1. <button id="qm3rj"><thead id="qm3rj"></thead></button>
      <samp id="qm3rj"></samp>
      <source id="qm3rj"><menu id="qm3rj"><pre id="qm3rj"></pre></menu></source>

      <video id="qm3rj"><code id="qm3rj"></code></video>

        1. <tt id="qm3rj"><track id="qm3rj"></track></tt>
            1. 2.765

              2022影響因子

              (CJCR)

              • 中文核心
              • EI
              • 中國科技核心
              • Scopus
              • CSCD
              • 英國科學文摘

              留言板

              尊敬的讀者、作者、審稿人, 關于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復。謝謝您的支持!

              姓名
              郵箱
              手機號碼
              標題
              留言內容
              驗證碼

              基于流形正則化框架和MMD的域自適應BLS模型

              趙慧敏 鄭建杰 郭晨 鄧武

              趙慧敏, 鄭建杰, 郭晨, 鄧武. 基于流形正則化框架和MMD的域自適應BLS模型. 自動化學報, 2021, x(x): 1?14 doi: 10.16383/j.aas.c210009
              引用本文: 趙慧敏, 鄭建杰, 郭晨, 鄧武. 基于流形正則化框架和MMD的域自適應BLS模型. 自動化學報, 2021, x(x): 1?14 doi: 10.16383/j.aas.c210009
              Zhao Hui-Min, Heng Jian-Jie, Guo Chen, Deng Wu. Domain adaptive BLS model based on manifold regularization framework and MMD. Acta Automatica Sinica, 2021, x(x): 1?14 doi: 10.16383/j.aas.c210009
              Citation: Zhao Hui-Min, Heng Jian-Jie, Guo Chen, Deng Wu. Domain adaptive BLS model based on manifold regularization framework and MMD. Acta Automatica Sinica, 2021, x(x): 1?14 doi: 10.16383/j.aas.c210009

              基于流形正則化框架和MMD的域自適應BLS模型

              doi: 10.16383/j.aas.c210009
              基金項目: 國家自然科學基金(61771087, 51879027), 中國民航大學科研啟動基金(2020KYQD123)
              詳細信息
                作者簡介:

                趙慧敏:中國民航大學電子信息與自動化學院教授, 碩士生導師. 主要研究方向為智能控制與信息處理、深度學習與智能優化、智能診斷與性能評估. E-mail: hm_zhao1977@126.com

                鄭建杰:首都師范大學心理學院博士生. 主要研究方向為寬度學習系統與圖像處理、人類腦圖譜的構建和應用. E-mail: zheng853796151@126.com

                郭晨:大連海事大學船舶電氣工程學院教授, 博士生導師. 主要研究方向為船舶自動控制系統、智能控制理論與應用、虛擬現實技術及應用. E-mail: dmuguoc@126.com

                鄧武:中國民航大學電子信息與自動化學院教授, 博士生導師. 主要研究方向為智能優化與資源調度、深度學習與智能診斷, 本文通信作者. E-mail: dw7689@163.com

              Domain Adaptive BLS Model Based on Manifold Regularization Framework and MMD

              Funds: Supported by National Natural Science Foundation of P. R. China (61771087, 51879027), and the Research Foundation for Civil Aviation University of China (2020KYQD123).
              More Information
                Author Bio:

                ZHAO Hui-Min Professor at the College of Electronic Information and Automation, Civil Aviation University of China. Her research interest includes Intelligent control and information processing, deep learning and intelligent optimization, intelligent diagnosis and performance evaluation

                ZHENG Jian-Jie Doctor at the College of School of Psychology, Capital Normal University. His research interest includes broad learning system and image processing, construction and application of human brain atlas

                GUO Chen Professor at the School of Marine Electrical Engineering, Dalian Maritime University. His research interest includes ship automatic control system, intelligent control theory and application, virtual reality technology and application

                DENG Wu Professor at the College of Electronic Information and Automation, Civil Aviation University of China. His research interest includes intelligent optimization and resource scheduling, deep learning and intelligent diagnosis. Corresponding author of this paper

