Search results

Improving the prediction accuracy of design time for complex products is significant for improving the accuracy of product development and control plans. The purpose of this study is to propose an intelligent pre-estimation method of design time for complex products based on v-SVM.

First, an evaluation model for designer knowledge abilities based on v-SVM is built, which considers the fuzziness and dynamics of designer knowledge abilities. Next, a pre-estimation method for the design time of complex products based on v-SVM is built. This method takes into account the impacts of designer knowledge abilities and design task characteristics on the design time. Then, an adaptive genetic algorithm is programmed to optimize the parameters in the evaluation model and the pre-estimation method. Finally, a practical application and comparative analysis of the proposed pre-estimation method is suggested to verify the validity and applicability of this research.

First, the evaluation of designer knowledge abilities is a prediction problem that is both fuzzy and multivariate time series. Second, the pre-estimation of design time is a problem that is fuzzy and multivariate. Third, the pre-estimation accuracy of the proposed method is higher when compared with traditional methods.

This paper presents an intelligent pre-estimation method of design time for complex products. Unlike previous research, the pre-estimation method takes into account the impacts of both the designer knowledge abilities and the design task characteristics on the design time.

The authors investigate the extent to which online talk can influence contemporaneous and future stock trading, especially when market news is unpresented.

The authors propose an improved sentiment formula incorporating online hype, neutral sentiment and poster reputation. In addition, they conduct event study, OLS regression analyses and probit models.

First, investors tend to be more talkative in relation to firms that are (1) smaller size, (2) more growth-like, (3) with lower prices and higher short interests and (4) of higher beta. Second, the bullish tone of investors positively affects the abnormal returns of small-capitalization stocks. However, online talk has little impact on large-capitalization stocks, except that more postings boost trading liquidity. Third, online talk predicts the presence of future news regardless of firm size, with stronger predictive power found for small-capitalization stocks.

It is of interest to practitioners and researchers to study online talk so as to better understand the trading psychology of retail investors and the effects on the stock market. Furthermore, policymakers are interested in tracking activities on stock message boards in order to prevent security fraud and protect investors' interests.

The results are robust and suggest that online talk has significant impacts on stock trading exploiting an information asymmetry. This study of stock message board posting activities helps researchers to understand whether message contents contain valuable and unique content compared with information available via more traditional media channels.

The purpose of this paper is to review the current literature in the field of tourism demand forecasting.

Published papers in the high quality journals are studied and categorized based their used forecasting method.

There is no forecasting method which can develop the best forecasts for all of the problems. Combined forecasting methods are providing better forecasts in comparison to the traditional forecasting methods.

This paper reviews the available literature from 2007 to 2017. There is not such a review available in the literature.

This study aims to describe a bibliometric analysis of recent articles addressing the applications of e- noses with particular emphasis on those dealing with fuel-related products. Documents covering the general area of e-nose research and published between 1975 and 2021 were retrieved from the Web of Science database, and peer-reviewed articles were selected and appraised according to specific descriptors and criteria.

Analyses were performed by mapping the knowledge domain using the software tools VOSviewer and RStudio. It was possible to identify the countries, research organizations, authors and disciplines that were most prolific in the area, together with the most cited articles and the most frequent keywords. A total of 3,921 articles published in peer-reviewed journals were initially retrieved but only 47 (1.19%) described fuel-related e-nose applications with original articles published in indexed journals. However, this number was reduced to 38 (0.96%) articles strictly related to the target subject.

Rigorous appraisal of these documents yielded 22 articles that could be classified into two groups, those aimed at predicting the values of key parameters and those dealing with the discrimination of samples. Most of these 22 selected articles (68.2%) were published between 2017 and 2021, but little evidence was apparent of international collaboration between researchers and institutions currently working on this topic. The strategy of switching energy systems away from fossil fuels towards low-carbon renewable technologies that has been adopted by many countries will generate substantial research opportunities in the prediction, discrimination and quantification of volatiles in biofuels using e-nose.

It is important to highlight that the greatest difficulty in using the e-nose is the interpretation of the data generated by the equipment; most studies have so far used the maximum value of the electrical resistance signal of each e-nose sensor as the only data provided by this sensor; however, from 2019 onwards, some works began to consider the entire electrical resistance curve as a data source, extracting more information from it.

This study opens a new and promising way for the effective use of e-nose as a fuel analysis instrument, as low-cost sensors can be developed for use with the new data analysis methodology, enabling the production of portable, cheaper and more reliable equipment.

This paper aims to propose an approach to automatically annotate a large corpus in Arabic dialect. This corpus is used in order to analyse sentiments of Arabic users on social medias. It focuses on the Algerian dialect, which is a sub-dialect of Maghrebi Arabic. Although Algerian is spoken by roughly 40 million speakers, few studies address the automated processing in general and the sentiment analysis in specific for Algerian.

