Deep Integration Research Articles

Can informatization improve urban entrepreneurial activity? Evidence from China

Informatization plays a leading role in promoting the deep integration of technology and industry and stimulating the vitality of new business creation. Based on city-level data from 2003 to 2022, this study investigates the effect of informatization on urban entrepreneurial activity and the mechanisms using the establishment of “pilot zones for informatization and industrialization integration” as a policy shock and employing a time-varying difference-in-differences (DID) method. The findings show that informatization significantly enhances urban entrepreneurial activity. Moreover, this effect is stronger in the smart manufacturing and service industries, as well as in cities with superior economic levels and higher administrative rankings. The mechanism test reveals that informatization mainly stimulates urban entrepreneurial activity by enhancing technical talents and technological foundations, expanding market demand, and improving the investment environment. This study not only enriches research on the correlation between informatization and entrepreneurship but also provides important theoretical basis and policy implications for fully leveraging the advantages of informatization construction and promoting urban entrepreneurship development.

The Impact of International Education on Chinese Education in the Context of Globalization

With the deepening of globalization, in Chinas educational system, international education (IE) has emerged as a key area for reform and development. This paper aims to explore how to effectively localize IE in China in the context of its flourishing development, in order to adapt to China's national conditions and needs. The paper systematically analyzes the connotation of IE and its development in China and points out the main challenges China faces in promoting IE. The paper focuses on the integration strategy of IE and local education(LE) and puts forward specific localization practice paths. The study finds that by adhering to the development of educational field openness, promoting bidirectional cultural exchange and interaction, firmly upholding cultural confidence, and developing student-international exchange programs, it is possible to effectively promote the deep integration and innovation of IE in China. Finally, the paper summarizes the research findings and looks forward to future trends.

The Impact of Chip Technology Innovation on the Marketing Strategy of Consumer Electronics Products: A Case Study of Smartphones

Chip technology innovation has become the core driving force for the development of the smartphone industry, and its far-reaching impact on product performance optimization and marketing strategy transformation is particularly significant. This paper explores the theoretical connotation and development trend of chip technology innovation, and analyzes its key role in improving smartphone hardware performance, enhancing user experience and promoting market competition. In addition, through the case studies of two major brands, Apple and Huawei, it reveals the specific practice of the deep integration of chip technology and marketing strategy, including differentiated product positioning, technology-driven brand building and market promotion of innovative functions. The study shows that the breakthrough of chip technology not only gives smartphones significant technical advantages, but also provides strong support for brands to enhance market influence and user loyalty, thus enabling them to gain a competitive advantage in the rapidly changing consumer electronics market.

On the role of digital solutions in the development of an innovative environment for high-tech production and ensuring the priorities of the national economy

The relevance of the study is determined by the recently increased role of digital services and technologies in shaping the architecture of high-tech production and ensuring the priorities of the national economy. The development of digital services and services produces the emergence of ecosystems and the spread of customeroriented business models in the high-tech sector, the importance of which in the country's economy will only increase.The purpose of the study is determined by the need to study modern trends in the development of digital services and technologies that influence the development of the innovative environment of high-tech industries and ensuring the priorities of the national economy.Objectives: to explore the role of digital services and technologies in shaping the architecture of high-tech industries and ensuring the priorities of the national economy; to identify the periodization and content of the digital transformation of the national economy; to analyze the basic indicators characterizing the dynamics of the spread of digitalization processes; to explore the content and key characteristics accompanying the spread of digital platforms and ecosystems.Methodology: the research methodology is based on historical, logical and economic-statistical analysis regarding the processes of digital transformation in the national economy.The results of the study show that digital transformation in the national economy is actively spreading, involving an ever-increasing circle of participants and setting new imperatives in doing business related to the emergence and spread of digital ecosystems. However, the architecture of the largest domestic ecosystems has not been fully formed and they have not achieved their growth potential.Conclusions obtained as a result of the study indicate that digital services and technologies are a factor contributing to a multiple increase in the capitalization of high-tech companies involved in the development of digital transformation processes. Digital ecosystems have prospects associated with increasing their impact on the national economy and deeper integration into the socio-economic space in connection with the development of new digital technological solutions.

