Data Predictive Analytics Research Articles

Advancing Predictive Data Analytics in IoT and AI Leveraging Real time Data for Proactive Operations and System Resilience

Integration of the IoT and AI is turning data analytics and realtime decision making on their heads, opening up new spaces across industries. The data the IoT devices generate is not only in realtime form but also from multiple sources such as sensors, machines, and connected devices. While of immense value, the raw data is complex and bulky, demanding advanced processing into actionable insights. Leverage AI, using machine learning and deep learning techniques, in order to analyze IoT data efficiently and come up with autonomous and intelligent responses regarding the dynamic situations. Analytics based on AI can support realtime decisions for organizations based on data, improving operational efficiency, reducing downtime, and enhancing customer experience. Using AI capabilities, realtime analytics can predict equipment failure in healthcare, manufacturing, and logistics, monitor patients' health, and streamline supply chains instantaneously. Data will be generated through speedy processing and actionable output. These facilitate the businesses in taking decisions through timely responses. This is how the strength of IoT integrates well with AI and propels toward self reinforcing learning cycle and optimization. AI algorithms keep evolving in time with even more input of data. Predictive and prescriptive analytics thereby forms an excellent framework which places the companies at excellent positions with respect to competitiveness in high volatile markets through agility and responsiveness.

Optimizing warehouse management system with blockchain and machine learning predictive data analytics

Blockchain technology is proving to be a disruptive technology in many areas of supply chain, manufacturing, medical, agriculture, and so on. Warehouses are an inevitable part of the supply chain. Issues like space optimization, route optimization, quick item pick-up, demand forecasting, and transaction management are of importance to address in warehouse management systems (WMS). Traditional database systems have limitations of interoperability among different entities involved in warehouses. This paper presents an innovative application of blockchain technology and machine learning (ML) to build a smart warehouse management system in Web3 (SWMW3). We developed a decentralized application (DApp) using Web3.0 principles, integrating ReactJS for the frontend, express for the backend, and blockchain through smart contracts. This integration enhances security and transparency by storing WMS operational data in the blockchain and automating payments and verifications through smart contracts. Additionally, we implemented a ML model for predicting the total time from order receipt to delivery, leveraging historical data to optimize workflow, reduce delays, and improve overall efficiency. This combination of blockchain for secure transactions and ML for predictive analytics generates a robust, efficient, and optimized management system for the warehouse.

Exploiting LSTM Neural Network Algorithm Potentiality for Early Identification of Delayed Graduation in Higher Education

Adoption of deep learning classification algorithms in the domain area of higher education provides exploratory predictive data analytics able to exploit students’ academic behavior. Concretely, student retention and success are critical concerns in higher education globally. Timely identification of potential delays in graduation is essential for universities to provide effective interventions and support, ensuring students’ progress efficiently and maintaining high graduation rates, thereby enhancing institutional reputation. This study examines data from a typical computer science department of a central Greek university, covering student performance for almost two decades (1999-2018). Through extended data preprocessing, we developed a robust dataset focusing on key courses indicative of students' likelihood to graduate on time or experience delays. We employed a deep learning Long Short-Term Memory (LSTM) Neural Network algorithm, leveraging this dataset to classify and predict students' final academic outcomes. Our findings reveal that early-semester performance data can successfully forecast graduation timelines, enabling proactive educational strategies to support student success during their studies at the university.

Conceptualising a data analytics framework to support targeted teacher professional development

ABSTRACT This paper proposes a conceptual framework enabling the development and adoption of descriptive, diagnostic, predictive and recommendatory data analytics in teacher professional learning by harnessing some of the affordances of digital technologies to convert data into actionable insights. The paper argues for a technology-enhanced approach that uses data to support teachers in selecting appropriate professional development (PD) options to improve their professional practice. The ultimate goal is to lay the foundations for a robust and adaptable data analytics framework that could offer tailored PD recommendations based on the developmental trajectories of individual teachers. The paper analyses data-supported personalised professional learning as meaning-making and the appropriation of cultural artefacts within the ‘mobile complex’ - consisting of structures, agency, and the dynamic interplay between cultural and technological tools and practices. This study undertakes a comprehensive literature review to identify key concepts, gaps, and theoretical insights, informing the development of a data analytics framework. The resultant framework integrates personalisation, teacher agency and autonomy, contextual relevance, and ethical safeguards into PD process, aiming to foster a responsive, collaborative, and context-aware data-supported PD.

