GeoNER:Geological Named Entity Recognition with Enriched Domain Pre-Training Model and Adversarial Training

As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.

Enhanced UAV Pursuit-Evasion Using Boids Modelling:A Synergistic Integration of Bird Swarm Intelligence and DRL

TheUAV pursuit-evasion problem focuses on the efficient tracking and capture of evading targets using unmanned aerial vehicles(UAVs),which is pivotal in public safety applications,particularly in scenarios involving intrusion monitoring and interception.To address the challenges of data acquisition,real-world deployment,and the limited intelligence of existing algorithms in UAV pursuit-evasion tasks,we propose an innovative swarm intelligencebased UAV pursuit-evasion control framework,namely“Boids Model-based DRL Approach for Pursuit and Escape”(Boids-PE),which synergizes the strengths of swarm intelligence from bio-inspired algorithms and deep reinforcement learning(DRL).The Boids model,which simulates collective behavior through three fundamental rules,separation,alignment,and cohesion,is adopted in our work.By integrating Boids model with the Apollonian Circles algorithm,significant improvements are achieved in capturing UAVs against simple evasion strategies.To further enhance decision-making precision,we incorporate a DRL algorithm to facilitate more accurate strategic planning.We also leverage self-play training to continuously optimize the performance of pursuit UAVs.During experimental evaluation,we meticulously designed both one-on-one and multi-to-one pursuit-evasion scenarios,customizing the state space,action space,and reward function models for each scenario.Extensive simulations,supported by the PyBullet physics engine,validate the effectiveness of our proposed method.The overall results demonstrate that Boids-PE significantly enhance the efficiency and reliability of UAV pursuit-evasion tasks,providing a practical and robust solution for the real-world application of UAV pursuit-evasion missions.

A discussion about the limitations of the Eurocode’s high-speed load model for railway bridges

High-speed railway bridges are subjected to normative limitations concerning maximum permissible deck accelerations.For the design of these structures,the European norm EN 1991-2 introduces the high-speed load model(HSLM)—a set of point loads intended to include the effects of existing high-speed trains.Yet,the evolution of current trains and the recent development of new load models motivate a discussion regarding the limits of validity of the HSLM.For this study,a large number of randomly generated load models of articulated,conventional,and regular trains are tested and compared with the envelope of HSLM effects.For each type of train,two sets of 100,000 load models are considered:one abiding by the limits of the EN 1991-2 and another considering wider limits.This comparison is achieved using both a bridge-independent metric(train signatures)and dynamic analyses on a case study bridge(the Canelas bridge of the Portuguese Railway Network).For the latter,a methodology to decrease the computational cost of moving loads analysis is introduced.Results show that some theoretical load models constructed within the stipulated limits of the norm can lead to effects not covered by the HSLM.This is especially noted in conventional trains,where there is a relation with larger distances between centres of adjacent vehicle bogies.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

Disturbance rejection tube model predictive levitation control of maglev trains

Magnetic levitation control technology plays a significant role in maglev trains.Designing a controller for the levitation system is challenging due to the strong nonlinearity,open-loop instability,and the need for fast response and security.In this paper,we propose a Disturbance-Observe-based Tube Model Predictive Levitation Control(DO-TMPLC)scheme combined with a feedback linearization strategy for the levitation system.The proposed strategy incorporates state constraints and control input constraints,i.e.,the air gap,the vertical velocity,and the current applied to the coil.A feedback linearization strategy is used to cancel the nonlinearity of the tracking error system.Then,a disturbance observer is implemented to actively compensate for disturbances while a TMPLC controller is employed to alleviate the remaining disturbances.Furthermore,we analyze the recursive feasibility and input-to-state stability of the closed-loop system.The simulation results indicate the efficacy of the proposed control strategy.

Robust Parameter Identification Method of Adhesion Model for Heavy Haul Trains

A robust parameter identification method based on Kiencke model was proposed to solve the problem of the parameter identification accuracy being affected by the rail environment change and noise interference for heavy-duty trains. Firstly, a Kiencke stick-creep identification model was constructed, and the parameter identification task was transformed into a quadratic programming problem. Secondly, an iterative algorithm was constructed to solve the problem, into which a time-varying forgetting factor was added to track the change of the rail environment, and to solve the uncertainty problem of the wheel-rail environment. The Granger causality test was adopted to detect the interference, and then the weights of the current data were redistributed to solve the problem of noise interference in parameter identification. Finally, simulations were carried out and the results showed that the proposed method could track the change of the track environment in time, reduce the noise interference in the identification process, and effectively identify the adhesion performance parameters.

