Search Results (652)

This study investigates how cognitive and self-regulation factors impact online interview performance among college students with ADHD. With unemployment rates for individuals with disabilities significantly higher than the general population, understanding the unique challenges posed by AI-driven virtual interviews is critical. Forty-six students with ADHD completed a structured interview simulation using the Big Interview platform, coupled with eye-tracking data and cognitive assessments. Results reveal that higher-performing participants (Gold tier) demonstrated a balanced focus on content comprehension and interviewer engagement, while lower-performing participants (Bronze tier) spent significantly more time on content fixation. Logistic regression indicated that cognitive flexibility, as measured by NIH Dimensional Card Sorting, predicts interview success, emphasizing the importance of task-switching skills in virtual environments. These findings suggest the need for targeted interventions, such as executive function training, to prepare neurodivergent individuals for the demands of AI-driven hiring practices. The study highlights the potential of psychophysiological metrics in understanding and enhancing interview performance, advocating for inclusive, evidence-based strategies that align with Diversity, Equity, Inclusion, and Belonging (DEIB) principles. This research provides actionable insights for educators, employers, and technology developers aiming to create accessible and equitable virtual interview platforms. Full article

Generative artificial intelligence (GenAI) technologies based on big language models are becoming a transformative power that reshapes the future shape of education. Although the impact of GenAI on education is a key issue, there is little exploration of the challenges and response strategies of GenAI on the sustainability of education from a public perspective. This data mining study selected ChatGPT as a representative tool for GenAI. Five topics and 14 modular semantic communities of public attitudes towards using ChatGPT in education were identified through Latent Dirichlet Allocation (LDA) topic modeling and the semantic network community discovery process on 40,179 user comments collected from social media platforms. The results indicate public ambivalence about whether GenAI technology is empowering or disruptive to education. On the one hand, the public recognizes the potential of GenAI in education, including intelligent tutoring, role-playing, personalized services, content creation, and language learning, where effective communication and interaction can stimulate users’ creativity. On the other hand, the public is worried about the impact of users’ technological dependence on the development of innovative capabilities, the erosion of traditional knowledge production by AI-generated content (AIGC), the undermining of educational equity by potential cheating, and the substitution of students by the passing or good performance of GenAI on skills tests. In addition, some irresponsible and unethical usage behaviors were identified, including the direct use of AIGC and using GenAI tool to pass similarity checks. This study provides a practical basis for educational institutions to re-examine the teaching and learning approaches, assessment strategies, and talent development goals and to formulate policies on the use of AI to promote the vision of AI for sustainable development in education. Full article

This paper developed an artificial intelligence home environment monitoring system by using the Android Studio development platform. A database was constructed within a server to store sensor data. The proposed system comprises multiple sensors, a message queueing telemetry transport (MQTT) communication protocol, cloud data storage and computation, and end device control. A mobile application was developed using MongoDB software, which is a file-oriented NoSQL database management system developed using C++. This system represents a new database for processing big sensor data. The k-nearest neighbor (KNN) algorithm was used to impute missing data. Node-RED development software was used within the server as a data-receiving, storage, and computing environment that is convenient to manage and maintain. Data on indoor temperature, humidity, and carbon dioxide concentrations are transmitted to a mobile phone application through the MQTT communication protocol for real-time display and monitoring. The system can control a fan or warning light through the mobile application to maintain ambient temperature inside the house and to warn users of emergencies. A long short-term memory (LSTM) model and a convolutional neural network (CNN) model were used to predict indoor temperature, humidity, and carbon dioxide concentrations. Average relative errors in the predicted values of humidity and carbon dioxide concentration were approximately 0.0415% and 0.134%, respectively, for data storage using the KNN algorithm. For indoor temperature prediction, the LSTM model had a mean absolute percentage error of 0.180% and a root-mean-squared error of 0.042 °C. The CNN–LSTM model had a mean absolute percentage error of 1.370% and a root-mean-squared error of 0.117 °C. Full article

This paper examines the role of digital economy tools, including big data, mobile applications, e-commerce, and sharing economy platforms, in the sustainable development of the tourism sector. The focus is on studying how the digital economy tools can contribute to more efficient and sustainable tourism services, to service quality improvement, to reducing the negative environmental impact, and thus increase the availability of tourism resources in local destinations. Using the example of the successful use of digital technologies in Russian regions, this paper discusses the introduction of online platforms for booking services, the use of mobile applications for navigation and obtaining information about tourist sites, as well as the use of digital tools for predicting consumer preferences. A systematic approach to the analysis of tourism services digitalization, based on a set of technical and functional–digital indicators, allowed us to evaluate the impact of the digitalization level on the local destination’s sustainable development in transition economy conditions. The proposed methodology for assessing and applying tourism services digitalization tools in Russian regions takes into account the transition economy specifics and aims to promote more sustainable practices. This study will add to the existing literature by defining both technical and functional criteria for the implementation of digital technologies as tools for the creation of new business models in tourism, and the development of a tourism services digitalization model, based on the assessment of the regional digitalization level, to ensure the movement towards achieving sustainable development goals in local destinations. Full article