Predictive Big Data Analytics Capability Model to Enhancing Healthcare Organization Performance

Big data analytics capabilities have the potential to help healthcare organizations improve performance and provide high-quality care, and this awareness is growing. However, implementing BDA to optimize healthcare performance is a fundamental challenge for researchers and practitioners alike. This study investigates how big data analytics capabilities can predict the performance of healthcare organizations through five broad categories of BDA capabilities (organizational, technical, analytical, cognitive, and social) with their subcompetencies to improve decision-making and reshape the future of healthcare transmission. These thematic categories were used to develop a prediction model to predict healthcare organization performance accurately. We collect 205 responses from big data analysts and those who work in the hospital’s information technology departments through a survey, preprocessing the data, then we use the machine learning and neural networks algorithms to develop and evaluate the model. Insights into the relationship between big data analytics competencies are provided by the results of predictive modelling. The results of the proposed model were good for all capabilities. the model's accuracy at a range 77.6% to 85.4% for all capabilities, these results show that the model has strong and consistent performance, and make it a trustworthy instrument for decision-making in the healthcare industry

Applications of Neuro Deep Learning Models in Predictive Data Analytics for the Movements and Trends of the Indian Stock Market: Financial Data Mining, Nonlinearity, and Quantum Finance

The financial world of today is high-frequency data-driven and characterized by the application and use of information technology for better business development and decision-making. The price movements of stock markets are mainly influenced by micro and macroeconomic variables, legal frameworks, and taxation policies of the respective economies. The crux of the issue lies in exactly forecasting the future stock price movements of individual firms, based on historical prices. Achieving accuracy for forecasting the market trend has become difficult due to the prevalence of stochastic behaviour in the stock market and volatility in the stock prices. This paper analyzes the stochastic movement pattern of the highly volatile thirty individual company stocks (in terms of market capitalization) of BSE-Sensex, using the Neuro Deep Learning method, a model of deep learning approach. The findings of the study would help the investors, to make rational and well-informed investment decisions, and to optimize the returns by investing in the most valuable stocks of listed corporate enterprises.

Predictive Data Analytics in Telecare and Telehealth: Systematic Scoping Review.

Telecare and telehealth are important care-at-home services used to support individuals to live more independently at home. Historically, these technologies have reactively responded to issues. However, there has been a recent drive to make better use of the data from these services to facilitate more proactive and predictive care. This review seeks to explore the ways in which predictive data analytics techniques have been applied in telecare and telehealth in at-home settings. The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist was adhered to alongside Arksey and O'Malley's methodological framework. English language papers published in MEDLINE, Embase, and Social Science Premium Collection between 2012 and 2022 were considered and results were screened against inclusion or exclusion criteria. In total, 86 papers were included in this review. The types of analytics featuring in this review can be categorized as anomaly detection (n=21), diagnosis (n=32), prediction (n=22), and activity recognition (n=11). The most common health conditions represented were Parkinson disease (n=12) and cardiovascular conditions (n=11). The main findings include: a lack of use of routinely collected data; a dominance of diagnostic tools; and barriers and opportunities that exist, such as including patient-reported outcomes, for future predictive analytics in telecare and telehealth. All papers in this review were small-scale pilots and, as such, future research should seek to apply these predictive techniques into larger trials. Additionally, further integration of routinely collected care data and patient-reported outcomes into predictive models in telecare and telehealth offer significant opportunities to improve the analytics being performed and should be explored further. Data sets used must be of suitable size and diversity, ensuring that models are generalizable to a wider population and can be appropriately trained, validated, and tested.

