Search

South African pulp and paper mills have encountered frequent breakdowns of centrifugal pumps, resulting in considerable production losses. A case study was conducted to determine the factors contributing to these failures and devise ways to enhance pump reliability. Data were collected through questionnaires and operational records. The study revealed that inadequate maintenance, misalignment of pump components, lack of lubrication, improper baseplate installation, subpar sealing arrangements, inadequate design of the pumping system, and foreign materials entering the system were the primary causes of pump failure. To improve reliability, this study suggests employing machine learning methods to select the optimal maintenance strategy and provide internal maintenance personnel with training in condition monitoring systems. This will enable both pulp and paper mills and pump manufacturers to identify blind spots and improve the dependability of centrifugal pumps. [ABSTRACT FROM AUTHOR]

Assuring product quality has been always a main concern of a production process. PT IGP Internasional Sleman is a company that produces Printed Tissue Paper. This company's defect tolerance limit is 2%. Based on early observations, the defect rate reaches 5.2%. The Eight Disciplines (8D) method was used to solve the problem. First, the team was built to engage all related divisions in the project. Then, Failure Mode and Effects Analysis (FMEA) was carried out to sort the problems. Root Cause Analysis using Fishbone diagram was also used to find the causes. Proposed improvements to reduce defects have been implemented. There are adding Rotogravure machine operators, conducting supervision/inspection by production leader, and providing socialization related to the importance of product quality and production. The implementation has successfully reduced the defects to fulfill the company's standard. [ABSTRACT FROM AUTHOR]

This study investigated the trends in quality 4.0 and what they mean for various industries. Scopus was the main database used in the systematic literature review. Only papers written in English that directly addressed the study's research objectives and were published between 2017 and 2023 were included in the analysis. The number of papers on quality 4.0 has increased exponentially over the years. The majority of papers came from the TQM Journal, followed by the International Journal of Quality Research and Sustainability Switzerland. In our investigation into what quality 4.0 means for industries, we used a sample of 14 papers. We used qualitative data analysis known as thematic coding, and through inductive thematic coding, we were able to identify 99 codes that were associated with quality 4.0. The study found that quality 4.0 is a broad term encompassing nearly all aspects of quality management, including big data, digital quality management, connectivity, cybernetics, managing disruptions, simulation, and more. According to the study, quality 4.0 is unlikely to change the traditional quality management strategy; rather, it will make things smarter, faster, and more intelligent. The study's findings were consistent with previous research and had both reliability and validity. [ABSTRACT FROM AUTHOR]

In the current era, one of the key challenges in utilizing the Holt-Winters Method of forecasting is the accurate selection of smoothing coefficients. To address this issue, researchers have explored an optimization approach that aims to minimize forecasting errors, such as Mean Squared Errors (MSE) or Mean Absolute Deviation (MAD). This paper presents a novel methodology that employs a Genetic Algorithm (GA) to optimize the forecasting error by determining the optimal smoothing coefficients for the Holt-Winters Method. The objective value of the optimization problem is the Mean Square Error (MSE), which serves as a measure of the accuracy of the forecast. To evaluate the effectiveness of the proposed approach, actual test cases based on rice stock commercial commodity in the Philippines during the COVID-19 pandemic were utilized. The paper examines different variants of the Holt-Winters Method and assesses their suitability for capturing the characteristics of the rice stock data. The findings indicate that an additive seasonal effect is more appropriate for modeling the seasonal patterns observed in the rice stock data. Furthermore, the performance of the proposed GA-based approach is compared to other forecasting models to ascertain its efficacy. The results demonstrate promising outcomes, suggesting that the GA-based optimization approach for determining the smoothing coefficients in the Holt-Winters Method improves the accuracy of rice stock forecasting during the COVID-19 pandemic. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to cover the many different pieces of research that have come out in the last six years. By classifying the topics covered in these papers, and then analyzing the contents and suggestions made by them, this paper offers a conglomeration of the information stored to help others plan future research in the field. Analysis of how certain proposed solutions work, and how their results are achieved is also done with some real-world statistics. Using all this information, examples of future research into smart mobility are given based on the information parsed in the making of this paper. [ABSTRACT FROM AUTHOR]

This paper aims to review several related papers on Quality Management and Industry 4.0 in the pharmaceutical industry environment to achieve the benefits required future and give a better vision of the extant regulatory and technical barriers for realizing it. Quality Management and industry 4.0 require efforts to better understand a GMP (Good Manufacturing Practices) pharmaceutical industry situation. Product quality in the pharmaceutical industry is a fundamental thing that must be achieved as a fulfillment of regulatory requirements. GMP for the Pharmaceutical Industry is a minimum standard of compliance for the pharmaceutical quality system requirement that must be designed, applied, managed, and maintained properly so that the main objective is achieved where the production process so that medicinal products always have robust quality in fulfilling efficacy and patient safety. Industry 4.0 in the pharmaceutical industry (which is popular with the term Pharma 4.0) is challenging to implement within the GMP 'high-regulated industry' environment. It will have consequences to moving transition into it step by step in a delicate careful slide. The internet of things (IoT), artificial intelligence (AI), robotics, machine learning, cyber-physical system, and advanced computing as a character of industry 4.0 will dramatically change the landscape of manufacturing including the quality system inside. The research results presented in this paper show an increasing trend towards research that focuses on the slices of 'quality management', 'pharmaceutical quality system' and 'industry 4.0'. Further research needs to be done to create a pharma 4.0 quality system implementation model. [ABSTRACT FROM AUTHOR]

The traditional software space (1.0) has seen more than fifty years of creation, testing, and delivery of deterministic software, but this tradition is being disrupted by machine learning (2.0). However, ML and traditional software are considerably different, and the nascent ML industry uses unique workflows and toolsets for both life cycles. This "one foot in each raft" scenario forces companies to support duplicate resources which are essentially doing the same thing. This paper proposes an answer to the research question: Can software 2.0 quality assurance be performed effectively using the same process as 1.0? A systematic literature review was performed and process documents from a machine learning company reviewed. 132 papers were selected and refined to 24. ML process documents supported what is an industry standard ML life cycle. While the literature review shows a gap relative to holistic QA solutions for ML products, process documents showed the answer to the research question is...perhaps, since it was determined that the typical ML life cycle can be mapped to the standard software 1.0 life cycle. This paper proposes using that mapping to extend an existing 1.0 QA process architecture, the Quality Assurance Machine (QAM), to effectively manage both 1.0 and 2.0 QA. [ABSTRACT FROM AUTHOR]

