检索结果-南通市图书馆

在线全文

学校读者我要写书评

暂无评论

大模型及其在材料科学中的应用与展望

工程科学学报 2024年第2期46卷 290-305页

作者：李长泰韩旭蒋若辉贠培文胡鹏飞班晓娟北京科技大学北京材料基因工程高精尖创新中心北京100083 北京科技大学智能科学与技术学院北京100083 北京科技大学新材料技术研究院材料先进制备技术教育部重点实验室北京100083 北京科技大学新材料技术研究院现代交通金属材料与加工技术北京实验室北京100083 北京科技大学新材料技术研究院北京100083 北京科技大学智能仿生无人系统教育部重点实验室北京100083 辽宁材料实验室材料智能技术研究所沈阳110004

以大模型在材料科学中的应用为着眼点,首先综述了大模型,介绍了大模型的基本概念、发展过程、技术分类与特点等内容;其次从通用领域大模型和垂直领域大模型两个角度,总结了大模型的应用,列举分析了不同种类大模型的应用场景和功能.再次... 详细信息

以大模型在材料科学中的应用为着眼点,首先综述了大模型,介绍了大模型的基本概念、发展过程、技术分类与特点等内容;其次从通用领域大模型和垂直领域大模型两个角度,总结了大模型的应用,列举分析了不同种类大模型的应用场景和功能.再次,结合材料科学领域中的具体需求研究现状,调研并综述了语言大模型、视觉大模型和多模态大模型在材料科学中的应用情况,以自然语言处理和计算机视觉中的具体任务为切入,参考典型应用案例,综合提示工程策略和零样本知识迁移学习,厘清了当前将大模型应用至材料科学的研究范式和制约因素,并利用改进SAM视觉大模型在四种材料显微图像数据上进行了验证性图像分割与关键结构提取实验,结果表明SAM带来的零样本分割能力对于材料微结构的精准高效表征具有巨大应用潜力.最后,提出了大模型相关技术、方法在材料科学中的未来研究机遇,从单模态到综合性多模态的大模型研发与调优,评估了可行性及技术难点.

关键词：大模型深度学习 ChatGPT SAM 材料科学多模态

Continuous-Time Prediction of Industrial Paste Thickener System With Differential ODE-Net

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 686-698页

作者： Zhaolin Yuan Xiaorui Li Di Wu xiaojuan ban Nai-Qi Wu Hong-Ning Dai Hao Wang the Beijing Advanced Innovation Center for Materials Genome Engineering Institute of Artificial IntelligenceBeijing Key Laboratory of Knowledge Engineering for Materials ScienceSchool of Computer and Communication EngineeringUniversity of Science and Technology Beijing the Department of ICT and Natural Science Norwegian University of Science and Technology IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and Technology the Department of Computing and Decision Sciences Lingnan University the Department of Computer Science Norwegian University of Science and Technology

It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the *** proliferation of industrial sensors and the availability of thickening-system data make this ***,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive *** address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening *** a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental *** results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system *** proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.

关键词： Industrial 24 paste thickener ordinary differential equation(ODE)-net recurrent neural network time series prediction

Interaction model of artificial fish in virtual environment

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2008年第5期19卷 982-987页

作者： Meng Xiangsong ban xiaojuan Yin Yixin Univ. of Science and Technology Beijing Beijing 100083 P. R. China

Conventional artificial fish has some shortages on the interaction with environment, other fish, and the animator. This article proposes a multi-tier interaction control model of artificial fish, realizes the interaction model through integration of virtual reality technology and Markov sequence, and provides a virtual marine world to describe the interaction between artificial fish and the virtual environment and the interaction between the artificial fish and the animator. Simulation results show that the interaction model owns not only the basic characteristics of virtual biology, but also has high trueness interaction function.

关键词： artificial life artificial fish interaction model Markov sequence.

An effective method for grasp planning on objects with complex geometry combining human experience and analytical approach

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2016年第11期59卷 170-181页

作者： Chunfang LIU Fuchun SUN xiaojuan ban Department of Computer Science and Technology Tsinghua University Department of Computer Science and Technology University of Science and Technology Beijing

In this paper, an effective method for identifying the graspable components of objects with complex geometry is proposed for grasp planning based on human experience. Instead of focusing on individual objects,our method identifies graspable components on the category level under the assumption that geometrically alike objects share similar graspable components. Firstly, employing a modified SHOT descriptor, a fast KNN-based method is developed for object categorization. Then, the graspable components are identified by adopting a learning framework based on human experience. Afterwards, a fast analytical grasp planning method is proposed which comprises of contact points exaction and hand kinematics calculation. Finally, a regression model based on the extreme learning method(ELM) is built which inputs the desired contact points and the wrist orientation and outputs the wrist position. This approach is time-saving comparing with the optimization method. The simulations and experiments demonstrate the effectiveness of the proposed approach by realizing grasps on the graspable components of human choice for objects with complex geometry.