Integration of Artificial Intelligence into Sustainable Development Goals in India

In the pursuit of sustainable development, the fusion of artificial intelligence (AI) with legal mechanisms emerges as a potent force for transformative change. This paper delves into the intricate interplay between AI technologies and the legal framework, elucidating their collective capacity to address multifaceted challenges and propel progress towards the Sustainable Development Goals (SDGs). At the forefront of environmental stewardship, AI-driven solutions offer unprecedented capabilities in pollution monitoring, waste management, and climate change adaptation. From predictive analytics for air quality assessment to real-time monitoring of deforestation patterns, AI empowers stakeholders with actionable insights to mitigate environmental degradation and foster resilience. Simultaneously, AI applications hold promise in addressing socio-economic inequities through innovative approaches to poverty alleviation, financial inclusion, and inclusive growth strategies. By leveraging predictive modelling and data analytics, AI facilitates targeted interventions tailored to the unique needs of marginalized communities, thereby fostering sustainable development trajectories. However, the ethical and regulatory dimensions of AI deployment necessitate careful consideration within the legal framework. Ensuring data privacy, algorithmic transparency, and equitable access emerges as imperatives in harnessing the full potential of AI for societal benefit. Through the formulation of robust regulatory frameworks and ethical guidelines, the legal system plays a pivotal role in safeguarding against potential risks and maximizing the societal dividends of AI innovation. Moreover, interdisciplinary collaboration and stakeholder engagement are paramount in navigating the evolving landscape of AI governance, fostering dialogue, and consensus-building among diverse stakeholders. Thus, this paper advocates for a holistic approach to sustainable development, synergizing the transformative potential of AI with the protective mechanisms of the legal system. By fostering innovation, inclusivity, and accountability, this symbiotic relationship serves as a catalyst for advancing the global agenda towards a more equitable, resilient, and sustainable future. Keywords: Artificial Intelligence, Climate Change Adaptation, Deforestation, Education, Healthcare, Legal System, Pollution, Poverty, Sustainable Development Goals, Water and Waste Management.

Clustering data analytics of urban land use for change detection

In this study, the author proposes and details a workflow for the spatial-temporal demarcation of urban areal features in 8 cities of Tamilnadu, India. During the inception phase, functional requirements and non-functional parameters are analyzed and designed, within a suitable pixel area and object-oriented derived paradigm. Land use categories are defined from OpenStreetMap (OSM) related works with the scope of conducting climate change, using multispectral sensors onboard Landsat series. Furthermore, we augment the bands dataset with Spatially Invariant Feature Transform (SIFT), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Leaf Area Index (LAI), and Texture base indices, as a means of spatially integrating auto-covariance to stationarity patterns. In doing so, change detection can be pursuit by scaling up the segmentation of regional/zonal boundaries in a multi-dimensional environment, with the aid of Wide Area Networks (WAN) cluster computers such as the BEOWULF/Google Earth Engine clusters. GeoAnalytical measures are analyzed in the design of local and zonal spatial models (GRID, RASTER, DEM, IMAGE COLLECTION). Finally, multi variate geostatistical works are ensued for precision and recall in predictive data analytics. The author proposes reusing machine learning tools (filtering by attribute-based indexing in PaaS clouds) for pattern recognition and visualization of features and feature collection.

Multiple Correspondence Analysis for Assessment of the Socioeconomic and Social Impact of the COVID-19 Pandemic in Gezira State, Sudan

