Optimization and prediction in the early design stage of office buildings using genetic and XGBoost algorithms

Building and Environment, Journal Year: 2022, Volume and Issue: 218, P. 109081 - 109081

Published: April 14, 2022

Language: Английский

---

Gross electricity consumption forecasting using LSTM and SARIMA approaches: A case study of Türkiye

Energy, Journal Year: 2023, Volume and Issue: 284, P. 128575 - 128575

Published: Aug. 1, 2023

Language: Английский

---

Natural gas consumption forecasting using a novel two-stage model based on improved sparrow search algorithm

Journal of Pipeline Science and Engineering, Journal Year: 2024, Volume and Issue: 5(1), P. 100220 - 100220

Published: Aug. 23, 2024

The foundation of natural gas intelligent scheduling is the accurate prediction consumption (NGC). However, because its volatility, this brings difficulties and challenges in accurately predicting NGC. To address problem, an improved model developed combining sparrow search algorithm (ISSA), long short-term memory (LSTM), wavelet transform (WT). First, performance ISSA tested. Second, NGC divided into several high- low-frequency components applying different layers Coilfets', Fejer-Korovkins', Symletss', Haars', Discretes' orders. In addition, LSTM applied to forecast decomposed view one- multi-step, hyper-parameters are optimized by ISSA. At last, final results reconstructed. research indicate that: (1) Comparing other machine algorithms (e.g. fuzzy neural network), convergence speed stability stronger standard deviation mean; (2) better than that forecasting models; (3) single-step superior two-, three-, four- step; (4) computational load proposed highest compared models, accuracy still excellent on extended time series.

Language: Английский

---

An Ensemble Approach to Predict a Sustainable Energy Plan for London Households

Sustainability, Journal Year: 2025, Volume and Issue: 17(2), P. 500 - 500

Published: Jan. 10, 2025

The energy sector plays a vital role in driving environmental and social advancements. Accurately predicting demand across various time frames offers numerous benefits, such as facilitating sustainable transition planning of resources. This research focuses on consumption using three individual models: Prophet, eXtreme Gradient Boosting (XGBoost), long short-term memory (LSTM). Additionally, it proposes an ensemble model that combines the predictions from all to enhance overall accuracy. approach aims leverage strengths each for better prediction performance. We examine accuracy Mean Absolute Error (MAE), Percentage (MAPE), Root Square (RMSE) through means resource allocation. investigates use real data smart meters gathered 5567 London residences part UK Power Networks-led Low Carbon project Datastore. performance was recorded follows: 62.96% Prophet model, 70.37% LSTM, 66.66% XGBoost. In contrast, proposed which XGBoost, achieved impressive 81.48%, surpassing models. findings this study indicate enhances efficiency supports towards future. Consequently, can accurately forecast maximum loads distribution networks households. addition, work contributes improvement load forecasting networks, guide higher authorities developing plans.

Language: Английский

---

An Improved Neural Network Based on SENet for Sleep Stage Classification

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2022, Volume and Issue: 26(10), P. 4948 - 4956

Published: March 8, 2022

Sleep staging is an important step in analyzing sleep quality. Traditional manual analysis by psychologists time-consuming. In this paper, we propose automatic model with improved attention module and hidden Markov (HMM). The driven single-channel electroencephalogram (EEG) data. It automatically extracts features through two convolution kernels different scales. Subsequently, based on Squeeze-and-Excitation Networks (SENet) will perform feature fusion. neural network give a preliminary stage the learned features. Finally, HMM apply transition rules to refine classification. proposed method tested sleep-EDFx dataset achieves excellent performance. accuracy Fpz-Cz channel 84.6%, kappa coefficient 0.79. For Pz-Oz channel, 82.3% 0.76. experimental results show that mechanism plays positive role And our improves classification addition, applying helps improve performance, especially N1, which difficult identify.

Language: Английский

---

Air quality forecasting with hybrid LSTM and extended stationary wavelet transform

Building and Environment, Journal Year: 2022, Volume and Issue: 213, P. 108822 - 108822

Published: Jan. 24, 2022

Language: Английский

---

Dynamic energy efficient task offloading and resource allocation for NOMA-enabled IoT in smart buildings and environment

Building and Environment, Journal Year: 2022, Volume and Issue: 226, P. 109513 - 109513

Published: Aug. 30, 2022

Language: Английский

---

Collaborative deep learning framework on IoT data with bidirectional NLSTM neural networks for energy consumption forecasting

Journal of Parallel and Distributed Computing, Journal Year: 2022, Volume and Issue: 163, P. 248 - 255

Published: Jan. 31, 2022

Language: Английский

---

Forecasting turning points in stock price by applying a novel hybrid CNN-LSTM-ResNet model fed by 2D segmented images

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 116, P. 105464 - 105464

Published: Oct. 2, 2022

Language: Английский

---

A deep learning framework using multi-feature fusion recurrent neural networks for energy consumption forecasting

Applied Energy, Journal Year: 2023, Volume and Issue: 348, P. 121563 - 121563

Published: July 15, 2023

Language: Английский

---