Search results

The purpose of this paper is to understand the customer sentiment towards telemedicine apps and also to apply machine learning algorithms to analyse the sentiments in the adoption during the COVID-19 pandemic.

Text mining that uses natural language processing to extract insights from unstructured text is used to find out the customer sentiment towards the telemedicine apps during the COVID-19 pandemic. Machine learning algorithms like support vector machine (SVM) and Naïve Bayes classifier are used for classification, and their sensitivity and specificity are found using a confusion matrix.

The paper explores the customer sentiment towards telemedicine apps and their adoption during the COVID-19 pandemic. Text mining that uses natural language processing to extract insights from unstructured text is used to find out the customer sentiment towards the telemedicine apps during the COVID-19 pandemic. Machine learning algorithms like SVM and Naïve Bayes classifier are used for classification, and their sensitivity and specificity are found using a confusion matrix. The customers who used telemedicine apps have positive sentiment as well as negative sentiment towards the telemedicine apps. Some of the customers have concerns about the medicines delivered, their delivery time, the quality of service and other technical difficulties. Even a small percentage of doctors feel uncomfortable in online consultation through the application.

The primary value of this paper lies in providing an overview of the customers’ approach towards the telemedicine apps, especially during the COVID-19 pandemic.

In current era, retaining the best-performing employees has become essential for businesses to compete in the dynamic technological landscape. Consequently, organizations must ensure that their star performers believe that company’s reward and recognition (R&R) system is fair and equal. This study aims to use an explainable machine learning (eXML) model to develop a prediction algorithm for employee satisfaction with the fairness of R&R systems.

The current study uses state-of-the-art machine learning models such as Naive Bayes, Decision Tree C5.0, Random Forest and support vector machine-RBF to predict employee satisfaction towards fairness in R&R. The primary data used in the study has been collected from the employees of a large public sector undertaking from an emerging economy. This study also proposes a novel improved Naïve Bayes (INB) algorithm, the efficiency of which is compared with the state-of-the-art algorithms.

It is seen that the proposed INB model outperforms the state-of-the-art algorithms in many scenarios. Further, the proposed model and feature interaction are explained using the explainable machine learning (XML) concept. In addition, this study incorporates text mining techniques to corroborate the results from XML and suggests that “Transparency”, “Recognition”, “Unbiasedness”, “Appreciation” and “Timeliness in reward” are the most important features that impact employee satisfaction.

To the best of the authors’ knowledge, this is one of the first studies to use INB algorithm and mixed method research (text mining along with machine learning algorithms) for the prediction of employee satisfaction with respect to the R&R system.

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.

The complexity of citizenship behavior in organizations has long been a focus of research. Traditional methodologies have been predominantly used to address this complexity. This paper aims to tackle the problem using a cutting-edge technological tool: business process mining. The objective is to enhance citizenship behaviors by leveraging primary data collected from 326 white-collar employees in the Indian service industry.

The study focuses on two main processes: training and creativity, with the ultimate goal of fostering organizational citizenship behavior (OCB), both in its overall manifestation (OCB-O) and its individual components (OCB-I). Seven different machine learning algorithms were used: artificial neural, behavior, prediction network, linear discriminant classifier, K-nearest neighbor, support vector machine, extreme gradient boosting (XGBoost), random forest and naive Bayes. The approach involved mining the most effective path for predicting the outcome and automating the entire process to enhance efficiency and sustainability.

The study successfully predicted the OCB-O construct, demonstrating the effectiveness of the approach. An optimized path for prediction was identified, highlighting the potential for automation to streamline the process and improve accuracy. These findings suggest that leveraging automation can facilitate the prediction of behavioral constructs, enabling the customization of policies for future employees.

The findings have significant implications for organizations aiming to enhance citizenship behaviors among their employees. By leveraging advanced technological tools such as business process mining and machine learning algorithms, companies can develop more effective strategies for fostering desirable behaviors. Furthermore, the automation of these processes offers the potential to streamline operations, reduce manual effort and improve predictive accuracy.

This study contributes to the existing literature by offering a novel approach to addressing the complexity of citizenship behavior in organizations. By combining business process mining with machine learning techniques, a unique perspective is provided on how technological advancements can be leveraged to enhance organizational outcomes. Moreover, the findings underscore the value of automation in refining existing processes and developing models applicable to future employees, thus improving overall organizational efficiency and effectiveness.