Background COVID-19 spread in Sudan like other countries in the world. The first COVID-19 case in Sudan was confirmed on 13 March 2020. It has been shown that Sudan's economy was affected before the COVID-19 pandemic because of currency increases, high inflation, and the incapability of the authorities to propose support. Methods The study aimed to assess the economic and social influence of COVID-19 in Al Gazira State, Sudan. This study used the primary data collected from Gezira state in Sudan. A structured questionnaire was used for data collection in 2020-2021, and the sample size was 800 participants. An analysis of multiple correspondences was used to analyze the data concerning COVID-19. The study was validated by ensuring that the survey follows sound research methodologies. This includes clearly defining research questions, using appropriate data collection methods, and applying rigorous analytical techniques. Besides that, it is important to explore the impact of the socioeconomic, demographic, and geographic variables. Results The educational level distribution shows that 36.7% of urban and 26.6% of rural residents have completed secondary education. Furthermore, all participants, 100% in urban regions and 99% in rural areas, were aware of the COVID-19 epidemic. Likewise, all participants in urban areas and 99.5% in rural areas were informed about the lockdowns and measures to curb the spread of COVID-19. Concerning the decision to refrain from attending social gatherings amid COVID-19, 87.6% of participants in urban areas and 75.3% in rural regions opted to cancel such events. Similarly, 86.2% in urban areas and 73.4% in rural areas believe avoiding handshakes is necessary to mitigate the spread of COVID-19. Regarding concerns about job loss during the COVID-19 lockdown period, 52.4% of rural participants did not express anxiety about potential job loss. Conversely, 55.3% of respondents in rural areas were indeed anxious about possibly losing their jobs. The results obtained from the multiple correspondence analysis revealed a relationship between the socioeconomic and demographic variables concerning COVID-19 epidemics. Conclusion This study concluded that socioeconomic, demographic, and geographic variables have a combined influence on the COVID-19 epidemic. One potential technical contribution to the assessment of the economic and social impact of the COVID-19 pandemic could be the application of sophisticated data analysis and modeling techniques to comprehend the complex interrelationships among the numerous components impacted by the pathogen. Predictive models, machine learning, data analytics, simulation studies, and geographic analysis are a few examples of similar techniques.

Smart traffic forecasting: leveraging adaptive machine learning and big data analytics for traffic flow prediction

The issue of road traffic congestion has become increasingly apparent in modern times. With the rise of urbanization, technological advancements, and an increase in the number of vehicles on the road, almost all major cities are experiencing poor traffic environments and low road efficiency. To address this problem, researchers have turned to diverse data resources and focused on predicting traffic flow, a crucial issue in Intelligent Transportation Systems (ITS) that can help alleviate congestion. By analyzing data from correlated roads and vehicles, such as speed, density, and flow rate, it is possible to anticipate traffic congestion and patterns. This paper presents an adaptive traffic system that utilizes supervised machine learning and big data analytics to predict traffic flow. The system monitors and extracts relevant traffic flow data, analyzes and processes the data, and stores it to enhance the model's accuracy and effectiveness. A simulation was conducted by the authors to showcase the proposed solution. The outcomes of the study carry substantial implications for transportation systems, offering valuable insights for enhancing traffic flow management.

Clustering data analytics of urban land use for change detection

In this study, the author proposes and details a workflow for the spatial-temporal demarcation of urban areal features in 8 cities of Tamilnadu, India. During the inception phase, functional requirements and non-functional parameters are analyzed and designed, within a suitable pixel area and object-oriented derived paradigm. Land use categories are defined from OpenStreetMap (OSM) related works with the scope of conducting climate change, using multispectral sensors onboard Landsat series. Furthermore, we augment the bands dataset with Spatially Invariant Feature Transform (SIFT), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Leaf Area Index (LAI), and Texture base indices, as a means of spatially integrating auto-covariance to stationarity patterns. In doing so, change detection can be pursuit by scaling up the segmentation of regional/zonal boundaries in a multi-dimensional environment, with the aid of Wide Area Networks (WAN) cluster computers such as the BEOWULF/Google Earth Engine clusters. GeoAnalytical measures are analyzed in the design of local and zonal spatial models (GRID, RASTER, DEM, IMAGE COLLECTION). Finally, multi variate geostatistical works are ensued for precision and recall in predictive data analytics. The author proposes reusing machine learning tools (filtering by attribute-based indexing in PaaS clouds) for pattern recognition and visualization of features and feature collection.

