用于異質(zhì)信息的信任區(qū)間交互式多屬性識(shí)別方法

李雙明; 關(guān)欣; 衣曉; 吳斌

doi:10.11999/JEIT200038

用于異質(zhì)信息的信任區(qū)間交互式多屬性識(shí)別方法

doi: 10.11999/JEIT200038 cstr: 32379.14.JEIT200038

李雙明^{1, 2, ,},
關(guān)欣¹,
衣曉¹,
吳斌¹

1.
海軍航空大學(xué) 煙臺(tái) 264001
2.
92941部隊(duì) 葫蘆島 125001

基金項(xiàng)目: 國(guó)防科技卓越青年科學(xué)基金(2017-JCJQ-ZQ-003)，泰山學(xué)者工程專項(xiàng)經(jīng)費(fèi)(ts 201712072)

詳細(xì)信息

作者簡(jiǎn)介:
李雙明：男，1986年生，博士，主要研究方向?yàn)槟繕?biāo)識(shí)別技術(shù)

關(guān)欣：女，1978年生，博士，教授，主要研究方向?yàn)樾畔⑷诤?、電子?duì)抗及智能計(jì)算

衣曉：男，1975年生，博士，教授，主要研究方向?yàn)闊o(wú)線傳感器網(wǎng)絡(luò)，多源信息融合

吳斌：男，1992年生，博士，主要研究方向?yàn)橹饕芯糠较驗(yàn)闊o(wú)線傳感器網(wǎng)絡(luò)

通訊作者:
李雙明　aminglishuang@126.com

中圖分類號(hào): TN911.7; TN957
計(jì)量
- 文章訪問數(shù): 1200
- HTML全文瀏覽量: 347
- PDF下載量: 52
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2020-01-09
- 修回日期: 2020-10-23
- 網(wǎng)絡(luò)出版日期: 2020-12-07
- 刊出日期: 2021-05-18

A BI-TODIM Approach Used for Heterogeneous Information Fusion

Shuangming LI^{1, 2
, ,},
Xin GUAN¹,
Xiao YI¹,
Bin WU¹

1.
Naval Aviation University, Yantai 264001, China
2.
PLA Unit 92941, Huludao 125001, China

Funds: The National Defense Science and Technology Excellence Youth Talent Fund (2017-JCJQ-ZQ-003), The Taishan Scholar Engineering Special Fund (ts 201712072)

摘要

摘要: 為了解決混合類型數(shù)據(jù)與專家知識(shí)等異質(zhì)信息的融合決策問題，該文提出了基于信任區(qū)間的交互式多屬性識(shí)別(BI-TODIM)方法。完善了混合類型數(shù)據(jù)的距離測(cè)度，根據(jù)信任區(qū)間的構(gòu)建定理和灰關(guān)聯(lián)方法構(gòu)建了未知目標(biāo)混合類型數(shù)據(jù)的信任區(qū)間，闡明了信任區(qū)間與直覺模糊數(shù)之間的等價(jià)關(guān)系，創(chuàng)建了混合類型數(shù)據(jù)和專家知識(shí)的識(shí)別決策模型，實(shí)現(xiàn)了特征層信息和決策層信息的統(tǒng)一表達(dá)；分析了基于信度函數(shù)的逼近理想解(BF-TOPSIS)方法的反轉(zhuǎn)現(xiàn)象及算法的復(fù)雜度，定義了區(qū)間數(shù)的序關(guān)系，提出了BI-TODIM識(shí)別決策方法，及基于直覺模糊熵的未知權(quán)重計(jì)算方法。結(jié)合算例和目標(biāo)識(shí)別案例，驗(yàn)證了該文方法在解決排序反轉(zhuǎn)和異質(zhì)信息融合方面的有效性，突出了該方法時(shí)間復(fù)雜度低、穩(wěn)定性好、識(shí)別準(zhǔn)確度高的優(yōu)點(diǎn)。
- 信任區(qū)間 /
- 交互式多屬性 /
- 異質(zhì)信息 /
- 距離測(cè)度 /
- 關(guān)聯(lián)系數(shù)
Abstract: A the Interative Multi-criteria Decision making based on Belief Interval (BI-TODIM) approach is proposed to solve the fusion decision problem of heterogeneous information with mixed type data and expert knowledge. According to the construction theorem of trust interval and grey relation method, the trust interval of mixed type data of unknown target is constructed. The equivalence relationship between trust interval and intuitionistic fuzzy number is clarified. The recognition decision model of mixed type data and expert knowledge is established. The unified expression of feature layer information and decision layer information is realized. The shortcomings of the Technique for Order Preference by Similarity to Ideal Solution based on Belief Function (BF-TOPSIS) method are analyzed such as the inversion phenomenon and the complexity. To solve this problem, the order relation of interval numbers is defined, the BI-TODIM recognition decision method and the method of calculating unknown weight based on intuitionistic fuzzy entropy are proposed. The effectiveness of the proposed method in resolving ranking inversion and heterogeneous information fusion is verified by an example and a target identification case, which underlines low time complexity, good stability and high recognition accuracy.
- Belief interval /
- Interative multi-criteria /
- Heterogeneous information /
- Distance measure /
- Correlation coefficient

