摘要：
Chinese possesses the essential attributes of unique character composition structure and the nested nature of medical entities, which causes many challenges for Chinese Electronic Health Records (EHRs) in medical named entity recognition tasks, such as scarce annotated data, strong tokenization ambiguity, and blurred entity boundaries. This increases the difficulty of extracting medical named entity categories. The paper proposes an effective Chinese clinical named entity recognition model that integrates BERT and adversarial enhancement in a dual channel architecture to address this issue. Firstly, the model integrates various advanced technologies, such as Bidirectional Long Short-Term Memory networks (BiLSTM), Iterative Deep Convolutional Neural Networks (IDCNN), and Conditional Random Fields (CRF), to improve the accuracy of named entity recognition. Secondly, the paper collected texts from medical record websites and utilized the YEDDA tool for professional annotation and processing of these texts, ultimately forming a more comprehensive target dataset. This process ensures that the model is exposed to representative Chinese clinical data during training, thereby improving recognition performance.Finally, experimental results indicate that the BPBIC model achieved a precision of 93.80%, a recall of 94.44%, and an F1 score of 94.12% on the augmented dataset CCKS2019 (CCKS2019+). Moreover, through knowledge graph analysis of medical entities extracted from single and multiple disease EHRs, the model assists doctors in achieving rapid and accurate diagnoses, thereby enhancing the efficiency of healthcare professionals.
通讯机构：
[Liu, GH ] G;Guangxi Normal Univ, Coll Comp Sci & Engn, Guilin 541004, Peoples R China.
关键词：
Image retrieval;Deep contrast feature;Contrast-based layer;Generalized mean aggregation;Multi-orientational PCA whitening
摘要：
BackgroundIn the field of content-based image retrieval (CBIR), fused feature-based methods have demonstrated their advanced performance on the popular benchmark datasets. However, it is inevitable increase the vector dimensionality because the fused features have diversity. Therefore, achieving both a low-dimensional representation and high retrieval performance remains challenging.MethodsTo address this problem, an image retrieval method based on the deep contrast-based layer is proposed, namely the deep contrast feature histogram (DCFH), to image retrieval. There are three highlights as follows: (1) texture features based on the edge orientation are calculated to build contrast-based layer; it can enhance the discriminative power of deep features; (2) a generalized mean aggregation method is introduced to effectively aggregate the representative information in the deep feature maps of convolutional neural network (CNN); (3) a multi-orientational PCA whitening method is proposed to provide a compact yet discriminative representation.ResultsComparative experiments demonstrated that our method can provide outstandingly competitive retrieval performance on popular benchmark datasets.ConclusionsThis work captures visual information from both global and local perspectives, presenting an approach in line with human visual cognitive. Experiments demonstrated that our method can efficiently combine the strengths of various features to provide the robust representation, thereby improving the retrieval performance. Moreover, our method is easily to be implemented without requiring to retrain the CNN models and not the use of additional supervision.
作者机构：
[Deng, Yuhua] Hunan Inst Technol, Sch Int Studies, Hengyang 421001, Peoples R China.;[Liu, Huying] Cent South Univ Forestry & Technol, Swan Coll, Changsha 410211, Peoples R China.;[Liu, Huying] Stamford Int Univ, Grad Sch, Bangkok 10250, Thailand.
通讯机构：
[Liu, HY ] C;Cent South Univ Forestry & Technol, Swan Coll, Changsha 410211, Peoples R China.;Stamford Int Univ, Grad Sch, Bangkok 10250, Thailand.
关键词：
Test anxiety;Techno competence;Teacher support;Self-efficacy;Autonomy
摘要：
This study explores the interplay between techno competence, teacher support, self-efficacy, autonomy, and test anxiety in the context of online assessments among 30 learners from a university in China. Employing a narrative inquiry approach, the study delves into the reflective narratives of participants, capturing their perceptions, experiences, and coping strategies related to test anxiety in online assessment settings. Findings reveal nuanced relationships between techno competence, teacher support, self-efficacy, autonomy, and test anxiety, highlighting the pivotal role of these factors in shaping students’ experiences and outcomes. Learners with high techno competence demonstrate greater confidence in navigating online assessment platforms and employ adaptive coping strategies to manage test anxiety effectively. Conversely, those with low techno competence may experience heightened anxiety due to technical challenges and a lack of confidence in their digital skills. Perceived teacher support emerges as a crucial determinant in mitigating test anxiety, with supportive and nurturing relationships fostering a sense of security and confidence among learners. Additionally, self-efficacy and autonomy play significant mediating roles, influencing students’ perceptions of their capabilities and their ability to regulate their learning processes. These findings underscore the importance of fostering techno competence, providing teacher support, and promoting self-efficacy and autonomy to alleviate test anxiety and enhance academic success in online assessment environments.
