2020
Kyritsis, Konstantinos; Diou, Christos; Delopoulos, Anastasios
A Data Driven End-to-end Approach for In-the-wild Monitoring of Eating Behavior Using Smartwatches Journal Article
In: IEEE Journal of Biomedical and Health Informatics, 2020.
Abstract | Links | BibTeX | Tags: Feature extraction, Informatics, Monitoring, Obesity, Sensors, Tools, Wrist
@article{kyritsis2020data,
title = {A Data Driven End-to-end Approach for In-the-wild Monitoring of Eating Behavior Using Smartwatches},
author = {Konstantinos Kyritsis and Christos Diou and Anastasios Delopoulos},
doi = {10.1109/JBHI.2020.2984907},
year = {2020},
date = {2020-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
publisher = {IEEE},
abstract = {The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior. Despite the study of obesity being in the spotlight, such tools can also be used to study eating disorders (e.g. anorexia nervosa) or provide a personalized monitoring platform for patients or athletes. This paper presents a complete framework towards the automated i) modeling of in-meal eating behavior and ii) temporal localization of meals, from raw inertial data collected in-the-wild using commercially available smartwatches. Initially, we present an end-to-end Neural Network which detects food intake events (i.e. bites). The proposed network uses both convolutional and recurrent layers that are trained simultaneously. Subsequently, we show how the distribution of the detected bites throughout the day can be used to estimate the start and end points of meals, using signal processing algorithms. We perform extensive evaluation on each framework part individually. Leave-one-subject-out (LOSO) evaluation shows that our bite detection approach outperforms four state-of-the-art algorithms towards the detection of bites during the course of a meal (0.923 F1 score). Furthermore, LOSO and held-out set experiments regarding the estimation of meal start/end points reveal that the proposed approach outperforms a relevant approach found in the literature (Jaccard Index of 0.820 and 0.821 for the LOSO and held-out experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.},
keywords = {Feature extraction, Informatics, Monitoring, Obesity, Sensors, Tools, Wrist},
pubstate = {published},
tppubtype = {article}
}
The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior. Despite the study of obesity being in the spotlight, such tools can also be used to study eating disorders (e.g. anorexia nervosa) or provide a personalized monitoring platform for patients or athletes. This paper presents a complete framework towards the automated i) modeling of in-meal eating behavior and ii) temporal localization of meals, from raw inertial data collected in-the-wild using commercially available smartwatches. Initially, we present an end-to-end Neural Network which detects food intake events (i.e. bites). The proposed network uses both convolutional and recurrent layers that are trained simultaneously. Subsequently, we show how the distribution of the detected bites throughout the day can be used to estimate the start and end points of meals, using signal processing algorithms. We perform extensive evaluation on each framework part individually. Leave-one-subject-out (LOSO) evaluation shows that our bite detection approach outperforms four state-of-the-art algorithms towards the detection of bites during the course of a meal (0.923 F1 score). Furthermore, LOSO and held-out set experiments regarding the estimation of meal start/end points reveal that the proposed approach outperforms a relevant approach found in the literature (Jaccard Index of 0.820 and 0.821 for the LOSO and held-out experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.
Kyritsis, Konstantinos; Fagerberg, Petter; Ioakimidis, Ioannis; Klingelhoefer, Lisa; Reichmann, Heinz; Delopoulos, Anastasios
Using IMU sensors to assess motor degradation of PD patients by modeling in-meal plate-to-mouth movement elongation Inproceedings
In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 494–497, IEEE 2020.