HTML全文

圖 1 算法流程示意圖

下載: 全尺寸圖片幻燈片

圖 2 直覺模糊信息的圖形表示

下載: 全尺寸圖片幻燈片

圖 3 信任區(qū)間的圖形表示

下載: 全尺寸圖片幻燈片

圖 4 未知目標(biāo)1/2/3的前景值變化曲線

下載: 全尺寸圖片幻燈片

表 1 本文方法及BF-TOPSIS1/2的計(jì)算結(jié)果

排序方法	備選方案集	排序結(jié)果	運(yùn)行時(shí)間(s)
本文方法	{A₁, A₂, A₃, A₄}	A₁$ \succ $A₂$ \succ $A₄$ \succ $A₃	0.003306
BF-TOPSIS1		A₁$ \succ $A₂$ \succ $A₄$ \succ $A₃	0.663752
BF-TOPSIS2		A₁$ \succ $A₂$ \succ $A₄$ \succ $A₃	0.789059
BF-TOPSIS3		A₂$ \succ $A₁$ \succ $A₄$ \succ $A₃	21.255864

下載: 導(dǎo)出CSV

表 2 分類結(jié)果比較(%)

分類方法	數(shù)據(jù)集
分類方法	Iris	Wine	Glass
KNN	95.33	72.47	74.29
LST-KSVC	99.27	94.27	65.76
FGGCA	97.22	97.10	93.65
WLTSVM	98.00	96.40	49.91
本文方案	97.10	96.20	94.70

下載: 導(dǎo)出CSV

表 3 工作模式的數(shù)據(jù)取值范圍

類別	特征參數(shù)
類別	RF(MHz)	PRI(μs)	PW(μs)	Cr
R₁	[4940, 5160]	[3680, 3750]	[0.6, 1.2]	[0.3800, 0.4041]
R₂	[5420, 5520]	[3600, 3680]	[0.2, 0.5]	[0.6626, 0.6731]
R₃	[5100, 5420]	[3580, 3650]	[1.6, 2.0]	[0.1622, 0.2294]
R₄	[5160, 5220]	[3730, 3800]	[0.9, 1.4]	[0.6587, 0.6981]
R₅	[5520, 5620]	[3450, 3550]	[1.2, 1.5]	[0.7776, 0.8098]

下載: 導(dǎo)出CSV

表 4 參數(shù)1下識(shí)別結(jié)果的正確率(%)

目標(biāo)	本文方法			BF-TOPSIS1方法
目標(biāo)	本文權(quán)重	權(quán)重1	權(quán)重2	本文權(quán)重	權(quán)重1	權(quán)重2
1	97.3	91.8	60.6	87.2	86.0	33.6
2	94.4	86.8	38.0	79.6	79.6	27.9
3	97.1	92.3	52.4	88.7	87.8	33.2

下載: 導(dǎo)出CSV

參考文獻(xiàn)(16)