Data analytics for predicting disease outbreaks: A review of models and tools

The burgeoning field of data analytics has emerged as a pivotal force in the realm of public health, particularly in the context of predicting and mitigating disease outbreaks. This comprehensive review delves into the diverse landscape of models and tools employed in data analytics for disease outbreak prediction. With a focus on synthesizing existing knowledge, the paper aims to provide a nuanced understanding of the strengths, limitations, and future directions within this dynamic field. The review begins with an exploration of various models utilized for disease outbreak prediction, ranging from statistical approaches to machine learning models and epidemiological frameworks. Each model category is scrutinized for its efficacy in capturing the complexities inherent in infectious disease dynamics. Simultaneously, the paper investigates the array of tools and technologies leveraged in disease outbreak prediction, encompassing Geographic Information Systems (GIS), data visualization tools, and big data analytics platforms. A critical aspect of the review lies in the examination of diverse data sources contributing to predictive analytics. Epidemiological data, environmental factors, and the burgeoning influence of social media and web data are dissected for their roles in enhancing the accuracy and timeliness of outbreak predictions. Amidst the promises of data analytics, the paper navigates the challenges inherent in predicting disease outbreaks. Issues of data quality and availability, model complexity, interpretability, and ethical considerations are dissected, providing a holistic view of the hurdles that practitioners encounter. Drawing upon case studies and real-world applications, the review showcases instances where data analytics has proven successful in predicting disease outbreaks, shedding light on both triumphs and setbacks. The implications for public health, lessons learned from challenges, and the evolving role of data analytics in shaping global health preparedness are thoroughly discussed. As the paper unfolds, it illuminates future trends and innovations in the field, foreseeing the integration of advanced technologies, global collaboration for information sharing, and the adaptation of predictive analytics for emerging diseases. The review culminates in a comprehensive conclusion, summarizing key findings and emphasizing the potential transformative impact of data analytics on the landscape of disease outbreak prediction.

Big Data Analysis for Product Demand Prediction in Indonesian E-commerce

The Indonesian e-commerce sector has witnessed exponential growth in recent years, necessitating effective strategies for predicting product demand to meet consumer expectations and stay competitive. Leveraging big data analytics offers a promising solution to this challenge, allowing businesses to harness vast volumes of data to forecast demand accurately. This research explores the utilization of big data analysis for product demand prediction in Indonesian e-commerce through a qualitative analysis approach. Interviews with e-commerce executives, data scientists, and industry experts revealed key themes, including data quality and integration, analytical techniques and tools, and organizational culture and capability. Results highlight the challenges, opportunities, and best practices associated with leveraging big data analytics for demand prediction in Indonesian e-commerce, providing valuable insights for businesses striving to optimize their predictive capabilities and enhance decision-making processes in this dynamic and rapidly evolving market.

Artificial Intelligence: Opportunities and Challenges for the Social Education and Profession

Artificial intelligence (AI) is rapidly advancing and holds both opportunities and risks for the social work profession. This review article provides an analysis of the potential applications and implications of AI technologies for social work practice, education, research, and ethics. The article highlights promising uses of AI tools like predictive risk models, virtual simulations, chatbots, and data analytics to enhance social work services and training. However, it also critically examines the ethical considerations and social justice concerns related to the integration of AI in social work, including issues of privacy, transparency, accountability, consent, bias, displacement of roles, and threats to human dignity. To responsibly leverage AI's benefits while mitigating its risks, the article offers recommendations for social workers to collaborate on AI design, follow ethical protocols, pursue education on AI, and conduct further research. Key areas for future research identified include studying client perspectives on AI, testing the efficacy of AI systems for social work tasks, auditing algorithms for bias, and analyzing AI's impact on social work employment. In conclusion, while acknowledging AI's significant potential, the article emphasizes that purposeful oversight, participatory design, and adherence to social work values must remain priorities to ensure AI promotes dignity, autonomy, and justice. This review provides a balanced, evidence-based analysis to inform discussions on optimizing AI's integration in the social work profession.

Railway safety through predictive vertical displacement analysis using the PINN-EKF synergy

Scientific Machine Learning (SciML) finds extensive application in daily life, industry, and scientific research. Specifically, in railway data analysis, it utilizes tools such as time series analysis, classification, and data visualization. Among these, monitoring vertical displacement, or the movement of railway components relative to a fixed point, is vital. This indicates changes in the elevation of railway infrastructure, highlighting track settlement and structural shifts. However, relying solely on single sensor measurements for these displacement calculations can introduce inaccuracies. To overcome this, sensor fusion techniques are employed. These techniques employ advanced algorithms to combine data from multiple sensors, thereby enhancing accuracy. They consider the individual characteristics of each sensor, effectively mitigating the limitations of any single sensor. This study introduces a hybrid approach that combines the Extended Kalman Filter (EKF) with the Physics-Informed Neural Network (PINN) to refine predictive data analytics in dynamic railway environments. The experimental results underscore the efficacy of this innovative methodology.

