Exploration of noisy data in differential electronic nose

2016 ◽  
Vol 35 (4) ◽  
pp. 1382-1392
Author(s):  
Stanislaw Osowski ◽  
Krzysztof Siwek ◽  
Tomasz Grzywacz
Keyword(s):  
Electronic Nose ◽  
Support Vector ◽  
Noisy Environment ◽  
Classifier Systems ◽  
Content Type ◽  
On Line ◽  
Sensor Signals ◽  
High Level ◽  
Baseline Estimation

Purpose – The paper is concerned with exploration of sensor signals in differential electronic nose. It is a special type of nose, which applies double sensor matrices and exploits only their differential signals, which are used in recognition of patterns associated with them. The purpose of this paper is to study the application of differential nose in dynamic measurement of aroma of 11 brands of cigarettes. Design/methodology/approach – The most important task in pattern recognition using electronic nose is its resistance to the noise corrupting the measurement. The authors will analyze and compare the performance of the nose in the noisy environment by applying two classifier systems: the support vector machine (SVM) and random forest (RF) of decision trees. Findings – On the basis of numerical experiments the authors have found that application of SVM as the classifier in the electronic nose is more advantageous than RF, especially at high level of noise and small number of measuring sensors. Its application allowed to recognize 11 brands of cigarettes with the accuracy close to 100 percent. Practical implications – Thanks to application of two identical sensors working in a differential mode the authors avoid the baseline estimation and thus the solution is well suited for on-line dynamic measurements of the process. Originality/value – The paper has studied the advantages and limitations of the differential electronic nose following from the existence of the noise, corrupting the measurements. It has pointed an important role of the applied classifier system in getting the electronic nose of the highest quality.

scholarly journals Mining Data of Noisy Signal Patterns in Recognition of Gasoline Bio-Based Additives using Electronic Nose

2017 ◽  
Vol 24 (1) ◽  
pp. 27-44 ◽  
Author(s):  
Stanisław Osowski ◽  
Krzysztof Siwek
Keyword(s):  
Support Vector Machine ◽  
Electronic Nose ◽  
Data Clustering ◽  
Wavelet Transformation ◽  
Principal Component ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Noisy Environment ◽  
Special Stress ◽  
Sensor Signals

Abstract The paper analyses the distorted data of an electronic nose in recognizing the gasoline bio-based additives. Different tools of data mining, such as the methods of data clustering, principal component analysis, wavelet transformation, support vector machine and random forest of decision trees are applied. A special stress is put on the robustness of signal processing systems to the noise distorting the registered sensor signals. A special denoising procedure based on application of discrete wavelet transformation has been proposed. This procedure enables to reduce the error rate of recognition in a significant way. The numerical results of experiments devoted to the recognition of different blends of gasoline have shown the superiority of support vector machine in a noisy environment of measurement.

A novel sensor array and classifier optimization method of electronic nose based on enhanced quantum-behaved particle swarm optimization

Sensor Review ◽  
2014 ◽  
Vol 34 (3) ◽  
pp. 304-311 ◽  
Author(s):  
Pengfei Jia ◽  
Fengchun Tian ◽  
Shu Fan ◽  
Qinghua He ◽  
Jingwei Feng ◽  
...  
Keyword(s):  
Particle Swarm Optimization ◽  
Wound Infection ◽  
Electronic Nose ◽  
Classification Accuracy ◽  
Sensor Array ◽  
Particle Swarm ◽  
Optimization Method ◽  
Support Vector ◽  
Swarm Optimization ◽  
Content Type

