The Node Deployment of Intelligent Sensor Networks Based on the Spatial Difference of Farmland Soil

Abstract

Considering that agricultural production is characterized by vast areas, scattered fields and long crop growth cycles, intelligent wireless sensor networks (WSNs) are suitable for monitoring crop growth information. Cost and coverage are the most key indexes for WSN applications. The differences in crop conditions are influenced by the spatial distribution of soil nutrients. If the nutrients are distributed evenly, the crop conditions are expected to be approximately uniform with little difference; on the contrary, there will be great differences in crop conditions. In accordance with the differences in the spatial distribution of soil information in farmland, fuzzy c-means clustering was applied to divide the farmland into several areas, where the soil fertility of each area is nearly uniform. Then the crop growth information in the area could be monitored with complete coverage by deploying a sensor node there, which could greatly decrease the deployed sensor nodes. Moreover, in order to accurately judge the optimal cluster number of fuzzy c-means clustering, a discriminant function for Normalized Intra-Cluster Coefficient of Variation (NICCV) was established. The sensitivity analysis indicates that NICCV is insensitive to the fuzzy weighting exponent, but it shows a strong sensitivity to the number of clusters.

Node Deployment with k-Connectivity in Sensor Networks for Crop Information Full Coverage Monitoring

“…Real-time, large-scale assessment of crop conditions is conducive to precise control of crop growth and development [1,2,3,4]. It has important guiding significance in increasing production and improving crop quality.…”

“…With the development of quantitative spectral analysis techniques, the relationships between crop canopy reflectance spectra and crop growth information have been assessed [8,9,10], and the monitoring models of different crop information such as yield, biomass, nitrogen content, and chlorophyll a content were constructed based on crop spectra [11,12,13,14,15,16]. The development of spectrum monitoring technology for crop growth information promotes the development of crop sensors and portable crop growth monitors [17,18,19,20,21], thus providing an effective means of obtaining crop growth information in real time, using sensors installed in wireless sensor networks (WSNs), intelligent agricultural machinery, and unmanned aerial vehicles (UAVs) [2,22,23,24,25,26]. Agricultural production covers broad areas, highly variegated field information spaces, and long crop cycles, which increases the difficulty of obtaining crop information in real time.…”

“…Bauer et al integrated photosynthetically active radiation (PAR) sensors into WSNs to achieve in-situ measurement of crop leaf area index, and the measurement accuracy was closely correlated with LAI-2200 measurements [22]. Liu et al used WSN equipped with spectral sensors to monitor the growth information of rice and wheat [2]. …”

“…Due to temporal and spatial differences in crop growth information, therefore, the primary issue in crop WSN deployment should be to fully access crop information. According to the correlation between crop growth and farmland soil, Liu et al used differences in the spatial distribution of soil nutrients to divide large-scale farmland into subsections [2]. After division, soil nutrients within each divided subsection were similar, so deploying one crop sensor per field allowed full coverage monitoring of crop information, which breaks the blindness of farmland sensor node deployment and greatly reduces its cost.…”

Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design

“…The K - means (KM) and fuzzy clustering algorithms, e.g., fuzzy K - means (FKM), have been used in a wide range of scenarios and applications, such as: digital soil pattern recognition [32], archaeology [33], indoor localization [34], discrimination of cabernet sauvignon grapevine elements [35], white blood cell segmentation [36], abnormal lung sounds diagnosis [37], intelligent sensor networks in agriculture [38], magnetic resonance image (MRI) segmentation [39,40], speaker recognition [41] and image compression by VQ [29,42,43]. …”