              • 摘要: 寬度學習系統(Broad learning system, BLS)作為一種基于隨機向量函數型網絡(Random vector functional link network, RVFLN)的高效增量學習系統, 具有快速自適應模型結構選擇能力和高精度的特點. 但針對目標分類任務中有標簽數據匱乏問題, 傳統的BLS難以借助相關領域知識來提升目標域的分類效果, 為此本文提出一種基于流形正則化框架和最大均值差異(Maximum mean discrepancy, MMD)的域適應BLS(DABLS)模型, 實現目標域無標簽條件下的跨域圖像分類. DABLS模型首先構造BLS的特征節點和增強節點, 從源域和目標域數據中有效提取特征; 再利用流形正則化框架構造拉普拉斯矩陣, 以探索目標域數據中的流形特性, 挖掘目標域數據的潛在信息. 接著基于遷移學習方法構建源域數據與目標域數據之間的MMD懲罰項, 以匹配源域和目標域之間的投影均值; 將特征節點、增強節點、MMD懲罰項和目標域拉普拉斯矩陣相結合, 構造目標函數, 并采用嶺回歸分析法對其求解, 獲得輸出系數, 從而提高模型的跨域分類性能. 最后在不同圖像數據集上進行大量的驗證與對比實驗, 結果表明DABLS在不同圖像數據集上均能獲得較好的跨域分類性能, 具有較強的泛化能力和較好的穩定性.
              • 圖  1  BLS的結構示意圖

                Fig.  1  Structure diagram of BLS

                圖  2  DABLS模型的算法流程

                Fig.  2  Algorithm flow of DABLS model

                圖  3  第一行顯示Office和Caltech256數據集, 第二行顯示MNIST, USPS和COIL20數據集(從左到右)

                Fig.  3  The first row shows office and caltech256 datasets, and the second row shows MNIST, USPS and COIL20 datasets (from left to right)

                圖  4  顯示ImageNet和 VOC2007數據集

                Fig.  4  Display ImageNet and VOC207 datasets

                表  1  數據集的詳細描述

                Table  1  Detailed description of dataset

                數據集樣本數目特征維數類別子集
                USPS180025610U
                MNIST200025610M
                COIL201440102420CO1, CO2
                Office141080010A, W, D
                Caltech256112380010C
                ImageNet734140965I
                VOC2007337640965V
                下載: 導出CSV

                表  2  不同節點數下DABLS的實驗結果

                Table  2  Experimental results of DABLS with different number of nodes

                特征
                節點
                增強
                節點
                M→UU→M
                精度(%)時間(s)STD精度(%)時間(s)STD
                10050060.4119.011.2545.2520.501.84
                100100063.9419.591.6147.5722.462.14
                100150066.9821.561.4948.0526.162.27
                100200068.5423.981.6750.1327.271.53
                100250068.7727.151.7250.2529.271.64
                100300069.2233.12.1.8150.3732.831.78
                100350069.3137.261.8949.9136.251.92
                100400068.9540.961.7549.6341.171.82
                150200068.3625.031.8749.4927.921.72
                200200067.5325.912.0150.0828.721.79
                300200066.5726.412.0349.9229.621.87
                400200064.3526.973.3748.5930.581.95
                500200062.9627.494.6149.3831.411.64
                下載: 導出CSV

                表  3  從源域到目標域的平均分類精度(%)

                Table  3  Average classification accuracy from source domain to target domain (%)

                任務BLSSS-BLSTCACDELMCD-CDBNDABLS
                M→U25.3459.6754.2853.2750.2768.54
                U→ M20.2529.8452.0039.8041.6550.13
                平均值22.7944.7553.1446.5345.9659.33
                下載: 導出CSV

                表  4  從源域到目標域的平均訓練時間(s)

                Table  4  Average training time from source domain to target domain (s)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                M→U0.6912.7527.1424.77548.4723.98
                U→M0.5813.1822.3623.63536.9522.27
                平均值0.6412.9724.7524.20542.7123.13
                下載: 導出CSV

