ICACSIS 2014 International Conference on Advanced Computer Science and Information System 2012 (ICACSIS 2014) Hotel Ambhara, Jakarta October 18th - 19th, 2014 Committees | Table of Contents | Author's Index | About This CD-ROM Search View Please enable Javascript on your browser to view all the page properly. Copyright Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promortional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from Faculty of Computer Science, Universitas Indonesia, Indonesia. Contacts ICACSIS Committee Email: icacsis@cs.ui.ac.id Phone: +62 21 786 3419 ext. 3225 Faculty of Computer Science, Universitas Indonesia Kampus UI Depok Indonesia - 16424 Phone: +62 21 786 3419 Fax: +62 21 786 3415 Email: humas@cs.ui.ac.id Faculty of Computer Science - Universitas Indonesia ©2014 ICACSIS 2014 International Conference on Advanced Computer Science and Information System 2012 (ICACSIS 2014) Hotel Ambhara, Jakarta October 18th - 19th, 2014 Committees | Table of Contents | Author's Index | About This CD-ROM Committee Honorary Chairs A. Jain, Fellow IEEE, Michigan State University, US T. Fukuda, Fellow IEEE, Nagoya-Meijo University, JP M. Adriani, Universitas Indonesia, ID General Chairs E. K. Budiardjo, Universitas Indonesia, ID D.I. Sensuse, Universitas Indonesia, ID Z.A. Hasibuan, Universitas Indonesia, ID Program Chairs H.B. Santoso, Universitas Indonesia, ID W. Jatmiko, Universitas Indonesia, ID A. Buono, Institut Pertanian Bogor, ID D.E. Herwindiati, Universitas Tarumanagara, ID Section Chairs K. Wastuwibowo, IEEE Indonesia Section, ID Publication Chairs A. Wibisono, Universitas Indonesia, ID Program Committees A. Azurat, Universitas Indonesia, ID A. Fanar, Lembaga Ilmu Pengetahuan Indonesia, ID A. Kistijantoro, Institut Teknologi Bandung, ID A. Purwarianti, Institut Teknologi Bandung, ID A. Nugroho, PTIK BPPT, ID A. Srivihok, Kasetsart University, TH A. Arifin, Institut Teknologi Sepuluh Nopember, ID A.M. Arymurthy, Universitas Indonesia, ID A.N. Hidayanto, Universitas Indonesia, ID B. Wijaya, Universitas Indonesia, ID B. Yuwono, Universitas Indonesia, ID Search B. Hardian, Universitas Indonesia, ID B. Purwandari, Universitas Indonesia, ID B.A. Nazief, Universitas Indonesia, ID B.H. Widjaja, Universitas Indonesia, ID Denny, Universitas Indonesia, ID D. Jana, Computer Society of India, IN E. Gaura, Coventry University, UK E. Seo, Sungkyunkwan University, KR F. Gaol, IEEE Indonesia Section, ID H. Manurung, Universitas Indonesia, ID H. Suhartanto, Universitas Indonesia, ID H. Sukoco, Institut Pertanian Bogor, ID I. Budi, Universitas Indonesia, ID I. Sitanggang, Institut Pertanian Bogor, ID I. Wasito, Universitas Indonesia, ID K. Sekiyama, Nagoya University, JP L. Stefanus, Universitas Indonesia, ID Marimin, Institut Pertanian Bogor, ID M.T. Suarez, De La Salle University, PH M. Fanany, Universitas Indonesia, ID M. Kyas, Freie Universitat Berlin, DE M. Nakajima, Nagoya University, JP M. Widyanto, Universitas Indonesia, ID M. Widjaja, PTIK BPPT, ID N. Maulidevi, Institut Teknologi Bandung, ID O. Sidek, Universiti Sains Malaysia, MY O. Lawanto, Utah State University, US P. Hitzler, Wright State University, US P. Mursanto, Universitas Indonesia, ID S. Bressan, National University of Singapore, SG S. Kuswadi, Institut Teknologi Sepuluh Nopember, ID S. Nomura, Nagaoka University of Technology, JP S. Yazid, Universitas Indonesia, ID T. Basaruddin, Universitas Indonesia, ID T. Hardjono, Massachusetts Institute of Technology, US T. Gunawan, Int. Islamic University Malaysia, MY T.A. Masoem, Universitas Indonesia, ID V. Allan, Utah State University, US W. Chutimaskul, King Mokut’s Univ. of Technology, TH W. Molnar, Public Research Center Henri Tudor, LU W. Nugroho, Universitas