作者机构：
[Yaping Jiang] School of Information and Engineering, Swan College, Central South University of Forestry and Technology, Changsha, China
会议名称：
2025 7th International Conference on Computer Science and Technologies in Education (CSTE)
会议时间：
18 April 2025
会议地点：
Wuhan, China
会议论文集名称：
2025 7th International Conference on Computer Science and Technologies in Education (CSTE)
关键词：
AI;platform data;digital intelligence teaching;big data technology;engineering practice;innovation ability
摘要：
With the rapid development of digital and intelligent technology, the training of big data talents is facing higher requirements and challenges. However, the current big data technology curriculum still has shortcomings in content update, engineering practice, and innovation ability training, and the personalized learning path and course evaluation system need to be improved. In order to solve the above problems, this paper discusses the digital intelligent teaching reform for big data technology curriculum based on AI and platform data, focusing on how to optimize teaching resources, strengthen practical links, and innovate teaching methods and evaluation systems through teaching platforms. Research shows that the digital intelligence reform not only improves the teaching efficiency of teachers but also significantly enhances students' practical and innovation ability, thus effectively improving the quality of big data technology education and having important theoretical and practical value.
作者机构：
[Yiou Zhang; Xiangquan Gui] School of Computer and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China;[Quan Song] Swan College, Central South University of Forestry and Technology, Changsha, Hunan, China
会议名称：
2025 6th International Conference on Computer Engineering and Application (ICCEA)
会议时间：
25 April 2025
会议地点：
Hangzhou, China
会议论文集名称：
2025 6th International Conference on Computer Engineering and Application (ICCEA)
摘要：
Dunhuang murals, as invaluable cultural heritage, hold distinct artistic significance. Transforming them into line drawings aids in preservation and creative reuse. However, current deep learning-based style transfer methods often suffer from blurred lines, style inconsistency, and poor structural fidelity. To overcome these challenges, this paper proposes DMLT-GAN, a GAN-based model integrating multi-level convolution, asymmetric cycle consistency loss, and gradient loss to enhance the stylistic fidelity and line clarity. Experiments demonstrate that DMLT-GAN achieves superior visual quality and stylistic accuracy, contributing to the digital preservation and artistic revival of Dunhuang art.
摘要：
The ongoing trade war between China and the United States significantly impacts both nations and their internal regions, yet few studies have explored these localized effects. Utilizing a multi-region and multi-sector trade model that encompasses 50 US states and 43 economies, alongside re-estimated elasticities, we quantify the welfare and real wage changes resulting from tariff hikes by both the US and China with the 2017 tariff data. Our findings indicate that China suffered a larger aggregate welfare loss than the US after two rounds tariff increases, primarily due to reduced trade volumes. Real wages decreased in both countries, with the extent of tariff hikes directly influencing the severity of impact. Notably, there was significant regional variation within the US, especially in areas specialized in sectors facing tariff increases. Mexico appears as a potential major beneficiary, enjoying improved terms of trade, while South Korea experiences losses.
期刊：
International Journal of Continuing Engineering Education and Life-Long Learning,2025年35(1-2):112-126 ISSN：1560-4624
通讯作者：
Li, Z
作者机构：
[Zhou Li; Li, Zhou] City Univ Malaysia, Kuala Lumpur 46100, Malaysia.;[Zhou Li; Li, Zhou] Cent South Univ Forestry & Technol, Swan Coll, Changsha 410211, Peoples R China.;[Huisuan Wei] City Univ Malaysia, Fac Educ & Liberal Studies, Kuala Lumpur 46100, Malaysia.
通讯机构：
[Li, Z ] C;City Univ Malaysia, Kuala Lumpur 46100, Malaysia.;Cent South Univ Forestry & Technol, Swan Coll, Changsha 410211, Peoples R China.
关键词：
UTAUT model;AI technology;English speaking teaching;individual attributes;willingness to use
摘要：
To improve the adaptability and universality of teachers using intelligent technology to analyse the influencing factors of English speaking, this paper proposes a study on the impact of AI technology on English speaking teaching behaviour under the UTAUT model. By identifying the influencing factors and designing a survey questionnaire, a UTAUT model was constructed to study the impact on English oral teaching behaviour. The experimental results show that this study has high adaptability and universality, with an accuracy rate consistently above 90%, indicating that the model has shown good performance in terms of analytical performance. This indicates that the research model is of great significance for a deeper understanding of the role of AI technology in English oral teaching.
