Search results

This paper aims to introduce a hierarchical fuzzy system for an online review analysis named FLORA. FLORA enables tourists to decide their destination without reading numerous reviews from experienced tourists. It summarizes reviews and visualizes them through a hierarchical structure. The visualization does not only present overall quality of an accommodation, but it also presents the condition of the bed, hospitality of the front desk receptionist and much more in a snap.

FLORA is a complete system which acquires online reviews, analyzes sentiments, computes feature scores and summarizes results in a hierarchical view. FLORA is designed to use an overall score, rated by real tourists as a baseline for accuracy comparison. The accuracy of FLORA has achieved by a novel sentiment analysis process (as part of a knowledge acquisition engine) based on semantic analysis and a novel rating technique, called hierarchical fuzzy calculation, in the knowledge inference engine.

The performance comparison of FLORA against related work has been assessed in two aspects. The first aspect focuses on review analysis with binary format representation. The results reveal that the hierarchical fuzzy method, with probability weighting of FLORA, is achieved with the highest values in precision, recall and F-measure. The second aspect looks at review analysis with a five-point rating scale rating by comparing with one of the most advanced research methods, called fuzzy domain ontology. The results reveal that the hierarchical fuzzy method, with probability weighting of FLORA, returns the closest results to the tourist-defined rating.

This research advances knowledge of online review analysis by contributing a novel sentiment analysis process and a novel rating technique. The FLORA system has two limitations. First, the reviews are based on individual expression, which is an arbitrary distinction and not always grammatically correct. Consequently, some opinions may not be extracted because the context free grammar rules are insufficient. Second, natural languages evolve and diversify all the time. Many emerging words or phrases, including idioms, proverbs and slang, are often used in online reviews. Thus, those words or phrases need to be manually updated in the knowledge base.

This research contributes to the tourism business and assists travelers by introducing comprehensive and easy to understand information about each accommodation to travelers. Although the FLORA system was originally designed and tested with accommodation reviews, it can also be used with reviews of any products or services by updating data in the knowledge base. Thus, businesses, which have online reviews for their products or services, can benefit from the FLORA system.

This research proposes a FLORA system which analyzes sentiments from online reviews, computes feature scores and summarizes results in a hierarchical view. Moreover, this work is able to use the overall score, rated by real tourists, as a baseline for accuracy comparison. The main theoretical implication is a novel sentiment analysis process based on semantic analysis and a novel rating technique called hierarchical fuzzy calculation.

The aim of this paper is to explore the value preference space associated with the optimization and generalization performance of GEFeWSML.

In this paper, the authors modified the evaluation function utilized by GEFeWSML such that the weights assigned to each objective (i.e. error reduction and feature reduction) were varied. For each set of weights, GEFeWSML was used to evolve FMs for the face, periocular, and face + periocular templates. The best performing FMs on the training set (FMtss) and the best performing FMs on the validation set (FM*s) were then applied to the test set in order to evaluate how well they generalized to the unseen subjects.

By varying the weights assigned to each of the objectives, the authors were able to suggest values that would result in the best optimization and generalization performances for facial, periocular, and face + periocular recognition. GEFeWSML using these suggested values outperformed the previously reported GEFeWSML results, using significantly fewer features while achieving the same recognition accuracies statistically.

In this paper, the authors investigate the relative weighting of each objective using a value preference structure and suggest the best weights to be used for each biometric modality tested.

The presented research proposes a method aimed to improve a case retrieval phase of the case-based reasoning (CBR) system through optimization of feature relevance parameters, i.e. feature weights.

The improvement is achieved by applying the metaheuristic optimization technique, called electromagnetism-like algorithm (EM), in order to appropriately adjust the feature weights used in k-NN classifier. The usability of the proposed EM k-NN algorithm is much broader since it can also be used outside the CBR system, e.g. for solving general pattern recognition tasks.

It is showed that the proposed EM k-NN algorithm improves the baseline k-NN model and outperforms the appropriately tuned artificial neural network (ANN) in the task of predicting the case (data record) output values. The results are verified by performing statistical analysis.

The proposed method is currently adjusted to deal with numerical features, so, as a direction for future work, the variant of EM k-NN algorithm that deals with symbolic or some more complex types of features should be considered.

