检索结果-内蒙古大学图书馆

Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Li, Jiatong Liu, Qi Wang, Fei Liu, Jiayu Huang, Zhenya Yao, Fangzhou Zhu, Linbo Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China School of Computer Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners’ cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing cognitive diagnosis models (CDMs) follow the proficiency-response paradigm that views learner traits and question parameters as trainable embeddings and learns them through learner performance prediction. However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners’ cognitive states and the quality of web learning services. To address these problems, we propose an identifiable cognitive diagnosis framework (ID-CDF) based on a novel response-proficiency-response paradigm inspired by encoder-decoder models. Specifically, we first devise the diagnostic module of ID-CDF, which leverages inductive learning to eliminate randomness in optimization to guarantee identifiability and captures the monotonicity between overall response data distribution and cognitive states to prevent explainability overfitting. Next, we propose a flexible predictive module for ID-CDF to ensure diagnosis preciseness. We further present an implementation of ID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments on four real-world datasets with different characteristics demonstrate that ID-CDF can effectively address the problems without loss of diagnosis preciseness. Our code is available at https://***/CSLiJT/ID-CDF. Copyright © 2023, The Authors. All rights reserved.

关键词： HTTP

Microstructure, Mechanism and Performance of Tungsten Coating Electrodeposited in Na2wo4–Wo3–Napo3–Y2o3 Molten Salt

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Xi, Xiaoli Qin, Wenxuan Zhang, Liwen Nie, Zuoren Collaborative Innovation Center of Capital Resource-Recycling Material Technology Beijing University of Technology Beijing100124 China Key Laboratory of Advanced Functional Materials Ministry of Education Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China

In this paper, smooth tungsten coatings with fine grains were prepared by constant direct current electrodeposition in different molten salt. The X–ray diffraction, scanning electron microscopy and laser scanning confocal microscope were used to characterize the microstructure and micromorphology of tungsten coatings. The micromorphology and surface roughness of tungsten coatings are significantly influenced by the cathodic overpotential. The cathodic overpotential can be modified by the addition of NaPO3 and Y2O3 to influence the coating surface quality. When 3.0 mol% Y2O3 was added to the Na2WO4–WO3–NaPO3 molten salt, the coating has the finest average grains size of 9.86 µm. What’s more, with the Y2O3 concentration increasing, the Ra of the coatings decreases. It is noteworthy that the synergistic addition of NaPO3 and Y2O3 results in superior surface quality. The microhardness and thermal shock resistance of the coatings are improved due to grain refinement. The electroreduction mechanism was explored by electrochemical testing and thermodynamic calculations. The results indicated that the electroreduction of tungsten ions is W(VI)→W(IV)→W, and differences in redox potential and overpotential of tungsten ions in different molten salt were observed by electrochemical tests. © 2022, The Authors. All rights reserved.

关键词： Electrodeposition

Bayesian Optimization of Double-SAC Robotic Arm Path Planning Using Recent Prioritized Experience Replay

学校读者我要写书评

暂无评论

Bayesian Optimization of Double-SAC Robotic Arm Path Plannin...

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Shuai Yuan Ke Wen Feng Zhang Jianqiang Xiong School of Computer Science and Engineering Shenyang Jianzhu University Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Branch of National Special Computer Engineering Technology Research Center Shengyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shengyang China

As for the path planning of robotic arms, Deep Reinforcement Learning (DRL) algorithms have recently been developed. However, the high-dimensional action space and state space will result in reward sparsity and low training efficiency of robotic arm path planning. We propose a Bayesian optimization of Double-SAC algorithm using recent priority experience replay to solve these issues. We first propose the sampling method of recent prioritized experience replay (RPER), which combines recent sampling and prioritized experience replay (PER). The interval of experience pool is divided according to the recent sampling method, and sampling is performed according to the sample priority of the interval. Then we adopt a Bayesian optimization method that reduces the variance of the random strategy and improve the quality of the sampled actions. The larger variance is more beneficial for exploring the environment. Smaller variance is advantageous for exploiting good experiences to obtain higher returns. Our approach finds a good balance between exploration and exploitation. We train two Soft Actor Critic (SAC) agents to obtain two independent probability distributions, and a Bayesian optimizer is adopted to combine the two distributions to design a hybrid strategy. The hybrid strategy can output better actions according to the uncertainty estimation of the distribution, and further enhance training efficiency and stability. Finally, simulation tests are performed on the ROS-Gazebo platform, and the simulation results illustrate that the algorithm proposed in this paper converges faster and has a shorter training time than the original algorithm in terms of path planning performance.

