Search results

To be sustainable and competitive in the current business environment, it is useful to understand users’ sentiment towards products and services. This critical task can be achieved via natural language processing and machine learning classifiers. This paper aims to propose a novel probabilistic committee selection classifier (PCC) to analyse and classify the sentiment polarities of movie reviews.

An Indian movie review corpus is assembled for this study. Another publicly available movie review polarity corpus is also involved with regard to validating the results. The greedy stepwise search method is used to extract the features/words of the reviews. The performance of the proposed classifier is measured using different metrics, such as F-measure, false positive rate, receiver operating characteristic (ROC) curve and training time. Further, the proposed classifier is compared with other popular machine-learning classifiers, such as Bayesian, Naïve Bayes, Decision Tree (J48), Support Vector Machine and Random Forest.

The results of this study show that the proposed classifier is good at predicting the positive or negative polarity of movie reviews. Its performance accuracy and the value of the ROC curve of the PCC is found to be the most suitable of all other classifiers tested in this study. This classifier is also found to be efficient at identifying positive sentiments of reviews, where it gives low false positive rates for both the Indian Movie Review and Review Polarity corpora used in this study. The training time of the proposed classifier is found to be slightly higher than that of Bayesian, Naïve Bayes and J48.

Only movie review sentiments written in English are considered. In addition, the proposed committee selection classifier is prepared only using the committee of probabilistic classifiers; however, other classifier committees can also be built, tested and compared with the present experiment scenario.

In this paper, a novel probabilistic approach is proposed and used for classifying movie reviews, and is found to be highly effective in comparison with other state-of-the-art classifiers. This classifier may be tested for different applications and may provide new insights for developers and researchers.

The proposed PCC may be used to classify different product reviews, and hence may be beneficial to organizations to justify users’ reviews about specific products or services. By using authentic positive and negative sentiments of users, the credibility of the specific product, service or event may be enhanced. PCC may also be applied to other applications, such as spam detection, blog mining, news mining and various other data-mining applications.

The constructed PCC is novel and was tested on Indian movie review data.

The purpose of this paper is to study the fault diagnosis of internal combustion (IC) engine gearbox using vibration signals with signal processing and machine learning (ML) techniques.

Vibration signals from the gearbox are acquired for healthy and induced faulty conditions of the gear. In this study, 50% tooth fault and 100% tooth fault are chosen as gear faults in the driver gear. The acquired signals are processed and analyzed using signal processing and ML techniques.

The obtained results show that variation in the amplitude of the crankshaft rotational frequency (CRF) and gear mesh frequency (GMF) for different conditions of the gearbox with various load conditions. ML techniques were also employed in developing the fault diagnosis system using statistical features. J48 decision tree provides better classification accuracy about 85.1852% in identifying gearbox conditions.

The proposed approach can be used effectively for fault diagnosis of IC engine gearbox. Spectrum and continuous wavelet transform (CWT) provide better information about gear fault conditions using time–frequency characteristics.

In this paper, experiments are conducted on real-time running condition of IC engine gearbox while considering combustion. Eddy current dynamometer is attached to output shaft of the engine for applying load. Spectrum, cepstrum, short-time Fourier transform (STFT) and wavelet analysis are performed. Spectrum, cepstrum and CWT provide better information about gear fault conditions using time–frequency characteristics. ML techniques were used in analyzing classification accuracy of the experimental data to detect the gearbox conditions using various classifiers. Hence, these techniques can be used for detection of faults in the IC engine gearbox and other reciprocating/rotating machineries.

The stock market generates massive databases of various financial companies that are highly volatile and complex. To forecast daily stock values of these companies, investors frequently use technical analysis or fundamental analysis. Data mining techniques coupled with fundamental and technical analysis types have the potential to give satisfactory results for stock market prediction. In the current paper, an effort is made to investigate the accuracy of stock market predictions by using the combined approach of variables from technical and fundamental analysis for the creation of a data mining predictive model.

We chose 381 companies from the National Stock Exchange of India's CNX 500 index and conducted a two-stage data analysis. The first stage is identifying key fundamental variables and constructing a portfolio based on that study. Artificial neural network (ANN), support vector machines (SVM) and decision tree J48 were used to build the models. The second stage entails applying technical analysis to forecast price movements in the companies included in the portfolios. ANN and SVM techniques were used to create predictive models for all companies in the portfolios. We also estimated returns using trading decisions based on the model's output and then compared them to buy-and-hold returns and the return of the NIFTY 50 index, which served as a benchmark.