Transforming Breast Cancer Detection: AI as a Catalyst for Enhanced Clinical Outcomes

A revolutionary development in contemporary healthcare, especially in oncology, is the application of artificial intelligence (AI) to breast cancer diagnosis. The use of AI-powered diagnostic tools in breast cancer screening programs is examined in detail in this article, which shows notable gains in workflow efficiency, accuracy, and early detection. Along with quantitative performance indicators and system reliability measures, it examines the technological framework, which includes deep learning architectures and integration workflows. Through a thorough analysis of data processing issues, fixes, and clinical implications, the article shows how AI enhances radiologists' skills without replacing human knowledge. It also discusses future technological advancements and scaling issues, emphasizing the possibility of integrating multi-modal imaging and improving predictive capacities. This approach makes a strong case for wider deployment across healthcare systems and is a blueprint for future AI integration in medical diagnostics.

Influencing Factors and Formation Mechanism of Brand Preference in Community E-Commerce

The deep integration of social media and e-commerce has fueled the rapid growth in community e-commerce, which has become a major trend in global e-commerce development. Researching the formation of brand preference in community e-commerce can promote the sustainable development of these brands. The distinctive social networking features and group interaction methods of community e-commerce offer new perspectives on the formation of brand preferences. In this paper, a model of factors influencing brand preference in community e-commerce is developed, where community platforms, product value, e-commerce services, content quality, and community interaction serve as antecedent variables; community experience and brand image act as mediating variables; and brand preference is the dependent variable. The model is empirically tested using structural equation modeling. The results indicate that community interaction, e-commerce services, product value, content quality, and community platforms significantly affect the community experience in e-commerce. Moreover, community interaction, product value, and content quality have significant impacts on brand image in community e-commerce. Both community experience and brand image positively influence brand preference.

Driving Behaviour Research for Autonomous Vehicle Interaction Design: A Comprehensive Review and Future Directions

Despite the crucial role of driving behaviour research in shaping autonomous vehicle interaction design, the current state of their deep integration remains unexplored, constraining the design innovative of autonomous vehicle. This study conducted a systematic review by analysing 320 publications from 2003 to 2023 following PRISMA guidelines. Initially, the research evolution trajectory was depicted through performance analysis, followed by exploring dynamic research themes using scientific mapping. The results reveal the pivotal role of driving behaviour research in fostering innovative practices within autonomous vehicle interaction design and the evolution of thematic content. Three future directions are identified: behaviour insights of diverse interactive entities, all-in-one design solutions, and mixed-reality design evaluation tools. These findings provide practical guidance for utilizing driving behaviour research to foster innovation in AV interaction design, thereby accelerating the socialization of AVs and the transformation towards intelligent mobility.

Can government green discourse-behavior congruence mitigate carbon emissions? A polynomial regression with response surface analysis

As global climate change intensifies, the efficacy of governmental environmental policies and their implementation is pivotal for carbon emission control. The alignment between governmental green initiatives and their actions not only affects authority credibility but also determines the success of environmental governance outcomes. Therefore, investigating the congruence between government green discourse and behavior in achieving “dual carbon” objectives is critical for addressing climate change and facilitating systemic reforms. Applying panel data from 30 provinces in China from 2012 to 2022 based on polynomial regression and response surface, this study summarizes three main pathways through which government green discourse-behavior congruence influences carbon emissions: the state of congruence or incongruence, the degree of congruence, and the direction of incongruence. Congruent government green discourse and behavior more effectively reduce carbon emissions intensity than incongruent ones, while a higher degree of congruence leads to more significant reductions. The direction of incongruence also impacts carbon emissions intensity, particularly when government behaviors fall short of its discourses, leading to a higher carbon intensity growth rate. Furthermore, the moderating role of non-governmental entities' green innovation vitality is considered. The results reveal that the green innovation of non-governmental entities can partly substitute for the need for government discourse-behavior congruence in achieving carbon reduction. Specifically, green innovation of research institutions primarily enhances the positive environmental effects of increased government discourse-behavior congruence degree, while corporate green innovation mainly mitigates the negative environmental impacts of government incongruence direction. Consequently, the deep integration of government environmental initiatives and actions is advocated, along with the stimulation of green innovation among various entities, to more effectively combat global climate change. This study not only extends traditional congruence research from the micro level to the meso and macro levels and fills a theoretical gap, but also provides new insights into the process of government green governance worldwide.

