A Multilayer Perceptron-Based Impulsive Noise Detector with Application to Power-Line-Based Sensor Networks
KAUST DepartmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
Permanent link to this recordhttp://hdl.handle.net/10754/627597
MetadataShow full item record
AbstractFor power-line-based sensor networks, impulsive noise (IN) will dramatically degrade the data transmission rate in the power line. In this paper, we present a multilayer perceptron (MLP)-based approach to detect IN in orthogonal frequency-division multiplexing (OFDM)-based baseband power line communications (PLCs). Combining the MLP-based IN detection method with the outlier detection theory allows more accurate identification of the harmful residual IN. For OFDM-based PLC systems, the high peak-to-average power ratio (PAPR) of the received signal makes detection of harmful residual IN more challenging. The detection mechanism works in an iterative receiver that contains a pre-IN mitigation and a post-IN mitigation. The pre-IN mitigation is meant to null the stronger portion of IN, while the post-IN mitigation suppresses the residual portion of IN using an iterative process. Compared with previously reported IN detectors, the simulation results show that our MLP-based IN detector improves the resulting bit error rate (BER) performance.
CitationChien Y-R, Chen J-W, Xu SS-D (2018) A Multilayer Perceptron-Based Impulsive Noise Detector with Application to Power-Line-Based Sensor Networks. IEEE Access: 1–1. Available: http://dx.doi.org/10.1109/ACCESS.2018.2825239.
SponsorsThis work was supported in part by the Ministry of Science and Technology (MOST), Taiwan, under the Grants MOST 103-2221-E-197-010 and MOST 106-2221-E-011-083.