关键词：

Characteristics of Pedestrian Dynamics in Narrow Aisles: Empirical Results

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Fu, Zhijian Feng, Yujing Xiong, Xingwen Yang, Yunjia Luo, Lin Li, Jian School of Transportation and Logistics Southwest Jiaotong University PRC Chengdu611756 China National Engineering Laboratory for Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China China Academy of Safety Science and Technology Beijing100012 China

As an essential problem in non-equilibrium physics, the characteristics of pedestrian dynamics in narrow aisles have not been fully uncovered. Thus, in this study, we performed experiments with participants passing through narrow aisles with various widths under open boundaries. There is a transition from lateral to forward movement with the increase of aisle width, and the critical width is 0.30m, the average hip width of Chinese adults. Transforming from the lateral to forward movement, we observed that the deviation angles, step behaviors, and individual speed represent various features. With the aisle width rising from 0.20m to 0.30m, the jam relieves significantly. However, with the aisle width increasing from 0.30m to 0.35m, the flow efficiency improves little. This study contributes empirical results on movement in narrow aisles to pedestrian dynamics and provides basic inputs for pedestrian models and insights into the design of pedestrian facilities. © 2023, The Authors. All rights reserved.

关键词： Efficiency

The Adsorption and Separation of Tungsten and Molybdenum by Chitosan and Chitosan-D301: Experiments and Dft Theoretical Calculation

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Chen, Na Ma, Liwen Xi, Xiaoli Nie, Zuoren Collaborative Innovation Center of Capital Resource-Recycling Material Technology College of Materials Science and Engineering Beijing University of Technology Beijing100124 China Key Laboratory of Advanced Functional Materials Ministry of Education College of Materials Science and Engineering Beijing University of Technology Beijing100124 China National Engineering Laboratory for Industrial Big-data Application Technology College of Materials Science and Engineering Beijing University of Technology Beijing100124 China

The adsorption and separation of tungsten and molybdenum are important for efficient recycling of W-Mo secondary resources. The sustainable development of them requires new green and efficient materials. In this paper, Chitosan (CS)-D301 material was obtained by impregnation method, CS and CS-D301 were applied to the adsorption and separation of W and Mo. The adsorption optimization results indicated that W was adsorbed by CS and CS-D301 adsorbents, the separation factor of W/Mo for CS-D301 increased from 21.34 to 26.45compared to CS. The desorption efficiency was still above 94% after five adsorption-desorption cycles. The adsorption energy of the adsorbent was calculated using density functional theory, which belongs to the chemical adsorption behavior. FT-IR, XPS and DFT theoretical calculations indicated that as the surface group N+-R of CS-D301 showed more affinity for W, making it easier to selectively separate W and Mo than CS. It was also found that N is the surface active adsorption site, and belongs to stable chemical adsorption processes. CS-D301 had stronger interaction with W from the Frontier orbital theory. CS and CS-D301 adsorbents were expected to become green adsorbent materials for efficient separation of W and Mo to support resource protection and sustainable development. © 2024, The Authors. All rights reserved.

关键词： Adsorption

Dft Calculations for Leaching Mechanism of Spent Hds Catalysts with Acidic or Alkaline Leaching Agents

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Ma, Liwen Shi, Tiantian Nie, Zhuanghua Xi, Xiaoli Key Laboratory of Advanced Functional Materials Ministry of Education Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China Collaborative Innovation Center of Capital Resource-Recycling Material Technology Beijing University of Technology Beijing100124 China National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China

The leaching mechanism of the spent hydrodesulfurization (HDS) catalyst was investigated by density functional theory (DFT) calculations and experiments. The ad-molecular (ADM) model of NiO-MoO3/Al2O3 was created to simulate the spent HDS catalyst. The model shows a stable structure with the length of chemical bonds varied greatly and the low symmetry. The adsorption configurations and state densities of different leaching agents on the NiO-MoO3/Al2O3 model were calculated. The results showed that NaOH increased the bond lengths of Mo-O3 and Mo-O4 by 0.062 Å and 0.052 Å;increased the bond lengths of Ni-O4, Ni-O5 and Ni-O6 by 0.092 Å, 0.023 Å and 0.058 Å, respectively. HCl increased the bond length of Mo-O3, Ni-O4 and Ni-O5 by 0.016 Å, 0.043 Å and 0.041 Å, respectively;HNO3 increased the length of Ni-O4 bond by 0.127 Å;H2SO4 increased the bond length of Mo-O1 and Ni-O4 by 0.036 Å and 0.165 Å. The influencing order of agents on Mo leaching was H2SO4>NaOH>HNO3>HCl and H2SO4>NaOH>HNO3≈HCl on Ni leaching according to the bond length increasing value. The leaching experimental results showed that the leaching efficiency of Mo and Ni was almost consistent with the calculated influence order. © 2023, The Authors. All rights reserved.

