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

Efficient Deep learning-based Real-time Migration Strategies for Containers in SDN 6

Efficient Deep learning-based Real-time Migration Strategies...

引用

6th International Conference on Next Generation Data-Driven Networks, NGDN 2024

作者： Huang, Shan Liu, Yanan Li, Yanuo He, Feili Duan, Xiaodong School of Computer Science and Engineering Dalian Minzu University Dalian China Key Laboratory of Big Data Application Technology of the State Ethnic Affairs Commission Dalian China Dalian Ethnic Culture Digital Technology Key Laboratory Dalian China

ISBN: (纸本)9798350388374

Container technology is widely used and improve the efficiency of container real-time migration has become an important research topic. Existing studies mainly focus on optimizing iterative dumping of containers without fully considering the impact of migration node selection on migration efficiency. Software-defined networking (SDN), achieves centralized control of the network by separating the control plane and the forwarding plane. Applying deep learning to SDN makes tasks such as traffic prediction and network optimization more intelligent. This paper proposes Prediction Model based on CLCB (CNN-LSTM-CBAM) uses real-time collected load data as input, extracts feature components of load data using one-dimensional convolutional neural networks, and then predicts using LSTM. To improve prediction accuracy, a lightweight CBAM attention module is introduced, and the prediction results are output through fully connected layers. The Network Traffic Prediction Model based on GCGRU-Conv (GCN-GRU-CNN) considers both spatial and temporal features of network traffic. GCN and GRU are used to extract spatial and temporal features of network traffic, respectively, and then these features are fused together using convolutional neural networks. To address the gradient problem caused by increasing network depth, a residual network structure is introduced. Experimental results show that the method proposed can effectively reduce the container migration time and has better prediction results. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

IntML-KNN: A Few-Shot Radio Frequency Fingerprint Identification Scheme for Lora Devices

引用

IEEE Signal Processing Letters 2025年 32卷 2259-2263页

作者： Cao, Xin Tan, Weijie Gao, Qiangqiang Hu, Zhilong Li, Chunguo Guizhou University College of Computer Science and Technology Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptograph Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

Deep learning (DL) is widely used in radio frequency fingerprint identification (RFFI). However, in few-shot case, traditional DL-based RFFI need to construct auxiliary dataset to realize radio frequency fingerprint identification. To address this issue, we propose a few-shot RFFI (FS-RFFI) method based on interpolating metric learning and KNN (IntML-KNN). Specifically, the method first extends the dataset with data augmentation, and CutMix interpolation. Secondly, combining with metric learning to enhance the generalization capacity of the model. Finally, KNN algorithm is designed to realize device classification and detection. The proposed IntML-KNN method is verified on the commercial available LoRa dataset. The experimental results indicate that the proposed scheme exhibits strong classification and generalization performance in FS-RFFI. Meanwhile, the recognition rate of the proposed IntML-KNN reaches 97.00% with only 10% samples. © 1994-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Aided Reinforcement Learning for Accelerated Optimization of Antenna Topology

引用

Applied Computational Electromagnetics Society Journal 2025年第1期40卷 35-41页

作者： Dou, Jiangling Gong, Hao Wei, Shuaibing Chen, Haokang Chen, Yujie Shen, Tao Song, Jian Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming650500 China School of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China College of Mechanical and Electrical Engineering Yunnan Electromechanical Vocational and Technical College Kunming650500 China

A machine learning (ML) framework is proposed to achieve the automatic and rapid optimization of antenna topologies. A convolutional neural network (CNN) is utilized as a surrogate model (SM) and is combined with reinforcement learning (RL) algorithms. Specifically, the RL agent interacts with simulation software to learn. Data accumulated from electromagnetic (EM) simulations are used to train the SM. The CNN-based SM predicts antenna performance based on the topology of the antenna. Subsequently, the SM replaces EM simulations within the RL training environment. The RL agent interacts with the CNN-based SM to search for the optimal topology. This approach significantly reduces dependence on time-consuming EM simulations. To validate the effectiveness of the optimization method, a center-fed microstrip patch antenna is optimized. Simulation results demonstrate that, compared to other optimization methods, impedance bandwidth is improved, while the number of simulation samples and optimization time are significantly reduced. © ACES.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A quantum‐like approach for text generation from knowledge graphs