Indonesia, ID W. Prasetya, Universiteit Utrecht, NL W. Sediono, Int. Islamic University Malaysia, MY W. Susilo, University of Wollongong, AU W. Wibowo, Universitas Indonesia, ID X. Li, The University of Queensland, AU Y. Isal, Universitas Indonesia, ID Y. Sucahyo, Universitas Indonesia, ID Faculty of Computer Science - Universitas Indonesia ©2014 ICACSIS 2014 International Conference on Advanced Computer Science and Information System 2012 (ICACSIS 2014) Hotel Ambhara, Jakarta October 18th - 19th, 2014 Committees | Table of Contents | Author's Index | About This CD-ROM View: 1-25 | 26-50 | 51-75 Search Evaluation on People Aspect in Knowledge Management System Implementation: A Case Study of Bank Indonesia Putu Wuri Handayani Page(s): 1-9 Abstract | Full Text: PDF Relative Density Estimation using Self-Organizing Maps Denny Page(s): 10-15 Abstract | Full Text: PDF Multicore Computation of Tactical Integration System in the Maritime Patrol Aircraft using Intel Threading Building Block Muhammad Faris Fathoni, Bambang Sridadi Page(s): 16-21 Abstract | Full Text: PDF Government Knowledge Management System Analysis: Case Study Badan Kepegawaian Negara Elin Cahyaningsih, lukman -, Dana Indra Sensuse Page(s): 22-28 Abstract | Full Text: PDF Forecasting the Length of the Rainy Season Using Time Delay Neural Network Agus Buono, Muhammad Asyhar Agmalaro, Amalia Fitranty Almira Page(s): 29-34 Abstract | Full Text: PDF Hybrid Sampling for Multiclass Imbalanced Problem: Case Study of Students' Performance Prediction Wanthanee Prachuabsupakij, Nuanwan Soonthornphisaj Page(s): 35-40 Abstract | Full Text: PDF Interaction between users and buildings: results of a multicreteria analysis Audrey Bona, Jean-Marc Salotti Page(s): 41-46 Abstract | Full Text: PDF Digital watermarking in audio for copyright protection Hemis Mustapha, Boudraa Bachir Page(s): 47-51 Abstract | Full Text: PDF Multi-Grid Transformation for Medical Image Registration Porawat Visutsak Page(s): 52-56 Abstract | Full Text: PDF Creating Bahasa Indonesian - Javanese Parallel Corpora Using Wikipedia Articles Bayu Distiawan Trisedya Page(s): 57-63 Abstract | Full Text: PDF An Extension of Petri Network for Multi-Agent System Representation Pierre Sauvage Page(s): 64-71 Abstract | Full Text: PDF Gamified E-Learning Model Based on Community of Inquiry Andika Yudha Utomo, Afifa Amriani, Alham Fikri Aji, Fatin Rohmah Nur Wahidah, Kasiyah M. Junus Page(s): 72-78 Abstract | Full Text: PDF Model Prediction for Accreditation of Public Junior High School in Bogor Using Spatial Decision Tree Endang Purnama Giri, Aniati Murni Arymurthy Page(s): 79-84 Abstract | Full Text: PDF Application of Decision Tree Classifier for Single Nucleotide Polymorphism Discovery from Next-Generation Sequencing Data Muhammad Abrar Istiadi, Wisnu Ananta Kusuma, I Made Tasma Page(s): 85-89 Abstract | Full Text: PDF Quality Evaluation of Airline’s E-Commerce Website, A Case Study of AirAsia and Lion Air Websites Farah Shafira Effendi, Ika Alfina Page(s): 90-93 Abstract | Full Text: PDF A comparative study of sound sources separation by Independent Component Analysis and Binaural Model Bagus Tris Atmaja Page(s): 94-98 Abstract | Full Text: PDF Enhancing Reliability of Feature Modeling with Transforming Representation into Abstract Behavioral Specification (ABS) Muhammad Irfan Fadhillah Page(s): 99-104 Abstract | Full Text: PDF Classification of Campus E-Complaint Documents using Directed Acyclic Graph Multi-Class SVM Based on Analytic Hierarchy Process Imam Cholissodin, Maya Kurniawati, Indriati, Issa Arwani Page(s): 105-111 Abstract | Full Text: PDF Making Energy-saving Strategies: Using a Cue Offering Interface Yasutaka Kishi, Kyoko Ito, Shogo Nishida Page(s): 