1
|
Zhao Y, Si D, Pei J, Yang X. Geodesic Basis Function Neural Network. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:8386-8400. [PMID: 37015442 DOI: 10.1109/tnnls.2022.3227296] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
In the learning of existing radial basis function neural networks-based methods, it is difficult to propagate errors back. This leads to an inconsistency between the learning and recognition task. This article proposes a geodesic basis function neural network with subclass extension learning (GBFNN-ScE). The geodesic basis function (GBF), which is defined here for the first time, uses the geodetic distance in the manifold as a measure to obtain the response of the sample with respect to the local center. To learn network parameters by back-propagating errors for the purpose of correct classification, a specific GBF based on a pruned gamma encoding cosine function is constructed. This function has a concise and explicit expression on the hyperspherical manifold, which is conducive to the realization of error back propagation. In the preprocessing layer, a sample unitization method with no loss of information, nonnegative unit hyperspherical crown (NUHC) mapping, is proposed. The sample can be mapped to the support set of the GBF. To alleviate the problem that one-hot encoding is not effective enough in the differential expression of data labels within a class, a subclass extension (ScE) learning strategy is proposed. The ScE learning strategy can help the learned network be more robust. For the working of GBFNN-ScE, the original sample is projected onto the support set of GBF through the NUHC mapping. Then the mapped samples are sent to the nonlinear computation units composed of GBFs in the hidden layer. Finally, the response obtained in the hidden layer is weighted by the learned weight to obtain the network output. This article theoretically proves that the separability of the data with ScE learning is stronger. The experimental results show that the proposed GBFNN-ScE has a better performance in recognition tasks than existing methods. The ablation experiments show that the ideas of the GBFNN-ScE contribute to the algorithm performance.
Collapse
|
2
|
Huang B, Fong LWR, Chaudhari R, Zhang S. Development and evaluation of a java-based deep neural network method for drug response predictions. Front Artif Intell 2023; 6:1069353. [PMID: 37035534 PMCID: PMC10076891 DOI: 10.3389/frai.2023.1069353] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2022] [Accepted: 03/03/2023] [Indexed: 04/11/2023] Open
Abstract
Accurate prediction of drug response is a crucial step in personalized medicine. Recently, deep learning techniques have been witnessed with significant breakthroughs in a variety of areas including biomedical research and chemogenomic applications. This motivated us to develop a novel deep learning platform to accurately and reliably predict the response of cancer cells to different drug treatments. In the present work, we describe a Java-based implementation of deep neural network method, termed JavaDL, to predict cancer responses to drugs solely based on their chemical features. To this end, we devised a novel cost function and added a regularization term which suppresses overfitting. We also adopted an early stopping strategy to further reduce overfit and improve the accuracy and robustness of our models. To evaluate our method, we compared with several popular machine learning and deep neural network programs and observed that JavaDL either outperformed those methods in model building or obtained comparable predictions. Finally, JavaDL was employed to predict drug responses of several aggressive breast cancer cell lines, and the results showed robust and accurate predictions with r 2 as high as 0.81.
Collapse
|
3
|
Xu K, Fan B, Yang H, Hu L, Shen W. Locally Weighted Principal Component Analysis-Based Multimode Modeling for Complex Distributed Parameter Systems. IEEE TRANSACTIONS ON CYBERNETICS 2022; 52:10504-10514. [PMID: 33735089 DOI: 10.1109/tcyb.2021.3061741] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Global principal component analysis (PCA) has been successfully introduced for modeling distributed parameter systems (DPSs). In spite of the merits, this method is not feasible due to parameter variations and multiple operating domains. A novel multimode spatiotemporal modeling method based on the locally weighted PCA (LW-PCA) method is developed for large-scale highly nonlinear DPSs with parameter variations, by separating the original dataset into tractable subsets. This method implements the decomposition by making full use of the dependence among subset densities. First, the spatiotemporal snapshots are divided into multiple different Gaussian components by using a finite Gaussian mixture model (FGMM). Once the components are derived, a Bayesian inference strategy is then applied to calculate the posterior probabilities of each spatiotemporal snapshot belonging to each component, which will be regarded as the local weights of the LW-PCA method. Second, LW-PCA is adopted to calculate each locally weighted snapshot matrix, and the corresponding local spatial basis functions (SBFs) can be generated by the PCA method. Third, all the local temporal models are estimated using the extreme learning machine (ELM). Thus, the local spatiotemporal models can be produced with local SBFs and corresponding temporal model. Finally, the original system can be approximated using the sum form of each local spatiotemporal model. Unlike global PCA, which uses global SBFs to construct a global spatiotemporal model, LW-PCA approximates the original system by multiple local reduced SBFs. Numerical simulations verify the effectiveness of the developed multimode spatiotemporal model.
