Your search for: 'author:("Li, Juan")' has returned 22 results. (0.036s) Save search

Authors: Li, You | Li, Juan

Article Type: Research Article

Abstract: Interactive animation based on motion capture is a relatively new animation technique that implements the action of transforming an actor’s actions into a model within the computer in real time. To solve this problem, a visualized interactive computer vision system was developed. A brief introduction to the design of the entire system and some important technologies, focusing on the principles of node-based visual programming, the integration of functional modules, and the plug-in architecture of the system. The experimental results show that the process is simple, fast and real-time, especially in the field of entertainment and education.

Keywords: Computer vision, interactive animation, motion capture, image processing

DOI: 10.3233/JCM-191007

Citation: Journal of Computational Methods in Sciences and Engineering, vol. 19, no. S1, pp. 47-53, 2019

Authors: Li, Juan | Li, You

Article Type: Research Article

Abstract: Aiming at the shortcomings of computer-aided innovative design software at home and abroad in problem analysis tools, innovative solution strategies and knowledge bases, combined with the characteristics of product innovation design and technology innovation implementation methodology, a model of computer-aided innovation design platform is proposed. As a computer-aided tool, the platform can assist designers in innovative design and open up the designer’s thinking space in the process of problem analysis, strategic solution, knowledge data support and program management evaluation. The platform improves the problem of insufficient system reasoning ability by genetic algorithm optimization combination and expounds the platform’s major modules, …design knowledge base, physical structure, function principle and function, and illustrates the system operation process by example. Its integrity and feasibility were verified. Show more

Keywords: Product innovation, computer, auxiliary system, system structure

DOI: 10.3233/JCM-191006

Citation: Journal of Computational Methods in Sciences and Engineering, vol. 19, no. S1, pp. 41-46, 2019

Authors: Tay, Francis Eng Hock | Cao, Li Juan

Article Type: Research Article

Abstract: Recently, support vector machine (SVM) has been receiving increasing attention in the field of regression estimation due to its remarkable characteristics such as good generalization performance, the absence of local minima and sparse representation of the solution. However, within the SVMs framework, there are very few established approaches for identifying important features. Selecting significant features from all candidate features is the first step in regression estimation, and this procedure can improve the network performance, reduce the network complexity, and speed up the training of the network. This paper investigates the use of saliency analysis (SA) and genetic algorithm (GA) in …SVMs for selecting important features in the context of regression estimation. The SA measures the importance of features by evaluating the sensitivity of the network output with respect to the feature input. The derivation of the sensitivity of the network output to the feature input in terms of the partial derivative in SVMs is presented, and a systematic approach to remove irrelevant features based on the sensitivity is developed. GA is an efficient search method based on the mechanics of natural selection and population genetics. A simple GA is used where all features are mapped into binary chromosomes with a bit “1” representing the inclusion of the feature and a bit of “0” representing the absence of the feature. The performances of SA and GA are tested using two simulated non-linear time series and five real financial time series. The experiments show that with the simulated data, GA and SA detect the same true feature set from the redundant feature set, and the method of SA is also insensitive to the kernel function selection. With the real financial data, GA and SA select different subsets of features. Both selected feature sets achieve higher generation performance in SVMs than that of the full feature set. In addition, the generation performance between the selected feature sets of GA and SA is similar. All the results demonstrate that that both SA and GA are effective in SVMs for identifying important features. Show more

Keywords: feature selection, support vector machines, structural risk minimization principle, saliency analysis, genetic algorithm

