检索结果-内蒙古大学图书馆

A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems

Journal of Computer science & technology 2023年第6期38卷 1203-1222页

作者：刘嘉聿汪飞马海平黄振亚刘淇陈恩红苏喻 School of Data Science University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Cognitive Intelligence Hefei 230088China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei 230026China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601China School of Computer Science and Artificial Intelligence Hefei Normal UniversityHefei 230061China

Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge *** existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning *** this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis ***,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness ***,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model *** UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.

关键词： cognitive diagnosis probabilistic graphical model item response theory(IRT) stochastic process expectation maximization(EM)algorithm

来源：评论

学校读者我要写书评

暂无评论

A Progressive Skip Reasoning Fusion Method for Multi-Modal Classification 24

A Progressive Skip Reasoning Fusion Method for Multi-Modal C...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Qian Liang, Xinyan Qian, Yuhua Cui, Zhihua Wen, Jie Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Taiyuan China Institute of Big Data Science and Industry Shanxi University Taiyuan China

ISBN: (纸本)9798400706868

In multi-modal classification tasks, a good fusion algorithm can effectively integrate and process multi-modal data, thereby significantly improving its performance. Researchers often focus on the design of complex fusion operators and have proposed numerous fusion operators, while paying less attention to the design of feature fusion usage, specifically how features should be fused to better facilitate multi-modal classification tasks. In this article, we propose a progressive skip reasoning fusion network (PSRFN) to make some attempts to address this issue. Firstly, unlike most existing multi-modal fusion methods that only use one fusion operator in a single stage to fuse all view features, PSRFN utilizes the progressive skip reasoning (PSR) block to fuse all views with a fusion operator at each layer. Specifically, each PSR block utilizes all view features and the fused features from the previous layer to jointly obtain the fused features for the current layer. Secondly, each PSR block utilizes a dual-weighted fusion strategy with learnable parameters to adaptively allocate weights during the fusion process. The first level of weighting assigns weights to each view feature, while the second level assigns weights to the fused features from the previous layer and the fused features obtained from the first level of weighting in the current layer. This strategy ensures that the PSR block can dynamically adjust the weights based on the actual contribution of features. Finally, to enable the model to fully utilize feature information from different levels for feature fusion, the skip connections are adopted between PSR blocks. Extensive experiment results on six real multi-modal datasets show that a better usage for fusion operator is indeed able to improve performance. © 2024 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Integrated Sensing-Communication-Computation for Edge Artificial Intelligence

引用

IEEE Internet of Things Magazine 2024年第4期7卷 14-20页

作者： Wen, Dingzhu Li, Xiaoyang Zhou, Yong Shi, Yuanming Wu, Sheng Jiang, Chunxiao School of Information Science and Technology ShanghaiTech University China Shenzhen Research Institute of Big Data China Beijing University of Posts and Telecommunications China Tsinghua University Beijing National Research Center for Information Science and Technology China

Edge artificial intelligence (AI) has been a promising solution towards 6G to empower a series of advanced techniques such as digital twins, holographic projection, semantic communications, and auto-driving, for achieving intelligence of everything. The performance of edge AI tasks, including edge learning and edge AI inference, depends on the quality of three highly coupled processes, i.e., sensing for data acquisition, computation for information extraction, and communication for information transmission. However, these three modules need to compete for network resources for enhancing their own quality-of-services. To this end, integrated sensing-communication-computation (ISCC) is of paramount significance for improving resource utilization as well as achieving the customized goals of edge AI tasks. By investigating the interplay among the three modules, this article presents various kinds of ISCC schemes for federated edge learning tasks and edge AI inference tasks in both application and physical layers. © 2018 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Green technology innovation guiding policies under the synergy of government and financial institutions

引用

Sustainable Operations and Computers 2024年第1期5卷 269-277页

作者： Ma, Yanhong Zhao, Hui School of Economics and Management Beijing Information Science and Technology University Beijing100192 China Beijing Key Lab of Green Development Decision Based on Big Data Beijing100192 China

Guiding enterprises towards green technology innovation (GTI) is a pivotal strategy for mitigating pollution and energy wastage, thereby facilitating the transition towards a green and low-carbon economy. In order to solve the single irrationality of the existing guidance policy and improve its implementation effect, parameters of environmental regulation and green credit policy are hereby introduced to construct a tripartite evolutionary game model of the government, financial institutions, and enterprises. The evolutionary stability of the government and financial institutions in guiding enterprises' GTI is analyzed. Simulation analysis method is used to visualize the evolution path of the game system under different policy options. The study results show that increasing interest rate subsidies can promote the financial institutions and the government to formulate GTI guidance policies. Besides, there is a significant synergistic effect between interest rate subsidies and green credits, which can efficiently foster GTI within enterprises and decrease their innovation costs. Building on this foundation, further increasing the carbon tax rate can lead to a reduction in government subsidy expenditures, improve the evolution rate of the ideal strategy, and expedite the realization of a green, low-carbon transformation. © 2024