112-117 Abstract | Full Text: PDF Knowledge Management System Development with Evaluation Method in Lesson Study Activity Murein Miksa Mardhia, Armein Z.R. Langi, Yoanes Bandung Page(s): 118-123 Abstract | Full Text: PDF Extending V-model practices to support SRE to build Secure Web Application Ala Ali Abdulrazeg Page(s): 124-129 Abstract | Full Text: PDF Shared Service in E-Government Sector: Case Study of Implementation in Developed Countries Ravika Hafizi, Suraya Miskon, Azizah Abdul Rahman Page(s): 130-137 Abstract | Full Text: PDF Implementation of Steganography using LSB with Encrypted and Compressed Text using TEA-LZW on Android Ledya Novamizanti Page(s): 138-143 Abstract | Full Text: PDF Hotspot Clustering Using DBSCAN Algorithm and Shiny Web Framework Karlina Khiyarin Nisa Page(s): 144-147 Abstract | Full Text: PDF Framework Model of Sustainable Supply Chain Risk for Dairy Agroindustry Based on Knowledge Base Winnie Septiani Page(s): 148-154 Abstract | Full Text: PDF View: 1-25 | 26-50 | 51-75 Faculty of Computer Science - Universitas Indonesia ©2014 ICACSIS 2014 International Conference on Advanced Computer Science and Information System 2012 (ICACSIS 2014) Hotel Ambhara, Jakarta October 18th - 19th, 2014 Committees | Table of Contents | Author's Index | About This CD-ROM Search A Achmad Benny Mutiara Achmad Nizar Hidayanto Adhi Kusnadi Aditia Ginantaka Afifa Amriani Agus Buono Agus Widodo Ahmad Eries Antares Ahmad Nizar Hidayanto Ahmad Tamimi Fadhilah Aini Suri Talita Ajeng Anugrah Lestari Ala Ali Abdulrazeg Albertus Sulaiman Alexander Agung Santoso Gunawan Alfan Presekal Alham Fikri Aji Amalia Fitranty Almira Anang Kurnia Andika Yudha Utomo Andreas Febrian Aniati Murni Arymurthy Anthony J.H. Simons Anto S Nugroho Arief Ramadhan Arin Karlina Ario Sunar Baskoro Armein Z.R. Langi 467-471 425-430 171-176 354-360 72-78 29-34 256-261 171-176 295-300 269-276 467-471 301-306 124-129 415-419 237-240 312-317 72-78 29-34 342-347 72-78 492-497 79-84, 216-221, 425-430 231-236 177-181 289-294 204-209 227-230 118-123 Audrey Bona Ayu Purwarianti Aziz Rahmad Azizah Abdul Rahman Azrifirwan 41-46 371-375 182-186 130-137 388-393 Bagus Tris Atmaja Bambang Sridadi Bayu Distiawan Trisedya Belawati Widjaja Belladini Lovely Bob Hardian Boudraa Bachir 94-98 16-21 57-63 256-261 318-323 410-414 47-51 Chanin Wongyai Cliffen Allen 210-215 376-381 Dana Indra Sensuse Darius Andana Haris Darmawan Baginda Napitupulu Dean Apriana Ramadhan Denny Devi Fitrianah Diah E. Herwindiati Dwi Hendratmo Widyantoro Dyah E. Herwindiati 22-28, 289-294 376-381, 438-445 420-424 382-387 10-15 425-430 431-437 324-329 450-454 Elfira Febriani Elin Cahyaningsih Endang Purnama Giri Enrico Budianto Eri Prasetio Wibowo Eric Punzalan 262-268 22-28 79-84, 216-221 492-497 467-471 155-160 Fadhilah Syafria Fajar Munichputranto Fajri Koto 336-341 262-268 193-197 B C D E F Farah Shafira Effendi Faris Al Afif Fatin Rohmah Nur Wahidah Febriana Misdianti Firman Ardiansyah 90-93 484-491 72-78 330-335 204-209 Gladhi Guarddin 312-317 Hamidillah Ajie Harish Muhammad Nazief Harry Budi Santoso Hemis Mustapha Herman Tolle Heru Sukoco Husnul Khotimah 251-255 312-317 402-409 47-51 472-477 367-370 461-466 I Made Tasma Ida Bagus Putu Peradnya Dinata Ika Alfina Ikhsanul Habibie Ikhwana Elfitri Imaduddin Amin Imam Cholissodin Imas Sukaesih Sitanggang Indra Budi Indriati Irsyad Satria Issa Arwani Ito Wasito Iwan Aang Soenandi 85-89 410-414 90-93 361-366, 492-497 307-311 324-329 105-111 166-170 256-261 105-111 342-347 105-111 446-449 283-288 Janson Hendryli Jean-Marc Salotti Jeanny Pragantha Joel Ilao John Derrick Junaidy Budi Sanger 431-437 41-46 376-381 155-160 231-236 367-370 G H I J K Karlina Khiyarin Nisa Kasiyah M. Junus Kyoko Ito 