Search

Abstract Time series analysis and prediction have attained significant attention from the research community in the past few decades. However, the prediction accuracy of the models highly depends on the models’ learning process. In order to optimize resource usage, a better learning methodology, in terms of accuracy and learning time, is needed. In this context, the current research work proposes EvoLearn, a novel method to improve and optimize the learning process of neural-based models. The presented technique integrates the genetic algorithm with back-propagation to train model weights during the learning process. The fundamental idea behind the proposed work is to select the best components from multiple models during the training process to obtain an adequate model. To demonstrate the applicability of EvoLearn, the method is tested on the state-of-the-art neural models (namely MLP, DNN, CNN, RNN, and GRU), and performances are compared. Furthermore, the presented study aims to forecast two types of time series, i.e. air pollution and energy consumption time series, using the developed framework. In addition, the considered neural models are tested on two datasets of each time series type. From the performance comparison and evaluation of EvoLearn using a one-tailed paired T-test against the conventional back-propagation-based learning approach, it was found that the proposed method significantly improves the prediction accuracy.

Each states play pivotal roles in contributing to the economic performance of the nation. They have their own unique economic strengths, resources, and industries that contribute to the overall economic development. Terengganu, an east coast state in Malaysia has historically faced economic challenges, marked by a lag in development compared to other regions. The fundamental problem addressed is the potential correlation between educational attainment and the region’s economic growth, aiming to understand how advancements in education might serve as a catalyst for economic progress. The objective of this research is to empirically analyze the impact of educational achievement on the economic development in Terengganu. Utilizing secondary data sourced from the Department of Statistics Malaysia and Economy Planning Unit Terengganu spanning from 2006 to 2022, Autoregressive Distributed Lag (ARDL) model has been employed to estimate and understand the relationship between educational attainment and economic development. The findings suggested that educational achievement plays positive impact in heightening the economic development within the region. Education contributes to the development of human capital, fostering a skilled and knowledgeable populace capable of engaging in diverse economic activities. This, in turn, attracts investments and facilitates the emergence of industries and sectors that rely on a knowledgeable and skilled labour force. This study would provide valuable insights for policymakers and academicians to formulate targeted policies and initiatives, ultimately enhancing the economic development of the states, thus contribute to a prosperous Malaysia.

Background Occupational diseases are one of the most important health problems related to employment However, in Malaysia, there are few epidemiological studies discussing these issues, especially among workers in the industry. For that, this study aimed to screen workers from high-risk industrial sectors, identify hazards in the workplace and recommend improvement measures in the workplace to prevent occupational diseases.Methods and analysis This is a 3-year project in which a survey of 100 000 workers from all 13 states in Malaysia will be conducted using a web-based screening tool that is comprised of two parts: occupational disease screening tool and hazard identification, risk assessment and risk control method. Data will be collected using a multistage stratified sampling method from 500 companies, including seven critical industrial sectors. The independent variables will be sociodemographic characteristics, comorbidities, previous medical history, high-risk behaviour and workplace profile. The dependent variable will be the types of occupational diseases (noise-induced hearing loss, respiratory, musculoskeletal, neurotoxic, skin and mental disorders). Subsequently, suggestions of referral for medium and high-risk workers to occupational health clinics will be attained. The approved occupational health service clinics/providers will make a confirmatory diagnosis of each case as deemed necessary. Subsequently, a walk-through survey to identify workplace hazards and recommend workplace improvement measures to prevent these occupational diseases will be achieved. Both descriptive and inferential statistics will be used in this study. Simple and adjusted binary regression will be used to find the determinants of occupational diseases.Ethics and dissemination This study has been approved by the MARA University of Technology Research Ethics Board. Informed, written consent will be obtained from all study participants. Findings will be disseminated to the Department of Occupational Health and Safety, involved industries, and through peer-reviewed publications.

Objectives Occupational skin diseases (OSDs) pose significant risks to the health and well-being of restaurant workers. However, there is presently limited evidence on the burden and determinants of OSDs among this occupational group. This research aims to estimate the prevalence and associated factors of suspected OSDs among restaurant workers in Peninsular Malaysia.Design A secondary data analysis of the 2023 Registry of Occupational Disease Screening (RODS) was performed. The RODS survey tool, which included the Nordic Occupational Skin Questionnaire, a symptoms checklist and items on work-relatedness, was used to screen for OSDs. Logistic regression analyses were performed to identify associated factors.Setting and participants Restaurant workers (n=300) registered in RODS from February 2023 to April 2023, aged 18 years and above and working in restaurants across Selangor, Melaka and Pahang for more than 1 year, were included in the study, whereas workers who had pre-existing skin diseases were excluded.Results The prevalence of suspected OSDs among study participants was 12.3%. Higher odds of suspected OSDs among study participants were observed among those exposed to wet work (adjusted OR (AOR) 22.74, 95% CI 9.63 to 53.68) and moderate to high job stress levels (AOR 4.33, 95% CI 1.80 to 10.43).Conclusions These findings suggest that OSDs are a significant occupational health problem among restaurant workers. Interventions targeting job content and wet work may be vital in reducing OSDs among this group of workers.

