1. “Knowledge Graph Construction for Social Customer Advocacy in Online Customer Engagement”
by Bilal Abu-Salih and Salihah Alotaibi
Technologies 2023, 11(5), 123; https://doi.org/10.3390/technologies11050123
Available online: https://www.mdpi.com/2227-7080/11/5/123
Summary: The paper proposes a framework leveraging the XLNet-BiLSTM-CRF architecture to build a knowledge graph for social customer advocacy. This study aims to identify online brand advocates and enhance customer engagement using advanced natural language processing techniques. The significance of the work lies in its ability to provide businesses with deeper insights into customer behaviors, fostering more effective customer–brand interactions and strengthening brand loyalty.

2. “Multi-Scale CNN: An Explainable AI-Integrated Unique Deep Learning Framework for Lung-Affected Disease Classification”
by Ovi Sarkar, Md. Robiul Islam, Md. Khalid Syfullah, Md. Tohidul Islam, Md. Faysal Ahamed, Mominul Ahsan and Julfikar Haider
Technologies 2023, 11(5), 134; https://doi.org/10.3390/technologies11050134
Available online: https://www.mdpi.com/2227-7080/11/5/134
Summary: This paper presents a novel deep learning architecture that incorporates multi-scale convolutional neural networks and explainable AI techniques. This approach enhances both the accuracy and transparency of classifying lung diseases from medical images. The research is pivotal in advancing AI-driven healthcare by providing models that not only perform well but also offer interpretability for better clinical decision-making.

3. “Electrospinning for the Modification of 3D Objects for the Potential Use in Tissue Engineering”
by Laura Bauer, Lisa Brandstäter, Mika Letmate, Manasi Palachandran, Fynn Ole Wadehn, Carlotta Wolfschmidt, Timo Grothe, Uwe Güth and Andrea Ehrmann
Technologies 2022, 10(3), 66; https://doi.org/10.3390/technologies10030066
Available online: https://www.mdpi.com/2227-7080/10/3/66
Summary: Electrospinning can be used to modify the surface of 3D objects. Here, we show the effect of conductive and isolating 3D-printed parts on nanofiber positioning and orientation.

4. “User-Centric Design Methodology for mHealth Apps: The PainApp Paradigm for Chronic Pain”
by Yiannis Koumpouros
Technologies 2022, 10(1), 25; https://doi.org/10.3390/technologies10010025
Available online: https://www.mdpi.com/2227-7080/10/1/25
Summary: Unlocking the future of chronic pain management, our latest research unveils a user-centric design methodology for mHealth apps tailored to empower patients and enhance their treatment experience. Dive in and discover how the PainApp Paradigm is changing the landscape of healthcare. Transforming the patient experience in chronic pain management starts here! This paper introduces a revolutionary approach to mHealth app design focusing on user needs and preferences. Join us in exploring the PainApp Paradigm and its potential to reshape how we support pain management. In the battle against chronic pain, patient-centered solutions are key. Our paper presents an innovative user-centric design methodology for mHealth apps, ensuring that technology truly meets the needs of those it serves. Discover the PainApp Paradigm and be part of the change.

5. “Jordan Canonical Form for Solving the Fault Diagnosis and Estimation Problems”
by Oleg Sergiyenko, Alexey Zhirabok, Paolo Mercorelli, Alexander Zuev, Vladimir Filaretov and Vera Tyrsa
Technologies 2023, 11(3), 72; https://doi.org/10.3390/technologies11030072
Available online: https://www.mdpi.com/2227-7080/11/3/72
Summary: The main contribution of this paper lies in the development of methods that apply the Jordan Canonical Form to solve the problems related to diagnostic and sliding mode observers, virtual sensors, and interval observers for linear and nonlinear systems. Unlike the known methods, the suggested approach is based on the reduced-order model derived from the original system, which is insensitive or has minimal sensitivity to the disturbance. This allows for obtaining the observers and sensors of less dimensions, reducing the impact of disturbances on the accuracy of diagnosis and estimation results.

6. “Hyperparameter Optimization and Combined Data Sampling Techniques in Machine Learning for Customer Churn Prediction: A Comparative Analysis”
by Mehdi Imani and Hamid Reza Arabnia
Technologies 2023, 11(6), 167; https://doi.org/10.3390/technologies11060167
Available online: https://www.mdpi.com/2227-7080/11/6/167
Summary: This study applies various machine learning models, including Artificial Neural Networks, Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, XGBoost, LightGBM, and CatBoost (optimized with Optuna), to predict customer churn in telecommunications. To address imbalanced data, three sampling strategies—SMOTE, SMOTE combined with Tomek Links, and SMOTE combined with Edited Nearest Neighbors (ENN)—were applied.