基于多核最大均值差異遷移學(xué)習(xí)的WLAN室內(nèi)入侵檢測方法
doi: 10.11999/JEIT190358 cstr: 32379.14.JEIT190358
-
1.
重慶郵電大學(xué)通信與信息工程學(xué)院 重慶 400065
-
2.
香港浸會大學(xué)計(jì)算機(jī)系 香港 999077
WLAN Indoor Intrusion Detection Approach Based on Multiple Kernel Maximum Mean Discrepancy Transfer Learning
-
1.
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
-
2.
Department of Computer Science, Hong Kong Baptist University, Hong Kong 999077, China
-
摘要:
無線局域網(wǎng)(WLAN)室內(nèi)入侵檢測技術(shù)是目前智能檢測領(lǐng)域的研究熱點(diǎn)之一，而傳統(tǒng)基于數(shù)據(jù)庫構(gòu)建的入侵檢測技術(shù)沒有考慮復(fù)雜室內(nèi)環(huán)境中WLAN信號的時(shí)變性，從而導(dǎo)致WLAN室內(nèi)入侵檢測系統(tǒng)的魯棒性較差。為了解決這一問題，該文提出一種基于多核最大均值差異(MKMMD)遷移學(xué)習(xí)的WLAN室內(nèi)入侵檢測方法。該方法首先利用離線有標(biāo)記和在線偽標(biāo)記的接收信號強(qiáng)度(RSS)特征來分別構(gòu)建源域和目標(biāo)域；其次，通過構(gòu)造最優(yōu)遷移矩陣以最小化源域和目標(biāo)域RSS特征混合分布之間的MKMMD；再次，利用遷移后的源域RSS特征與對應(yīng)標(biāo)簽來訓(xùn)練分類器，并將其用于對遷移后的目標(biāo)域RSS特征進(jìn)行分類以得到目標(biāo)域標(biāo)簽集；最后，迭代更新目標(biāo)域標(biāo)簽集直至算法收斂，進(jìn)而實(shí)現(xiàn)對目標(biāo)環(huán)境的入侵檢測。實(shí)驗(yàn)結(jié)果表明，該文所提方法在保證較高檢測精度的同時(shí)，能夠有效克服信號時(shí)變性對檢測性能的影響。
-
關(guān)鍵詞:
- 室內(nèi)入侵檢測 /
- 多核最大均值差異 /
- 遷移學(xué)習(xí) /
- 最優(yōu)遷移矩陣 /
- 無線局域網(wǎng)
Abstract:Wireless Local Area Network (WLAN) indoor intrusion detection technique is one of the current research hotspots in the field of intelligent detection, but the conventional database construction based intrusion detection technique does not consider the time-variant property of WLAN signal in the complicated indoor environment, which results in the low robustness of WLAN indoor intrusion detection system. To address this problem, a Multiple Kernel Maximum Mean Discrepancy (MKMMD) transfer learning based WLAN indoor intrusion detection approach is proposed. First of all, the offline labeled and online pseudo-labeled Received Signal Strength (RSS) features are used to construct source and target domains respectively. Second, the optimal transfer matrix is constructed to minimize the MKMMD of the joint distributions of RSS features in source and target domains. Third, a classifier trained from the transferred RSS features and the corresponding labels in source domain is used to classify the transferred RSS features in target domain, and meanwhile the label set corresponding to target domain is obtained. Finally, the label set corresponding to target domain is updated in an iterative manner until the proposed algorithm converges, and then the intrusion detection in target environment is achieved. The experimental results indicate that the proposed approach is able to preserve high detection accuracy as well as overcome the impact of time-variant signal property on the detection performance.