                表  5  不同節點數下DABLS的實驗結果

                Table  5  Experimental results of DABLS with different number of nodes

                特征
                節點
                增強
                節點
                CO1→CO2CO2→CO1
                精度(%)時間(s)STD精度(%)時間(s)STD
                10050085.432.591.8282.702.831.61
                100100086.403.171.8083.293.351.71
                100150086.833.651.3283.833.761.52
                100200087.334.501.2784.044.021.46
                100250087.694.931.3084.414.851.32
                100300088.185.851.1284.725.021.28
                100350088.266.541.1384.165.811.21
                100400087.557.611.1783.766.101.06
                150300087.556.021.1583.616.211.21
                200300087.096.151.1682.956.381.63
                300300085.926.641.1581.526.621.18
                400300084.087.241.2080.486.791.20
                500300082.297.421.0279.517.041.11
                下載: 導出CSV

                表  6  從源域到目標域的平均分類精度(%)

                Table  6  Average classification accuracy from source domain to target domain (%)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                CO1→CO282.2583.7588.6181.6684.6788.12
                CO2→CO180.6381.1786.3380.1980.7484.72
                平均值81.4482.4687.4780.9382.7086.42
                下載: 導出CSV

                表  7  從源域到目標域的平均訓練時間(s)

                Table  7  Average training time from source domain to target domain (s)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                CO1→CO21.383.2219.985.87125.335.35
                CO2→CO10.852.9514.675.48136.785.33
                平均值1.123.0917.325.68131.055.34
                下載: 導出CSV

                表  8  不同節點數下DABLS的實驗結果

                Table  8  Experimental results of DABLS with different number of nodes

                特征
                節點
                增強
                節點
                A→CW→C
                精度(%)時間(s)STD精度(%)時間(s)STD
                5005043.638.810.7534.696.010.35
                50010043.738.860.5335.246.240.91
                50015043.828.920.7735.536.500.65
                50020043.929.010.6235.616.780.71
                50030043.989.180.8535.936.930.92
                50040044.029.530.8736.277.210.77
                50050044.299.770.4436.507.430.70
                50060043.509.980.6136.527.720.93
                50080043.3610.520.5936.218.010.64
                500100043.1810.900.8236.048.390.33
                10050042.018.720.7632.396.480.91
                20050042.369.020.8333.956.660.99
                30050042.839.300.6534.276.870.92
                40050043.599.530.6936.117.120.77
                60050044.2510.440.7836.177.850.82
                80050043.4310.750.6535.778.030.69
                下載: 導出CSV

                表  9  從源域到目標域的平均分類精度(%)

                Table  9  Average classification accuracy from source domain to target domain (%)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                A$ \to $C20.8242.1640.7831.6735.5644.29
                A$ \to $D17.8339.4031.8532.4833.7942.06
                A$ \to $W19.6140.6137.6331.47)27.4642.09
                C$ \to $A29.1649.6744.8944.9938.7851.68
                C$ \to $D24.8444.2045.8435.3736.9445.85
                C$ \to $W20.4645.7436.6138.9235.5447.79
                D$ \to $A32.4235.5731.5230.6128.3436.73
                D$ \to $C30.0330.1932.5028.9626.7932.47
                D$ \to $W79.9879.11)87.1276.9550.7880.06
                W$ \to $A34.6137.5130.6935.5530.8940.01
                W$ \to $C31.7335.2927.1632.0327.2636.50
                W$ \to $D80.8180.8990.4578.9950.4282.73
                平均值35.1946.6945.3841.5035.2148.52
                下載: 導出CSV

                表  10  從源域到目標域的平均訓練時間(s)

                Table  10  Average training time from source domain to target domain (s)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                A$ \to $C0.785.3936.696.8346.369.77
                A$ \to $D0.670.8311.731.2933.282.76
                A$ \to $W0.640.9913.651.5234.232.91
                C$ \to $A0.683.8635.715.7441.448.18
                C$ \to $D0.710.9315.051.5835.863.71
                C$ \to $W0.671.0916.751.5938.373.63
                D$ \to $A0.593.5811.824.1420.125.50
                D$ \to $C0.545.1916.216.1426.637.45
                D$ \to $W0.550.793.530.7320.481.17
                W$ \to $A0.583.4314.294.3345.535.93
                W$ \to $C0.575.1719.056.1256.287.43
                W$ \to $D0.520.693.220.6612.401.02
                平均值0.622.6616.483.3930.084.96
                下載: 導出CSV

