Leveraging Unlabelled Data in Multiple-Instance Learning Problems for Improved Detection of Parkinsonian Tremor in Free-Living Conditions

Data-driven approaches for remote detection of Parkinson's Disease and its motor symptoms have proliferated in recent years, owing to the potential clinical benefits of early diagnosis. The holy grail of such approaches is the free-living scenario, in which data are collected continuously and unobtrusively during every day life. However, obtaining fine-grained ground-truth and remaining unobtrusive is a contradiction and therefore, the problem is usually addressed via multiple-instance learning. Yet for large scale studies, obtaining even the necessary coarse ground-truth is not trivial, as a complete neurological evaluation is required. In contrast, large scale collection of data without any ground-truth is much easier. Nevertheless, utilizing unlabelled data in a multiple-instance setting is not straightforward, as the topic has received very little research attention. Here we try to fill this gap by introducing a new method for combining semi-supervised with multiple-instance learning. Our approach builds on the Virtual Adversarial Training principle, a state-of-the-art approach for regular semi-supervised learning, which we adapt and modify appropriately for the multiple-instance setting. We first establish the validity of the proposed approach through proof-of-concept experiments on synthetic problems generated from two well-known benchmark datasets. We then move on to the actual task of detecting PD tremor from hand acceleration signals collected in-the-wild, but in the presence of additional completely unlabelled data. We show that by leveraging the unlabelled data of 454 subjects we can achieve large performance gains (up to 9% increase in F1-score) in per-subject tremor detection for a cohort of 45 subjects with known tremor ground-truth.

Listen to your heart: A self-supervised approach for detecting murmur in heart-beat sounds for the Physionet 2022 challenge

Heart murmurs are abnormal sounds present in heartbeats, caused by turbulent blood flow through the heart. The PhysioNet 2022 challenge targets automatic detection of murmur from audio recordings of the heart and automatic detection of normal vs. abnormal clinical outcome. The recordings are captured from multiple locations around the heart. Our participation investigates the effectiveness of self-supervised learning for murmur detection. We evaluate the use of a backbone CNN, whose layers are trained in a self-supervised way with data from both this year's and the 2016 challenge. We use two different augmentations on each training sample, and normalized temperature-scaled cross-entropy loss. We experiment with different augmentations to learn effective phonocardiogram representations. To build the final detectors we train two classification heads, one for each challenge task. We present evaluation results for all combinations of the available augmentations, and for our multiple-augmentation approach.

Chewing Detection from Commercial Smart-glasses

Automatic dietary monitoring has progressed significantly during the last years, offering a variety of solutions, both in terms of sensors and algorithms as well as in terms of what aspect or parameters of eating behavior are measured and monitored. Automatic detection of eating based on chewing sounds has been studied extensively, however, it requires a microphone to be mounted on the subject's head for capturing the relevant sounds. In this work, we evaluate the feasibility of using an off-the-shelf commercial device, the Razer Anzu smart-glasses, for automatic chewing detection. The smart-glasses are equipped with stereo speakers and microphones that communicate with smart-phones via Bluetooth. The microphone placement is not optimal for capturing chewing sounds, however, we find that it does not significantly affect the detection effectiveness. We apply an algorithm from literature with some adjustments on a challenging dataset that we have collected in house. Leave-one-subject-out experiments yield promising results, with an F1-score of 0.96 for the best case of duration-based evaluation of eating time.

A Bottom-up method Towards the Automatic and Objective Monitoring of Smoking Behavior In-the-wild using Wrist-mounted Inertial Sensors

The consumption of tobacco has reached global epidemic proportions and is characterized as the leading cause of death and illness. Among the different ways of consuming tobacco (e.g., smokeless, cigars), smoking cigarettes is the most widespread. In this paper, we present a two-step, bottom-up algorithm towards the automatic and objective monitoring of cigarette-based, smoking behavior during the day, using the 3D acceleration and orientation velocity measurements from a commercial smartwatch. In the first step, our algorithm performs the detection of individual smoking gestures (i.e., puffs) using an artificial neural network with both convolutional and recurrent layers. In the second step, we make use of the detected puff density to achieve the temporal localization of smoking sessions that occur throughout the day. In the experimental section we provide extended evaluation regarding each step of the proposed algorithm, using our publicly available, realistic Smoking Event Detection (SED) and Free-living Smoking Event Detection (SED-FL) datasets recorded under semi-controlled and free-living conditions, respectively. In particular, leave-one-subject-out (LOSO) experiments reveal an F1-score of 0.863 for the detection of puffs and an F1-score/Jaccard index equal to 0.878/0.604 towards the temporal localization of smoking sessions during the day. Finally, to gain further insight, we also compare the puff detection part of our algorithm with a similar approach found in the recent literature.

