dal3006 Goto Github PK

followers: 0.0 following: 0.0 repos: 821.0 gists: 1.0

Type: User

dal3006's Projects

feature-ranking-self-growing-forest

A tree ensemble algorithm that automatically grows decision trees so that the trees' structure diversity is optimized for performance and low computational cost. Can be used for both classification and regression tasks. Functions and a script example is programmed in MATLAB. A class is implemented for Python.

fiblock

Fault Injection Block for Simulink models

final-thesis-short-term-load-forecasting-in-khatulistiwa-power-system-using-long-short-term-memory

finance-forecasting

Stock Market Forecasting using LSTM\GRU

fitting-probability-distribution

When dealing with any type of dataset it is important to create a probabilistic model of the data

flow-forecast

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

fluke289_data_access

A series of Python scripts to access measurements from Fluke 28X meters. Fluke IR Remote Interface required.

fluke_scopemeter_matlab

Communication with Fluke Oscilloscope "scope meter" via Matlab

forecast-ai

A bitcoin and stock price forecaster utilizing an ensemble of autoregressive, N-BEATS, LSTM and layer normalized models, trained on various loss functions in TensorFlow. Utilizing Java for implementing a front-end interface for the application.

forecast_evaluation

Methods and tools for evaluating probabilistic forecasts

forecast_the_geomagnetic_storms

In this project, the task will be to forecast Dst in real-time to help satellite operators, power grid operators, and users of magnetic navigation systems prepare for magnetic disturbances. We used a DNN algorithm implemented in Python with Keras.

forecasting

Time-series forecasting with Deep Learning: RNN, LSTM, GRU, Rolling RNN/LSTM/GRU

forecasting-and-classification-of-mechanical-faults

predictive-maintenance-fault-classification(CWRU data)-and-remaining-useful-life(NASA’s Turbofan Engine )

forecasting-method-based-upon-gru-based-deep-learning-model

In this World Model, we specifically modified the RNN model by replacing the LSTM model with Bidirectional GRU. A typical advantage of using GRU is that it has less training parameters as compared to LSTM which eventually trains faster.

forecasting-sunspot-time-series-using-deep-learning.-

The number of sunspots increases and decreases over time in a regular, approximately 11-year cycle, called the sunspot cycle. The exact length of the cycle can vary. In this project, we study this time series using neural networks.

forecasting-temperature-bidirectional-lstm

Bidirectional LSTM model to forecast the minimum temperature on a daily level

forecasting-the-total-daily-covid--19-vaccination-accross-the-world

Performed EDA and introduced the Box-Cox transformation to stabilize the variance and made the time series

forecasting-with-time-series-imaging

time series forecasting with image

forecasting_air_pollution

Stacking a machine learning ensemble for multivariate time series forecasting, with the goal of predicting the one-period ahead PM 2.5 air pollution level, as published in Towards Data Science on Medium.com

forecasting_heatload

This projects develops several SARIMAX time series models and neural networks (LSTM, GRU, CNN) to predict the hourly heat demand in a district heating network.