The establishment of human body three vital measurements regression relationship based on SVR method

2015 ◽  
Vol 27 (1) ◽  
pp. 148-158
Author(s):  
Xiaojiu Li ◽  
Xiaoning Jing
Keyword(s):  
Design Methodology ◽  
Mass Measurement ◽  
Young Female ◽  
Support Vector ◽  
Feature Size ◽  
Content Type ◽  
Training Samples ◽  
Sample Data ◽  
Regression Relationship ◽  
Chest Girth

Purpose – The purpose of this paper is to obtain circumference sizes from 2D feature sizes in the parts of three vital measurements of young female, the dimensions of chest width, chest depth, waist width, waist depth, hip width, hip depth, chest girth, waist girth and hip girth of 400 young female samples are collected. Design/methodology/approach – Inside which, 300 samples are used as learning samples, and the remaining 100 samples are used as training samples, the sample data are entered to the network constructed by support vector machine regression (SVR) and the predictive value of circumference sizes are gained. Findings – Finally, the regression model is established between 2D feature size and the corresponding circumference size. Through the trained prediction model based on SVR, the circumference sizes in three vital measurement parts of a new sample are predicted for convenient mass measurement. Originality/value – The research of measurement regression relationship in parts of three vital measurements of young female is the basis for conveniently obtaining dimensions in garment mass measurement. It can provide the accurate data to feminine dress industry, and has high precision.

Sentiment classification of Chinese cosmetic reviews based on integration of collocations and concepts

2019 ◽  
Vol 38 (1) ◽  
pp. 155-169
Author(s):  
Chihli Hung ◽  
You-Xin Cao
Keyword(s):  
Design Methodology ◽  
Classification Performance ◽  
Sentiment Classification ◽  
Support Vector ◽  
Research Approach ◽  
Content Type ◽  
Novel Approach ◽  
The Relationship ◽  
Modelling Approach

Purpose 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. Design/methodology/approach 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. Findings 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. Originality/value 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.

“Are you crewed up with that bird from the uni?” the complexities of conducting ethnographic research in policing

2020 ◽  
Vol 9 (3) ◽  
pp. 365-377
Author(s):  
Claudia Emeline Cox
Keyword(s):  
Police Officers ◽  
Design Methodology ◽  
Moral Dilemmas ◽  
Young Female ◽  
Original Research ◽  
Ethnographic Research ◽  
Content Type ◽  
Conducting Research ◽  
Researcher Identity ◽  
Female Researcher

PurposeThe purpose of this paper is to provide some initial reflections on the complexities and challenges faced when conducting observations with police officers working in response and neighbourhood policing roles from the perspective of a young, female, researcher.Design/methodology/approachThe research consisted of 200 hours spent with operational police officers in a medium sized UK police force, predominantly in 3 cities, to explore the realities of frontline policing and policy implementation. This paper offers a reflexive account of conducting the research, as opposed to a discussion of the findings which align to the original research aim.FindingsConducting this fieldwork highlighted a number of complexities arising as a result of conducting ethnographic research in policing. This paper is concerned with the constructing of a researcher identity and navigating moral dilemmas based on the culture and use of language observed.Originality/valueWhilst this will be of interest to those engaged with similar policing research, such findings are also likely to apply to those conducting ethnography where there is conflict between their insider/outsider status, the potential for internalised moral debates and women conducting research in male-dominated settings.

scholarly journals Am I worth it? Gifting myself with luxury

2014 ◽  
Vol 18 (2) ◽  
pp. 112-132 ◽  
Author(s):  
Hannele Kauppinen-Räisänen ◽  
Johanna Gummerus ◽  
Catharina von Koskull ◽  
Åke Finne ◽  
Anu Helkkula ◽  
...  
Keyword(s):  
Design Methodology ◽  
Research Topic ◽  
The Self ◽  
Luxury Brands ◽  
Content Type ◽  
Data Collection And Analysis ◽  
Sample Data ◽  
Marketing Activities ◽  
Key Dimensions ◽  
Practical Implications

