Search results
1 – 10 of 748Larissa Arakawa Martins, Veronica Soebarto, Terence Williamson and Dino Pisaniello
This paper presents the development of personal thermal comfort models for older adults and assesses the models’ performance compared to aggregate approaches. This is necessary as…
Abstract
Purpose
This paper presents the development of personal thermal comfort models for older adults and assesses the models’ performance compared to aggregate approaches. This is necessary as individual thermal preferences can vary widely between older adults, and the use of aggregate thermal comfort models can result in thermal dissatisfaction for a significant number of older occupants. Personalised thermal comfort models hold the promise of a more targeted and accurate approach.
Design/methodology/approach
Twenty-eight personal comfort models have been developed, using deep learning and environmental and personal parameters. The data were collected through a nine-month monitoring study of people aged 65 and over in South Australia, who lived independently. Modelling comprised dataset balancing and normalisation, followed by model tuning to test and select the best hyperparameters’ sets. Finally, models were evaluated with an unseen dataset. Accuracy, Cohen’s Kappa Coefficient and Area Under the Receiver Operating Characteristic Curve (AUC) were used to measure models’ performance.
Findings
On average, the individualised models present an accuracy of 74%, a Cohen’s Kappa Coefficient of 0.61 and an AUC of 0.83, representing a significant improvement in predictive performance when compared to similar studies and the “Converted” Predicted Mean Vote (PMVc) model.
Originality/value
While current literature on personal comfort models have focussed solely on younger adults and offices, this study explored a methodology for older people and their dwellings. Additionally, it introduced health perception as a predictor of thermal preference – a variable often overseen by architectural sciences and building engineering. The study also provided insights on the use of deep learning for future studies.
Details
Keywords
Md Shamim Hossain, Humaira Begum, Md. Abdur Rouf and Md. Mehedul Islam Sabuj
The goal of the current research is to use different machine learning (ML) approaches to examine and predict customer reviews of food delivery apps (FDAs).
Abstract
Purpose
The goal of the current research is to use different machine learning (ML) approaches to examine and predict customer reviews of food delivery apps (FDAs).
Design/methodology/approach
Using Google Play Scraper, data from five food delivery service providers were collected from the Google Play store. Following cleaning the reviews, the filtered texts were classified as having negative, positive, or neutral sentiments, which were then scored using two unsupervised sentiment algorithms (AFINN and Valence Aware Dictionary for sentiment Reasoning (VADER)). Furthermore, the authors employed four ML approaches to categorize each review of FDAs into the respective sentiment class.
Findings
According to the study's findings, the majority of customer reviews of FDAs were positive. This research also revealed that, while all of the methods (decision tree, linear support vector machine, random forest classifier and logistic regression) can appropriately classify the reviews into a sentiment category, support vector machines (SVM) beats the others in terms of model accuracy. The authors' study also showed that logistic regression provided the highest recall, F1 score and lowest Root Mean Square Error (RMSE) among the four ML models.
Practical implications
The findings aid FDAs in determining customer review behavior. The study's findings could help food apps developers better understand how customers feel about the developers' products and services. The food apps developer can learn how to use ML techniques to better understand the users' behavior.
Originality/value
The current study uses ML methodologies to investigate and predict consumer attitude regarding FDAs.
Details
Keywords
Manju Priya Arthanarisamy Ramaswamy and Suja Palaniswamy
The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG)…
Abstract
Purpose
The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.
Design/methodology/approach
DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.
Findings
The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.
Originality/value
Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.
Details
Keywords
Amir Asgari, Ali Khorsandi Taskoh and Saeed Ghiasi Nodooshan
This paper aims to introduce a conceptual model for the shaping of the innovation district under the anchor approach by extracting the specifications of the fourth-generation…
Abstract
Purpose
This paper aims to introduce a conceptual model for the shaping of the innovation district under the anchor approach by extracting the specifications of the fourth-generation university.
Design/methodology/approach
This study selected 550 resources and reduced them to 190 to achieve the most appropriate resources. This study used a meta-synthesis analysis approach using a text-mining method due to the multidisciplinary and voluminous nature of contents.
Findings
The results first reveal the shaping process and the components of innovation districts, which are: innovational urban infrastructures, knowledge economy and competitiveness and academic development. Second, this study also shows the specifications of a fourth-generation university to shape innovation districts.
Practical implications
This study also informs the policymakers and researchers internationally about the implementation requirements of a fourth-generation university and the shaping mechanisms of an innovation district.
Originality/value
This paper is pioneer about two concepts, first, it shows the shaping process of an innovation district, providing a large-scale insight about the components and second, this illustrates for the first time the specifications of a fourth-generation University practically as an anchor institute to shape innovation district.
