Big AI Research Articles

AI-driven Educational Evaluation Innovation: Construction and Practice of Big Data Analysis and Intelligent Evaluation System

This study offers an intelligent education assessment model incorporating Big Data and AI technology, and built a complete technical framework including data collection, optimization of algorithms and dynamic feedback. According to the empirical test of 12 schools, the system response speed is increased by 40% and the precision rate is increased to 92.3% compared to the traditional evaluation method. The Core algorithm module performs real -time analysis of the learning behavior trajectory and forms a personalized evaluation card. Experimental data show that the system can effectively capture 78% of unconventional learning characteristics and improve the accuracy of educational interventions by 2.1 times. Look for and develop the visual analysis platform at the same time, and operating efficiency on the teacher side is improved by 60% compared to the old system. These technological breakthroughs offer a way achievable for the digital transformation of education assessment, in particular in the formulation of differentiated teaching strategies. The search for follow-up will focus on the elimination of the strangulation neck of the merger of multi-round data and the exploration of the potential for applying advanced computer science in real-time feedback.

Implications of digital twin applications on management accounting practices to support competitive advantage: A foresight view from the Saudi business environment

The study addresses the transformative implications of digitalization, notably the integration of digital twins, in various manufacturing and management application areas, including accounting information systems, operational costs, and organizational changes. It emphasizes the need for comprehensive policies and training programs to enhance preparedness and adaptability within Saudi organizations while highlighting the importance of robust cybersecurity measures and strategic partnerships with technology providers. This study applied exploratory research and a qualitative case study to collect data using multiple tools such as interviews, observations, and content analysis. The findings emphasize the proactive and forward-thinking approach required for organizations to effectively navigate the digital landscape, embrace emerging technologies, and maintain flexibility to drive growth and success. The study's primary objective is to enhance the comprehension of how digital twins can generate additional value and provide a competitive edge within the Saudi business landscape. This emphasizes the significance of utilizing digital technologies to maintain a leading position in the global market. The research enhances our understanding of how Digital Twins can bolster management analytics (MA) practices to gain a competitive advantage, yet it underscores a significant gap for future studies. Current investigations have largely centered on individual technologies, such as big data, AI, or IoT, concerning MA, rather than exploring the intricate interactions among multiple technologies within Digital Twins. A more in-depth examination of these integrations across different applications is essential to identify the challenges and impacts on MA practices, especially considering the reliance on extensive unstructured data. However, the findings are somewhat limited as they are derived from a case study of a leading energy company, which may not accurately represent broader circumstances due to diminished uncertainty and competitive pressures. Future research should investigate these associations across varied contexts to deepen our understanding.

A Systematic Literature Review on the Evolving Landscape of the Shadow Economy and Tax Evasion: Global Challenges in the Digital Age

ABSTRACT This study conducts a Systematic Literature Review (SLR) of 115 articles (2010–2025) using the PRISMA methodology to explore the nexus between the shadow economy, tax evasion, and international tax policy effectiveness. The findings highlight that despite initiatives like BEPS, CRS, and AEOI, tax evasion persists due to regulatory disparities, legal loopholes, and emerging financial technologies. The shadow economy continues to erode revenues and deepen inequality. The study advocates for greater transparency, advanced digital tax systems leveraging big data and AI, and enhanced tax literacy to strengthen compliance and safeguard global fiscal stability.

Leveraging Big Data and AI for Personalized Healthcare Solutions in Smart Cities

The emergence of smart cities brings with it new challenges and opportunities regarding personalized healthcare services. The prevalence of chronic diseases, an aging population, and a rising need for efficient health management have put additional demands on healthcare to seek innovative solutions. This study discusses big data and AI integration to provide personalized healthcare services in smart cities. A quantitative research approach was implemented based on data from wearable devices, environmental sensors, and healthcare records. Health data analytics utilized machine learning algorithms, including decision trees and neural networks, to construct predictive models in the management of chronic diseases and early warning systems. Preprocessing and analysis of data were done using Python, R, and Hadoop to ensure accuracy and scalability. The AI models achieved an accuracy of 85% in the identification of early symptoms of chronic diseases like diabetes and cardiovascular conditions. A 20% increase in citizen satisfaction concerning healthcare services was noticed in those regions that implemented this model of AI-driven health management. Besides this, proactive alerts generated by the model resulted in a measurable decrease in the rate of progression of diseases, particularly in elderly populations. The results prove that AI can bring transformational changes to personalized healthcare in smart cities, in line with global research trends. These findings are academically significant in offering new methods of data analysis and are of practical value for policymakers in the design of efficient health management strategies. Limitations include regional bias and data privacy challenges. Future research should be directed toward a wider integration of data, advanced protection of privacy, and scalable solutions across cities to maximize the impact of AI-driven healthcare.