Collapse
|
4
|
Tao J, Yu Z, Zhang R, Gao F. RBF neural network modeling approach using PCA based LM–GA optimization for coke furnace system. Appl Soft Comput 2021. [DOI: 10.1016/j.asoc.2021.107691] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/24/2023]
|
5
|
Li P, Lin Z, Shen H, Zhang Z, Mei X. Optimized neural network based sliding mode control for quadrotors with disturbances. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2021; 18:1774-1793. [PMID: 33757210 DOI: 10.3934/mbe.2021092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
In this paper, optimized radial basis function neural networks (RBFNNs) are employed to construct a sliding mode control (SMC) strategy for quadrotors with unknown disturbances. At first, the dynamics model of the controlled quadrotor is built, where some unknown external disturbances are considered explicitly. Then SMC is carried out for the position and the attitude control of the quadrotor. However, there are unknown disturbances in the obtained controllers, so RBFNNs are employed to approximate the unknown parts of the controllers. Furtherly, Particle Swarm optimization algorithm (PSO) based on minimizing the absolute approximation errors is used to improve the performance of the controllers. Besides, the convergence of the state tracking errors of the quadrotor is proved. In order to exposit the superiority of the proposed control strategy, some comparisons are made between the RBFNN based SMC with and without PSO. The results show that the strategy with PSO achieves quicker and smoother trajectory tracking, which verifies the effectiveness of the proposed control strategy.
Collapse
Affiliation(s)
- Ping Li
- College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
| | - Zhe Lin
- College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
| | - Hong Shen
- College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
| | - Zhaoqi Zhang
- College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
| | - Xiaohua Mei
- College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
| |
Collapse
|
6
|
Yang F, Li X, Bai J, Zhang R, Gao F. Nonlinear Process Quality Prediction Using Wavelet Denoising OSC-SVM-PLS. Ind Eng Chem Res 2020. [DOI: 10.1021/acs.iecr.0c00224] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Fan Yang
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Xiang Li
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Jianjun Bai
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Ridong Zhang
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
- Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong
| | - Furong Gao
- Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong
| |
Collapse
|
7
|
Yu Q, Hou Z, Bu X, Yu Q. RBFNN-Based Data-Driven Predictive Iterative Learning Control for Nonaffine Nonlinear Systems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020; 31:1170-1182. [PMID: 31251197 DOI: 10.1109/tnnls.2019.2919441] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
In this paper, a novel data-driven predictive iterative learning control (DDPILC) scheme based on a radial basis function neural network (RBFNN) is proposed for a class of repeatable nonaffine nonlinear discrete-time systems subjected to nonrepetitive external disturbances. First, by utilizing the dynamic linearization technique (DLT) with a newly introduced and unknown system parameter pseudopartial derivative (PPD) and designing a new RBFNN estimation algorithm along the iterative learning axis for addressing the unknown PPD and the unknown nonrepetitive external disturbances, a data-driven prediction model is established. It is theoretically shown that by constructing a composite energy function (CEF) with respect to the modeling error for the first time, the convergence of the modeling error via the proposed DLT-based RBFNN modeling method can be guaranteed, and the convergence speed is tunable. Then, a DDPILC with a disturbance compensation term is designed, and the convergence of the tracking control error is analyzed. Finally, simulations of a train operation system reveal that even if the train suffers from randomly varying load disturbances and nonlinear running resistance, the proposed scheme can make both the modeling error and the tracking control error decrease successively with increasing operation number.
