Nzivugira Patrick D. Profile

0,0

(0 avaliações)

Você está agora seguindo

Erro seguindo usuário.

Esse usuários não permite que o sigam.

Você já está seguindo esse usuário.

Seu plano permite apenas 0 seguidas. Aprimore-o aqui.

Deixou de seguir com sucesso

Ocorreu um erro ao deixar de seguir o usuário.

Você recomendou com sucesso

Ocorreu um erro ao recomendar o usuário.

Algo deu errado. Por favor, atualize a página e tente novamente.

E-mail verificado com sucesso

$25 USD / hora

seoul,

korea, republic of

$25 USD / hora

Atualmente, está 8:18 PM aqui

Ingressou em março 8, 2024

0 Recomendações

Nzivugira Patrick D.

@TheBlueCipher

0,0

(0 avaliações)

0,0

$25 USD / hora

seoul,

korea, republic of

$25 USD / hora

Não se aplica

Trabalhos Concluídos

Não se aplica

Dentro do Orçamento

Não se aplica

No Prazo

Não se aplica

Taxa de Recontratação

Machine Learning Engineer

As a strategically adept ML Research Engineer, I specialize in applying ML techniques to enhance operational efficiencies across various domains. My expertise lies in developing predictive models and AI algorithms that significantly enhance decision-making processes, contributing to sustainable developments within the tech and engineering sectors. With a comprehensive background in data analysis, I have successfully led cross-functional teams, leveraging my technical skills to provide actionable insights in fast-paced, innovative environments. My work focuses on bridging the gap between complex data and practical solutions, driving progress and efficiency in every project I undertake.

Ver todos Python Developers em Korea, Republic of

Contate Nzivugira Patrick D. sobre seu trabalho

Faça login para discutir quaisquer detalhes via chat.

Portfólio

1. Access the specified URL to initiate the data scraping process.
2. Extract all data from table columns on the betting website.
3. Organize the extracted data and store it systematically in a database.
4. Automate the scraping process to recur every 10 minutes, ensuring continuous data updates.

Scraping data from a betting website using Selenium

Analyzing trends and seasonality in a time series for efficient decision-making:

1. Using the autocorrelation function to evaluate the seasonality.
2. Using the STL method to decompose the time series.
3. Analyzing daily and weekly patterns.

Time series analysis

1.Data Preprocessing: Cleaning and preparing the data for analysis, including normalization and handling missing values.

2. LSTM Model Development: Developing Long Short-Term Memory (LSTM) models to forecast urban air pollutants based on historical meteorology data.

3. Performance Testing: Testing the performance of 110 different LSTM models across various pollutants and conditions.
Analysis of Sensor Requirements: Investigating the necessary number of meteorological sensors for effective air quality management.

4. Impact Assessment of Extreme Conditions: Assessing how extreme conditions such as bush fires and COVID-19 lock downs affect pollutant predictability.

5. Forecasting Capability Exploration: Exploring the forecasting capabilities of models under standard and non-standard conditions.

LSTM model to forecast outdoor air pollutants

1. Machine Learning Model Development: Developing and training CNN, GRU, and CNN + GRU models for predicting indoor illuminance.

2. Model Performance Optimization and Evaluation: Tuning model parameters and evaluating performance using metrics like R2, RMSE, and MAE.

3. Generalization and Sensor Grouping: Testing models' generalization on unseen data and grouping illuminance sensors for analysis.

4. Computational Efficiency Analysis: Comparing models in terms of training time, prediction speed, and model size.

Machine Learning for Daylight Prediction

1. Data Collection and Processing: Hourly air temperature data over 18 years from 8 sites around Sydney was collected, with quality control measures applied to ensure data integrity.

2. Temporal UHI Variations Analysis: Investigated diurnal, monthly, seasonal, and annual variations of UHI intensity using the difference in temperature between urban areas and a suburban/rural reference location.

3. LSTM Model Development: Two types of LSTM models were developed; one using ambient temperature (LSTMT) and the other incorporating both air temperature and wind speed (LSTMW), to forecast UHI intensity.

4. Model Settings and Performance Validation: Model parameters were optimized through trial and error, and performance was validated using statistical metrics such as RMSE, MAE, and R^2.

5. Analysis of Results: The UHI trends and patterns were analyzed, including the impact of diurnal and seasonal changes, and spatial distribution across the different monitoring stations.

Forecasting UHI Intensity in Sydney Using LSTM Models

Scraping data from a betting website using Selenium

Time series analysis

LSTM model to forecast outdoor air pollutants

Machine Learning for Daylight Prediction

Forecasting UHI Intensity in Sydney Using LSTM Models

Avaliações

Mudanças salvas

Nenhuma avaliação aqui!

Experiência

ENSSEL

jul. 2023 - Atual

Developing AI-based solutions across various sectors.

Educação

Combined Ms-Ph.D. in Artificial Intelligence

Kyung Hee University,

Korea, Republic of

2019 - 2023

(4 anos)

B.Tech in Computer Science and Engineering

Jawaharlal Nehru Technological University,

India

2014 - 2018

(4 anos)

Qualificações

Google Career Certificates

2023

This certificate equips participants with the skills to analyze and interpret data by building machine learning and regression models. It also teaches the creation of data visualizations and the application of statistical methods, enhancing the ability to effectively communicate insights to stakeholders within an organization.