关键词： Density functional theory

Decomposed Neural Architecture Search for image denoising

学校读者我要写书评

暂无评论

Applied Soft Computing 2022年 124卷

作者： Li, Di Bai, Yunpeng Bai, Zongwen Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an710129 China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY233DB United Kingdom Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an716000 China

In practical applications of deep learning, as the demand for the modeling capability increases, the network size may need to be massively enlarged in response. This may form a significant challenge in practice, especially when facing the dilemma of limited computational resources, making model compression indispensable. It can be time-consuming and interminable to obtain an appropriate network architecture through manual compression. In this paper, we propose an automated method for searching decomposed network architectures, named DNAS (standing for Decomposed Neural Architecture Search). It integrates both tasks of neural architecture search and tensor decomposition based model compression within a unified framework. The method is able to efficiently find a compact network with high performance for image denoising, with respect to memory and runtime. Particularly, using one single V100 GPU, it only takes about 1.5 h to obtain a denoising network on the BSD500 dataset. Experimental results demonstrate that compared with models developed using existing methods, DNAS consumes significantly less inference time and employs much fewer trainable parameters, outperforming existing approaches on both synthetic and real-world denoising datasets. © 2022 Elsevier B.V.

关键词： Network architecture

Understanding the Long-Distance Travel Mobility of Passengers Based on big Railway data: Travel Network and Motif Perspectives

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Xu, Jin Song, Haonan Lu, Zhaoyang Department of Information System & Operation Management School of Economics and Management Southwest Jiaotong University Sichuan Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Sichuan Chengdu China Service Science and Innovation Key Laboratory of Sichuan Province Sichuan Chengdu China

With the booming construction of new railway lines and stations in China, the number of railway passengers is increasing. The large railway population shows certain mobility characteristics that we are interested in clarifying. Based on the theory of complex networks, this paper proposes a novel method to identify travel patterns from big railway data, which associates travel motifs with travel networks. This paper derives some meaningful results from the data analysis of more than three million railway travel records of a city in China. These results illustrate that higher motif complexity leads to a narrower travel radius for motif-based subnets. The higher the stability of the travel sequence is, the shorter the average length of the sequence. Four types of travel patterns are identified and classified by analyzing the motif of travel activities, i.e., labor, tourism, surrounding and commuting. The methodology and findings presented in this paper contribute to a better understanding of the long-distance travel mobility of railway passengers. The method designed in this paper can also be used to analyze traffic data from airlines, buses, subways, etc. © 2022, The Authors. All rights reserved.

关键词： Complex networks

A heterogeneous group CNN for image super-resolution

学校读者我要写书评

暂无评论

arXiv

arXiv 2022年

作者： Tian, Chunwei Zhang, Yanning Zuo, Wangmeng Lin, Chia-Wen Zhang, David Yuan, Yixuan The School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science Northwestern Polytechnical University The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Guangdong Shenzhen518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong

Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image superresolution (SR) under complex scenes. In this paper, we present a heterogeneous group SR CNN (HGSRCNN) via leveraging structure information of different types to obtain a high-quality image. Specifically, each heterogeneous group block (HGB) of HGSRCNN uses a heterogeneous architecture containing a symmetric group convolutional block and a complementary convolutional block in a parallel way to enhance internal and external relations of different channels for facilitating richer low-frequency structure information of different types. To prevent appearance of obtained redundant features, a refinement block with signal enhancements in a serial way is designed to filter useless information. To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN. Besides, a parallel up-sampling mechanism is developed to train a blind SR model. Extensive experiments illustrate that the proposed HGSRCNN has obtained excellent SR performance in terms of both quantitative and qualitative analysis. Codes can be accessed at https://***/hellloxiaotian/HGSRCNN. © 2022, CC BY-NC-SA.

关键词： Convolutional neural networks