Purpose – Consumers gift themselves with luxury fashion brands, yet the motives for self-gifting are not well understood. Whereas traditionally, self-gifting is defined as self-orientated in nature, luxury brands are seen as social statements, and self-gifting of luxury fashion brands that combine these two controversial areas is an interesting research topic. The purpose of this paper is to address this issue by exploring the self-gifting behaviour of consumers, in particular focusing on the personal motives of gifting oneself with luxury fashion brands. Design/methodology/approach – The study takes a multi-qualitative approach involving a small (n=19) but rich sample. Data collection and analysis were triangulated to reduce researcher biases. Findings – The study provides key dimensions for understanding consumers’ perceptions of luxury fashion brands and self-gifting motives (self and socially orientated). The findings reveal that reflections from others are part of the self-gifting phenomenon. It appeared that although self-orientated benefits and personally orientated motives trigger the self-gifting act, the act of actually purchasing explicitly luxury brands for oneself as a gift may be triggered by other-orientated benefits and socially orientated motives. The findings also imply that luxury holds a self-orientated aspect; luxury brands are not only purchased for socially orientated reasons but also for reasons related to oneself. In addition, the findings discuss the act of shopping, where the act can be perceived as a luxury experience and overrun the importance of the brand. Practical implications – The findings provide insights to consumers’ gifting behaviour that may be valuable for retailers and fashion marketers as they plan for marketing activities related to their customers’ self-gifting. Originality/value – Self-gifting represents a view of gifting that remains under-researched. This study uncovers the motives for gifting oneself with luxury fashion brands, a further sub-area in need for more investigation.

To create the value of indigenous tourism in multicultural market based on tourists' cultural experience

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yin-Ju Chen
Keyword(s):  
Design Methodology ◽  
Cultural Experience ◽  
Content Type ◽  
Effective Strategies ◽  
The Past ◽  
Sample Data ◽  
Domestic Tourism ◽  
Experiential Value ◽  
Indigenous Tourism

PurposeTourism development can reduce the economic disadvantages of indigenous tribes; however, it is also reproached for the destruction of local culture. The challenge for tourism and culture is to reach those diverse audiences through a multicultural marketing perspective for managers to make decisions. Therefore, learning the activity preferences of tourism experiences and creating the value of indigenous tourism by strategies are essential indicators of this research.Design/methodology/approachThe knowledge lacks cultural understanding and the acceptance of prices concerned with indigenous tourism. This research introduces the value of cultural experience into indigenous tourism experiences and establishes a link between the attributes of tourists' preferences and tourism. The data mining methods are used to analyze relevant indigenous tribal data on the cultural experience.FindingsBy providing a different quality of service for various tourists, it is expected to improve the sustainable tourism of the tribe through the experiential value of different attributes and strategies of push–pull factors.Research limitations/implicationsThe experiential activities are based on second-hand data collected from Taitung's indigenous tourism activities, and sample data are the domestic tourism experiences of tourists over the past year. Through empirical analyses, the attributes of tourists' preferences can create the value of the cultural experience for indigenous tourism.Originality/valueThis research explores how indigenous cultural experience can be communicated via learning the value of cultural experience to formulate effective strategies.

Grey wolf optimization based parameter selection for support vector machines

2016 ◽  
Vol 35 (5) ◽  
pp. 1513-1523 ◽  
Author(s):  
Sathish Eswaramoorthy ◽  
N. Sivakumaran ◽  
Sankaranarayanan Sekaran
Keyword(s):  
Design Methodology ◽  
Support Vector ◽  
Svm Classifier ◽  
Grey Wolf Optimizer ◽  
Grey Wolf ◽  
Grey Wolf Optimization ◽  
Content Type ◽  
Vector Machines ◽  
Human Perceptions ◽  
Selection For

