Feature Selection for Portable Spectral Sensing Data of Soil Using Broad Learning Network in Fusion With Fuzzy Technique

Urban sensing has become prevalent for monitoring dynamic urban status due to the development of intelligent computing. Fast sensing and accurate analysis of soil quality promote data-driven urban planning and management. Soil contamination hiders the sustainable development of the city's environmental ecology. Decentralized sensing based on an Internet of Things (IoTs) architecture is a state-of-art technology. Portable spectral detection serves for immediate quantitative analysis of target components. In this case, portable sensing combined with federated learning simply shares the informative features extracted from the IoT-based spectral sensing data. However, the modeling technique for the analysis of spectroscopic sensing data faces several challenges due to the emerge of the big data problem in IoT-based sceneries. The consideration of possible federal learning of multinode collective data should ask for deep studies of modeling methodologies. In this article, we built up an IoT-based portable spectral sensing system for simultaneous sensing and detecting soil data at distributed sensing places. The collaborative training model was established for dealing with the dynamic sensing data, by the fusion design of a broad learning network (BLN) and a fuzzy partial least square (fPLS) model. The BLN output feature variables are produced from the scalable pseudo input layer with training linking weights adaptively, and the number of fuzzy rules is scalable. In the experiment, the decentralized sensing system and the fusion modeling framework carry out the model optimization for the portable near-infrared (NIR) spectroscopic sensing data of heavy metals in soil samples. The quantification of two elements demonstrated that the proposed framework yielded superior prediction results to the conventional PLS model for the training and evaluation of the dynamic sensing data. In interaction with the IoT architecture, the framework is prospectively expected as an advanced intelligent technical support for fast analysis of portable spectroscopic sensing data.