Search results

Higher energy conversion efficiency of internal combustion engine can be achieved with optimal control of unsteady in-cylinder flow fields inside a direct-injection (DI) engine. However, it remains a daunting task to predict the nonlinear and transient in-cylinder flow motion because they are highly complex which change both in space and time. Recently, machine learning methods have demonstrated great promises to infer relatively simple temporal flow field development. This paper aims to feature a physics-guided machine learning approach to realize high accuracy and generalization prediction for complex swirl-induced flow field motions.

To achieve high-fidelity time-series prediction of unsteady engine flow fields, this work features an automated machine learning framework with the following objectives: (1) The spatiotemporal physical constraint of the flow field structure is transferred to machine learning structure. (2) The ML inputs and targets are efficiently designed that ensure high model convergence with limited sets of experiments. (3) The prediction results are optimized by ensemble learning mechanism within the automated machine learning framework.

The proposed data-driven framework is proven effective in different time periods and different extent of unsteadiness of the flow dynamics, and the predicted flow fields are highly similar to the target field under various complex flow patterns. Among the described framework designs, the utilization of spatial flow field structure is the featured improvement to the time-series flow field prediction process.

The proposed flow field prediction framework could be generalized to different crank angle periods, cycles and swirl ratio conditions, which could greatly promote real-time flow control and reduce experiments on in-cylinder flow field measurement and diagnostics.

This study aims to present the cost and revenue efficiency evaluation models in data envelopment analysis in the presence of fuzzy inputs, outputs and their prices that the prices are also fuzzy. This study applies the proposed approach in the energy sector of the oil industry.

This study proposes a value-based technology according to fuzzy input-cost and revenue-output data, and based on this technology, the authors propose an approach to calculate fuzzy cost and revenue efficiency based on a directional distance function approach. These papers incorporated a decision-maker’s (DM) a priori knowledge into the fuzzy cost (revenue) efficiency analysis.

This study shows that the proposed approach obtains the components of fuzzy numbers corresponding to fuzzy cost efficiency scores in the interval [0, 1] corresponding to each of the decision-making units (DMUs). The models presented in this paper satisfies the most important properties: translation invariance, translation invariance, handle with negative data. The proposed approach obtains the fuzzy efficient targets corresponding to each DMU.

In the proposed approach, by selecting the appropriate direction vector in the model, we can incorporate preference information of the DM in the process of evaluating fuzzy cost or revenue efficiency and this shows the efficiency of the method and the advantages of the proposed model in a fully fuzzy environment.

In today’s business settings, most firms strive to closely integrate their resources and activities with those of their business partners. However, these linkages tend to create lock-in effects when changes are needed. In such situations, firms need to generate new space for action. The purpose of this paper is twofold: analysis of potential action spaces for restructuring; and examination of how action spaces can be exploited and the consequences accompanying this implementation.

Network dynamics originate from changes in the network interdependencies. This paper is focused on the role of the three dual connections – actors–activities, actors–resources and activities–resources, identified as network vectors. In the framing of the study, these network vectors are combined with managerial action expressed in terms of networking and network outcome. This framework is then used for the analysis of major restructuring of the car industries in the USA and Europe at the end of the 1900s.

This study shows that the restructuring of the car industry can be explained by modifications in the three network vectors. Managerial action through changes of the vector features generated new action space contributing to the transition of the automotive network. The key to successful exploitation of action space was interaction – with individual business partners, in triadic constellations, as well as on the network level.

This paper presents a new view of network dynamics by relying on the three network vectors. These concepts were developed in the early 1990s. This far, however, they have been used only to a limited extent.

This paper aims to study almost Ricci–Yamabe soliton in the context of certain contact metric manifolds.

The paper is designed as follows: In Section 3, a complete contact metric manifold with the Reeb vector field ξ as an eigenvector of the Ricci operator admitting almost Ricci–Yamabe soliton is considered. In Section 4, a complete K-contact manifold admits gradient Ricci–Yamabe soliton is studied. Then in Section 5, gradient almost Ricci–Yamabe soliton in non-Sasakian (k, μ)-contact metric manifold is assumed. Moreover, the obtained result is verified by constructing an example.