Details
Keywords
Mahesh Babu Mariappan, Kanniga Devi, Yegnanarayanan Venkataraman, Ming K. Lim and Panneerselvam Theivendren
This paper aims to address the pressing problem of prediction concerning shipment times of therapeutics, diagnostics and vaccines during the ongoing COVID-19 pandemic using a…
Abstract
Purpose
This paper aims to address the pressing problem of prediction concerning shipment times of therapeutics, diagnostics and vaccines during the ongoing COVID-19 pandemic using a novel artificial intelligence (AI) and machine learning (ML) approach.
Design/methodology/approach
The present study used organic real-world therapeutic supplies data of over 3 million shipments collected during the COVID-19 pandemic through a large real-world e-pharmacy. The researchers built various ML multiclass classification models, namely, random forest (RF), extra trees (XRT), decision tree (DT), multilayer perceptron (MLP), XGBoost (XGB), CatBoost (CB), linear stochastic gradient descent (SGD) and the linear Naïve Bayes (NB) and trained them on striped datasets of (source, destination, shipper) triplets. The study stacked the base models and built stacked meta-models. Subsequently, the researchers built a model zoo with a combination of the base models and stacked meta-models trained on these striped datasets. The study used 10-fold cross-validation (CV) for performance evaluation.
Findings
The findings reveal that the turn-around-time provided by therapeutic supply logistics providers is only 62.91% accurate when compared to reality. In contrast, the solution provided in this study is up to 93.5% accurate compared to reality, resulting in up to 48.62% improvement, with a clear trend of more historic data and better performance growing each week.
Research limitations/implications
The implication of the study has shown the efficacy of ML model zoo with a combination of base models and stacked meta-models trained on striped datasets of (source, destination and shipper) triplets for predicting the shipment times of therapeutics, diagnostics and vaccines in the e-pharmacy supply chain.
Originality/value
The novelty of the study is on the real-world e-pharmacy supply chain under post-COVID-19 lockdown conditions and has come up with a novel ML ensemble stacking based model zoo to make predictions on the shipment times of therapeutics. Through this work, it is assumed that there will be greater adoption of AI and ML techniques in shipment time prediction of therapeutics in the logistics industry in the pandemic situations.
Details
Keywords
Arunima Rana, Anil Bhat and Leela Rani
The purpose of the paper is to systematically review and summarize the literature addressing various sources of online brand equity. The evolution of social media, online forums…
Abstract
Purpose
The purpose of the paper is to systematically review and summarize the literature addressing various sources of online brand equity. The evolution of social media, online forums and virtual communities drive the diversity in nomenclature of online marketing variables. Different researchers have used different marketing variables to indicate the same source of online brand equity. The definitions of the marketing variables change with the change in context, due to the complex e-commerce environment. The marketing variables used in different studies have lead to a conceptual overlap and repetitiveness.
Design/methodology/approach
This confusion is sought to be classified by the proposed classificatory scheme that used content analysis of 42 previous studies. The definitions of the antecedents of sources of the online brand equity used by the authors are analyzed with the help of content analysis to summarize the marketing variables in a meaningful way.
Findings
The paper identifies 15 major marketing variables by authors in their studies related to various sources of online brand equity. The final list contains 13 frequently used variables which also comprises variables which are evolving due to the dynamic e-commerce environment like the feeling of “virtual-real”.
Practical implications
The variables identified can be used by the businesses as a check list to their marketing activities.
Originality/value
This is the first paper which identifies and clarifies the ambiguity present in the application of the various online marketing variables.
Details
Keywords
Anthony Cocciolo and Debbie Rabina
The aim of this research project is to uncover if place‐based learning can increase learner engagement and understanding of historical topics.
Abstract
Purpose
The aim of this research project is to uncover if place‐based learning can increase learner engagement and understanding of historical topics.
Design/methodology/approach
To study this, learners will use GeoStoryteller to learn about a historical topic on the places where significant events occurred, and then be interviewed by the researchers. GeoStoryteller is a tool developed by the researchers that runs on smartphones, such as an iPhone or Android. It provides the user multimedia stories about the historical sites, delivered via the mobile web or through Layar, an augmented reality web browser. The initial application of this technology focuses on German immigration to New York City between 1840 and 1945 through a partnership with the Goethe‐Institut, the Federal Republic of Germany's cultural institution. After using GeoStoryteller to learn about this content, n=31 participants were interviewed by the researchers, and transcripts were subjected to a quantitative content analysis.
Findings
Results indicate that the use of place increases learner perceptions of their engagement and understanding of historical topics; however, novel user interfaces like augmented reality impose significant usability issues, and more standard interfaces are preferred by users.