Purpose The purpose of this paper is to tune support vector machine (SVM) classifier using grey wolf optimizer (GWO). Design/methodology/approach The schema of the work aims at extracting the features from the collected data followed by a SVM classifier and metaheuristic optimization to tune the classifier parameters. Findings The optimal tuning of classifier parameters lowers errors due to manual elucidation and decreases the risk in human perceptions and repeated visual dignosis. Originality/value A novel, GWO based tuning algorithm is used for SVM classifier, which is implemented in classifying the complex and nonlinear biomedical signals like intracranial electroencephalogram.

scholarly journals Ontology-based text summarization. The case of Texminer

2014 ◽  
Vol 32 (2) ◽  
pp. 229-248
Author(s):  
Pedro Hípola ◽  
José A. Senso ◽  
Amed Leiva-Mederos ◽  
Sandor Domínguez-Velasco
Keyword(s):  
Language Processing ◽  
Design Methodology ◽  
Coastal Engineering ◽  
Text Summarization ◽  
Support Vector ◽  
Knowledge Domain ◽  
Cognitive Approach ◽  
Specific Knowledge ◽  
Content Type ◽  
Cognitive User

Purpose – The purpose of this paper is to look into the latest advances in ontology-based text summarization systems, with emphasis on the methodologies of a socio-cognitive approach, the structural discourse models and the ontology-based text summarization systems. Design/methodology/approach – The paper analyzes the main literature in this field and presents the structure and features of Texminer, a software that facilitates summarization of texts on Port and Coastal Engineering. Texminer entails a combination of several techniques, including: socio-cognitive user models, Natural Language Processing, disambiguation and ontologies. After processing a corpus, the system was evaluated using as a reference various clustering evaluation experiments conducted by Arco (2008) and Hennig et al. (2008). The results were checked with a support vector machine, Rouge metrics, the F-measure and calculation of precision and recall. Findings – The experiment illustrates the superiority of abstracts obtained through the assistance of ontology-based techniques. Originality/value – The authors were able to corroborate that the summaries obtained using Texminer are more efficient than those derived through other systems whose summarization models do not use ontologies to summarize texts. Thanks to ontologies, main sentences can be selected with a broad rhetorical structure, especially for a specific knowledge domain.

Categorization of fabric design using multi-class least-square support vector machine

2014 ◽  
Vol 26 (1) ◽  
pp. 58-66 ◽  
Author(s):  
A. Ghosh ◽  
T. Guha ◽  
R. Bhar
Keyword(s):  
Pattern Recognition ◽  
Design Methodology ◽  
Inequality Constraints ◽  
Recognition System ◽  
Least Square ◽  
Support Vector ◽  
Content Type ◽  
Reasonable Degree ◽  
Vector Machines ◽  
Fabric Design

Purpose – The purpose of this paper is to give an approach for categorization of diverse textile designs using their textural features as extracted from their gray images by means of multi-class least-square support vector machines (LS-SVM). Design/methodology/approach – In this work, the authors endeavor to devise a pattern recognition system based on LS-SVM which performs a multi-class categorization of three basic woven designs namely plain, twill and sateen after analyzing their features. Findings – The result establishes that LS-SVM is able to classify the fabric design with a reasonable degree of accuracy and it outperforms the standard SVM. Originality/value – The algorithmic simplicity of LS-SVM resulting from replacement of inequality constraints by equality ones and ability of handling noisy data by accommodating an error variable in its algorithm make it eminently suitable for textile pattern recognition. This paper offers a maiden application of LS-SVM in textile pattern recognition.

scholarly journals How perceived risk, benefit and trust determine user Fintech adoption: a new dimension for Islamic finance

foresight ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Muhammad Ali ◽  
Syed Ali Raza ◽  
Bilal Khamis ◽  
Chin Hong Puah ◽  
Hanudin Amin
Keyword(s):  
Perceived Risk ◽  
Design Methodology ◽  
Economies Of Scale ◽  
Islamic Finance ◽  
Self Administration ◽  
Content Type ◽  
Intention To Adopt ◽  
Perceived Benefit ◽  
Sample Data ◽  
User Trust

