Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection ...Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same time.In order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement prediction.Through MIC,a suitable input sequence length is selected for the LSTM model.To investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different lengths.The teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://rp5.ru)to improve the model’s expression capability,and the student model learns sequence information from other time series.An attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention mode.Finally,the predicted displacement is obtained through a linear layer.The proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention models.It achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PCCS)of 0.85.Additionally,it exhibits enhanced prediction stability and interpretability,rendering it an indispensable tool for landslide disaster prevention and mitigation.展开更多
In this work,we propose a comprehensive theoretical framework for the multilevel NAND(NOT AND logic)flash memory,built upon the modified Student’s t distribution where the distortion of the threshold voltage caused b...In this work,we propose a comprehensive theoretical framework for the multilevel NAND(NOT AND logic)flash memory,built upon the modified Student’s t distribution where the distortion of the threshold voltage caused by the random telegraph noise,cell-to-cell interference and data retention noise are jointly considered.Based on the superposition modulation,we build a non-orthogonal multiuser communication model where a linear mapping is conducted between the verify voltages and binary antipodal symbols.Aimed at improving the storage efficiency,we propose an unequal amplitude mapping(UAM)solution by optimizing the weighting coefficients of verify voltages to intelligently adjust the width of each state.Moreover,the uniform storage efficiency region and sum storage efficiency of different labelings with various decoding schemes are discussed.Simulation results validate the effectiveness of our proposed UAM solution where an up to 20.9%storage efficiency gain can be achieved compared to the current used benchmark scheme.In addition,analytical and simulation results also demonstrate that the successive cancellation decoding outperforms other decoding schemes for all labelings.展开更多
Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation...Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation,and adaptive testing.Cognitive Diagnosis(CD)and Knowledge Tracing(KT)are two mainstream categories for student cognitive modeling,which measure the cognitive ability from a limited time(e.g.,an exam)and the learning ability dynamics over a long period(e.g.,learning records from a year),respectively.Recent efforts have been dedicated to the development of open-source code libraries for student cognitive modeling.However,existing libraries often focus on a particular category and overlook the relationships between them.Additionally,these libraries lack sufficient modularization,which hinders reusability.To address these limitations,we have developed a unified PyTorch-based library EduStudio,which unifies CD and KT for student cognitive modeling.The design philosophy of EduStudio is from two folds.From a horizontal perspective,EduStudio employs the modularization that separates the main step pipeline of each algorithm.From a vertical perspective,we use templates with the inheritance style to implement each module.We also provide eco-services of EduStudio,such as the repository that collects resources about student cognitive modeling and the leaderboard that demonstrates comparison among models.Our open-source project is available at the website of edustudio.ai.展开更多
The pedagogical promise of Competency-Based Education(CBE)has been historically undermined by pro-found challenges of scalability,creating an implementation gap between its theoretical merits and practicalapplication....The pedagogical promise of Competency-Based Education(CBE)has been historically undermined by pro-found challenges of scalability,creating an implementation gap between its theoretical merits and practicalapplication.This paper proposes a testable mechanism model wherein Artificial Intelligence(Al)enables the scaling of CBE through three interconnected pathways-diagnostic tracking,adaptive supply,and teacher or-chestration-formalized within a distributed cognition framework.To operationalize this model,this paper in-troduces novel constructs including the"Adaptive-Autonomy Curve"for systematically cultivating self-regulated learning in personalized environments,and a"Situated Performance-Based Assessment Pipeline"for authentic,scalable evaluation of complex skills.The primary contributions of this work are fourfold:first,it provides a rigorous conceptual taxonomy that delineates CBE from adjacent paradigms such as mastery learning and per-sonalized learning;second,it advances a set of falsifiable propositions to guide future empirical research;third,it formalizes the human-Al pedagogical relationship with operational design principles;and fourth,it presents an integrated governance and interoperability protocol for the responsible and effective implementation of Al in competency-based systems.展开更多