摘要：
As an important component of the building, the sound insulation performance (SIP) of doors greatly influences the quality of the indoor acoustic environment. Therefore, this paper presents a systematic study on the SIP of wooden doors. Firstly, this study comparatively analyzes SIP across distinct core structures in both fully assembled door systems and isolated door panels, aiming to identify frequency-dependent acoustic variations across standardized bands. Secondly, acoustic finite element modeling and Gompertz's theory of the rectangular gap sound transmission coefficient are used to further analyze the SIP of the wooden door structure across different frequency bands. This reveals the inherent relationship between the core structure, the sealing material, and the SIP of the wooden door. The results show that the SIP of the three core structures for the entire door can range from 24 dB to 27 dB. Among them, the core structure has a greater impact on low-frequency SIP, while the sealing structure has a more notable effect on high-frequency SIP. Therefore, after optimizing the wooden door design, the sound SIP can be increased by 5 dB to 8 dB. This study establishes a theoretical framework and practical design protocols for high-performance sound-insulated wooden doors, critically enabling architectural acoustic environment optimization.
摘要：
Using a sample of A-share listed enterprises in the Shanghai and Shenzhen Stock Exchanges, this study shows that environmental investors can effectively stimulate green technological innovation measured by green patents. The stimulating effect is substantially heterogeneous across different types of enterprises and innovations. The mechanism analysis reveals that environmental investors promote green innovation mainly by increasing internal environmental investment rather than by obtaining more government subsidies. This study provides rare micro-evidence of the important role of independent environmental investors in green innovation.
作者机构：
[Feng, Xiuxia] Shanghai Lida Univ, Sch Gen Educ & Foreign languages, Shanghai 201608, Peoples R China.;[Liu, Huying] Cent South Univ Forestry & Technol, SWAN Coll, Changsha 410211, Peoples R China.;[Liu, Huying] Stamford Int Univ, Grad Sch, Bangkok 10250, Thailand.
通讯机构：
[Liu, HY ] C;Cent South Univ Forestry & Technol, SWAN Coll, Changsha 410211, Peoples R China.;Stamford Int Univ, Grad Sch, Bangkok 10250, Thailand.
摘要：
This phenomenological study explored the experiences of language learners in the digital age, specifically investigating the intersection of digital literacy, technostress, online engagement, autonomy, and academic success. Twenty participants, selected through purposive sampling, shared Chinese as their native language and were between 18 and 20 years old, with five participants being female. Employing interviews and document analysis, the study aimed to understand the subjective meanings, emotions, and perceptions associated with these phenomena. The findings revealed the multifaceted nature of technostress, the crucial role of digital literacy in shaping online engagement and autonomy, and the nuanced impact on academic success. These qualitative insights contribute to a deeper understanding of the complex relationships in the digital language learning landscape. The study has implications for educators, materials developers, syllabus designers, and policy-makers, providing practical insights to enhance language learning experiences in the digital era. Future research may further explore specific dimensions uncovered in this study to adapt educational practices to the evolving digital terrain.
期刊：
World Electric Vehicle Journal,2024年15(9):403- ISSN：2032-6653
通讯作者：
Chao He
作者机构：
[Jian Wei] College of Information and Engineering, Swan College, Central South University of Forestry and Technology, Hunan 410211, China;[Qiankun Zhang] China Information Technology Designing and Consulting Institute Co., Ltd., Beijing 100048, China;[Wenhui Jiang; Junting Li] School of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing 404130, China;Author to whom correspondence should be addressed.;[Jiang Guo] Chengdu Tangyuan Electric Co., Ltd., Sichuan 610046, China
通讯机构：
[Chao He] S;School of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing 404130, China<&wdkj&>Author to whom correspondence should be addressed.
关键词：
intelligent vehicle;quintic polynomial;internet of vehicles;trajectory planning;real-time
摘要：
The autonomous lane change maneuver is a critical component in the advancement of intelligent transportation systems (ITS). To enhance safety and efficiency in dynamic traffic environments, this study introduces a novel autonomous lane change strategy leveraging a quintic polynomial function. To optimize the trajectory, we formulate an objective function that balances the time required for lane changes with the peak acceleration experienced during the maneuver. The proposed method addresses key challenges such as driver discomfort and prolonged lane change durations by considering the entire lane change process rather than just the initiation point. Utilizing a fifth-order polynomial for trajectory planning, the strategy ensures smooth and continuous vehicle movement, reducing the risk of collisions. The effectiveness of the method is validated through comprehensive simulations and real-world vehicle tests, demonstrating significant improvements in lane change performance. Despite its advantages, the model requires further refinement to address limitations in mixed traffic conditions. This research provides a foundation for developing intelligent vehicle systems that prioritize safety and adaptability.