DeepMap: Deep learning-based single-cell data integration using iterative cell matching and structure preservation constraints

DeepMap: Deep learning-based single-cell data integration using iterative cell matching and structure preservation constraints

China's Carbon Trading Market Globalization Strategy: A Conceptual Review

China has once participated in the international carbon market through the Clean Development Mechanism (CDM) faced problems such as falling certified emission reductions (CER) prices and carbon sink fraud, which led to the decline of China's carbon trading market. However, with China's announcement of the goal of peaking carbon emissions before 2030 and achieving carbon neutrality before 2060, China's carbon market has regained vitality and launched China Certified Emission Reductions (CCER) as the main trading product. The study discusses the opportunities and challenges of China in the globalization of the carbon trading market, including key obstacles such as differences in rules and inconsistent carbon absorption measurement methods. At the same time, the paper proposes strategies such as connecting China's carbon trading market with the global market through the Hong Kong platform, strengthening international cooperation, optimizing market mechanisms, and improving technological innovation capabilities to promote the deep integration and coordinated development of China's carbon trading market with the international market. It emphasizes China's position and role in the global carbon trading system in the future, as well as its positive role in promoting global low-carbon transformation and international exchanges and cooperation.

Explainable AI for News Classification

Abstract: The proliferation of news content across digital platforms necessitates robust and interpretable machine learning models to classify news into predefined categories effectively. This study investigates the integration of Explainable AI (XAI) techniques within the context of traditional machine learning models, including Naive Bayes, Logistic Regression, and Support Vector Machines (SVM), to achieve interpretable and accurate news classification. Utilizing the News Category Dataset, we preprocess the data to focus on the top 15 categories while addressing class imbalance challenges. Models are trained using Term Frequency-Inverse Document Frequency (TF-IDF) vectorization, achieving an acceptable classification accuracy of 67% across all models despite the complexity introduced by the high number of classes. To elucidate the decision-making processes of these models, we employ feature importance visualizations derived from model coefficients and feature log probabilities, complemented by local interpretability techniques such as LIME (Local Interpretable Model-agnostic Explanations). These methodologies enable granular insights into word-level contributions to predictions for each news category. Comparative heatmaps across models reveal significant consistencies and divergences in feature reliance, highlighting nuanced decision-making patterns. The integration of explainability into news classification provides critical interpretive capabilities, offering transparency and mitigating the risks associated with algorithmic opacity. The findings demonstrate how XAI enhances stakeholder trust by aligning model predictions with human interpretability, particularly in ethically sensitive domains. This work emphasizes the role of XAI in fostering responsible AI deployment and paves the way for future advancements, including deep learning integration and multilingual news classification with inherent interpretability frameworks

Discussion about Testing Scheme of Intelligent Medical Devices

Intelligent medical devices are flourishing with the deep integration of modern information and artificial intelligence technologies into healthcare. Testing is an important means of performance evaluation and quality control for intelligent medical devices. Compared with traditional medical devices, the testing methods and technologies of intelligent medical devices are still immature, and need active research to promote the progress in this area. Intelligent medical devices are classified according to their characteristics as artificial intelligence medical devices in the form of software and medical robots based on a general discussion of their development. The medical-device Internet of Things (IoT) system has also been included due to its close relation to the construction of smart hospitals. For each type of intelligent medical device, testing indexes and testing plans are discussed. It is suggested that specific test rules should be further developed for various specific devices. Besides, the evaluation method of complex intelligent systems should be introduced and real-world data should be used for evaluation. This paper aims to accelerate the development of intelligent medical device testing, laying the foundation for quality control and performance evaluation of intelligent medical devices.

The Summary of Artificial Intelligence Vehicle Obstacle Avoidance System

With the rapid increase in the global number of vehicles, frequent traffic accidents and urban traffic congestion have become urgent social problems that need to be solved. As an innovative solution, autonomous driving technology is gradually demonstrating its potential, and in this cutting-edge field, automatic obstacle avoidance technology is undoubtedly the core. It deeply integrates advanced sensing technology and intelligent control algorithms, aiming to enable vehicles to quickly make safe and accurate evasive actions when encountering potential obstacles. The evolution of automatic obstacle avoidance technology has gone beyond simple functional pursuits and shifted towards deep integration of various cutting-edge technologies to optimize obstacle avoidance efficiency. In summary, the innovation and development of automatic obstacle avoidance technology are leading the technological revolution in the field of autonomous driving, not only profoundly changing the mode of human vehicle interaction, but also having a profound impact on the vision of future smart city transportation systems.