We prove that if the metric g admits an almost (α, β)-Ricci–Yamabe soliton with α ≠ 0 and potential vector field collinear with the Reeb vector field ξ on a complete contact metric manifold with the Reeb vector field ξ as an eigenvector of the Ricci operator, then the manifold is compact Einstein Sasakian and the potential vector field is a constant multiple of the Reeb vector field ξ. For the case of complete K-contact, we found that it is isometric to unit sphere S²ⁿ⁺¹ and in the case of (k, μ)-contact metric manifold, it is flat in three-dimension and locally isometric to Eⁿ⁺¹ × Sⁿ(4) in higher dimension.

All results are novel and generalizations of previously obtained results.

The paper proposed a fast procedure for solving the reliability-based robust design optimization (RBRDO) by modifying the RBRDO formulation and transforming it into a series of RBRDO subproblems. Then for each subproblem, the objective function, constraint function and reliability index are approximated using Taylor series expansion, and their approximate forms depend on the deterministic design vector rather than the random vector and the uncertain estimation in the inner loop of RBRDO can be avoided. In this way, it can greatly reduce the evaluation number of performance function. Lastly, the trust region method is used to manage the above sequential RBRDO subproblems for convergence.

As is known, RBRDO is nested optimization, where the outer loop updates the design vector and the inner loop estimate the uncertainties. When solving the RBRDO, a large evaluation number of performance functions are needed. Aiming at this issue, the paper proposed a fast integrated procedure for solving the RBRDO by reducing the evaluation number for the performance functions. First, it transforms the original RBRDO problem into a series of RBRDO subproblems. In each subproblem, the objective function, constraint function and reliability index caused are approximated using simple explicit functions that solely depend on the deterministic design vector rather than the random vector. In this way, the need for extensive sampling simulation in the inner loop is greatly reduced. As a result, the evaluation number for performance functions is significantly reduced, leading to a substantial reduction in computation cost. The trust region method is then employed to handle the sequential RBRDO subproblems, ensuring convergence to the optimal solutions. Finally, the engineering test and the application are presented to illustrate the effectiveness and efficiency of the proposed methods.

The paper proposes a fast procedure of solving the RBRDO can greatly reduce the evaluation number of performance function within the RBRDO and the computation cost can be saved greatly, which makes it suitable for engineering applications.

The standard deviation of the original objective function of the RBRDO is replaced by the mean and the reliability index of the original objective function, which are further approximated by using Taylor series expansion and their approximate forms depend on the deterministic design vector rather than the random vector. Moreover, the constraint functions are also approximated by using Taylor series expansion. In this way, the uncertainty estimation of the performance functions (i.e. the mean of the objective function, the constraint functions) and the reliability index of the objective function are avoided within the inner loop of the RBRDO.

The possibility function-based grey clustering model has evolved into a complete approach for dealing with uncertainty evaluation problems. Existing models still have problems with the choice dilemma of the maximum criteria and instances when the possibility function may not accurately capture the data's randomness. This study aims to propose a multi-stage skewed grey cloud clustering model that blends grey and randomness to overcome these problems.

First, the skewed grey cloud possibility (SGCP) function is defined, and its digital characteristics demonstrate that a normal cloud is a particular instance of a skewed cloud. Second, the border of the decision paradox of the maximum criterion is established. Third, using the skewed grey cloud kernel weight (SGCKW) transformation as a tool, the multi-stage skewed grey cloud clustering coefficient (SGCCC) vector is calculated and research items are clustered according to this multi-stage SGCCC vector with overall features. Finally, the multi-stage skewed grey cloud clustering model's solution steps are then provided.

The results of applying the model to the assessment of college students' capacity for innovation and entrepreneurship revealed that, in comparison to the traditional grey clustering model and the two-stage grey cloud clustering evaluation model, the proposed model's clustering results have higher identification and stability, which partially resolves the decision paradox of the maximum criterion.

