Logo Freelancer
Se connecter S'inscrire
Publier un projet
EXPLORER
Django
Python
React.js
Photo de couverture du profil
Vous suivez désormais
Erreur de suivi de l'utilisateur.
Cet utilisateur n'utilise pas les utilisateurs à le suivre.
Vous suivez déjà cet utilisateur.
Votre plan d'adhésion ne permet que 0 suivis. Améliorez ici.
Ne suit désormais plus
Erreur lors de l'arrêt du suivi de l'utilisateur.
Vous avez désormais recommandé
Erreur lors de la recommendation de l'utilisateur.
Une erreur a eu lieu. Veuillez rafraîchir la page et réessayer.
E-mail désormais vérifié.
Avatar de l'utilisateur

Amine S.

@aminesouissii

monthly-level-three.svgverified-v2.svg
5,0
21
5,1
5,1
91%

CLIENT FIRST | Python & React | AI Tech Lead

$40 USD / Heure
・
Drapeau de
Morocco (11:42 AM)
・
Inscrit depuis le février 23, 2021
$40 USD / Heure
・
I am a Data Science Engineer with a passion for Python and a specialization in AI, Machine Learning, and Deep Learning. I also serve as a Full Stack Tech Lead, proficient in ReactJS and Django. I have a strong analytical and synthesis mind, and I excel in adapting to new challenges and environments. My thirst for knowledge drives me to continuously learn and grow in my field. My skills : ★ OS : Windows • Linux(Ubuntu, Fedora, Mint, Redhat). ★ Languages: • Python (Web Services: Flask, Django, Dash) • JavaScript • SQL • R ★ Full-Stack Development: • Frontend: ReactJS (Hooks, Redux, Context API, Zustand) • Backend: Django (REST Framework), Flask • Databases: MySQL, SQL Server, PostgreSQL, MongoDB • Cloud Services: AWS (EC2, S3) • Other Technologies: WebSocket, Payments API ★ Data Science: • Web Scraping: Selenium, BeautifulSoup • Machine Learning: Regression, Classification, Clustering • Natural Language Processing (NLP): Sentiment Analysis, Speech To Text (STT), Text To Speech (TTS) • Deep Learning: ANN, CNN, RNN (LSTM), Seq2Seq, DBN • Computer Vision: HandTracking, FaceDetection, MeshDetection • Data Mining: Text Mining (.txt, .csv, .pdf), Natural Language Processing • Big Data: Hadoop, Spark (PySpark), MongoDB, Cassandra ★ Prompt Engineering: • Creating and optimizing prompts for AI models • Fine-tuning model parameters, integrating AI solutions with existing workflows • Enhancing model performance for specific tasks • Generating images with DALL-E 3. • Automating prompts with OpenAI API. ★ Tools: • AWS • Docker • GitLab • GitHub • Visual Studio Code (VSCode) (many more) • Postman • Power BI • Tableau • VirtualBox • VMware • Ansible • Icinga • Qt Designer • LaTeX ★ Management: • Project Management • Digital Transformation • Digital Marketing • Software Quality Assurance (SQA) • SCRUM (Certified) ★ Languages: • English • French • Arabic I currently work as a Medical Data Scientist in e-health at Keenturtle in Paris,French. Bringing a unique combination of data science and prompt engineering skills to my projects. I'm also serving as full-stack tech lead at ArkanPro in Riyadh, Saudi Arabia. Best Regards,
Vérifications
Dans les temps
96 %
Dans le budget
68 %
Taux d'acceptation
79 %
Taux de réembauche
13 %
Freelancer Python Developers Morocco
Voir tous les Python Developers en Morocco