The global population is estimated to increase by 2.6 billion by 2050, in which 70% of the world's population will be staying in the cities. Countries will have to introduce solutions to traffic congestion, pollution, and security. South Africa is not immune to the global challenges and the rise in population. The purpose of this study is to evaluate the effectiveness of Smart Transport Systems in developing countries. The study used a qualitative approach, and scoping research methodology technology to review the papers published between 2015-2021, which were specifically concentrated on South African smart cities and transport. Articles relating to smart cities and transport in South Africa were intensively reviewed and 250 papers were selected. It was found that despite the challenges which South Africa as a country is facing, relating to the socio-economic, its initiatives are gradually developing especially in different metropolitan municipalities which are leading to very successful projects in both the public and the private sector. South Africa does have smart transport infrastructure in place which gives a good kick start and development of smart transport. However, good monitoring, evaluation, and planning of the current infrastructure are of great importance. [ABSTRACT FROM AUTHOR]

The notion of risk exists in every aspect of the business, as it cannot be eliminated but rather reduced to an attainable level through the utilization of effective risk management techniques. For the insurance industry in particular, risk is traded and transferred to the insurance providers as the company offers a shield from the exposure to risk consequences and the likelihood of loss, therefore, escalating the risk from the insured entity to the insurer for a given premium. This research is a development on a previously published paper by the author which had focused on the same issue but with the utilization of binary regression. The paper now proposes a modern model to risk classification which will be used for property lines insurance. The significance of the research lies in the fact that the process of risk prediction can be extremely complex since there are many parameters to keep in mind. In addition, accurate premium pricing can be difficult to estimate given the unpredictability of the risks occurring to the covered property. The data will be categorized into "A", "B", "C", and "D" using multinomial regression followed by a pricing model. The proposed model will be validated via data collected from surveyed properties of a UAE based insurance company. The model is expected to serve as a tool that helps provide better estimates of risk, premiums, and precise pricing. [ABSTRACT FROM AUTHOR]

Existing evidence indicates that Free/Libre Open-Source Software (FLOSS) ecosystems offer extensive learning opportunities. Community members actively participate in various activities, both during their interactions with peers and while utilizing these environments. Given that FLOSS repositories contain valuable data on participant interactions and activities, our study focuses on analyzing knowledge exchange and interactions within emails to track learning activities across different phases of the learning process, with a focus on the first phase (Initiation). In this paper, we leverage Natural Language Processing (NLP) and Machine Learning (ML) techniques within a process mining framework. Specifically, we employ NLP techniques to analyze the contents of emails and messages exchanged in these FLOSS repositories to generate event logs for the purpose of modeling learning patterns. Subsequently, we construct corresponding event logs, which serve as input to Disco, the process mining tool, for learning process discovery in these environments. The output comprises visual workflow nets that we interpret as representations of learning activity traces within FLOSS, capturing their sequential occurrences. To enhance the understanding of these models, we incorporate additional statistical details for contextualization and description. This approach enables a nuanced exploration of learning dynamics within FLOSS environments, emphasizing the role of NLP and ML in uncovering valuable insights on how FLOSS participants acquire and exchange knowledge. [ABSTRACT FROM AUTHOR]

Lean thinking is an essential concept that has emerged in most organizations and industries. This is due to its proven outcomes in improving the process by removing waste and delivering value to the customer. Applying lean has also benefited the process by making it more sustainable by reducing the waste that negatively affects the three pillars of sustainability (Environment, Economy, and Society). Although lean has been established as a concept to improve the manufacturing process, it has extended to cover the maintenance process with reliance on established maintenance principles like Total Productive Maintenance (TPM) and existing lean methods. This paper aims to study and analyze a preventive maintenance (PM) process of a construction company in Qatar and implement lean maintenance methods with TPM to improve the process by minimizing lean waste with a focus on improving process sustainability. The methodology has been assessed through a real case study from a construction project of the company selected. The project equipment preventive maintenance process was analyzed, sustainability indicators were identified, and lean maintenance tools were implemented. The results have revealed that the process has been improved, and sustainability wastes have been minimized. [ABSTRACT FROM AUTHOR]

There is a growing interest in the concept of Industry 5.0 (I5.0), which supports a transition towards a more sustainable, resilient and human-oriented industrial paradigm. This paper focuses on the I5.0 sustainability pillar, which is crucial to optimize and support I5.0’s data-driven and circular supply chains. In order to pursue a Sustainable Supply Chain (SSC) and improve data quality management across it, it is first imperative to understand to what extent the existing SSC quality indicators are aligned with the opportunities of the digitalization era, and if they support the path to I5.0 sustainable practices. This paper aims to do a comprehensive study and analysis of relevant groups of SSC metrics and indicators. Through a broad literature review, SSC metrics and indicators are identified. Then, they are assessed to determine if they are suitable and relevant to assist decision makers in the challenges towards SSC 5.0. Results reveal that despite growing interest in the progress of data-driven SSC in recent years, there are still research gaps, mainly concerning the standardization of indicators, the simplification of models, and the use of consistent models for the treatment and conversion of proper data into relevant information. [ABSTRACT FROM AUTHOR]