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1455-1463页

作者： Jia Zhu Xiaodong Ma Zhihao Lin Pasquale De Meo Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal UniversityJinhuaChina School of Computer Science South China Normal UniversityGuangzhouChina DICAM Department University of MessinaMessinaItaly

Recent text generation methods frequently learn node representations from graph‐based data via global or local aggregation,such as knowledge *** all nodes are connected directly,node global representation encoding enables direct communication between two distant nodes while disregarding graph *** local representation encoding,which captures the graph structure,considers the connections between nearby nodes but misses out onlong‐range relations.A quantum‐like approach to learning bettercontextualised node embeddings is proposed using a fusion model that combines both encoding *** methods significantly improve on two graph‐to‐text datasets compared to state‐of‐the‐art models in various experiments.

关键词： data mining knowledge‐based vision machine learning natural language processing text analysis

来源：评论

学校读者我要写书评

暂无评论

Radioactive Waste Repackaging Methods Based on Genetic Algorithms and Simulation for Reactor Decommissioning 5

Radioactive Waste Repackaging Methods Based on Genetic Algor...

引用

5th International Conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2024

作者： Wu, Tong Wang, Deying Chen, Fengjuan Zhang, Nan Yang, Fan Wang, Jiaqi Xu, Meng Computer Application Institute of Nuclear Industry Beijing China Beijing University of Technology Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education Beijing China

ISBN: (纸本)9798331533991

After going through the lifecycle of design, construction, and operation, nu-clear reactors need go to decommissioning phase according to requirement of nuclear regulator or need of environmental protection. Decommissioning, as the last phase of a nuclear facility's lifecycle, is characterized by its difficulty, long duration, and high cost. During the decommissioning process, various types of waste are generated, such as solid, liquid, gas waste, and mixed waste. In order to protect the surrounding environment from radioactive contamination and prevent excessive radiation exposure to workers and residents, radioactive waste needs to be processed, prepared, transported, stored, and disposed of according to standards. In response to the low space utilization of steel containers due to the irregular shapes of waste when packing decommissioned reactor components, this paper optimizes the process using genetic algorithm to determine the optimal number of cut chunks for reactor components and the best placement of cut chunks in the steel container. First, the complex three-dimensional irregular part packing problem is projected onto a two-dimensional plane for study to simplify the problem's difficulty;second, genetic algorithm is used for individual selection, crossover, and mutation to obtain the optimal layout of individuals;finally, the optimal number of cut chunks in different areas is determined based on the optimization results of individuals, and a global packing solution for all cut chunks is obtained. The results indicate that the proposed method not only provides the optimal cutting solutions for different cutting areas of reactor components and the best placement of cut chunks in the steel container but also satisfies all cutting constraints, potentially providing insights for future reactor decommissioning work © 2024 IEEE.

关键词： Steel containers

来源：评论

学校读者我要写书评

暂无评论

A real-Time framework for dangerous behavior detection based on deep learning 4

A real-Time framework for dangerous behavior detection based...

引用

4th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Yang, Heng Liu, Pengjie Li, Shiyuan Liu, Hongyu Wang, Haofeng Ark Key Laboratory Beijing Institute of Computer Technology and Application Beijing China

ISBN: (纸本)9781450398343

Identifying dangerous behaviors of workers in complex production operation scenarios is an important research field of intelligent monitoring technology. When implementing practical applications, it often has complex and diverse function requirements and business logic. To this end, this paper proposes a unified and simple framework for monitoring unsafe behavior based on deep learning technology. We first conduct data analysis and demand logic disassembly based on six actual production scenarios and decouple the complex task requirement as a coupled problem of object detection function, adaptive and variable scene recognition function, behavior analysis function, and safety logic reasoning function. Then we build a unified detection framework and use four sub-modules for real-Time and high-efficiency detection, which are a perceptron-based efficient scene recognition module, a Yolov5s-based real-Time object detection module, an area-based behavior judgment module, and a configurable safety rule inference module. While maintaining the characteristics of splitting and combining these modules for different application requirements, their effects on the test set have also reached the best. Among them, the accuracy rate of the scene recognition module has reached 100.00%, and the mAP of the object detection module has reached 99.06%, average FPS of the overall framework reached 72.05. © 2022 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Instrument Recognition Method Based on Improved YOLOv5s and ESPNet 6

