MétaCan
Menu
Back to cohort
Record W4404104773 · doi:10.1145/3703599.3703602

Exploring AI-Based System for African Food Weight-Loss Recommendations

2024· article· en· W4404104773 on OpenAlex
Grace Ataguba, Halleluyah Oluwatobi Aworinde, Rita Orji

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueACM SIGACCESS Accessibility and Computing · 2024
Typearticle
Languageen
FieldMedicine
TopicNutritional Studies and Diet
Canadian institutionsDalhousie University
Fundersnot available
KeywordsComputer scienceWeight lossData scienceMedicineInternal medicine

Abstract

fetched live from OpenAlex

This research leverages artificial intelligence to design an African food recommendation system for weight loss. The rationale for designing this system was based on our recently published study on the design of socio-cultural food recognition systems for Africans. Based on our previous study, results revealed that users considered the socio-cultural food recognition system to provide nutritional value and would require a robust system with more African foods. Hence, to tailor our findings to effective dietary planning where obesity could be a concern, we propose the current system given the health implications of additional foods for specific users (that is, overweight users). Our current study is in three phases. The first phase will focus on validating some African foods with dieticians to determine their appropriateness for weight loss and better alternatives based on calories and other important metrics. Additionally, we will invite dieticians and some overweight users to evaluate some low-fidelity (Lo-fi) prototypes for the design requirement elicitation of the final prototype. The second phase will involve the development of our AI models (computer vision and large language models) and their evaluation. Furthermore, we will leverage the design requirements gathered from the lo-fi prototype study together with the AI models to develop a high-fidelity (Hi-fi) AI system that will run on mobile devices (the final prototype). Consequently, a post-study evaluation will be conducted with dieticians and overweight users to obtain subjective feedback. Hence, findings from this study will provide design recommendations for integrating African foods into existing and related large-scale AI-based systems in the future.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.686
Threshold uncertainty score0.657

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.137
GPT teacher head0.352
Teacher spread0.214 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it