Baseline correction using a deep-learning model combining ResNet and UNet.

Most spectral data, such as those obtained via infrared, Raman, and mass spectroscopy, have baseline drifts due to fluorescence or other reasons, which have an adverse impact on subsequent analyses. Therefore, several researchers have proposed the use of various baseline-correction methods to address the aforementioned issue. However, most baseline-correction methods require manual adjustment of the parameters to achieve desirable performance. In this study, we propose a baseline-correction method based on a deep-learning model that combines ResNet and UNet. The method uses a deep-learning model trained with simulated spectral data to perform baseline corrections and eliminates the need for manual parameter adjustments. Based on the results of the qualitative and quantitative analyses of the simulated spectral data and actual Raman spectra, the proposed method is easier to apply and has better performance compared to the existing methods. As the proposed method can be applied to Raman spectra and other spectra, it is expected to be widely used.

Energy-Efficient Cluster Management Using a Mobile Charger for Solar-Powered Wireless Sensor Networks.

In solar-powered wireless sensor networks (SP-WSNs), sensor nodes can continuously harvest energy to relieve the energy constraint problem in battery-powered WSNs. With the advent of wireless power transmission (WPT) technology, the nodes can be charged remotely if the energy harvested is insufficient. However, even in SP-WSNs with WPT, an energy imbalance problem is observed, in which the energy consumption of the nodes around a sink node increases abnormally if the sink node is stationary. To solve this problem, recent studies have been conducted using a mobile sink node instead of a stationary one. Generally, a clustering scheme is used for the efficient utilization of a mobile sink. However, even in the case of mobile sinks, it is still necessary to minimize the energy burden of the cluster heads and their surrounding nodes. In this study, we propose a scheme that mitigates the energy imbalance problem of SP-WSNs by using a WPT-capable mobile sink and an efficient clustering scheme. In the proposed scheme, the energy imbalance is minimized by electing the cluster heads effectively after considering the energy state of the nodes, and by enabling the sink node to charge the energy of the cluster heads while collecting data from them. Consequently, this scheme allows the sink node to collect more data with fewer blackouts of the sensor nodes.