IEEE

Enhancing EV Charging Station Integration: A Hybrid ARIMA-LSTM Forecasting and Optimization Framework

Abstract: Electric vehicles (EVs) offer substantial environmental benefits but introduce challenges to power grids due to capacity limitations. Effective deployment and coordination of EV Charging ...
GitHub

Step-by-Step ARIMA Model Building

The study explores the effectiveness of the ARIMA(3,1,3) model in predicting market trends, specifically accounting for macroeconomic shifts like the 2026 CPI base year updates. Stationarity ...
GitHub

Time Series Analysis with LSTM, ARIMA, Prophet, and Anomaly Detection

├── src/ # Source code modules │ ├── lstm_model.py # LSTM implementation with PyTorch │ ├── forecasting_models.py # ARIMA, Prophet, and statistical models │ ├── anomaly_detection.py # Anomaly ...
BMJ

Global, regional, and national characteristics of the main causes of increased disease burden due to the covid-19 pandemic: time-series modelling analysis of global burden of ...

Absolute and relative rate differences were calculated, along with their 95% confidence intervals (95% CIs), between the observed and expected rates for 174 causes of increases in incidence, ...
Scientific Research Publishing

Brownlee, J. (2018). Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery.

ABSTRACT: Gender balance is a key part of the Australian identity, for creating diverse workplaces and fostering social cohesion throughout Australia. This study aims to provide a comprehensive ...
ascopubs.org

Time Series Prediction of Lung Cancer Death Rates on the Basis of SEER Data

Three models for yearly time series predictions were built: autoregressive integrated moving average (ARIMA), simple exponential smoothing (SES), and Holt's double expansional smoothing (HDES) models.