Toward Smart and Sustainable Port Operations: A Blue Ocean Strategy Approach for the Spanish Port System

The digital transformation of the maritime sector, driven by Industry 4.0, is reshaping port operations toward smarter and more sustainable models. This paper analyzed the implementation of Port 4.0 technologies in the Spanish port system through the lens of the Blue Ocean Strategy. By redefining competitive boundaries and applying tools such as the Four Actions Framework and value innovation curves, the study proposes a new strategic vision where ports collaborate rather than compete. Key enabling technologies (such as Big Data, IoT, AI, and Blockchain) were assessed for their capacity to optimize energy use, reduce emissions, and enhance operational efficiency. The findings highlight the potential for a unified, data-driven port ecosystem that creates a new uncontested market space for Spanish ports while promoting environmental and economic sustainability.

Integrating Big Data and AI in Nutrition

Food nutrition is the source of heat energy in human body. The human body obtains nutrients from food, such as proteins, fats, carbohydrates and so on. Nutrition is very important for human health. The technology is used in every sectors. Indeed, AI is emerging as an important tool in clinical nutrition using telematic means to self-monitor various health metrics, including blood glucose levels, body weight, heart rate, fat percentage, blood pressure, activity tracking and calorie intake trackers. In particular, the most common application of digital technology is in the area of nutrition. Data Analytics and similar technologies play a leading role, and here in this paper different aspect related to the Big-data and Artificial Intelligence with references to the Food and Nutritional Systems have been described with current and future scenario. The existing works related to the fields are well described and reported with major highlights.

Big Tech, Big Energy, and AI

Big Tech, Big Energy, and AI

The Impact of Digital Transformation Technology in Enhancing Organizational Creativity

The research examines the role of digital technologies in organizational creativity in a telecommunications and information technology company, emphasizing innovation and strategic decision-making fostered by these digital tools such as Internet of Things (IoT), big data analytics, artificial intelligence, cloud computing, and cyber systems. The study followed a quantitative research approach, whereby a Likert-scale questionnaire was administered among 100 senior and middle managers. The collected data were analyzed using SPSS software to measure relationships between digital transformation and creativity dimensions. The analysis found that digital transformation shows a positive and significant impact on organizational creativity. It was found that cloud computing has the highest effect on accelerating innovation through enhanced access to data and process optimization. Cyber systems also provided increased security and operational efficiency, while big data analytics and AI were enablers for better decision-making and creative problem-solving. Some barriers for complete implementation included insufficient strategic planning, as well as resistance to change. The research concludes that an organization needs to have a flexible and adaptive digital strategy to maximize creativity and keep its competitive edge. Future studies should focus on exploring long-term implications of the digital transformation on organizational culture and innovation sustainability.

Development of the Methodology and Mathematical Tools for Strategic Decision-Making Process Modeling of the Digital Business Ecosystem

This article presents a methodology of the decision-making process using mathematical tools, which can become a practical tool for decision-makers on the functioning and strategic development of business ecosystems and their components depending on changes in the internal, micro- and macroenvironment. An algorithm for finding linearly independent elements of digital business ecosystems and a new option for interpreting their results are developed. It is proposed that this impact be determined by calculating the eigenvectors of the matrix and identifying the dependence through the contribution of the eigenvectors to the overall mechanism of the system. A system analysis of the properties of business ecosystems is carried out with a subsequent description of the methodology for studying the impact of financial indicators on it. As an example of data for calculation, the article uses Yandex data for 2023, as the most indicative business ecosystem with all the necessary properties. The results of the study allow formulating recommendations for top management on making management decisions and points of application of efforts. Combining the developed methodology with promising technologies for automated calculation of big data and AI will provide a flexible management tool with the possibility of its further development.

