A critical challenge in prediction of material property is the accuracy of estimation for regression coefficient between the structure or process of material and its macroscopic property. One source of the estimation errors is measurement errors which commonly exist in practice. To provide guidance on the use of simple linear regression methods in measurement error modeling for prediction of material property, we investigated and compared least squares (LS) and orthogonal regression (OR) theoretically. And their applications in prediction of tensile strength for quenched and tempered steel 45 were presented as an example. OR has better performance than LS in the prediction of material property in presence of measurement errors under certain conditions.
This paper presents an optimal design process for the steering system of a forklift vehicle. An efficient procedure for minimizing the engine-induced idle vibration is developed in this study. Reciprocating unbalance and gas pressure torque as two major sources of engine excitation are studied. Using the field vibration tests and FEM analysis, the cause and characteristics of steering system’s idle vibration are recognized. So as to distribute the characteristic modes based on the optimization strategy, global sensitivity analysis of the main parameters is also carried out to achieve the optimal combination of the optimization factors. Based on all analysis above, some structure modifications for optimization are presented to control the idle vibration. The effectiveness and rationality of the improvements are also verified through experimental prototyping testing. This study also makes it possible to provide a design guideline using CAE (computer aided engineering) analysis for some other objects.
Sentiment analysis is one of the central issues in Natural Language Processing and has become more and more important in many fields. Typical sentiment analysis classifies the sentiment of sentences into several discrete classes (e.g.,positive or negative). In this paper we describe our deep learning system(combining GRU and SVM) to solve both two-, three-and five-tweet polarity classifications. We first trained a gated recurrent neural network using pre-trained word embeddings, then we extracted features from GRU layer and input these features into support vector machine to fulfill both the classification and quantification subtasks. The proposed approach achieved 37th, 19th, and 14rd places in subtasks A, B, and C, respectively.
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.