物聯(lián)網(wǎng)中基于相似性計(jì)算的傳感器搜索

劉素艷; 劉元安; 吳帆; 范文浩

doi:10.11999/JEIT171085

物聯(lián)網(wǎng)中基于相似性計(jì)算的傳感器搜索

doi: 10.11999/JEIT171085 cstr: 32379.14.JEIT171085

劉素艷^{1, 2, ,},
劉元安¹,
吳帆^{1, 2},
范文浩^{1, 2}

1.
北京郵電大學(xué)電子工程學(xué)院 ??北京 ??100876
2.
北京郵電大學(xué)安全生產(chǎn)智能監(jiān)控北京市重點(diǎn)實(shí)驗(yàn)室 ??北京 ??100876

基金項(xiàng)目: 國家自然科學(xué)基金(61272518, 61502050)，安全生產(chǎn)智能監(jiān)控北京市重點(diǎn)實(shí)驗(yàn)室主任基金(北京郵電大學(xué))，廣東省‘揚(yáng)帆計(jì)劃’引進(jìn)創(chuàng)新創(chuàng)業(yè)團(tuán)隊(duì)項(xiàng)目

詳細(xì)信息

作者簡介:
劉素艷：女，1982年生，博士生，研究方向?yàn)槲锫?lián)網(wǎng)搜索、無線傳感器網(wǎng)絡(luò)

劉元安：男，1963年生，教授，研究方向?yàn)殡姶偶嫒?、泛在無線網(wǎng)絡(luò)

吳帆：女，1981年生，副教授，研究方向?yàn)槲锫?lián)網(wǎng)搜索、泛在無線網(wǎng)絡(luò)

范文浩：男，1986年生，講師，研究方向?yàn)橐苿?dòng)設(shè)備、云計(jì)算

通訊作者:
劉素艷　 153897455@qq.com

中圖分類號: TP393
計(jì)量
- 文章訪問數(shù): 2049
- HTML全文瀏覽量: 822
- PDF下載量: 58
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-11-20
- 修回日期: 2018-09-12
- 網(wǎng)絡(luò)出版日期: 2018-09-20
- 刊出日期: 2018-12-01

Sensor Search Based on Sensor Similarity Computing in the Internet of Things

Suyan LIU^{1, 2
, ,},
Yuanan LIU¹,
Fan WU^{1, 2},
Wenhao FAN^{1, 2}

1.
School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
2.
Beijing Key Laboratory of Work Safety Intelligent Monitoring, Beijing University of Posts and Telecommunications, Beijing 100876, China

Funds: The National Natural Science Foundation of China (61272518, 61502050), The Beijing Key Laboratory Director Foundation of Work Safety Intelligent Monitoring (Beijing University of Posts and Telecommunications), The YangFan Innovative & Entrepreneurial Research Team Project of Guangdong Province

摘要

摘要: 物聯(lián)網(wǎng)逐漸成為學(xué)術(shù)界研究的熱點(diǎn)領(lǐng)域，無處不在的傳感器設(shè)備促進(jìn)了傳感器搜索服務(wù)的產(chǎn)生。物聯(lián)網(wǎng)中搜索的強(qiáng)時(shí)空性、海量數(shù)據(jù)的異構(gòu)性與傳感器節(jié)點(diǎn)的資源受限性，給物聯(lián)網(wǎng)搜索引擎高效地查詢傳感器提出了挑戰(zhàn)。該文提出基于傳感器定量數(shù)值的線性分段擬合相似性(PLSS)搜索算法。PLSS算法通過分段和線性擬合的方法，構(gòu)建傳感器定量數(shù)值的相似性計(jì)算模型，從而計(jì)算傳感器的相似度，根據(jù)相似度查找最相似的傳感器集群。與模糊集(FUZZY)算法和最小二乘法相比，PLSS算法平均查詢精度和查詢效率較高。與原數(shù)據(jù)相比，PLSS算法的存儲開銷至少降低了兩個(gè)數(shù)量級。
- 物聯(lián)網(wǎng) /
- 搜索服務(wù) /
- 傳感器搜索 /
- 傳感器相似性計(jì)算 /
- 線性分段擬合
Abstract: The Internet of Things (IoT) is becoming a hot research area, and tens of billions of devices are being connected to the Internet which are advancing on the sensor search service. IoT features (searches are strong spatiotemporal variability, limited resources of the sensor, and mass heterogeneous dynamic data) raise a challenge to the search engines for efficiently and effectively searching and selecting the sensors. In this paper, Piecewise-Linear fitting Sensor Similarity (PLSS) search method is proposed. Based on the content values, PLSS calculates the sensor similarity models to search most similarity sensors. PLSS improves the accuracy and efficiency of search compared with FUZZY set algorithm (FUZZY) and least squares method. PLSS storage costs are at least two order of magnitude less than raw data.
- Internet of Things (IoT) /
- Search services /
- Sensor search /
- Sensor similarity computing /
- Piecewise-linear function fitting

