AI Based Monitoring of Different Risk Levels in COVID-19 Context

COVID-19 was responsible for devastating social, economic, and political effects all over the world. Although the health authorities imposed restrictions provided relief and assisted with trying to return society to normal life, it is imperative to monitor people’s behavior and risk factors to keep virus transmission levels as low as possible. This article focuses on the application of deep learning algorithms to detect the presence of masks on people in public spaces (using RGB cameras), as well as the detection of the caruncle in the human eye area to make an accurate measurement of body temperature (using thermal cameras). For this task, synthetic data generation techniques were used to create hybrid datasets from public ones to train state-of-the-art algorithms, such as YOLOv5 object detector and a keypoint detector based on Resnet-50. For RGB mask detection, YOLOv5 achieved an average precision of 82.4%. For thermal masks, glasses, and caruncle detection, YOLOv5 and keypoint detector achieved an average precision of 96.65% and 78.7%, respectively. Moreover, RGB and thermal datasets were made publicly available.

Winning the NIST Contest: A scalable and general approach to differentially private synthetic data

We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.

Synthetic Data Generation with Differential Privacy via Bayesian Networks

This paper describes PrivBayes, a differentially private method for generating synthetic datasets that was used in the 2018 Differential Privacy Synthetic Data Challenge organized by NIST.

The African swine fever modelling challenge: objectives, model description and synthetic data generation

African swine fever (ASF) is an emerging disease currently spreading at the interface between wild boar and pig farms in Europe and Asia. Current disease control regulations, which involve massive culling with significant economic and animal welfare costs, need to be improved. Modelling enables relevant control measures to be explored, but conducting the exercise during an epidemic is extremely difficult. Modelling challenges enhance modellers' ability to provide timely advice to policy makers, improve their readiness when facing emerging threats, and promote international collaborations. The ASF-Challenge, which ran between August 2020 and January 2021, was the first modelling challenge in animal health. In this paper, we describe the objectives and rules of the challenge. We then demonstrate the mechanistic multi-host model that was used to mimic as accurately as possible an ASF-like epidemic, provide a detailed explanation of the surveillance and intervention strategies that generated the synthetic data, and describe the different management strategies that were assessed by the competing modelling teams. We then outline the different technical steps of the challenge as well as its environment. Finally, we synthesize the lessons we learnt along the way to guide future modelling challenges in animal health.

Synthetic Data Generation to Speed-Up the Object Recognition Pipeline

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of men at sea, lead us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features to be applied to various contexts.

Producing Synthetic Dataset for Human Fall Detection in AR/VR Environments

Human poses and the behaviour estimation for different activities in (virtual reality/augmented reality) VR/AR could have numerous beneficial applications. Human fall monitoring is especially important for elderly people and for non-typical activities with VR/AR applications. There are a lot of different approaches to improving the fidelity of fall monitoring systems through the use of novel sensors and deep learning architectures; however, there is still a lack of detail and diverse datasets for training deep learning fall detectors using monocular images. The issues with synthetic data generation based on digital human simulation were implemented and examined using the Unreal Engine. The proposed pipeline provides automatic “playback” of various scenarios for digital human behaviour simulation, and the result of a proposed modular pipeline for synthetic data generation of digital human interaction with the 3D environments is demonstrated in this paper. We used the generated synthetic data to train the Mask R-CNN-based segmentation of the falling person interaction area. It is shown that, by training the model with simulation data, it is possible to recognize a falling person with an accuracy of 97.6% and classify the type of person’s interaction impact. The proposed approach also allows for covering a variety of scenarios that can have a positive effect at a deep learning training stage in other human action estimation tasks in an VR/AR environment.