Self-Supervised Feature Learning of 1D Convolutional Neural Networks with Contrastive Loss for Eating Detection Using an In-Ear Microphone

The importance of automated and objective monitoring of dietary behavior is becoming increasingly accepted. The advancements in sensor technology along with recent achievements in machine-learning--based signal-processing algorithms have enabled the development of dietary monitoring solutions that yield highly accurate results. A common bottleneck for developing and training machine learning algorithms is obtaining labeled data for training supervised algorithms, and in particular ground truth annotations. Manual ground truth annotation is laborious, cumbersome, can sometimes introduce errors, and is sometimes impossible in free-living data collection. As a result, there is a need to decrease the labeled data required for training. Additionally, unlabeled data, gathered in-the-wild from existing wearables (such as Bluetooth earbuds) can be used to train and fine-tune eating-detection models. In this work, we focus on training a feature extractor for audio signals captured by an in-ear microphone for the task of eating detection in a self-supervised way. We base our approach on the SimCLR method for image classification, proposed by Chen et al. from the domain of computer vision. Results are promising as our self-supervised method achieves similar results to supervised training alternatives, and its overall effectiveness is comparable to current state-of-the-art methods. Code is available at https://github.com/mug-auth/ssl-chewing .

Bite-Weight Estimation Using Commercial Ear Buds

While automatic tracking and measuring of our physical activity is a well established domain, not only in research but also in commercial products and every-day life-style, automatic measurement of eating behavior is significantly more limited. Despite the abundance of methods and algorithms that are available in bibliography, commercial solutions are mostly limited to digital logging applications for smart-phones. One factor that limits the adoption of such solutions is that they usually require specialized hardware or sensors. Based on this, we evaluate the potential for estimating the weight of consumed food (per bite) based only on the audio signal that is captured by commercial ear buds (Samsung Galaxy Buds). Specifically, we examine a combination of features (both audio and non-audio features) and trainable estimators (linear regression, support vector regression, and neural-network based estimators) and evaluate on an in-house dataset of 8 participants and 4 food types. Results indicate good potential for this approach: our best results yield mean absolute error of less than 1 g for 3 out of 4 food types when training food-specific models, and 2.1 g when training on all food types together, both of which improve over an existing literature approach.

Recognition of food-texture attributes using an in-ear microphone

Food texture is a complex property; various sensory attributes such as perceived crispiness and wetness have been identified as ways to quantify it. Objective and automatic recognition of these attributes has applications in multiple fields, including health sciences and food engineering. In this work we use an in-ear microphone, commonly used for chewing detection, and propose algorithms for recognizing three food-texture attributes, specifically crispiness, wetness (moisture), and chewiness. We use binary SVMs, one for each attribute, and propose two algorithms: one that recognizes each texture attribute at the chew level and one at the chewing-bout level. We evaluate the proposed algorithms using leave-one-subject-out cross-validation on a dataset with 9 subjects. We also evaluate them using leave-one-food-type-out cross-validation, in order to examine the generalization of our approach to new, unknown food types. Our approach performs very well in recognizing crispiness (0.95 weighted accuracy on new subjects and 0.93 on new food types) and demonstrates promising results for objective and automatic recognition of wetness and chewiness.

An Interpretable Multiple-Instance Approach for the Detection of referable Diabetic Retinopathy from Fundus Images

Diabetic Retinopathy (DR) is a leading cause of vision loss globally. Yet despite its prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for assessing their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to DR severity estimates for patients in remote regions or even for complementing the human expert's diagnosis. In this paper, we propose a machine learning system for the detection of referable DR in fundus images that is based on the paradigm of multiple-instance learning. By extracting local information from image patches and combining it efficiently through an attention mechanism, our system is able to achieve high classification accuracy. Moreover, it can highlight potential image regions where DR manifests through its characteristic lesions. We evaluate our approach on publicly available retinal image datasets, in which it exhibits near state-of-the-art performance, while also producing interpretable visualizations of its predictions.

A Data Driven End-to-end Approach for In-the-wild Monitoring of Eating Behavior Using Smartwatches

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 heldout experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.

Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning

Parkinson's Disease (PD) is a slowly evolving neuro-logical 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.