The results show that the returns of both the portfolios are higher than the benchmark buy-and-hold strategy return. It can be concluded that data mining techniques give better results, irrespective of the type of stock, and have the ability to make up for poor stocks. The comparison of returns of portfolios with the return of NIFTY as a benchmark also indicates that both the portfolios are generating higher returns as compared to the return generated by NIFTY.

As stock prices are influenced by both technical and fundamental indicators, the current paper explored the combined effect of technical analysis and fundamental analysis variables for Indian stock market prediction. Further, the results obtained by individual analysis have also been compared. The proposed method under study can also be utilized to determine whether to hold stocks for the long or short term using trend-based research.

Predicting the impact of social entrepreneurship is crucial as it can help social entrepreneurs to determine the achievement of their social mission and performance. However, there is a lack of existing social entrepreneurship models to predict social enterprises' social impacts. This paper aims to propose the social impact prediction model for social entrepreneurs using a data analytic approach.

This study implemented an experimental method using three different algorithms: naive Bayes, k-nearest neighbor and J48 decision tree algorithms to develop and test the social impact prediction model.

The accurate result of the developed social impact prediction model is based on the list of identified social impact prediction variables that have been evaluated by social entrepreneurship experts. Based on the three algorithms' implementation of the model, the results showed that naive Bayes is the best performance classifier for social impact prediction accuracy.

Although there are three categories of social entrepreneurship impact, this research only focuses on social impact. There will be a bright future of social entrepreneurship if the research can focus on all three social entrepreneurship categories. Future research in this area could look beyond these three categories of social entrepreneurship, so the prediction of social impact will be broader. The prospective researcher also can look beyond the difference and similarities of economic, social impacts and environmental impacts and study the overall perspective on those impacts.

This paper fulfills the need for the Malaysian social entrepreneurship blueprint to design the social impact in social entrepreneurship. There are none of the prediction models that can be used in predicting social impact in Malaysia. This study also contributes to social entrepreneur researchers, as the new social impact prediction variables found can be used in predicting social impact in social entrepreneurship in the future, which may lead to the significance of the prediction performance.

Surveillance is the emerging concept in the current technology, as it plays a vital role in monitoring keen activities at the nooks and corner of the world. Among which moving object identifying and tracking by means of computer vision techniques is the major part in surveillance. If we consider moving object detection in video analysis is the initial step among the various computer applications. The main drawbacks of the existing object tracking method is a time-consuming approach if the video contains a high volume of information. There arise certain issues in choosing the optimum tracking technique for this huge volume of data. Further, the situation becomes worse when the tracked object varies orientation over time and also it is difficult to predict multiple objects at the same time. In order to overcome these issues here, we have intended to propose an effective method for object detection and movement tracking. In this paper, we proposed robust video object detection and tracking technique. The proposed technique is divided into three phases namely detection phase, tracking phase and evaluation phase in which detection phase contains Foreground segmentation and Noise reduction. Mixture of Adaptive Gaussian (MoAG) model is proposed to achieve the efficient foreground segmentation. In addition to it the fuzzy morphological filter model is implemented for removing the noise present in the foreground segmented frames. Moving object tracking is achieved by the blob detection which comes under tracking phase. Finally, the evaluation phase has feature extraction and classification. Texture based and quality based features are extracted from the processed frames which is given for classification. For classification we are using J48 ie, decision tree based classifier. The performance of the proposed technique is analyzed with existing techniques k-NN and MLP in terms of precision, recall, f-measure and ROC.

Project manager’s competency is crucial in the construction sector for the successful completion of projects, particularly in the case of developing countries like Nepal. Therefore, it is very essential to select competent project managers by finding the competency factors required by them. Hence, this study aims to identify the characteristics of competent project managers by expert opinion method and to evaluate their competency level by a questionnaire survey to develop a prediction model using a supervised machine learning approach via Waikato Environment for Knowledge Analysis (WEKA), a machine learning tool which predicts Project manager’s performance as “Higher than expected,” “Expected” or “Lower than expected” for the medium complexity construction projects of Nepal (from US$200,000 up to US$10M).