Digital Technology Adoption and Its Impact on Third-Party Logistics Service Providers in Tamil Nadu

The paper mainly focused on third-party logistics as the central part of the changes that have undergone quick development in digital technologies. It helps to improve service delivery and maintain competitiveness in changing markets to streamline operations. 3PL should provide TN, the center of manufacturing, trade, and logistics in India. This research study mainly explained that the 3PL services are provided to the TN used by digital technology. It also explored the various effects related to overall performance, cost reduction, and operational efficiency. These technologies impact cloud computing, big data analysis, warehouse automation, AI, and real-time tracking systems. The research findings are that digital technologies provide productivity to improve customer communications. Most digital platforms are enabled by delivering various services, such as response time, personalized solutions, and real-time tracking. Challenges include high implementation costs and data security. This research study mainly benefited from digital advancements. Digital technology adoption has various key factors, along with expansion and competitiveness among Tamil Nadu 3PLs.

Symmetrical Resilience: Detection of Cyberattacks for SCADA Systems Used in IIoT in Big Data Environments

In recent years, Internet of Things (IoT) systems are used in Industrial Internet of Things (IIoT) systems due to their widespread use in industrial sectors, providing convenience to users in SCADA systems, like other domains. In addition to the diverse technological advancements discussed, the inherent symmetry within the network structures of SCADA systems utilized in the IIoT echoes a fundamental balance sought in digital frameworks. However, along with the advantages of IIoT systems, there are also disadvantages, one major drawback being their vulnerability to attacks. It has been observed that advanced methods such as artificial intelligence, unlike traditional detection techniques, are more successful at detecting attacks on IIoT systems used in SCADA systems. The proposed model was developed to detect cyberattacks on SCADA systems using machine learning and deep learning models. The SCADA network traffic consists of over 7 million rows and has a size of 627 MB. Attack network traffic refers to the type of traffic aimed at causing damage to the system. The attack traffic in this study includes five different attacks. Normal traffic is the type of traffic that facilitates the system’s usual communication. Prepared network traffic is not a different type of traffic. Prepared network traffic, as named, is the state of the traffic dataset that has been made ready for analysis with models. The prepared network traffic was examined using eight machine learning models, including the CART, Decision Tree, KNN, Logistic Regression, Naive Bayes, Random Forest, SVM, and XGBoost models, as well as seven deep learning models, namely, CNN, GRU, LSTM, MLP, RNN, CNN-LSTM, and LSTM-CNN. During the evaluation of the models, performance parameters such as the accuracy, F-score, precision, and recall were considered, and the results are presented accordingly. Upon examining the dataset with various models, the highest outcomes were achieved using the MLP model. The investigation utilizing the MLP model resulted in an accuracy of 99.95%, a precision of 99.63%, a recall of 99.49%, and an F-score of 99.56%. These values were obtained with a batch-size combination of 100 and 20 epochs. By addressing cyberattack detection in SCADA systems used in the IIoT within a big data environment, the study encompasses a multidisciplinary approach, touching upon cybersecurity, big data analytics, AI, information security, and IoT-related concerns, all of which are focal points within the scope of the journal. This breadth and depth of coverage make the study highly relevant and aligned with the diverse interests of the journal.

Stakeholder interactions and ethical imperatives in big data and AI development

Stakeholder interactions and ethical imperatives in big data and AI development

빅데이터와 인공지능 시대 미디어학의 연구 동향

빅데이터와 인공지능 시대 미디어학의 연구 동향

Digital remote monitoring of people with multiple sclerosis.

Multiple sclerosis (MS) is a chronic neurodegenerative disease that affects over 2.8 million people globally, leading to significant motor and non-motor symptoms. Effective disease monitoring is critical for improving patient outcomes but is often hindered by the limitations of infrequent clinical assessments. Digital remote monitoring tools leveraging big data and AI offer new opportunities to track symptoms in real time and detect disease progression. This narrative review explores recent advancements in digital remote monitoring of motor and non-motor symptoms in MS. We conducted a PubMed search to collect original studies aimed at evaluating the use of AI and/or big data for digital remote monitoring of pwMS. We focus on tools and techniques applied to data from wearable sensors, smartphones, and other connected devices, as well as AI-based methods for the analysis of big data. Wearable sensors and machine learning algorithms show significant promise in monitoring motor symptoms, such as fall risk and gait disturbances. Many studies have demonstrated their reliability not only in clinical settings and for independent execution of motor assessments by patients, but also for passive monitoring during everyday life. Cognitive monitoring, although less developed, has seen progress with AI-driven tools that automate the scoring of neuropsychological tests and analyse passive keystroke dynamics. However, passive cognitive monitoring is still underdeveloped, compared to monitoring of motor symptoms. Some preliminary evidence suggests that application of AI and big data to other understudied aspects of MS (namely sleep and circadian autonomic patterns) may provide novel insights. Advances in AI and big data offer exciting possibilities for improving disease management and patient outcomes in MS. Digital remote monitoring has the potential to revolutionize MS care by providing continuous, long-term granular data on both motor and non-motor symptoms. While promising results have been demonstrated, larger-scale studies and more robust validation are needed to fully integrate these tools into clinical practice and generalise their results to the wider MS population.