Application and Challenge of Edge Computing Based on 5G Communication in Information and Communication Systems

With the rapid development of information technology, 5G communication technology has gradually entered real life, among which the application of edge computing is particularly significant in the information and communication system field. This paper focuses on using edge computing based on 5G communication in information and communication systems. First, the study analyzes the importance of combining edge computing technology with 5G communication technology, and its advantages, such as high efficiency and low latency in processing large amounts of data. The study then explores multiple application scenarios of edge computing in information and communication systems, such as integrated use in the Internet of Things, intelligent transportation, telemedicine and Industry 4.0. The research method is mainly based on theoretical analysis and experimental verification, combined with the characteristics of the 5G network to optimize the edge computing model and test the performance of edge computing in different scenarios through experimental simulation. The results show that edge computing significantly improves the data processing capacity and response speed of ICS in a 5G environment. However, there are also a series of challenges in practical application, including data security and privacy protection, the complexity of resource management and allocation, and the guarantee of quality of service (QoS). Through the case analysis and problem analysis, the paper puts forward the corresponding solution strategies, such as strengthening the data security protocol, introducing the intelligent resource scheduling system and establishing a multi-dimensional service quality monitoring mechanism. Finally, this study points out that the deep integration of edge computing and 5G communication will continue to promote the innovative development of information and communication systems, which has a far-reaching impact and important practical significance for promoting the transformation and upgrading in the field of information technology.

GPTrans: A Biological Language Model-Based Approach for Predicting Disease-Associated Mutations in G Protein-Coupled Receptors.

Accurately predicting mutations in G protein-coupled receptors (GPCRs) is critical for advancing disease diagnosis and drug discovery. In response to this imperative, GPTrans has emerged as a highly accurate predictor of disease-related mutations in GPCRs. The core innovation of GPTrans resides in the design of a novel feature extraction network, that is capable of integrating features from both wildtype and mutant protein variant sites, utilizing multifeature connections within a transformer framework to ensure comprehensive feature extraction. A key aspect of GPTrans's effectiveness is our introduction of an innovative deep feature integration strategy, which merges embeddings and class tokens from multiple protein language models, including evolutionary scale modeling and ProtTrans, thus shedding light on the biochemical properties of proteins. Leveraging transformer components and a self-attention mechanism, GPTrans captures higher-level representations of protein features. Employing both wildtype and mutation site information for feature fusion not only enriches the predictive feature set but also avoids the common issue of overestimation associated with sequence-based predictions. This approach distinguishes GPTrans, enabling it to significantly outperform existing methods. Our evaluations across diverse GPCR data sets, including ClinVar and MutHTP, demonstrate GPTrans's superior performance, with average AUC values of 0.874 and 0.590 in 10-fold cross-validation. Notably, compared to the AlphaMissense method, GPTrans exhibited a remarkable 38.03% improvement in accuracy when predicting disease-associated mutations in the MutHTP data set. A thorough analysis of the predicted results further validates the model's effectiveness. The source code, data sets, and prediction results for GPTrans are available for academic use at https://github.com/EduardWang/GPTrans.

Enhancing brain tumor MRI classification with an ensemble of deep learning models and transformer integration.

Brain tumors are widely recognized as the primary cause of cancer-related mortality globally, necessitating precise detection to enhance patient survival rates. The early identification of brain tumor is presented with significant challenges in the healthcare domain, necessitating the implementation of precise and efficient diagnostic methodologies. The manual identification and analysis of extensive MRI data are presented as a challenging and laborious task, compounded by the importance of early tumor detection in reducing mortality rates. Prompt initiation of treatment hinges upon identifying the specific tumor type in patients, emphasizing the urgency for a dependable deep learning methodology for precise diagnosis. In this research, a hybrid model is presented which integrates the strengths of both transfer learning and the transformer encoder mechanism. After the performance evaluation of the efficacy of six pre-existing deep learning model, both individually and in combination, it was determined that an ensemble of three pretrained models achieved the highest accuracy. This ensemble, comprising DenseNet201, GoogleNet (InceptionV3), and InceptionResNetV2, is selected as the feature extraction framework for the transformer encoder network. The transformer encoder module integrates a Shifted Window-based Self-Attention mechanism, sequential Self-Attention, with a multilayer perceptron layer (MLP). These experiments were conducted on three publicly available research datasets for evaluation purposes. The Cheng dataset, BT-large-2c, and BT-large-4c dataset, each designed for various classification tasks with differences in sample number, planes, and contrast. The model gives consistent results on all three datasets and reaches an accuracy of 99.34%, 99.16%, and 98.62%, respectively, which are improved compared to other techniques.