Portfolio

Portfolio

11989017
Developed a ML model to enhance secure drug use in hospitals using clustering techniques, showcasing my skills in data science, ML and healthcare data analysis + Django Web Service Integration. ★ Objective: Create a reliable model to identify patterns in drug usage and detect anomalies, ensuring safe and efficient medication practices in hospitals. ★ Features: • Data Collection: Gathered comprehensive hospital drug usage datasets. Cleaned, normalized, and selected features. • Model Development: Implemented clustering algorithms like K-means, DBSCAN, and Hierarchical Clustering to identify patterns and anomalies. • Training: Trained models on historical data, fine-tuned parameters, and performed cross-validation for accuracy. • Evaluation: Assessed performance using metrics like silhouette score and Davies-Bouldin index. Validated with a test set. • Visualization: Created visualizations to illustrate clusters and detected anomalies. ★ Technologies: Python, Scikit-learn, Pycaret, VsCode
Secure Drug Uses in hospitals using ML Clustering
Developed a ML model to enhance secure drug use in hospitals using clustering techniques, showcasing my skills in data science, ML and healthcare data analysis + Django Web Service Integration. ★ Objective: Create a reliable model to identify patterns in drug usage and detect anomalies, ensuring safe and efficient medication practices in hospitals. ★ Features: • Data Collection: Gathered comprehensive hospital drug usage datasets. Cleaned, normalized, and selected features. • Model Development: Implemented clustering algorithms like K-means, DBSCAN, and Hierarchical Clustering to identify patterns and anomalies. • Training: Trained models on historical data, fine-tuned parameters, and performed cross-validation for accuracy. • Evaluation: Assessed performance using metrics like silhouette score and Davies-Bouldin index. Validated with a test set. • Visualization: Created visualizations to illustrate clusters and detected anomalies. ★ Technologies: Python, Scikit-learn, Pycaret, VsCode
Secure Drug Uses in hospitals using ML Clustering
11988956
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
11988838
Overview: Developed a predictive model to forecast water demand using Long Short-Term Memory (LSTM) networks. This project highlights my expertise in time series forecasting and deep learning applied to a critical real-world issue. Objective: Create a reliable model to predict future water demand from historical data, aiding efficient water resource management and sustainability. Features: Data Preprocessing: Collected and cleaned historical water demand data, performed normalization and feature engineering. Model Architecture: Implemented an LSTM network to capture temporal dependencies. Training & Optimization: Trained and fine-tuned the model to enhance accuracy. Evaluation: Assessed performance using MAE and RMSE, validated with unseen data. Visualization: Compared predicted vs. actual demand to demonstrate accuracy. Technologies: Python, TensorFlow, Keras, NumPy, Pandas, Matplotlib, Scikit-learn, VsCode.
Water demand prediction using LSTM(s)
10184455
Explosives Detection using CNN and LSTM(s)
11989017
Developed a ML model to enhance secure drug use in hospitals using clustering techniques, showcasing my skills in data science, ML and healthcare data analysis + Django Web Service Integration. ★ Objective: Create a reliable model to identify patterns in drug usage and detect anomalies, ensuring safe and efficient medication practices in hospitals. ★ Features: • Data Collection: Gathered comprehensive hospital drug usage datasets. Cleaned, normalized, and selected features. • Model Development: Implemented clustering algorithms like K-means, DBSCAN, and Hierarchical Clustering to identify patterns and anomalies. • Training: Trained models on historical data, fine-tuned parameters, and performed cross-validation for accuracy. • Evaluation: Assessed performance using metrics like silhouette score and Davies-Bouldin index. Validated with a test set. • Visualization: Created visualizations to illustrate clusters and detected anomalies. ★ Technologies: Python, Scikit-learn, Pycaret, VsCode
Secure Drug Uses in hospitals using ML Clustering
Developed a ML model to enhance secure drug use in hospitals using clustering techniques, showcasing my skills in data science, ML and healthcare data analysis + Django Web Service Integration. ★ Objective: Create a reliable model to identify patterns in drug usage and detect anomalies, ensuring safe and efficient medication practices in hospitals. ★ Features: • Data Collection: Gathered comprehensive hospital drug usage datasets. Cleaned, normalized, and selected features. • Model Development: Implemented clustering algorithms like K-means, DBSCAN, and Hierarchical Clustering to identify patterns and anomalies. • Training: Trained models on historical data, fine-tuned parameters, and performed cross-validation for accuracy. • Evaluation: Assessed performance using metrics like silhouette score and Davies-Bouldin index. Validated with a test set. • Visualization: Created visualizations to illustrate clusters and detected anomalies. ★ Technologies: Python, Scikit-learn, Pycaret, VsCode
Secure Drug Uses in hospitals using ML Clustering
11988956
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
