Nutrition-Related Knowledge Graph Neural Network for Food Recommendation

Foods, Год журнала: 2024, Номер 13(13), С. 2144 - 2144

Опубликована: Июль 5, 2024

Food recommendation systems are becoming increasingly vital in modern society, given the fast-paced lifestyle and diverse dietary habits. Existing research implemented solutions often rely on user preferences past behaviors for recommendations, which poses significant issues. Firstly, this approach inadequately considers nutritional content of foods, potentially leading to recommendations that overly homogeneous lacking diversity. Secondly, it may result repetitive suggestions same types thereby encouraging users develop unhealthy habits could adversely affect their overall health. To address issue, we introduce a novel nutrition-related knowledge graph (NRKG) method based convolutional networks (GCNs). This not only enhances users’ ability select appropriate foods but also encourages development healthy eating habits, contributing public The NRKG comprises two key components: food recipe nutrition components. first component gathers information from recipes show interest synthesizes these data reference. second connects with similar profiles, forming complex heterogeneous structure. By learning graph, integrates data, resulting more accurate personalized recommendations. We evaluated against six baseline methods using real-world datasets. In 100% dataset, five metrics exceeded performance best by 2.8%, 5.9%, 1.5%, 9.7%, 6.0%, respectively. results indicate our significantly outperforms methods, including FeaStNet, DeepGCN, GraphSAGE, GAT, UniMP, GATv2, demonstrating its superiority effectiveness promoting healthier Unlike primarily focus hierarchical propagation, offers comprehensive integrating preferences.

Язык: Английский

---

The perceptual primacy of feeling: Affectless visual machines explain a majority of variance in human visually evoked affect

Proceedings of the National Academy of Sciences, Год журнала: 2025, Номер 122(4)

Опубликована: Янв. 23, 2025

Looking at the world often involves not just seeing things, but feeling things. Modern feedforward machine vision systems that learn to perceive in absence of active physiology, deliberative thought, or any form feedback resembles human affective experience offer tools demystify relationship between and feeling, assess how much visually evoked experiences may be a straightforward function representation learning over natural image statistics. In this work, we deploy diverse sample 180 state-of-the-art deep neural network models trained only on canonical computer tasks predict ratings arousal, valence, beauty for images from multiple categories (objects, faces, landscapes, art) across two datasets. Importantly, use features these without additional learning, linearly decoding responses activity same way neuroscientists decode information recordings. Aggregate analysis our survey, demonstrates predictions purely perceptual explain majority explainable variance average alike. Finer-grained within survey (e.g. comparisons shallower deeper layers, randomly initialized, category-supervised, self-supervised models) point rich, preconceptual abstraction (learned diversity visual experience) as key driver predictions. Taken together, results provide further computational evidence an information-processing account affect linked directly efficient statistics, hint locus aesthetic valuation immediately proximate perception.

Язык: Английский

---

Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition

PLoS Computational Biology, Год журнала: 2025, Номер 21(1), С. e1012751 - e1012751

Опубликована: Янв. 27, 2025

The human visual system possesses a remarkable ability to detect and process faces across diverse contexts, including the phenomenon of face pareidolia—–seeing in inanimate objects. Despite extensive research, it remains unclear why employs such broadly tuned detection capabilities. We hypothesized that pareidolia results from system’s optimization for recognizing both To test this hypothesis, we used task-optimized deep convolutional neural networks (CNNs) evaluated their alignment with behavioral signatures responses, measured via magnetoencephalography (MEG), related processing. Specifically, trained CNNs on tasks involving combinations identification, detection, object categorization, detection. Using representational similarity analysis, found included categorization training represented faces, real matched objects more similarly responses than those did not. Although these showed similar overall data, closer examination internal representations revealed specific had distinct effects how were layers. Finally, interpretability methods only CNN identification relied face-like features—such as ‘eyes’—to classify stimuli mirroring findings perception. Our suggest human-like may emerge within context generalized categorization.

Язык: Английский

---

A study comparing energy consumption and environmental emissions in ostrich meat and egg production

Journal of Agricultural Engineering, Год журнала: 2025, Номер 56(1)

Опубликована: Фев. 11, 2025

The assessment of energy usage in the production ostrich meat and eggs provides a comprehensive analysis consumption efficiency. per 1000 units is 1,086,825.54 MJ for 1,197,794.25 egg. When considering protein supply, egg seems to be more justifiable terms efficiency compared production. This study delves into impact on human health, revealing slight difference 0.23 disability adjusted life years (DALY), hinting that could potentially have marginally negative health effects than Artificial neural network (ANN) indicates optimizing machinery, diesel fuel, can enhance productivity It also suggests there possibility greater resource as opposed production, highlighting focus within yield positive environmental benefits. Additionally, coefficient determination adaptive neuro-fuzzy inference system (ANFI) 4 model favorable outcome factors related those Moreover, low mean squared error value reflects high accuracy results obtained analysis.

Язык: Английский

---

Non-bifurcation regulation of chaos in a memristive Hopfield neural network

Nonlinear Dynamics, Год журнала: 2025, Номер unknown

Опубликована: Фев. 14, 2025

Язык: Английский

---