Search results

The purpose of this paper extends the authors’ previous contributions on aircraft system identification, such as open loop identification or closed loop identification, to cascade system identification. Because the cascade system is one special network system, existing in lots of practical engineers, more unknown systems are needed to identify simultaneously within the statistical environment with the probabilistic noises. Consider this problem of cascade system identification, prediction error method is proposed to identify three unknown systems, which are parameterized by three unknown parameter vectors. Then the cascade system identification is transferred as one parameter identification problem, being solved by the online subgradient descent algorithm. Furthermore, the nonparametric estimation is proposed to consider the general case without any parameterized process. To make up the identification mission, model validation process is given to show the asymptotic interval of the identified parameter. Finally, simulation example confirms the proposed theoretical results.

Firstly, aircraft system identification is reviewed through the understanding about system identification and advances in control theory, then cascade system identification is introduced to be one special network system. Secondly, for the problem of cascade system identification, prediction error method and online subgradient decent algorithm are combined together to identify the cascade system with the parameterized systems. Thirdly from the point of more general completeness, another way is proposed to identify the nonparametric estimation, then model validation process is added to complete the whole identification mission.

This cascade system corresponds to one network system, existing in lots of practice, such as aircraft, ship and robot, so it is necessary to identify this cascade system, paving a way for latter network system identification. Parametric and nonparametric estimations are all studied within the statistical environment. Then research on bounded noise is an ongoing work.

To the best of the authors’ knowledge, research on aircraft system identification only concern on open loop and closed loop system identification, no any identification results about network system identification. This paper considers cascade system identification, being one special case on network system identification, so this paper paves a basic way for latter more advanced system identification and control theory.

Motivated by a problem in the context of DiDi Travel, the biggest taxi hailing platform in China, the purpose of this paper is to propose a novel facility location problem, specifically, the single source capacitated facility location problem with regional demand and time constraints, to help improve overall transportation efficiency and cost.

This study develops a mathematical programming model, considering regional demand and time constraints. A novel two-stage neighborhood search heuristic algorithm is proposed and applied to solve instances based on data sets published by DiDi Travel.

The results of this study show that the model is adequate since new characteristics of demand can be deduced from large vehicle trajectory data sets. The proposed algorithm is effective and efficient on small and medium as well as large instances. The research also solves and presents a real instance in the urban area of Chengdu, China, with up to 30 facilities and demand deduced from 16m taxi trajectory data records covering around 16,000 drivers.

This study examines an offline and single-period case of the problem. It does not consider multi-period or online cases with uncertainties, where decision makers need to dynamically remove out-of-service stations and add other stations to the selected group.

Prior studies have been quite limited. They have not yet considered demand in the form of vehicle trajectory data in facility location problems. This study takes into account new characteristics of demand, regional and time constrained, and proposes a new variant and its solution approach.

The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.

The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications” is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.

Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.

The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.

The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.

The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.

Course recommendations are important for improving learner satisfaction and reducing dropout rates on massive open online course (MOOC) platforms. This study aims to propose an interpretable method of analyzing students' learning behaviors and recommending MOOCs by integrating multiple data sources.

The study proposes a deep learning method of recommending MOOCs to students based on a multi-attention mechanism comprising learning records attention, word-level review attention, sentence-level review attention and course description attention. The proposed model is validated using real-world data consisting of the learning records of 6,628 students for 1,789 courses and 65,155 reviews.

The main contribution of this study is its exploration of multiple unstructured information using the proposed multi-attention network model. It provides an interpretable strategy for analyzing students' learning behaviors and conducting personalized MOOC recommendations.

The findings suggest that MOOC platforms must fully utilize the information implied in course reviews to extract personalized learning preferences.

This study is the first attempt to recommend MOOCs by exploring students' preferences in course reviews. The proposed multi-attention mechanism improves the interpretability of MOOC recommendations.

The purpose of this paper is twofold: first to carry out a comprehensive literature review for state of the art regarding airline schedule planning and second to identify some new research directions that might help academic researchers and practitioners.

