Evaluation of therapeutic response to algorithm assisted improvement of oral mucosa damage in male AIDS patients DOI Open Access
Zhaolin Zhang, Shufeng Zhang, Jing Zhang

et al.

Molecular & cellular biomechanics, Journal Year: 2024, Volume and Issue: 21, P. 137 - 137

Published: Aug. 5, 2024

HIV/AIDS is now the biggest cause of mortality in Africa and fourth highest death globally. Half or more HIV-infected individuals as many 80% AIDS patients develop oral lesions. People living with may benefit from early testing, diagnosis, treatment if lesions are detected, they initial clinical characteristics infection strong indicators immunodeficiency. Oral candidiasis (OPC), hairy leukoplakia (OHL), Kaposi’s sarcoma (OKS), HIV-associated periodontal diseases were subjects this comprehensive review designed to assess available data for management these other common mucosa damage that linked HIV. Further exacerbating condition host variables such xerostomia, smoking, dental caries, prosthesis, diabetes, cancer treatments. A separate portion Worldwide Workshop discusses salivary gland illness injury does not have a reliable diagnostic approach. Improving diagnosis Mucosa male was primary goal work, which sought construct an Artificial Intelligence (AI) model high sensitivity. To demonstrate Gradient Boosting Regression (GBR) based method assessing efficacy treatments patients. Both investigation applications predictor. Results show that, compared existing models, suggested AI GBR methods can accurately predict deterioration This study significantly contributes profession by improving accuracy diagnoses providing useful information options.

Language: Английский

The hidden concept and the beauty of multiple “R” in the framework of waste strategies development reflecting to circular economy principles DOI
Antonis A. Zorpas

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 952, P. 175508 - 175508

Published: Aug. 15, 2024

Language: Английский

Citations

24
AI-Driven Sustainable Marketing in Gulf Cooperation Council Retail: Advancing SDGs Through Smart Channels DOI Creative Commons
Hanadi A. Salhab, Munif Zoubi, Laith T. Khrais

et al.

Administrative Sciences, Journal Year: 2025, Volume and Issue: 15(1), P. 20 - 20

Published: Jan. 7, 2025

This paper explores how AI drives GCC sector retail towards the fulfillment of UN SDGs. Analyzing a survey conducted on 410 executives, using PLS-SEM, this study underlines role in promoting operational efficiency, waste reduction, and consumer engagement with greener products. Key highlights include that AI-enabled marketing strategies improve adoption sustainable practices among consumers; AI-powered smart distribution channels enhance supply chain reduce carbon emissions, optimize logistics. For retailer, practical applications use demand forecasting to potentially waste, personalized efficiently promote products, deploying systems energy consumption. While these benefits are real, data privacy algorithmic bias remain valid concerns, thus underlining need for ethics transparency practice AI. The following provides actionable insights retailers align sustainability goals, fostering competitive advantages environmental responsibility.

Language: Английский

Citations

2
Internet of things and deep learning-enhanced monitoring for energy efficiency in older buildings DOI Creative Commons

M. Arun,

Gokul Gopan,

Savithiri Vembu

et al.

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: 61, P. 104867 - 104867

Published: July 27, 2024

Retrofitting older buildings for energy efficiency is paramount in today's sustainability and environmental awareness era. Older contribute greatly to waste since they typically lack new energy-efficient technology. Reducing carbon emissions, lowering bills, extending the life of these historic landmarks all depend on fixing inefficiency that plagues buildings. Despite advanced technologies' remarkable progress, potential Internet Things deep learning has not been unexplored. Major obstacles include expensive out-of-date infrastructure difficulty incorporating technology into historically significant structures. Existing research mostly ignored infrastructures' unique requirements limitations favour current or newly built services. In addition, comprehensive integrating with this specific environment lacking. Smart building management made possible by (IoT) learning. Architectural limitations, outmoded infrastructure, necessity non-invasive retrofitting solutions monitoring improvement This proposes combining IoT Deep Learning-enhanced Predictive Energy Modeling (DL-PEM) make an system can change adapt needs Data from sensors collected occupancy, temperature, lighting, equipment usage then analyzed using Learning models determine most efficient consumption patterns. Beyond its energy-saving potential, method many uses. Spotting structural problems before become major improve occupant comfort, reduce maintenance costs, pave way predictive maintenance. Integration grid demand response programs be facilitated, too, improving reliability power as a whole. Our Learning-based solution optimizes usage, reduces expenses, mitigates impact buildings, shown extensive simulation studies. The system's performance compared more conventional methods, flexibility evaluated various contexts.The experimental outcomes show suggested DL-PEM model increases forecasting analysis, thermal comfort optimization seasonal variation occupancy data analysis

Language: Английский

Citations

13
Deep learning-enabled integration of renewable energy sources through photovoltaics in buildings DOI Creative Commons

M. Arun,

Thanh Tuan Le, Debabrata Barik

et al.

