution coefficients for model interpretation. To better understand the behavior factors to weight loss or gain, the contributing factors were calculated by the contribution coefficients in test sets to interpret the effects of contributing factors to weight loss. RESULTS A total of 17,867 eligible users were included in the analysis. The overall mean average percentage error of the model was 3.50% and the errors of the model declined from 3.78% to 3.45% by observing the data at the end of the program. The time level contribution was shown to be equally distributed at 0.0625 in each week, but this gradually decreased as it approached 16 weeks. Factors such as usage pattern, weight input frequency and meal input adherence, exercise, and sharp decreases in weight trajectories had negative contribution coefficients of -0.021, -0.032, -0.015, and -0.066, respectively. As for time-invariant variables, males had a -0.091 contribution coefficient. CONCLUSIONS An interpretable artificial intelligence to utilize both data and time fixed data can forecast weight loss precisely after obesity management application while preserving model transparency. This week to week prediction model is expected to improve weight loss and provide a global explanation of contributing factors, leading to better outcomes.

Actuation and dynamic mechanical characteristics of a core free flat dielectric electro-active polymer soft actuator

2020 ◽  
Vol 14 (4) ◽  
pp. 7396-7404
Author(s):  
Abdul Malek Abdul Wahab ◽  
Emiliano Rustighi ◽  
Zainudin A.
Keyword(s):  
Theoretical Model ◽  
Resonance Frequency ◽  
Dynamic Testing ◽  
Experimental Results ◽  
Percentage Error ◽  
Initial Tension ◽  
Average Percentage ◽  
Soft Actuator ◽  
Average Percentage Error ◽  
Mechanical Dynamics

Various complex shapes of dielectric electro-active polymer (DEAP) actuator have been promoted for several types of applications. In this study, the actuation and mechanical dynamics characteristics of a new core free flat DEAP soft actuator were investigated. This actuator was developed by Danfoss PolyPower. DC voltage of up to 2000 V was supplied for identifying the actuation characteristics of the actuator and compare with the existing formula. The operational frequency of the actuator was determined by dynamic testing. Then, the soft actuator has been modelled as a uniform bar rigidly fixed at one end and attached to mass at another end. Results from the theoretical model were compared with the experimental results. It was found that the deformation of the current actuator was quadratic proportional to the voltage supplied. It was found that experimental results and theory were not in good agreement for low and high voltage with average percentage error are 104% and 20.7%, respectively. The resonance frequency of the actuator was near 14 Hz. Mass of load added, inhomogeneity and initial tension significantly affected the resonance frequency of the soft actuator. The experimental results were consistent with the theoretical model at zero load. However, due to inhomogeneity, the frequency response function’s plot underlines a poor prediction where the theoretical calculation was far from experimental results as values of load increasing with the average percentage error 15.7%. Hence, it shows the proposed analytical procedure not suitable to provide accurate natural frequency for the DEAP soft actuator.

scholarly journals Adaptive Neuro-Fuzzy Inference System for Modelling the Effect of Slurry Impacts on PLA Material Processed by FDM

Polymers ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 118
Author(s):  
Bahaa Saleh ◽  
Ibrahem Maher ◽  
Yasser Abdelrhman ◽  
Mahmoud Heshmat ◽  
Osama Abdelaal
Keyword(s):  
Weight Gain ◽  
Fused Deposition Modeling ◽  
Synergetic Effect ◽  
Solid Particles ◽  
Percentage Error ◽  
Inference System ◽  
Average Percentage ◽  
Fused Deposition ◽  
Effect Of Water ◽  
Neuro Fuzzy

In this research, the effect of water-silica slurry impacts on polylactic acid (PLA) processed by fused deposition modeling (FDM) is examined under different conditions with the assistance of an adaptive neuro-fuzzy interference system (ANFIS). Building orientation, layer thickness, and slurry impact angle are considered as the controllable variables. Weight gain resulting from water, net weight gain, and total weight gain are the predicting variables. Results uncover the accomplishment of the ANFIS model to appropriately appraise slurry erosion in correlation with comparing real data. Both experimental and ANFIS results are almost identical with average percentage error less than 5.45 × 10−6. We observed during the slurry impacts tests that all specimens showed an increase in their weights. This weight gain was finally interpreted to the synergetic effect of water absorption and the solid particles fragmentations immersed within the specimens due to the successive slurry impacts.

scholarly journals Long-Term Iron and Vitamin B12 Deficiency Are Present after Bariatric Surgery, Despite the Widespread Use of Supplements