Purpose This study’s objectives are twofold; first, this paper aims to explore the determinants of perceived benefit and perceived risk of Islamic Fintech. Second, this study examines the influence of perceived benefit, perceived risk and user trust on the intention to adopt Islamic Fintech. Design/methodology/approach The sample of 350 was distributed among the respondents, while a usable sample of 321 was retained for the analysis. The study performed a self-administration survey to collect the sample data while the hypothesized model was tested using SmartPLS. Findings The results revealed that perceived benefit and perceived risk were significant and positively influenced by their factors. Moreover, perceived benefits showed a positive and significant impact on trust. However, perceived risk had a negative and significant impact on trust. The results also found a strong positive and significant relationship between trust and intention to adopt Islamic Fintech. Originality/value The outcome of this research may be used to develop strategies for Fintech and enables the financial sector to attain economies of scale in the world.

The effect of students' conceptions of feedback on academic self-efficacy and self-regulation: evidence from higher education in Pakistan

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shafaque Fatima ◽  
Muhammad Ali ◽  
Muhammad Ismail Saad
Keyword(s):  
Higher Education ◽  
Self Efficacy ◽  
Structural Equation ◽  
Design Methodology ◽  
Self Regulation ◽  
Equation Modeling ◽  
Comprehensive Strategy ◽  
Content Type ◽  
Sample Data ◽  
Academic Self Efficacy

PurposeThis study investigated the influence of students' conceptions of feedback (ScoF) dimensions on academic self-efficacy (SE) and self-regulation (SRG).Design/methodology/approachThe study employed the partial least squares structural equation modeling (PLS-SEM) approach on a sample data of 528 students from ten different universities of Karachi city.FindingsResults indicate that active use of feedback (AUF) and enjoyment (ENJ) has a positive and significant impact on SE, while ignorance showed an adverse and significant effect on SE. Additionally, SE showed its positive and significant influence on self-regulation. However, meet expectation (MEXPT), peers’ help (PHP) and tutor comment (TC) showed a positive but insignificant impact on SE.Originality/valueThe study provides useful insights for academicians and policymakers to develop a comprehensive strategy for university students to improve their academic SE and self-regulation.

Digital library service model for predictive analysis of user satisfaction based on multivariate fuzzy logic

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ridhima Mehta
Keyword(s):  
Fuzzy Logic ◽  
Digital Library ◽  
Digital Libraries ◽  
User Satisfaction ◽  
Design Methodology ◽  
Qualitative Assessment ◽  
Data Set ◽  
Content Type ◽  
Sample Data ◽  
Fuzzy Logic Technique

Purpose This paper aims to evaluate the user satisfaction criterion for qualitative assessment of timeliness and efficacy of digital libraries based on the multivariate fuzzy logic technique. Design/methodology/approach In this paper, the performance of digital library services using fuzzy logic modeling are evaluated. This model based on fuzzy logic control is used to compute the dynamic response of users by using multiple independent variables. These parameters with inherent uncertainties in practical scenarios are characterized by fuzzy linguistic information. Findings Several parameters determining the user satisfaction metric in the deployment of digital library exhibit implicit uncertainties which can be intelligently modeled by means of fuzzy control systems. Given the sample data set for the proposed fuzzy multi-attribute decision-making framework, the simulation results are used to compute various error performance measures in the estimation of the fuzzy output variables. Research limitations/implications The size of the considered sample data set is considerably small. Scalable real-world data sets can be used to reinforce the statistical efficiency and accuracy of the proposed model. Moreover, other techniques such as evolutionary multi-objective optimization and the Markovian process can be implemented to explore the efficient correlation between different parameters influencing the users’ behavior and facilitate the general application of the proposed technique. Originality/value The paper applied a fuzzy design methodology in which several attributes related to the service of digital library and the affiliated online resource provisions are used to assess their synchronous impact on user convenience in accessing and manipulating the library information. End-users’ satisfaction is crucial for quality-based valuation of compliance with the time limitations and proficiency of digital libraries.

Sign in / Sign up

Export Citation Format

Share Document