DOI: 10.3233/IDA-2001-5302

Citation: Intelligent Data Analysis, vol. 5, no. 3, pp. 191-209, 2001

Authors: Tay, Francis Eng Hock | Cao, Li Juan

Article Type: Research Article

Abstract: A two-stage neural network architecture constructed by combining Support Vector Machines (SVMs) with self-organizing feature map (SOM) is proposed for financial time series forecasting. In the first stage, SOM is used as a clustering algorithm to partition the whole input space into several disjoint regions. A tree-structured architecture is adopted in the partition to avoid the problem of predetermining the number of partitioned regions. Then, in the second stage, multiple SVMs, also called SVM experts, that best fit each partitioned region are constructed by finding the most appropriate kernel function and the optimal learning parameters of SVMs. The Santa Fe …exchange rate and five real futures contracts are used in the experiment. It is shown that the proposed method achieves both significantly higher prediction performance and faster convergence speed in comparison with a single SVM model. Show more

Keywords: financial time series forecasting, non-stationarity, support vector machines, self-organizing feature map

DOI: 10.3233/IDA-2001-5405

Citation: Intelligent Data Analysis, vol. 5, no. 4, pp. 339-354, 2001

Authors: Li, Juan | Shao, Yabin | Qi, Xiaoding

Article Type: Research Article

Abstract:  With respect to multiple attribute group decision making problems in which the attribute weights and the expert weights take the form of real numbers and the attribute values take the form of interval-valued uncertain linguistic variable. In this paper, we introduce the idea of variable precision into the incomplete interval-valued fuzzy information system and propose the theory of variable precision rough sets over incomplete interval-valued fuzzy information systems. Then, we give the properties of rough approximation operators and study the knowledge discovery and attribute reduction in the incomplete interval-valued fuzzy information system under the condition that a certain degree of …misclassification rate is allowed to exist. Furthermore, a decision rule and decision model are given. Finally, an illustrative example is given and compared with the existing methods, the practicability and effectiveness of this method are further verified. Show more

Keywords: Interval-valued fuzzy set, incomplete information systems, variable precision interval-valued rough fuzzy set, attribute reduction, decision rules

DOI: 10.3233/JIFS-192161

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 1, pp. 463-475, 2021

Authors: Agordzo, George K. | Fang, Xianwen | Li, Juan

Article Type: Research Article

Abstract: In today’s digital age, log files are crucial. However, the conversion of text log files into images has only recently been developed. The security of log files is a major source of concern, and the security of the systems in which the logs are stored determines the safety of the log file in process mining. This calls for the first conversion of a text log file into an image file. Thus, this research aims to convert the log files into images in a mugshot database and detect illegal activity and criminals from the converted images employing a novel Convolutional Neural …Network (CNN). The developed model has three stages: pre-processing, feature extraction, and detection and matching. The pre-processing was performed by min-max normalization, and in feature extraction, the deep learning method was used. Moreover, in the detection phase, CNN is employed for detecting illegal activities, and the matching process is performed for detecting illegal activities from converted images and criminals in the mugshot database. The model’s performance is evaluated in terms of precision, F1-score, recall, and accuracy values of 99.6%, 98.5%, 98.7%, and 99.8%, respectively. A further comparison has been performed to show the effectiveness of the suggested model over other methods. Show more

Keywords: Privacy, log file, convolutional neural network, process mining, machine learning algorithm

DOI: 10.3233/JIFS-224486

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 1, pp. 1-12, 2023

Authors: Zhou, Jian | Liu, Lin-Feng | Sun, Li-Juan | Xiao, Fu

Article Type: Research Article

Abstract:  The hesitant fuzzy linguistic term set (HFLTS) is usually used in the uncertain decision situation. In order to solve the problem of multi-criteria decision-making (MCDM) with HFLTS, a new MCDM method based on the cloud model and evidence theory is proposed in this paper. A new envelope, whose representation is a synthetic cloud generated by the multiple linguistic term in the HFLTS, is presented for HFLTS to facilitate the computing processes and take both the randomness and fuzziness of linguistic variables into consideration. As to overcome the drawbacks of tradition aggregation operator, the criteria values in the form of the …belief degrees are obtained from the synthetic clouds and aggregated using the evidential reasoning algorithm. An illustrative example, which is given to confirm the feasibility and validity, also shows that with the proposed method more reasonable and accurate ranking results can be obtained. Moreover, the belief degree of each linguistic term as well as the hesitant degree of the assessment can be obtained simultaneously. Show more

