Analyses on Usage of MLP Regression with WSN Data for Predicting Room Occupancy DOI
Dalibor Dobrilović, Răzvan Bogdan, Visnja Ognjenovic

et al.

Published: Oct. 26, 2023

The recent events in the world, such as Covid-19 pandemics raise importance of tracking room occupancy. estimating number persons present is not related only to epidemic scenarios and attempts avoid people contact with goal stop spreading diseases. This can be expanded when we want presence a higher certain areas offer their safety security for variety reasons, e.g. employee welfare, hazardous material presence, etc. Although there are numerous approaches tackle this problem, paper deals usage Wireless Sensor Networks (WSN), standard or common nodes set estimate targeted space.The significant factor that may facilitate deployment system occupancy monitoring possibility being upgraded upon existing Network (WSN). presents analysis using Multi-layer Perceptron Regression (MLPR) on dataset collected WSN. MLPR implemented Python scikit-learn open-source machine learning library chosen basis positive experience other good predicting results. methodology presented here predicts based light, temperature, sound, CO 2 , PIR motion sensor data.

Language: Английский

Multi-objective optimization for sustainable and economical polycarbonate production with reaction kinetics inference for real-world industrial process DOI

Eunbyul Lee,

Minsu Kim, Il Moon

et al.

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 490, P. 151484 - 151484

Published: April 25, 2024

Language: Английский

Citations

6
Predicting absolute adsorption of CO2 on Jurassic shale using machine learning DOI Creative Commons

Changhui Zeng,

Shams Kalam, Haiyang Zhang

et al.

Fuel, Journal Year: 2024, Volume and Issue: 381, P. 133050 - 133050

Published: Oct. 11, 2024

Language: Английский

Citations

6
Study on a cationic agent-based salt-free reactive dyeing process for cotton knit fabric and comparison with a traditional dyeing process DOI Creative Commons
Joyjit Ghosh,

Nishat Sarmin Rupanty

Heliyon, Journal Year: 2023, Volume and Issue: 9(9), P. e19457 - e19457

Published: Sept. 1, 2023

Since the majority of reactive dyes only have a moderate affinity for cotton, significant amounts electrolytes are frequently needed to cause tiredness. As result, wastewater contains salt and dye, increasing salinity rivers has an effect on delicate biochemistry aquatic life. The aim study was find sustainable dyeing process cotton knit fabric using EPTMAC (2, 3-epoxypropyl trimethyl ammonium chloride) as cationic agent comparison (salt free dyeing) with regular (dyeing salt). For this purpose, samples were dyed following salt. Afterwards, color fastness (wash rubbing), spectrophotometric evaluation, bursting strength test, analysis dye bath discharge water Scanning Electron Microscope (SEM) image carried out. Moreover, consumption also evaluated both process. In terms fastness, cationized showed no change slight loss in depth (rating 4–5) wash rubbing fastness. From it found that appeared darker less yellowish tone. case strength, black, hot pink, light pink colored fabrics possessed strengths 287 kPa, 337 440 correspondingly. After water, Biological Oxygen Demand (BOD), Chemical (COD), Total Dissolved Solids (TDS) value 45%, 39%, 54% greater than respectively. Cationized (DO) 6.39 mg/l, which within acceptable limit. SEM asserted had consistent dispersion, adhesion, anomalies. Considering consumption, 37%, 27% 23% amount required dark, medium shade due fewer washes after elimination fixing steps. addition that, total cost chemical utility use, shorter time needed. Cationic is practice offers numerous advantages when compared low environmental pollution.

Language: Английский

Citations

12
A Systematic Review of Polluting Processes Produced by the Textile Industry and Proposals for Abatement Methods DOI Creative Commons
Enzo Conde Miranda, Paola Gabriel Prado, César León-Velarde

et al.

Textile & Leather Review, Journal Year: 2024, Volume and Issue: 7, P. 88 - 103

Published: Jan. 19, 2024

The textile industry is one of the most polluting industries worldwide because its processes that entail excessive use water and chemicals, resulting in effluents that, turn, are not treated controlled correctly. This review aims to identify efficient methods reduce footprint. PICO method was used define search equation obtain studies based on topic, a total 4783 articles; then, PRISMA statement carefully select studies, which 32 articles met inclusion criteria. industry's supply chain presents high pollution levels, especially dyeing process, with percentage 33% effluents, since they toxic chemicals such as ammonia, sulphide, lead. Therefore, study analyzes physical (hydrodynamic cavitation flocculation), (electrocoagulation, EC-EO, EC-EF), biological (degradation assisted by bacteria) treat wastewater. After analysis above for treating wastewater, electrocoagulation combined electro-oxidation (EC-EO) obtained highest efficiency rate 88% COD removal 100% colour removal.

