An EMG-based Eating Behaviour Monitoring System with Haptic Feedback to Promote Mindful Eating (Preprint)

2020 ◽  
Author(s):  
Chee Siang Ang ◽  
Benjamin Nicholls ◽  
Eiman Kanjo ◽  
Panote Siriyaraya ◽  
Woon-Hong Yeo ◽  
...  
Keyword(s):  
Haptic Feedback ◽  
Eating Behaviour ◽  
Automated System ◽  
Support Vector ◽  
Mindful Eating ◽  
Feedback Systems ◽  
Unhealthy Eating ◽  
Traditional Approaches ◽  
Chewing Behaviour ◽  
Improve Health

BACKGROUND Mindless eating, or the lack of awareness of the food we are consuming, has been linked to health problems attributed to unhealthy eating behaviour, including obesity. Traditional approaches used to moderate eating behaviour often rely on inaccurate self-logging, manual observations or bulky equipment. Overall, there is a need for an intelligent and lightweight system which can automatically monitor eating behaviour and provide feedback. OBJECTIVE In this paper, we investigate: i) the development of an automated system for detecting eating behaviour using wearable Electromyography (EMG) sensors, and ii) the application of such a system in combination with real time wristband haptic feedback to facilitate mindful eating. METHODS Data collected from 16 participants were used to develop an algorithm for detecting chewing and swallowing. We extracted 18 features from EMG and presented those features to different machine learning classifiers. Based on this algorithm, we developed a system to enable participants to self-moderate their chewing behaviour using haptic feedback. An experiment study was carried out with 20 additional participants to evaluate the effectiveness of eating monitoring and haptic interface in promoting mindful eating. RESULTS Our proposed algorithm is able to automatically assess eating behaviour accurately using the EMG-extracted features and a Support Vector Machine (SVM): F1-Score=0.94 for chewing classification, and F1-Score=0.86 for swallowing classification. The experimental study showed that that participants exhibited a lower rate of chewing when haptic feedback delivered in forms of wristband vibration was used compared to a baseline and non-haptic condition (F (2,38) = 58.243, p <.001). CONCLUSIONS These findings may have major implications for research in eating behaviour, providing key insights into the impacts of automatic chewing detection and haptic feedback systems on moderating eating behaviour with the aim to improve health outcomes.

To intend or to be willing? The prediction of unhealthy eating behaviour amongst adolescents

2008 ◽  
Author(s):  
J. H. Gerrits ◽  
J. B. F. De Wit ◽  
R. G. Kuijer ◽  
D. T. D. De Ridder
Keyword(s):  
Eating Behaviour ◽  
Unhealthy Eating

Mindful eating for overweight and obese women in Brazil: An exploratory mixed-methods pilot study

2021 ◽  
pp. 026010602110527
Author(s):  
Vera Salvo ◽  
Adriana Sanudo ◽  
Jean Kristeller ◽  
Mariana Cabral Schveitzer ◽  
Patricia Martins ◽  
...  
Keyword(s):  
Weight Loss ◽  
Mixed Methods ◽  
Qualitative Data ◽  
Eating Behaviour ◽  
Risk Level ◽  
Mindful Eating ◽  
Adult Women ◽  
Post Intervention ◽  
Obese People ◽  
Eat 26

Background: Worldwide, approximately 95% of obese people who follow diets for weight loss fail to maintain their weight loss in the long term. To fill this gap, mindfulness-based interventions, with a focus on mindful eating, are promising therapies to address this challenging public health issue. Aim: To verify the effects of the Mindfulness-Based Eating Awareness Training (MB-EAT) protocol by exploring quantitative and qualitative data collected from Brazilian women. Methods: A single-group, mixed-methods trial was conducted at a public university with adult women ( n = 34). Four MB-EAT groups were offered weekly for 2.5-h sessions over 12 weeks. Pre- and post-intervention assessments included body mass index (BMI) and self-report measures of anxiety, depression, mindfulness, self-compassion, and eating behaviour. Qualitative information was collected using focus groups in the last session of each group, including both participants and MB-EAT instructors. The qualitative data were examined using thematic analyses and empirical categories. Results: Twenty participants (58.8%) completed both pre- and post-intervention assessments, with adequate attendance (≥4 sessions). There was a significant average decrease in weight of 1.9 ± 0.6 kg from pre- to post-intervention. All participants who had scored at the risk level for eating disorders on the EAT-26 decreased their score below this risk level. Qualitative analysis identified that participants were able to engage a more compassionate perspective on themselves, as well as greater self-awareness and self-acceptance. Conclusion: The MB-EAT showed preliminary efficacy in promoting weight loss and improvements in mindfulness and eating behaviour. This intervention promoted effects beyond those expected, extending to other life contexts.

