Abstract
The adoption of sustainable dietary patterns that consider simultaneously nutritional well-being and reduced environmental impact is of paramount importance. This paper introduces the Dietary Pattern Sustainability Index (DIPASI), as a method to assess the sustainability of dietary patterns by covering the environmental, nutritional, and economic dimensions in a single score. Environmental indicators include carbon footprint, water footprint, and land use, the nutritional quality is evaluated through the Nutritional Rich Diet 9.3 score, and the economic aspects are considered using diet cost. DIPASI measures the deviation (in %) of an individual's diet in relation to a reference diet. The case study utilized dietary data from the Portuguese National Food, Nutrition, and Physical Activity Survey (IAN-AF 2015-2016), which included 2999 adults aged 18 to 64. The Portuguese dietary patterns (covering 1492 food products consumed), were compared against the reference Mediterranean diet. Results indicated that the Portuguese dietary pattern had a higher environmental impact (CF: 4.32 kg CO2eq/day, WF: 3162.88 L/day, LU: 7.03 m(2)/day), a lower nutritional quality (NRD9.3: 334), and a higher cost (6.65 euros/day) when compared to the Mediterranean diet (CF: 3.30 kg CO2eq/day, WF: 2758.84 L/day, LU: 3.67 m(2)/day, NRD9.3: 668, cost: 5.71 euros/day). DIPASI reveals that only 4% of the sample's population does not deviate or presents a positive deviation (> - 0.5%) from the Mediterranean diet, indicating that the majority of Portuguese individuals have lower sustainability performance. For the environmental sub-score, this percentage was 21.3%, for the nutritional sub-score was 10.9%, and for the economic sub-score was 34.2%. This study provides a robust framework for assessing dietary sustainability on a global scale. The comprehensive methodology offers an essential foundation for understanding and addressing challenges in promoting sustainable and healthy dietary choices worldwide.

Abstract
This scoping review systematizes the current research related to the use of both blockchain and machine learning techniques in medical imaging applications. A systematic electronic search was performed, and twenty-five studies were included in the review. These studies aimed to use blockchain and machine learning techniques to provide (i) efficient security mechanisms to support the communication of medical imaging data, (ii) aggregation of distributed medical imaging data to train machine learning algorithms, and (iii) machine learning algorithms based on federated learning strategies. Among the ten machine learning techniques identified in the included studies, Convolutional Neural Network was the most representative (i.e., 44% of the studies). Moreover, Artificial Neural Network, Capsule Network, Deep Neural Network, Gated Recurrent Units, and Neural Network were machine learning techniques used by more than one study. Although the included studies developed algorithms with potential impact in clinical practice, it must be noted that they did not discuss the generalizability of their algorithms in real-world clinical conditions.

Abstract
With the increasing popularity of social media platforms like Instagram, there is a growing need for effective methods to detect and analyze abnormal actions in user-generated content. Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning that can learn complex patterns. This article proposes a novel deep learning approach for detecting abnormal actions in social media clips, focusing on behavioural change analysis. The approach uses a combination of Deep Learning and textural, statistical, and edge features for semantic action detection in video clips. The local gradient of video frames, time difference, and Sobel and Canny edge detectors are among the operators used in the proposed method. The method was evaluated on a large dataset of Instagram and Telegram clips and demonstrated its effectiveness in detecting abnormal actions with about 86% of accuracy. The results demonstrate the applicability of deep learning-based systems in detecting abnormal actions in social media clips.

Abstract
Objectives: The purpose of this study was to field-test a recently developed AR-based serious game designed to promote SSE self-efficacy, called Spot. Methods: Thirty participants played the game and answered 3 questionnaires: a baseline questionnaire, a second questionnaire immediately after playing the game, and a third questionnaire 1 week later (follow-up). Results: The majority of participants considered that the objective quality of the game was high, and considered that the game could have a real impact in SSE promotion. Participants showed statistically significant increases in SSE self-efficacy and intention at follow-up. Of the 24 participants that had never performed a SSE or had done one more than 3 months ago, 12 (50.0%) reported doing a SSE at follow-up. Conclusions: This study provides supporting evidence to the use of serious games in combination with AR to educate and motivate users to perform SSE. Spot seems to be an inconspicuous but effective strategy to promote SSE, a cancer prevention behavior, among healthy individuals. Practice implications: Patient education is essential to tackle skin cancer, particularly melanoma. Serious games, such as Spot, have the ability to effectively educate and motivate patients to perform a cancer prevention behavior.

Abstract
We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.

Abstract
Ensuring robust semantic interoperability is essential for efficient data exchange in the energy sector. This paper introduces SEMAPTIC, a lightweight framework that simplifies semantic interoperability by providing a standardized approach for attaching metadata to exchanged data. SEMAPTIC utilizes ontologies to define the meaning of data elements and employs a new structured metadata map to guide data interpretation. This approach simplifies data exchange, minimizes maintenance effort, and fosters unambiguous data understanding across heterogeneous systems. Compared to traditional methods that often require complex data transformations, SEMAPTIC offers greater flexibility and reduced overhead. The paper explores the benefits of SEMAPTIC, including simplified integration, minimal maintenance, enhanced interoperability, reduced misinterpretation, facilitated data reuse, and future-proofing. A practical example showcases how SEMAPTIC enriches a JSON data structure with semantic context without the need of modifying the original structure and without inflating data size. Finally, the importance of well-defined ontologies is emphasized, highlighting how SEMAPTIC empowers the energy sector to achieve seamless and reliable data exchange, paving the way for a more efficient and intelligent energy ecosystem. © The Institution of Engineering & Technology 2024.