EM k-NN algorithm can be incorporated as a case retrieval component inside a general CBR system. This is the future direction of the investigation since the authors intend to build a complete specialized CBR system for construction project management. The overall CBR with incorporated EM k-NN will have significant implication in the construction management as it will be able to produce more accurate prediction of viability and the life cycle of new construction projects.

The electromagnetism-like algorithm is applied to the problem of finding feature weights for the first time. EM potential for solving the problem of weighting features lies in its internal structure because it is based on the real-valued EM vectors. The overall EM k-NN algorithm is applied on data sets generated from real construction projects data corpus. The proposed algorithm proved its efficiency as it outperformed baseline k-NN model and ANN. Its applicability in more complex and specialized CBR systems is high since it can be easily added due to its modular (black-box) design.

Rapid developments in social networks and their usage in everyday life have caused an explosion in the amount of short electronic documents. Thus, the need to classify this type of document based on their content has a significant implication in many applications. The need to classify these documents in relevant classes according to their text contents should be interested in many practical reasons. Short-text classification is an essential step in many applications, such as spam filtering, sentiment analysis, Twitter personalization, customer review and many other applications related to social networks. Reviews on short text and its application are limited. Thus, this paper aims to discuss the characteristics of short text, its challenges and difficulties in classification. The paper attempt to introduce all stages in principle classification, the technique used in each stage and the possible development trend in each stage.

The paper as a review of the main aspect of short-text classification. The paper is structured based on the classification task stage.

This paper discusses related issues and approaches to these problems. Further research could be conducted to address the challenges in short texts and avoid poor accuracy in classification. Problems in low performance can be solved by using optimized solutions, such as genetic algorithms that are powerful in enhancing the quality of selected features. Soft computing solution has a fuzzy logic that makes short-text problems a promising area of research.

Using a powerful short-text classification method significantly affects many applications in terms of efficiency enhancement. Current solutions still have low performance, implying the need for improvement. This paper discusses related issues and approaches to these problems.

Previous experiments demonstrated the value of relevance weighting for search terms, but relied on substantial relevance information for the terms. The present experiments were designed to study the effects of weights based on very limited relevance information, for example supplied by one or two relevant documents. The tests simulated iterative searching, as in an on‐line system, and show that even very little relevance information can be of considerable value.

The purpose of this paper is to develop an effective approach to support and guide production improvement processes utilising online product reviews.

This paper combines two methods: (1) natural language processing (NLP) to support advanced text mining to increase the accuracy of information extracted from product reviews and (2) quality function deployment (QFD) to utilise the extracted information to guide the product improvement process.

The paper proposes an approach to automate the process of obtaining voice of the customer (VOC) by performing text mining on available online product reviews while considering key factors such as the time of review and review usefulness. The paper enhances quality management processes in organisations and advances the literature on customer-oriented product improvement processes.

Online product reviews are a valuable source of information for companies to capture the true VOC. VOC is then commonly used by companies as the main input for QFD to enhance quality management and product improvement. However, this process requires considerable time, during which VOC may change, which may negatively impact the output of QFD. This paper addresses this challenge by providing an improved approach.

The purpose of this paper is to propose an approach that integrates three complementary perspectives, multi-agent systems, fuzzy logic and case-based reasoning. Unsatisfied customers, information overload and high uncertainty are the main challenges that are faced by today’s supply chains. In addition, a few existing agent-based approaches are tied to real-world supply chain functions like supplier selection. These approaches are static and do not adequately take the qualitative and quantitative factors into consideration. Therefore, an agent-based framework is needed to address these issues.

The proposed approach integrates three complementary perspectives, multi-agent systems, fuzzy logic and case-based reasoning, as a common framework. These perspectives were rarely used together as a common framework in previous studies. Furthermore, an exploratory case study in an office furniture company is undertaken to illustrate the value of the framework.

The proposed agent-based framework evaluates supply offers based on customers’ preferences, recommends alternative products in the case of stock-out and provides a collaborative environment among agents who represent different supply chain entities. The proposed fuzzy case-based reasoning (F-CBR) approach reduces the information overload by organizing them into the relevant cases that causes less overall search between cases. In addition, its fuzzy aspect addresses the high uncertainty of supply chains, especially when there are different customers’ orders with different preferences.

The present study does not include the functions of inventory management and negotiation between agents. Furthermore, only the case description and case retrieval phases of the case-based reasoning approach are investigated, and the remaining phases like case retaining, case reusing and case revising are not included in the scope of this paper.