Zinc-specific Food Frequency Questionnaire To Assess College Women’s Eating Habits

2009 ◽  
Vol 70 (4) ◽  
pp. 204-208 ◽  
Author(s):  
Janet M. Lacey ◽  
Deanne U. Zotter
Keyword(s):  
Food Frequency Questionnaire ◽  
Assessment Tool ◽  
Eating Habits ◽  
Eating Behaviour ◽  
Eating Attitudes ◽  
Eating Attitude ◽  
Food Frequency ◽  
Unhealthy Eating ◽  
Starting Point ◽  
Eat 26

Zinc deficiency has been reported in individuals with eating disorders, the risks of which increase during the adolescent and early adult years. A food frequency questionnaire (FFQ) specific for zinc-rich foods was tested for its usefulness in identifying problematic eating behaviour tendencies in college-age women. Ninety-two female students enrolled in a university introductory psychology course volunteered to complete demographic information, the Eating Attitudes Test (EAT-26), and a zinc-specific FFQ (ZnFFQ). Relationships among estimated zinc intakes, food/lifestyle habits, and eating attitude variables were examined. Twenty-five women had estimated intakes below the Recommended Dietary Allowance (RDA) for zinc. Individuals in the highest zinc intake group (over twice the RDA) had a tendency to score higher on the EAT-26 and the bulimia subscale. Vegetarians also scored high on the EAT-26. Although our data are limited, the ZnFFQ should be studied further to determine whether it could play a useful role in identifying individuals at risk for bulimia. The ZnFFQ is a simple, non-confrontational assessment tool and may be a helpful starting point for identifying women with unhealthy eating habits.

Supervised Change Detection in Satellite Imagery Using Super Pixels and Relevance Feedback

GEOMATICA ◽  
2014 ◽  
Vol 68 (1) ◽  
pp. 5-14 ◽  
Author(s):  
Surender Varma Gadhiraju ◽  
Hichem Sahbi ◽  
Biplab Banerjee ◽  
Krishna Mohan Buddhiraju
Keyword(s):  
Change Detection ◽  
Relevance Feedback ◽  
Ground Truth ◽  
Feedback Mechanism ◽  
User Preferences ◽  
Support Vector ◽  
Remotely Sensed Data ◽  
Detection Strategy ◽  
Final Output ◽  
Traditional Approaches

The data from remote sensing satellites provide opportunities to acquire information about land at varying resolutions and has been widely used for change detection studies. A large number of change detection methodologies and techniques utilizing remotely sensed data have been developed, and newer techniques are still emerging. In this paper, a novel supervised approach of change detection using Support Vector Machine (SVM) and super pixels is proposed. In the formulation of change detection, SVM is modeled as a binary classifier to get the final output as “Change” and “No-Change” information. A relevant feedback mechanism is also included in to the change detection strategy so that it adapts in accordance with user preferences. Both ground truth and relevance feedback are collected using the developed GUIs. Comparison of the proposed approach with three other techniques of change detection is done via the experiments conducted on three multitemporal datasets. It is observed that the supervised, super pixel based change detection strategy gives superior results compared to traditional approaches of change detection. It is also seen that the usage of relevance feedback fine-tunes the results of change detection and acts as a desirable post-change detection process.

scholarly journals Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3532 ◽  
Author(s):  
Nicola Mansbridge ◽  
Jurgen Mitsch ◽  
Nicola Bollard ◽  
Keith Ellis ◽  
Giuliana Miguel-Pacheco ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Time Budget ◽  
Learning Algorithms ◽  
Eating Behaviour ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Optimum Number ◽  
Eating Behaviours ◽  
Adaptive Boosting

Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.

scholarly journals PSO-SVM hybrid system for melanoma detection from histo-pathological images

2019 ◽  
Vol 9 (4) ◽  
pp. 2941
Author(s):  
Maen Takruri ◽  
Mohamed Khaled Abu Mahmoud ◽  
Adel Al-Jumaily
Keyword(s):  
Hybrid System ◽  
Wavelet Packet ◽  
Automated System ◽  
Support Vector ◽  
Svm Classifier ◽  
Pathology Laboratory ◽  
Swarm Optimization ◽  
Image Histogram ◽  
Melanoma Detection ◽  
Occurrence Matrix

This paper introduces an automated system for skin cancer (melanoma) detection from Histo-pathological images sampled from microscopic slides of skin biopsy. The proposed system is a hybrid system based on Particle Swarm Optimization and Support Vector Machine (PSO-SVM). The features used are extracted from the grayscale image histogram, the co-occurrence matrix and the energy of the wavelet coefficients resulting from the wavelet packet decomposition. The PSO-SVM system selects the best feature set and the best values for the SVM parameters (C and γ) that optimize the performance of the SVM classifier.   The system performance is tested on a real dataset obtained from the Southern Pathology Laboratory in Wollongong NSW, Australia. Evaluation results show a classification accuracy of 87.13%, a sensitivity of 94.1% and a specificity of 80.22%.The sensitivity and specificity results are comparable to those obtained by dermatologists.