2021 ◽  
Vol 18 (9) ◽  
pp. 4541
Author(s):  
Mauro Lombardo ◽  
Arianna Franchi ◽  
Roberto Biolcati Rinaldi ◽  
Gianluca Rizzo ◽  
Monica D’Adamo ◽  
...  
Keyword(s):  
Bariatric Surgery ◽  
Weight Loss ◽  
Vitamin B12 ◽  
Vitamin B12 Deficiency ◽  
Ideal Body Weight ◽  
Excess Weight ◽  
Nutritional Deficiencies ◽  
Average Percentage ◽  
Nutritional Studies

There are few long-term nutritional studies in subjects undergoing bariatric surgery that have assessed weight regain and nutritional deficiencies. In this study, we report data 8 years after surgery on weight loss, use of dietary supplements and deficit of micronutrients in a cohort of patients from five centres in central and northern Italy. The study group consisted of 52 subjects (age: 38.1 ± 10.6 y, 42 females): 16 patients had Roux-en-Y gastric bypass (RYGB), 25 patients had sleeve gastrectomy (SG) and 11 subjects had adjustable gastric banding (AGB). All three bariatric procedures led to sustained weight loss: the average percentage excess weight loss, defined as weight loss divided by excess weight based on ideal body weight, was 60.6% ± 32.3. Despite good adherence to prescribed supplements, 80.7% of subjects (72.7%, AGB; 76.7%, SG; 93.8 %, RYGB) reported at least one nutritional deficiency: iron (F 64.3% vs. M 30%), vitamin B12 (F 16.6% vs. M 10%), calcium (F 33.3% vs. M 0%) and vitamin D (F 38.1% vs. M 60%). Long-term nutritional deficiencies were greater than the general population among men for iron and among women for vitamin B12.

scholarly journals European Guidelines for Obesity Management in Adults with a Very Low-Calorie Ketogenic Diet: A Systematic Review and Meta-Analysis

Obesity Facts ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 222-245
Author(s):  
Giovanna Muscogiuri ◽  
Marwan El Ghoch ◽  
Annamaria Colao ◽  
Maria Hassapidou ◽  
Volkan Yumuk ◽  
...  
Keyword(s):  
Systematic Review ◽  
Weight Loss ◽  
Body Composition ◽  
Body Weight ◽  
Side Effects ◽  
Ketogenic Diet ◽  
Meta Analysis ◽  
Dietary Treatment ◽  
Obesity Management ◽  
Weight Loss Interventions

<b><i>Background:</i></b> The very low-calorie ketogenic diet (VLCKD) has been recently proposed as an appealing nutritional strategy for obesity management. The VLCKD is characterized by a low carbohydrate content (&#x3c;50 g/day), 1–1.5 g of protein/kg of ideal body weight, 15–30 g of fat/day, and a daily intake of about 500–800 calories. <b><i>Objectives:</i></b> The aim of the current document is to suggest a common protocol for VLCKD and to summarize the existing literature on its efficacy in weight management and weight-related comorbidities, as well as the possible side effects. <b><i>Methods:</i></b> This document has been prepared in adherence with Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines. Literature searches, study selection, methodology development, and quality appraisal were performed independently by 2 authors and the data were collated by means of a meta-analysis and narrative synthesis. <b><i>Results:</i></b> Of the 645 articles retrieved, 15 studies met the inclusion criteria and were reviewed, revealing 4 main findings. First, the VLCKD was shown to result in a significant weight loss in the short, intermediate, and long terms and improvement in body composition parameters as well as glycemic and lipid profiles. Second, when compared with other weight loss interventions of the same duration, the VLCKD showed a major effect on reduction of body weight, fat mass, waist circumference, total cholesterol and triglyceridemia as well as improved insulin resistance. Third, although the VLCKD also resulted in a significant reduction of glycemia, HbA1c, and LDL cholesterol, these changes were similar to those obtained with other weight loss interventions. Finally, the VLCKD can be considered a safe nutritional approach under a health professional’s supervision since the most common side effects are usually clinically mild and easily to manage and recovery is often spontaneous. <b><i>Conclusions:</i></b> The VLCKD can be recommended as an effective dietary treatment for individuals with obesity after considering potential contra-indications and keeping in mind that any dietary treatment has to be personalized. <b><i>Prospero Registry:</i></b> The assessment of the efficacy of VLCKD on body weight, body composition, glycemic and lipid parameters in overweight and obese subjects: a meta-analysis (CRD42020205189).