The internal combustion engine (IC engine) is a complex mechanical system that plays a vital role in many industries. In order to design and optimize IC engines, accurate modeling and simulation of the engine's geometry and fluid flow are essential. This review paper provides an overview of the latest research in the field of geometric modeling and fluid flow simulation of IC engines. Firstly, the different techniques used for geometric modeling of IC engines are discussed, including the advantages and disadvantages of each approach. The impact of geometric modeling on the accuracy of fluid flow simulations is also examined. Next, the various approaches to simulating fluid flow in IC engines are reviewed, including the use of different turbulence models and boundary conditions. The challenges involved in accurately modeling and simulating IC engines are highlighted, such as the complex geometry and the presence of multiple phases. Furthermore, this review paper discusses the potential future research directions in this field, including the use of artificial intelligence and machine learning algorithms to improve the accuracy of simulations, and the incorporation of real-world driving conditions in simulations. In conclusion, this review paper provides a comprehensive overview of the latest research in the field of geometric modeling and fluid flow simulation of IC engines, highlighting the challenges and potential future directions in this important area of research. [ABSTRACT FROM AUTHOR]

This study conducts a comprehensive bibliometric examination to analyze Model-Based Customer Churn Research. Through Scopus, PRISMA, and VOSviewer. last two decades, academic publications and interest have increased. Empirical research, growth, and trends are examined in this paper. Evidence suggests churn prediction models using advanced data analytics, machine learning, and industry-specific methods. This shows scientific collaboration to predict industry churn. The study highlights "Expert Systems with Applications" and "ACM International Conference Proceedings Series," which spurred field dialogue. These publications provide cutting-edge research and expert opinions. Geographically, we study China, India, and the US. Global churn research matters. Bibliometric research shows model-based customer churns evolve. The resource can help academic and business researchers develop innovative client retention methods in different markets. By analyzing Model-Based Customer Churn the research studies, growth, and trends are examined. Evidence suggests churn prediction models use advanced data analytics, machine learning, and industry-specific methods. This shows scientific collaboration to predict industry churn. The study highlights "Expert Systems with Applications" and "ACM International Conference Proceedings Series," which spurred field dialogue. These publications provide cutting-edge research and expert opinions. Geographically, we study China, India, and the US. Global churn research matters. Bibliometric research shows that model-based customer churns evolve. The resource significantly assists academic and business researchers in developing innovative client retention methods in different markets. [ABSTRACT FROM AUTHOR]

This paper discusses the various works and researches in Supply Chain Risk Assessment SCRA. The methodology chosen is the systematic literature review and the network analysis in order to collect and analysis methods and tendences of supply chain risk assessment in the period between 2019 and 2022. To this end, the study detected four methods extracted from 72 article, which are: Analytic Hierarchy Process (AHP), Failure Mode and Effect Analysis (FMEA), Decision Making Trial and Evaluation Laboratory (DEMATEL) and House of risks method HOR. This study analyses also the bibliometric data and the visualization of similarities (VOS) viewer method to graphically map that data collected from the Web of Science database. The graphical analysis uses citation, co-citation, and cooccurrence analysis. All these results provide a strong starting point for operations researches in this domain for future works. [ABSTRACT FROM AUTHOR]

Additive manufacturing (AM) has emerged as a transformative force, reshaping traditional manufacturing methodologies and fostering agility and efficiency to respond effectively to disruptions and fluctuating demands. The research landscape has witnessed a surge in interest and exploration of AM, encompassing diverse applications such as automotive spare parts, electronics, medical accessories, and fashionable consumer goods. The fundamental objective of AM is to establish seamless collaboration within manufacturing functions, particularly in the face of disruptive events, by facilitating the rapid availability of required products or components through the concept of digitally holding inventory. The integration of AM has engendered substantial improvements in the resilience of supply chains, although it has also introduced unique challenges and implications. This review paper aims to provide a comprehensive overview of studies conducted in the past two decades, elucidating the transformative impact of AM on supply chain resilience within manufacturing organizations. This study employs a bibliometric analysis to identify prominent trends and thematic patterns within this research domain. Furthermore, a narrative review analysis is presented, examining the framework of AM processes across specific industries and delineating how AM has revolutionized traditional manufacturing procedures. The study highlights the tangible benefits of AM implementation and sheds light on the challenges encountered during its adoption. By offering a comprehensive review, this paper seeks to contribute to the existing knowledge base and serve as a foundation for future research endeavours in this evolving field. [ABSTRACT FROM AUTHOR]

Predictive maintenance shows significant impact in managing and controlling the utility systems of commercial buildings. Here in this paper, the predictive maintenance that is in line with Industry 4.0/ Quality 4.0 is applied. The chilled water system is highlighted in this research and the main goal is to reach out the most occurred faults in one of the chilled water system, which is cooling tower. An engineering management framework was used through three parts, set up, machine learning, and quality control. Having said machine learning, decision tree algorithm is used in this research and prediction model showed high prediction accuracy. During an empirical period, the most occurred faults were malfunctioning blowdown system, over current, and low water basin level. [ABSTRACT FROM AUTHOR]

Digital transformation is a concept that is currently being discussed and emphasized in many policies, industrial and corporate strategies. In the scientific literature, digital transformation is often discussed as one of the pillars of a sustainable economy. On the other hand, the question is how to ensure that the digital transformation process itself is sustainable in the long term. That is, not only the transformation process itself but also the application of digital technologies in companies afterwards. This paper aims to explore the sustainability of digital transformation by analyzing its environmental, economic, and social impact. Through a literature review, this paper identifies several key factors that contribute to the sustainability of digital transformation, including the term energy transformation and education and digital skills, security, and business continuity. Based on the conducted research a model of sustainable digital transformation was proposed. The model presents the key elements for the sustainability of digital transformation. The paper concludes by discussing the implications of these findings for organizations, and individuals. [ABSTRACT FROM AUTHOR]

