Search

Abstract In recent years, major advances in artificial intelligence (AI) have led to the development of powerful AI systems for use in the field of nutrition in order to enhance personalized dietary recommendations and improve overall health and well-being. However, the lack of guidelines from nutritional experts has raised questions on the accuracy and trustworthiness of the nutritional advice provided by such AI systems. This paper aims to address this issue by introducing a novel AI-based nutrition recommendation method that leverages the speed and explainability of a deep generative network and the use of novel sophisticated loss functions to align the network with established nutritional guidelines. The use of a variational autoencoder to robustly model the anthropometric measurements and medical condition of users in a descriptive latent space, as well as the use of an optimizer to adjust meal quantities based on users’ energy requirements enable the proposed method to generate highly accurate, nutritious and personalized weekly meal plans. Coupled with the ability of ChatGPT to provide an unparalleled pool of meals from various cuisines, the proposed method can achieve increased meal variety, accuracy and generalization capabilities. Extensive experiments on 3000 virtual user profiles and 84000 daily meal plans, as well as 1000 real profiles and 7000 daily meal plans, demonstrate the exceptional accuracy of the proposed diet recommendation method in generating weekly meal plans that are appropriate for the users in terms of energy intake and nutritional requirements, as well as the easiness with which it can be integrated into future diet recommendation systems.

In a multi-view 3D reconstruction problem, the task is to infer the 3D shape of an object from various images taken from different viewpoints. Transformer-based networks have demonstrated their ability to achieve high performance in such problems, but they face challenges in identifying the optimal way to merge the different views in order to estimate with great fidelity the 3D shape of the object. This work aims to address this issue by proposing a novel approach to compute information-rich inter-view features by combining image tokens with similar distinctive characteristics among the different views dynamically. This is achieved by leveraging the self-attention mechanism of a Transformer, enhanced with a multi-manifold attention module, to estimate the importance of image tokens on-the-fly and re-arrange them among the different views in a way that improves the viewpoint merging procedure and the 3D reconstruction results. Experiments on ShapeNet and Pix3D validate the ability of the proposed method to achieve state-of-the-art performance in both multi-view and single-view 3D object reconstruction.

Mobile applications have been shown to be an effective and feasible intervention medium for improving healthy food intake in different target groups. As part of the PeRsOnalized nutriTion for hEalthy livINg (PROTEIN) European Union H2020 project, the PROTEIN mobile application was developed as an end-user environment, aiming to facilitate healthier lifestyles through artificial intelligence (AI)-based personalised dietary and physical activity recommendations. Recommendations were generated by an AI advisor for different user groups, combining users’ personal information and preferences with a custom knowledge-based system developed by experts to create personalised, evidence-based nutrition and activity plans. The PROTEIN app was piloted across different user groups in five European countries (Belgium, Germany, Greece, Portugal, and the United Kingdom). Data from the PROTEIN app’s user database (n = 579) and the PROTEIN end-user questionnaire (n = 446) were analysed using the chi-square test of independence to identify associations between personal goals, meal recommendations, and meal adherence among different gender, age, and user groups. The results indicate that weight loss-related goals are more prevalent, as well as more engaging, across all users. Health- and physical activity-related goals are key for increased meal adherence, with further differentiation evident between age and user groups. Congruency between user groups and their respective goals is also important for increased meal adherence. Our study outcomes, and the overall research framework created by the PROTEIN project, can be used to inform the future development of nutrition mobile applications and enable researchers and application designers/developers to better address personalisation for specific user groups, with a focus on user intent, as well as in-app features.

