Yazar "Wang, Zheng" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Design of progressive fuzzy polynomial neural networks through gated recurrent unit structure and correlation/probabilistic selection strategies
    (Elsevier, 2023) Wang, Zhen; Oh, Sung-Kwun; Wang, Zheng; Fu, Zunwei; Pedrycz, Witold; Yoon, Jin Hee
    This study focuses on two critical design aspects of a progressive fuzzy polynomial neural network (PFPNN): the influence of the gated recurrent unit (GRU) structure and the implementation of fitness-based candidate neuron selection (FCNS) through two probabilistic strategies. The primary objectives are to enhance modeling accuracy and to reduce the computational load associated with nonlinear regression tasks. Compared with the existing fuzzy rule-based modeling architecture, the proposed dynamic model consists of the GRU structure and the hybrid fuzzy polynomial architecture. In the initial two layers of the PFPNN, we introduce three types of polynomial and fuzzy rules into the GRU neurons (GNs) and fuzzy polynomial neurons (FPNs), which can effectively reveal potential complex relationships in the data space. The synergy of the FCNS strategies and the l2 regularization learning method is to design a progressive regression model adept at melding the GRU structure with a self-organizing architecture. The proposed GRU structure and polynomial-based neurons significantly improve the modeling accuracy for time-series datasets. The rational utilization of FCNS strategies can reinforce the network structure and discover the potential performance of neurons of the network. Furthermore, the inclusion of l2 norm regularization provides additional stability to the proposed model and mitigates the overfitting issue commonly encountered in many existing learning methods. We validated the proposed neural networks using six time-series, four machine learning, and two real-world datasets. The PFPNN outperformed other models in the comparison studies in 83.3% of the datasets, emphasizing its superiority in terms of developing a stable deep structure from diverse candidate neurons and reducing computational overhead. (c) 2023 Elsevier B.V. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Design of Tobacco Leaves Classifier Through Fuzzy Clustering-Based Neural Networks With Multiple Histogram Analyses of Images
    (Ieee-Inst Electrical Electronics Engineers Inc, 2024) Kim, Eun-Hu; Wang, Zheng; Zong, Hao; Jiang, Ziwu; Fu, Zunwei; Pedrycz, Witold
    This article is concerned with designing a tobacco leaves classifier through fuzzy clustering-based neural networks, which leverage multiple histogram analyses of images. The key issue of the study is to recognize high-quality and low-quality tobacco leaves only by using color images obtained from real industrial areas. This study applies multiple histogram analyses from different color spaces as image preprocessing to extract the meaningful features from high-resolution images. Dimensionality reduction is performed through principal component analysis to extract essential features to reduce model complexity and alleviate overfitting problems. In a classifier, we apply fuzzy clustering-based neural networks that incorporate fuzzy clustering techniques, especially fuzzy C-means clustering, along with a cross-entropy loss function and its learning mechanism. The process of setting and training the membership function of node in the hidden layer is substituted with fuzzy C-means clustering. Also, Softmax function produces the model's output in terms of class probabilities. The cost function of the networks is determined using the cross-entropy loss function, while the learning process involves Newton's method-based iterative nonlinear least square error estimation. The experiment validates the competitiveness of the proposed design methodology using real tobacco images obtained from the industry. The performance of the proposed classifier is compared against other classifiers previously reported in the literature to demonstrate its effectiveness.
  • Küçük Resim Yok
    Öğe
    A study on hand gesture recognition algorithm realized with the aid of efficient feature extraction method and convolution neural networks: design and its application to VR environment
    (Springer, 2023) Wang, Zhen; Yoo, Sung-Hoon; Oh, Sung-Kwun; Kim, Eun-Hu; Wang, Zheng; Fu, Zunwei; Jiang, Yuepeng
    Humans maintain and develop interrelationships through various forms of communication, including verbal and nonverbal communications. Gestures, which constitute one of the most significant forms of nonverbal communication, convey meaning through diverse forms and movements across cultures. In recent decades, research efforts aimed at providing more natural, human-centered means of interacting with computers have garnered increasing interest. Technological advancements in real-time, vision-based hand motion recognition have become progressively suitable for human-computer interaction, aided by computer vision and pattern recognition techniques. Consequently, we propose an effective system for recognizing hand gestures using time-of-flight (ToF) cameras. The hand gesture recognition system outlined in the proposed method incorporates hand shape analysis, as well as robust fingertip and palm center detection. Furthermore, depth sensors, such as ToF cameras, enhance finger detection and hand gesture recognition performance, even in dark or complex backgrounds. Hand shape recognition is performed by comparing newly recognized hand gestures with pre-trained models using a YOLO algorithm-based convolutional neural network. The proposed hand gesture recognition system is implemented in real-world virtual reality applications, and its performance is evaluated based on detection performance and recognition rate outputs. Two distinct gesture recognition datasets, each emphasizing different aspects, were employed. The analysis of results and associated parameters was conducted to evaluate the performance and effectiveness. Experimental results demonstrate that the proposed system achieves competitive classification performance compared to conventional machine learning models evaluated on standard evaluation benchmarks.