This paper addresses the critical need for a holistic,evidence-based national strategy to cultivate a world-class artificial intelligence(Al)talent pool.As Al reshapes global economies,labor markets,and the geopolitic...This paper addresses the critical need for a holistic,evidence-based national strategy to cultivate a world-class artificial intelligence(Al)talent pool.As Al reshapes global economies,labor markets,and the geopolitical land-scape,national competitiveness hinges on the ability to develop,attract,and retain Al expertise.Employing a systematic scoping review methodology,this study synthesizes evidence from academic literature,government policy documents,and industry white papers to construct an integrated strategic blueprint.The analysis decon-structs the core components of a comprehensive talent development policy,proposing a multi-pillar framework that integrates a lifelong learning continuum,a differentiated talent pipeline architecture,synergistic public-private enablers,and modernized evaluation paradigms.Through a comparative analysis of divergent nationalstrategies-including the market-driven model of the United States,the governance-first approach of the Eu-ropean Union,and the state-directed models of India,Singapore,the United Arab Emirates,and Canada-this paper illuminates the trade-offs between different philosophical and tactical choices.Key findings reveal the heterogeneous nature of Al's impact on labor,the centrality of public trust as a prerequisite for adoption,and a necessary paradigm shift from credential-based to competency-based talent evaluation.The proposed blueprint,which introduces a novel"Builder-Bridger"talent model,offers a comprehensive,actionable guide for policymakers and academic leaders aiming to build a sustainable and globally competitive national Al talent base capable of navigating the complexities of the Al era.展开更多
This paper presents the use of a student model to improve the explanations provided by an intelligent tu- toring system,namely SimpleQuestl,in the domain of electronics.The method of overlay modelling is adopted to bu...This paper presents the use of a student model to improve the explanations provided by an intelligent tu- toring system,namely SimpleQuestl,in the domain of electronics.The method of overlay modelling is adopted to build the student model.The diagnosis is based on the comparison of the behavinurs of the student and the ex- pert.The student model is consulted by the “explainer” and “debugging” procedures in order to re-order the sequence of the explanation.展开更多
基金This research work is supported by Sichuan Science and Technology Program(Grant No.2022YFS0586)the National Key R&D Program of China(Grant No.2019YFC1509301)the National Natural Science Foundation of China(Grant No.61976046).
文摘Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same time.In order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement prediction.Through MIC,a suitable input sequence length is selected for the LSTM model.To investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different lengths.The teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://rp5.ru)to improve the model’s expression capability,and the student model learns sequence information from other time series.An attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention mode.Finally,the predicted displacement is obtained through a linear layer.The proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention models.It achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PCCS)of 0.85.Additionally,it exhibits enhanced prediction stability and interpretability,rendering it an indispensable tool for landslide disaster prevention and mitigation.
基金supported by Key Project of Sichuan Provincial Natural Science Foundation(No.2022NSFSC0043).
文摘In this work,we propose a comprehensive theoretical framework for the multilevel NAND(NOT AND logic)flash memory,built upon the modified Student’s t distribution where the distortion of the threshold voltage caused by the random telegraph noise,cell-to-cell interference and data retention noise are jointly considered.Based on the superposition modulation,we build a non-orthogonal multiuser communication model where a linear mapping is conducted between the verify voltages and binary antipodal symbols.Aimed at improving the storage efficiency,we propose an unequal amplitude mapping(UAM)solution by optimizing the weighting coefficients of verify voltages to intelligently adjust the width of each state.Moreover,the uniform storage efficiency region and sum storage efficiency of different labelings with various decoding schemes are discussed.Simulation results validate the effectiveness of our proposed UAM solution where an up to 20.9%storage efficiency gain can be achieved compared to the current used benchmark scheme.In addition,analytical and simulation results also demonstrate that the successive cancellation decoding outperforms other decoding schemes for all labelings.