                表  11  不同節點數下DABLS的實驗結果

                Table  11  Experimental results of DABLS with different number of nodes

                特征
                節點
                增強
                節點
                V→II→V
                精度(%)時間(s)STD精度(%)時間(s)STD
                10060074.1335.251.0566.6116.621.31
                15060075.9437.990.7566.8319.240.77
                20060076.5342.290.5967.5122.420.62
                25060077.8744.510.3367.8326.030.41
                30060077.6547.640.2967.8128.960.43
                40060076.8753.890.3667.2431.620.45
                50060075.6757.130.1967.0235.370.39
                60060075.2061.290.2766.8638.690.37
                25020074.2926.560.7366.3214.730.87
                25040077.2131.590.6767.1317.330.54
                25080077.2346.210.5667.6924.090.42
                250100076.8352.680.6567.5227.550.34
                250150074.9365.710.4667.4236.430.31
                250200073.8683.610.3667.3343.530.33
                250250071.77103.380.3166.7350.920.26
                下載: 導出CSV

                表  12  從源域到目標域的平均分類精度(%)

                Table  12  Average classification accuracy from source domain to target domain (%)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                V → I76.2277.0373.7976.8276.0277.87
                I → V66.3267.1364.3466.8567.1967.83
                平均值71.2772.0869.0671.8371.6072.85
                下載: 導出CSV

                表  13  從源域到目標域的平均訓練時間(s)

                Table  13  Average training time from source domain to target domain(s)

                任務/方法BLSSS-BLSTCACDELMCD-CDBNDABLS
                V → I6.3737.6952.1555.041039.0344.51
                I → V3.6217.3230.4233.39823.3526.03
                平均值4.9627.5041.2844.25931.1935.27
                下載: 導出CSV
                1. <button id="qm3rj"><thead id="qm3rj"></thead></button>
                  <samp id="qm3rj"></samp>
                  <source id="qm3rj"><menu id="qm3rj"><pre id="qm3rj"></pre></menu></source>

                  <video id="qm3rj"><code id="qm3rj"></code></video>

                    1. <tt id="qm3rj"><track id="qm3rj"></track></tt>
                        亚洲第一网址_国产国产人精品视频69_久久久久精品视频_国产精品第九页
                      1. [1] Salakhutdinov R, Hinton G. An efficient learning procedure for deep boltzmann machine. Neural Computation, 2014, 24(8): 1967?2006
                        [2] 林景棟, 吳欣怡, 柴毅, 尹宏鵬. 卷積神經網絡結構優化綜述. 自動化學報, 2020, 46(1): 24?37

                        Lin Jing-Dong, Wu Xin-Yi, Chai Yi, Yin Hong-Peng. Structure optimization of convolutional neural networks: A survey. Acta Automatica Sinica, 2020, 46(1): 24?37
                        [3] Hinton G E, Osinderos T YW. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527?1554 doi: 10.1162/neco.2006.18.7.1527
                        [4] 劉建偉, 謝浩杰, 羅雄麟. 生成對抗網絡在各領域應用研究進展. 自動化學報, 2020, 46(12): 2500?2536

                        Liu Jian-Wei, Xie Hao-Jie, Luo Xiong-Lin. Research progress on application of generative adversarial networks in various fields. Acta Automatica Sinica, 2020, 46(12): 2500?2536
                        [5] Feng L, Chen Z, Jie W. Video image target monitoring based on RNN-LSTM. Multimedia Tools Applications, 2018, 78(2): 1?18
                        [6] Chen C L P, Liu Z. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(1): 10?24 doi: 10.1109/TNNLS.2017.2716952
                        [7] Chen C L P, Liu Z, Feng S. Universal approximation capability of broad learning system and its structural variations. IEEE Transactions on Neural Networksand Learning Systems, 2019, 30(4): 1191?1204 doi: 10.1109/TNNLS.2018.2866622
                        [8] Jin J W, Philip Chen C L. Regularized robust broad learning system for uncertain data modeling. Neurocomputing, 2018, 322(1): 58?69
                        [9] 楊剛, 陳鵬, 戴麗珍, 楊輝. 一種基于池計算的寬度學習系統. 控制與決策, 2020, Doi: 10.13195/j.kzyjc.2019.1729.