关键词： Green economy

来源：评论

学校读者我要写书评

暂无评论

Benefit of aerosol reduction to winter wheat during China's clean air action:A case study of Henan Province

引用

Journal of Environmental sciences 2024年第7期36卷 90-101页

作者： Yang Bai Pengfei Zhao Xueyang Chen Lijun Wang Wenjuan Chang Jianzhong Guo Jiayao Wang College of Geography and Environmental Science Henan UniversityKaifeng 475004China Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan UniversityZhengzhou 475000China Henan Technology Innovation Center of Spatio-Temporal Big Data Henan UniversityZhengzhou 450046China Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions(Henan University) Ministry of EducationKaifeng 475000China

A strongly declining aerosol radiative effect has been observed in China since 2013 after implementing the clean air action,yet its impact on wheat(Triticum aestivum L.)production remains *** use satellite measures and a biophysical crop model to assess the impact of aerosol-induced radiative perturbations on winter wheat production in the agricultural belt of Henan province from 2013 to *** calibrating parameters with the extended Fourier Amplitude Sensitivity Test(EFAST)and the generalized likelihood uncertainty estimation(GLUE)method,the DSSAT CERES-Wheat model was able to simulate crop biomass and yield more *** found that the aerosol negatively impacted wheat biomass by 21.87%and yield by 22.48%from 2006 to 2018,and the biomass effects from planting to anthesis were more significant compared to anthesis to *** to the strict clean air action,under all-sky conditions,the surface solar shortwave radiation(SSR)in 2018 increased by about 7.08%over 2006-2013 during the wheat growing *** a result of the improvement of crop photosynthesis,winter wheat biomass and yield increased by an average of 5.46%and 2.9%,*** findings show that crop carbon uptake and yield will benefit from the clean air action in China,helping to ensure national food and health security.

关键词： Haze pollution Clean air action Aerosol-induced radiative perturbation Wheat production DSSAT model

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis of batch process based on improved GA-SeparableConv1D-TCN network 43

Fault diagnosis of batch process based on improved GA-Separa...

引用

第43届中国控制会议

作者： He Yueyang Liang Xiuxia Xia Manman Liang Tao School of Artificial Intelligence and Data Science Hebei University of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Batch process is an indispensable part of modern industrial production. Because of its flexibility and high efficiency,it is widely used in biopharmaceutical,wastewater treatment,fine chemical and other fields. Due to the improvement of modern equipment and the expansion of the scale of the factory,the chance of accidents and failures also showed an exponential increase trend. Therefore,fault diagnosis is very important to ensure the stability and safety of chemical processes. In order to improve the safety and reliability of batch process,an improved Genetic Algorithm is proposed to optimize the parameters of Separable Convolution Network and Temporal Convolutional Network(SeparableConv1D-TCN) for fault diagnosis of batch process. Firstly,the SeparableConv1D-TCN network is constructed to extract features from the original intermittent data and perform fault diagnosis by standardizing the intermittent data. In order to find the network parameters with high diagnostic accuracy,the genetic algorithm with good point set method and optimal domain search is used to optimize. The effectiveness of the method is verified by simulation experiments and comparative experiments with penicillin experimental data.

关键词： Batch Process Fault Diagnosis SeparableConv1D-TCN Genetic Algorithm

来源：评论

学校读者我要写书评

暂无评论

Proximal Policy Optimization-Based Intrusion Detection Model for Satellite Networks 5

Proximal Policy Optimization-Based Intrusion Detection Model...

引用

5th International Symposium on Computer Engineering and Intelligent Communications, ISCEIC 2024

作者： Liang, Shuaishuai Feng, Huibin Wu, Jiawei He, Canfei College of Computer and Data Science Fuzhou University Fuzhou China School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798331518677

As satellite network communication systems become an increasingly pivotal role in modern life, The routine maintenance of satellite networks is challenging due to limited resources and their susceptibility to interference. Satellite networks are more reliant on interruption detection systems than terrestrial networks. The importance of interruption detection systems in satellite networks is becoming increasingly evident. In this paper, we propose a novel intrusion detection model based on Proximal Policy Optimization (PPO). This method interacts with the environment to learn and optimize detection strategies, allowing for dynamic adaptation to environmental changes and attack patterns. We evaluated our model on benchmark datasets and compared its performance metrics against existing models. The results demonstrate that our proposed model significantly enhances overall accuracy and precision, and outperforms baseline models in terms of training convergence speed. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