Collapse
|
8
|
Wang X, Jin Y, Hao K. Evolving Local Plasticity Rules for Synergistic Learning in Echo State Networks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020; 31:1363-1374. [PMID: 31247578 DOI: 10.1109/tnnls.2019.2919903] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Existing synaptic plasticity rules for optimizing the connections between neurons within the reservoir of echo state networks (ESNs) remain to be global in that the same type of plasticity rule with the same parameters is applied to all neurons. However, this is biologically implausible and practically inflexible for learning the structures in the input signals, thereby limiting the learning performance of ESNs. In this paper, we propose to use local plasticity rules that allow different neurons to use different types of plasticity rules and different parameters, which are achieved by optimizing the parameters of the local plasticity rules using the evolution strategy (ES) with covariance matrix adaptation (CMA-ES). We show that evolving neural plasticity will result in a synergistic learning of different plasticity rules, which plays an important role in improving the learning performance. Meanwhile, we show that the local plasticity rules can effectively alleviate synaptic interferences in learning the structure in sensory inputs. The proposed local plasticity rules are compared with a number of the state-of-the-art ESN models and the canonical ESN using a global plasticity rule on a set of widely used prediction and classification benchmark problems to demonstrate its competitive learning performance.
Collapse
|
9
|
Feng CM, Xu Y, Liu JX, Gao YL, Zheng CH. Supervised Discriminative Sparse PCA for Com-Characteristic Gene Selection and Tumor Classification on Multiview Biological Data. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:2926-2937. [PMID: 30802874 DOI: 10.1109/tnnls.2019.2893190] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Principal component analysis (PCA) has been used to study the pathogenesis of diseases. To enhance the interpretability of classical PCA, various improved PCA methods have been proposed to date. Among these, a typical method is the so-called sparse PCA, which focuses on seeking sparse loadings. However, the performance of these methods is still far from satisfactory due to their limitation of using unsupervised learning methods; moreover, the class ambiguity within the sample is high. To overcome this problem, this paper developed a new PCA method, which is named the supervised discriminative sparse PCA (SDSPCA). The main innovation of this method is the incorporation of discriminative information and sparsity into the PCA model. Specifically, in contrast to the traditional sparse PCA, which imposes sparsity on the loadings, here, sparse components are obtained to represent the data. Furthermore, via the linear transformation, the sparse components approximate the given label information. On the one hand, sparse components improve interpretability over the traditional PCA, while on the other hand, they are have discriminative abilities suitable for classification purposes. A simple algorithm is developed, and its convergence proof is provided. SDSPCA has been applied to the common-characteristic gene selection and tumor classification on multiview biological data. The sparsity and classification performance of SDSPCA are empirically verified via abundant, reasonable, and effective experiments, and the obtained results demonstrate that SDSPCA outperforms other state-of-the-art methods.
Collapse
|
10
|
Zhao Y, Pei J, Chen H. Multi-layer radial basis function neural network based on multi-scale kernel learning. Appl Soft Comput 2019. [DOI: 10.1016/j.asoc.2019.105541] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|
11
|
Guo B, Zheng Q. Using Naïve Bayes Algorithm to Estimate the Response to Drug in Lung Cancer Patients. Comb Chem High Throughput Screen 2019; 21:734-748. [PMID: 30686250 DOI: 10.2174/1386207322666190125151624] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2018] [Revised: 09/11/2018] [Accepted: 11/02/2018] [Indexed: 11/22/2022]
Abstract
AIM AND OBJECTIVE Lung cancer is a highly heterogeneous cancer, due to the significant differences in molecular levels, resulting in different clinical manifestations of lung cancer patients there is a big difference. Including disease characterization, drug response, the risk of recurrence, survival, etc. Method Clinical patients with lung cancer do not have yet particularly effective treatment options, while patients with lung cancer resistance not only delayed the treatment cycle but also caused strong side effects. Therefore, if we can sum up the abnormalities of functional level from the molecular level, we can scientifically and effectively evaluate the patients' sensitivity to treatment and make the personalized treatment strategies to avoid the side effects caused by over-treatment and improve the prognosis. RESULT & CONCLUSION According to the different sensitivities of lung cancer patients to drug response, this study screened out genes that were significantly associated with drug resistance. The bayes model was used to assess patient resistance.