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 105115 - 105115

Published: Sept. 1, 2024

Language: Английский

Citations

8
Fuzzy logic-supported building design for low-energy consumption in urban environments DOI Creative Commons

M. Arun,

Cristina Efremov, Van Nhanh Nguyen

et al.

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 105384 - 105384

Published: Oct. 1, 2024

Language: Английский

Citations

7
Economic, Policy, Social, and Regulatory Aspects of AI-Driven Smart Buildings DOI

M. Arun,

Debabrata Barik,

Sreejesh S.R. Chandran

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 111666 - 111666

Published: Dec. 1, 2024

Language: Английский

Citations

5
Economic Sustainability of Scrapping Electric and Internal Combustion Vehicles: A Comparative Multiple Italian Case Study DOI Creative Commons
Angelo Corallo, Alberto Di Prizio, Mariangela Lazoi

et al.

World Electric Vehicle Journal, Journal Year: 2025, Volume and Issue: 16(1), P. 32 - 32

Published: Jan. 9, 2025

The transition to sustainable mobility is one of the most pressing and complex challenges for automotive industry, with impacts that extend beyond mere reduction emissions. Electric vehicles, while at center this evolution, raise questions about consumption natural resources, such as lithium, copper, cobalt, their long-term sustainability. In addition, introduction advanced technologies, including artificial intelligence (AI) autonomous systems, brings new related management components materials needed production, creating a significant impact on supply chains. growing demand electric vehicles pushing industry rethink production models, favoring adoption circular economy principles minimize waste optimize use resources. To better understand implications transition, study adopts multiple case methodology, which allows in-depth exploration different contexts scenarios, analysis real cases dismantling recycling internal combustion engines (ICEs) (EVs). research includes financial simulation comparison revenues from ICE EV highlighting differences in value recycled effectiveness practices applied two types vehicles. This approach provides detailed overview economic benefits end life helping outline optimal strategies cost-effective future sector.

Language: Английский

Citations

0
Optimizing Stock Predictions With Bi-Directional LSTM and Levy Flight Fuzzy Social Spider Optimization (LFFSSO) DOI Open Access

Dhananjay Raghunathan,

M. Krishnamoorthi

International Journal on Semantic Web and Information Systems, Journal Year: 2025, Volume and Issue: 21(1), P. 1 - 25

Published: Jan. 10, 2025

Stock Market Prediction (SMP) has developed into a significant area of research, especially in recent decades. Major novelty the work is to develop an Evolutionary Bidirectional Long Short-Term Memory (EBi-LSTM) framework depends on investors' sentiment tweets (SM). In addition, three feature selectors: Chi-Square Test (CST), Analysis Of VAriance (ANOVA) technique and Mutual Information (MI) method are introduced for selecting most important features. Levy Flight Fuzzy Social Spider Optimization (LFFSSO) algorithm used optimal tuning parameters Bi-LSTM classifier. EBi-LSTM been worked datasets like Twitter, Stock, Weather, Coronavirus disease (COVID-19). The proposed model extends Valence Aware Dictionary sEntiment Reasoner (VADER), TextBlob, robustly optimized Encoder Representations from Transformers Retraining Approach (RoBERTa) analysis. Highest results 88.26%, 90.43%, 89.33% 92.63% precision, recall, F1-score accuracy attained by system.

Language: Английский

Citations

0
Advancements in Metal Recovery from Industrial Wastes: A Comprehensive Overview DOI
Mohd Aizudin Abd Aziz,

Muhammad Auni Hairunnaja,

Mohd Azmir Arifin

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Seagull optimization based deep belief network model for biofuel production DOI Open Access

Neetish Kumar,

S. Vijayabaskar,

L. Murali

et al.

Environmental Progress & Sustainable Energy, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 12, 2025

Abstract Biofuels have emerged as a promising alternative to conventional fossil fuels due their potential decrease greenhouse gas emissions and reliance on non‐renewable resources. Fluctuating energy costs policy interventions substantially increased global interest in biofuel production, imperative for population growth accelerated economic development. High computation complexity, low accuracy, other factors limited earlier works biological which were overcome by predictive modeling, approach enhance efficiency sustainability through precise forecasting process optimization. This article introduces an innovative production prediction model named the Seagull optimization based deep belief network (SGO‐DBN), comprising four major stages: data pre‐processing, reconstruction, prediction, SGO The proposed initially performs pre‐processing using empirical mode decomposition (EMD) technique. A DBN is used predict further optimized seagull algorithm‐based hyperparameter optimizer. rate consistently over six years with minimal divergence between predicted actual outcome. comparative analysis showed time of SGO‐DBN was lower than that existing techniques, while emphasized model's robust performance. Results numerous simulations conducted evaluate performance various metrics surpassed recent state‐of‐the‐art techniques.

Language: Английский

Citations

0