This framework balances the interests of different supply chain structural elements where each of them is represented by a specific agent for better collaboration, decision-making and problem-solving in a multi-agent environment. In addition, the supplier selection and order gathering mechanisms are developed based on customers’ orders.

Citations have been used as a common basis to measure the academic accomplishments of scientific books. However, traditional citation analysis ignored content mining and without consideration of citation equivalence, which may lead to the decline of evaluation reliability. Hence, this paper aims to integrate multi-level citation information to conduct multi-dimensional analysis.

In this paper, books’ academic impacts were measured by integrating multi-level citation resources, including books’ citation frequencies and citation-related contents. Specifically, firstly, books’ citation frequencies were counted as the frequency-level metric. Secondly, content-level metrics were detected from multi-dimensional citation contents based on finer-grained mining, including topic extraction on the metadata and citation classification on the citation contexts. Finally, differential metric weighting methods were compared with integrate the multi-level metrics and computing books’ academic impacts.

The experimental results indicate that the integration of multiple citation resources is necessary, as it can significantly improve the comprehensiveness of the evaluation results. Meanwhile, compared with the type differences of books, disciplinary differences need more attention when evaluating the academic impacts of books.

Academic impact assessment of books via integrating multi-level citation information can provide more detailed evaluation information and cover shortcomings of methods based on single citation data. Moreover, the method proposed in this paper is publication independent, which can be used to measure other publications besides books.

Vehicle fault diagnosis is a key factor in ensuring the safe and efficient operation of the railway system. Due to the numerous vehicle categories and different fault mechanisms, there is an unbalanced fault category problem. Most of the current methods to solve this problem have complex algorithm structures, low efficiency and require prior knowledge. This study aims to propose a new method which has a simple structure and does not require any prior knowledge to achieve a fast diagnosis of unbalanced vehicle faults.

This study proposes a novel K-means with feature learning based on the feature learning K-means-improved cluster-centers selection (FKM-ICS) method, which includes the ICS and the FKM. Specifically, this study defines cluster centers approximation to select the initialized cluster centers in the ICS. This study uses improved term frequency-inverse document frequency to measure and adjust the feature word weights in each cluster, retaining the top τ feature words with the highest weight in each cluster and perform the clustering process again in the FKM. With the FKM-ICS method, clustering performance for unbalanced vehicle fault diagnosis can be significantly enhanced.

This study finds that the FKM-ICS can achieve a fast diagnosis of vehicle faults on the vehicle fault text (VFT) data set from a railway station in the 2017 (VFT) data set. The experimental results on VFT indicate the proposed method in this paper, outperforms several state-of-the-art methods.

This is the first effort to address the vehicle fault diagnostic problem and the proposed method performs effectively and efficiently. The ICS enables the FKM-ICS method to exclude the effect of outliers, solves the disadvantages of the fault text data contained a certain amount of noisy data, which effectively enhanced the method stability. The FKM enhances the distribution of feature words that discriminate between different fault categories and reduces the number of feature words to make the FKM-ICS method faster and better cluster for unbalanced vehicle fault diagnostic.

In a classroom, a support vector machines model with a linear kernel, a neural network and the k-nearest neighbors algorithm failed to detect simulated money laundering accounts generated from the Panama papers data set of the offshore leak database. This study aims to resolve this failure.

Build a graph attention network having three modules as a new money laundering detection tool. A feature extraction module encodes these input data to create a weighted graph structure. In it, directed edges and their end vertices denote financial transactions. Each directed edge has weights for storing the frequency of money transactions and other significant features. Social network metrics are features of nodes for characterizing an account’s roles in a money laundering typology. A graph attention module implements a self-attention mechanism for highlighting target nodes. A classification module further filters out such targets using the biased rectified linear unit function.

Resulted from the highlighting of nodes using a self-attention mechanism, the proposed graph attention network outperforms a Naïve Bayes classifier, the random forest method and a support vector machines model with a radial kernel in detecting money laundering accounts. The Naïve Bayes classifier produces second accurate classifications.

This paper develops a new money laundering detection tool, which outperforms existing methods. This new tool produces more accurate detections of money laundering, perfects warns of money laundering accounts or links and provides sharp efficiency in processing financial transaction records without being afraid of their amount.