Purpose – The purpose of the paper is to propose a new optimization algorithm to realize a synchronous optimization of sensor array and classifier, to improve the performance of E-nose in the detection of wound infection. When an electronic nose (E-nose) is used to detect the wound infection, sensor array’s optimization and parameters’ setting of classifier have a strong impact on the classification accuracy. Design/methodology/approach – An enhanced quantum-behaved particle swarm optimization based on genetic algorithm, genetic quantum-behaved particle swarm optimization (G-QPSO), is proposed to realize a synchronous optimization of sensor array and classifier. The importance-factor (I-F) method is used to weight the sensors of E-nose by its degree of importance in classification. Both radical basis function network and support vector machine are used for classification. Findings – The classification accuracy of E-nose is the highest when the weighting coefficients of the I-F method and classifier’s parameters are optimized by G-QPSO. All results make it clear that the proposed method is an ideal optimization method of E-nose in the detection of wound infection. Research limitations/implications – To make the proposed optimization method more effective, the key point of further research is to enhance the classifier of E-nose. Practical implications – In this paper, E-nose is used to distinguish the class of wound infection; meanwhile, G-QPSO is used to realize a synchronous optimization of sensor array and classifier of E-nose. These are all important for E-nose to realize its clinical application in wound monitoring. Originality/value – The innovative concept improves the performance of E-nose in wound monitoring and paves the way for the clinical detection of E-nose.

Promoting authenticity through celebrity brands

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Amanda Kennedy ◽  
Stacey M. Baxter ◽  
Alicia Kulczynski
Keyword(s):  
Design Methodology ◽  
Consumer Attitudes ◽  
Purchase Intentions ◽  
Consumer Perceptions ◽  
Positive Outcomes ◽  
Content Type ◽  
Monetary Compensation ◽  
High Level ◽  
Practical Implications

Purpose This paper aims to examine the importance of celebrity brands in influencing consumer perceptions of celebrity authenticity, which drives positive consumer attitudes and intentions. In addition, the notion of low-celebrity investment is investigated as a factor that diminishes the positive outcomes associated with celebrity brands. Design/methodology/approach Study 1 examines the effect of brand situation (endorsement versus celebrity brand) on consumer attitudes and intentions. Studies 2 and 3 investigate the role of celebrity authenticity in explaining the effects observed in Study 1. Study 4 examines celebrity investment as a bound of the phenomenon. Findings Study 1 demonstrates that consumers report heightened attitudes and intentions towards celebrity brands when compared to endorsements. Studies 2 and 3 provide evidence that authenticity explains the effects observed in Study 1. Results of Study 4 show that when consumers are aware of low-celebrity investment, the celebrity is viewed as inauthentic regardless of brand situation. Research limitations/implications This research is limited as it focuses only on known celebrity endorsers who were matched with products that had a high level of fit. In addition, purchase intentions were measured as opposed to the study of actual purchase behaviour. Practical implications This research has important implications for the development of endorsements and celebrity brands by demonstrating that consumers view celebrities as authentic when they are involved with brands for reasons other than monetary compensation. Originality/value This research shows that consumers have heightened attitudes and intentions towards celebrity brands compared to endorsements. This research identifies celebrity authenticity as the process underlying the observed phenomenon. However, celebrity investment is identified as a boundary condition demonstrating that knowledge of low investment results in a celebrity being viewed as inauthentic.

Customer centricity and guanxi prevalence as social capital: a study of international business relationships

2018 ◽  
Vol 33 (8) ◽  
pp. 1209-1220 ◽  
Author(s):  
Angeline Close Scheinbaum ◽  
Stephen W. Wang
Keyword(s):  
Structural Equation ◽  
Equation Modeling ◽  
Global Business ◽  
Global Marketing ◽  
Logistics Industry ◽  
Content Type ◽  
Global Logistics ◽  
High Level ◽  
Customer Centricity

