Search

This paper presents a new learning-based framework to jointly solve equalization and symbol detection problems in orthogonal frequency division multiplexing systems with quadrature amplitude modulation. The framework utilizes extreme learning machine (ELM), a recent addition to the class of supervised learning algorithms, to achieve fast training, high performance, and low error rates. The proposed ELM scheme employs infinitely differentiable nonlinear activation functions in least-square solution to learn the channel response, which is the equalization part. In addition to equalization, ELM performs symbol detection. Existing learning-based schemes require an additional symbol slicer for the symbol detection. The proposed framework does not experience training bottleneck imposed by gradient descent-based approaches. Simulation results show that the proposed framework outperforms other learning-based equalizers in terms of symbol error rate and training speeds. [ABSTRACT FROM AUTHOR]

IEEE 802.15.4, commonly known as ZigBee, is a Media Access Control (MAC) and physical layer standard specifically designed for short range wireless communication where low rate, low power, and low bandwidth are required. This makes ZigBee an ideal choice when it comes to sensor networks for monitoring data collection and/or triggering process responses. However, these very characteristics bring into question ZigBee's ability to perform reliably in harsh environments. This paper thoroughly explains the experimental testbed setup and execution to demonstrate ZigBee's performance in several practical applications. This testbed is capable of measuring the minimum, maximum, and average received signal strength indicator (RSSI), bit error rate (BER), packet error rate (PER), packet loss rate (PLR), and the bit error locations. Results show that ZigBee has the potential capabilities to be used in all four tested environments. [ABSTRACT FROM AUTHOR]