scholarly journals Adaptive Bacteria Colony Picking in Unstructured Environments Using Intensity Histogram and Unascertained LS-SVM Classifier

2014 ◽  
Vol 2014 ◽  
pp. 1-10
Author(s):  
Kun Zhang ◽  
Minrui Fei ◽  
Xin Li ◽  
Huiyu Zhou
Keyword(s):  
Support Vector Machine ◽  
Mean Shift ◽  
Least Square ◽  
Support Vector ◽  
Svm Classifier ◽  
Least Square Estimation ◽  
Unstructured Environments ◽  
Novel Approach ◽  
Traditional Approaches ◽  
Improved Support Vector Machine

Features analysis is an important task which can significantly affect the performance of automatic bacteria colony picking. Unstructured environments also affect the automatic colony screening. This paper presents a novel approach for adaptive colony segmentation in unstructured environments by treating the detected peaks of intensity histograms as a morphological feature of images. In order to avoid disturbing peaks, an entropy based mean shift filter is introduced to smooth images as a preprocessing step. The relevance and importance of these features can be determined in an improved support vector machine classifier using unascertained least square estimation. Experimental results show that the proposed unascertained least square support vector machine (ULSSVM) has better recognition accuracy than the other state-of-the-art techniques, and its training process takes less time than most of the traditional approaches presented in this paper.

Haptic and Gesture-Based Assistive Technologies for People with Motor Disabilities

2014 ◽  
pp. 1-27
Author(s):  
Luis Alberto Rivera ◽  
Guilherme N. DeSouza
Keyword(s):  
Haptic Feedback ◽  
Component Analysis ◽  
Literature Survey ◽  
Assistive Technologies ◽  
Support Vector ◽  
Motor Disabilities ◽  
Multiple Sensors ◽  
Frequent Use ◽  
Power Wheelchairs ◽  
Single Sensor

The goal of this chapter is to explain how haptic and gesture-based assistive technologies work and how people with motor disabilities can interact with computers, cell phones, power wheelchairs, and so forth. The interaction is achieved through gestures and haptic feedback interfaces using bioelectrical signals such as in surface Electromyography. The chapter also provides a literature survey on ElectroMyoGraphic (EMG) devices and their use in the design of assistive technology, while it covers typical techniques used for pattern recognition and classification of EMG signals (including Independent Component Analysis, Artificial Neural Networks, Fuzzy, Support Vector Machines, Principle Component Analysis, the use of wavelet coefficients, and time versus frequency domain features) the main point driven by this literature survey is the frequent use of multiple sensors in the design and implementation of assistive technologies. This point is contrasted with the state-of-the-art, more specifically the authors’ current work, on the use of a single sensor as opposed to multiple sensors.

scholarly journals Investigating the Physics of Tokamak Global Stability with Interpretable Machine Learning Tools

2020 ◽  
Vol 10 (19) ◽  
pp. 6683
Author(s):  
Andrea Murari ◽  
Emmanuele Peluso ◽  
Michele Lungaroni ◽  
Riccardo Rossi ◽  
Michela Gelfusa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Independent Learning ◽  
Support Vector ◽  
Learning Tools ◽  
Feedback Systems ◽  
Theoretical Understanding ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Mining Tools

The inadequacies of basic physics models for disruption prediction have induced the community to increasingly rely on data mining tools. In the last decade, it has been shown how machine learning predictors can achieve a much better performance than those obtained with manually identified thresholds or empirical descriptions of the plasma stability limits. The main criticisms of these techniques focus therefore on two different but interrelated issues: poor “physics fidelity” and limited interpretability. Insufficient “physics fidelity” refers to the fact that the mathematical models of most data mining tools do not reflect the physics of the underlying phenomena. Moreover, they implement a black box approach to learning, which results in very poor interpretability of their outputs. To overcome or at least mitigate these limitations, a general methodology has been devised and tested, with the objective of combining the predictive capability of machine learning tools with the expression of the operational boundary in terms of traditional equations more suited to understanding the underlying physics. The proposed approach relies on the application of machine learning classifiers (such as Support Vector Machines or Classification Trees) and Symbolic Regression via Genetic Programming directly to experimental databases. The results are very encouraging. The obtained equations of the boundary between the safe and disruptive regions of the operational space present almost the same performance as the machine learning classifiers, based on completely independent learning techniques. Moreover, these models possess significantly better predictive power than traditional representations, such as the Hugill or the beta limit. More importantly, they are realistic and intuitive mathematical formulas, which are well suited to supporting theoretical understanding and to benchmarking empirical models. They can also be deployed easily and efficiently in real-time feedback systems.

Sign in / Sign up

Export Citation Format

Share Document