Federated Learning (FL) enables collaborative training of Machine Learning (ML) models across decentralized clients while preserving data privacy. One of the challenges that FL faces is when the clients’ data is not independent and identically distributed (non-IID). It is, therefore, crucial to quantify how non-IID data impacts performance. However, due to the limited number of federated data available, it is not easy to carry out real-world simulations. In this work, we propose for the first time (1) the Hist-Dirichlet-based and Min-Size-Dirichlet methods for partitioning data into multiple nodes using the features and quantity distribution and the Dirichlet distribution. We use the (2) Jensen-Shannon and Hellinger distances for quantifying the degree of IID data. Moreover, we implemented (3) state-of-the-art partitioning methods based on the labels’ distribution across clients. All our proposals are open-source in a library called FedArtML, publicly available on PyPI. It facilitates research on cross-silo and cross-device FL, allowing a systematic and controlled partition of centralized datasets using the label, features, and quantity skewness. To demonstrate the value of our proposed methods and the robustness of FedArtML, we experimented in the ECG arrhythmia detection field with Physionet 2020 data. Our results demonstrate that our tool generates federated datasets for multi-client model training and accurately measures client distribution heterogeneity. Our approach achieves 48% higher non-IID-ness than existing feature skew methods, providing more granularity. Furthermore, we validate our simulated federated datasets against real-world data, revealing only a 2% F1-Score difference, affirming the method’s real-life applicability.

Designing advanced health monitoring systems is still an active research topic. Wearable and remote monitoring devices enable monitoring of physiological and clinical parameters (heart rate, respiration rate, temperature, etc.) and analysis using cloud-centric machine-learning applications and decision-support systems to predict critical clinical states. This paper moves from a totally cloud-centric concept to a more distributed one, by transferring sensor data processing and analysis tasks to the edges of the network. The resulting solution enables the analysis and interpretation of sensor-data traces within the wearable device to provide actionable alerts without any dependence on cloud services. In this paper, we use a supervised-learning approach to detect heartbeats and classify arrhythmias. The system uses a window-based feature definition that is suitable for execution within an asymmetric multicore embedded processor that provides a dedicated core for hardware assisted pattern matching. We evaluate the performance of the system in comparison with various existing approaches, in terms of achieved accuracy in the detection of abnormal events. The results show that the proposed embedded system achieves a high detection rate that in some cases matches the accuracy of the state-of-the-art algorithms executed in standard processors.

In the last two decades, we have witnessed an immense increase in the use of multimedia content on the internet, for multiple applications ranging from the most innocuous to very critical ones. Naturally, this emergence has given rise to many types of threats posed when this content can be manipulated/used for malicious purposes. For example, fake media can be used to drive personal opinions, ruining the image of a public figure, or for criminal activities such as terrorist propaganda and cyberbullying. The research community has of course moved to counter attack these threats by designing manipulation-detection systems based on a variety of techniques, such as signal processing, statistics, and machine learning. This research and practice activity has given rise to the field of multimedia forensics. The success of deep learning in the last decade has led to its use in multimedia forensics as well. In this survey, we look at the latest trends and deep-learning-based techniques introduced to solve three main questions investigated in the field of multimedia forensics. We begin by examining the manipulations of images and videos produced with editing tools, reporting the deep-learning approaches adopted to counter these attacks. Next, we move on to the issue of the source camera model and device identification, as well as the more recent problem of monitoring image and video sharing on social media. Finally, we look at the most recent challenge that has emerged in recent years: recognizing deepfakes, which we use to describe any content generated using artificial-intelligence techniques; we present the methods that have been introduced to show the existence of traces left in deepfake content and to detect them. For each problem, we also report the most popular metrics and datasets used today.