Bidirectional DC-DC converters (BDCs) are certainly an important power electronic converter for managing bidirectional power flow in various applications. It offers the ability to flow power in both directions, which is useful in systems with renewable energy sources and energy storage. BDCs are becoming increasingly important in various applications, including renewable energy systems, electric vehicles, and energy storage. The development of new BDC topologies and control strategies is expected to further improve their efficiency and performance. Non-Isolated Bidirectional DC-DC Converters (NBDCs) and Isolated Bidirectional DC-DC Converters (IBDCs) are the two main types of BDCs with different isolation properties and trade-offs in terms of size, cost and performance. Topological classification of BDCs further distinguishes various BDC types based on their configurations and voltage-boosting techniques. IBDCs are preferred over NBDCs due to high-power applications, and wide voltage range with higher efficiency; the performance of IBDCs is improving day by day. To provide a framework for comparison in implementing novel configurations or identifying the best converter for a given application, this study is concentrated on each topology and its usual applications. Soft switching converters are also discussed pointed to Resonant Power Converters (RPCs) for the application into Electric Vehicles (EVs). It is worth noting that the choice of BDC depends on the specific requirements of the application, such as power level, voltage range, efficiency, and cost. A detailed comparison, application, advantage and disadvantage table can be useful in comparing the characteristics of different BDCs and selecting the most suitable one.

In industrial environments, efficient indoor transportation is a cornerstone of streamlined operations. However, the availability of high-end robotic transportation systems often poses a challenge for small-scale manufacturers due to their prohibitive costs. Addressing this disparity, this research introduces “Pony”, an innovative and cost-effective semi-autonomous self-driven robotic system tailored for indoor transportation purposes. Built upon a microcontroller-based platform, Pony harnesses low-cost technology to create and store m-graphs effectively, facilitating seamless navigation within indoor facilities. Moreover, the study presents a novel Pruned-BFS (P-BFS) algorithm designed to efficiently traverse m-graphs, outperforming conventional graph-traversal approaches. Furthermore, the experimental validation in the study encompasses a comprehensive evaluation of Pony’s performance across a range of scenarios. Randomly generated graphs, varying in complexity from 26 to 200 nodes, serve as the testing ground. Notably, four distinct algorithms—Breadth First Seach (BFS), Depth First Search (DFS), Iterative DFS (ID), and P-BFS are put through their paces during numerous random walks on each graph. A meticulously executed full factorial design of the experiment demonstrates statistical significance in execution time, and the number of nodes traversed, further underscoring Pony’s prowess. By converging affordability, AI-driven intelligence, and robust performance, Pony heralds a promising evolution in the landscape of indoor robotic transportation.

Probability estimation plays a pivotal role across diverse domains, particularly in scenarios where the objective is to select non-repetitive units one at a time, with the option of replacement, from a predefined set of units. Traditional probability calculations in this scenario pose three challenges: the number of floating-point operations to be executed is directly proportional to the chosen set size, susceptibility to floating-point precision errors, and exponential growth in storage needs with increasing number of chosen units. In this scenario, the presented work aims to develop SPM: a sigmoid function-based model that estimates probabilities for such problems with a fixed number of calculations (independent of the input parameter), achieving a constant time complexity algorithm. The research methodology involves generating probability data points, selecting the optimal sigmoid function, augmenting additional data to enhance parameter estimation, identifying parameter estimation equations, and evaluating the model. Moreover, the study’s second objective includes training and comparing six established machine learning-based models (including Decision Tree, Random Forest, Support Vector, Linear Regression, Nearest Neighbour, and Artificial Neural Network) against the proposed SPM. The rigorous assessment of the model’s performance, utilising metrics including RMSE, MAE and $r^{2}$ across a wide range of scenarios involving varying values of the total units, affirms the model’s accuracy and resilience. The study findings can improve decision-making processes in various domains, including statistics, cryptography, machine learning and optimisation, by offering a faster, more adaptable solution for probability estimation in units’ selection with replacement.

