Search

As a class of randomized learner model, stochastic configuration networks (SCNs) have been successfully applied in a few data analytics tasks. Given the industrial big data modeling tasks, however, the original SCNs potentially lead to excessive training time. To this end, this article extends SCNs to a hybrid parallel version, termed hybrid parallel SCNs (HPSCNs). In the hybrid parallel learning algorithm, two SCNs are synchronously constructed. The difference between the two of them is that one employs a point-incremental algorithm, and another one adopts a block-incremental algorithm. Moreover, a data parallel method is established based on a dynamic block strategy to accelerate the establishment of candidate node pool for each SCN. Additionally, this article proposes an adaptive hyperparameter adjustment method, which allows the hyperparameters in the supervisory mechanism to be automatically adjusted along with the learning process. Comparative experiments are first conducted through four large-scale benchmark datasets, followed by the fully discussion on the algorithm parameters. Finally, a practical industrial application case is made, where a grinding particle size soft sensor is developed based on HPSCN, showing the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The emergence of optical Internet of Things (optical-IoT) for sixth-generation (6G) networks has been envisaged to relieve the bandwidth congestion in the conventional radio frequency (RF) channel, and to support the ever-increasing number of smart devices. Among the plethora of device innovations deemed essential for fortifying the development, herein we report on the visible-to-near-infrared color-conversion luminescent-dyes based on lead sulphide quantum dots (PbS QDs), so as to achieve an eye-safe high-speed optical link. The solution-processed PbS QDs exhibited strong absorption in the visible range, radiative recombination lifetime of 6.4 μs, as well as high photoluminescence quantum yield of up to 88%. Our proof-of-principle demonstration based on an orthogonal frequency-division multiplexing (OFDM) modulation scheme established an infrared data transmission of 0.27 Mbit/s, readily supporting an indoor optical-IoT system, and shed light on the possibility for PbS-integrated transceivers in supporting remote access control of multiple nodes. We further envisaged that our investigations could find applications in future development of solution-processable PbS-integrated luminescent fibers, concentrators, and waveguides for high-speed optical receivers. [ABSTRACT FROM AUTHOR]