This study aims to understand how InsurTech has developed in Korea. To achieve this, we collected InsurTech-related news articles published in the Korean media over the past eight years. Using a relatedness analysis based on the TopicRank algorithm, a text-mining technique, we extracted the top keywords associated with InsurTech by year. The extracted keywords were analyzed and discussed in terms of development trends: which technologies gained prominence over time, who the key players were, and what solutions were introduced. The analysis revealed several key trends in InsurTech’s development in Korea. First, regarding changes in InsurTech technology, blockchain and the Internet of Things initially garnered significant attention, but artificial intelligence and big data later emerged as more critical technologies. Second, in terms of market players, government agencies and research institutes initially created forums for discussion, such as seminars to draw social attention to InsurTech. Over time, innovative startups entered the market, general agencies specializing in insurance brokerage gained prominence in the online marketplace, and the entry of Big Tech platforms further diversified the market. Finally, in terms of InsurTech-related insurance solutions, early attention was focused on developing new products. However, the trend gradually shifted toward improving the accessibility and convenience of existing insurance services. Additionally, asset management and payment settlement services—linked to financial services beyond traditional insurance—emerged, along with new concepts such as healthcare, which reshaped the approach to insurance services. This study contributes to understanding how InsurTech has evolved by identifying key trends in emerging technologies, leading market players, and innovations in the insurance value chain. The Korean case provides insights that may help explore similar patterns in other countries. Full article

The rational development of urban underground space resources (UUSRs) is especially crucial for alleviating “urban diseases”, and it is of great significance for exploring the appropriateness of urban underground space (UUS) development under multiple constraints for the rational use of UUSRs. This research selects the UUS in Nantong City, Jiangsu Province, as the research object, and establishes an evaluation index system for the suitability of UUS development under the perspective of sustainable development, including terrain and geomorphology, engineering geological environment, hydrogeological environment, sensitive geological factors, the regional development level, and the distribution of ecological reserve, as well as other multi-source heterogeneous data. On this basis, the relationship between the appropriateness of underground space development and the utilization and various factors was studied. We constructed a comprehensive evaluation model for the suitability of UUS using the Analytic Hierarchy Process (AHP) and the multi-objective linear weighting method. The results of the study show that ecological protection constraints and geological hazards have a greater impact on the evaluation of suitability. The suitable and secondarily suitable areas for the development of the underground space in Nantong City account for 14.74% and 30.66% of the total area, respectively. These areas are mainly distributed in Rugao City and Chongchuan District. The less suitable and unsuitable areas account for 37.17% and 17.44%, with a significant concentration in near-sea areas. Full article

This narrative review evaluates the curtail components of data maturity in manufacturing industries, the associated challenges, and the application of industrial data science (IDS) to improve organisational decision-making. As data availability grows larger, manufacturing organisations face difficulties comprehending heterogeneous datasets of varying quality, which may lead to inefficient decision-making and other operational inefficiencies. It underlines that data appropriate for its intended application is considered quality data. The importance of including stakeholders in the data review process to enhance the data quality is accentuated in this paper, specifically when big data analysis is to be integrated into corporate strategies. Manufacturing industries leveraging their data thoughtfully can optimise efficiency and facilitate informed and productive decision-making by establishing a robust technical infrastructure and developing intuitive platforms and solutions. This study highlights the significance of IDS in revolutionising manufacturing sectors within the framework of Industry 4.0 and the Industrial Internet of Things (IIoT), demonstrating that big data can substantially improve efficiency, reduce costs, and guide strategic decision-making. The gaps or maturity levels among industries show a substantial discrepancy in this analysis, which is classified into three types: Industry 4.0 maturity levels, data maturity or readiness condition index, and industrial data science and analytics maturity. The emphasis is given to the pressing need for resilient data science frameworks enabling organisations to evaluate their digital readiness and execute their data-driven plans efficiently and effortlessly. Simultaneously, future work will focus on pragmatic applications to enhance industrial competitiveness within the heavy machinery sector. Full article

Lithium-ion batteries are a key technology for addressing energy shortages and environmental pollution. Assessing their health is crucial for extending battery life. When estimating health status, it is often necessary to select a representative characteristic quantity known as a health indicator. Most current research focuses on health indicators associated with decreased capacity and increased internal resistance. However, due to the complex degradation mechanisms of lithium-ion batteries, the relationship between these mechanisms and health indicators has not been fully explored. This paper reviews a large number of literature sources. We discuss the application scenarios of different health factors, providing a reference for selecting appropriate health factors for state estimation. Additionally, the paper offers a brief overview of the models and machine learning algorithms used for health state estimation. We also delve into the application of health indicators in the health status assessment of battery management systems and emphasize the importance of integrating health factors with big data platforms for battery status analysis. Furthermore, the paper outlines the prospects for future development in this field. Full article