Modern lifestyle trends, such as sedentary behaviour and unhealthy diets, have been associated with obesity, a major health challenge increasing the risk of multiple pathologies. This has prompted many to reassess their routines and seek expert guidance on healthy living. In the digital era, users quickly turn to mobile apps for support. These apps monitor various aspects of daily life, such as physical activity and calorie intake; collect extensive user data; and apply modern data-driven technologies, including artificial intelligence (AI) and machine learning (ML), to provide personalised diet and lifestyle recommendations. This work examines the state of the art in data-driven technologies for personalised nutrition, including relevant data collection technologies, and explores the research challenges in this field. A literature review, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline, was conducted using three databases, covering studies from 2021 to 2024, resulting in 67 final studies. The data are presented in separate subsections for recommendation systems (43 works) and data collection technologies (17 works), with a discussion section identifying research challenges. The findings indicate that the fields of data-driven innovation and personalised nutrition are predominately amalgamated in the use of recommender systems.

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through highly descriptive patch embeddings and hierarchical structures, there is still limited research on utilizing additional data representations so as to refine the self-attention map of a Transformer. To address this problem, a novel attention mechanism, called multi-manifold multi-head attention, is proposed in this work to substitute the vanilla self-attention of a Transformer. The proposed mechanism models the input space in three distinct manifolds, namely Euclidean, Symmetric Positive Definite and Grassmann, thus leveraging different statistical and geometrical properties of the input for the computation of a highly descriptive attention map. In this way, the proposed attention mechanism can guide a Vision Transformer to become more attentive towards important appearance, color and texture features of an image, leading to improved classification and segmentation results, as shown by the experimental results on well-known datasets.

Grape maturity estimation is vital in precise agriculture as it enables informed decision making for disease control, harvest timing, grape quality, and quantity assurance. Despite its importance, there are few large publicly available datasets that can be used to train accurate and robust grape segmentation and maturity estimation algorithms. To this end, this work proposes the CERTH grape dataset, a new sizeable dataset that is designed explicitly for evaluating deep learning algorithms in grape segmentation and maturity estimation. The proposed dataset is one of the largest currently available grape datasets in the literature, consisting of around 2500 images and almost 10 k grape bunches, annotated with masks and maturity levels. The images in the dataset were captured under various illumination conditions and viewing angles and with significant occlusions between grape bunches and leaves, making it a valuable resource for the research community. Thorough experiments were conducted using a plethora of general object detection methods to provide a baseline for the future development of accurate and robust grape segmentation and maturity estimation algorithms that can significantly advance research in the field of viticulture.

The ubiquitous nature of smartphone ownership, its broad application and usage, along with its interactive delivery of timely feedback are appealing for health-related behavior change interventions via mobile apps. However, users' perspectives about such apps are vital in better bridging the gap between their design intention and effective practical usage. In this vein, a modified technology acceptance model (mTAM) is proposed here, to explain the relationship between users' perspectives when using an AI-based smartphone app for personalized nutrition and healthy living, namely, PROTEIN, and the mTAM constructs toward behavior change in their nutrition and physical activity habits. In particular, online survey data from 85 users of the PROTEIN app within a period of 2 months were subjected to confirmatory factor analysis (CFA) and regression analysis (RA) to reveal the relationship of the mTAM constructs, i.e., perceived usefulness (PU), perceived ease of use (PEoU), perceived novelty (PN), perceived personalization (PP), usage attitude (UA), and usage intention (UI) with the users' behavior change (BC), as expressed via the acceptance/rejection of six related hypotheses (H1–H6), respectively. The resulted CFA-related parameters, i.e., factor loading (FL) with the related p-value, average variance extracted (AVE), and composite reliability (CR), along with the RA results, have shown that all hypotheses H1–H6 can be accepted (p < 0.001). In particular, it was found that, in all cases, FL > 0.5, CR > 0.7, AVE > 0.5, indicating that the items/constructs within the mTAM framework have good convergent validity. Moreover, the adjusted coefficient of determination (R2) was found within the range of 0.224–0.732, justifying the positive effect of PU, PEoU, PN, and PP on the UA, that in turn positively affects the UI, leading to the BC. Additionally, using a hierarchical RA, a significant change in the prediction of BC from UA when the UI is used as a mediating variable was identified. The explored mTAM framework provides the means for explaining the role of each construct in the functionality of the PROTEIN app as a supportive tool for the users to improve their healthy living by adopting behavior change in their dietary and physical activity habits. The findings herein offer insights and references for formulating new strategies and policies to improve the collaboration among app designers, developers, behavior scientists, nutritionists, physical activity/exercise physiology experts, and marketing experts for app design/development toward behavior change.