Collapse
Affiliation(s)
- Baoling Guo
- Department of Oncology, Longyan First Hospital, Affiliated to Fujian Medical University, Longyan, China
| | - Qiuxiang Zheng
- Department of Oncology, Longyan First Hospital, Affiliated to Fujian Medical University, Longyan, China
| |
Collapse
|
12
|
Wang S, Wang Z, Hu Y. Optimal control research on a manipulator’s combined feedback device by the variational method genetic algorithm radial basis function method. INT J ADV ROBOT SYST 2019. [DOI: 10.1177/1729881419855824] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
This article aims to improve the accuracy of each joint in a manipulator and to ensure the high-speed and real-time requirements. A method called the variational method genetic algorithm radial basis function, which is based on a combination feedback controller, is proposed to solve the optimal control problem. It is proposed a combined feedback with a linear part and a nonlinear part. We reconstruct the manipulator’s kinematics and dynamics models with a feedback control. In this model, the optimal trajectory, which was solved by the variation method, is regarded as the desired output. The other one is also established an improved genetic algorithm radial basis function neural network model. The optimal trajectory is rapidly solved by using the desired output and the improved genetic algorithm radial basis function neural network. This method can greatly improve the speed of the calculation and guarantee real-time performance while simultaneously ensuring accuracy.
Collapse
Affiliation(s)
- Song Wang
- College of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| | - Zhaoyang Wang
- College of Automation, Beijing Institute of Technology, Beijing, China
| | - Yanzhu Hu
- College of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| |
Collapse
|
13
|
Li X, Wu F, Zhang R, Gao F. Nonlinear Multivariate Quality Prediction Based on OSC-SVM-PLS. Ind Eng Chem Res 2019. [DOI: 10.1021/acs.iecr.8b06079] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Xiang Li
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Feng Wu
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Ridong Zhang
- The Belt and Road Information Research Institute, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
- Department of Chemical and Biomolecular Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong
| | - Furong Gao
- Department of Chemical and Biomolecular Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong
| |
Collapse
|
14
|
Hu X, Wang L, Gao F. Genetic-Algorithm-Optimization-Based Infinite Horizon Linear Quadratic Control for Injection Molding Batch Processes with Uncertainty. Ind Eng Chem Res 2018. [DOI: 10.1021/acs.iecr.8b04921] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Xiaomin Hu
- School of Science, Hangzhou Dianzi University, Hangzhou 310018, P. R. China
| | - Limin Wang
- School of Mathematics and Statistics, Hainan Normal University, Haikou 571158, P. R. China
| | - Furong Gao
- Department of Chemical and Biomolecular Engineering, Hong Kong University of Science and Technology, Kowloon 300071, Hong Kong
| |
Collapse
|
15
|
Zhang R, Lv Q, Tao J, Gao F. Data Driven Modeling Using an Optimal Principle Component Analysis Based Neural Network and Its Application to a Nonlinear Coke Furnace. Ind Eng Chem Res 2018. [DOI: 10.1021/acs.iecr.8b00071] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Ridong Zhang
- The Belt and Road Information Research Institute, Automation College, Hangzhou Dianzi University, Hangzhou, 310018, P.R. China
| | - Qiang Lv
- The Belt and Road Information Research Institute, Automation College, Hangzhou Dianzi University, Hangzhou, 310018, P.R. China
| | - Jili Tao
- Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, P.R. China
| | - Furong Gao
- Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, P.R. China
| |
Collapse
|