                        Yang Gang, Chen Peng, Dai Li-Zhen, Yang Hui. A broad learning system based on reservoir computing. Control and Decision, 2020, doi: 10.13195/j.kzyjc.2019.1729.
                        [10] 鄒偉東, 夏元清. 基于壓縮因子的寬度學習系統的虛擬機性能預測. 自動化學報, 2019, Doi: 10.16383/j.aas.c190307.

                        Zou Wei-Dong, Xia Yuan-Qing. Virtual machine performance prediction using broad learning system based on compression factor. Acta Automatica Sinica, 2019, Doi: 10.16383/j.aas.c190307.
                        [11] Kong Y, Wang X, Cheng Y, Chen C. Hyperspectral imagery classification based on semi-supervised broad learning system. Remote Sensing, 2018, 10(5): 685 doi: 10.3390/rs10050685
                        [12] 鄭云飛, 陳霸東. 基于最小p-范數的寬度學習系統. 模式識別與人工智能, 2019, 32(1): 51?57

                        Zheng Yun-Fei, Chen Ba-Dong. Least p-Norm based broad learning system. Pattern Recognition and Artificial Intelligence, 2019, 32(1): 51?57
                        [13] Lin J, Liu Z, Chen C L P, Zhang Y. Quaternion broad learning system: a novel multi-dimensional filter for estimation and elimination tremor in teleoperation. Neurocomputing, 2020, 380: 78?86 doi: 10.1016/j.neucom.2019.10.059
                        [14] Han M, Feng S B, Chen C L P, et al. Structured manifold broad learning system: A manifold perspective for large-scale chaotic time series analysis and prediction. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(9): 1809?1821 doi: 10.1109/TKDE.2018.2866149
                        [15] Fan J H, Wang X, Wang X X, et al. Incremental wishart broad learning system for fast polsar image classification. IEEE Geoscience and Remote Sensing Letters, 2019, 16(12): 1854?1858 doi: 10.1109/LGRS.2019.2913999
                        [16] Feng S, ChenN C L P. Fuzzy Broad Learning System: A novel neuro-fuzzy model for regression and classification. IEEE Transactions on Cybernetics, 2020, 50(2): 414?424 doi: 10.1109/TCYB.2018.2857815
                        [17] Xu M L, Han M, Chen C L P, et al. Recurrent broad learning systems for time series prediction. IEEE Transactions on Cybernetics, 2020, 50(4): 1405?1417 doi: 10.1109/TCYB.2018.2863020
                        [18] Chu F, Liang T, Chen C L P, et al. Weighted broad learning system and its application in nonlinear industrial process modeling. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(8): 3017?3031 doi: 10.1109/TNNLS.2019.2935033
                        [19] Liu Y, Wang Y F, Chen L, et al. Incremental Bayesian broad learning system and its industrial application. Artificial Intelligence Review, 2020, Doi: 10.1007/s10462-020-09929-z.
                        [20] Shi Z H, Chen X M, Zhao C M, et al. Multi-view broad learning system for primate oculomotor decision decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020, 28(9): 1908?1920 doi: 10.1109/TNSRE.2020.3003342
                        [21] Zhao H M, Zheng J J, Deng W, et al. Semi-supervised broad learning system based on manifold regularization and broad network. IEEE Transactions on Circuits and Systems--I: Regular Papers, 2020, 67(3): 983?994 doi: 10.1109/TCSI.2019.2959886
                        [22] Li S, Song S J, Huang G, et al. Cross-domain extreme learning machines for domain adaptation. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018, 49(6): 2168?2216
                        [23] Pan S J, Tsang I W, Kwok J T, et al. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 2021, 22(2): 199?210
                        [24] Huang G B. Learning hierarchical representations for face verification with convolutional deep belief networks. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), . 2012: 2518−2525.
                      2. 加載中
                      3. 計量
                        • 文章訪問數:  2005
                        • HTML全文瀏覽量:  701
                        • 被引次數: 0
                        出版歷程
                        • 收稿日期:  2021-01-04
                        • 錄用日期:  2021-05-12
                        • 網絡出版日期:  2021-06-28

                        目錄

                          /

                          返回文章
                          返回