O.11 Contributing factors to weight loss in chronicbronchitis and emphysema

1997 ◽  
Vol 16 ◽  
pp. 3-4
Author(s):  
E.M. Baarends ◽  
E.C. Creutzberg ◽  
E.F.M. Wouters ◽  
A.M.W.J. Schols
Keyword(s):  
Weight Loss ◽  
Contributing Factors ◽  
O 11

Weight loss trajectories and related factors in a 16-week mobile obesity intervention: A retrospective observational study (Preprint)

2021 ◽  
Author(s):  
Ho Heon Kim ◽  
Young In Kim ◽  
Andreas Michaelides ◽  
Yu Rang Park
Keyword(s):  
Machine Learning ◽  
Weight Loss ◽  
Effect Size ◽  
Weight Change ◽  
Average Weight ◽  
Learning Approach ◽  
Obesity Management ◽  
Significant Difference ◽  
Machine Learning Approach ◽  
Cluster 2

BACKGROUND In obesity management, whether patients lose 5% or more of their initial weight is a critical factor in their clinical outcome. However, evaluations that only take this approach cannot identify and distinguish between individuals whose weight change varies and those who steadily lose weight. Evaluation of weight loss considering the volatility of weight change through a mobile-based intervention for obesity can facilitate the understanding of individuals’ behavior and weight changes from a longitudinal perspective. OBJECTIVE With machine learning approach, we examined weight loss trajectories and explored the factors related to behavioral and app usage characteristics that induce weight loss. METHODS We used the lifelog data of 19,784 individuals who enrolled in a 16-week obesity management program on the healthcare app Noom in the US during August 8, 2013 to August 8, 2019. We performed K-means clustering with dynamic time warping to cluster the weight loss time series and inspected the quality of clusters with the total sum of distance within the clusters. To identify the usage factors to determine clustering assignment, we longitudinally compared weekly usage statistics with effect size on a weekly basis. RESULTS Initial Body Mass Index (BMI) of participants was 33.9±5.9 kg/m2, and ultimately reached an average BMI of 32.0±5.7 kg/m2. In their weight log, 5 Clusters were identified: Cluster 1 (sharp decrease) showed a high proportion of weight reduction class between 10% and 15%—the highest among the five clusters (n=2,364/12,796, 18.9%)—followed by Cluster 2 (moderate decrease), Cluster 3 (increase), Cluster 4 (yoyo), Cluster 5 (other). In comparison between cluster 2 and cluster 4, although the effect size of difference in the average meal input adherence and average weight input adherence did not show a significant difference in the first week, it increased continuously for 7 weeks (Cohen’s d=0.408; 0.38). CONCLUSIONS With machine learning approach clustering shape-based timeseries similarity, this study identified 5 weight loss trajectories in mobile weight management app. Overall adherence and early adherence related to self-monitoring emerged as a potential predictor of these trajectories.

scholarly journals SPASIAL DATA MINING MENGGUNAKAN MODEL SAR-KRIGING

2011 ◽  
Vol 5 (3) ◽  
pp. 52
Author(s):  
Atje Setiawan ◽  
Rudi Rosadi
Keyword(s):  
Data Mining ◽  
Elementary School ◽  
Spatial Data ◽  
Spatial Data Mining ◽  
Education Quality ◽  
Percentage Error ◽  
Kriging Method ◽  
National Education ◽  
Software Application ◽  
Average Percentage

The region of Indonesia is very sparse and it has a variation condition in social, economic and culture, so the problem in education quality at many locations is an interesting topic to be studied. Database used in this research is Base Survey of National Education 2003, while a spatial data is presented by district coordinate as a least analysis unit. The aim of this research is to study and to apply spatial data mining to predict education quality at elementary and junior high schools using SAR-Kriging method which combines an expansion SAR and Kriging method. Spatial data mining process has three stages. preprocessing, process of data mining, and post processing.For processing data and checking model, we built software application of Spatial Data Mining using SAR-Kriging method. An application is used to predict education quality at unsample locations at some cities at DIY Province.  The result shows that SAR-Kriging method for some cities at DIY for elementary school has an average percentage error 6.43%. We can conclude that for elementary school, SAR-Kriging method can be used as a fitted model. Keywords—  Expansion SAR, SAR-Kriging, quality education

scholarly journals Using the Habit App for Weight Loss Problem Solving: Development and Feasibility Study (Preprint)

2018 ◽  
Author(s):  
Sherry Pagoto ◽  
Bengisu Tulu ◽  
Emmanuel Agu ◽  
Molly E Waring ◽  
Jessica L Oleski ◽  
...  
Keyword(s):  
Weight Loss ◽  
Problem Solving ◽  
Mobile Apps ◽  
Mobile App ◽  
Behavioral Weight Loss ◽  
Problem Solving Therapy ◽  
Pilot Studies ◽  
Self Monitoring ◽  
Problem Solving Skills ◽  
Automated Delivery