The purpose of this study is to determine propeller damage based on acoustic recordings taken from unmanned aerial vehicle (UAV) propellers operated at different thrust conditions on a test bench. Propeller damage is especially critical for fixed-wing UAVs to sustain a safe flight. The acoustic characteristics of the propeller vary with different propeller damages.

For the research, feature extraction methods and machine learning techniques were used during damage detection from propeller acoustic data. First of all, sound recordings were obtained by operating five different damaged propellers and undamaged propellers under three different thrusts. Afterwards, the harmonic-to-noise ratio (HNR) feature extraction technique was applied to these audio recordings. Finally, model training and validation were performed by applying the Gaussian Naive Bayes machine learning technique to create a diagnostic approach.

A high recall value of 96.19% was obtained in the performance results of the model trained according to damaged and undamaged propeller acoustic data. The precision value was 73.92% as moderate. The overall accuracy value of the model, which can be considered as general performance, was obtained as 81.24%. The F1 score has been found as 83.76% which provides a balanced measure of the model’s precision and recall values.

This study include provides solid method to diagnose UAV propeller damage using acoustic data obtain from the microphone and allows identification of differently damaged propellers. Using that, the risk of in-flight failures can be reduced and maintenance costs can be lowered with addressing the occurred problems with UAV propeller before they worsen.

This study introduces a novel method to diagnose damaged UAV propellers using the HNR feature extraction technique and Gaussian Naive Bayes classification method. The study is a pioneer in the use of HNR and the Gaussian Naive Bayes and demonstrates its effectiveness in augmenting UAV safety by means of propeller damages. Furthermore, this approach contributes to UAV operational reliability by bridging the acoustic signal processing and machine learning.

This study aims to explore the integration of machine learning (ML) in tribology to optimize lubrication interval decisions, aiming to enhance equipment lifespan and operational efficiency through wear image analysis.

Using a data set of scanning electron microscopy images from an internal combustion engine, the authors used AlexNet as the feature extraction algorithm and the J48 decision tree algorithm for feature selection and compared 15 ML classifiers from the lazy-, Bayes and tree-based families.

From the analyzed ML classifiers, instance-based k-nearest neighbor emerged as the optimal algorithm with a 95% classification accuracy against testing data. This surpassed individually trained convolutional neural networks’ (CNNs) and closely approached ensemble deep learning (DL) techniques’ accuracy.

The proposed approach simplifies the process, enhances efficiency and improves interpretability compared to more complex CNNs and ensemble DL techniques.

Technology serves as a key catalyst in shaping society and the economy, significantly altering customer dynamics. Through a deep understanding of these evolving behaviors, a service can be tailored to address each customer's unique needs and personality. We introduce a strategy to integrate customer complaints with their personality traits, enabling responses that resonate with the customer’s unique personality.

We propose a strategy to incorporate customer complaints with their personality traits, enabling responses that reflect the customer’s unique personality. Our approach is twofold: firstly, we employ the customer complaints ontology (CCOntology) framework enforced with multi-class classification based on a machine learning algorithm, to classify complaints. Secondly, we leverage the personality measurement platform (PMP), powered by the big five personality model to predict customer’s personalities. We develop the framework for the Indonesian language by extracting tweets containing customer complaints directed towards Indonesia's three biggest e-commerce services.

By mapping customer complaints and their personality type, we can identify specific personality traits associated with customer dissatisfaction. Thus, personalizing how we offer the solution based on specific characteristics.

The research enriches the state-of-the-art personalizing service research based on captured customer behavior. Thus, our research fills the research gap in considering customer personalities. We provide comprehensive insights by aligning customer feedback with corresponding personality traits extracted from social media data. The result is a highly customized response mechanism attuned to individual customer preferences and requirements.

Many studies have examined pre-diploma students' backgrounds and academic performance with results showing that some did not achieve the expected level of competence. This study aims to examine the relationship between students’ demographic characteristics and their academic achievement at the pre-diploma level using machine learning.

Secondary data analysis was used in this study, which involved collecting information about 1,052 pre-diploma students enrolled at Universiti Teknologi MARA (UiTM) Pahang Branch between 2017 and 2021. The research procedure was divided into two parts: data collecting and pre-processing, and building the machine learning algorithm, pre-training and testing.