In recent years, the growing number of Online Travel Review (OTR) platforms and advances in social media and search engine technologies have led to a new way of accessing information for tourists, placing projected Tourist Destination Image (TDI) and electronic Word of Mouth (eWoM) at the heart of travel decision-making. This research introduces a big data-driven approach to analyzing and measuring the perceived and conveyed TDI in OTRs concerning the reflected perceptive, spatial, and affective dimensions of search results. To test this approach, a massive metadata analysis of search engine was conducted on approximately 2700 reviews from TripAdvisor users for the category “Attractions” of the city of Kastoria, Greece. Using artificial intelligence, an analysis of the photos accompanying user comments on TripAdvisor was performed. Based on the results, we created five themes for the image narratives, depending on the focus of interest (monument, activity, self, other person, and unknown) in which the content was categorized. The results obtained allow us to extract information that can be used in business intelligence applications. Full article

Big data, artificial intelligence, and other cutting-edge technologies are combined in a novel way by big data comprehensive pilot zones (BDCPZs) to provide cities with more comprehensive and precise evaluation and management services. However, it is still unclear how this platform will affect cities, especially with regard to carbon emissions. A sample of Chinese prefecture-level cities is used in this study. It examines the impact of BDCPZ buildings on carbon emissions in urban settings using a double-difference model. According to our data, even under rigorous testing, the use of BDCPZ substantially reduces carbon emissions. According to our analysis of the mechanism, the BDCPZ lowers carbon emissions by raising environmental awareness among the general population and strengthening urban green innovation capacities. The effect of BDCPZ in reducing urban carbon emissions is more pronounced in cities that are not dependent on natural resources, and are located in the eastern and western regions, and have greater levels of human capital, according to an examination of heterogeneity. Drawing from the aforementioned findings, this essay makes specific policy recommendations to support the development of low-carbon development in urban areas. Full article

This study aims to analyze the impact of sea-level rise and tropical cyclones on mangroves in the context of global climate change from 1993 to 2023, and to explore the development status, co-operative relationships and future trends in this research field. In order to analyze future research directions for mangroves in the context of climate, this study also provides an important basis and reference for the development of research related to the mitigation of natural disasters. Using CNKI and the Web of Science as data sources, this study employs the bibliometric tool CiteSpace 6.3 R1 to conduct a quantitative and visual analysis of the research field. The research findings indicate the following: (1) The volume of publications in this field has been increasing year by year; especially since 2010, the rate of increase has accelerated, indicating an increased academic interest in this area. (2) From the authorship maps of the two data sources, it can be observed that the collaboration network is dense, indicating the existence of co-operative relationships among researchers. (3) From the analysis of the keywords, it is evident that, with the rise of artificial intelligence, the focus of keywords has gradually shifted from traditional mangrove mechanism research and ecosystem studies to research on mangroves that integrates big data, artificial intelligence, and high-resolution remote sensing data. (4) As time has progressed, areas of research interest have been shifting from the study of disturbances and damage to mangrove vegetation to the study of mangrove resilience and vulnerability in the context of natural disasters, their carbon sequestration capabilities, and their protective functions against wind and waves. The use of remote sensing technology for the monitoring and conservation of mangroves has emerged as a key area of focus for future research. In future research, there will be a focus on the adaptive capacity of mangroves to varying degrees of sea-level rise and the increasing frequency of tropical cyclones, as well as on what measures can be taken to enhance the resilience of mangrove ecosystems. Quantitative and visual analysis of the development trends in this field can provide a reference for the construction of a disaster monitoring platform for mangroves affected by sea-level rise and tropical cyclones, and can aid the development of research aimed at mitigating the impacts of natural disasters. Furthermore, the integration of remote sensing technology and ecological models can facilitate more detailed research, offering more effective tools and strategies for the conservation and management of mangroves. This approach also provides a reference point for developing a monitoring platform for mangrove disasters associated with sea-level rise and the impact of tropical cyclones. Full article

