Training Data Compression Algorithms and Reliability in Large Wireless Sensor Networks

Abstract

With the availability of low-cost sensor nodes there have been many standards developed to integrate and network these nodes to form a reliable network allowing many different types of hardware vendors to coexist. Most of these solutions however have aimed at industry-specific interoperability but not the size of the sensor network and the large amount of data which is collected in course of its lifetime. In this paper we use well studied data compression algorithms which optimize on bringing down the data redundancy which is related to correlated sensor readings and using a probability model to efficiently compress data at the cluster heads. As in the case of sensor networks the data reliability goes down as the network resource depletes and these types of networks lacks any central synchronization making it even more a global problem to compare different reading at the central coordinator. The complexity of calibrating each sensor and using an adaptable measured threshold to correct the reading from sensors is a severe drain in terms of network resources and energy consumption. In this paper we separate the task of comparative global analysis to a central coordinator and use a reference PMax which is a normalized probability of individual source which reflects the current lifetime reliability of the sensors calculated at the cluster heads which then is compared with the current global reliability index based on all the PMax of cluster heads. As this implementation does not need any synchronization at the local nodes it uses compress once and stamp locally without any threshold such as application specific calibration values (30 o C) and the summarization can be application independent making it more a sensor network reliability index and using it independent of the actual measured values.

Ensemble stream model for data-cleaning in sensor networks

“…A comparison metric (Iyer et al, 2008g) is used by classification algorithms let it be similarity based or discriminative model. In a probability model or when learning weights are in a neural network, the total sum of probabilities must be equal to 1.…”

“…A OMNET mobility framework simulator, using interference modeling as derived in Section IV and Table 9.3. We use two models to analyze the data collected from the mobility simulator, one uses the covariance technique (Kumar et al, 2008), (Iyer et al, 2008g) to optimize as shown in equation (9.12), when not too much of co-channel interference is seen. The second (Duda et al, 2000), which de-correlates under the presence of heavy co-channel interference.…”

“…So each cluster head has a unique P M ax but not all cluster heads have the same measured value. If the cluster size in n, from the cluster equation (Iyer et al, 2008g) then the entropy of data aggregation…”

Compression in wireless sensor networks

“…Given the limited number of publications on the topic [Iyer et al 2008;Marco and Neuho↵ 2004], there is clearly significant scope for future work in this area.…”

Industrial Robot Calibration Using a Virtual Linear Constraint

“…The calibration experiment was performed on a real IRB120 robot as shown in Figure 3. The locations of laser spot at both PSDs were wirelessly [20,21] transferred to the computer.…”