How “is” shapes “ought” for folk-biological concepts

Knowing which features are frequent among a biological kind (e.g., that most zebras have stripes) shapes people’s representations of what category members are like (e.g., that typical zebras have stripes) and normative judgments about what they ought to be like (e.g., that zebras should have stripes). In the current work, we ask if people’s inclination to explain why features are frequent is a key mechanism through which what “is” shapes beliefs about what “ought” to be. Across four studies (N = 591), we find that frequent features are often explained by appeal to feature function (e.g., that stripes are for camouflage), that functional explanations in turn shape judgments of typicality, and that functional explanations and typicality both predict normative judgments that category members ought to have functional features. We also identify the causal assumptions that license inferences from feature frequency and function, as well as the nature of the normative inferences that are drawn: by specifying an instrumental goal (e.g., camouflage), functional explanations establish a basis for normative evaluation. These findings shed light on how and why our representations of how the natural world is shape our judgments of how it ought to be.

Multipoint Optimal Minimum Entropy Deconvolution Adjusted for Automatic Fault Diagnosis of Hoist Bearing

Multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) is a powerful method that can extract the periodic characteristics of signal effectively, but this method needs to evaluate the fault cycle a priori, and moreover, the results obtained in a complex environment are easily affected by noise. These drawbacks reduce the application of MOMEDA in engineering practice greatly. In order to avoid such problems, in this paper, we propose an adaptive fault diagnosis method composed of two parts: fault information integration and extracted feature evaluation. In the first part, a Teager energy spectrum amplitude factor (T-SAF) is proposed to select the intrinsic mode function (IMF) components decomposed by ensemble empirical mode decomposition (EEMD), and a combined mode function (CMF) is proposed to further reduce the mode mixing. In the second part, the particle swarm optimization (PSO) taking fractal dimension as the objective function is employed to choose the filter length of MOMEDA, and then the feature frequency is extracted by MOMEDA from the reconstructed signal. A cyclic recognition method is proposed to appraise the extracted feature frequency, and the evaluation system based on threshold and weight coefficient removes the wrong feature frequency. Finally, the feasibility of the method is verified by simulation data, experimental signals, and on-site signals. The results show that the proposed method can effectively identify the bearing state.

A Fault Feature Extraction Method for Rolling Bearing Based on Intrinsic Time-Scale Decomposition and AR Minimum Entropy Deconvolution

It is very difficult to extract the feature frequency of the vibration signal of the rolling bearing early weak fault and in order to extract its feature frequency quickly and accurately. A method of extracting early weak fault vibration signal feature frequency of the rolling bearing by intrinsic time-scale decomposition (ITD) and autoregression (AR) minimum entropy deconvolution (MED) is proposed in this paper. Firstly, the original early weak fault vibration signal of the rolling bearing is decomposed by the ITD algorithm to proper rotations (PRs) with fault feature frequency. Then, the sample entropy value of each PR is calculated to find the largest PRs of the sample entropy. Finally, the AR-MED filtering algorithm is utilized to filter and reduce the noise of the largest PRs of the sample entropy value, and the early weak fault vibration signal feature frequency of the rolling bearing is accurately extracted. The results show that the ITD-AR-MED method can extract the early weak fault vibration signal feature frequency of the rolling bearing accurately.

Fault Diagnosis of Intershaft Bearing Using Variational Mode Decomposition with TAGA Optimization

To efficiently extract the features of aeroengine intershaft bearing faults with weak signal, the variational mode decomposition (VMD) method based on the tolerant adaptive genetic algorithm (TAGA) (TAGA-VMD) is proposed by introducing the idea of tolerance into the traditional adaptive genetic algorithm in this paper. In this method, the tolerant genetic algorithm was adopted to find the optimum empirical parameters K and α of VMD. A fault simulation experiment system of intershaft bearings was built for the inner ring fault and outer ring fault of bearings to verify the proposed TAGA-VMD method. The results show that the proposed method can effectively extract the fault feature frequency of intershaft bearings, and the error between the extracted fault feature frequency and the theoretical value of fault frequency is less than 0.1%. The efforts of this study provide one promising fault feature extraction approach for aeroengine intershaft bearing fault diagnosis with weak signal.

What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values

Online product reviews play important roles in the word-of-mouth marketing of e-commerce enterprises, but only helpful reviews actually influence customers’ purchase decisions. Current research focuses on how to predict the helpfulness of a review but lacks a thorough analysis of why it is helpful. In this paper, feature sets covering review text and context cues are firstly proposed to represent review helpfulness. Then, a set of gradient boosted trees (GBT) models is introduced, and the optimal one, which as implemented in eXtreme Gradient Boosting (XGBoost), is chosen to predict and explain review helpfulness. Specially, by including the SHAP (Shapley) values method to quantify feature contribution, this paper presents an integrated framework to better interpret why a review is helpful at both the macro and micro levels. Based on real data from Amazon.cn, this paper reveals that the number of words contributes the most to the helpfulness of reviews on headsets and is interactively influenced by features like the number of sentences or feature frequency, while feature frequency contributes the most to the helpfulness of facial cleanser reviews and is interactively influenced by the number of adjectives used in the review or the review’s entropy. Both datasets show that individual feature contributions vary from review to review, and individual joint contributions gradually decrease with the increase of feature values.