A Reversible Automatic Selection Normalization (RASN) Deep Network for Predicting in the Smart Agriculture System

Agronomy, Journal Year: 2022, Volume and Issue: 12(3), P. 591 - 591

Published: Feb. 27, 2022

Due to the nonlinear modeling capabilities, deep learning prediction networks have become widely used for smart agriculture. Because sensing data has noise and complex nonlinearity, it is still an open topic improve its performance. This paper proposes a Reversible Automatic Selection Normalization (RASN) network, integrating normalization renormalization layer evaluate select module of model. The accuracy been improved effectively by scaling translating input with learnable parameters. application results show that model good ability adaptability greenhouse in Smart Agriculture System.

Language: Английский

---

BE-LSTM: An LSTM-Based Framework for Feature Selection and Building Electricity Consumption Prediction on Small Datasets

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111910 - 111910

Published: Jan. 1, 2025

Language: Английский

---

Fuzzy adaptive-normalized deep encoder-decoder network: Medium and long-term predictor of temperature and humidity in smart greenhouses

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 226, P. 109480 - 109480

Published: Sept. 29, 2024

Language: Английский

---

Assessment of sanitation service gap in urban slums for tackling COVID-19

Journal of Urban Management, Journal Year: 2021, Volume and Issue: 10(3), P. 230 - 241

Published: July 8, 2021

Coronavirus disease 2019 (COVID-19), caused by Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), has been declared as a global pandemic the World Health Organization (WHO). As is highly infectious, Global South countries are in vulnerable situation with high urban population density and lack of Water, Sanitation, Hygiene (WASH) services. The for slum dwellers low-income group clusters becoming worse. Lack health sanitation service availability already an issue them before beginning pandemic. So, it predictable that adopting this massive critical challenge them. This paper assesses gap slums, which become severe to tackle due COVID-19. study areas research Ranarmath Khema Khulna city, Bangladesh. SERVQUAL model used identify quality available these informal residential settlements. interpretation questionnaire survey data from two slums reveals one lacks Assurance Empathy, where other Tangibility Responsiveness. However, Tangibility, Reliability, Responsiveness condition both flawed latrine functionalities services concerned authorities. incompatibility identified evaluating WHO's different management policy concludes like handwashing facilities water supply directly related COVID-19 prevention indigent slums.

Language: Английский

---

A hybrid CNN-BiLSTM approach for remaining useful life prediction of EVs lithium-Ion battery

Measurement and Control, Journal Year: 2022, Volume and Issue: 56(1-2), P. 371 - 383

Published: Sept. 23, 2022

For accelerating the technology development and facilitating reliable operation of lithium-ion batteries, accurate prediction for battery remaining useful life (RUL) are both critical. In this paper, a 1D CNN-BiLSTM method is proposed to extract RUL Electric Vehicles (EVs). By using one dimensional convolutional neural network (1D CNN) bidirectional long short-term memory (BiLSTM) simultaneously, selecting ELU activation function apply layer, hybrid improve accuracy stability prediction. The CNN used fully mine deep features SOH data, while BiLSTM adopted study in two directions, output through dense layer. To verify effectiveness method, data National Aeronautics Space Administration (NASA) utilized make some comparisons among RNN model, LSTM model model. results show that has higher generalization ability than others.

Language: Английский

---

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

Electric Power Systems Research, Journal Year: 2022, Volume and Issue: 216, P. 109065 - 109065

Published: Dec. 8, 2022

Language: Английский

---

Time series analysis in compressor-based machines: a survey

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: March 5, 2025

Language: Английский

---

Considering Active Support Capability and Intelligent Soft Open Point for Optimal Scheduling Strategies of Urban Microgrids

Processes, Journal Year: 2025, Volume and Issue: 13(5), P. 1338 - 1338

Published: April 27, 2025

With the increasing penetration of renewable energy in power system, how to ensure normal operation urban microgrids is gradually receiving attention. It necessary evaluate overall active support capability and provide optimal strategies for microgrids. The paper proposes an active–reactive coordinated optimization method with a high proportion energy. Firstly, quantification model established capacity reactive microgrids, respectively. Then, collaborative model, which considers multiple types distributed resources, scheduling Consequently, platform integrating evaluation regulation functions constructed enable resources resource operations. This aims solve key technical challenges safe new simulation results demonstrate that proposed can reduce comprehensive operating costs by up 19.86% decrease voltage deviation rate 7.25%, simultaneously improving both economic efficiency operational security.

Language: Английский

---

A Hybrid Forecast Model for Household Electric Power by Fusing Landmark-Based Spectral Clustering and Deep Learning

Sustainability, Journal Year: 2022, Volume and Issue: 14(15), P. 9255 - 9255

Published: July 28, 2022

Household power load forecasting plays an important role in the operation and planning of grids. To address prediction issue household consumption grids, this paper chooses a time series historical as feature variables uses landmark-based spectral clustering (LSC) deep learning model to cluster predict dataset, respectively. Firstly, investigated data are reshaped into matrix all missing entries recovered by completion. Secondly, samples divided three clusters LSC method according periodicity regularity consumption. Then, each expanded via bootstrap aggregating technique. Subsequently, combination convolutional neural network (CNN) long short-term memory (LSTM) is employed The goal CNN extract features from input sequence learning, LSTM aims train Finally, performance LSC–CNN–LSTM compared with several other models verify its reliability effectiveness field load. experimental results show that proposed hybrid superior state-of-the-art techniques performance.

Language: Английский

---

Short-term load forecasting based on IPSO-DBiLSTM network with variational mode decomposition and attention mechanism

Applied Intelligence, Journal Year: 2022, Volume and Issue: 53(10), P. 12701 - 12718

Published: Sept. 30, 2022

Language: Английский

---