The authors mainly focus on the research work appeared in the last three decades. The search process was conducted in database searches using four keywords: “Flight scheduling,” “Fleet assignment,” “Aircraft maintenance routing” (AMR), and “Crew scheduling”. Moreover, the combination of the keywords was used to find the integrated models. Any duplications due to database variety and the articles that were written in non-English language were discarded.

The authors studied 106 research papers and categorized them into five categories. In addition, according to the model features, subcategories were further identified. Moreover, after discussing up-to-date research work, the authors suggested some future directions in order to contribute to the existing literature.

The presented categories and subcategories were based on the model characteristics rather than the model formulation and solution methodology that are commonly used in the literature. One advantage of this classification is that it might help scholars to deeply understand the main variation between the models. On the other hand, identifying future research opportunities should help academic researchers and practitioners to develop new models and improve the performance of the existing models.

This study proposed some considerations in order to enhance the efficiency of the schedule planning process practically, for example, using the dynamic Stackelberg game strategy for market competition in flight scheduling, considering re-fleeting mechanism under heterogeneous fleet for fleet assignment, and considering the stochastic departure and arrival times for AMR.

In the literature, all the review papers focused only on one category of the five categories. Then, this category was classified according to the model formulation and solution methodology. However, in this work, the authors attempted to propose a comprehensive review for all categories for the first time and develop new classifications for each category. The proposed classifications are hence novel and significant.

This study proposes an approach to solve the fundamental problem in using query-based methods (i.e. searching engines and patent retrieval tools) to screen patents of information and communication technology in construction (ICTC). The fundamental problem is that ICTC incorporates various techniques and thus cannot be simply represented by man-made queries. To investigate this concern, this study develops a binary classifier by utilizing deep learning and NLP techniques to automatically identify whether a patent is relevant to ICTC, thus accurately screening a corpus of ICTC patents.

This study employs NLP techniques to convert the textual data of patents into numerical vectors. Then, a supervised deep learning model is developed to learn the relations between the input vectors and outputs.

The validation results indicate that (1) the proposed approach has a better performance in screening ICTC patents than traditional machine learning methods; (2) besides the United States Patent and Trademark Office (USPTO) that provides structured and well-written patents, the approach could also accurately screen patents form Derwent Innovations Index (DIX), in which patents are written in different genres.

This study contributes a specific collection for ICTC patents, which is not provided by the patent offices.

The proposed approach contributes an alternative manner in gathering a corpus of patents for domains like ICTC that neither exists as a searchable classification in patent offices, nor is accurately represented by man-made queries.

A deep learning model with two layers of neurons is developed to learn the non-linear relations between the input features and outputs providing better performance than traditional machine learning models. This study uses advanced NLP techniques lemmatization and part-of-speech POS to process textual data of ICTC patents. This study contributes specific collection for ICTC patents which is not provided by the patent offices.

The purpose of the paper is to improve the rating prediction accuracy in recommender systems (RSs) by metric learning (ML) method. The similarity metric of user and item is calculated with gray relational analysis.

First, the potential features of users and items are captured by exploiting ML, such that the rating prediction can be performed. In metric space, the user and item positions can be learned by training their embedding vectors. Second, instead of the traditional distance measurements, the gray relational analysis is employed in the evaluation of the position similarity between user and item, because the latter can reduce the impact of data sparsity and further explore the rating data correlation. On the basis of the above improvements, a new rating prediction algorithm is proposed. Experiments are implemented to validate the effectiveness of the algorithm.

The novel algorithm is evaluated by the extensive experiments on two real-world datasets. Experimental results demonstrate that the proposed model achieves remarkable performance on the rating prediction task.

The rating prediction algorithm is adopted to predict the users' preference, and then, it provides personalized recommendations for users. In fact, this method can expand to the field of classification and provide potentials for this domain.

The algorithm can uncover the finer grained preference by ML. Furthermore, the similarity can be measured using gray relational analysis, which can mitigate the limitation of data sparsity.