Edge Mining the Internet of Things

Gaura, Elena; Brusey, James; Allen, Michael; Wilkins, Ross; Goldsmith, Daniel; Rednic, Ramona

doi:10.1109/jsen.2013.2266895

Cited by 91 publications

(54 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data prediction has been extensively studied, resulting in different techniques based on constant, linear [2], [9], [19], [20], non-linear [7] and correlation models [21]. Hung et al [22] compare representative techniques from each category according to data reduction and prediction accuracy.…”

Section: Related Workmentioning

confidence: 99%

Practical Data Prediction for Real-World Wireless Sensor Networks

Raza

Camerra

Murphy

et al. 2015

IEEE Trans. Knowl. Data Eng.

136

View full text Add to dashboard Cite

Abstract-Data prediction is proposed in wireless sensor networks (WSNs) to extend the system lifetime by enabling the sink to determine the data sampled, within some accuracy bounds, with only minimal communication from source nodes. Several theoretical studies clearly demonstrate the tremendous potential of this approach, able to suppress the vast majority of data reports at the source nodes. Nevertheless, the techniques employed are relatively complex, and their feasibility on resource-scarce WSN devices is often not ascertained. More generally, the literature lacks reports from real-world deployments, quantifying the overall system-wide lifetime improvements determined by the interplay of data prediction with the underlying network. These two aspects, feasibility and system-wide gains, are key in determining the practical usefulness of data prediction in real-world WSN applications. In this paper, we describe Derivative-Based Prediction (DBP), a novel data prediction technique much simpler than those found in the literature. Evaluation with real data sets from diverse WSN deployments shows that DBP often performs better than the competition, with data suppression rates up to 99% and good prediction accuracy. However, experiments with a real WSN in a road tunnel show that, when the network stack is taken into consideration, DBP only triples lifetime-a remarkable result per se, but a far cry from the data suppression rates above. To fully achieve the energy savings enabled by data prediction, the data and network layers must be jointly optimized. In our testbed experiments, a simple tuning of the MAC and routing stack, taking into account the operation of DBP, yields a remarkable seven-fold lifetime improvement w.r.t. the mainstream periodic reporting.

show abstract

Section: Related Workmentioning

confidence: 99%

Practical Data Prediction for Real-World Wireless Sensor Networks

Raza

Camerra

Murphy

et al. 2015

IEEE Trans. Knowl. Data Eng.

136

View full text Add to dashboard Cite

show abstract

“…After the switching frequency shifts to f 2 , assuming the duty cycle remains the same, the peak to peak current ripple is 2 2…”

Section: Shape Of the Modulated Carriermentioning

confidence: 99%

“…When the switching frequency is f 1 , the average current is i AV1 , the peak to peak current ripple is i L1 . After the switching frequency shifts to f 2 , the peak to peak current ripple is 2 2…”

Section: Shape Of the Modulated Carriermentioning

confidence: 99%

See 1 more Smart Citation

Power Conversion and Signal Transmission Integration Method Based on Dual Modulation of DC–DC Converters

Lin

et al. 2015

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

“…6 Each sensor reports (for example, to a cloud-based service via a gateway) occurrence of events within the environment rather than raw sensor readings. The sensor systematizes its historical readings using a simplistic internal representation model that is based on linear, decisiontree, or histogram representation of the readings.…”

Section: Edge Miningmentioning

confidence: 99%