HTML全文

圖 2 PLSS搜索流程

下載: 全尺寸圖片幻燈片

圖 1 物聯(lián)網(wǎng)基于內(nèi)容的傳感器查詢體系架構(gòu)

下載: 全尺寸圖片幻燈片

圖 3 數(shù)據(jù)分段示意圖

下載: 全尺寸圖片幻燈片

圖 4 Intel Berkeley傳感器分布圖

下載: 全尺寸圖片幻燈片

圖 5 查詢準(zhǔn)確度對比

下載: 全尺寸圖片幻燈片

圖 6 查詢速度比較

下載: 全尺寸圖片幻燈片

表 1 數(shù)據(jù)存儲開銷分析

	傳感器1	傳感器20	數(shù)據(jù)個(gè)數(shù)統(tǒng)計(jì)
原數(shù)據(jù) (時(shí)間，傳感器值)	1317×2	2059×2	6.752×10³
FUZZY算法 (傳感器平均數(shù)據(jù)密度函數(shù))	16×4×10	20×4×10	2.400×10³
FUZZY算法 (傳感器平均數(shù)據(jù)斜率密度函數(shù))	10×4×10	14×4×10	2.400×10³
最小二乘多項(xiàng)式擬合算法 (傳感器函數(shù)系數(shù))	9	9	1.800×10
PLSS算法 (傳感器函數(shù)系數(shù))	16	25	4.100×10

下載: 導(dǎo)出CSV

參考文獻(xiàn)(19)

BELLO O and ZEADALLY S. Intelligent device-to-device communication in the internet of things[J]. IEEE Systems Journal, 2016, 10(3): 1172–1182 doi: 10.1109/JSYST.2014.2298837

EVANS D. The Internet of things: How the next evolution of the internet is changing everything[C]. Cisco Internet Business Solutions Group, San Francisco, USA, 2011.

RIBEIRO M, GROLINGER K, and CAPRETZ M A M. MLaaS: Machine learning as a service[C]. 2015 IEEE 14th International Conference on Machine Learning and Applications., Miami, USA, 2015: 896–902.

LI Shancang, LI Daxu, and ZHAO Shanshan. The internet of things: A survey[J]. Information Systems Frontiers, 2015, 17(2): 243–259 doi: 10.1007/s10796-014-9492-7

張普寧. 面向物聯(lián)網(wǎng)搜索服務(wù)的實(shí)體狀態(tài)匹配估計(jì)方法研究[D]. [博士論文], 北京郵電大學(xué), 2017.

ZHANG Puning. Research on entity state matching estimation method towards search service in the internet of things[D]. [Ph.D. dissertation], Beijing University of Posts and Telecommunications, 2017.

