United States

In a pandemic crisis such as the one that the world has been experiencing since January 2020, utilizing remote mobile health monitoring can help monitor the cardiac health of healthy individuals as well as chronically ill patients. Apple Watch is a fitness tracker that measures heart rate and can facilitate this need due to its availability worldwide and relative affordability. Hence, it has the potential of being useful in assessing and monitoring one’s cardiac health. This paper reports the preliminary results from an ongoing study aimed at assessing the accuracy of the Apple Watch in measuring heart rate variability. To achieve the goal of the study, concurrent measurements of electrocardiogram (ECG), as a gold standard, and instantaneous Apple Watch heartrate values were made in six (4 male) age 26.4±3.2 years old volunteer healthy subjects. Both time and frequency domain measures of heartrate variability (HRV) were obtained from the recorded ECG and estimated from the Apple Watch instantaneous heartrate values. The results indicate that it may be possible to obtain a reasonable estimate of HRV time-domain and frequency-domain metrics using Apple Watch in healthy subjects.

PETRA 2021

Estimation of Heart Rate Variability Measures Using Apple Watch and Evaluating Their Accuracy

fitness tracking ecosystem

exercise therapy

wearable fitness tracking

wearable health monitor

**About**
 The PErvasive Technologies Related to Assistive Environments (PETRA) conference is a highly interdisciplinary conference that focuses on computational and engineering approaches to improve the quality of life and enhance human performance in a wide range of settings, in the workplace, at home, in public spaces, urban environments, and other. Outcomes of this conference have a broad impact in application areas that include, manufacturing, transportation, healthcare, energy systems, security and safety, robotics, biomedicine, environment and conservation, and many others. PETRA brings together very different types of technologies to also address important social and healthcare issues for sensitive populations, such as the elderly, persons suffering from chronic conditions such as Alzheimer’s, Parkinson’s, Cerebral Palsy, and other disabilities or traumas.

 PETRA (which means “stone” in Greek) addresses important human living needs. From a technological perspective, PETRA motivates and inspires new scientific thrusts, innovations and discoveries to improve living environments, a particularly important issue, in an increasingly crowded and complex world where the need for inclusiveness and connectivity with the rest of the world is key. For the elderly in particular, PETRA addresses the fact that, as people grow older; they will increasingly rely on technology to be able to prolong staying in their homes and enjoy an independent life.

 The PETRA 2021 proceedings will be published in the ACM Digital Library as part of the ACM ICPS program. The ISBN number assigned to PETRA '21 is 978-1-4503-8792-7

The PErvasive Technologies Related to Assistive Environments (PETRA) conference is a highly interdisciplinary conference that focuses on computational and engineering approaches to improve the quality of life and enhance human performance in a wide range of settings, in the workplace, at home, in public spaces, urban environments, and other. Outcomes of this conference have a broad impact in application areas that include, manufacturing, transportation, healthcare, energy systems, security and safety, robotics, biomedicine, environment and conservation, and many others. PETRA brings together very different types of technologies to also address important social and healthcare issues for sensitive populations, such as the elderly, persons suffering from chronic conditions such as Alzheimer’s, Parkinson’s, Cerebral Palsy, and other disabilities or traumas.

workshop paper

Automatic building extraction from satellite RGB images, is a low-cost alternative to perform important urban planning tasks. Yet, itis a challenging one, especially when natural and non-city block objects interfere in the semantic segmentation of algorithms that extract their key features. In this work we approach the automatic building extraction using a Convolution Neural Network based on the U-Net architecture. In contrast to existing approaches, it successfully encodes important features and decodes the buildings’ localization by requiring both reduced computational time and dataset size. We evaluate the U-Net’s performance using RGB images selected from the SpaceNet 1 dataset and the experimental results show an accuracy in building localization of 92.3%. Finally,favorable comparison with existing CNN approaches to hyper-spectral images targeting the SpaceNet 1 dataset, demonstrated its effectiveness.

Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach

The presentation provides a novel method for reducing a multi-class Confusion Matrix into a 2 × 2 version enabling the use of the relevant performance metrics and methods like the Receiver Operating Characteristic and the Area Under the Curve for the assessment of different classification algorithms. The reduction method is based on class grouping and leads to a specific Confusion Matrix format. The developed method is then exploited for the assessment of several state-of-the-art machine learning algorithms applied on a customer experience metric called Net Promoter Score (NPS).

Multi-Class Confusion Matrix Reduction method and its application on Net Promoter Score classification problem

Man overboard incidents in a maritime vessel are serious accidents where, the efficient and rapid detection is crucial in the recovery of the victim. The severity of such accidents, urge the use of intelligent systems that are able to automatically detect a fall and provide relevant alerts. To this end the use of novel deep learning and computer vision algorithms have been tested and proved efficient in problems with similar structure. This paper presents the use of a deep learning framework for automatic detection of man overboard incidents. We investigate the use of simple RGB video streams for extracting specific properties of the scene, such as movement and saliency, and use convolutional spatiotemporal autoencoders to model the normal conditions and identify anomalies. Moreover, in this work we present a dataset that was created to train and test the efficacy of our approach.

Man Overboard: Fall detection using spatiotemporal convolutional autoencoders in maritime environments

Bioinformatics systems for monitoring and mitigating epidemics: The STAMINA Paradigm

Emotion recognition is a field of psychology that involves the process of identifying emotions and treating mental conditions like autism. The advancements in the field of machine learning and deep learning have paved the way for scientists to develop models for evaluating emotions by analyzing facial expressions, speech and text. However, the task of evaluating emotions could be best done by processing the bio-signals and neural imaging of the brain. In that sense, bio-signals such as Electroencephalogram (EEG) are less expensive to use and non-invasive, giving them an edge over traditional methods like Magnetic Resonant Imaging (MRI). However,
not many datasets are publicly available due to privacy issues and their availability is highly limited by the classification task. These constraints, along with the problem of data scarcity, motivates this work as an attempt to enhance the accuracy scores by generating synthetic features that are close to actual data distribution. In this research, we propose a Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) based model that can help tackle this problem. The dataset that is investigated is DEAP, one of the benchmark datasets for evaluating emotion recognition algorithms. In the method proposed, nine descriptive features are extracted from the original data and baseline models are evaluated. 
Subsequently, a WGAN-GP is trained on these extracted features and is used to generate a new set of synthetic data features. The synthetic features are then analysed for quality and appended to the original data to expand this dataset. Experiments with different augmentation factors (x2, x3, x4) are investigated to evaluate the impact of the data augmentation procedure. The experimental results
demonstrate that the proposed method gives a considerable enhancement of the classification task’s performance.

GAN-Based Data Augmentation For Improving The Classification Of EEG Signals

A novel deep learning methodology for the assessment of ergonomic risks in any given work-related task with high accuracy and in real-time is presented. The proposed method takes as input a video sequence, extracts 3D skeletal features using VIBE algorithm and then processes these features to predict REBA risk scores for the entire body and individual body parts. Results on two well-known datasets and against other state-of-the-art methods verify the ability of the proposed method in predicting REBA ergonomic risk scores with high accuracy.

Towards Real-time Generalized Ergonomic Risk Assessment for the Prevention of Musculoskeletal Disorders

Physiological data are nowadays frequently used to recognize the
affective state of subjects while performing different tasks. Automatic
recognition of a stressful state as a consequence of a high level
of cognitive load is significant to prevent illnesses like depression,
anxiety and sleep disorders that are often due to excessive workload.
The spread of wearable sensors that are increasingly reliable and
comfortable makes them easy to use in day-life activities. However,
due to the nature of experiments that involve subjects, the cardinality
of the acquired data is often low, making difficult to train
deep learning methods from the scratch. In this paper we consider
the photopletismography (PPG) that measures the blood volume
registered just under the skin, which can be used to obtain the heart
rate of the subject. It is well known that PPG data are particularly
relevant to detect high level of arousal that is activated by stress.
We show that, converting monodimensional photopletismography
(PPG) data into bidimensional signals it is possible to apply a pretrained
CNN, obtaining deep features that outperform handcrafted
ones in classification tasks, especially introducing feature selections
strategies to avoid curse of dimensionality.

A Deep Learning Approach to Recognize Cognitive Load using PPG Signalshttps://dl.acm.org/doi/10.1145/3453892.3461625

As access to new technologies becomes increasingly less expensive and complex, technologies such as virtual reality (VR) are also becoming interesting and relevant for applications outside consumer entertainment. Especially with VR for blind and visually impaired people, VR can overcome the limitations of real-world environments (e.g., hazardous locations and reliance on sighted companionship for training) by virtually exploring its digital model using consumer hardware. In this context, we conducted two within-subject user study with 11 and 5 participants that were asked to learn and re-walk an audio-landmark enriched path in a virtual environment. Our results showed, that the ability to learn and re-walk an audio landmark-enriched environment using an auditive only locomotion interface is possible, but yet difficult. To be able to re-walk even a simple corridor entails a relatively big training effort, but distinctive structures are recognizable again. The results also indicated that the intuitive use of controller based locomotion brings advantages over a keyboard and mouse based approach. Furthermore, we discovered different characteristics of auditive navigation (e.g., walking zigzag, in circles or collision-oriented with regard to the rooms' walls), encountered acoustic rendering problems in acute corners and were able to show a training effect when having trained a path within a virtual environment with respect to re-walking, both inside a virtual environment and outside to a physically re-walked path. This work underlines the feasibility, problems, but also chances of different locomotion implementations in VR and is intended to foster future work towards both technical and methodological optimization in this area.

Preliminary Analysis on Interaction Characteristics with Auditive Navigation in Virtual Environments

Virtual and Augmented Reality technologies are nowadays increasingly adopted as core elements of modern applications for creating unique user experiences. 
Following the capabilities of hardware and its constantly reducing cost, their use is moving from scientific and research projects to everyday life applications such as social media, architectural design and of course games.
In this work, we present a state-of-the-art exergame implementation paradigm, which can facilitate the development of exergames exploiting advanced user interactivity, augmented reality and modern gamification techniques.
The platform has been used for the development of a set of prototype games for Android phones based on the popular AR Core framework. 
The overall approach has been evaluated in real-world scenarios with exceptional usability and performance results.

On the development of augmented reality based exergames for assessing human activity and cognition on mobile devices

Increasing digitization in healthcare promises easier exchange and more efficient use of medical information for patients, institutions and research. 
The number of sharing options for medical data increases, e.g., through personal health records, as well as the volume of data.
To use this data in medical research patients' consent is important.
As more and more data access is regulated by consent forms and their complexity also increases.
For the patient, it becomes less comprehensible which information could be gained from his or her disclosed data. 
This becomes more important when presumably anonymized data has the risk of potential re-identification of an individual.
In this paper we introduce a consent-privacy-impact-quantification (CPIQ) as a risk model of consent forms for the release of personal medical data for use within research projects.
CPIQ evaluates how reasonable a consent decision is for the patient. 
It takes relevant factors such as the patient’s preferences into account, the circumstances and benefits of the research project, and the potential risk to the patient.
The model can be parameterized so that different aspects such as the benefit of the research project, the risk of a data leak or the risk of a patient’s confidential data becoming known can be represented.
We present the feasibility of this model by including it in an existing consent management system.

Downloads

Next from PETRA 2021

Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach

Similar lecture

Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from PETRA 2021

Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach

Similar lecture

Automated ROP Diagnostic System based on Comparisons and U-Net Segmentation

Downloads