本文選題：無線傳感器網(wǎng)絡 + 傳感器部署�。� 參考：《北京郵電大學》2017年碩士論文

【摘要】：農(nóng)業(yè)是國家現(xiàn)代化的基礎,也是全面建成小康社會的重點和難點。當前我國仍處于由傳統(tǒng)農(nóng)業(yè)向現(xiàn)代農(nóng)業(yè)轉變的關鍵時期。大田狀態(tài)感知的數(shù)據(jù)量多、結構復雜,引入數(shù)據(jù)聚類方法能夠有效挖掘感知數(shù)據(jù)的內在聯(lián)系,從而為過濾冗余數(shù)據(jù)和合理優(yōu)化傳感器部署提供了可行方案。為此,本文在國家支撐計劃的支持下,針對大田狀態(tài)感知的數(shù)據(jù)冗余大和傳感器部署混疊的問題,研究融合特征距離與信息熵的大田土壤數(shù)據(jù)聚類方法,主要研究內容如下:1、面向大田作業(yè)的數(shù)據(jù)效能分析和聚類算法支撐。研究當前大田作業(yè)的空氣和土壤的特征變化情況,得到大田作業(yè)感知數(shù)據(jù)的維度和時效需求。研究藍牙、射頻、Zigbee等不同傳感器網(wǎng)絡在大田作業(yè)中的數(shù)據(jù)感知能力。分析BIRCH、STING、DENCLUE以及k-means等四種數(shù)據(jù)聚類算法的數(shù)據(jù)處理能力。2、融合特征距離與信息熵數(shù)據(jù)聚類算法。針對現(xiàn)有聚類算法的聚類簇難以確定,以及初始聚類中心敏感的問題,本文提出融合特征距離與信息熵數(shù)據(jù)聚類算法,對多維擴散的感知進行數(shù)據(jù)標準量化,降低原始數(shù)據(jù)的偏差值�；跉W式聚類因子對感知數(shù)據(jù)進行初級聚類,得到概略的聚類簇,限定數(shù)據(jù)的分類范圍�；诟怕跃垲惔�,仍需要進一步提升數(shù)據(jù)的聚類程度。針對非均勻稀疏數(shù)據(jù)的處理效果差的問題,提出融合熵增減的聚類優(yōu)化,構建基于熵增減的多目標聚類準則函數(shù),通過級聯(lián)熵增減的多目標聚類收斂方法,實現(xiàn)面向大田作業(yè)狀態(tài)感知數(shù)據(jù)的最優(yōu)聚類。通過仿真表明,融合特征距離與信息熵數(shù)據(jù)聚類算法能夠提升數(shù)據(jù)能效2.3%。3、研制特征距離與信息熵數(shù)據(jù)聚類的大田墑情監(jiān)測與預測系統(tǒng)。設計并完成大田墑情監(jiān)測與預測系統(tǒng)的總體架構、硬件架構、軟件架構和數(shù)據(jù)庫字典。基于級聯(lián)熵增減的非均勻稀疏數(shù)據(jù)聚類算法,優(yōu)化大田傳感器部署。通過搭建大田墑情監(jiān)測與預測系統(tǒng)對融合特征距離與信息熵的大田土壤數(shù)聚類方法進行測試和性能分析。利用河南長葛試驗田采集到的數(shù)據(jù)為聚類樣本進行聚類,根據(jù)聚類結果指導當?shù)氐膫鞲衅鞑渴?大田覆蓋信息度為93%,利用優(yōu)化前后的數(shù)據(jù)對大田墑情進行預測。實測數(shù)據(jù)表明,基于融合特征距離與信息熵的數(shù)據(jù)聚類方法的傳感器部署方案采集的數(shù)據(jù)對大田土壤墑情預測平均誤差為0.016。
[Abstract]:Agriculture is the foundation of national modernization and the key point and difficulty of building a well-off society in an all-round way.At present, our country is still in the key period of transition from traditional agriculture to modern agriculture.Because of the large amount of data and complex structure, the data clustering method can effectively mine the internal relationship of the perceived data, which provides a feasible scheme for filtering redundant data and optimizing the sensor deployment.Therefore, in this paper, with the support of the State support Plan, aiming at the problem of large data redundancy in field state perception and the problem of sensor deployment aliasing, a field soil data clustering method based on the fusion of feature distance and information entropy is studied.The main research contents are as follows: 1, data efficiency analysis and clustering algorithm support for field operations.The changes of air and soil characteristics of field operations were studied, and the dimension and time requirement of field job perceptual data were obtained.The data sensing ability of different sensor networks such as Bluetooth and RF Zigbee in field operation is studied.This paper analyzes the data processing ability of four data clustering algorithms, such as Birch and STINGNCLUE and k-means, and combines the feature distance and information entropy data clustering algorithm.In view of the difficulty to determine the clustering clusters of the existing clustering algorithms and the sensitivity of the initial clustering centers, this paper proposes a data clustering algorithm based on the fusion of feature distance and information entropy, which quantifies the perception of multidimensional diffusion.Reduces the deviation value of the original data.Based on the Euclidean clustering factor, the perceptual data is preliminarily clustered, and a general clustering cluster is obtained, which limits the classification range of the data.Based on the general clustering, it is necessary to further improve the clustering degree of data.Aiming at the problem of poor processing effect of non-uniform sparse data, the clustering optimization of fusion entropy increase or decrease is proposed, and the multi-objective clustering criterion function based on entropy increase and subtraction is constructed, and the multi-objective clustering convergence method based on cascade entropy increase or decrease is proposed.The optimal clustering for field job state perception data is realized.The simulation results show that the feature distance and information entropy data clustering algorithm can improve the data energy efficiency of 2.33. 3. A field soil moisture monitoring and forecasting system based on feature distance and information entropy data clustering is developed.The overall structure, hardware structure, software architecture and database dictionary of the field moisture monitoring and forecasting system are designed and completed.A nonuniform sparse data clustering algorithm based on concatenated entropy increases and decreases to optimize sensor deployment in the field.The field soil moisture monitoring and forecasting system was set up to test and analyze the performance of the field soil number clustering method which combines the characteristic distance and the information entropy.The data collected from Changge experimental field in Henan Province were used as clustering samples. According to the clustering results, the local sensor deployment was guided. The information degree of field coverage was 933. The soil moisture content was predicted by the data before and after optimization.The measured data show that the average error of soil moisture prediction based on the sensor deployment scheme based on data clustering method based on feature distance and information entropy is 0.016.
【學位授予單位】：北京郵電大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：S126;TP311.13

