Ekstraksi TF-IDF untuk Kansei Word dalam Perancangan Interface E-Kinerja

E-performance web-based software is used to manage and assess the performance of employees in local government agencies. In the process, some of the local governments racing to create and develop E-performance applications. But there are still many E-performance applications that fail because they don't get a good response from their users in this case the State Civil Apparatus. Then it should be carried out supporting studies in the implementation process of making E-performance applications. One method to determine what is needed by the application of information systems in accordance with what is desired by users emotionally is the Kansei Engineering method. Because through Kansei Engineering can be investigated from various points of view that encourage users to use the information system application. In this research, an application program was created using the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to select and determine several words from a few sentences in an article that will be used as a kansei word. After the screening and selection finally obtained as many as 20 words used as kansei words. A total of 30 participants were involved in this study, namely the State Civil Apparatus in the Government of Bandung City. Furthermore, the results of the questionnaire were processed using multivariate statistical analysis which includes Correlation Coefficient Analysis (CCA), Principal Component Analysis (PCA), Factor Analysis (FA) and Partial Least Square (PLS). After passing through multivariate statistical analysis, the main factor of emotion concept in the design of the E-performance interface is obtained, the optimal factor. But there are other factors supporting the concept of emotion as an alternative design in designing the E-performance interface, the Smart factor. So as to obtain recommendations for designing the E-performance interface produced through the Kansei Engineering method approach in the form of a proposed matrix in which there are several design elements based on the "Optimal" emotional concept

Download Full-text

Wood discrimination analyses of Pterocarpus tinctorius and endangered Pterocarpus santalinus using DART-FTICR-MS coupled with multivariate statistics

IAWA Journal ◽

10.1163/22941932-40190224 ◽

2019 ◽

Vol 40 (1) ◽

pp. 58-74 ◽

Cited By ~ 7

Author(s):

Maomao Zhang ◽

Guang Jie Zhao ◽

Bo Liu ◽

Tuo He ◽

Juan Guo ◽

...

Keyword(s):

Statistical Analysis ◽

Multivariate Statistical Analysis ◽

Partial Least Square ◽

Least Square ◽

Chemical Information ◽

Ion Cyclotron Resonance ◽

Timber Species ◽

Multivariate Statistical ◽

Fticr Ms ◽

Pterocarpus Santalinus

ABSTRACT Pterocarpus santalinus, listed in CITES Appendix II, is an endangered timber species as a result of illegal harvesting due to its high value and commercial demand. The growing demand for P. santalinus and timbers with the morphologically similar Pterocarpus tinctorius has resulted in confusion as well as identification problems. Therefore, it is of vital importance to explore reliable ways to accurately discriminate between P. santalinus and P. tinctorius. In this study, the method of direct analysis in real time and fourier transform ion cyclotron resonance mass spectrometry (DART-FTICR-MS), combined with multivariate statistical analysis, was used to extract chemical information from xylarium wood specimens and to explore the feasibility of distinguishing these two species. Significant differences were observed in their DART-FTICR-MS spectra. Orthogonal partial least square-discriminant analysis (OPLS-DA) showed the highest prediction, with an accuracy of 100%. These findings demonstrate the feasibility of authenticating wood types using DART-FTICR-MS coupled with multivariate statistical analysis.

Download Full-text

Redesign the User Interface of the Purwakarta Disdukcapil Mobile Application Using Kansei Engineering

SinkrOn ◽

10.33395/sinkron.v7i1.11240 ◽

2022 ◽

Vol 7 (1) ◽

pp. 66-75

Author(s):

Yudhi Raymond Ramadhan ◽

Imam Maruf Nugroho ◽

Imam Khaerul Anwar

Keyword(s):