Compared with current models, the proposed model in this study can dynamically depict the clustering process through multi-stage clustering, ensuring the stability and integrity of the clustering results and advancing grey system theory.

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

Aim to the limitations of grey relational analysis of interval grey number, based on the generalized greyness of interval grey number, this paper tries to construct a grey angle cosine relational degree model from the perspective of proximity and similarity.

Firstly, the algorithms of the generalized greyness of interval grey number and interval grey number vector are given, and its properties are analyzed. Then, based on the grey relational theory, the grey angle cosine relational model is proposed based on the generalized greyness of interval grey number, and the relationship between the classical cosine similarity model and the grey angle cosine relational model is analyzed. Finally, the validity of the model in this paper is illustrated by the calculation examples and an application example of related factor analysis of maize yield.

The results show that the grey angle cosine relational degree model has strict theoretical basis, convenient calculation and is easy to program, which can not only fully utilize the information of interval grey numbers but also overcome the shortcomings of greyness relational degree model. The grey angle cosine relational degree is an extended form of cosine similarity degree of real numbers. The calculation examples and the related factor analysis of maize yield show that the model proposed in this paper is feasible and valid.

The research results not only further enrich the grey system theory and method but also provide a basis for the grey relational analysis of the sequences in which the interval grey numbers coexist with the real numbers.

The paper succeeds in realizing the algorithms of the generalized greyness of interval grey number and interval grey number vector, and the grey angle cosine relational degree, which provide a new method for grey relational analysis.

Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics.

The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value.

Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared.

To the best of the author’s knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression.

Textual information about restaurants, such as online reviews and food categories, is essential for consumer purchase decisions. However, previous restaurant recommendation studies have failed to use textual information containing essential information for predicting consumer preferences effectively. This study aims to propose a novel restaurant recommendation model to effectively estimate the assessment behaviors of consumers for multiple restaurant attributes.

The authors collected 1,206,587 reviews from 25,369 consumers of 46,613 restaurants from Yelp.com. Using these data, the authors generated a consumer preference vector by combining consumer identity and online consumer reviews. Thereafter, the authors combined the restaurant identity and food categories to generate a restaurant information vector. Finally, the nonlinear interaction between the consumer preference and restaurant information vectors was learned by considering the restaurant attribute vector.

This study found that the proposed recommendation model exhibited excellent performance compared with state-of-the-art models, suggesting that combining various textual information on consumers and restaurants is a fundamental factor in determining consumer preference predictions.

To the best of the authors’ knowledge, this is the first study to develop a personalized restaurant recommendation model using textual information from real-world online restaurant platforms. This study also presents deep learning mechanisms that outperform the recommendation performance of state-of-the-art models. The results of this study can reduce the cost of exploring consumers and support effective purchasing decisions.

关于餐厅的文本信息, 如在线评论和食品分类, 对于消费者的购买决策产生至关重要。然而, 先前的餐厅推荐研究未能有效利这些文本信息去预测消费者喜好。本研究提出了一种新颖的餐厅推荐模型, 以有效估计消费者对多个餐厅属性的评估行为。

我们从 Yelp.com 收集了来自25,369名消费者对 46,613 家餐厅的 1,206,587 条评论。利用这些数据, 我们通过结合消费者身份和在线消费者评论生成了消费者偏好向量。然后, 我们结合了餐厅身份和食品分类来生成餐厅信息向量。最后, 考虑到餐厅属性向量, 本研究调查了消费者偏好和餐厅信息向量之间的非线性交互关系。

我们发现, 所提出的推荐模型相比于之前最先进的模型表现出更优秀的性能, 这表明结合消费者和餐厅的各种文本信息是预测消费者喜好的基本因素。

据我们所知, 这是第一项利用来自真实在线餐厅平台的文本信息开发个性化餐厅推荐模型的研究。本研究还提出了胜过最先进模型的深度学习机制。本研究的结果可以降低探索消费者行为的成本并支持有效的购买决策。