Big Data and Blockchain Synergies in Healthcare: Opportunities for Enhanced Decision-Making and Operational Management

Healthcare can only benefit from the integration of Big Data and Blockchains that improve decision making, operational management and data security. This research examines how Big Data analytics and AI driven algorithms can improve patient care, resource allocation, and predictive modeling as well as Blockchain technology to assures data lapses, integrity, privacy, and supply chain security. Four healthcare data analysis focused approaches, i.e., Federated Learning, Time-Series Prediction, Deep Learning and Smart Management Information Systems were implemented. By using the proposed model, the accuracy on disease prediction, fraud detection and medical supply chain management are achieved 95.4, 87.6 and 92.3 respectively, and are better than existing centralized systems. Related work comparative analysis reveals that solutions leveraging Blockchain into Big Data have better security, scalability, and real time processing when compared to standard Big Data. Finally, the study shows that privacy preserving AI models integrated with decentralized blockchain ledgers can decrease data breach by 74.2 percent and optimize the decision making of medical problems by 89.5 percent. While faced by regulatory impediments and interoperability difficulties, the findings emphasize the big data and Blockchain synergy as a potent means to revolutionize the healthcare managements. The focus in future research should be on scalability improvements, regulations for cross border data sharing and optimization of the Blockchain for real time processing in order to take full advantage of this technology.

The Convergence of Curating and Technology: A Multidimensional Perspective on Practice

Curation has traditionally been a static practice confined to physical spaces, focusing primarily on the display and interpretation of artworks. However, with the rapid development of digital technologies such as VR, AR, and AI, curatorial practices have evolved, integrating virtual and interactive elements that expand beyond physical locations. This study investigates the impact of digital technologies on contemporary curatorial practices, exploring how tools like big data, VR, and AI are transforming the way curators create interactive, immersive, and multi-layered exhibition experiences. Through case studies and analysis of curatorial projects utilizing these technologies, the research examines the ethical, political, and aesthetic dimensions of curatorial practices and explores the role of technology in enhancing curatorial precision, expanding spatial boundaries, and enabling new forms of audience engagement. The study finds that technologies such as VR and AI provide curators with innovative tools to create dynamic and participatory exhibitions. However, it also highlights the ethical risks associated with overusing technology, including the potential commodification of exhibits and the diminished focus on physical artworks. Digital technologies offer significant potential for expanding and enriching curatorial practices, transforming curation into a bridge between art, culture, and society. Nevertheless, these innovations come with challenges, requiring curators to balance technological integration with maintaining the integrity of traditional curatorial values across ethical, political, and aesthetic dimensions.

Queer ecological data: Where artificial intelligence meets the avian

Nonhuman life is increasingly analyzed and acted upon through big data and AI tools. Birds in particular are among the most datafied wild beings. However, avian—like human—data sets present challenges of bias, misclassification, and harmful collection methods. For example, avian data includes bias along lines of sex and sexuality, female, queer, and intersex birds are significantly understudied. These missing birds not only represent consequences for biodiversity loss but also “naturalize” assumptions about sex and sexuality for all species, including humans. In this article, we interrogate avian datafication practices and introduce Salvaging Birds, a multimodal project proposing “queer data surrogacy” as a method for generating “queer ecological data,” that is data resisting normative environmental frameworks. Here queer data surrogates were produced by creatively subverting AI toward generating speculative missing birds. Bridging critical data and archival studies with queer ecology, we argue that data logics demand examination at nonhuman sites and scales.