144-147 72-78 112-117 Lailan Sahrina Hasibuan Ledya Novamizanti 222-226 138-143 M Anwar Ma'sum M. Anwar Ma'sum M. Iqbal Tawakal Maria Ulfah Siregar Maya Kurniawati Meidy Layooari Mira Suryani Mohammad Uliniansyah Muhammad Abrar Istiadi Muhammad Asyhar Agmalaro Muhammad Faris Fathoni Muhammad Iqbal Muhammad Irfan Fadhillah Muhammad Octaviano Pratama Muhammad Rifki Shihab Muhammad Sakti Alvissalim Murein Miksa Mardhia 394-401 484-491, 492-497 484-491 231-236 105-111 177-181 402-409 177-181 85-89 29-34 16-21 467-471 99-104 289-294 295-300, 301-306, 330-335 198-203 118-123 Ni Made Satvika Iswari Nina Hairiyah Nuanwan Soonthornphisaj Nursidik Heru Praptono 171-176 262-268 35-40 425-430 Pauzi Ibrahim Nainggolan Pierre Sauvage Porawat Visutsak Prane Mariel Ong Prasetia Putra Putu Satwika 161-165 64-71 52-56 155-160 251-255 492-497 L M N P Putu Wuri Handayani 1-9 Ralph Vincent Javellana Regalado Ravika Hafizi Reggio N Hartono Riva Aktivia Roger Luis Uy 246-250 130-137 177-181 455-460 155-160 Sani M. Isa Satyanto Saptomo Setia Damawan Afandi Shogo Nishida Sigit Prasetyo Siobhan North Sri Tiatri Sri Wahyuni Stanley Karouw Stewart Sentanoe Suraya Miskon Syandra 431-437, 450-454 367-370 187-192 112-117 348-353 231-236 498-504 295-300 277-282 177-181 130-137 478-483 Taufik Djatna Teny Handayani Tji beng Jap Tonny Adhi Sabastian 262-268, 283-288, 318-323, 354-360, 388-393, 455-460, 461-466 446-449 498-504 312-317 Vina Ayumi 289-294 Wanthanee Prachuabsupakij Widodo Widodo Wilson Fonda Wina Winnie Septiani Wisnu Ananta Kusuma Wisnu Jatmiko 35-40 251-255 371-375 450-454 148-154 85-89 484-491 R S T V W Y YB Dwi Setianto Yani Nurhadryani Yasutaka Kishi Yaumil Miss Khoiriyah Yoanes Bandung Yudho Giri Sucahyo Yustina Retno W. Utami 241-245 342-347, 455-460, 461-466 112-117 166-170 118-123 348-353 241-245 Zainal A. Hasibuan lukman - 402-409 22-28 Z Faculty of Computer Science - Universitas Indonesia ©2014 ICACSIS 2014 International Conference on Advanced Computer Science and Information System 2012 (ICACSIS 2014) Hotel Ambhara, Jakarta October 18th - 19th, 2014 Committees | Table of Contents | Author's Index | About This CD-ROM Search View Please enable Javascript on your browser to view all the page properly. Copyright Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promortional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from Faculty of Computer Science, Universitas Indonesia, Indonesia. Contacts ICACSIS Committee Email: icacsis@cs.ui.ac.id Phone: +62 21 786 3419 ext. 3225 Faculty of Computer Science, Universitas Indonesia Kampus UI Depok Indonesia - 16424 Phone: +62 21 786 3419 Fax: +62 21 786 3415 Email: humas@cs.ui.ac.id Faculty of Computer Science - Universitas Indonesia ©2014 2014 International Conference on Advanced Computer Science and Information Systems (Proceedings) Ambhara Hotel, Jakarta October 18th-19th , 2014 Published by: Faculty of Computer Science Universitas Indonesia ICACSIS 2014 Element Extraction and Evaluation of Packaging Design using Computational Kansei Engineering Approach Taufik Djatna, Fajar Munichputranto, Nina Hairiyah, Elfira Febriani Laboratory of Industrial System and Engineering Faculty of Agricultural Technology, Bogor Agricultural University taufikdjatna@ipb.ac.id, fajarm0997@apps.ipb.ac.id nina.hairiyah12p@apps.ipb.ac.id, elfira.febriani12p@apps.ipb.ac.id Abstract—Currently packaging design needs more a computational processing roles and became the fundamental selling art of products. Design of packaging is very subjective and company needs to understand customer’s behavior, perception and attractiveness. Challenges arise when marketing in fast moving consumer goods is getting very dynamic and competitive. Computational needs to identify customer’s