BACKGROUND Reviews of weight loss mobile apps have revealed they include very few evidence-based features, relying mostly on self-monitoring. Unfortunately, adherence to self-monitoring is often low, especially among patients with motivational challenges. One behavioral strategy that is leveraged in virtually every visit of behavioral weight loss interventions and is specifically used to deal with adherence and motivational issues is problem solving. Problem solving has been successfully implemented in depression mobile apps, but not yet in weight loss apps. OBJECTIVE This study describes the development and feasibility testing of the Habit app, which was designed to automate problem-solving therapy for weight loss. METHODS Two iterative single-arm pilot studies were conducted to evaluate the feasibility and acceptability of the Habit app. In each pilot study, adults who were overweight or obese were enrolled in an 8-week intervention that included the Habit app plus support via a private Facebook group. Feasibility outcomes included retention, app usage, usability, and acceptability. Changes in problem-solving skills and weight over 8 weeks are described, as well as app usage and weight change at 16 weeks. RESULTS Results from both pilots show acceptable use of the Habit app over 8 weeks with on average two to three uses per week, the recommended rate of use. Acceptability ratings were mixed such that 54% (13/24) and 73% (11/15) of participants found the diet solutions helpful and 71% (17/24) and 80% (12/15) found setting reminders for habits helpful in pilots 1 and 2, respectively. In both pilots, participants lost significant weight (P=.005 and P=.03, respectively). In neither pilot was an effect on problem-solving skills observed (P=.62 and P=.27, respectively). CONCLUSIONS Problem-solving therapy for weight loss is feasible to implement in a mobile app environment; however, automated delivery may not impact problem-solving skills as has been observed previously via human delivery. CLINICALTRIAL ClinicalTrials.gov NCT02192905; https://clinicaltrials.gov/ct2/show/NCT02192905 (Archived by WebCite at http://www.webcitation.org/6zPQmvOF2)

The Impact of Weight Labels on Body Image, Internalized Weight Stigma, Affect, Perceived Health, and Intended Weight Loss Behaviors in Normal-Weight and Overweight College Women

2016 ◽  
Vol 31 (6) ◽  
pp. 484-490 ◽  
Author(s):  
Jamal H. Essayli ◽  
Jessica M. Murakami ◽  
Rebecca E. Wilson ◽  
Janet D. Latner
Keyword(s):  
Weight Loss ◽  
Body Image ◽  
Negative Affect ◽  
Perceived Health ◽  
Normal Weight ◽  
Weight Stigma ◽  
The Body ◽  
Actual Weight ◽  
Main Effects ◽  
The Impact

Purpose: To explore the psychological impact of weight labels. Design: A double-blind experiment that randomly informed participants that they were “normal weight” or “overweight.” Setting: Public university in Honolulu, Hawai‘i. Participants: Normal-weight and overweight female undergraduates (N = 113). Measures: The Body Image States Scale, Stunkard Rating Scale, Weight Bias Internalization Scale, Positive and Negative Affect Schedule, General Health question from the 12-item Short Form Health Survey, modified version of the Weight Loss Methods Scale, and a manipulation check. Analysis: A 2 × 2 between-subjects analysis of variance explored the main effects of the assigned weight label and actual weight and interactions between assigned weight label and actual weight. Results: Significant main effects of the assigned weight label emerged on measures of body dissatisfaction, F(1, 109) = 12.40, p = .001, [Formula: see text] = 0.10, internalized weight stigma, F(1, 108) = 4.35, p = .039, [Formula: see text] = .04, and negative affect, F(1, 108) = 9.22, p = .003, [Formula: see text] = .08. Significant assigned weight label × actual weight interactions were found on measures of perceived body image, F(1, 109) = 6.29, p = .014, [Formula: see text] = .06, and perceived health, F(1, 109) = 4.18, p = .043, [Formula: see text] = .04. Conclusion: A weight label of “overweight” may have negative psychological consequences, particularly for overweight women.

A method for predicting the capacity of a lithium-ion battery based on deep neural network

2021 ◽  
Author(s):  
JamesChan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Lithium Ion ◽  
Chemical Conversion ◽  
Absolute Error ◽  
Production Costs ◽  
Percentage Error ◽  
Average Percentage ◽  
True Value ◽  
Battery Capacity

This paper proposes a solution to predict the capacity of the lithium-ion battery's capacity division process using deep learning methods. This solution extracts the physical observation records of part of the process steps from the chemical conversion and volumetric processes as features, and trains a Deep Neural Network (DNN) to achieve accurate prediction of battery capacity. According to the test, the average percentage absolute error (Mean Absolute Percentage Error, MAPE) of the battery capacity predicted by this model is only 0.78% compared with the true value. Combining this model with the production line can greatly reduce production time and energy consumption, and reduce battery production costs.

Sign in / Sign up

Export Citation Format

Share Document