Driver impairment is yet another human factor that is likely to cause dangerous driving behavior (aka distracted driving), leading to safety hazards on the roads. Assuring acceptable drivers' cognitive state can improve safe driving performance. Behavioral and self-report measures are used to assess drivers' cognitive states, but psychophysiological measures can add more considerable value in the real-world driving context. Hence, monitoring, detecting, and responding to drivers' psychophysiological state compose a safety countermeasure that can reduce the risk of distracted driving and thus eliminate or mitigate safety hazards. The research investigates the recent used measures to detect drivers' psychophysiological state, in addition to the drivers' psychophysiological state classification using machine learning. Eye movement, respiration rate, electrocardiogram, electroencephalography, and electromyography are all examples of measures used to deduce drivers' overall psychophysiological state. Tracking and assessing these measures rely on several different metrics, methods, and technologies. For example, drowsiness, as a well-known psychophysiological state, can be assessed and tracked by the eye aspect ratio metric. This paper reviews the recent state-of-the-art measures used for detecting the drivers' overall psychophysiological state. The review considers different psychophysiological states such as fatigue, drowsiness, distraction, and stress. The paper also discusses the strengths and limitations of each reviewed measure, its usage, and its real-time applications. The result showed that the most common used measures are eyes and mouth state measures. Also, several machine learning methods have proven their reliability in classifying drivers' psychophysiological states, especially SVM and CNN as they have wider applications. [ABSTRACT FROM AUTHOR]

Supply Chain Management (SCM) cannot distance itself from seeking both sustainability and resilience to deal with consecutive change. To achieve this objective, SCM has seen the adoption of digital technologies as a decisive tool to face challenges, such as the COVID-19 pandemic and the war in Ukraine. These disruptions guide SC managers to search for new opportunities and strategies that impact them in the short and long term. The terms “supply chain sustainability” and “supply chain resilience” have been well explored in literature as independent terms, but there is a lack of studies on their combination, especially in the digital field. This paper aims to explore the extant literature focused on the adoption of digital technologies that contribute to the development of sustainable and resilient SCs, recurring to a systematic literature review. The objective is to identify the trade-offs and the synergies that characterize the relationship between technological-enabled practices for sustainability and resilience. The database used was Scopus and the formulated query resulted from de author’s discussion including words related to supply chain, sustainability, resilience, and digital technologies. Only articles published in journals and in English were considered, and there was no restriction regarding the date of publication. The first search presented a total of 136 articles (March 2023). The selection was performed in two stages: (1) reading the abstracts and keywords of all papers; (2) full reading of the papers selected in the first stage. After the first analysis (step 1), we selected 63 articles. After step 2, 42 papers that address the relationship between digital technologies and sustainability and resilience were kept. The results showed an increase in the production of papers approaching the themes, possibly (at least in part) due to the COVID-19 pandemic and the pressure that competition provokes on the stakeholders. The technologies majorly identified are related to Blockchain, Additive Manufacturing, Big Data, and the Internet of Things as means to achieve SCs with higher levels of resilience and sustainability, being also identified papers that approach the terms “industry 4.0” and “industry 5.0”. The main fields where papers have been conducted are food supply chain, agriculture, and automotive industries because of the traceability capabilities of most technologies. These findings lead to the conclusion that these technologies are the ones with the potential to change organizations and research is focusing on the initial links of SC. According to the quantitative analysis, 2022 was the year when more articles were published in the journals Operations Management Research, Annals of Operations Research, and Production Planning and Control as the ones that published more. Most papers focused on the utilization of one technology and do not identify a specific theory. We conclude that there is crescent interest in this topic and a lack of theoretical support. This study contributes to increasing the body of knowledge related to digital technologies in SCs that simultaneously contributes to achieving resilience and sustainability in those SCs. The findings resulting from this systematic literature review help consolidate the theme for future research. [ABSTRACT FROM AUTHOR]

When it comes to brick-and-mortar retailing and E-Commerce, anticipating demand accurately is one of the most important aspects in minimizing loss (through unavailability of items) and maximizing profit for any time period. This literature review aims to pursue a deeper understanding in founding a prediction model for forecasting retail sales by using deep learning techniques. The researchers gathered various papers from reputable publishers and institutions and sorted those that dealt with the use of deep learning techniques and machine learning techniques. The researchers found that the most frequent techniques used are Long-Short Term Memory and Random Forest for deep and machine learning respectively. Thus, the researchers proposed a model using LSTM with learning features inherited from common features observed through the related studies gathered and Random Forest as the proposed comparator or baseline model. [ABSTRACT FROM AUTHOR]

The advancement of digital technology in the industry is making it possible for products and processes to connect people, materials, energy, plant, and equipment efficiently. More productive business processes will have an impact throughout the economy and the environment. Connected products generate data that is being seen as a key source of competitive advantage, and the management and processing of that data is generating new challenges in the industrial environment. The work to be presented looks into the framework of the adoption of Artificial Intelligence and Machine Learning in the Industrial sector under industry 4.0 or smart manufacturing framework. This work is focused on the discussion around Artificial Intelligence as a driver for Industrial Process optimization and looks into its link with process operators and people in the shop floor, and IIoT. The paper includes a bibliometric analysis of the key topics around Artificial Intelligence under Industry 4.0 or Smart Manufacturing paradigm. The main findings are related to the importance that the subject has adquired since 2017 in terms of published articles, and the complexity of the approach of the issue proposed by this work at the industrial environment. [ABSTRACT FROM AUTHOR]

Machine learning is the current hot topic in the technology industry with many seeing what potential uses it has across many different fields. One such potential application is in a specific subset of smart mobility, resource optimization. This paper analyzes the use of machine learning techniques to optimize the performance and design of batteries and engines. By analyzing other works a generalized overview of the topic is achieved alongside suggestions for future research. [ABSTRACT FROM AUTHOR]