【相似文獻】

相關期刊論文 前3條

1 張麗娜;姜新華;那日蘇;;基于改進的ISODATA算法的大樣本數(shù)據(jù)聚類方法研究[J];內蒙古農(nóng)業(yè)大學學報(自然科學版);2013年01期

2 汪雪紅;焦清局;常盼盼;黃繼風;;基于最小編碼長度的基因數(shù)據(jù)聚類(英文)[J];Agricultural Science & Technology;2012年06期

3 汪雪紅;焦清局;常盼盼;黃繼風;;基于最小編碼長度的基因數(shù)據(jù)聚類[J];安徽農(nóng)業(yè)科學;2012年19期

相關會議論文 前6條

1 武森;張桂瓊;王瑩;吳玲玉;;容差集合差異度高維不完備數(shù)據(jù)聚類[A];第十二屆中國管理科學學術年會論文集[C];2010年

2 吳繼兵;李心科;;基于分治融合的混合屬性數(shù)據(jù)聚類算法研究[A];全國第20屆計算機技術與應用學術會議(CACIS·2009)暨全國第1屆安全關鍵技術與應用學術會議論文集（下冊）[C];2009年

3 高學東;周磊;;Web點擊流數(shù)據(jù)聚類算法[A];全國第十屆企業(yè)信息化與工業(yè)工程學術年會論文集[C];2006年

4 陶紅霞;車建華;劉國華;;基于聚類的個性化推薦算法[A];2005年全國理論計算機科學學術年會論文集[C];2005年

5 王琳;羅可;羅永紅;;一種基于混合的IGA & PSO的數(shù)據(jù)聚類算法[A];2008'中國信息技術與應用學術論壇論文集（二）[C];2008年

6 武森;高學東;;高維稀疏數(shù)據(jù)聚類的CABOSFV算法[A];第七屆北京青年科技論文評選獲獎論文集[C];2003年

相關博士學位論文 前4條

1 程媛;多關系數(shù)據(jù)聚類算法及其應用研究[D];哈爾濱工程大學;2014年

2 白天;生物醫(yī)學數(shù)據(jù)聚類方法研究[D];吉林大學;2012年

3 彭柳青;高維高噪聲數(shù)據(jù)聚類中關鍵問題研究[D];西安電子科技大學;2011年

4 孫志偉;空間數(shù)據(jù)聚類的研究[D];天津大學;2007年

相關碩士學位論文 前10條

1 谷云霞;融合特征距離與信息熵的大田土壤數(shù)據(jù)聚類方法[D];北京郵電大學;2017年

2 李凱;基于網(wǎng)絡優(yōu)化最小樹的大數(shù)據(jù)聚類分析研究[D];蘭州大學;2015年

3 楊果利;基于模糊聚類的大規(guī)模數(shù)據(jù)聚類算法及其應用研究[D];西安電子科技大學;2014年

4 宋翰瀛;基于C-MDP的決策優(yōu)化系統(tǒng)的設計與實現(xiàn)[D];南京大學;2014年

5 曹陽;基于復雜網(wǎng)絡的網(wǎng)絡大數(shù)據(jù)聚類應用研究[D];蘭州交通大學;2016年

6 譚佳;高維分類數(shù)據(jù)聚類方法研究與實現(xiàn)[D];東華大學;2017年

7 王建新;符號型數(shù)據(jù)聚類算法的研究[D];山西大學;2016年

8 王_g欣;有標簽的數(shù)據(jù)聚類算法[D];天津工業(yè)大學;2017年

9 羅陽;基于大數(shù)據(jù)處理的森林生態(tài)站數(shù)據(jù)聚類研究[D];北京林業(yè)大學;2016年

10 張小宇;基于圖論的符號型數(shù)據(jù)聚類算法研究[D];山西大學;2009年

，

本文編號：1739763