Air target intention recognition (ATIR) is critical for unmanned systems in modern air defense operations. Through the analysis of typical air defense combat scenarios, first, the paper defines the intention space and intention parameters of air units based on military experience and domain knowledge. Then, a rule-based agent for unmanned systems for online intention recognition is proposed, with no training, no tagging, and no big data support, which is not only for intention recognition and parameter prediction, but also for formation identification of air targets. The most critical point of the agent is the introduction and application of a thermal distribution grid graph (TDGG) and virtual grid dictionary (VGD), where the former is used to identify the formation information of air targets, and the latter is used to optimize the storage space and simplify the access process for the large-scale and real-time combat information. Finally, to have a performance evaluation and application analysis for the algorithm, we carried out a data instance analysis of ATIR for unmanned systems and an air defense warfare simulation experiment based on a Wargame platform; the comparative experiments with the classical k-means, FCNIRM, and the sector-based forward search method verified the effectiveness and feasibility of the proposed agent, which characterizes it as a promising tool or baseline model for the battlefield situational awareness tasks of unmanned systems. Full article

Poor solubility of many drugs, with ensuing low bioavailability, is a big challenge in pharmaceutical development. Nanosuspensions have emerged as a platform approach for long-acting injectables and solid dosages that enhance drug bioavailability. Despite improvements in nanosuspension preparation methods, ensuring nanosuspension stability remains a critical issue. Conventionally, synthetic and semi-synthetic polymers and surfactants are used in nanosuspension formulations. However, no polymer or surfactant group is universally applicable to all drugs. This fact, as well as their toxicity and side effects, especially if used in excess, have sparked the interest of researchers in the search for novel, natural stabilizers. The objective of this paper is to provide a comprehensive analysis of non-traditional natural stabilizers reported in the literature published over the last decade. First, physical stability and stabilization mechanisms are briefly reviewed. Then, various classes of non-traditional natural stabilizers are introduced, with particular emphasis on their stabilization potential, safety, and pharmaceutical acceptability. Wherever data were available, their performance was compared with the traditional stabilizers. Furthermore, the benefits and limitations of using these stabilizers are examined, concluding with future prospects. This review is expected to serve as a valuable guide for researchers and formulators, offering insights into non-traditional natural stabilizers in drug nanosuspension formulations. Full article

In the current competition process of e-commerce platforms, the technical and algorithmic wars that can quickly grasp user needs and accurately recommend target commodities are the core tools of platform competition. At the same time, the existing online purchase behavior prediction models lack consideration of time series features. This paper combines the Recurrent Neural Network, which is more suitable for the commodity recommendation scenario of the e-commerce platform, with Naive Bayes, which is simple in logic and efficient in operation and constructs the online purchase behavior prediction model RNN-NB, which can consider the features of time series. The RNN-NB model is trained and tested using 3 million time series data with purchase behavior provided by the Ali Tianchi big data platform. The prediction effect of the RNN-NB model and Naive Bayes model is evaluated and compared respectively under the same experimental conditions. The results show that the overall prediction effect of the RNN-NB model is better and more stable. In addition, through the analysis of user time series features, it can be found that the possibility of user purchase is negatively correlated with the length of time series, and merchants should pay more attention to those users with shorter time series in commodity recommendation and targeted offers. The contributions of this paper are as follows: (1) By constructing an online purchasing behavior model RNN-NB, which integrates the N vs 1 structure Recurrent Neural Network and naive Bayesian model, the validity limitations of some single-architecture recommendation algorithms are solved. (2) Based on the existing naive Bayesian model, the prediction accuracy of online purchasing behavior is further improved. (3) The analysis based on the features of the time series provides new ideas for the research of later scholars and new guidance for the marketing of platform merchants. Full article

In the field of industrial big data, the key issue in discovering data value lies not in overcoming the bottlenecks formed by analysis methods and data mining algorithms but in the difficulty of providing data element resources that meet business analysis needs. Due to the surge in data volume and the increasing reliance of enterprises on data-driven decision-making, future data management strategies are constantly evolving to meet higher quality and efficiency requirements. Data metadata resources that meet business analysis needs require high-quality data integration, standardization, and metadata management. The key is to ensure the consistency and availability of data to support accurate analysis and decision-making. By leveraging automation and machine learning, organizations can more effectively integrate and manage data metadata resources, thereby improving data quality and analytical capabilities. The multi-value chain data space is a digital ecological platform for organizing and managing industrial big data. Research on optimizing the supply of its business data resources is a significant topic. This paper studies the evaluation index system of data quality and data utility, constructs an evaluation matrix of business data resources, and addresses the issues of data sparsity and cold start in evaluation calculations through a data quality-utility-based evaluation model of business data resources. It investigates a business data resource algorithm based on collaborative filtering, forming a recommendation set of similar data quality-utility data resources to provide to data analysis users. Finally, using actual production datasets, the paper validates the business data resource evaluation model, compares the performance and effectiveness of three business data resource recommendation algorithms based on collaborative filtering, empirically demonstrates the recommendation accuracy and stability performance of the combined improved data quality-utility collaborative filtering algorithm (CFA-DQU), and provides technical research recommendations for optimization of business data resources. Full article