Spatio-Temporal Evolution and Interactive Relationship Between Digital Economy and Green Development in China

A digital economy parallel with green development holds profound significance for achieving sustainability. The primary objective of this study was to explore the synergistic interaction effects between the digital economy and green development in China and forecast their future development. This study analyzed the spatio-temporal characteristics of provincial digital economy and green development in China by integrating a combined assignment method, an unconditional spatial kernel density estimation method, and a standard deviation ellipse model. The interplay between the digital economy and green development was examined using a panel vector autoregression model. Additionally, digital economy and green development levels were forecasted using univariate time series and radial basis function kernel ε-support vector regression models. The results indicate that both the digital economy and green development levels in China exhibited an upward trend from 2013 to 2021, with the digital economy increasing at a faster rate. However, both domains demonstrated regional disparities in their development processes. The mutual interaction between the digital economy and green development intensified as the lag period increased. The digital economy contributed 21% to green development, whereas green development contributed 18% to the digital economy. The initial effect of the digital economy on green development was negative, however, this impact gradually diminished over time. Additionally, the influence of green development on the digital economy was shown to follow a consistent trend of transitioning from negative to positive across the eastern, central, and western regions. Therefore, it can be seen that the digital economy exerts a sustainable impact on green development, albeit with a one-phase lag. This research provides a scientific basis for the deep integration of the digital economy and green development, thereby fostering sustainable socioeconomic growth.

Research on the English Writing Teaching Model in the AI Era

With the rapid development of artificial intelligence (AI) technology, the education sector, particularly language teaching, is undergoing unprecedented changes. English writing, as an essential component of language learning, is increasingly struggling to meet the demands for personalization and efficiency in traditional teaching models. This paper aims to explore the innovation and development of English writing teaching models in the AI era, analyzing the application of AI technology in English writing and its impact on teaching effectiveness. First, the paper reviews the development of AI technology and examines its potential value in English writing teaching, especially in the use of intelligent writing assistance tools and personalized learning paths. Next, it analyzes the challenges facing English writing teaching in the AI era, including the imbalance in technology dissemination and the transformation of teachers' roles. Finally, based on future development trends, the paper proposes strategies and recommendations for promoting the deep integration of AI technology with English writing teaching. This research aims to provide theoretical support for the innovation of English writing teaching models and offer practical references for educational policymakers and practitioners.

The spatial differentiation mechanism of intangible cultural heritage and its integration with tourism development based on explainable machine learning and coupled coordination models: a case study of the Jiang-Zhe-Hu in China

As a vital carrier of traditional culture, Intangible Cultural Heritage (ICH) not only preserves historical value but also fosters cultural identity and confidence. This study utilizes explainable machine learning and coupled coordination models to analyze the spatial distribution and formation mechanisms of ICH resources in the Jiangsu-Zhejiang-Shanghai (Jiang-Zhe-Hu). The results indicate that (1) ICH resources in the Jiang-Zhe-Hu exhibit a clustered distribution pattern characterized by “three primary cores and two secondary cores.” The primary core areas are Shanghai, Hangzhou, and Suzhou, while the secondary core areas are Yangzhou and Nanjing. (2) Population, number of religious places, and GDP have a significant positive impact on the distribution of ICH in the Jiang-Zhe-Hu. NDVI and road mileage have relatively minor effects on ICH distribution. (3) In terms of ICH resources, Zhejiang Province overall has a higher level than Jiangsu Province, with Lishui having the highest evaluation value and the most abundant resources. Regarding the level of tourism industry development, Shanghai has the highest comprehensive evaluation value, followed by Suzhou, Nanjing, Hangzhou, Wuxi, and Changzhou, all of which have relatively high levels of tourism development. (4) According to the coupled coordination model analysis, Shanghai demonstrates the best coupling degree between ICH resources and the tourism industry, achieving a good coordination level. In Jiangsu Province, the integration of ICH resources and the tourism industry is relatively better in the southern (e.g., Nanjing, Suzhou), but there are still imbalances in development in the northern. Zhejiang Province has an overall higher degree of integration between ICH and the tourism industry compared to Jiangsu, with more balanced development. However, there is still room for improvement in the deep integration of ICH resources with the tourism industry.

Digital Tourism and Smart Development: State-of-the-Art Review

The intersection between digital technologies and tourism emerges as a prominent area of research within the tourism industry. This is primarily driven by the immense complexity of digital tourism itself as a multifaceted social, economic, and cultural phenomenon. This paper reveals the future implications of tourism in the context of digital intelligence. To gain insights into the latest applications of digital tourism, this work reviews 278 studies spanning from 2012 to 2024. A systematic literature analysis method is proposed to identify the research hotspots and trends. Through value co-creation theory and Schumpeter’s innovation theory, five key trajectories are suggested, as follows: in-depth application of digital technologies in tourism, spawning new scenarios, new forms and new modes of digital tourism, and deep integration of digital economy and tourism real economy. This state-of-the-art review will help to reflect the efforts towards promoting the smart development of digital technologies in tourism.