The data collection procedure for this research is based on an expert opinion method and survey. Expert opinion method is conducted to find the characteristics of a competent project manager by validating the top 15 competency factors based on literature review. The survey is conducted with the top management to assess their project manager’s competency level. Both qualitative and quantitative approaches are used to collect data for classification and prediction in WEKA, a machine learning tool.

The results illustrate that the project managers in Nepal have a high score in leadership skills, personal characteristics, team development and delegation, communication skills, technical skills, problem-solving/coping with situation skills and stakeholder/relationship management skills. Furthermore, among the seven classifiers (naïve Bayes, sequential minimal optimization [SMO], multilayer perceptron, logistic, KStar, J48 and random forest), the accuracy given by the SMO algorithm is highest of all in both the percentage split and k-folds cross validation method. The model developed using SMO classifier by k-folds cross-validation (k = 10) is acknowledged as a final model.

This research focuses to develop a prediction model to predict and analyze the competency of project managers by applying a supervised machine learning approach. Seven extensively used algorithms (Naïve Bayes, SMO, multilayer perceptron, logistic, KStar, J48, random forest) are used to check the accuracy of models and an algorithm that gives the highest accuracy is adopted. Data collection for this research is carried out by expert opinion method to validate the characteristics (factors) essential for competent project managers in the first round and the description of each factor as high, medium and low is inquired with the same experts in the second round. After an expert opinion, a structured questionnaire is prepared for the survey to assess the competency level of project managers (PMs). The competency level of PMs working under government funded, foreign aided or private projects from the contractor’s side is measured. This research is limited to the medium scale construction projects of Nepal.

This model can be a huge asset in the human resource department of construction companies as it helps to know the performance level of project managers in terms of “Higher than expected,” “Expected” or “Lower than expected” for the medium complexity construction projects of Nepal. Also, the model will assist human intelligence to make the decision while recruiting a new project manager/s for different types of projects at a time. Moreover, the model can be used for self-assessment of project manager/s to know their performance level. The model can be used to develop a user friendly interface system or an application such that it can be conveniently used anywhere any time.

This research shows that most of the project managers working in a medium complexity construction project of Nepal are male, maximum of them hold bachelor’s degree and study for road projects. Furthermore, most of the project managers scored high in leadership skills, personal characteristics, communication skills, technical skills, problem-solving/coping with situation skills, team development and delegation and stakeholder/relationship management skills. The model has given the “Personal characteristics” attribute the highest weightage. Likewise, other attributes having high weightage are communication skills, analytical abilities, project budget, stakeholder/relationship management, team development and delegation and time management skills.

This research was conducted to find the competency factors and to study the competency level of project managers in Nepal to develop a prediction model to predict the PM’s performance using a machine learning approach in medium scale construction projects. There is a lack of research to develop a model that predicts project manager’s competency using the machine learning approach. Therefore, the predictive model developed here helps in the identification of a competent project manager as it will be advantageous for project completion with a high success rate.

Students pursuing different professional courses at the higher education level during 2021–2022 saw the first-time occurrence of a pandemic in the form of coronavirus disease 2019 (COVID-19), and their mental health was affected. Many works are available in the literature to assess mental health severity. However, it is necessary to identify the affected students early for effective treatment.

Predictive analytics, a part of machine learning (ML), helps with early identification based on mental health severity levels to aid clinical psychologists. As a case study, engineering and medical course students were comparatively analysed in this work as they have rich course content and a stricter evaluation process than other streams. The methodology includes an online survey that obtains demographic details, academic qualifications, family details, etc. and anxiety and depression questions using the Hospital Anxiety and Depression Scale (HADS). The responses acquired through social media networks are analysed using ML algorithms – support vector machines (SVMs) (robust handling of health information) and J48 decision tree (DT) (interpretability/comprehensibility). Also, random forest is used to identify the predictors for anxiety and depression.

The results show that the support vector classifier produces outperforming results with classification accuracy of 100%, 1.0 precision and 1.0 recall, followed by the J48 DT classifier with 96%. It was found that medical students are affected by anxiety and depression marginally more when compared with engineering students.