Purpose This research blends perspectives of the Eastern phenomenon of guanxi with the more Western perspectives of relationship marketing and customer centricity. Extending scholarship on guanxi in marketing (e.g. Park and Luo, 2001; Sheu and Hu, 2009; Luo et al., 2008; Fowler and Reisenwitz, 2014), the objective is to highlight the indirect role of customer centricity (i.e. how visible or central it is for the business partner to communicate with/have information sharing with), for firms in regions with a prevalence of guanxi. Design/methodology/approach The empirical model is tested in context of global marketing in the business-to-business (B2B) logistics industry (n = 508). A total of 508 global logistics employees and managers with experience in global business participated in the survey in Taiwan. Structural equation modeling was used for data analysis with multi-group analyses. Findings Customer centricity intensifies positive outcomes of guanxi prevalence. Specifically, a high level of customer centricity strengthens established associations among guanxi prevalence, trust, relationship commitment and firm performance. Originality/value While most work on guanxi has a focus in China, this research focuses on Taiwan. While building on a wealth of literature, relatively less work has focused on customer centricity.

Does transformational leadership always matter in frontline service roles?

2018 ◽  
Vol 28 (6) ◽  
pp. 733-751 ◽  
Author(s):  
Keo Mony Sok ◽  
Phyra Sok ◽  
Lan Snell ◽  
Pingping Qiu
Keyword(s):  
Customer Service ◽  
Service Performance ◽  
Hierarchical Regression ◽  
Content Type ◽  
Service Employees ◽  
High Level ◽  
Frontline Service Employees ◽  
The Relationship ◽  
Frontline Service

Purpose The purpose of this paper is to examine the role of frontline service employees (FSEs) motivation (enjoyment of work and driven to work) and ability (customer service ability) in the relationship between TFL and employee service performance. Design/methodology/approach This is a survey-based study which involves 534 FSEs and 135 supervisors in a hair salon setting. Hierarchical regression analysis was used to test the proposed hypotheses. Findings Results show that TFL is significantly related to employee service performance; this relationship is enhanced with the presence of driven to work; yet, it is neutralized with the presence of enjoyment of work. Further, the three-way interaction of TFL, enjoyment of work and customer service ability as well as TFL driven to work, and customer service ability are negatively associated with employee service performance. Practical implications The results advance service managers’ understanding of the importance of FSEs motivation and ability if they are to fully reap the benefits from their FSEs. The role of leader is not always effective in all situations. FSEs with high level of enjoyment of work and customer service ability would least rely on the guidance and support from the supervisors. Originality/value This research is one of the first to examine the role of subordinate’s characteristics (motivation – enjoyment of work and driven to work and ability – customer service ability) as the key moderators in the relationship between TFL and employee service performance.

Reciprocity and commitment in online travel communities

2019 ◽  
Vol 119 (2) ◽  
pp. 397-411 ◽  
Author(s):  
Daniel Belanche ◽  
Luis V. Casaló ◽  
Carlos Flavián ◽  
Miguel Guinalíu
Keyword(s):  
Social Exchange ◽  
Structural Equation ◽  
Social Exchange Theory ◽  
Active Participation ◽  
Equation Modeling ◽  
Relational Capital ◽  
Content Type ◽  
High Level ◽  
Online Travel

PurposeWith social exchange theory as a basis, the purpose of this paper is to seek a better understanding of advice processes in online travel communities, which offer crucial advice for travelers’ decisions. It also predicts that relational capital variables (commitment, reciprocity perceptions) moderate the main relationships.Design/methodology/approachData from a web survey of 456 users of online travel communities affirm the scale’s validity and provide the input for structural equation modeling and multisample analyses of the hypotheses.FindingsHigher levels of commitment reinforce the effect of following past advice on passive and active participation intentions. Users’ perceptions of reciprocity in the community strengthen the influence of following past advice on active participation. However, a high level of reciprocity causes users following past advice to reduce their intentions to continue following that advice.Practical implicationsManagement tactics should specify active and passive participation in online travel communities. Specifically, to encourage the creation of high-quality new content, community managers should create interactive environments marked by high levels of reciprocity and commitment.Originality/valueThis research elucidates the role of relational capital variables in advice processes and advances understanding of online travel communities.