User Interface ◽

Mobile Application ◽

Partial Least Square ◽

Least Square ◽

Type I ◽

Kansei Engineering ◽

Design Factor ◽

Design Elements ◽

Ui Design ◽

Emotional Factors

The function and usability of a mobile application are the main reasons for making the application. In addition, the User Interface (UI) design factor is also an important consideration in making a mobile application. Good UI design is the main attraction for the application to use. There are many ways to make a good UI design. Kansei Engineering (KE) is one of the methods that can be used in the UI design process. Since the creation of the Mobile Disdukcapil application, there has never been a study on the application's design interface. This research aims to make recommendations on design elements desired by users. The KE method can detect the user's feelings towards an interface. So that the KE method will produce a UI design for the Disdukcapil mobile application that is liked by the user. The methodology used refers to the Kansei Engineering Type I methodology. This research uses Kansei Words to represent the emotional factors of the user when viewing a product specimen. Kansei Word used as many as 10 words related to the UI display on the mobile application. The mobile application specimens used were 5 specimens, which were taken from various similar applications. This study involved 80 participants to fill out the questionnaire. The results of the questionnaire were processed using multivariate statistical analysis, namely Cronbach's Alpha, Coefficient Correlation Analysis (CCA), Principal Component Analysis (PCA), Factor Analysis (FA), and Partial Least Square (PLS). The results of this study are in the form of recommendations for UI design elements based on the most dominant emotional factors. Based on the results of data processing, the dominant emotional factors are "Colorful" and "Simple".

Download Full-text

Implementasi Kansei Engineering pada Aplikasi E-learning Untuk Sekolah Menengah Kejuruan

JURNAL SISTEM INFORMASI BISNIS ◽

10.21456/vol9iss2pp165-176 ◽

2019 ◽

Vol 9 (2) ◽

pp. 165

Author(s):

Yoga Megasyah

Keyword(s):

Teaching And Learning ◽

Logical Consequence ◽

Principal Component ◽

Word List ◽

Partial Least Square ◽

Least Square ◽

Kansei Engineering ◽

Multivariate Statistical ◽

Coefficient Corrélation ◽

E Learning

E-learning is the basis and logical consequence of the development of information and communication technology. With E-learning, teaching and learning methods in schools that use technology through electronic media such as computers, laptops, netbooks, or smartphones with internet networks or others. This study uses Kansei Word to detect the feelings of users of E-learning applications. The Kansei Word list is used as many 15 words related to the appearance of the E-learning application. E-learning application specimens used 8 specimens. This study involved 80 participants consisting of 40 students from SMK PGRI 3 Cimahi, 40 students from SMK 4 Padalarang. The questionnaire results from participants were then processed using multivariate statistical analysis, namely Cronbach's Alpha, Coefficient Correlation Analysis (CCA), Principal Component Analysis (PCA), Factor Analysis (FA) and Partial Least Square (PLS) analysis. This study produced 3 recommendations for the design of E-learning application. This recommendation is the result of the Kansei Engineering process which comes from 3 groups of participant data, namely groups of data of all participants, participants of SMK PGRI 3 Cimahi students and participants of SMK 4 Padalarang students.

Download Full-text

Combined multivariate statistical and flux balance analyses uncover media bottlenecks to the growth and productivity of CHO cell cultures

10.22541/au.162696287.70196763/v1 ◽

2021 ◽

Author(s):

Hock Chuan Yeo ◽

Seo-Young Park ◽

Tessa Tan ◽

Say Kong Ng ◽

Meiyappan Lakshmanan ◽

...

Keyword(s):

Statistical Analysis ◽

Cell Cultures ◽

Cho Cells ◽

Multivariate Statistical Analysis ◽

Chinese Hamster ◽

Partial Least Square ◽

Multivariate Statistical ◽

Flux Balance ◽

A Genome ◽

Commercial Medium

Chinese hamster ovary (CHO) cells are widely used for producing recombinant proteins. To enhance their growth, productivity, and product quality, practically media reformulation has been one of key focuses with several technical challenges which are due to the myriad of intricate molecular and regulatory mechanisms underlying the media effects on culture behaviours; it is highly required to systematically characterize metabolic bottlenecks of cell cultures in various media conditions. To do so, we combined multivariate statistical analysis with flux balance analysis of a genome-scale metabolic model of CHO cells based on the culture profiles of CHO-DG44 under one commercial medium and two in-house media. At the outset, we used partial least square regression to identify metabolite exchanges that are correlated to specific growth and productivity. By using a commercial medium as reference, we found sub-optimal level of four nutrients and two metabolic wastes that plausibly hinder cell growth and productivity with in-house media. Subsequently, we elucidated that the recycling of lactate and ammonia wastes to be affected by both glutamine and asparagine metabolisms mechanistically, and further modulated by hitherto unsuspected folate and choline supplements. In summary, the current work successfully demonstrated how multivariate statistical analysis can be synergistically combined with in silico analysis of metabolic models to uncover the mechanistic elements underlying the differing performance of various media. Our approach for the systematic identification of promising nutrient targets thus paves the way for cell culture medium reformulation to enhance cellular growth and recombinant protein production.