Abstract | Links | BibTeX | Tags: Accelerometers, control, Degradation, Feature extraction, Mouth, PD, Sensors, Support vector machines
@inproceedings{kyritsis2020using,
title = {Using IMU sensors to assess motor degradation of PD patients by modeling in-meal plate-to-mouth movement elongation},
author = {Konstantinos Kyritsis and Petter Fagerberg and Ioannis Ioakimidis and Lisa Klingelhoefer and Heinz Reichmann and Anastasios Delopoulos},
doi = {10.1109/EMBC44109.2020.9175615},
year = {2020},
date = {2020-01-01},
booktitle = {2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)},
pages = {494--497},
organization = {IEEE},
abstract = {Parkinson's disease (PD) is the second most common age-related neurodegenerative disorder after Alzheimer's disease, associated, among others, with motor symptoms such as resting tremor, rigidity and bradykinesia. At the same time, early diagnosis of PD is hindered by a high misdiagnosis rate and the subjective nature of the diagnosis process itself. Recent developments in mobile and wearable devices, such as smartphones and smartwatches, have allowed the automated detection and objective measurement of PD symptoms. In this paper we investigate the hypothesis that PD motor symptom degradation can be assessed by studying the in-meal behavior and modeling the food intake process. To achieve this, we use the inertial data from a commercial smartwatch to investigate the in-meal eating behavior of healthy controls and PD patients. In addition, we define and provide a methodology for calculating Plate-to-Mouth (PtM), an indicator that relates with the average time that the hand spends transferring food from the plate towards the mouth during the course of a meal. The presented experimental results, using our collected dataset of 28 participants (7 healthy controls and 21 PD patients), support our hypothesis. Results initially point out that PD patients have a higher PtM value than the healthy controls. Finally, using PtM we achieve a precision/recall/F1 of 0.882/0.714/0.789 towards classifying the meals from the PD patients and healthy controls.},
keywords = {Accelerometers, control, Degradation, Feature extraction, Mouth, PD, Sensors, Support vector machines},
pubstate = {published},
tppubtype = {inproceedings}
}
Parkinson's disease (PD) is the second most common age-related neurodegenerative disorder after Alzheimer's disease, associated, among others, with motor symptoms such as resting tremor, rigidity and bradykinesia. At the same time, early diagnosis of PD is hindered by a high misdiagnosis rate and the subjective nature of the diagnosis process itself. Recent developments in mobile and wearable devices, such as smartphones and smartwatches, have allowed the automated detection and objective measurement of PD symptoms. In this paper we investigate the hypothesis that PD motor symptom degradation can be assessed by studying the in-meal behavior and modeling the food intake process. To achieve this, we use the inertial data from a commercial smartwatch to investigate the in-meal eating behavior of healthy controls and PD patients. In addition, we define and provide a methodology for calculating Plate-to-Mouth (PtM), an indicator that relates with the average time that the hand spends transferring food from the plate towards the mouth during the course of a meal. The presented experimental results, using our collected dataset of 28 participants (7 healthy controls and 21 PD patients), support our hypothesis. Results initially point out that PD patients have a higher PtM value than the healthy controls. Finally, using PtM we achieve a precision/recall/F1 of 0.882/0.714/0.789 towards classifying the meals from the PD patients and healthy controls.
2019
Kyritsis, Konstantinos; Diou, Christos; Delopoulos, Anastasios
Modeling wrist micromovements to measure in-meal eating behavior from inertial sensor data Journal Article
In: IEEE journal of biomedical and health informatics, 23 (6), pp. 2325–2334, 2019.
