• Feature selection and classification of noisy proteomics mass spectrometry data based on one-bit perturbed compressed sensing

    14 days ago - By Oxford Journals

    AbstractMotivationThe classification of high-throughput protein data based on mass spectrometry is of great practical significance in medical diagnosis. Generally, MS data is characterized by high dimension, which inevitably leads to prohibitive cost of computation. To solve this problem, one-bit compressed sensing , which is an extreme case of quantized CS, has been employed on MS data to select important features with low dimension. Though enjoying remarkably reduction of computation complexity, the current one-bit CS method does not consider the unavoidable noise contained in MS...
    Read more ...

     

  • Grey Wolf based compressive sensing scheme for data gathering in IoT based heterogeneous WSNs

    15 days ago - By Springer

    Abstract
    Sensor node energy constraint is considered as an impediment in the further development of the Internet of Things technology. One of the most efficient solution is to combine between compressive sensing and routing techniques. However, this combination faces many challenges that makes it an attractive point for research. This paper proposes an Efficient Multi-hop Cluster-based Aggregation scheme using Hybrid CS for IoT based heterogeneous wireless sensor networks. EMCA-CS efficiently combines between CS and routing protocols to extend the network lifetime and reduces the...
    Read more ...