Download Full-text

Emotional responses in augmented reality based M-learning applications using Kansei engineering for secondary school students

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v24.i3.pp1846-1854 ◽

2021 ◽

Vol 24 (3) ◽

pp. 1846

Author(s):

Farah Asyikin Jasmy ◽

Fauziah Redzuan ◽

Rogayah Abdul Majid ◽

Norisan Abd Karim

Keyword(s):

Augmented Reality ◽

Secondary School ◽

Mobile Learning ◽

Mobile Applications ◽

Emotional Responses ◽

Partial Least Square ◽

Least Square ◽

Kansei Engineering ◽

Design Elements ◽

Pls Analysis

Design that evoked emotions are one of the main concerning issues in developing mobile applications for online learning in general and for augmented reality (AR) based mobile learning applications in specific. Emotional design could attract users by creating different feelings while using AR-based mobile learning applications. Suitable emotions related to design could motivate students towards fascinating learning experiences. The aim of this research is to evaluate the emotional responses of the students based on different designs in AR-based mobile learning applications using Kansei engineering technique. In this research, about thirty-two students from secondary school were involved in an experiment to identify the Kansei (emotion) words for AR-based mobile applications. The data gathered were analysed using factor analysis (FA), principal component analysis (PCA), and partial least square (PLS) analysis. The results revealed four important pillars of emotions or known as Kansei semantic space such as challenging-thinking, motivated, humorous, preoccupied and also touched as an additional pillar. Based on the PLS analysis of design elements of AR-based mobile learning applications suggested specific design and emotions based on the pillars. In conclusion, this research is motivated to give affective formulae that would guide the design of AR-based mobile learning materials in the future.

Download Full-text

Phytochemical analysis of trifoliate orange during fermentation by HPLC–DAD–ESI–MS/MS coupled with multivariate statistical analysis

Acta Chromatographica ◽

10.1556/1326.2020.00818 ◽

2020 ◽

Author(s):

Dan Gao ◽

Chong Woon Cho ◽

Le Ba Vinh ◽

Jin Hyeok Kim ◽

Young Ho Kim ◽

...

Keyword(s):

Quality Control ◽

Statistical Analysis ◽

Multivariate Statistical Analysis ◽

Partial Least Square ◽

Array Detector ◽

Phytochemical Analysis ◽

Chemical Compositions ◽

Trifoliate Orange ◽

Multivariate Statistical ◽

Esi Ms

AbstractDuring the process of fermentation, the chemical compositions of trifoliate orange (Poncirus trifoliate (L). Raf) changed greatly. To provide a completely phytochemical profile, high-performance liquid chromatography-diode array detector-hyphenated with tandem mass spectrometry (HPLC–DAD–ESI-MS/MS) has been successfully applied to screen and identify the unknown constituents of trifoliate orange during fermentation, which make it available for the quality control of fermented products. Multivariate statistical analysis was performed to classify the trifoliate oranges based on the status of fermentation. A total of 8 components were identified among the samples. Hierarchical Clustering Analysis (HCA) and Principal Component Analysis (PCA) demonstrated the fermented and unfermented trifoliate oranges were obviously different, an effective and reliable Partial Least Square Discriminate Analysis (PLS-DA) technique was more suitable to provide accurate discrimination of test samples based their different chemical patterns. Furthermore, a permutation validated the reliability of PLS-DA and variable importance plot revealed that the characterized syringing, naringin, and poncirin showed the high ability to distinguish the trifoliate oranges during fermentation. The present investigation could provide detailed information for the quality control and evaluation of trifoliate oranges during the fermentation process.