Soft computing based audio signal analysis for accident prediction

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hima Bindu Valiveti ◽  
Anil Kumar B. ◽  
Lakshmi Chaitanya Duggineni ◽  
Swetha Namburu ◽  
Swaraja Kuraparthi
Keyword(s):  
Feature Extraction ◽  
Audio Signal ◽  
Support Vector ◽  
Classification Algorithms ◽  
Spectral Features ◽  
Road Accidents ◽  
Content Type ◽  
Detection Techniques ◽  
Car Crashes ◽  
High Level

Purpose Road accidents, an inadvertent mishap can be detected automatically and alerts sent instantly with the collaboration of image processing techniques and on-road video surveillance systems. However, to rely exclusively on visual information especially under adverse conditions like night times, dark areas and unfavourable weather conditions such as snowfall, rain, and fog which result in faint visibility lead to incertitude. The main goal of the proposed work is certainty of accident occurrence. Design/methodology/approach The authors of this work propose a method for detecting road accidents by analyzing audio signals to identify hazardous situations such as tire skidding and car crashes. The motive of this project is to build a simple and complete audio event detection system using signal feature extraction methods to improve its detection accuracy. The experimental analysis is carried out on a publicly available real time data-set consisting of audio samples like car crashes and tire skidding. The Temporal features of the recorded audio signal like Energy Volume Zero Crossing Rate 28ZCR2529 and the Spectral features like Spectral Centroid Spectral Spread Spectral Roll of factor Spectral Flux the Psychoacoustic features Energy Sub Bands ratio and Gammatonegram are computed. The extracted features are pre-processed and trained and tested using Support Vector Machine (SVM) and K-nearest neighborhood (KNN) classification algorithms for exact prediction of the accident occurrence for various SNR ranges. The combination of Gammatonegram with Temporal and Spectral features of the validates to be superior compared to the existing detection techniques. Findings Temporal, Spectral, Psychoacoustic features, gammetonegram of the recorded audio signal are extracted. A High level vector is generated based on centroid and the extracted features are classified with the help of machine learning algorithms like SVM, KNN and DT. The audio samples collected have varied SNR ranges and the accuracy of the classification algorithms is thoroughly tested. Practical implications Denoising of the audio samples for perfect feature extraction was a tedious chore. Originality/value The existing literature cites extraction of Temporal and Spectral features and then the application of classification algorithms. For perfect classification, the authors have chosen to construct a high level vector from all the four extracted Temporal, Spectral, Psycho acoustic and Gammetonegram features. The classification algorithms are employed on samples collected at varied SNR ranges.

Novel and practical idea generation

2019 ◽  
Vol 11 (3) ◽  
pp. 325-343 ◽  
Author(s):  
Chih-Huei Ko ◽  
Sou-Chin Wu ◽  
Chien-Yu Chen
Keyword(s):  
New Product Development ◽  
Virtual Communities ◽  
Computer Mediated Communication ◽  
Idea Generation ◽  
Individual Characteristics ◽  
Content Type ◽  
Brand Knowledge ◽  
Interactive Behaviors ◽  
High Level

Purpose Numerous studies have examined individual attitudes and behaviors in both face-to-face (FTF) communication and computer-mediated communication (CMC). However, little research has focused on differences between FTF communication and CMC with respect to idea generation for new product development or on the role of their individual characteristics. Thus, the purpose of this study is to examine the influences of FTF, CMC and brand knowledge on idea generation. Design/methodology/approach This study conducted a 4 × 2 quasi-experimental design to examine the effects of four types of interactive groups (low and high level of FTF × low and high level of CMC) and brand knowledge (low and high) on novel and practical idea generation. Data from168 members of the Mondeo Motor Club in Taiwan were assessed. Findings Participants with more FTF interaction were more likely to generate novelty ideas than practicality ideas. In addition, participants with high brand knowledge produced more novel and practical ideas compared with participants with low brand knowledge. However, the empirical findings did not support the moderating role of brand knowledge in the relationship between interactive behaviors and idea generations. Research limitations/implications The results of this study are relevant for facilitating the “novelty” and “practicality” ideas in virtual brand communities. However, this research examined a single community, which may limit the generalizability of its results to other virtual communities. Originality/value Few studies have focused on online idea generation from a consumer-to-consumer (C2C) interaction perspective. The results of this study can assist marketers to understand how C2C interactive behaviors differentiate the “novelty” and “practicality” ideas.