NEURON-ENHANCED AUTOENCODER MATRIX COMPLETION AND COLLABORATIVE FILTERING: THEORY AND PRACTICE 12

NEURON-ENHANCED AUTOENCODER MATRIX COMPLETION AND COLLABORAT...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Fan, Jicong Chen, Rui Zhang, Zhao Ding, Chris H.Q. School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Computer Science & Information Engineering Hefei University of Technology China

Neural networks have shown promising performance in collaborative filtering and matrix completion but the theoretical analysis is limited and there is still room for improvement in terms of the accuracy of recovering missing values. This paper presents a neuron-enhanced autoencoder matrix completion (AEMC-NE) method and applies it to collaborative filtering. Our AEMC-NE adds an element-wise autoencoder to each output of the main autoencoder to enhance the reconstruction capability. Thus it can adaptively learn an activation function for the output layer to approximate possibly complicated response functions in real data. We provide theoretical analysis for AEMC-NE as well as AEMC to investigate the generalization ability of autoencoder and deep learning in matrix completion, considering both missing completely at random and missing not at random. We show that the element-wise neural network has the potential to reduce the generalization error bound, the data sparsity can be useful, and the prediction performance is closely related to the difference between the numbers of variables and samples. The numerical results on synthetic data and five benchmark datasets demonstrated the effectiveness of AEMC-NE in comparison to many baselines. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

High Performance Electrically Small Huygens Rectennas Enable Wirelessly Powered Internet of Things Sensing Applications:A Review

引用

Engineering 2022年第4期8卷 42-59页

作者： Wei Lin Richard W.Ziolkowski Global Big Data Technologies Centre School of Electrical and Data EngineeringUniversity of Technology SydneyUltimoNSW 2007Australia

Far-field wireless power transfer(WPT)is a major breakthrough technology that will enable the many anticipated ubiquitous Internet of Things(IoT)applications associated with fifth generation(5G),sixth generation(6G),and beyond wireless ***,which are the combination of rectifying circuits and antennas,are the most critical components in far-field WPT ***,compact application devices require even smaller integrated rectennas that simultaneously have large electromagnetic wave capture capabilities,high alternating current(AC)-to-direct current(DC)(AC-to-DC)conversion efficiencies,and facilitate a multifunctional wireless *** paper reviews various rectenna miniaturization techniques such as meandered planar inverted-F antenna(PIFA)rectennas;miniaturized monopole-and dipole-based rectennas;fractal loop and patch rectennas;dielectric-loaded rectennas;and electrically small near-field resonant parasitic *** performance characteristics are summarized and then compared with our previously developed electrically small Huygens rectennas that are proven to be more suitable for IoT *** have been tailored,for example,to achieve batteryfree IoT sensors as is demonstrated in this ***-free,wirelessly powered devices are smaller and lighter in weight in comparison to battery-powered ***,they are environmentally friendly and,hence,have a significant societal benefit.A series of high-performance electrically small Huygens rectennas are presented including Huygens linearly-polarized(HLP)and circularly-polarized(HCP)rectennas;wirelessly powered IoT sensors based on these designs;and a dual-functional HLP rectenna and antenna ***,two linear uniform HLP rectenna array systems are considered for significantly larger wireless power *** arrays illustrate how they can be integrated advantageously with DC or radio frequency(RF)power-combining schemes for practical IoT applications.

关键词： Antenna Array Cardioid pattern Electrically small antenna Huygens dipole antenna Internet of Things(IoT) Rectenna Rectifier circuit Wireless power transfer

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Traditional Chinese Medicine Image Classification and Recognition with an Improved YOLOv5 2

Revolutionizing Traditional Chinese Medicine Image Classific...

引用

2nd International Conference on Health big data and Intelligent Healthcare, ICHIH 2023

作者： Che, Kaihua Liang, Yuheng Zeng, Yuyu Li, Tongfei Zhu, Xiaolin Lv, Wei Zhuhai College of Science and Technology School of Aliyun Big Data Application Zhuhai China

ISBN: (纸本)9798350309324

With the continuous development and application of traditional Chinese medicine (TCM), automated recognition and classification of TCM herbs has become increasingly important. This thesis introduces a YOLOv5 model based on the GIOU loss function for the classification and recognition task of TCM images. The model combines the fast target detection capability of YOLOv5 and the superior performance of the GIOU loss function to achieve efficient and robust classification of TCM images. Experiments were conducted on a dataset containing a large number of TCM images to evaluate the performance of our model. The experimental results show that the improved YOLOv5 model has an average precision of 85.15% and an accuracy of 98.64% for a threshold range of 0.5 to 0.95, which is an improvement over the native yolov5s type. This meets the requirements of Chinese herbal medicine image classification in the actual application. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：