Gender, family income, region and achievement in the national secondary school examination (Sijil Pelajaran Malaysia [SPM]) predict academic performance. Female students were 1.2 times more likely to succeed academically. Central region students performed better with a value of 1.26. M40-income students were more likely to excel with an odds ratio of 2.809. Students who excelled in SPM English and Mathematics had a better likelihood of succeeding in higher education.

This research was limited to pre-diploma students from UiTM Pahang Branch. For better generalizability of the results, future research should include pre-diploma students from other UiTM branches that offer this programme.

This study is expected to offer insights for policymakers, particularly, the Ministry of Higher Education, in developing a comprehensive policy to improve the tertiary education system by focusing on the fourth Sustainable Development Goal.

These pre-diploma students were found to originate mainly from low- or middle-income families; hence, the programme may help them acquire better jobs and improve their standard of living. Most students enrolling on the pre-diploma performed below excellent at the secondary school level and were therefore given the opportunity to continue studying at a higher level.

This predictive model contributes to guidelines on the minimum requirements for pre-diploma students to gain admission into higher education institutions by ensuring the efficient distribution of resources and equal access to higher education among all communities.

This study evaluates machine learning (ML) classifiers for diagnosing Parkinson’s disease (PD) using subcortical brain region data from 3D T1 magnetic resonance imaging (MRI) Parkinson’s Progression Markers Initiative (PPMI database). We aim to identify top-performing algorithms and assess gender-related differences in accuracy.

Multiple ML algorithms will be compared for their ability to classify PD vs healthy controls using MRI scans of the brain structures like the putamen, thalamus, brainstem, accumbens, amygdala, caudate, hippocampus and pallidum. Analysis will include gender-specific performance comparisons.

The study reveals that ML classifier performance in diagnosing PD varies across subcortical brain regions and shows gender differences. The Extra Trees classifier performed best in men (86.36% accuracy in the putamen), while Naive Bayes performed best in women (69.23%, amygdala). Regions like the accumbens, hippocampus and caudate showed moderate accuracy (65–70%) in men and poor performance in women. The results point out a significant gender-based performance gap, highlighting the need for gender-specific models to improve diagnostic precision across complex brain structures.

This study highlights the significant impact of gender on machine learning diagnosis of PD using data from subcortical brain regions. Our novel focus on these regions uncovers their diagnostic potential, improves model accuracy and emphasizes the need for gender-specific approaches in medical AI. This work could ultimately lead to earlier PD detection and more personalized treatment.

The construction projects are highly subjected to uncertainties, which result in overruns in time and cost. Realistic estimates of workforce and duration are imperative for construction projects to attain their intended objectives. The aim of this study is to provide accurate labor and duration estimates for the construction projects, considering actual uncertainties.

The dataset was formulated from the information collected from 186 construction projects through direct interviews, group discussions and questionnaire methods. The actual uncertainties and exposure conditions of construction activities were recorded. The data were verified with the standard guideline to remove the outliers. The prediction model was developed using support vector regression (SVR), a machine learning (ML) method. The performance was evaluated using the widely adopted regression metrics. Further, the cross validation was made with the visualization of residuals and predicted errors, ridge regression with transformed target distribution and a Gaussian Naive Bayes (NB) regressor.

The prediction models predicted the duration and labor requirements with the consideration of actual uncertainties. The residual plot indicated the appropriate use of SVR to develop the prediction model. The duration (DC) and resource constraint (RC) prediction models obtained 80 and 82% accuracy, respectively. Besides, the developed model obtained better accuracy for the training and test scores than the Gaussian NB regressor. Further, the range of the explained variance score and R² was from 0.95 to 0.97, indicating better efficiency compared with other prediction models.

The researchers will utilize the research findings to estimate the duration and labor requirements under uncertain conditions and further improve the construction project management practices.

The research findings will enable industry practitioners to accurately estimate the duration and labor requirements, considering historical uncertain conditions. A precise estimation of resources will ensure the attainment of the intended project outcomes.

Delays in construction projects will be reduced by implementing the research findings, which significantly ensures the effective utilization of resources and attainment of other economic benefits. The policymakers will develop a guideline to develop a database to collect the uncertainties of the construction projects and relatively estimate the resource requirements.

This is the first study to consider the actual uncertainties of construction projects to develop RC and DC prediction models. The developed prediction models accurately estimate the duration and labor requirements with minimal computational time. The industry practitioners will be able to accurately estimate the duration and labor requirements using the developed models.