Language: Английский

Citations

4
A review of deep learning and artificial intelligence in dyeing, printing and finishing DOI
Nilesh P. Ingle, Warren J. Jasper

Textile Research Journal, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 18, 2024

This review focuses on the transformative applications of deep learning and artificial intelligence in textile dyeing, printing, finishing. In topics span color prediction, color-based classification, dyeing recipe pattern recognition, nuanced domain fabric defect detection. machine center around detection printed fabrics, generation novel patterns, critical task detecting defects textiles. finishing prediction thermosetting parameters is discussed. Artificial neural networks, diverse convolutional network variations like AlexNet, traditional approaches including support vector regression, principal component analysis, XGBoost, generative such as adversarial well genetic algorithms all find application this multifaceted exploration. At its core, interest to use these methodologies because need minimize repetitive time-consuming manual tasks, curtail prototyping costs, promote process automation. The unravels a plethora innovative architectures frameworks, each tailored address specific challenges. However, persistent hurdle looms – scarcity data, which remains significant impediment. While unveiling collection research findings, also spotlights inherent challenges implementing solutions printing domain.

Language: Английский

Citations

2
Modification of melamine sponge by solid-phase esterification of citric acid-polyvinyl alcohol and its selective adsorption for cationic dyes DOI

Lianyong Wu,

Yuyan Li,

Zhigang Jia

et al.

Inorganic Chemistry Communications, Journal Year: 2024, Volume and Issue: 161, P. 112004 - 112004

Published: Jan. 5, 2024

Language: Английский

Citations

1
Towards environmental protection and safety coloration process in wool fibers: Role of disperse reactive dyes structure DOI

Daixuan Gong,

Huanda Zheng, Pengfei Lv

et al.

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 186, P. 874 - 883

Published: March 26, 2024

Language: Английский

Citations

1
Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions DOI Creative Commons
Seval Ene Yalçın

Systems, Journal Year: 2024, Volume and Issue: 12(12), P. 528 - 528

Published: Nov. 27, 2024

The reduction of greenhouse gas emissions, in order to effectively address the issue climate change, has critical importance worldwide. To achieve this aim and implement necessary strategies policies, projection emissions is essential. This paper presents a forecasting framework for based on advanced machine learning algorithms: multivariable linear regression, random forest, k-nearest neighbor, extreme gradient boosting, support vector, multilayer perceptron regression algorithms. algorithms employ several input variables associated with emission outputs. In evaluate applicability performance developed framework, nationwide statistical data from Turkey are employed as case study. dataset study includes six annual sectoral total CO2 eq. output variables. provides scenario-based approach future forecasts sector-based analysis country considering multiple present indicates that stated can be successfully applied emissions.

Language: Английский

Citations

1
Analyses on Usage of MLP Regression with WSN Data for Predicting Room Occupancy DOI
Dalibor Dobrilović, Răzvan Bogdan, Visnja Ognjenovic

et al.

Published: Oct. 26, 2023

The recent events in the world, such as Covid-19 pandemics raise importance of tracking room occupancy. estimating number persons present is not related only to epidemic scenarios and attempts avoid people contact with goal stop spreading diseases. This can be expanded when we want presence a higher certain areas offer their safety security for variety reasons, e.g. employee welfare, hazardous material presence, etc. Although there are numerous approaches tackle this problem, paper deals usage Wireless Sensor Networks (WSN), standard or common nodes set estimate targeted space.The significant factor that may facilitate deployment system occupancy monitoring possibility being upgraded upon existing Network (WSN). presents analysis using Multi-layer Perceptron Regression (MLPR) on dataset collected WSN. MLPR implemented Python scikit-learn open-source machine learning library chosen basis positive experience other good predicting results. methodology presented here predicts based light, temperature, sound, CO 2 , PIR motion sensor data.

Language: Английский

Citations

2