When is transparent packaging beneficial?

2020 ◽  
Vol 48 (8) ◽  
pp. 781-801 ◽  
Author(s):  
Ouidade Sabri ◽  
Hai Van Doan ◽  
Faten Malek ◽  
Hager Bachouche
Keyword(s):  
Perceived Risk ◽  
Purchase Intention ◽  
Product Category ◽  
Perceived Quality ◽  
Content Type ◽  
Mediating Role ◽  
High Level ◽  
Positive Effect ◽  
Moderating Role

PurposeThe purpose of this paper is to demonstrate that the positive effect of packaging transparency on purchase intention is moderated by product quality risk (PQR) associated with the product category.Design/methodology/approachTwo separate experiments were conducted. Study 1 was designed to test the mediating role of perceived quality to account for the positive effect of transparency on purchase intention. Two types of packaging (opaque vs transparent) for a product associated with a high level of PQR were examined. Study 2 extended the findings by introducing the moderating role of PQR. A 2 (type of packaging: opaque vs transparent)*2 (PQR: low vs high) between subjects design was used.FindingsThe moderating role of the product PQR level is established: transparent packaging improves the product perceived quality and brand purchase intention when the product is associated with a high PQR, whereas there is no such preference for transparent packaging when the product is associated with a low PQR.Practical implicationsThe results offer insights to better understand the potential gains from adopting transparent packaging. If a brand manager's main goals are to develop sales, costly investments in research and development of transparent packaging appear to be fruitful only for products associated with high PQR.Originality/valueThis paper contributes to packaging, cue utilisation and perceived risk literatures by evidencing the moderating role of PQR to explain the positive effect of transparency on purchase intention.

EWOM firestorm: young consumers and online community

2019 ◽  
Vol 21 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Sasithorn Suwandee ◽  
Jiraporn Surachartkumtonkun ◽  
Aurathai Lertwannawit
Keyword(s):  
Social Media ◽  
Online Community ◽  
Community Members ◽  
Content Type ◽  
Service Failures ◽  
Young Consumers ◽  
Mixed Factorial Design ◽  
Information Characteristics ◽  
High Level

Purpose This study aims to examine the influence of homophily in an online community and the effect of electronic word of mouth (eWOM) consensus on young consumers’ attitudes. Design/methodology/approach This study implemented an experimental research design using a two (low/high homophily) × two (low/high eWOM consensus) mixed factorial design. This study explores young consumers’ changes in brand attitude after encountering negative eWOM. Findings The results indicate that a high consensus of negative eWOM among online community members leads to significant changes in attitude, while a low consensus of negative eWOM does not produce such an effect. Negative eWOM from either high or low homophilous sources produces significant changes in attitude. There are significant attitude changes when a strong consensus of negative eWOM is received from a source with a high level of homophily. Research limitations/implications Service failures in offline service settings lead to the dissemination of negative eWOM on social media. To handle and prevent social media crises, researchers should understand online crises antecedents relating to information characteristics i.e. eWOM consensus and characteristics of online community members to evaluate the crises impact. Brands should monitor tone and dialogue of online community member on social media to remedy and diminish any damage done to their brand image from negative eWOM. Originality/value This study contributes to the application of social network theory by understanding the role of nodes on negative eWOM effect in social media.

Sign in / Sign up

Export Citation Format

Share Document