Continuous Sign Language Recognition (CSLR) refers to the challenging problem of recognizing sign language glosses and their temporal boundaries from weakly annotated video sequences. Previous methods focus mostly on visual feature extraction neglecting text information and failing to effectively model the intra-gloss dependencies. In this work, a cross-modal learning approach that leverages text information to improve vision-based CSLR is proposed. To this end, two powerful encoding networks are initially used to produce video and text embeddings prior to their mapping and alignment into a joint latent representation. The purpose of the proposed cross-modal alignment is the modelling of intra-gloss dependencies and the creation of more descriptive video-based latent representations for CSLR. The proposed method is trained jointly with video and text latent representations. Finally, the aligned video latent representations are classified using a jointly trained decoder. Extensive experiments on three well-known sign language recognition datasets and comparison with state-of-the-art approaches demonstrate the great potential of the proposed approach.

Ergonomic risk assessment is vital for identifying work-related human postures that can be detrimental to the health of a worker. Traditionally, ergonomic risks are reported by human experts through time-consuming and error-prone procedures; however, automatic algorithmic methods have recently started to emerge. To further facilitate the automatic ergonomic risk assessment, this paper proposes a novel variational deep learning architecture to estimate the ergonomic risk of any work-related task by utilizing the Rapid Entire Body Assessment (REBA) framework. The proposed method relies on the processing of RGB images and the extraction of 3D skeletal information that is then fed to a novel deep network for accurate and robust estimation of REBA scores for both individual body parts and the entire body. Through a variational approach, the proposed method processes the skeletal information to construct a descriptive skeletal latent space that can accurately model human postures. Moreover, the proposed method distills knowledge from ground truth ergonomic risk scores and leverages it to further enhance the discrimination ability of the skeletal latent space, leading to improved accuracy. Experiments on two well-known datasets (i.e., University of Washington Indoor Object Manipulation (UW-IOM) and Technische Universität München (TUM) Kitchen) validate the ability of the proposed method to achieve accurate results, overcoming current state-of-the-art methods.

Human-Computer Interaction (HCI) and games set a new domain in understanding people’s motivations in gaming, behavioral implications of game play, game adaptation to player preferences and needs for increased engaging experiences in the context of HCI serious games (HCI-SGs). When the latter relate with people’s health status, they can become a part of their daily life as assistive health status monitoring/enhancement systems. Co-designing HCI-SGs can be seen as a combination of art and science that involves a meticulous collaborative process. The design elements in assistive HCI-SGs for Parkinson’s Disease (PD) patients, in particular, are explored in the present work. Within this context, the Game-Based Learning (GBL) design framework is adopted here and its main game-design parameters are explored for the Exergames, Dietarygames, Emotional games, Handwriting games, and Voice games design, drawn from the PD-related i-PROGNOSIS Personalized Game Suite (PGS) (www.i-prognosis.eu) holistic approach. Two main data sources were involved in the study. In particular, the first one includes qualitative data from semi-structured interviews, involving 10 PD patients and four clinicians in the co-creation process of the game design, whereas the second one relates with data from an online questionnaire addressed by 104 participants spanning the whole related spectrum, i.e., PD patients, physicians, software/game developers. Linear regression analysis was employed to identify an adapted GBL framework with the most significant game-design parameters, which efficiently predict the transferability of the PGS beneficial effect to real-life, addressing functional PD symptoms. The findings of this work can assist HCI-SG designers for designing PD-related HCI-SGs, as the most significant game-design factors were identified, in terms of adding value to the role of HCI-SGs in increasing PD patients’ quality of life, optimizing the interaction with personalized HCI-SGs and, hence, fostering a collaborative human-computer symbiosis.

