AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system’s effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.

Millions of people suffering from partial or complete hearing loss use variants of sign language to communicate with each other or hearing people in their everyday life. Thus, it is imperative to develop systems to assist these people by removing the barriers that affect their social inclusion. These systems should aim towards capturing sign language in an accurate way, classifying sign language to natural words and representing sign language by having avatars or synthesized videos execute the exact same moves that convey a meaning in the sign language. This chapter reviews current state-of-the-art approaches that attempt to solve sign language recognition and representation and analyzes the challenges they face. Furthermore, this chapter presents a novel AI-based solution to the problem of robust sign language capturing and representation, as well as a solution to the unavailability of annotated sign language datasets before limitations and directions for future work are discussed. Request access from your librarian to read this chapter's full text.

Personalised nutrition could promote greater adherence to a healthy lifestyle, and thereby potentially improve health outcomes. The principal aim of the PROTEIN project was to develop a mobile application that delivers tailored nutrition advice to adults. In this pilot study, 80 participants were recruited from the general public and sorted into three groups: (i) adults with a poor-quality diet (PQD, n 29), (ii) adults with iron deficiency anaemia (IDA, n 11; Hb < 120 mg/L) and (iii) adults who were overweight (OW, n 40; BMI 25–30 kg/m²). The participants provided baseline anthropometric and general health data, which were inputted into the PROTEIN dashboard, along with their dietary preferences and individual goals, triggering the generation of an individualised 7-day nutrition and activity plan (NAP), which the participants were encouraged to follow. Their interactions with the app were determined through the number of occasions the user would either ‘confirm’ that they had consumed or ‘skipped’ a recommended meal. They were also expected to rate the meals and input their own instead of, or as well as, those recommended. Following 4 weeks of use, the participants were asked to complete online questionnaires on the usability of the app and report their current weight. The data are presented as mean (±SD); the significance was set at p < 0.05. The mean age and BMI were 44.7 ± 16.1 years and 27.7 ± 5.5 kg/m², respectively, for the whole sample. Over 90% of the users did not confirm that they had consumed or skipped a meal, thereby suggesting a lack of user acceptability of the meal plans provided. However, the OW group users who completed the intervention (n 32) reported an average of −1.1 ± 1.4 kg weight loss. The responses to questionnaires from all users suggested that the app increased their ‘motivation to’ and ‘ability to eat a healthy diet’ (n 35 and 41, respectively). Overall, the PROTEIN app could motivate users to improve their lifestyle, in line with previous pilots. Furthermore, the system could accurately define appropriate meal plans and aid its users achieve their personal ‘goals’. Future versions of the mobile app should focus on developing a more user-friendly system to increase interaction.