Security Vulnerability Analyses of Large Language Models (LLMs) through Extension of the Common Vulnerability Scoring System (CVSS) Framework

Large Language Models (LLMs) have revolutionized Generative Artificial Intelligence (GenAI) tasks, becoming an integral part of various applications in society, including text generation, translation, summarization, and more. However, their widespread usage emphasizes the critical need to enhance their security posture to ensure the integrity and reliability of their outputs and minimize harmful effects. Prompt injections and training data poisoning attacks are two of the most prominent vulnerabilities in LLMs, which could potentially lead to unpredictable and undesirable behaviors, such as biased outputs, misinformation propagation, and even malicious content generation. The Common Vulnerability Scoring System (CVSS) framework provides a standardized approach to capturing the principal characteristics of vulnerabilities, facilitating a deeper understanding of their severity within the security and AI communities. By extending the current CVSS framework, we generate scores for these vulnerabilities such that organizations can prioritize mitigation efforts, allocate resources effectively, and implement targeted security measures to defend against potential risks.

Contribution of the MERISE-Type Conceptual Data Model to the Construction of Monitoring and Evaluation Indicators of the Effectiveness of Training in Relation to the Needs of the Labor Market in the Republic of Congo

This study proposes the use of the MERISE conceptual data model to create indicators for monitoring and evaluating the effectiveness of vocational training in the Republic of Congo. The importance of MERISE for structuring and analyzing data is underlined, as it enables the measurement of the adequacy between training and the needs of the labor market. The innovation of the study lies in the adaptation of the MERISE model to the local context, the development of innovative indicators, and the integration of a participatory approach including all relevant stakeholders. Contextual adaptation and local innovation: The study suggests adapting MERISE to the specific context of the Republic of Congo, considering the local particularities of the labor market. Development of innovative indicators and new measurement tools: It proposes creating indicators to assess skills matching and employer satisfaction, which are crucial for evaluating the effectiveness of vocational training. Participatory approach and inclusion of stakeholders: The study emphasizes actively involving training centers, employers, and recruitment agencies in the evaluation process. This participatory approach ensures that the perspectives of all stakeholders are considered, leading to more relevant and practical outcomes. Using the MERISE model allows for: • Rigorous data structuring, organization, and standardization: Clearly defining entities and relationships facilitates data organization and standardization, crucial for effective data analysis. • Facilitation of monitoring, analysis, and relevant indicators: Developing both quantitative and qualitative indicators helps measure the effectiveness of training in relation to the labor market, allowing for a comprehensive evaluation. • Improved communication and common language: By providing a common language for different stakeholders, MERISE enhances communication and collaboration, ensuring that all parties have a shared understanding. The study’s approach and contribution to existing research lie in: • Structured theoretical and practical framework and holistic approach: The study offers a structured framework for data collection and analysis, covering both quantitative and qualitative aspects, thus providing a comprehensive view of the training system. • Reproducible methodology and international comparison: The proposed methodology can be replicated in other contexts, facilitating international comparison and the adoption of best practices. • Extension of knowledge and new perspective: By integrating a participatory approach and developing indicators adapted to local needs, the study extends existing research and offers new perspectives on vocational training evaluation.

Exploration of the Integrated Training Model for Information Technology Teachers

With the acceleration of the social information process,information awareness and information skills have become the basic qualities of every citizen.The establishment of the training mechanism for scientific and technological innovation talents from the beginning of higher education is insufficient to meet the needs of the development of the times.It is imperative to improve the training of information technology innovation talents and explore a new training model.This paper describes the general situation of the development of education in the field of information technology from a domestic and international perspective.It then analyzes the existing problems,explores new exploration models and implementation suggestions,and puts forward prospects at the end of the paper.

Temporally Preserving Latent Variable Models:Offline and Online Training for Reconstruction and Interpretation of Fault Data for Gearbox Condition Monitoring

Latent variable models can effectively determine the condition of essential rotating machinery without needing labeled data.These models analyze vibration data via an unsupervised learning strategy.Temporal preservation is necessary to obtain an informative latent manifold for the fault diagnosis task.In a temporalpreserving context,two approaches exist to develop a condition-monitoring methodology:offline and online.For latent variable models,the available training modes are not different.While many traditional methods use offline training,online training can dynamically adjust the latent manifold,possibly leading to better fault signature extraction from the vibration data.This study explores online training using temporal-preserving latent variable models.Within online training,there are two main methods:one focuses on reconstructing data and the other on interpreting the data components.Both are considered to evaluate how they diagnose faults over time.Using two experimental datasets,the study confirms that models from both training modes can detect changes in machinery health and identify faults even under varying conditions.Importantly,the complementarity of offline and online models is emphasized,reassuring their versatility in fault diagnostics.Understanding the implications of the training approach and the available model formulations is crucial for further research in latent variable modelbased fault diagnostics.

Training and Implementation of Subjective Questions Scoring System Based on the Baidu Qianfan Model Platform

Leveraging the Baidu Qianfan model platform,this paper designs and implements a highly efficient and accurate scoring system for subjective questions,focusing primarily on questions in the field of computer network technology.The system enhances the foundational model by utilizing Qianfan’s training tools and integrating advanced techniques,such as supervised fine-tuning.In the data preparation phase,a comprehensive collection of subjective data related to computer network technology is gathered,cleaned,and labeled.During model training and evaluation,optimal hyperparameters and tuning strategies are applied,resulting in a model capable of scoring with high accuracy.Evaluation results demonstrate that the proposed model performs well across multiple dimensions-content,expression,and development scores-yielding results comparable to those of manual scoring.

A Study on the Work Process-Based Practical Training Model for Basic Nursing Skills in Vocational Colleges

Objective:To explore and analyze the work process-based practical training teaching model for basic nursing skills in vocational colleges and its implementation effects.Methods:A total of 82 nursing students from our school were selected for the study,which was conducted from April 2023 to April 2024.Using a random number table method,the students were divided into an observation group and a control group,each with 41 students.The control group received conventional practical training teaching,while the observation group followed the work process-based practical training model for basic nursing skills.The assessment scores and teaching satisfaction of the two groups were compared.Results:The comparison of assessment scores showed that the observation group performed significantly better than the control group(P<0.05).The comparison of teaching satisfaction also indicated that the observation group had significantly higher satisfaction than the control group(P<0.05).Conclusion:The work process-based practical training teaching model for basic nursing skills in vocational colleges can improve students’assessment scores and enhance teaching satisfaction,demonstrating its value for wider application.

Comprehensive Evaluation of Talent Training Model for Modern Rehabilitation Therapy Technology:A Case Study of School Y

The purpose of this study is to comprehensively evaluate the modern training model of rehabilitation therapy technology talents.Selecting the third-year students of the rehabilitation therapy technology program in School Y as the research subject,300 questionnaires were collected and the effective response rate was 92%.The strengths and weaknesses of the modern training model were analyzed through a mixed qualitative and quantitative research method.It was found that 68%of the students thought that the modern model had obvious advantages in practical teaching,but 42%of the students thought that it still needed to be improved in personalized teaching.This study provides an empirical basis and specific suggestions for optimizing the cultivation of rehabilitation therapy technology talents.

Comparative Analysis of Machine Learning Models for PDF Malware Detection:Evaluating Different Training and Testing Criteria

The proliferation of maliciously coded documents as file transfers increase has led to a rise in sophisticated attacks.Portable Document Format(PDF)files have emerged as a major attack vector for malware due to their adaptability and wide usage.Detecting malware in PDF files is challenging due to its ability to include various harmful elements such as embedded scripts,exploits,and malicious URLs.This paper presents a comparative analysis of machine learning(ML)techniques,including Naive Bayes(NB),K-Nearest Neighbor(KNN),Average One Dependency Estimator(A1DE),RandomForest(RF),and SupportVectorMachine(SVM)forPDFmalware detection.The study utilizes a dataset obtained from the Canadian Institute for Cyber-security and employs different testing criteria,namely percentage splitting and 10-fold cross-validation.The performance of the techniques is evaluated using F1-score,precision,recall,and accuracy measures.The results indicate that KNNoutperforms other models,achieving an accuracy of 99.8599%using 10-fold cross-validation.The findings highlight the effectiveness of ML models in accurately detecting PDF malware and provide insights for developing robust systems to protect against malicious activities.

A simplified pneumatic model for air brake of passenger trains

Braking system performance is relevant for both railway safety and network optimization. Most trains employ air brake systems;air brake systems of freight trains mostly cannot achieve a synchronous application of brake forces, which is usually customary for passenger trains. The paper generalizes a previous air brake pneumatic model to passenger trains and describes the needed modifications. Among them, the way the pressure reduces in the brake pipe is generalized. Moreover, this paper reports an analytical bi-dimensional function for calculating the nozzle diameter equivalent to the electro-pneumatic(EP) or the electronically controlled pneumatic(ECP)brake valve as a function of the wagon length and the time to vent the brake pipe locally. The numerical results of the new model are compared against several experimental tests of high-speed passenger trains of Trenitalia, namely ETR500 and ETR1000. The model is suitable to be integrated into the UIC software TrainDy, aiming to extend its computational field to passenger trains and to simulate the safety of trains during a recovery.

Joint On-Demand Pruning and Online Distillation in Automatic Speech Recognition Language Model Optimization

Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.

超声训练模型在医学院校超声实训教学的应用

超声是一门对操作技巧要求很高的学科,实训课教学中需要学生进行反复的超声检查操作训练。仿真检查训练模型是临床医学教学中的良好教具,在超声实训教学中的应用丰富了课堂教学资源、扩展了实训内容,可满足典型病例训练的需求,为学生提供了积极安全的实践机会。把应用体模教学与传统教学方法、灵活多样的先进教学手段有机地结合起来,提高超声实训课的教学效果,提高学生的实际操作技能和诊断能力,培养具有很强实践动手能力的应用型医学人才。

基于CIPP模型的全科基层实践基地指导医师门诊教学能力提升项目评价研究

背景基层实践基地指导医师的门诊教学能力是关系到全科住院医师规范化培训质量的重要因素。近年来,国内多个地区开展了社区全科师资培训项目,但缺少采用综合方法评价项目实施情况的相关研究。目的探明浙江大学医学院附属第二医院“分层督导式教学门诊”培训项目的实施现状与阻碍因素,为制定问题导向的应对策略提供理论参考和策略支持。方法2021年10月—2022年1月,基于CIPP模型,使用内容分析法、专家会议法、深度访谈法、专家评分法、问卷调查法等多种研究方法,从背景、输入、过程和成果4个方面对浙江大学医学院附属第二医院全科医学科“分层督导式教学门诊”培训项目的实施情况进行系统评估。结果政策文件分析和文献回顾结果表明,社区师资培训是受到国家卫生政策大力支持的医疗人才培养计划,且目前在国内已有广泛的实践基础。浙江大学医学院附属第二医院全科医学科“分层督导式教学门诊”培训制度基本涵盖了社区全科师资培训的内容和过程规范,基层实践基地制定的考核和激励制度缺乏实施细则,2021年5月—2022年1月,10名基层指导医师共完成了57人次社区教学门诊,每人参加4~7轮次,人均门诊教学能力评价得分从第1轮次的(78.6±5.7)分提升至第7轮次的(87.8±4.5)分。基层指导医师和全科住院医师对“教学场地与设备”“培训形式”“培训内容”及“培训效果”的满意度均超过90%,但基层指导医师对“教学激励制度”的满意度仅为20%。参与项目培训的受访者反映目前存在的主要阻碍因素是“教学相关激励制度不健全”“教学门诊患者招募困难”与“培训内容适用性不足”。结论“分层督导式教学门诊”培训项目初期取得了较为理想的结果,但仍有较大的提升空间,在下一阶段的培训中需要结合基层实践基地的实际情况制定相应的策略,以持续地改进培训质量。

基于RoBERTa-Span-Attack的标签指针网络军事命名实体识别

军事领域文本中存在大量军事实体信息,准确识别这些信息是军事文本信息提取和构建军事知识图谱的基础性任务。首先,提出了一种基于RoBERTa预训练模型、跨度和对抗训练的标签指针网络的融合深度模型(RoBERTa-Span-Attack),用于中文军事命名实体识别;然后,采用了一种基于Span的标签指针网络,同时完成实体的起止位置和类别的识别任务;最后,在模型训练过程中加入对抗训练策略,通过添加一些扰动来生成对抗样本进行训练。在军事领域数据集上的实验结果表明:所提出的军事领域命名实体识别模型相较于BERT-CRF、BERT-Softmax和BERT-Span,在识别准确度上具有更优的效果。

Research on the Evaluation of VBSE Practical Training Teaching Effectiveness Based on CIPP Model at X University

Based on the CIPP(context,input,process,and product)model,this paper constructs an index system suitable for evaluating the teaching effect of VBSE(virtual business social environment)practical training from four aspects:context evaluation,input evaluation,process evaluation,and product evaluation.Taking the students participating in VBSE practical training in X university as the survey population,381 valid sample data were obtained through an online questionnaire survey,and the index weights were determined by factor analysis method.The score value of the VBSE practical training teaching effect was calculated based on the evaluation mean value of three indexes.The results showed that the context evaluation score was 1.56,the input evaluation score was 1.54,the process evaluation score was 1.51,and the product evaluation score was 1.48.Subsequently,this paper put forward some countermeasures from the aspects of optimizing course arrangement,improving hardware facilities,and enhancing team cooperation to provide a guideline for improving the effect of VBSE practical training.