Announcements

1. “Lightweight Neural Network for COVID-19 Detection from Chest X-ray Images Implemented on an Embedded System”
by Theodora Sanida, Argyrios Sideris, Dimitris Tsiktsiris and Minas Dasygenis
Technologies 2022, 10(2), 37; https://doi.org/10.3390/technologies10020037
Available online: https://www.mdpi.com/2227-7080/10/2/37

Highlights:

1. Based on U-Net, the research team designed a lightweight neural network and used chest X-ray imaging to develop a fast and accurate COVID-19 diagnostic method;
2. The research team comprehensively tested the network’s accuracy and reliability in detecting COVID-19 cases;
3. The embedded system ensures deployment in places with limited medical infrastructure, accelerating diagnostic processes in the context of the COVID-19 pandemic.

2. “User-Centric Design Methodology for mHealth Apps: The PainApp Paradigm for Chronic Pain”
by Yiannis Koumpouros
Technologies 2022, 10, 25; https://doi.org/10.3390/technologies10010025
Available online: https://doi.org/10.3390/technologies10010025

Highlights:

1. The study focuses on user-centric design for mHealth apps, specifically targeting chronic or acute pain management;
2. The paper highlights the initial impressions and aesthetics, participatory design, subjective evaluation and reliable assessment scales;
3. Data protection concerns and compliance with regulations such as GDPR are addressed;
4. The research team describes future development plans such as PainApp’s AI integration and iOS deployment.

3. “A Review of Efficient Real-Time Decision Making in the Internet of Things”
by Kyoung-Don Kang
Technologies 2022, 10, 12; https://doi.org/10.3390/technologies10010012
Available online: https://doi.org/10.3390/technologies10010012

Highlights:

1. The ability to make cost-efficient real-time decisions is crucial, such as smart transportation, healthcare and energy management;
2. IoT technology plays a key role in real-time decision-making in retrieving and analyzing sensor data;
3. The authors defined real-time decision tasks in the IoT and reviewed state-of-the-art methodologies for scheduling and real-time sensor data analysis;
4. The authors sketched out potential avenues for future research.

4. “On the Exploration of Automatic Building Extraction from RGB Satellite Images Using Deep Learning Architectures Based on U-Net”
by Anastasios Temenos, Nikos Temenos, Anastasios Doulamis and Nikolaos Doulamis
Technologies 2022, 10, 19; https://doi.org/10.3390/technologies10010019
Available online: https://www.mdpi.com/2227-7080/10/1/19

Highlights:

1. The authors developed U-Net-based deep learning architecture for semantic segmentation, which aims at distinguishing building and non-building areas;
2. The use of the SpaceNet 1 dataset for evaluation, emphasizing RGB images' low cost and accessibility;
3. ResU-Net shows the highest precision (0.864) due to the residual block's ability to introduce additional information;
4. Attention U-Net uses attention gates for effective feature extraction and performs well in terms of accuracy, recall, F1, Jaccard scores and precision;
5. Attention U-Net has remarkably low false positive (FP) values due to skip connections, enhancing spatial information during decoding.

5. “The NESTORE e-Coach: Designing a Multi-Domain Pathway to Well-Being in Older Age”
by Leonardo Angelini, Mira El Kamali, Elena Mugellini, Omar Abou Khaled, Christina Röcke, Simone Porcelli, Alfonso Mastropietro, Giovanna Rizzo, Noemi Boqué, Josep Maria del Bas et al.
Technologies 2022, 10(2), 50; https://doi.org/10.3390/technologies10020050
Available online: https://doi.org/10.3390/technologies10020050

Highlights:

1. This paper delves deep into the co-design process of a multidomain pathway aimed at enhancing overall well-being in older adults, encompassing physical activity, nutrition, cognitive development and social engagement;
2. The authors examine the complexities of catering to diverse user needs, incorporating expert recommendations in each domain and managing implementation and evaluation intricacies;
3. The NESTORE virtual coaching ecosystem includes a mobile app, conversational agents, tangible devices, wearable technology and IoT devices;
4. The research team used a user-friendly interface design to create a seamless, immersive well-being experience for seniors.

6. “Detection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors”
by Konstantinos Papoutsakis, George Papadopoulos, Michail Maniadakis, Thodoris Papadopoulos, Manolis Lourakis, Maria Pateraki and Iraklis Varlamis
Technologies 2022, 10(2), 42; https://doi.org/10.3390/technologies10020042
Available online: https://doi.org/10.3390/technologies10020042

Highlights:

1. The research team used low-cost sensors to acquire visual data to assess workers’ sub-optimal postures during work;
2. The research team fused visual and heart rate data to improve the short-term forecasting of workers’ cardiovascular activity;
3. A multi-modal dataset of synchronous vision and heart-rate data acquired from real workers in a manufacturing workplace, used to train worker fatigue prediction models;
4. The efficiency of the model exceeds 70% of the classification rate measured based on F1 scores.