The approach is based on the construction and use of a sentiment lexicon to automatically annotate a large corpus of Algerian text that is extracted from Facebook. Using this approach allow to significantly increase the size of the training corpus without calling the manual annotation. The annotated corpus is then vectorized using document embedding (doc2vec), which is an extension of word embeddings (word2vec). For sentiments classification, the authors used different classifiers such as support vector machines (SVM), Naive Bayes (NB) and logistic regression (LR).

The results suggest that NB and SVM classifiers generally led to the best results and MLP generally had the worst results. Further, the threshold that the authors use in selecting messages for the training set had a noticeable impact on recall and precision, with a threshold of 0.6 producing the best results. Using PV-DBOW led to slightly higher results than using PV-DM. Combining PV-DBOW and PV-DM representations led to slightly lower results than using PV-DBOW alone. The best results were obtained by the NB classifier with F1 up to 86.9 per cent.

The principal originality of this paper is to determine the right parameters for automatically annotating an Algerian dialect corpus. This annotation is based on a sentiment lexicon that was also constructed automatically.

The purpose of this study is to propose an objective and efficient method for assessing credit risk by introducing and investigating to a greater extent the applicability of credit scoring models in the Jordanian banks and to what range they can be used to achieve their strategic and business objectives.

The research methodology comprises two phases. The first phase is the model development. Three modeling techniques are used to build the scoring models, namely, logistic regression (LR), artificial neural network (NN) and support vector machine (SVM), and the best performing model is selected for next stage. The second phase is two-fold: linking the credit expert knowledge in a way that can enhance the outcomes of the scoring model and a profitability test to explore if the selected model is efficient in meeting banks’ strategic and business objectives.

The findings showed that LR model outperformed both ANN and SVM across various performance indicators. The LR model also fits best with achieving the bank’s strategic and business objectives.

To the best of the authors’ knowledge, this study is the first that applied several modeling and classification techniques for Jordanian banks and calibrated the best model in terms of its strategic and business objectives. Furthermore, credit experts’ knowledge was engaged with the scoring model to determine its efficiency and reliability against the sole use of an automated scoring model in the hope to encourage the application of credit scoring models as an advisory tool for credit decisions.

The purpose of this paper is to present a generic pipeline for Resource Description Framework (RDF) graph mining to provide a comprehensive review of each step in the knowledge discovery from data process. The authors also investigate different approaches and combinations to extract feature vectors from RDF graphs to apply the clustering and theme identification tasks.

The proposed methodology comprises four steps. First, the authors generate several graph substructures (Walks, Set of Walks, Walks with backward and Set of Walks with backward). Second, the authors build neural language models to extract numerical vectors of the generated sequences by using word embedding techniques (Word2Vec and Doc2Vec) combined with term frequency-inverse document frequency (TF-IDF). Third, the authors use the well-known K-means algorithm to cluster the RDF graph. Finally, the authors extract the most relevant rdf:type from the grouped vertices to describe the semantics of each theme by generating the labels.

The experimental evaluation on the state of the art data sets (AIFB, BGS and Conference) shows that the combination of Set of Walks-with-backward with TF-IDF and Doc2vec techniques give excellent results. In fact, the clustering results reach more than 97% and 90% in terms of purity and F-measure, respectively. Concerning the theme identification, the results show that by using the same combination, the purity and F-measure criteria reach more than 90% for all the considered data sets.

The originality of this paper lies in two aspects: first, a new machine learning pipeline for RDF data is presented; second, an efficient process to identify and extract relevant graph substructures from an RDF graph is proposed. The proposed techniques were combined with different neural language models to improve the accuracy and relevance of the obtained feature vectors that will be fed to the clustering mechanism.

The purpose of this paper is to apply state-of-the-art machine learning techniques for assessing the quality of the restaurants using restaurant inspection data. The machine learning techniques are applied to solve the real-world problems in all sphere of life. Health and food departments pay regular visits to restaurants for inspection and mark the condition of the restaurant on the basis of the inspection. These inspections consider many factors that determine the condition of the restaurants and make it possible for the authorities to classify the restaurants.

In this paper, standard machine learning techniques, support vector machines, naïve Bayes and random forest classifiers are applied to classify the critical level of the restaurants on the basis of features identified during the inspection. The importance of different factors of inspection is determined by using feature selection through the help of the minimum-redundancy-maximum-relevance and linear vector quantization feature importance methods.

The experiments are accomplished on the real-world New York City restaurant inspection data set that contains diverse inspection features. The results show that the nonlinear support vector machine achieves better accuracy than other techniques. Moreover, this research study investigates the importance of different factors of restaurant inspection and finds that inspection score and grade are significant features. The performance of the classifiers is measured by using the standard performance evaluation measures of accuracy, sensitivity and specificity.

This research uses a real-world data set of restaurant inspection that has, to the best of the authors’ knowledge, never been used previously by researchers. The findings are helpful in identifying the best restaurants and help finding the factors that are considered important in restaurant inspection. The results are also important in identifying possible biases in restaurant inspections by the authorities.