Pharmaceutical industry is instrumental to the well-being of people around the world as it deals with the discovery, development, production and marketing of drugs and medications, which are one of life’s necessities. Recently, there is an emerging phenomenon that some hospitals in Vietnam must suppress their operation due to the deficiency of medical supply, and thus affecting patients who are in the need for treatment. One of the factors contributing to the situation is the incapability of providing these commodities on time from pharmaceutical companies, which results from their inaccurate forecasting. This paper investigates the application of machine learning algorithms in time series forecasting, specifically focusing on Support Vector Regression (SVR) to improve forecast accuracy. It evaluates the performance of two time series models, including ARIMA and Holt’s Trend, and three types of SVR, including Linear kernel, Polynomial kernel, and Radial Basic Function (RBF). The evaluation is based on the Mean Absolute Percentage Error (MAPE) metric, which measures the accuracy of the forecasts. The study then proposes hybrid models that combine SVR with traditional time series models via ensemble methods and compares their performance with the individual models. Finally, a case study of a pharmaceutical company is performed to assess the impacts of these methods. The results demonstrate that the hybrid ensemble method achieves lower MAPE values compared to the individual models. These findings offer promising insights and highlight the potential of the proposed hybrid models in improving forecast accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a method to estimate broiler weight automatically using computer vision approach and machine learning model. The data used in this paper obtained using a broiler cage video and manual weight calculation on daily basis for 33 days. The broilers image is processed using several image processing methods such as noise removal, adaptive thresholding, morphological operations, and image segmentation to generate morphological data of each broiler. The model development is carried out by utilizing morphological data of each broilers which increased along with the increase in weight. Five features of broilers were used, namely area, perimeter, mean radius, maximum radius, and major axis. The proposed model then was validated using a 10-fold cross validation method. The proposed model performance is calculated using the RMSE metrics, which shows SVR model has the best performance with RMSE value of 144,7 grams. [ABSTRACT FROM AUTHOR]

Over the past few decades, Internet sites have become integral components of business operations across all industries. This increased prominence, however, has also led to the emergence of various attack vectors damaging the web sites with service outages, poor user experiences, financial losses, and damaged reputations to the business. No web or mobile application on the Internet is immune to these attacks, underscoring the critical need for robust security solutions to safeguard websites against malicious attacks. At the heart of the security solutions lies the capability to accurately tell apart malicious actors from legitimate users with minimal false positives and false negatives, while the solutions should operate efficiently, exhibiting high performance, transparency, and cost-effectiveness. Robustness of the solution is also crucial to ensure that attackers cannot decipher the inner workings of the security systems, preventing them from adapting and circumventing security defenses over time. With the advent of machine learning and big data systems, security solutions have evolved to effectively detect and mitigate various threat vectors. The paper delves into an examination of various attack vectors, industry security solutions driven by big data and machine learning and outlines key design considerations necessary for creating effective and resilient security solutions. The paper concludes by offering a brief perspective on anticipated future developments to secure the Internet. [ABSTRACT FROM AUTHOR]

This paper investigates real-world data from a PVC manufacturing plant in Saudi Arabia to construct predictive statistical models leveraging machine learning techniques. The primary aim is to identify prevalent failures and predict their timing based on historical incidents. The study introduces the Random-Forest-Classifier algorithm to refine the dataset and enhance accuracy. Subsequently, the results are applied to simulation modeling, providing insights into proactive action and opportunistic maintenance behavior within PVC manufacturing. The motivation of the research was to reduce the sudden breakdown in the factory and provide practical recommendations to optimize maintenance practices, thereby enhancing operational efficiency. The paper concludes with a simulation model illustrating the use of opportunistic actions that support the Overall Equipment Efficiency (OEE) resulting from the predictive model's insights. [ABSTRACT FROM AUTHOR]

As the world moves towards renewable energy sources, solar energy is becoming more widely recognized. This impacts photovoltaic (PV) panel prices, which requires deeper analysis to shape strategic planning. This paper fills a gap in PV panel price forecasting by utilizing machine learning models for multivariate time series forecasting, offering a more robust, comprehensive, and adaptable approach. Based on literature review, feature analysis, and linear regression, PV panel prices factors were identified, and data was collected. The dataset consists of 26 monthly time series features covering January 2018 to July 2023. The study's methodology consists of two phases: Phase I involves applying machine learning models (CNN, KNN, Random Forest, SVR, XGBoost) to forecast prices, resulting in the selection of the Random Forest model as the most effective based on performance metrics and comprehensive evaluations. Phase II utilizes the aforementioned model, along with forecasted features from the SARIMA model, to predict future PV panel prices. Forecasts indicate a stabilized PV panel market for 36 months from July 2023, with slight price fluctuations. This stabilization hypothesis aligns with other research findings, suggesting industry agreement. As the solar industry is dynamic, regular market analyses and model calibrations are essential. Overall, the research enhances the understanding of solar energy price time series forecasting, merging data gaps, and outlining pivotal price-influencing factors, offering stakeholders direction towards a sustainable energy future. Recommendations include using a broader dataset, improving methodology, exploring more models, applying a hybrid model, and continually updating forecasting methods in alignment with industry dynamics. [ABSTRACT FROM AUTHOR]

Extending the work of Downing & Badar (2022), this paper presents the history of software, artificial intelligence, software quality assurance, and a software QA architecture called the Quality Assurance Machine (QAM). Using Design Science Research (DSR), the QAM was extended to support software containing ML models. Using descriptive statistics and hypothesis testing, this paper answers the research question: is QAM effective for assuring the quality of software containing ML? Future DSR efforts will add a Process Quality engine to the QAM to monitor and improve the processes used to create software and models. [ABSTRACT FROM AUTHOR]

Insurance fraud, especially automobile insurance fraud, is a common fraud topic which causes significant financial losses for insurance companies. Dishonest claims impose a significant financial strain on insurance companies which influence on the entire industry. Because of this, insurers are constantly seeking for more effective detection systems to get beyond the limitations of traditional techniques; therefore, building a reliable and effective fraud detection model is crucial to maintaining the insurance providers' financial stability and reputation. Our research paper major objective is to use machine learning techniques to develop a reliable system for detecting car insurance fraud. This study intends to examine multiple supervised machine learning algorithms using classification method, and assess their efficacy, to ultimately select the most accurate model with significant accuracy for identifying fraudulent insurance claims. [ABSTRACT FROM AUTHOR]

The aim of this paper is concerned with evaluating and assessing the COVID-19 waste management plan to develop a generalized waste management framework that can be adopted with future pandemics based on the UAE approach. Some existing models for waste management across different countries across the globe and the extent to which they could be applied in defined areas are discussed. An integrated framework that can serve as a basis for the development of a waste management system is proposed. Applicability, benefits, challenges, and limitations of the system are all outlined with a narrower scope focusing on the different approaches adopted by several Emirates in the UAE. An in-depth analysis of the current waste management methods, as well as the focus on disposing of medical waste contaminated with COVID-19. A comprehensive COVID-19 UAE-based framework is proposed alongside a generalized framework that can be implemented in future pandemics that are associated with a pathogen carrier. [ABSTRACT FROM AUTHOR]

