Charalampos Z. Patrikakis

Michael Xevgenis, Dimitrios Kogias, Ioannis Christidis et al.

A new era in ICT has begun with the evolution of Next Generation Networks (NGNs) and the development of human-centric applications. Ultra-low latency, high throughput, and high availability are a few of the main characteristics of modern networks. Network Providers (NPs) are responsible for the development and maintenance of network infrastructures ready to support the most demanding applications that should be available not only in urban areas but in every corner of the earth. The NPs must collaborate to offer high-quality services and keep their overall cost low. The collaboration among competitive entities can in principle be regulated by a trusted 3rd party or by a distributed approach/technology which can guarantee integrity, security, and trust. This paper examines the use of blockchain technology for resource management and negotiation among NPs and presents the results of experiments conducted in a dedicated real testbed. The implementation of the resource management mechanism is described in a Smart Contract (SC) and the testbeds use the Raft and the IBFT consensus mechanisms respectively. The goal of this paper is two-fold: to assess its performance in terms of transaction throughput and latency so that we can assess the granularity at which this solution can operate (e.g. support resource re-allocation among NPs on micro-service level or not) and define implementation-specific parameters like the consensus mechanism that is the most suitable for this use case based on performance metrics.

Panagiotis Kasnesis, Christos Chatzigeorgiou, Dimitrios G. Kogias et al.

Efficient and quick remote communication in search and rescue operations can be life-saving for the first responders. However, while operating on the field means of communication based on text, image and audio are not suitable for several disaster scenarios. In this paper, we present a smartwatch-based application, which utilizes a Deep Learning (DL) model, to recognize a set of predefined arm gestures, maps them into Morse code via vibrations enabling remote communication amongst first responders. The model performance was evaluated by training it using 4,200 gestures performed by 7 subjects (cross-validation) wearing a smartwatch on their dominant arm. Our DL model relies on convolutional pooling and surpasses the performance of existing DL approaches and common machine learning classifiers, obtaining gesture recognition accuracy above 95%. We conclude by discussing the results and providing future directions.

Panagiotis Kasnesis, Lazaros Toumanidis, Alessio Burrello et al.

Nowadays, Hearth Rate (HR) monitoring is a key feature of almost all wrist-worn devices exploiting photoplethysmography (PPG) sensors. However, arm movements affect the performance of PPG-based HR tracking. This issue is usually addressed by fusing the PPG signal with data produced by inertial measurement units. Thus, deep learning algorithms have been proposed, but they are considered too complex to deploy on wearable devices and lack the explainability of results. In this work, we present a new deep learning model, PULSE, which exploits temporal convolutions and multi-head cross-attention to improve sensor fusion's effectiveness and achieve a step towards explainability. We evaluate the performance of PULSE on three publicly available datasets, reducing the mean absolute error by 7.56% on the most extensive available dataset, PPG-DaLiA. Finally, we demonstrate the explainability of PULSE and the benefits of applying attention modules to PPG and motion data.

Panagiotis Kasnesis, Charalampos Z. Patrikakis, Iakovos S. Venieris

Human Activity Recognition (HAR) based on motion sensors has drawn a lot of attention over the last few years, since perceiving the human status enables context-aware applications to adapt their services on users' needs. However, motion sensor fusion and feature extraction have not reached their full potentials, remaining still an open issue. In this paper, we introduce PerceptionNet, a deep Convolutional Neural Network (CNN) that applies a late 2D convolution to multimodal time-series sensor data, in order to extract automatically efficient features for HAR. We evaluate our approach on two public available HAR datasets to demonstrate that the proposed model fuses effectively multimodal sensors and improves the performance of HAR. In particular, PerceptionNet surpasses the performance of state-of-the-art HAR methods based on: (i) features extracted from humans, (ii) deep CNNs exploiting early fusion approaches, and (iii) Long Short-Term Memory (LSTM), by an average accuracy of more than 3%.