关键词： grasp planning human experience analytical method kinematics learning ELM

Fatigue driving detection based on Haar feature and extreme learning machine

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2016年第4期23卷 91-100页

作者： Chang Zheng ban xiaojuan Wang Yu School of Computer and Communication Engineering University of Science and Technology Beijing

As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle driver and avoid the traffic accident. The disadvantages of the traditional fatigue driving detection method have been pointed out when we study on the traditional eye tracking technology and traditional artificial neural networks. On the basis of the image topological analysis technology, Haar like features and extreme learning machine algorithm, a new detection method of the intelligent fatigue driving has been proposed in the paper. Besides, the detailed algorithm and realization scheme of the intelligent fatigue driving detection have been put forward as well. Finally, by comparing the results of the simulation experiments, the new method has been verified to have a better robustness, efficiency and accuracy in monitoring and tracking the drivers＇ fatigue driving by using the human eye tracking technology.

关键词： Haar feature extreme learning machine fatigue driving detection

Compression method based on training dataset of SVM

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2008年第1期19卷 198-201页

作者： ban xiaojuan Shen Qilong Chen Hao Tu Xuyan School of Information Engineering University of Science & Technology Beijing Beijing 100083 P. R. China Beijing Institute of Radio Metrology & Measurements Beijing 100854 P. R. China

The method to compress the training dataset of Support Vector Machine （SVM） based on the character of the Support Vector Machine is proposed. First, the distance between the unit in two training datasets, and then the samples that keep away from hyper-plane are discarded in order to compress the training dataset. The time spent in training SVM with the training dataset compressed by the method is shortened obviously. The result of the experiment shows that the algorithm is effective.

关键词： statistical learning theory support vector machine compression method classification

Novel method for the evaluation of data quality based on fuzzy control

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2008年第3期19卷 606-610页

作者： ban xiaojuan Ning Shurong Xu Zhaolin Cheng Peng School of Information Engineering Univ. of Science & Technology Beijing Beijing 100083 P. R. China Beijing Inst. of Electronic System Engineering Beijing 100854 P. R. China

One of the goals of data collection is preparing for decision-making, so high quality requirement must be satisfied. Rational evaluation of data quality is an effective way to identify data problem in time, and the quality of data after this evaluation is satisfactory with the requirement of decision maker. A fuzzy neural network based research method of data quality evaluation is proposed. First, the criteria for the evaluation of data quality are selected to construct the fuzzy sets of evaluating grades, and then by using the learning ability of NN, the objective evaluation of membership is carried out, which can be used for the effective evaluation of data quality. This research has been used in the platform of ＇data report of national compulsory education outlay guarantee＇ from the Chinese Ministry of Education. This method can be used for the effective evaluation of data quality worldwide, and the data quality situation can be found out more completely, objectively, and in better time by using the method.

关键词： data quality evaluation system fuzzy control theory neural network.

Multiple feature fusion for unimodal emotion recognition

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2019年第2期26卷 17-29页

作者： Yang Lingzhi ban xiaojuan Michele Mukeshimana Chen Zhe School of Computer and Communication Engineering Beijing Key Laboratory of Knowledge Engineering for Materials ScienceUniversity of Science and Technology BeijingBeijing 10083China Citic Pacific Special Steel Holdings Qingdao Special Iron and Steel Company Limited Faculity of Engineering Sciences University of BurundiBujumbura P.0.Box 1550 BujumburaBurundi Qingdao Hisense Group Company Limited Qingdao 266000China

A new semi-serial fusion method of multiple feature based on learning using privileged information(LUPI) model was put *** exploitation of LUPI paradigm permits the improvement of the learning accuracy and its stability,by additional information and computations using optimization *** execution time is also reduced,by sparsity and dimension of testing *** essence of improvements obtained using multiple features types for the emotion recognition(speech expression recognition),is particularly applicable when there is only one modality but still need to improve the *** results show that the LUPI in unimodal case is effective when the size of the feature is *** comparison to other methods using one type of features or combining them in a concatenated way,this new method outperforms others in recognition accuracy,execution reduction,and stability.

关键词： multiple feature LUPI emotion recognition semi-serial fusion method

Fast and Stable Surface Feature Simulation for Particle-Based Fluids

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2019年第1期28卷 57-66页

作者： Xiaokun Wang Yanrui Xu xiaojuan ban Pengfei Ye School of Computer and Communication Engineering University of Science and Technology Beijing Beijing Key Laboratory of Knowledge Engineering for Materials Science

In order to efficiently and realistically capture microscopic features of fluid surface,a fast and stable surface feature simulation approach for particle-based fluids is presented in this *** method employs a steady tension and adhesion model to construct surface features with the consideration of the adsorption effect of fluid to *** cohesion and surface area minimization are appended for surface tension,and adhesion is added to better show the microscopic characteristics of fluid ***,the model is integrated to an implicit incompressible smoothed particle hydrodynamics(SPH)method to improve the efficiency and stability of *** experimental results demonstrate that the method can better simulates surface features in a variety of scenarios stably and efficiently.

关键词： virtual reality 3D visualization fluid simulation surface feature