★ Overview: Developed an AI model to predict house prices using Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), and Gradient Boosting, showcasing my skills in data science and real estate market analysis. ★ Objective: Create an accurate model to estimate house prices based on various features, aiding informed decisions for buyers, sellers, and real estate professionals. ★ Features: • Data Collection: Gathered comprehensive datasets, including property features and market trends. Cleaned, normalized, and selected features. • Model Development: Implemented CNNs, DBNs, and Gradient Boosting to identify patterns and relationships. • Training: Trained models on historical data, optimized hyperparameters, and performed cross-validation. • Evaluation: Assessed using RMSE and R², validated with a test set. • Visualization: Compared predicted prices with actual values. ★ Technologies: Python, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, VsCode.
House Pricing AI Model
11988838
Overview: Developed a predictive model to forecast water demand using Long Short-Term Memory (LSTM) networks. This project highlights my expertise in time series forecasting and deep learning applied to a critical real-world issue. Objective: Create a reliable model to predict future water demand from historical data, aiding efficient water resource management and sustainability. Features: Data Preprocessing: Collected and cleaned historical water demand data, performed normalization and feature engineering. Model Architecture: Implemented an LSTM network to capture temporal dependencies. Training & Optimization: Trained and fine-tuned the model to enhance accuracy. Evaluation: Assessed performance using MAE and RMSE, validated with unseen data. Visualization: Compared predicted vs. actual demand to demonstrate accuracy. Technologies: Python, TensorFlow, Keras, NumPy, Pandas, Matplotlib, Scikit-learn, VsCode.
Water demand prediction using LSTM(s)
10184455
Explosives Detection using CNN and LSTM(s)
Modifications enregistrées
5.0 · 21 Reviews
Commentaires
J
Easylife app • $460 USD
Responsible, open to dialogue. Honest, not harassing like other freelancers. You can work well with it at your own pace.
Jorge G.
@jorgejc1
•
Drapeau de
Panama City, Panama
•
il y a 2 ans
Partager
Avatar de l'utilisateur
ISR - Sentiment Analysis • $375 USD
He worked according to the requirement
Kishore Kumar A.
@kishoreanumola
•
Drapeau de
Hyderabad, India
•
il y a 2 ans
Partager
E
Need a Machine Learning tutor (good with PySpark and Python) • £220 GBP
Very easy to communicate with and responds very quickly to messages. Delivery time exceeded expectations, and work was completed to an excellent standard - also very good at explaining all work done and how it functions. Very satisfied and will likely contact Amine again in the future for any other ML-related queries.
Edgar G.
@EdGzelka
•
Drapeau de
Sleaford, United Kingdom
•
il y a 3 ans
Partager
P
Project for Amine S. -- 2 • $250 USD
Very hardworking and committed
Sunil P.
@pandeys14
•
Drapeau de
SIngapore, Singapore
•
il y a 3 ans
Partager
N
Information retrieval project • ₹24 908 INR
Nice co-ordination and great work
Nitish P.
@nitshreddy
•
Drapeau de
Hyderabad, India
•
il y a 3 ans
Partager
Expérience
Python Developper
févr., 2021 - Présent
•
3 ans, 10 mois
Keenturtle
févr., 2021 - Présent
•
3 ans, 10 mois
I'm currently in charge of a hospital located in Switzerland, I manage a specific part of the pharmaceutical application named 'Pharmaclass', this part is named 'PharmaCollect'. I receive data in excel, csv, etc ..., and I transforms it to a form according to norms and global standards, to then deploy the various components of this part; I manage the Patients, Prescriptions, Medico-biological analyzes, Physiological Constants, and Diagnostics part. Technologies : Python - NLP - SQL - JSON
févr., 2021 - Présent
•
3 ans, 10 mois
Machine Learning developper
juil., 2020 - sept., 2020
•
1 mois, 30 jours
Keenturtle
juil., 2020 - sept., 2020
•
1 mois, 30 jours
The goal was to secure the use of drugs in hospitals. My work consisted of studying medical data in excel, csv form by comparing them with 4 other ref dictionaries, I clustered the result according to keywords identified and indexed as for exp: Molecules, Substance, Drug name, Sex, Weight, Etc ..., then I added columns to the Data, so I did the clustering by finding similar actions , and finally creating decision rules for pharmacists. Techno : Python - Machine Learning - K-means - NLP
juil., 2020 - sept., 2020
•
1 mois, 30 jours
Svm as a service
mai, 2020 - mai, 2020
INPT
mai, 2020 - mai, 2020
•
0 secondes
Creation of a web service for purchase prediction for employees using the Support Vector Machine algorithm with Python using the Flask framework. Techno : Python - Machine Learning - Support Vector Machine as a service - Flask
mai, 2020 - mai, 2020
Certifications
P
Preferred Freelancer Program SLA
Invitation désormais envoyée !
Merci ! Nous vous avons envoyé un lien par e-mail afin de réclamer votre crédit gratuit.
Une erreur a eu lieu lors de l'envoi de votre e-mail. Veuillez réessayer.
Logo Freelancer France / Français
Aide & Assistance
 Freelance
CatégoriesProjetsConcours FreelancesEntreprise Développement d'IA AdhésionProgramme de Freelance PréféréGestion de projetEmplois locauxPhoto AnywherePrésentationAPI pour les développeurs Obtenir la certification Application Desktop
 À propos
À propos de nousComment cela fonctionneSécuritéInvestisseurPlan du siteHistoiresNouveautésÉquipeRécompensesCommuniqué de presseOffres d'emploi
 Termes
Politique de ConfidentialitéTermes et ConditionsPolitique de CopyrightCode de conduiteFrais et charges
Partenaires
Escrow.comLoadshiftWarrior Forum
 Applications
Logo d'Apple App StoreLogo Google play
Échec de copie dans le presse-papier, veuillez réessayer après avoir ajuster vos permissions.
Copié dans le presse-papier.
Utilisateurs enregistrés Total des travaux publiés
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2025 Freelancer Technology Pty Limited (ACN 142 189 759)
Chargement de l'aperçu
Permission donnée pour la géolocalisation.
Votre session de connexion a expiré et vous avez été déconnecté. Veuillez vous connecter à nouveau.