[1]	YING Chengshuo, LI Yanlai, CHIN K, et al. A new product development concept selection approach based on cumulative prospect theory and hybrid-information MADM[J]. Computers & Industrial Engineering, 2018, 122: 251–261. doi: 10.1016/j.cie.2018.05.023
[2]	陳可嘉, 陳萍. 基于三參數(shù)區(qū)間灰數(shù)的TOPSIS決策方法[J]. 系統(tǒng)工程與電子技術(shù), 2019, 41(1): 124–130. doi: 10.3969/j.issn.1001-506X.2019.01.18 CHEN Kejia and CHEN Ping. Decision making method of TOPSIS based on three-parameter interval grey numbers[J]. Systems Engineering and Electronics, 2019, 41(1): 124–130. doi: 10.3969/j.issn.1001-506X.2019.01.18
[3]	關(guān)欣, 孫貴東, 衣曉, 等. 基于關(guān)聯(lián)系數(shù)靶心距的混合多屬性識(shí)別[J]. 航空學(xué)報(bào), 2015, 36(7): 2431–2443. doi: 10.7527/S1000-6893.2014.0299 GUAN Xin, SUN Guidong, YI Xiao, et al. Hybrid multiple attribute recognition based on coefficient of incidence bull’s-eye-distance[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(7): 2431–2443. doi: 10.7527/S1000-6893.2014.0299
[4]	LOURENZUTTI R and KROHLING R A. TODIM based method to process heterogeneous information[J]. Procedia Computer Science, 2015, 55: 318–327. doi: 10.1016/j.procs.2015.07.056
[5]	CHEN S, KUO Liwei, and ZOU Xinyao. Multiattribute decision making based on Shannon’s information entropy, non-linear programming methodology, and interval-valued intuitionistic fuzzy values[J]. Information Sciences, 2018, 465: 404–424. doi: 10.1016/j.ins.2018.06.047
[6]	CHENG Jin, FENG Yixiong, LIN Zhiqiang, et al. Anti-vibration optimization of the key components in a turbo-generator based on heterogeneous axiomatic design[J]. Journal of Cleaner Production, 2017, 141: 1467–1477. doi: 10.1016/j.jclepro.2016.09.217
[7]	刁鵬飛, 王艷嬌. 基于節(jié)點(diǎn)休眠的水下無(wú)線傳感器網(wǎng)絡(luò)覆蓋保持分簇算法[J]. 電子與信息學(xué)報(bào), 2018, 40(5): 1101–1107. doi: 10.11999/JEIT170787 DIAO Pengfei and WANG Yanjiao. Coverage-preserving clustering algorithm for underwater sensor networks based on the sleeping mechanism[J]. Journal of Electronics &Information Technology, 2018, 40(5): 1101–1107. doi: 10.11999/JEIT170787
[8]	PAVLICIC D. Normalization affects the results of MADM methods[J]. Yugoslav Journal of Operations Research, 2001, 11(2): 251–265.
[9]	DEZERT J, HAN Deqiang, and YIN Hanlin. A new belief function based approach for multi-criteria decision-making support[C]. The 19th International Conference on Information Fusion, Heidelberg, Germany, 2016: 782–789.
[10]	李雙明, 關(guān)欣, 趙靜, 等. 一種參數(shù)區(qū)間交叉類型的目標(biāo)識(shí)別方法[J]. 北京航空航天大學(xué)學(xué)報(bào), 2020, 46(7): 1307–1316. LI Shuangming, GUAN Xin, ZHAO Jing, et al. A methodology for target recognition with parameters of interval cross type[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(7): 1307–1316.
[11]	IRPINO A and VERDE R. Dynamic clustering of interval data using a Wasserstein-based distance[J]. Pattern Recognition Letters, 2008, 29(11): 1648–1658. doi: 10.1016/j.patrec.2008.04.008
[12]	ACI M and AVCI M. K nearest neighbor reinforced expectation maximization method[J]. Expert Systems with Applications, 2011, 38(10): 12585–12591. doi: 10.1016/j.eswa.2011.04.046
[13]	NIE Qingfeng, JIN Lizuo, FEI Shumin, et al. Neural network for multi-class classification by boosting composite stumps[J]. Neurocomputing, 2015, 149: 949–956. doi: 10.1016/j.neucom.2014.07.039
[14]	SANCHEZ M A, CASTILLO O, CASTRO J R, et al. Fuzzy granular gravitational clustering algorithm for multivariate data[J]. Information Sciences, 2014, 279: 498–511. doi: 10.1016/j.ins.2014.04.005
[15]	SHAO Yuanhai, CHEN Weijie, WANG Zhen, et al. Weighted linear loss twin support vector machine for large-scale classification[J]. Knowledge-Based Systems, 2015, 73: 276–288. doi: 10.1016/j.knosys.2014.10.011
[16]	黃穎坤, 金煒東, 葛鵬, 等. 基于多尺度信息熵的雷達(dá)輻射源信號(hào)識(shí)別[J]. 電子與信息學(xué)報(bào), 2019, 41(5): 1084–1091. doi: 10.11999/JEIT180535 HUANG Yingkun, JIN Weidong, GE Peng, et al. Radar emitter signal identification based on multi-scale information entropy[J]. Journal of Electronics &Information Technology, 2019, 41(5): 1084–1091. doi: 10.11999/JEIT180535