Keywords: Hesitant fuzzy linguistic term set, multi-criteria decision-making, cloud model, evidence theory, uncertainty

DOI: 10.3233/JIFS-18051

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1797-1808, 2019

Authors: Liu, Rui-Lin | Yang, Hai-Long | Zhang, Li-Juan

Article Type: Research Article

Abstract: This paper studies information structures in a fuzzy β -covering information system. We introduce the concepts of a fuzzy β -covering information system and homomorphism between them, and investigate related properties. The concept of information structure of a fuzzy β -covering information system is given. We discuss the relationships between information structures from the view of dependence and separation. Then granularity measures for a fuzzy β -covering information system are studied. Finally, we discuss invariance of fuzzy β -covering information systems under homomorphism and illustrate its application on data compression.

Keywords: Fuzzy β-covering, fuzzy β-covering information system, information structure, homomorphism, invariance property

DOI: 10.3233/JIFS-202824

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 6, pp. 11691-11716, 2021

Authors: Li, Shengquan | Zhu, Chaowei | Li, Juan | Mao, Qibo

Article Type: Research Article

Abstract: Considering the internal and external disturbances in actual engineering structure, a composite active vibration control method is proposed for an all-clamped piezoelectric panel. First, the theoretical modal analysis and laser vibrometer are employed to obtain the natural frequency and mode shape of the panel, for reasonable arrangement of actuator and accelerometer. Second, a nonlinear extended state observer is introduced to estimate the total disturbances, i.e., modeling uncertainties, high-order harmonics, coupling and external excitations. Third, the estimated value is used to compensate and attenuate the influence of the total disturbances in real time. In addition, the feedback controller based on the …proportional differential and acceleration feedback method is designed to enhance the vibration suppression performance of the whole system. Finally, a semi-physical platform is built in MATLAB/Simulink real-time environment with the NI-PCIe6343 acquisition card to verify the effectiveness and superiority of the proposed method. Show more

Keywords: Piezoelectric actuator, all-clamped panel, nonlinear extended state observer, active disturbance rejection control, acceleration feedback

DOI: 10.3233/JAE-209346

Citation: International Journal of Applied Electromagnetics and Mechanics, vol. 64, no. 1-4, pp. 403-411, 2020

Authors: Tian, Shasha | Li, Yuanxiang | Li, Juan | Liu, Guifeng

Article Type: Research Article

Abstract: To overcome the disadvantages of low optimization accuracy and prematurity of the canonical PSO algorithm, we proposed an improved particle swarm optimization based on the interaction mechanism between leaders and individuals (PSO-IBLI), and used it to implement robot global path planning. In the PSO-IBLI algorithm, in different stages, each particle learns from the elites according to different regular. Moreover, the improved algorithm divides the execution state into two categories, where the parameters and the evaluation mechanisms are varied accordingly. In this way, the global best particles no longer walk randomly and have more learning objects. At the same time, other …particles learn from not only the global best position, their historical best positions, but also the other elites. The learning strategy makes the search mode always in the adaptive adjustment, and it improves the speed of convergence and promotes this algorithm to find a more precise solution. The experimental results suggest that the precision and convergence speed of the PSO-IBLI algorithm is higher than the other three different algorithms. Additionally, some experiments are carried out to plan the robot’s entire collision-free path using the PSO-IBLI algorithm and the other three algorithms. The results show that the PSO-IBLI algorithm can obtain the shortest collision-free way in four algorithms. Show more

Keywords: Particle swarm optimization, robot global path planning, optimization accuracy, interaction mechanism, learning object

DOI: 10.3233/JIFS-179978

Citation: Journal of Intelligent & Fuzzy Systems, vol. 39, no. 4, pp. 4925-4933, 2020