Multi-Modal Instrument Recognition Method Based on Improved ...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Shen, Shixian Wang, Jianguo Feng, Yong Li, Yingna Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming China China Copper Industry Co. Ltd Kunming China

ISBN: (纸本)9798350374315

Addressing the challenges of high cost, low accuracy, and poor real-time performance in anomaly detection within industrial production processes, this study proposes a multi-modal instrument recognition method based on improved YOLOv5s and ESPNet. Specifically, a dynamic non-monotonic focusing mechanism is introduced into the YOLOv5s object detection model, enhancing its ability to accurately detect the position of pointer-type instruments. Simultaneously, affine and perspective transformations are employed to rectify skewed and rotated images. Secondly, variable convolutions are integrated into the ESPNet segmentation network to adaptively capture nonlinear deformation elements of pointers and dials in images, thereby extracting comprehensive key information from both. Subsequently, a Hough transform operation is applied to fit the straight line representing the pointer, while contour tracking methods are utilized to extract the valid range of dial data. Based on linear proportional relationships, the reading of pointer-type instruments is computed. Finally, a comprehensive model is built by integrating image-acquired instrument data with corresponding sensor data, enabling anomaly detection from a multimodal data analysis perspective. Experimental results demonstrate an identification accuracy of 96.21% for pointer-type instruments, with an average detection speed of 0.216 seconds and a data anomaly detection rate of 99.43%. This method accurately and rapidly identifies data anomalies, meeting the demands for key indicator monitoring in industrial production. © 2024 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Lis...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Shen, Kailai Yan, Diqun Dong, Li Ren, Ying Wu, Xiaoxun Hu, Jing Ningbo University Faculty of Electrical Engineering and Computer Science China Zhejiang Key Laboratory of Mobile Network Application Technology China

ISBN: (纸本)9798350306897

In this paper, we propose the speech quality assessment transformer utilizing listener dependent modeling (SQAT-LD) mean opinion score (MOS) prediction system, which was submitted to the 2023 VoiceMOS Challenge. The system is based on a combination of self-supervised learning (SSL) models and listener-dependent modeling. Due to this challenge's emphasis on real-world and challenging zero-shot out-of-domain MOS prediction in three different voice evaluation scenarios, we specifically designed a two-branch module to predict scores and weights for each frame, aiming to achieve better generalization. In the challenge, our system achieved fourth place in Track 1a, second place in Track 1b and first place in Track 2. Additionally, we conducted an ablation study to investigate the effectiveness of our proposed method. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Information Granulation:Mapping-Equivalence Neighborhood Rough Set and Its Attribute Reduction

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 2059-2075页

作者： Changshun Liu Yan Liu Jingjing Song Taihua Xu School of Computer Jiangsu University of Science and TechnologyZhenjiang212100China Key Laboratory of Oceanographic Big Data Mining&Application of Zhejiang Province Zhejiang Ocean UniversityZhoushan316022China

Attribute reduction,as one of the essential applications of the rough set,has attracted extensive attention from *** granulation is a key step of attribute reduction,and its efficiency has a significant impact on the overall efficiency of attribute *** information granulation of the existing neighborhood rough set models is usually a single layer,and the construction of each information granule needs to search all the samples in the universe,which is *** fill such gap,a new neighborhood rough set model is proposed,which aims to improve the efficiency of attribute reduction by means of two-layer information *** first layer of information granulation constructs a mapping-equivalence relation that divides the universe into multiple mutually independent mapping-equivalence *** second layer of information granulation views each mapping-equivalence class as a sub-universe and then performs neighborhood informa-tion granulation.A model named mapping-equivalence neighborhood rough set model is derived from the strategy of two-layer information *** results show that compared with other neighborhood rough set models,this model can effectively improve the efficiency of attribute reduction and reduce the uncertainty of the *** strategy provides a new thinking for the exploration of neighborhood rough set models and the study of attribute reduction acceleration problems.

关键词： Attribute reduction information granulation mapping-equiva-lence relation neighborhood rough set

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：