Abstract | Links | BibTeX | Tags: Acceleration, Feature extraction, Informatics, Monitoring, Mouth, Obesity, Wrist
@article{kyritsis2019modeling,
title = {Modeling wrist micromovements to measure in-meal eating behavior from inertial sensor data},
author = {Konstantinos Kyritsis and Christos Diou and Anastasios Delopoulos},
doi = {10.1109/JBHI.2019.2892011},
year = {2019},
date = {2019-01-01},
journal = {IEEE journal of biomedical and health informatics},
volume = {23},
number = {6},
pages = {2325--2334},
publisher = {IEEE},
abstract = {Overweight and obesity are both associated with in-meal eating parameters such as eating speed. Recently, the plethora of available wearable devices in the market ignited the interest of both the scientific community and the industry toward unobtrusive solutions for eating behavior monitoring. In this paper, we present an algorithm for automatically detecting the in-meal food intake cycles using the inertial signals (acceleration and orientation velocity) from an off-the-shelf smartwatch. We use five specific wrist micromovements to model the series of actions leading to and following an intake event (i.e., bite). Food intake detection is performed in two steps. In the first step, we process windows of raw sensor streams and estimate their micromovement probability distributions by means of a convolutional neural network. In the second step, we use a long short-term memory network to capture the temporal evolution and classify sequences of windows as food intake cycles. Evaluation is performed using a challenging dataset of 21 meals from 12 subjects. In our experiments, we compare the performance of our algorithm against three state-of-theart approaches, where our approach achieves the highest F1 detection score (0.913 in the leave-one-subject-out experiment). The dataset used in the experiments is available at https://mug.ee.auth.gr/intake-cycle-detection/.},
keywords = {Acceleration, Feature extraction, Informatics, Monitoring, Mouth, Obesity, Wrist},
pubstate = {published},
tppubtype = {article}
}
Overweight and obesity are both associated with in-meal eating parameters such as eating speed. Recently, the plethora of available wearable devices in the market ignited the interest of both the scientific community and the industry toward unobtrusive solutions for eating behavior monitoring. In this paper, we present an algorithm for automatically detecting the in-meal food intake cycles using the inertial signals (acceleration and orientation velocity) from an off-the-shelf smartwatch. We use five specific wrist micromovements to model the series of actions leading to and following an intake event (i.e., bite). Food intake detection is performed in two steps. In the first step, we process windows of raw sensor streams and estimate their micromovement probability distributions by means of a convolutional neural network. In the second step, we use a long short-term memory network to capture the temporal evolution and classify sequences of windows as food intake cycles. Evaluation is performed using a challenging dataset of 21 meals from 12 subjects. In our experiments, we compare the performance of our algorithm against three state-of-theart approaches, where our approach achieves the highest F1 detection score (0.913 in the leave-one-subject-out experiment). The dataset used in the experiments is available at https://mug.ee.auth.gr/intake-cycle-detection/.
Papadopoulos, Alexandros; Kyritsis, Konstantinos; Klingelhoefer, Lisa; Bostanjopoulou, Sevasti; Chaudhuri, Ray K; Delopoulos, Anastasios
Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning Journal Article
In: IEEE Journal of Biomedical and Health Informatics, 2019.
Abstract | Links | BibTeX | Tags: Accelerometers, Annotations, Diseases, Feature extraction, Rigidity, Sensors, Standards
@article{papadopoulos2019detecting,
title = {Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning},
author = {Alexandros Papadopoulos and Konstantinos Kyritsis and Lisa Klingelhoefer and Sevasti Bostanjopoulou and Ray K Chaudhuri and Anastasios Delopoulos},
doi = {10.1109/JBHI.2019.2961748},
year = {2019},
date = {2019-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
publisher = {IEEE},
abstract = {Parkinson's Disease (PD) is a slowly evolving neurological disease that affects about 1% of the population above 60 years old, causing symptoms that are subtle at first, but whose intensity increases as the disease progresses. Automated detection of these symptoms could offer clues as to the early onset of the disease, thus improving the expected clinical outcomes of the patients via appropriately targeted interventions. This potential has led many researchers to develop methods that use widely available sensors to measure and quantify the presence of PD symptoms such as tremor, rigidity and braykinesia. However, most of these approaches operate under controlled settings, such as in lab or at home, thus limiting their applicability under free-living conditions. In this work, we present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device. We propose a Multiple-Instance Learning approach, wherein a subject is represented as an unordered bag of accelerometer signal segments and a single, expert-provided, tremor annotation. Our method combines deep feature learning with a learnable pooling stage that is able to identify key instances within the subject bag, while still being trainable end-to-end. We validate our algorithm on a newly introduced dataset of 45 subjects, containing accelerometer signals collected entirely in-the-wild. The good classification performance obtained in the conducted experiments suggests that the proposed method can efficiently navigate the noisy environment of in-the-wild recordings.},
keywords = {Accelerometers, Annotations, Diseases, Feature extraction, Rigidity, Sensors, Standards},
pubstate = {published},
tppubtype = {article}
}
Parkinson's Disease (PD) is a slowly evolving neurological disease that affects about 1% of the population above 60 years old, causing symptoms that are subtle at first, but whose intensity increases as the disease progresses. Automated detection of these symptoms could offer clues as to the early onset of the disease, thus improving the expected clinical outcomes of the patients via appropriately targeted interventions. This potential has led many researchers to develop methods that use widely available sensors to measure and quantify the presence of PD symptoms such as tremor, rigidity and braykinesia. However, most of these approaches operate under controlled settings, such as in lab or at home, thus limiting their applicability under free-living conditions. In this work, we present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device. We propose a Multiple-Instance Learning approach, wherein a subject is represented as an unordered bag of accelerometer signal segments and a single, expert-provided, tremor annotation. Our method combines deep feature learning with a learnable pooling stage that is able to identify key instances within the subject bag, while still being trainable end-to-end. We validate our algorithm on a newly introduced dataset of 45 subjects, containing accelerometer signals collected entirely in-the-wild. The good classification performance obtained in the conducted experiments suggests that the proposed method can efficiently navigate the noisy environment of in-the-wild recordings.