Fire is a primary threat to property and human safety in warehouses, and risk management of warehouse fires is challenging due to potential accident causes and various safety measures. Warehouse fires are caused by many factors such as the size of the buildings and the amount of stored combustible material. The size of the buildings and the volumes of combustible material held result in many of the fires becoming major conflagrations which pose challenges for fire and rescue services and result in significant property losses. Storage fires, like those in fuel storage facilities, can quickly spread to surrounding products, generate a number of secondary fires, resulting in conditions where accidents are uncontrollable, and severely destroy assets. The bowtie analysis approach was used in this paper for the industrial warehouse fire scenario. A generalized framework to manage warehouse fires was then developed followed by a general mitigation measure to control fires at industrial warehouses. A successful fire safety strategy is a thorough fire risk assessment that considers warehouse protection and life safety in compliance with national fire safety legislation. In the interests of developing a successful risk control program, an assessment will identify the fire threats and the potential for property losses and business interruption losses. The assessment shouldconsider the structure of the building and the flammability of the products stored and the mode of storage. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to apply Lean and Six Sigma techniques in Indian hospital to investigate the barriers in length of stay (LOS) period of Intestinal obstruction patients. The Six Sigma’s DMAIC (Define-Measure-Analyse-Improve-Control) procedure is being applied along with standard Lean tools. The detailed data of patients are observed over a period of eight months. The mean LOS is computed to be 11.55 days with standard deviation of 3.34 days. The value stream mapping is used to find various non-value added activities and Fishbone diagram is utilized to determine root causes of the process. Patient’s feedback and GEMBA observations are used to validate the possible causes for the problem. It is observed that nearly 70% of total LOS is non-value added time and can be minimized to reduce the LOS. The waiting time for surgery, time for admission, time for discharge, lack of motivation from doctors, etc. are identified as root causes for the process. It is concluded that Lean and Six Sigma methodologies have great potential to produce clinically significant improvement for surgical patients. [ABSTRACT FROM AUTHOR]

The lighting system is an essential component of any industrial city's infrastructure for drivers' safety to prevent accidents and facilitate ease of guidance as an accessibility manner to the city. However, street lighting accounts for a significant portion of the overall energy consumption in industrial cities that does not reflect the actual vehicles passing the street or the intended purpose of the lights. In this paper, we propose a smart sensing model to reduce street lights' electrical consumption based on demand using an Internet of Things (IoT) camera with a License Plate Recognition (LPR) function that detects vehicles. If a vehicle is detected using LPR, the street lights will be turned on for 15 seconds to allow the vehicle to pass the street, then turn off part of the street lights if no other vehicles are detected as an ideal status of the lights. Our results concluded that the proposed smart sensing model accomplishes its objective by achieving the highest street light electrical reduction in one hour across five days, which is 89.17 % for half of the lights controlled using IoT. Moreover, the highest average reduction for all five days with a period of 12 hours is 74.09% compared to regular status. [ABSTRACT FROM AUTHOR]

The purpose of this research is to develop innovative techniques and combinations of constituents to use composites in agricultural, infrastructural and other relevant industries. Industrial, infrastructural, and biodegradable structural applications using hemp fibers are of interest to enhancing environmental sustainability. The products including graphite or hemp reinforced polymers with different volume fractions and orientations are considered. While a large number of products could be used in the commercial production, we explore only two laminates in this investigation. In this paper we are analyzing interlaminar stress components contributing to delamination of composite laminate. Using analytical techniques, effective response characteristics and interlaminar stresses of representative composites are predicted and given in this paper. Based upon this research a set of influencing factors will be identified, specific number of composite laminates will be chosen, manufactured, analyzed and tested for their performance characteristics. This is a step towards further research in progress for comparative studies between predicted and experimental values. We have used hemp fiber properties from reference [2]. For hemp fiber the Young’s modulus varies from 2.9 msi to 5.8 msi and Poisson ratio is 0.15. The matrix material properties of EPON 828 with Young’s modulus 0.42 msi and Poisson ratio 0.35 are used from reference [1]. For computation of effective properties of (0/90)s hemp reinforced composite laminates, we have used Young’s modulus values 2.9 msi and 5.8 msi separately. Dr. Pagano [3] was the first to recognize the importance of interlaminar phenomena in high-performance composite materials. His discovery of the “stacking sequence phenomenon” led to new practices to reduce the potential for delamination. [ABSTRACT FROM AUTHOR]

The global outbreak of Covid-19 has had far-reaching effects on countries worldwide, influencing various aspects of life, economies, and markets. As a result of government policies, organizations have been compelled to adopt remote working arrangements. Within this context, the performance of employees becomes a crucial concern for organizations. To effectively navigate the pandemic and develop a capable and adaptable remote workforce, organizations need to prioritize the development of their human capital. Hence, this review paper focuses on exploring employee training during the Covid-19 period in Malaysia. The findings highlight the importance of training and development programs in successfully navigating the pandemic, as they offer numerous benefits and significantly influence employee performance. A great shift to digitalization of training is noticed with 86% of the companies shift their training and development programs to online, 76% of the companies plan to increase their online training programs, and 68% found online training to be equally effective. However, organizations face specific challenges when implementing virtual training, including the inadequacy of traditional programs and methods, limited collaboration and engagement, difficulties in assessing training outcomes, and issues in sustaining trainees' participation. Additionally, the paper recommends that organizations explore and utilize existing training programs and technologies, while investing further in digitalization and virtual training initiatives. [ABSTRACT FROM AUTHOR]