-
表 1 不同分類器的檢測性能(%)
類別 FP FN DA KNN(遷移前) 35.92 0 75.60 KNN(遷移后) 0 0 99.78 RF(遷移前) 6.67 1.92 83.96 RF(遷移后) 0 0 98.90 SVM(遷移前) 18.02 0 93.85 SVM(遷移后) 0 1.10 98.02 
下載: 導(dǎo)出CSV
表 2 不同方法的檢測性能(%)
指標(biāo) RASID PNN PRNN 本文方法 FP 6.72 3.42 0 0 FN 3.31 2.92 0 0 DA 93.46 94.40 95.60 99.78
下載: 導(dǎo)出CSV
-
周培培, 丁慶海, 羅海波, 等. 視頻監(jiān)控中的人群異常行為檢測與定位[J]. 光學(xué)學(xué)報(bào), 2018, 38(8): 0815007. doi: 10.3788/AOS201838.0815007ZHOU Peipei, DING Qinghai, LUO Haibo, et al. Anomaly detection and location in crowded surveillance videos[J]. Acta Optica Sinica, 2018, 38(8): 0815007. doi: 10.3788/AOS201838.0815007 程衛(wèi)東, 董永貴. 利用熱釋電紅外傳感器探測人體運(yùn)動特征[J]. 儀器儀表學(xué)報(bào), 2008, 29(5): 1020–1023. doi: 10.3321/j.issn:0254-3087.2008.05.025CHENG Weidong and DONG Yonggui. Detection of human body motion features using pyroelectric infrared sensor[J]. Chinese Journal of Scientific Instrument, 2008, 29(5): 1020–1023. doi: 10.3321/j.issn:0254-3087.2008.05.025 WANG Hongpeng, LIU Jingtai, SUN Lei, et al. Indoor intrusion detection using an intelligent sensor network[C]. 2008 IEEE World Congress on Intelligent Control and Automation, Chongqing, China, 2008: 2396–2401. doi: 10.1109/WCICA.2008.4593298. TIAN Zengshan, LI Yong, ZHOU Mu, et al. WiFi-based adaptive indoor passive intrusion detection[C]. 2018 IEEE 23rd International Conference on Digital Signal Processing, Shanghai, China, 2018: 1–5. doi: 10.1109/ICDSP.2018.8631613. YOUSSEF M, MAH M, and AGRAWALA A. Challenges: Device-free passive localization for wireless environments[C]. The 13th Annual ACM International Conference on Mobile Computing and Networking, Montréal, Canada, 2007: 222–229. doi: 10.1145/1287853.1287880. ZHOU Rui, CHEN Jiesong, LU Xiang, et al. CSI fingerprinting with SVM regression to achieve device-free passive localization[C]. The 18th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, Macau, China, 2017: 1–9. doi: 10.1109/WoWMoM.2017.7974313. KOSBA A E, SAEED A, and YOUSSEF M. RASID: A robust WLAN device-free passive motion detection system[C]. 2012 IEEE International Conference on Pervasive Computing and Communications, Lugano, Switzerland, 2012: 180–189. doi: 10.1109/PerCom.2012.6199865. TIAN Zengshan, ZHOU Xiangdong, ZHOU Mu, et al. Indoor device-free passive localization for intrusion detection using multi-feature PNN[C]. 2015 International Conference on Communications and Networking in China, Shanghai, China, 2015: 272–277. doi: 10.1109/CHINACOM.2015.7497950. DEAK G, CURRAN K, CONDELL J, et al. Detection of multi-occupancy using device-free passive localisation[J]. IET Wireless Sensor Systems, 2014, 4(3): 130–137. doi: 10.1049/iet-wss.2013.0031 LV Jiguang, MAN Dapeng, YANG Wu, et al. Robust WLAN-based indoor intrusion detection using PHY layer information[J]. IEEE Access, 2018, 6: 30117–30127. doi: 10.1109/access.2017.2785444 TAN Qingqing, HAN Chong, SUN Lijuan, et al. A CSI frequency domain fingerprint-based method for passive indoor human detection[C]. 2018 IEEE International Conference on Trust, Security and Privacy in Computing and Communications/12th IEEE International Conference on Big Data Science and Engineering, New York, USA, 2018: 1832–1837. doi: 10.1109/TrustCom/BigDataSE.2018.00277. GRETTON A, SRIPERUMBUDUR B, SEJDINOVIC D, et al. Optimal kernel choice for large-scale two-sample tests[C]. The 25th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, 2012: 1205–1213. LONG Mingsheng, WANG Jianmin, DING Guiguang, et al. Transfer feature learning with joint distribution adaptation[C]. 2013 IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 2200–2207. doi: 10.1109/ICCV.2013.274. DUAN Lixin, TSANG I W, and XU Dong. Domain transfer multiple kernel learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3): 465–479. doi: 10.1109/tpami.2011.114 BORGWARDT K M, GRETTON A, RASCH M J, et al. Integrating structured biological data by kernel maximum mean discrepancy[J]. Bioinformatics, 2006, 22(4): e49–e57. doi: 10.1093/bioinformatics/btl242 PAN S J, TSANG I W, KWOK J T, et al. Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Networks, 2011, 22(2): 199–210. doi: 10.1109/TNN.2010.2091281 SCHOLK?PF B, SMOLA A, and MüLLER K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10(5): 1299–1319. doi: 10.1162/089976698300017467 汪洪橋, 孫富春, 蔡艷寧, 等. 多核學(xué)習(xí)方法[J]. 自動化學(xué)報(bào), 2010, 36(8): 1037–1050. doi: 10.3724/SP.J.1004.2010.01037WANG Hongqiao, SUN Fuchun, CAI Yanning, et al. On multiple kernel learning methods[J]. Acta Automatica Sinica, 2010, 36(8): 1037–1050. doi: 10.3724/SP.J.1004.2010.01037 COVER T and HART P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21–27. doi: 10.1109/TIT.1967.1053964 BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5–32. doi: 10.1023/A:1010933404324 CORTES C and VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273–297. doi: 10.1007/BF00994018 -
計(jì)量
- 文章訪問數(shù): 3862
- HTML全文瀏覽量: 1920
- PDF下載量: 136
- 被引次數(shù): 0
下載:
