In this study, multilayer perceptron artificial neural networks are used to predict orthodontic treatment plans, including the determination of extraction-nonextraction, extraction patterns, and anchorage patterns. The neural network can output the feasibilities of several applicable treatment plans, offering orthodontists flexibility in making decisions. The neural network models show an accuracy of 94.0% for extraction-nonextraction prediction, with an area under the curve (AUC) of 0.982, a sensitivity of 94.6%, and a specificity of 93.8%. The accuracies of the extraction patterns and anchorage patterns are 84.2% and 92.8%, respectively. The most important features for prediction of the neural networks are “crowding, upper arch” “ANB” and “curve of Spee”. For handling discrete input features with missing data, the average value method has a better complement performance than the k-nearest neighbors (k-NN) method; for handling continuous features with missing data, k-NN performs better than the other methods most of the time. These results indicate that the proposed method based on artificial neural networks can provide good guidance for orthodontic treatment planning for less-experienced orthodontists.
The Bayesian network (BN) is an efficient tool for probabilistic modeling and causal inference, and it has gained considerable attentions in the field of reliability assessment. The common cause failure (CCF) is simultaneous failure of multiple elements in a system under a common cause, and it is a common phenomenon in engineering systems with dependent elements. Several models and methods have been proposed for modeling and assessment of complex systems with CCF. In this paper, a new reliability assessment method is proposed for the systems suffering from CCF in a dynamic environment. The CCF among components is characterized by a BN, which allows for bidirectional reasoning. A proportional hazards model is applied to capture the dynamic working environment of components and then the reliability function of the system is obtained. The proposed method is validated through an illustrative example, and some comparative studies are also presented.
Terahertz technology is a hotspot in the current academic research. In this study, a 400 GHz broadband multi‐branch waveguide hybrid coupler is designed, but it is very difficult to fabricate. In order to release the processing difficulty, a modified five‐branch hybrid coupler has also been designed, fabricated and measured. The hybrid coupler consists of five modified branches and has been optimised to a great performance, which increases the operation bandwidth. Compared to the traditional five‐branch hybrid coupler design, this structure has a wider operation bandwidth and the bandwidth is almost the same as traditional seven‐branch hybrid coupler. Based on this model, the performance of the coupler is optimised by HFSS software. The measurement results show good performance that >18 dB return loss (S11) and isolation (S23), 90° ± 2° phase difference and 0.3 dB amplitude imbalance are obtained in the frequency range of 380–460 GHz, agreeing well with the simulation results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.