Ruijian Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruijian Cheng has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Xu Sun
Institute of Applied Physics, Jiangxi Academy of Sciences, Nanchang 330096, China
2 shared publications - Hui Guo
Jiangxi Academy of Sciences
1 shared publication - Jiang Wei
Institute of Applied Physics, Jiangxi Academy of Sciences, Nanchang 330095, China
1 shared publication - Jiang Wei
Institute of Applied Physics, Jiangxi Academy of Sciences, Nanchang 330096, China
1 shared publication - Mengcheng Guan
Institute of Applied Physics, Jiangxi Academy of Sciences, Nanchang 330095, China
1 shared publication - Qi Liu
Institute of Energy Research, Jiangxi Academy of Sciences, Nanchang 330096, China
1 shared publication
Latest Publications
- Open Access
- 21 October 2025
- Published by MDPI AG in Applied System Innovation
- Vol. 8 (5) , 157
Switch Cabinet Temperature Prediction Using a Fusion of CNN and LSTM Neural Networks
This study investigates the effectiveness of a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) model for predicting the temperature of switchgear within electrical power systems. Given the critical importance of temperature monitoring for operational safety and stability, this research integrates CNNs and LSTMs to leverage their respective strengths in spatial feature extraction and temporal data processing. Utilizing a dataset from 2020 comprising hourly data points along with comprehensive environmental and operational variables, the model aims to deliver precise temperature predictions. Initial results indicate a high level of accuracy, with the CNN-LSTM model achieving an score of 0.95 and a mean absolute error of 0.12 °C, highlighting its significant potential to enhance the monitoring and management of safety in power systems.- 21 October 2025
- Published by MDPI AG in Applied System Innovation
- Vol. 8 (5) , 157
Open AccessSwitch Cabinet Temperature Prediction Using a Fusion of CNN and LSTM Neural Networks
This study investigates the effectiveness of a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) model for predicting the temperature of switchgear within electrical power systems. Given the critical importance of temperature monitoring for operational safety and stability, this research integrates CNNs and LSTMs to leverage their respective strengths in spatial feature extraction and temporal data processing. Utilizing a dataset from 2020 comprising hourly data points along with comprehensive environmental and operational variables, the model aims to deliver precise temperature predictions. Initial results indicate a high level of accuracy, with the CNN-LSTM model achieving an score of 0.95 and a mean absolute error of 0.12 °C, highlighting its significant potential to enhance the monitoring and management of safety in power systems. - Open Access
High-Sensitivity Terahertz Biosensor Based on Plasmon-Induced Transparency Metamaterials
This paper presents a metamaterial biosensor composed of dual-cut wires (DCWs) and quadruple split-ring resonators (QSRs), achieving polarization-independent plasmon-induced transparency (PIT) effects in the terahertz range. By leveraging the coupling between bright and dark modes, we observe a transparent window with a minimal loss at 1.22 THz. We investigate the physical mechanism of the PIT effect by analyzing the surface current distribution and electric fields. Simulations reveal that the PIT transparency shows a peak shift of up to 146.7 GHz with an analyte thickness of 14 μm. Moreover, as the refractive index of the analyte increases from 1.0 to 1.6, the biosensor’s theoretical sensitivity is calculated to be 281.25 GHz/RIU. Furthermore, we explore the application of the proposed DCW/QSR biosensor for the detection of bacteriophage viruses. Our simulation results demonstrate that the DCW/QSR biosensor serves as an effective sensing platform for detecting viruses such as PRD1 and MS2. These findings underscore the potential of our high-sensitivity metamaterial biosensor, which holds great promise in the field of biosensing, offering a practical and cost-effective approach to label-free biomedical detection.
Open AccessHigh-Sensitivity Terahertz Biosensor Based on Plasmon-Induced Transparency Metamaterials
This paper presents a metamaterial biosensor composed of dual-cut wires (DCWs) and quadruple split-ring resonators (QSRs), achieving polarization-independent plasmon-induced transparency (PIT) effects in the terahertz range. By leveraging the coupling between bright and dark modes, we observe a transparent window with a minimal loss at 1.22 THz. We investigate the physical mechanism of the PIT effect by analyzing the surface current distribution and electric fields. Simulations reveal that the PIT transparency shows a peak shift of up to 146.7 GHz with an analyte thickness of 14 μm. Moreover, as the refractive index of the analyte increases from 1.0 to 1.6, the biosensor’s theoretical sensitivity is calculated to be 281.25 GHz/RIU. Furthermore, we explore the application of the proposed DCW/QSR biosensor for the detection of bacteriophage viruses. Our simulation results demonstrate that the DCW/QSR biosensor serves as an effective sensing platform for detecting viruses such as PRD1 and MS2. These findings underscore the potential of our high-sensitivity metamaterial biosensor, which holds great promise in the field of biosensing, offering a practical and cost-effective approach to label-free biomedical detection.