Originality/value
The use of place in mobile learning environments provides a meaningful entry point into historical content. Teachers of history and social studies, as well as those working in memory institutions (museum, libraries, and archives), should be encouraged in using place in their teaching and mobile education initiatives.
Details
Keywords
Laurie R. Weingart, Leigh L. Thompson, Max H. Bazerman and John S. Carroll
This paper examined negotiator behavior in a variable‐sum two‐party negotiation task and its impact on individual and joint negotiator out‐come. Specifically, we examined the role…
Abstract
This paper examined negotiator behavior in a variable‐sum two‐party negotiation task and its impact on individual and joint negotiator out‐come. Specifically, we examined the role of negotiator opening offer, reciprocity and complementarity of the use of tactics, systematic progression of offers, and information sharing in a negotiation with integrative potential. Results indicated that initial offers affect final outcome differently across buyers and sellers. The buyer's initial offer was curvilinearly related to his or her final outcome in the form of an inverted‐U. The seller's initial offer was positive‐linearly related to seller's outcome. Second, negotiators reciprocated and complemented both distributive and integrative tactics. In addition, highly integrative dyads differed from less efficient dyads in their reciprocation of integrative behaviors and complementarity of distributive behaviors. Third, approximately forty percent of offers made represented systematic concessions, but the proportion of offers reflecting systematic concessions was not related to the efficiency of the joint outcome. Finally, while information sharing did appear to have a positive effect on the efficiency of agreements, differences in the amount of information provided did not affect the proportion of outcome claimed by each party.
Elisabete Correia, Susana Garrido and Helena Carvalho
The study aims to improve the understanding of the online sustainability disclosure phenomena considering the quantity and nature of the content of the information related to…
Abstract
Purpose
The study aims to improve the understanding of the online sustainability disclosure phenomena considering the quantity and nature of the content of the information related to sustainability disclosed in the corporate website of companies, providing evidence about the website sustainability disclosure of different size companies and characterizing the website sustainability disclosure of the Portuguese mold companies.
Design/methodology/approach
A content analysis methodology was used to the corporate websites of 83 companies in the sample. A direct approach was followed where the researcher is asked to read and classify the text in a previously defined category, but where the possibility of identifying new categories from the collected data is not excluded.
Findings
The information on sustainability disclosed by the mold companies is limited, whether in quantity or concerning the type of information. The information disclosed about environmental and social aspects is scarcer, being the focus more on aspects related to the economic dimension of sustainability, particularly in the areas related to products and services and customers.
Research limitations/implications
The research design can be broadened to include other sustainability dissemination tools and other research methodologies, such as case studies, to provide a deeper understanding of the concerns and initiatives/practices of sustainability of mold companies.
Practical implications
This study contributes to the knowledge of sustainability dissemination practices in SMEs, an area of research that needs to be more explored and, in an industrial sector (molds) that have not received much attention in this area.
Originality/value
Based on the premise of the importance of corporate sustainability communication, the study focuses on the Internet as an information dissemination tool. It provides indications on the theme and information type that can be used to report the company's sustainability.
Details
Keywords
Prabath Perera, Selva Selvanathan, Jayatilleke Bandaralage and Jen-Je Su
Digital inequality is considered one of the leading causes of socioeconomic disparities nowadays and a barrier to sustainable development. However, a dearth of empirical research…
Abstract
Purpose
Digital inequality is considered one of the leading causes of socioeconomic disparities nowadays and a barrier to sustainable development. However, a dearth of empirical research has examined the impact of digital inequality in attaining sustainable development. This study aims to systematically review the scientific publications on the impact of digital inequality in achieving sustainable development.
Design/methodology/approach
The preferred reporting items for systematic reviews and meta-analyses (PRISMA, 2020) guidelines were followed to carry out the systematic literature review (SLR) using Scopus, Web of Science, ProQuest and Google Scholar electronic databases. Numerous inclusion/exclusion criteria were employed to obtain the most relevant literature. Finally, 54 articles were included to prepare the final database and qualitative synthesis was performed using 12 variables.
Findings
While the findings show that there has been a substantial expansion of scientific publications on the focused area in recent years, there is still a lack of empirical and comparative studies; less focus on the offline benefits of online activities were also demonstrated by the results. Moreover, SDGs 04 and 05 were identified as the predominant goals in the literature. Findings further highlighted the importance of an accurate conceptualization of digital inequality.
Originality/value
In general, this study investigates the level of impact of digital inequality on the United Nations' Sustainable Development Goals. Moreover, it shows the evolution of scientific publications on digital inequality in terms of its contribution when achieving sustainable development.
Details