perception and attractiveness is unavoidable. In this paper we proposed new methodology to extract and evaluate information elements of packaging design from customer preferences using computational Kansei Engineering (KE) approach. The elements of packaging design were extracted from group discussion and evaluate centrality and novelty metrics using Key Element Extraction (KEE) algorithm. Correlation of packaging design elements and Kansei words was obtained with association rule mining (ARM). This formulation enabled us to define which packaging design elements are strongly correlated with each Kansei/affective words and gives recommendation to designer what kind of packaging to design. In short this proposed methods become a quantification of the art of packaging design that ease a reliable design. Keywords: Key Element Extraction, Engineering, packaging design, association rule challenges above which called as Kansei/Affective Engineering (KE) [2]. Thus Kansei/Affective Engineering must fit within the industry’s current highspeed product development process and demonstrate that it addresses gaps in the existing suite of methods [3]. The process of Kansei/Affective Engineering should also consider about what the customer are their Kansei word and how to evaluate the customer’s Kansei words [4]. The terms of Kansei words means the customer feeling or perception about a product design. KE formulation is processing Kansei word from respondent and correlates those Kansei words with specific design and physical properties of product. However, the main challenge in affective design is how to understand the implicit affective information and design product based on customer preferences (Fig. 1). For example: linguistic-implicit words such ‘beautiful’, ‘convenient’, ‘safe’ and ‘environment friendly’ have different meaning when industrial engineer try to implement this perception to a formal design object [2]. Kansei I. INTRODUCTION P ackaging became fundamental art for marketing business in market. Packaging is a media of communication between producers and consumers and also reflects the identity and personality of the product [1]. Many companies put maximum effort for the products with their own packaging design to attract customers’ heart. This awareness encourages every stakeholder within industry to produce better packaging design. A dynamic and high competition market affects to shorter product life cycle and this condition attempts company to be creative and innovative in designing packaging. They are required to understand customer behavior, perception and attraction through their feeling and emotion aspect of design. Information extraction system is really needed by company to survive in high market competition especially in (consumer goods). This paper proposed a term to solve Fig. 1. The Kansei ideas [4] Previous work shows that Kansei words and design element from respondents are identified using multiattribute utility tools such as Analytical Hierarchy Process (AHP) and Quality Function Deployment (QFD) [5]. This method requires many respondents and questionnaire to extract dataset. All choices and questions were already written on the questionnaire so this method does not provide room for improvement of ideas in accordance to create novel design elements. In this paper, we proposed a new method in easier way to extract Kansei words from focus group 262 ICACSIS 2014 discussion (FGD) by extracting key elements of packaging design with Key Element Extraction to solve the difficulties in extracting linguistic-implicit words such above. We also developed a method to evaluate the quality of the extracted packaging Kansei words by measuring its novelty and centrality within