Being the second most common neurodegenerative disease, Parkinson's disease (PD) can be symptomatically treated, although, unfortunately, it cannot be cured yet. Moreover, diagnosing and assessing PD patients is a complex process, requiring continuous monitoring. In this vein, the design, development, and validation of innovative assessment tools may be helpful in the management of patients with PD, in particular. Based on intelligent ICT interventions, the i-PROGNOSIS project intends to mitigate PD's specific symptoms, such as neurological movement disorders of gait, balance, coordination, and posture, already characterized in the early phase of the disease. From this perspective, an innovative iPrognosis motor assessment tool is presented here, taking into consideration the Unified Parkinson Disease Rating Scale (UPDRS) Part III motor skills testing items, for evaluating the motor skills status. The efficiency of the proposed Assessment Tests to reflect the motor skills status, similarly to the UPDRS Part III items, was validated via 27 participants (18 males; mean age = 62 years, SD = 10.36 years; range, 43–79 years) with early (n = 10) and moderate (n = 17) PD who performed the Assessment Tests. Features from the latter were then correlated with the corresponding clinically assessed UPDRS Part III items, and statistically significant negative correlations (range, −0.364 to −0.802) were identified between the median values of the Assessment Tests and the UPDRS Part III items. In this vein, the iPrognosis Assessment Tests were integrated within the personalized interventions of the i-PROGNOSIS project, providing alternative means of assessing their effect on the PD patient's motor skills enhancement. The promising results presented here elaborate on the concept of using ICT-based assessment means to achieve comparable outcomes with the clinical standards in motor skills assessment.

AI technologies can play an important role in breaking down the communication barriers of deaf or hearing-impaired people with other communities, contributing significantly to their social inclusion. Recent advances in both sensing technologies and AI algorithms have paved the way for the development of various applications aiming at fulfilling the needs of deaf and hearing-impaired communities. To this end, this survey aims to provide a comprehensive review of state-of-the-art methods in sign language capturing, recognition, translation and representation, pinpointing their advantages and limitations. In addition, the survey presents a number of applications, while it discusses the main challenges in the field of sign language technologies. Future research direction are also proposed in order to assist prospective researchers towards further advancing the field.

Continuous sign language recognition is a weakly supervised task dealing with the identification of continuous sign gestures from video sequences, without any prior knowledge about the temporal boundaries between consecutive signs. Most of the existing methods focus mainly on the extraction of spatio-temporal visual features without exploiting text or contextual information to further improve the recognition accuracy. Moreover, the ability of deep generative models to effectively model data distribution has not been investigated yet in the field of sign language recognition. To this end, a novel approach for context-aware continuous sign language recognition using a generative adversarial network architecture, named as Sign Language Recognition Generative Adversarial Network (SLRGAN), is introduced. The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels. The paper also investigates the importance of contextual information on sign language conversations for both Deaf-to-Deaf and Deaf-to-hearing communication. Contextual information, in the form of hidden states extracted from the previous sentence, is fed into the bidirectional long short-term memory module of the generator to improve the recognition accuracy of the network. At the final stage, sign language translation is performed by a transformer network, which converts sign language glosses to natural language text. Our proposed method achieved word error rates of 23.4%, 2.1% and 2.26% on the RWTH-Phoenix-Weather-2014 and the Chinese Sign Language (CSL) and Greek Sign Language (GSL) Signer Independent (SI) datasets, respectively.

The environmental challenges the world faces nowadays have never been greater or more complex. Global areas covered by forests and urban woodlands are threatened by natural disasters that have increased dramatically during the last decades, in terms of both frequency and magnitude. Large-scale forest fires are one of the most harmful natural hazards affecting climate change and life around the world. Thus, to minimize their impacts on people and nature, the adoption of well-planned and closely coordinated effective prevention, early warning, and response approaches are necessary. This paper presents an overview of the optical remote sensing technologies used in early fire warning systems and provides an extensive survey on both flame and smoke detection algorithms employed by each technology. Three types of systems are identified, namely terrestrial, airborne, and spaceborne-based systems, while various models aiming to detect fire occurrences with high accuracy in challenging environments are studied. Finally, the strengths and weaknesses of fire detection systems based on optical remote sensing are discussed aiming to contribute to future research projects for the development of early warning fire systems.