Download Full-text

Implementasi Kansei Engineering Dalam Perancangan Desain Karakter Dengan Prinsip Appeal (Studi Kasus : Karakter dalam Film Battle of Surabaya)

Creative Information Technology Journal ◽

10.24076/citec.2020v7i2.254 ◽

2021 ◽

Vol 7 (2) ◽

pp. 95

Author(s):

Dessy Riana Sari ◽

M. Suyanto ◽

Amir Fatah Sofyan

Keyword(s):

Statistical Analysis ◽

Kansei Engineering ◽

Scientific Contribution ◽

Multivariate Statistical ◽

Design Elements ◽

Face Shape ◽

Character Design ◽

The Creation ◽

Animated Characters

Dalam penciptaan desain karakter animasi erat kaitanya dengan prinsip Appeal, namun prinsip animasi ini sangat bergantung terhadap penilaian pribadi. Sehingga diperlukan cara yang sistematis untuk memahami penilaian prinsip appeal dalam penciptaan degain karakter animasi. Penelitian ini menggunakan Metode Kansei Engeneering untuk mendapatkan penilaian mengenai prinsip appeal dengan menggunakan studi kasus karakter dari animasi Battle of Surabaya. Metode Kansei Engeneering digunakan berdasarkan perasaan psikologis yang tercermin melalui kata kansei. Analisis yang digunakan dalam penelitian ini menggunakan analisis statistik multivariant. Hasil dari penelitian ini memberikan rekomendasi elemen desain karakter yang dihasilkan dengan prinsip appeal melalui pendekatan Kansei Engenering. Elemen desain pada penelitian ini diperoleh dari studi kasus karakter animasi di film Battle of Surabaya yang berpedoman dengan Kansei Word. Hasil analisis menunjukan bahwa pengaruh appeal pada design karakter dapat dicapai dengan elemen desain seperti Teritary Color, Near Realis, Hooded Eyes, dan Square Face Shape. Penelitian ini diharapkan dapat memberikan kontribusi ilmiah mengenai penciptaan desain karakter yang mengacu pada prinsip appeal. Kata Kunci—Kansei Engeneering, Appeal, Desain KarakterAbstractWhen created animated character designs closely related to the principle of Appeal, but the principle of animation is very dependent on personal judgment. A systematic way to understand the appraisal principle is required in the creation of animated characters. This research uses Kansei Engeneering Method to get consideration of comparative principles by using case studies of characters from the Battle of Surabaya animation. The Kansei Engeneering method is used based on psychological feelings that are reflected through the word kansei. The analysis in this research uses multivariate statistical analysis. This researchy provides recommendations for the character design elements produced with the principle of appeal through the Kansei Engenering approach. The design elements in this study were obtained from a case study of animated characters in the film Battle of Surabaya, which is guided by Kansei Word. The analysis shows that the effect of appeal on character design can be achieved with design elements such as Teritary Color, Near Realist, Hooded Eyes, and Square Face Shape. This research is expected to make a scientific contribution regarding the creation of character designs that refer to the principle of appeal.Keywords— Kansei Engeneering, Appeal, Character design

Download Full-text

Electrochemical Sensors Coupled with Multivariate Statistical Analysis as Screening Tools for Wine Authentication Issues: A Review

Chemosensors ◽

10.3390/chemosensors8030059 ◽

2020 ◽

Vol 8 (3) ◽

pp. 59

Author(s):

Elisabeta-Irina Geană ◽

Corina Teodora Ciucure ◽

Constantin Apetrei

Keyword(s):

Pattern Recognition ◽

Statistical Analysis ◽

Multivariate Statistical Analysis ◽

Electrochemical Sensors ◽

Electrochemical Techniques ◽

Partial Least Square ◽

Screening Tools ◽

Multivariate Statistical ◽

Advantages And Disadvantages ◽

Pattern Recognition Methods

Consumers are increasingly interested in the characteristics of the products they consume, including aroma, taste, and appearance, and hence, scientific research was conducted in order to develop electronic senses devices that mimic the human senses. Thanks to the utilization of electroanalytical techniques that used various sensors modified with different electroactive materials coupled with pattern recognition methods, artificial senses such as electronic tongues (ETs) are widely applied in food analysis for quality and authenticity approaches. This paper summarizes the applications of electrochemical sensors (voltammetric, amperometric, and potentiometric) coupled with unsupervised and supervised pattern recognition methods (principal components analysis (PCA), linear discriminant analysis (LDA), partial least square (PLS) regression, artificial neural network (ANN)) for wine authenticity assessments including the discrimination of varietal and geographical origins, monitoring the ageing processes, vintage year discrimination, and detection of frauds and adulterations. Different wine electrochemical authentication methodologies covering the electrochemical techniques, electrodes types, functionalization sensitive materials and multivariate statistical analysis are emphasized and the main advantages and disadvantages of using the proposed methodologies for real applications were concluded.

Download Full-text