EUVIMEDEUVIMED entdecken
Crossref

CHEMICAL COMPOUNDS RECOMMENDATION ENGINE BASED ON SKIN TYPES USING RETRIEVAL-AUGMENTED GENERATION AND OPTICAL CHARACTER RECOGNITION

L. Suryaprasad, Vasudev Joshi, Eshwari A., A. Haneen, M. S. Kendagannaswamy

ICTACT Journal on Data Science and Machine Learning · 01.06.2026 · 7 (3) · 1091-1096

DOI: 10.21917/ijdsml.2026.0200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICTACT Journal on Data Science and Machine Learning, online erschienen am 01.06.2026. Verfasst von L. Suryaprasad und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The assessment of chemical ingredients in cosmetic products against individual skin profiles is a largely manual and error-prone task. Existing consumer applications have primarily focused on the branding level and are without the depth of reasoning at the molecular level. Additionally, large language models (LLMs) without retrieval grounding generate hallucinations, resulting in unsafe recommendations and posing safety issues. This work presents a Chemical Compounds Recommendation Engine that integrates Optical Character Recognition (OCR) and a hierarchically structured Retrieval-Augmented Generation (RAG) framework to provide evidence-based recommendations on skincare ingredients. This engine processes a user query (optional product label image and skin type profile), retrieves relevant dermatology transcripts, employs evidence-based reasoning, and guides a structured response in JSON format (each recommendation is evidence-based and cited). Under a strict grounding condition, hallucinations are limited to a configurable evidence-overlap threshold (i.e., the rate = 2.7%). Role-Based Access Control (RBAC) provides a protective separation of doctor-level formulation safety analysis and consumer-level formulation safety analysis within a single microservices architecture (React, Spring Boot, Flask, and MongoDB) Provenance Tracking. Measuring 850 unique query responses, a separation F1 = 0.889 with 97.3% accurate grounding and 3.2 s latency is achieved, far surpassing the reliance on keyword, TF-IDF, ungrounded BERT, and zero retrieval GPT-4 benchmarks.

Zitieren

APA

Suryaprasad, L., Joshi, V., A., E., Haneen, A., & Kendagannaswamy, M. S. (2026). CHEMICAL COMPOUNDS RECOMMENDATION ENGINE BASED ON SKIN TYPES USING RETRIEVAL-AUGMENTED GENERATION AND OPTICAL CHARACTER RECOGNITION. ICTACT Journal on Data Science and Machine Learning, 7(3), 1091-1096. https://doi.org/10.21917/ijdsml.2026.0200

Vancouver

Suryaprasad L, Joshi V, A. E, Haneen A, Kendagannaswamy MS. CHEMICAL COMPOUNDS RECOMMENDATION ENGINE BASED ON SKIN TYPES USING RETRIEVAL-AUGMENTED GENERATION AND OPTICAL CHARACTER RECOGNITION. ICTACT Journal on Data Science and Machine Learning. 2026;7(3):1091-1096. doi:10.21917/ijdsml.2026.0200

BibTeX
@article{Suryaprasad2026,
  author = {Suryaprasad, L. and Joshi, Vasudev and A., Eshwari and Haneen, A. and Kendagannaswamy, M. S.},
  title = {CHEMICAL COMPOUNDS RECOMMENDATION ENGINE BASED ON SKIN TYPES USING RETRIEVAL-AUGMENTED GENERATION AND OPTICAL CHARACTER RECOGNITION},
  journal = {ICTACT Journal on Data Science and Machine Learning},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {1091--1096},
  doi = {10.21917/ijdsml.2026.0200}
}
Kostenlos starten →