The environmental challenges the world faces have never been greater or more complex. Global areas that are covered by forests and urban woodlands are threatened by large-scale forest fires that have increased dramatically during the last decades in Europe and worldwide, in terms of both frequency and magnitude. To this end, rapid advances in remote sensing systems including ground-based, unmanned aerial vehicle-based and satellite-based systems have been adopted for effective forest fire surveillance. In this paper, the recently introduced 360-degree sensor cameras are proposed for early fire detection, making it possible to obtain unlimited field of view captures which reduce the number of required sensors and the computational cost and make the systems more efficient. More specifically, once optical 360-degree raw data are obtained using an RGB 360-degree camera mounted on an unmanned aerial vehicle, we convert the equirectangular projection format images to stereographic images. Then, two DeepLab V3+ networks are applied to perform flame and smoke segmentation, respectively. Subsequently, a novel post-validation adaptive method is proposed exploiting the environmental appearance of each test image and reducing the false-positive rates. For evaluating the performance of the proposed system, a dataset, namely the “Fire detection 360-degree dataset”, consisting of 150 unlimited field of view images that contain both synthetic and real fire, was created. Experimental results demonstrate the great potential of the proposed system, which has achieved an F-score fire detection rate equal to 94.6%, hence reducing the number of required sensors. This indicates that the proposed method could significantly contribute to early fire detection.

The field of 3D hand pose estimation has been gaining a lot of attention recently, due to its significance in several applications that require human-computer interaction (HCI). The utilization of technological advances, such as cost-efficient depth cameras coupled with the explosive progress of Deep Neural Networks (DNNs), has led to a significant boost in the development of robust markerless 3D hand pose estimation methods. Nonetheless, finger occlusions and rapid motions still pose significant challenges to the accuracy of such methods. In this survey, we provide a comprehensive study of the most representative deep learning-based methods in literature and propose a new taxonomy heavily based on the input data modality, being RGB, depth, or multimodal information. Finally, we demonstrate results on the most popular RGB and depth-based datasets and discuss potential research directions in this rapidly growing field.

In this paper we address the problem of automated grading of invasive breast carcinoma through the encoding of histological images as VLAD (Vector of Locally Aggregated Descriptors) representations on the Grassmann manifold. The proposed method considers each image as a set of multidimensional spatially-evolving signals that can be efficiently modeled through a higher-order linear dynamical systems analysis. Subsequently, each H&E (Hematoxylin and Eosin) stained breast cancer histological image is represented as a cloud of points on the Grassmann manifold, while a vector representation approach is applied aiming to aggregate the Grassmannian points based on a locality criterion on the manifold. To evaluate the efficiency of the proposed methodology, two datasets with different characteristics were used. More specifically, we created a new medium-sized dataset consisting of 300 annotated images (collected from 21 patients) of grades 1, 2 and 3, while we also provide experimental results using a large dataset, namely BreaKHis, containing 7,909 breast cancer histological images, collected from 82 patients, of both benign and malignant cases. Experimental results have shown that the proposed method outperforms a number of state of the art approaches providing average classification rates of 95.8% and 91.38% with our dataset and the BreaKHis dataset, respectively.

Amidst an ongoing debate surrounding the traditional dichotomy of whether video games are good or bad for children, in this paper we present Path of Trust, a novel, prosocial game that aims at helping children understand the importance of teamwork and learn how and when to express trustworthiness. We have created a colorful, non-violent digital game, in which children aged 7-10 can be exposed to prosocial content and develop specific prosocial attitudes, such as cooperation and trustworthiness, driven by the fact that video games with prosocial content can be used to improve social interactions. The game was designed to maintain an attractive and engaging nature, which is usually associated with games that are often vilified within social circles in terms of being packed with tons of action and violence. We conducted two separate studies to test our game’s modeling of prosocial behavior, which demonstrate the potential of the game as a tool for teaching important prosocial behavior to children.