Review Article

Climate Change and Small Businesses: A Systematic Review of Artificial Intelligence Applications for Climate Change Adaptation, Resilience Building, Risk Prediction, Decision Support, and Sustainable Business Transformation

Dr. S. Arulraj & Dr. P. Vellingiri

Page No. 01-09

 Abstract: Climate change has emerged as a major global challenge, significantly impacting small-scale businesses and startups, particularly in sectors such as agriculture, manufacturing, energy, and retail. These businesses often lack the financial and infrastructural resilience to cope with climate-induced disruptions, making them highly vulnerable to extreme weather events, fluctuating resource availability, and changing consumer behaviors. However, the integration of Machine Learning (ML) and Deep Learning (DL) algorithms presents new opportunities to mitigate risks and enhance adaptive strategies. This paper provides a comprehensive review of how ML and DL models, including Random Forest, Support Vector Machines (SVM), Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNNs), are being used to forecast climate-induced risks, optimize supply chains, reduce operational inefficiencies, and ensure business continuity. Additionally, real-world case studies demonstrate how AI-driven climate adaptation strategies have helped businesses improve decision-making and sustainability.

DOI: Under Assignment

Research Article

Prevalence of Self-Reported Halitosis Among Pregnant Women in Saudi Arabia - Its Impact on Oral Health-Related Quality of Life

Ghousia Sayeed, Layla Ahmad Alnakhli & Haifa Salman Alrobaia

Page No. 10-17

 Abstract: Background: Halitosis is a common oral condition that may be influenced by physiological and hormonal changes during pregnancy. Despite its potential psychosocial impact, data on its prevalence and effect on oral health-related quality of life (OHRQoL) among pregnant women in Saudi Arabia are limited. Aim: This study aimed to determine the prevalence of self-reported halitosis among pregnant women in Saudi Arabia and evaluate its impact on OHRQoL. Methods: An analytical cross-sectional study was conducted among pregnant women residing in Saudi Arabia. Data were collected using a structured Arabic questionnaire covering sociodemographic and obstetric variables, self-reported halitosis, and the validated Arabic Oral Health Impact Profile (OHIP-14). Associations were tested using chi-square and independent samples t-tests, and multivariable regression models were used to identify predictors of halitosis and OHRQoL. Results: A total of 178 participants were analyzed, and the prevalence of self-reported halitosis was 36.8%. Participants with halitosis had significantly higher mean OHIP-14 scores than those without halitosis (19.6 ± 7.9 vs. 11.2 ± 6.5; p<0.001). Lack of tongue cleaning (adjusted odds ratio [AOR] = 2.14; p=0.002) and poor self-rated oral hygiene (AOR = 1.87; p=0.011) were significant predictors of halitosis. Conclusion: Halitosis was common in this cohort and was associated with poorer OHRQoL. Integrating targeted oral hygiene counseling, especially tongue cleaning education, into antenatal care may reduce burden and improve maternal oral health outcomes.

DOI: Under Assignment

Research Article

Hybrid Salp Swarm-Genetic Algorithm Optimization for the Multidimensional Knapsack Problem: A Conceptual Review and Framework Synthesis

Asaju La’aro Bolaji, Sanfo Bala, Andrew Ishaku Wreford & Anagu Emmanuel John

Page No. 18-38

 Abstract: The Multidimensional Knapsack Problem (MKP) is a classical NP-hard combinatorial optimization problem used in wide variety of applications such as in logistics, cloud computing, manufacturing, telecommunications, scheduling and resource allocation. Metaheuristic algorithms are widely used because as the size of the problem and complexity of the optimization problem grows, the traditional exact methods are not able to compute them. In this regard, the Genetic Algorithm (GA) and Salp Swarm Algorithm (SSA) have received high interest due to their complementary search capabilities. The global exploration via the adaptive leader–follower mechanism in SSA, and the strong local exploitation by evolutionary operators in GA, complement each other well. In recent years, these algorithms are being incorporated into hybrid frameworks to accelerate the convergence process, preserve the diversity of the population and increase the quality of the solutions in large-scale optimization problems. But most of the current research is implementation oriented, and there are very few conceptual syntheses of concepts for the theoretical foundations, evolution, hybridization strategies and emerging developments of SSA–GA optimization for MKP. This paper discusses the complete overview of the conceptual review of Hybrid Salp Swarm–Genetic Algorithm optimization in Multidimensional Knapsack Problem. It outlines the development of the MKP, metaheuristic optimization, evolutionary computation, swarm intelligence and hybrid optimization and discusses the complementary nature of exploring/exploiting, constraint-handling and adaptive optimization mechanisms. The review also outlines the recent research trends, conceptual gaps, and suggests a common framework to inform the design of the scalable, adaptive, and computationally efficient hybrid optimization models. By consolidating current knowledge and outlining future research directions, this review provides a valuable reference for researchers and practitioners working in combinatorial optimization and intelligent resource allocation.

DOI: Under Assignment