Kyritsis, Konstantinos; Diou, Christos; Delopoulos, Anastasios
Detecting meals in the wild using the inertial data of a typical smartwatch Inproceedings
In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4229–4232, IEEE 2019.
Abstract | Links | BibTeX | Tags: Accelerometers, Artificial neural networks, Detection algorithms, Feature extraction, Gyroscopes, Lenses, Monitoring
@inproceedings{kyritsis2019detecting,
title = {Detecting meals in the wild using the inertial data of a typical smartwatch},
author = {Konstantinos Kyritsis and Christos Diou and Anastasios Delopoulos},
doi = {10.1109/EMBC.2019.8857275},
year = {2019},
date = {2019-01-01},
booktitle = {2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
pages = {4229--4232},
organization = {IEEE},
abstract = {Automated and objective monitoring of eating behavior has received the attention of both the research community and the industry over the past few years. In this paper we present a method for automatically detecting meals in free living conditions, using the inertial data (acceleration and orientation velocity) from commercially available smartwatches. The proposed method operates in two steps. In the first step we process the raw inertial signals using an End-to-End Neural Network with the purpose of detecting the bite events throughout the recording. During the next step, we process the resulting bite detections using signal processing algorithms to obtain the final meal start and end timestamp estimates. Evaluation results obtained from our Leave One Subject Out experiments using our publicly available FIC and FreeFIC datasets, exhibit encouraging results by achieving an F1/Average Jaccard Index of 0.894/0.804.},
keywords = {Accelerometers, Artificial neural networks, Detection algorithms, Feature extraction, Gyroscopes, Lenses, Monitoring},
pubstate = {published},
tppubtype = {inproceedings}
}
Automated and objective monitoring of eating behavior has received the attention of both the research community and the industry over the past few years. In this paper we present a method for automatically detecting meals in free living conditions, using the inertial data (acceleration and orientation velocity) from commercially available smartwatches. The proposed method operates in two steps. In the first step we process the raw inertial signals using an End-to-End Neural Network with the purpose of detecting the bite events throughout the recording. During the next step, we process the resulting bite detections using signal processing algorithms to obtain the final meal start and end timestamp estimates. Evaluation results obtained from our Leave One Subject Out experiments using our publicly available FIC and FreeFIC datasets, exhibit encouraging results by achieving an F1/Average Jaccard Index of 0.894/0.804.
2018
Papadopoulos, Alexandros; Kyritsis, Konstantinos; Sarafis, Ioannis; Delopoulos, Anastasios
Personalised meal eating behaviour analysis via semi-supervised learning Inproceedings
In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4768–4771, IEEE 2018.