Human factors engineering aims to optimize socio-technical systems to enhance systems performance and human well-being throughout the systems lifecycle. The aviation industry is one of the sophisticated and influential industries that popularized human factors engineering principles in response to aircraft incidents and accidents. Now, there has been a slow pace in applying human factors in the lifecycle of socio-technical systems beyond the aviation industry. Lack of understanding of human factors benefits has been alluded to as one of the factors that hinder the application of human factors in other industries. A number of studies focus on the development and application of various human factors models, but there seems to be no study that adequately shortlists, discusses and presents the benefits of applying human factors. The aim of this paper is to uncover, examine and classify the benefits of applying human factors engineering principles in sociotechnical systems, especially in the era of 4IR. A narrative literature review methodology was adopted to analyze and synthesize various conference and journal articles on the application of human factors. The study revealed and classified the benefits of human factors according to performance, wellbeing, safety, quality, cost, and other operational benefits. The study's main contribution is making the benefits of applying HFE in various systems and processes visible to potential adopters and researchers involved in the application of HFE. Human factors such that they are visible to researchers and industry practitioners. Thus, it sets an agenda for future debate, discussion and research. [ABSTRACT FROM AUTHOR]

Machine learning provides various algorithms for application in different domains. In the educational field, huge volume of students' data is generated and machine learning algorithms serve as valuable tool for pattern identification in students' behavior. In this paper, CRISP DM standard for data mining is applied in the research with decision tree algorithm used for modelling on Croatian dataset to develop predictive models for students' outcomes prediction. Data set consisted of 264 students of largest Croatian university collected by online survey. The results prove that decision tree modelling achieves superior results in terms of high accuracy and reliability together with interpretability of tree structure and obtained rules in prediction of students' academic performance. This approach shows promise to be used in student success prediction in the universities in an automatic manner. Such model can be used to: (i) improve students' learning and develop personalized recommender systems for optimal learning paths, (ii) emphasize to professors most important determinants of students' academic success (iii) help management of higher education institutions to facilitate the provision of detailed student learning and adjust institutions strategies, (iv) automate adaptation of the course modules and faculty programs. [ABSTRACT FROM AUTHOR]

The fourth industrial revolution (industry 4.0) is a term used to describe the ongoing transformation of business processes combined with the latest technologies that are changing the way businesses operate, leading to the faster, cheaper, and effective delivery of products and services. Different companies and countries are preparing for this revolution by developing Industry 4.0 strategies. To assist the companies seeking to adopt Industry 4.0 in manageable phases, the maturity models (MMs) were created and used. However, in the context of Industry 4.0, literature reviews indicate that the number of models has increased sharply in recent years. This paper aims to present and analyze the results of bibliometric analysis and systematic literature review, which highlight the recent developments in the field of Industry 4.0 MMs, with a focus on investigating the existing models, their types, levels, and dimensions. Based on our findings, we introduced the core dimensions of the MMs that will require more intensive efforts to set the ground for the transformation journey, utilizing the power of AI and machine learning. This work will enable the scientific community to investigate the publication hierarchy in this emerging filed, and it will serve as a starting point for future MMs developments. [ABSTRACT FROM AUTHOR]

This paper aims to analyze and review the most recent scientific literature regarding the implementation of Machine Learning (ML) in Supply Chain Management (SCM). Moreover, an examination was conducted to find out what areas and industries were addressed in the use cases, and how ML may impact SCM. A Systematic Literature Review (SLR) was conducted for this purpose. It was found that the applied examples mainly used ML's prediction capabilities, and some industries such as health care and logistics were the main focus areas. Then, discussions were developed based on the results of the systematic literature analysis, which can be used as motivation for future research. [ABSTRACT FROM AUTHOR]

The paper aims to present an overview of previous research on "machine learning" applications in banking, covering key aspects of recent discoveries, their limits, and potential future research directions. It makes two contributions to the body of knowledge. It initially divides the literature to provide an overview of completed research endeavors. Second, it points out a gap in the existing body of research and suggests fresh avenues for investigation. The findings indicate that prior research has had difficulty developing a sound theoretical foundation for the subject. To support the proposed "theories," "notions," and "paradigms," more study is needed. In short, there is a big need for more research because there hasn't been a thorough evaluation of how machine learning has been used in banking. [ABSTRACT FROM AUTHOR]

As we all might have felt or seen, the impact of different mental illnesses has increased as the modern workforce is shifted from physically challenging tasks to mentally challenging tasks. With this change in the nature of work the impact on the human’s mental health is increasing as compared to earlier times. So we also need to give this area more attention than before. In this paper we have surveyed papers that discuss about using Audio features and using it for building machine learning models for predicting different mental illnesses. For this study Supervised learning ML models are preferable as going with the audio features unsupervised ML models may get confused with different excitement states. [ABSTRACT FROM AUTHOR]

In this paper we give 91 hypotheses and 6 conjecturers that relate various aspects of Information Technology / Systems (IT/S) as related to the strategy of the firms (cost leadership, differentiation and innovators). These are virtual teams (VTs) in track 1, enterprise social media (ESM) in track 2, analytics, strategy of organization (cost leadership/differentiation) and types of innovators (continuous innovation, modular innovation, architectural innovation and radical innovation) in track 3 and machine learning, artificial intelligence, types of programming (OOP, extreme and scrum) and internet of things (IoT) in track 4. These are new hypotheses and have tremendous implications for top management of firms as they go about managing its IT/S infrastructure. [ABSTRACT FROM AUTHOR]

Plastic's discovery resulted in a profound shift in human lives, and it is now used in a wide range of critical applications. Despite its importance, the world is struggling to control plastic waste and prevent it from infiltrating the natural environment. This paper intends to evaluate the environmental burdens of various plastic waste management scenarios using life cycle assessment (LCA). This paper evaluated five options: landfill, incineration, mechanical recycling, pyrolysis, and combined mechanical recycling and pyrolysis. The CML-IA Baseline approach is employed in this study for all scenarios, with OpenLCA software. The data for this paper came from the Ecoinvent 3.9.1 database and public reports. The last scenario, which is combined mechanical recycling and pyrolysis was found to have the lowest environmental burdens, according to the LCA results. Furthermore, the combined scenario may absorb a greater range of plastic waste, improving the whole waste management system to transition to a circular economy. Therefore, it is advised to build a portfolio of plastic waste handling techniques that provide high quality recovered products to meet numerous consumer requirements. Since it was established in this study that renewable energy has a notable favorable environmental impact across all impact categories, using renewable energy for electricity generation was recommended. [ABSTRACT FROM AUTHOR]