UTILIZING AI MODELS TO IDENTIFY AND PREDICT MOOD TRANSITION PATTERNS IN PATIENTS WITH BIPOLAR DISORDER

Abstract Bipolar disorder is characterized by recurrent episodes of depression and mania, making diagnosis and treatment challenging, often leading to poor prognosis. Predicting future episodes based on the assessment of current and past emotional phases in patients can offer valuable insights for clinicians, aiding in the prevention of misdiagnosis and relapse, and in intervention strategies. This study included 812 patients with bipolar disorder from 9 centers, who were assessed online or offline using BDCC, YMRS, and HAMD tools. We employed four AI methodologies to learn from the assessment results and time series, ultimately predicting future emotional phases of the patients. By learning from current assessment results to predict the next emotional phase, the AUCs of the four models were 0.81, 0.70, 0.84, and 0.81, respectively. External validation on 30-day and 90-day emotional phase follow-ups of patients showed prediction accuracies of 0.9, 0.65, 0.86, and 0.62 for each model. While predictive efficacy decreased over time, the average AUC remained above 0.75 at 180 days. Our findings suggest that utilizing big data and AI methods can effectively learn the characteristics of emotional phase transitions in bipolar patients, achieving high accuracy. This model holds significant value for clinical diagnosis and medication guidance for clinicians

Harnessing AI and Open Data Analytics to Combat Social Inequities Among Adolescents: 2024-25 High School Big Data and AI Challenge

The STEM Fellowship High School Big Data and AI Challenge provides students with a unique opportunity to utilize Open Data to investigate one of the UN Sustainable Development Goals while learning data science fundamentals in an experiential learning format – an essential skill set for a young researcher in the digital age. This year students tackled the challenge of Harnessing AI and Open Data Analytics to Combat Social Inequities Among Adolescents. Students suggested their own evidence-based solutions following the principles of Open Science. They investigated different topics, ranging from Optimizing Educational Equity to Advancing Equity for Disabled Youth. These future leaders were tasked with using Open Data to enhance our understanding of social inequities and explore areas for innovation to close inequity gaps and propagate the social pursuit of prosperity for all. Various topics were investigated, identifying different forms of socioeconomic determinants which impact inequity among adolescents on a global scale. By applying computational thinking, students explored the interplay between adolescent inequities and external factors, ultimately contributing to the development of new educational and social development approaches. STEM Fellowship has designed an interdisciplinary, agile educational environment with in-depth learning modules for students as a means to bridge the gap between traditional high school courseware and computational inquiry. Students learned how to uncover hidden patterns and trends in structured and unstructured data using a range of data analytics tools and programming languages. Python, R, LaTeX, and machine learning were some of the tools the students learned and used throughout the program. Additionally, all participants prepared a short slideshow and presented their research to a group of their peers. We are privileged to witness the analytical capabilities of this talented generation of students, and we are confident that they will demonstrate excellence throughout their academic and professional careers. The Western Canada and Eastern Canada finalist events were the culmination of the top participants’ trailblazing research, and were held at the Hunter Hub for Entrepreneurial Thinking at the University of Calgary in Calgary and at Microsoft Canadian Headquarters in Toronto respectively. On behalf of the STEM Fellowship, we extend our sincere congratulations to all students who participated in the challenge and wish them the best for all of their future endeavours. We also want to express our appreciation to all of the STEM Fellowship volunteers who made this challenge possible. We greatly appreciate the patronage of the program by the Canadian Commission for UNESCO, as well as the Lieutenant Governor of Alberta and the Lieutenant Governor of Ontario. We want to thank Canadian Science Publishing, Environment and Climate Change Canada, Let’s Talk Science, National Research Council Canada, RBC Future Launch, SciNet at the University of Toronto, Hunter Hub at the University of Calgary, Microsoft Canada, Canadian Science Publishing, Overleaf, and Cisco Academy for their invaluable support.

The Role of Azure Data Lake in Scalable and High-Performance Supply Chain Analytics

Growing complexity in global supply chains demands high- performance, scalable data management capabilities. Azure Data Lake offers a cloud-based platform wherein organizations can store, process, and analyze vast volumes of structured and unstructured data in a cost-effective manner. This study discusses how Azure Data Lake elevates supply chain analytics through the convergence of big data technologies, AI, and ML models. It is a mixed-method study, with case studies and statistical analysis being used for performance improvement measurement in supply chain activities. The main findings indicate that companies utilizing Azure Data Lake experience enhanced real-time decision-making, improved demand forecasting, and reduced inefficiencies in operations. However, challenges such as data protection and system integration persist. The paper concludes with sugges- tions for further research and strategies for optimizing Azure Data Lake utilization in supply chain analytics.