About Houssem Eddine
🚀 AI & Mobile Developer
Arabic
Native or bilingual
French
Fluent
English
Fluent
Experience
- SNAPYUMDÉVELOPPEUR MOBILETELECOMMUNICATIONSApril 2025 - June 2025 (2 months)
- Développement mobile avec Flutter pour les plateformes iOS et Android.
- Intégration du backend avec Flask, Firebase Realtime Database, Firestore, et Cloud Functions.
- Intégration du système de paiement via In‑App Purchase.
- Utilisation de l’API GPT‑4‑Vision pour la détection d’ingrédients à partir d’une image (object detection).
- Génération de recettes à partir d’ingrédients identifiés grâce à GPT‑4.
- Intégration de l’API YouTube pour afficher des vidéos explicatives des recettes.
- Fonctionnement de l’application : l’utilisateur prend une photo ou sélectionne une image des ingrédients, l’IA identifie les aliments et propose des recettes adaptées avec instructions pas à pas.
- Application pensée pour une expérience utilisateur simple et intuitive, axée sur l’intelligence artificielle et la cuisine personnalisée.
- Participation à toutes les étapes du cycle de développement, de la conception à la mise en production.
- Tests, corrections de bugs, et publication de l’application sur l’App Store et le Play Store.
- SESSTIMMachine Learning EngineerNovember 2023 - Today (2 years and 7 months)Marseille, FranceI worked as an AI Engineer at SESSTIM for 12 months on a project focused on analyzing the mental health of cancer patients using SNDS data (specifically VICAN data). The goal of this project was to detect and monitor mental health outcomes in cancer patients based on their treatment sequences, leveraging large-scale health data.My responsibilities encompassed the entire data science pipeline, including:
- Data Preprocessing and Cleaning: I worked on processing complex, multi-source SNDS data, cleaning and preparing it to ensure quality. I collaborated closely with cancer specialists to perform feature engineering, identifying key variables relevant to patient mental health based on treatment paths and sequences.
- Model Development and Evaluation: I applied a variety of machine learning models to predict mental health outcomes, including deep learning models such as LSTM with autoencoders to capture sequential patterns in treatment, as well as traditional models like Random Forest and XGBoost. I evaluated model performance and refined it to achieve reliable and interpretable results.
- Developing SNDSPOP Package: As part of the project, we developed a package called SNDSPOP for simplifying the characterization of cancer patient groups. This package enables developers and researchers to analyze patient characteristics with a single line of code. SNDSPOP provides detailed insights, such as:
- Treatment Usage: Automatically calculates the usage percentage of various treatments (e.g., radiotherapy, surgery).
- Treatment Regimen Analysis: Characterizes treatment regimens (e.g., neoadjuvant, adjuvant).
- Sankey Diagram Visualization: Generates a Sankey diagram to visualize patient treatment sequences, helping users understand treatment flows and transitions based on medical records.
I worked with a dataset of +7,000 patients, covering treatments under SNDS categories like CCAM, ICD-10, ATC, BIO, and LPP. - SESSTIMMachine Learning InternMarch 2023 - August 2023 (6 months)Marseille, FranceDuring my six-month internship at SESSTIM, I worked on PHARMA AI, a project designed to analyze medical prescription data from Marseille hospitals to identify potential prescription errors. These errors could include overdoses, underdoses, and incompatible medications prescribed together, among other issues.I was responsible for the end-to-end development of the project, handling tasks across the entire data science pipeline. This included:
- Data Cleaning and Verification: I ensured the quality and consistency of the prescription data, addressing any missing or erroneous values.
- Model Training and Evaluation: I built and trained machine learning models to detect prescription anomalies and rigorously evaluated their performance.
- Model Interpretability: I focused on making the model's decisions interpretable, which is essential in the healthcare field to ensure trust and transparency.
- Model Deployment: Finally, I deployed the model to ensure it could function in a real-world setting, integrating seamlessly into hospital workflows.
Recommendations
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Engineer's degree, Computer ScienceECOLE SUPERIEURE EN INFORMATIQUE 08 MAI 1945, SIDI BEL ABBES2023Engineer's degree, Computer Science
- Licence, InformatiqueCentre Universitaire de Souk-Ahras2020Licence, Informatique
Certifications
- Logo de Udacity AI Programming with PythonUdacity2019