The production systems are affected by degradations and failures caused by operational and environmental conditions. Indeed, unplanned, unscheduled maintenance (UUM) practices lead to lower productivity, lost production, expensive labour (call-outs, overtime) and damaged equipments. However, predictive maintenance (PdM) is a condition-based maintenance strategy (CBM) that has become popular among practitioners in recent years that carries out maintenance action when needed, avoiding unnecessary preventive measures or failures. Machine learning (ML) has become an advanced diagnostic approach in maintenance strategy to mitigate those challenges. Despite that, the ML-based PdM strategies are infancy stage due to the immaturity of the Industrial Internet of things (IIoT) which is responsible for data collection and execution. Implementing ML-based PdM is a difficult and expensive process, especially for those companies which often lack the necessary skills and financial and labour resources. Thus, a cost-oriented analysis is required to define when ML-based PdM. The proposed study develops the ML algorithm and provides an intelligent PdM model with a framework for practitioners and researchers considering aircraft industries. The contribution of the paper has twofold. The first is to developing an ML-based predictive maintenance model. The analysis shows that random forest outperformed other models scored 28.63 cycles to predicts Time to failure (TTF) within the average error range of ±28 cycles. While, the research finding helps to monitor that how to execute data wrangling and prepare pandas data frames to define TTF of the airlines engines. [ABSTRACT FROM AUTHOR]

Agriculture is the backbone of India as it is the source of food as well as one of the factors of economic development. The agriculture sector's contribution to the Indian economy is much higher than the world's average. Agriculture has several stages, such as soil preparation, crop selection, control of pests or insects, crop yield, and crop sales. Artificial Intelligence (AI) is one of the very emerging areas in the computer field. Applying AI in farming is now essential to increase crop production. Machine Learning (ML) and Deep Learning (DL) are sub-areas of AI. Though ML and DL follow their learning strategies. This paper gives an outline of ML and DL concerning agriculture. This paper also studies on comparison of ML and DL models with results. The majority of DL models are outperforming ML models. ML and DL are also applied in several other domains like medical, agriculture, business, transport (logistics), entertainment, education, and many more. [ABSTRACT FROM AUTHOR]

A Denial of Service (DOS) attack is a continuous security risk in cyberspace. They are weaponized with advanced technologies and becoming more and more powerful as Distributed Denial of Service (DDoS) attacks. DDoS is one of the most occurring attacks nowadays and new methods are being needed to be able to detect such attacks. Attackers use many different techniques to perform DDoS attacks. Different DoS attack types has different characteristics and research is still needed to identify such attacks. In this paper, we analyse slow DDoS attack types (slowloris, slow http attack, etc) and propose a framework to detect them using machine learning techniques. We utilize gain-ratio and chi-squared ranking methods to select optimal feature subset for training detection mechanism. CICIDS2017 and CSE-CIC-IDS 2018 datasets are used to evaluate the proposed detection mechanism. [ABSTRACT FROM AUTHOR]

Predicting crop yield in general is critical for agricultural planning, resource allocation, and food security. The recent adverse effects of climate change on agricultural productivity have given rise to crop yield prediction which is essential in assisting farmers in anticipating the worst and preparing accordingly. Maize is one of the most popular staple foods in sub-Saharan Africa, and at the same time is the most affected by climate change. Knowing the expected maize yield in advance therefore helps those communities that are heavily dependent on maize, to prepare in advance to handle the projected situation. Despite several efforts that have been done to predict maize crop yield, the topic remains an open discussion. This paper joins the debate and uses data analytics and machine learning to build a reliable predictive model for estimating maize crop yield. Using historical maize crop yield, weather, and environmental data, the Random Forest Regressor (RFR) technique is trained to capture non-linear patterns and identify complex correlations in the data. The results of the model’s evaluation show an accuracy of 70.52% demonstrating the model’s ability to capture a substantial portion of the variability in the data. The predictive model can be useful for maize production farmers and maize grain depots, as it gives them time to plan for the future. Policymakers may benefit from the model, as it helps them to make informed policies on grain management. Future research should consider testing this model in a live environment, before packing it for deployment on a large scale. [ABSTRACT FROM AUTHOR]

AI-based self-driving vehicles use open networks and develop self-driving vehicles using ICT technology based on artificial intelligence on computer platforms. However, as hacking attacks on electronic control systems of self-driving vehicles have become possible, various hacking cases such as vehicle control system attacks and remote-control attacks have occurred. Cases of such hacking attacks are increasing the threat of hacking by outside attackers, and if self-driving cars become popular, the number of hacking cases will increase further. In this paper, we propose countermeasures for hacking attacks in terms of cybersecurity systems and technology to cope with hacking attacks. By separately presenting technology and institutional-centric security enhancement measures related to cybersecurity, it contributes to the construction of security for self-driving vehicles and the development of cybersecurity for unmanned defense robots. As security holes owned by self-driving technology are expected to leak personal information or cause personal injury, the need for security research on self-driving cars is increasing, and research on hacking attacks and security measures against self-driving cars is needed. As an additional research task, it is necessary to study the development of smart keys using NFC communication methods for self-driving vehicles and encryption programming methods for security authentication. [ABSTRACT FROM AUTHOR]

A hybrid work environment enables employees to have a combination of working from home and the office. The intention of this paper is to investigate and provide a comparison between hybrid work and in-office work environments. As researchers indicate, WFH has a positive impact on employee productivity and well-being. In orderto provide a deep understanding, an empirical survey was conducted on 95 United Emirates workers. The key findingsof this survey illustrate that WFH has both positive and negative impacts on workers. The participants record positiveexperiences with WFH, including flexibility, increased efficiency, improved work-life balance, and better focus. However, the study revealed that some participants recorded various challenges, such as lack of social interaction, increased output expectations, and long working hours, which were obstructions to their participation in WFH. The findings from this research aid in understanding the benefits and challenges of WFH and inform organizations on thebest approach to follow when instituting a hybrid work environment within their workforce. [ABSTRACT FROM AUTHOR]