于海寧, 張宏莉, 方濱興, 等. 物聯(lián)網(wǎng)中物理實(shí)體搜索服務(wù)的研究[J]. 電信科學(xué), 2012, 28(10): 111–119 doi: 10.3969/j.issn.1000-0801.2012.10.019

YU Haining, ZHANG Hongli, FANG Binxing, et al. Research on search service for physical entities in the internet of things[J]. Telecommunications Science, 2012, 28(10): 111–119 doi: 10.3969/j.issn.1000-0801.2012.10.019

WU Dapeng, HE Jing, WANG Hongguang, et al. A hierarchical packet forwarding mechanism for energy harvesting wireless sensor networks[J]. IEEE Communication Magazine, 2015, 53(8): 92–98 doi: 10.1109/MCOM.2015.7180514

LI Dongsheng, ZHANG Wanxin, SHEN Siqi, et al. SES-LSH: Shuffle-efficient locality sensitive hashing for distributed similarity search[C]. 2017 IEEE 24th International Conference on Web Services, Honolulu, USA, 2017: 822–827.

ZHAO Xujun, ZHANG Jifu, and QIN Xiao. kNN-DP: Handling data skewness in kNN joins using mapreduce[J].IEEE Transactions on Parallel and Distributed Systems, 2017, 29(3): 600–613 doi: 10.1109/TPDS.2017.2767596

蔣翠清, 疏得友, 段銳. 基于用戶時(shí)空相似性的位置推薦算法[J]. 計(jì)算機(jī)工程, 2018, 44(7): 177–182 doi: 10.19678/j.issn.1000-3428.0047996

JIANG Cuiqing, SHU Deyou, and DUAN Rui. Location recommendation algorithm based on spatial-temporal similarity of user[J]. Computer Engineering, 2018, 44(7): 177–182 doi: 10.19678/j.issn.1000-3428.0047996

張普寧, 劉元安, 吳帆, 等. 物聯(lián)網(wǎng)中適用于內(nèi)容搜索的實(shí)體狀態(tài)匹配預(yù)測方法[J]. 電子與信息學(xué)報(bào), 2015, 37(12): 2815–2820 doi: 10.11999/JEIT150191

ZHANG Puning, LIU Yuanan, WU Fan, et al. An entity state matching prediction method for content-based search in the internet of things[J]. Journal of Electronics&Information Technology, 2015, 37(12): 2815–2820 doi: 10.11999/JEIT150191

ELAHI B M, ROMER K, OSTERMAIER B, et al. Sensor ranking: A primitive for efficient content-based sensor search[C]. International Conference on Information Processing in Sensor Networks, San Francisco, USA, 2009: 217–228.

ROMER K, OSTERMAIER B, OSTERMAIER F, et al. Real-time search for real-world entities: A survey[J]. Proceedings of the IEEE, 2010, 98(11): 1887–1902 doi: 10.1109/JPROC.2010.2062470

ZHANG Puning, LIU Yanan, WU Fan, et al. Low-overhead and high-precision prediction model for content-based sensor search in the internet of things[J]. IEEE Communications Letters, 2016, 20(4): 720–723 doi: 10.1109/LCOMM.2016.2521735

EBRAHIMI M, SHAFIEIBAVANI E, WONG R K, et al. An adaptive meta-heuristic search for the internet of things[J]. Future Generation Computer Systems, 2017, 76(11): 486–494.

TRUONG C, ROMER K, and CHEN K. Fuzzy-based sensor search in the web of things[C]. 2012 3rd International Conference on the Internet of Things, Wuxi, China, 2012: 127–134.

ZHUKOV V and KOMAROV M. Semantic control method of the internet of things based on linked open data[C]. 2017 IEEE 19th Conference on Business Informatics, Thessaloniki, Greece, 2017: 1–4.

Intel Berkeley Research lab. Intel berkeley research lab sensors data[OL]. http://db.csail.mit.edu/labdata/labdata.html. 2004.10.

DIAS G M, BELLALTA B, and OECHSNER S. A survey about prediction-based data reduction in wireless sensor networks[J]. ACM Computing Surveys, 2016, 49(3): 58.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)