基金supported in part by grants from the National Science and Technology Major Project,China(Grant No.2021ZD0111802)the National Natural Science Foundation of China(Grant Nos.72188101,62406096,and 62376086)the Fundamental Research Funds for the Central Universities,China(Grant No.JZ2024HGQB0093).
文摘Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation,and adaptive testing.Cognitive Diagnosis(CD)and Knowledge Tracing(KT)are two mainstream categories for student cognitive modeling,which measure the cognitive ability from a limited time(e.g.,an exam)and the learning ability dynamics over a long period(e.g.,learning records from a year),respectively.Recent efforts have been dedicated to the development of open-source code libraries for student cognitive modeling.However,existing libraries often focus on a particular category and overlook the relationships between them.Additionally,these libraries lack sufficient modularization,which hinders reusability.To address these limitations,we have developed a unified PyTorch-based library EduStudio,which unifies CD and KT for student cognitive modeling.The design philosophy of EduStudio is from two folds.From a horizontal perspective,EduStudio employs the modularization that separates the main step pipeline of each algorithm.From a vertical perspective,we use templates with the inheritance style to implement each module.We also provide eco-services of EduStudio,such as the repository that collects resources about student cognitive modeling and the leaderboard that demonstrates comparison among models.Our open-source project is available at the website of edustudio.ai.
文摘The pedagogical promise of Competency-Based Education(CBE)has been historically undermined by pro-found challenges of scalability,creating an implementation gap between its theoretical merits and practicalapplication.This paper proposes a testable mechanism model wherein Artificial Intelligence(Al)enables the scaling of CBE through three interconnected pathways-diagnostic tracking,adaptive supply,and teacher or-chestration-formalized within a distributed cognition framework.To operationalize this model,this paper in-troduces novel constructs including the"Adaptive-Autonomy Curve"for systematically cultivating self-regulated learning in personalized environments,and a"Situated Performance-Based Assessment Pipeline"for authentic,scalable evaluation of complex skills.The primary contributions of this work are fourfold:first,it provides a rigorous conceptual taxonomy that delineates CBE from adjacent paradigms such as mastery learning and per-sonalized learning;second,it advances a set of falsifiable propositions to guide future empirical research;third,it formalizes the human-Al pedagogical relationship with operational design principles;and fourth,it presents an integrated governance and interoperability protocol for the responsible and effective implementation of Al in competency-based systems.
文摘This paper addresses the critical need for a holistic,evidence-based national strategy to cultivate a world-class artificial intelligence(Al)talent pool.As Al reshapes global economies,labor markets,and the geopolitical land-scape,national competitiveness hinges on the ability to develop,attract,and retain Al expertise.Employing a systematic scoping review methodology,this study synthesizes evidence from academic literature,government policy documents,and industry white papers to construct an integrated strategic blueprint.The analysis decon-structs the core components of a comprehensive talent development policy,proposing a multi-pillar framework that integrates a lifelong learning continuum,a differentiated talent pipeline architecture,synergistic public-private enablers,and modernized evaluation paradigms.Through a comparative analysis of divergent nationalstrategies-including the market-driven model of the United States,the governance-first approach of the Eu-ropean Union,and the state-directed models of India,Singapore,the United Arab Emirates,and Canada-this paper illuminates the trade-offs between different philosophical and tactical choices.Key findings reveal the heterogeneous nature of Al's impact on labor,the centrality of public trust as a prerequisite for adoption,and a necessary paradigm shift from credential-based to competency-based talent evaluation.The proposed blueprint,which introduces a novel"Builder-Bridger"talent model,offers a comprehensive,actionable guide for policymakers and academic leaders aiming to build a sustainable and globally competitive national Al talent base capable of navigating the complexities of the Al era.
文摘This paper presents the use of a student model to improve the explanations provided by an intelligent tu- toring system,namely SimpleQuestl,in the domain of electronics.The method of overlay modelling is adopted to build the student model.The diagnosis is based on the comparison of the behavinurs of the student and the ex- pert.The student model is consulted by the “explainer” and “debugging” procedures in order to re-order the sequence of the explanation.