Optimizing Electric Vehicle Performance, Range and Parameter Estimation through NEDC Urban and Suburban Analysis using MATLAB

This research paper focuses on electric vehicle (EV) driving range and parameter estimation, with an emphasis on analyzing the New European Driving Cycle (NEDC) urban and suburban drive cycles. By examining these drive cycles, we obtain critical data on the moments when an electric vehicle transitions between constant velocity, acceleration, and deceleration phases, which significantly affect power consumption and driving range. We investigate various techniques for parameter estimation, including battery capacity, energy consumption rates, and powertrain efficiency, essential for improving EV performance and providing realistic range expectations. Empirical experiments in diverse driving conditions contribute valuable data to refine our understanding of EV driving range and performance in different scenarios. The research underscores the role of predictive modeling, data analytics, and advanced technologies in real-time parameter estimation, offering precise and convenient range predictions to enhance user confidence.

Advanced Drilling Optimization through Predictive Data Analytics and Machine Learning Pipeline

The paper provides a pattern and methodology to optimize drilling in the oil and gas industry through integration of data analytics and machine learning. Drilling operations have unpredictable subsurface conditions, which leads to operational inefficiencies. My methodology ingests historical drilling data, real-time sensor data, and geological data to train machine learning models. I discuss the implementation and analysis of a data analytics framework that collects and preprocesses data streams, and send the data for machine learning. The paper offers keywords aimed at enhancing discoverability, indexing, clarity, and visibility. The introduction section details context, relevance, objectives, scope and structure of the paper. The Problem Statement section details business problem. The solution section provides methodology to address the identified problem. The architecture diagram section illustrates the system architecture and design. The architecture review details the selected architecture. The implementation section provides steps to implement solution, detailing the specific tools, technologies, and methodologies utilized in its development. The implementation for Proof of Concept (PoC) section provides a strategy as how to plan for the implementation of the solution at the organization level. The use cases section provides details about what a business can derive information to make decision. The impact section details the business value. The extended use case section so how the proposed solution can be implemented across diverse industries and domains, highlighting the potential for widespread applicability.

Artificial Intelligence Applications in Natural Gas Industry: A Literature Review

One of the more controversial uses of artificial intelligence (AI) in the petroleum industry has been in technological advancement. The gas business generates data on a constant basis from several operational procedures. The gas sector is now very concerned about recording these data and using them appropriately. Making decisions based on inferential and predictive data analytics facilitates timely and accurate decision-making. The gas business is seeing a significant increase in the use of data analytics for decision-making despite numerous obstacles. Considerable progress has been made in the aforementioned field of study. With the use of artificial intelligence (AI) and machine learning (ML) techniques, many complicated issues may now be resolved with ease. This study, which looks at artificial intelligence applications in the natural gas sector, collected its data from numerous sources between 2005 and 2023. The current work might offer a technical framework for selecting pertinent technologies that will enable efficient information extraction from the massive amount of data produced by the gas industry.

Revisiting operations agility and formalizing digitalization in response to varying levels of uncertainty and customization

This paper aims to find how digitalization supports inter-organizational purchasing/order fulfillment processes and the required agility to respond to supply/demand uncertainties. The research method includes multiple case studies. Qualitative data are collected via interviews and documentation review. Within-case and cross-case analyses of the research lead to 14 propositions and a novel framework, which formalize and link agility and digitalization at different levels. The research findings point out the agility in micro and macro types for the demand and supply sides of the business, responding to different levels of uncertainties. The findings categorize the relevant applications of digitalization at three levels: data interchange, data integration, and predictive data analytics. Moreover, the agility-digitalization relationships are defined for different levels of customization, represented by customer order decoupling points. This paper contributes to the literature by offering an in-depth and explicit understanding of the impacts of digitalization on different types of agility for different levels of customization.