Abstract Background Recent pandemics have had far-reaching effects on the world’s largest economies and amplified the need to estimate the full extent and range of socioeconomic impacts of infectious diseases outbreaks on multi-sectoral industries. This systematic review aims to evaluate the socioeconomic impacts of airborne and droplet-borne infectious diseases outbreaks on industries. Methods A structured, systematic review was performed according to the PRISMA guidelines. Databases of PubMed, Scopus, Web of Science, IDEAS/REPEC, OSHLINE, HSELINE, and NIOSHTIC-2 were reviewed. Study quality appraisal was performed using the Table of Evidence Levels from Cincinnati Children’s Hospital Medical Center, Joanna Briggs Institute tools, Mixed Methods Appraisal Tool, and Center of Evidence Based Management case study critical appraisal checklist. Quantitative analysis was not attempted due to the heterogeneity of included studies. A qualitative synthesis of primary studies examining socioeconomic impact of airborne and droplet-borne infectious diseases outbreaks in any industry was performed and a framework based on empirical findings was conceptualized. Results A total of 55 studies conducted from 1984 to 2021 were included, reporting on 46,813,038 participants working in multiple industries across the globe. The quality of articles were good. On the whole, direct socioeconomic impacts of Coronavirus Disease 2019, influenza, influenza A (H1N1), Severe Acute Respiratory Syndrome, tuberculosis and norovirus outbreaks include increased morbidity, mortality, and health costs. This had then led to indirect impacts including social impacts such as employment crises and reduced workforce size as well as economic impacts such as demand shock, supply chain disruptions, increased supply and production cost, service and business disruptions, and financial and Gross Domestic Product loss, attributable to productivity losses from illnesses as well as national policy responses to contain the diseases. Conclusions Evidence suggests that airborne and droplet-borne infectious diseases have inflicted severe socioeconomic costs on regional and global industries. Further research is needed to better understand their long-term socioeconomic impacts to support improved industry preparedness and response capacity for outbreaks. Public and private stakeholders at local, national, and international levels must join forces to ensure informed systems and sector-specific cost-sharing strategies for optimal global health and economic security.

IntroductionWith increasing demand for food and changing environmental conditions, a better understanding of the factors impacting wheat yield is essential for ensuring food security and sustainable agriculture. By analyzing the effect of multiple factors on wheat yield, the presented research provides novel insights into the potential impacts of climate change on wheat production in India. In the present study, datasets consisting of countrywide environmental and agronomic factors and wheat yield were collected. In addition, the study also analyzes the effect of information demand of farmers on production.MethodologyThe study employs a regional analysis approach by dividing the country into five zonal clusters: Northern Hills, Central India, Indo-Gangetic Plains, North-Eastern India, and Peninsular India. Correlation and Principal Component Analysis (PCA) were performed to uncover the month-wise key factors affecting wheat yield in each zone. Furthermore, four Machine Learning/Deep Learning-based models, including XGBoost, Multi-layer Perceptron (MLP), Gated Recurrent Unit (GRU), and 1-D Convolutional Neural Network (CNN), were developed to estimate wheat yield. This study estimated partial derivatives for all factors using Newton's Quotient Technique, a numerical method-based approach.ResultsThe analysis focused on applying this technique to the best-performing wheat yield estimation model, which was the GRU-based model (with RMSE and MAE of 0.60 t/ha and 0.46 t/ha, respectively).DiscussionIn the later sections of the article, multiple policy recommendations are communicated based on the extracted insights. The results of the presented research help inform decision-making regarding the development of strategies and policies to mitigate the impacts of climate change on wheat production in India.

The use of distributed energy resources (DER) programs, which include separate renewable energy (RE) programs, has expanded in residential as well as commercial structures as an outcome of recent technological developments. The virtual power plant (VPP) may improve the security and reliability of an electricity grid's operations through including energy storage, changeable loads, and distributed energy resources (DER), among other characteristics. Consequently, a growing number of scholars tend to focus on VPP and providing recommendations for its improvement. In order to facilitate the incorporation of distributed generation into electricity distribution systems, cutting-edge management ideas for facilities have emerged in the last few years. As a result, it is now more crucial than ever to improve management abilities for the combining of dispersed energy output and consumption using various virtual power plants (VPPs). To increase operational profits, it's crucial to make use of their capacity to play a role in power markets. This work provides a classification scheme for, and an in-depth analysis of, recent studies that provide VPP models featuring interactions with various forms of electricity markets. The objective of this article is to find out which VPP strategy will yield the greatest possible return in each legislative scenario. These consist of the model's design, strategies for resolving complex mathematical problems, involvement in various marketplaces, and the application of the suggested models to real-world case studies. The research has been evaluated, and it has been concluded that contemporary models are more comprehensive and realistic. This article additionally elaborates on and emphasizes the VPP concept from other researchers' findings. Moreover, a number of prevalent VPP projects from throughout the globe are included. The VPP research also addresses some potential challenges and recommendations for prospective growth.

Solar photovoltaic (SPV) is one of the most common renewable energy sources used at present. The major issue with renewable energy resources is power quality to meet the growing energy demand. In recent times reliability and flexibility of energy supply are also associated with the quality of power. The issues attached with line faults, voltage sag/swell, harmonics in supply and flicker are the key concerns for poor power quality. The new scenario is designed to challenge electrical resources like generation, transmission and distribution. Considering renewable energy in the existing power system requires additional research and analysis to synchronize new components. From this point of view, many power electronics converters and switching devices are designed to increase the reliability and efficiency of the system. Similarly, solar PV system requires a maximum power point tracker to extract the power upto the maximum extent. It consists of two stages: DC to DC converter and Pulse Width Modulation controlling phase. A multi-level inverter (MLI) is used to enhance the power quality of the overall system. It reduces the harmonics distortion and stabilizes the system near the unity power factor. This paper comprehensively analyses the cascaded H-bridge Multilevel Inverter associated with the fuzzy logic controller (FLC) and SPV system. The simulation results are compared with the 3-level and five levels Multilevel Inverter.