Abstract | Links | BibTeX | Tags: Adaptation models, Entropy, Feature extraction, Hidden Markov models, Mouth, Support vector machines, Training
@inproceedings{papadopoulos2018personalised,
title = {Personalised meal eating behaviour analysis via semi-supervised learning},
author = {Alexandros Papadopoulos and Konstantinos Kyritsis and Ioannis Sarafis and Anastasios Delopoulos},
doi = {10.1109/EMBC.2018.8513174},
year = {2018},
date = {2018-01-01},
booktitle = {2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
pages = {4768--4771},
organization = {IEEE},
abstract = {Automated monitoring and analysis of eating behaviour patterns, i.e., “how one eats”, has recently received much attention by the research community, owing to the association of eating patterns with health-related problems and especially obesity and its comorbidities. In this work, we introduce an improved method for meal micro-structure analysis. Stepping on a previous methodology of ours that combines feature extraction, SVM micro-movement classification and LSTM sequence modelling, we propose a method to adapt a pretrained IMU-based food intake cycle detection model to a new subject, with the purpose of improving model performance for that subject. We split model training into two stages. First, the model is trained using standard supervised learning techniques. Then, an adaptation step is performed, where the model is fine-tuned on unlabeled samples of the target subject via semisupervised learning. Evaluation is performed on a publicly available dataset that was originally created and used in [1] and has been extended here to demonstrate the effect of the semisupervised approach, where the proposed method improves over the baseline method.},
keywords = {Adaptation models, Entropy, Feature extraction, Hidden Markov models, Mouth, Support vector machines, Training},
pubstate = {published},
tppubtype = {inproceedings}
}
Automated monitoring and analysis of eating behaviour patterns, i.e., “how one eats”, has recently received much attention by the research community, owing to the association of eating patterns with health-related problems and especially obesity and its comorbidities. In this work, we introduce an improved method for meal micro-structure analysis. Stepping on a previous methodology of ours that combines feature extraction, SVM micro-movement classification and LSTM sequence modelling, we propose a method to adapt a pretrained IMU-based food intake cycle detection model to a new subject, with the purpose of improving model performance for that subject. We split model training into two stages. First, the model is trained using standard supervised learning techniques. Then, an adaptation step is performed, where the model is fine-tuned on unlabeled samples of the target subject via semisupervised learning. Evaluation is performed on a publicly available dataset that was originally created and used in [1] and has been extended here to demonstrate the effect of the semisupervised approach, where the proposed method improves over the baseline method.
2017
Kyritsis, Konstantinos; Tatli, Christina Lefkothea; Diou, Christos; Delopoulos, Anastasios
Automated analysis of in meal eating behavior using a commercial wristband IMU sensor Inproceedings
In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2843–2846, IEEE 2017.
Abstract | Links | BibTeX | Tags: Acceleration, Accelerometers, Feature extraction, Gyroscopes, Hidden Markov models, Mouth, Support vector machines
@inproceedings{kyritsis2017automated,
title = {Automated analysis of in meal eating behavior using a commercial wristband IMU sensor},
author = {Konstantinos Kyritsis and Christina Lefkothea Tatli and Christos Diou and Anastasios Delopoulos},
doi = {10.1109/EMBC.2017.8037449},
year = {2017},
date = {2017-01-01},
booktitle = {2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
pages = {2843--2846},
organization = {IEEE},
abstract = {Automatic objective monitoring of eating behavior using inertial sensors is a research problem that has received a lot of attention recently, mainly due to the mass availability of IMUs and the evidence on the importance of quantifying and monitoring eating patterns. In this paper we propose a method for detecting food intake cycles during the course of a meal using a commercially available wristband. We first model micro-movements that are part of the intake cycle and then use HMMs to model the sequences of micro-movements leading to mouthfuls. Evaluation is carried out on an annotated dataset of 8 subjects where the proposed method achieves 0:78 precision and 0:77 recall. The evaluation dataset is publicly available at http://mug.ee.auth.gr/intake-cycle-detection/.},
keywords = {Acceleration, Accelerometers, Feature extraction, Gyroscopes, Hidden Markov models, Mouth, Support vector machines},
pubstate = {published},
tppubtype = {inproceedings}
}
Automatic objective monitoring of eating behavior using inertial sensors is a research problem that has received a lot of attention recently, mainly due to the mass availability of IMUs and the evidence on the importance of quantifying and monitoring eating patterns. In this paper we propose a method for detecting food intake cycles during the course of a meal using a commercially available wristband. We first model micro-movements that are part of the intake cycle and then use HMMs to model the sequences of micro-movements leading to mouthfuls. Evaluation is carried out on an annotated dataset of 8 subjects where the proposed method achieves 0:78 precision and 0:77 recall. The evaluation dataset is publicly available at http://mug.ee.auth.gr/intake-cycle-detection/.