The entire work is dependent on the social media-displayed online questionnaire, and the participants were not met in person. This indicates that the response rate could not be evaluated appropriately. Due to the medical restrictions imposed by COVID-19, which remain in effect in 2022, this is the only method found to collect primary data from college students. Additionally, students self-selected themselves to participate in this survey, which raises the possibility of selection bias.

The responses acquired through social media networks are analysed using ML algorithms. This will be a big support for understanding the mental issues of the students due to COVID-19 and can taking appropriate actions to rectify them. This will improve the quality of the learning process in higher education in Oman.

Furthermore, this study aims to provide recommendations for mental health screening as a regular practice in educational institutions to identify undetected students.

Comparing the mental health issues of two professional course students is the novelty of this work. This is needed because both studies require practical learning, long hours of work, etc.

Erythemato-squamous disease (ESD) is one of the complex diseases related to the dermatology field. Due to common morphological features, the diagnosis of ESDs become stringent and leads to inconsistency. Besides, diagnosis has been done on the basis of inculcated visible symptoms pertinent with the expertise of the physician. Hence, ontology construction for ESD is essential to ensure credibility, consistency, to resolve lack of time, labor and competence and to diminish human error.

This paper presents the design of an automatic ontology framework through data mining techniques and subsequently depicts the diagnosis of ESD using the available knowledge- and rule-based system.

The rule language (Semantic Web Rule Language) and rule engine (Jess and Drools) have been integrated to explore the severity of the ESD and foresee the most appropriate class to be suggested.

In this paper, the authors identify the efficiency of the rule engine and investigate the performance of the computational techniques in predicting ESD using three different measures.

Primarily, the approach assesses transfer time for total number of axioms exported to rule engine (Jess and Drools) while the other approach measures the number of inferred axioms (process time) using the rule engine while the third measure calculates the time to translate the inferred axioms to OWL knowledge (execution time).

This study aims to propose a service quality evaluation model for health-care services.

In this study, a service quality evaluation model is proposed based on the service quality measurement (SERVQUAL) scale and machine learning algorithm. Primarily, items that affect the quality of service are determined based on the SERVQUAL scale. Subsequently, a service quality assessment model is generated to manage the resources that are allocated to improve the activities efficiently. Following this phase, a sample of classification model is conducted. Machine learning algorithms are used to establish the classification model.

The proposed evaluation model addresses the following questions: What are the potential impact levels of service quality dimensions on the quality of service practically? What should be prioritization among the service quality dimensions and Which dimensions of service quality should be improved primarily? A real-life case study in a public hospital is carried out to reveal how the proposed model works. The results that have been obtained from the case study show that the proposed model can be conducted easily in practice. It is also found that there is a remarkably high-service gap in the public hospital, in which the case study has been conducted, regarding the general physical conditions and food services.

The primary contribution of this study is threefold. The proposed evaluation model determines the impact levels of service quality dimensions on the service quality in practice. The proposed evaluation model prioritizes service quality dimensions in terms of their significance. The proposed evaluation model finds out the answer to the question of which service quality dimensions should be improved primarily?

This paper aims to propose a novel approach which integrates collocations and domain concepts for Chinese cosmetic word of mouth (WOM) sentiment classification. Most sentiment analysis works by collecting sentiment scores from each unigram or bigram. However, not every unigram or bigram in a WOM document contains sentiments. Chinese collocations consist of the main sentiments of WOM. This paper reduces the complexity of the document dimensionality and makes an improvement for sentiment classification.

This paper builds two contextual lexicons for feature words and sentiment words, respectively. Based on these contextual lexicons, this paper uses the techniques of associated rules and mutual information to build possible Chinese collocation sets. This paper applies preference vector modelling as the vector representation approach to catch the relationship between Chinese collocations and their associated concepts.

This paper compares the proposed preference vector models with benchmarks, using three classification techniques (i.e. support vector machine, J48 decision tree and multilayer perceptron). According to the experimental results, the proposed models outperform all benchmarks evaluated by the criterion of accuracy.

This paper focuses on Chinese collocations and proposes a novel research approach for sentiment classification. The Chinese collocations used in this paper are adaptable to the content and domains. Finally, this paper integrates collocations with the preference vector modelling approach, which not only achieves a better sentiment classification performance for Chinese WOM documents but also avoids the curse of dimensionality.