discussion. Correlation between selected Kansei words and packaging design element are calculated using Association Rule Mining (ARM) to gain knowledge about what kind of packaging that appropriate to be released in market. We are focusing on composite material that mostly applied to beverages packaging. These proposed methods become an ‘art quantification’ of packaging design. II. ELEMENT EXTRACTION OF PACKAGING DESIGN A. Kansei Words Extraction Key Elements Extraction (KEE) is an algorithm to find the key discussants and key terms. This method is one of the ways to identify what customer’s perception and preferences through discourse or discussion. KEE is based on the idea of mutually reinforcing relationship between participants and terms: significant participants are the participants using many significant terms, and vice versa, significant terms are the terms used by many significant participants. The KEE algorithm is simple, easy to implement and works quite effectively [6]. In the following figure (Fig. 2), we illustrate the relationship between participant and Kansei words that mentioned in a discussion. The participants should include potential and existing customer. Each participant has its own Kansei words and it will affect each terms and participant scores. Every discussion will result a set of terms (Kansei words). The discussion has probability that one or more participants mention new terms (Kansei words) which has not mentioned in the previous term set. Only several terms that assumed as Kansei words will to process. Those Kansei words were then analyzed to correlate with packaging design element or physical properties as the base of packaging manufacturing. Fig. 2. Bipartite graph of Kansei discourse B. Participant and Term Scoring Calculation KEE algorithm obtains participant and term scores simultaneously by an iterative calculation. The calculation is depicted in (1). By this equation, participants are ranked by key scores of participants. Same equation is used to rank the terms, by key scores of terms. The equation is depicted as follows (2) [6]. (1) (2) The calculation resulted score of each participant and term/Kansei words. The score will determine which participants and terms that not to be eliminated for the next discussion. The evaluation will be explained on Section C below. For computational needs, the algorithm of scoring and extraction process is depicted in Fig. 4. Fig. 3. Participant and terms scoring Fig. 4. Kansei words extraction method C. Centrality and Novelty Evaluation . Every design of product needs to be validated on market to estimates customer attitudes and behavior that would have been made during development [7]. As the designer (of the company or enterprise) needs innovation, novelty becomes an important parameter to calculate and to make sure that Kansei words are not repeatedly extracted. Messages (Kansei words) are characterized by measuring the centrality and novelty. Centrality metric shows the strength of the messages to become a central topic of discussion. Higher centrality value means more central of messages would be. Novelty measures how much messages include new ideas, opinions or in this case are new Kansei words. Extracted Kansei words are as novel design if there were no previous Kansei that has been used. Novelty measurement is required for company in designing new packaging. The novelty is measured as depicted in Fig. 5. 263 ICACSIS 2014 Based on the evaluation, the characteristics of message/terms are divided into four classifications: potential chances; topic triggers; topic followers; and trifles. These classifications concluded the characteristic of extracted Kansei words [8]. Novelty parameter of extracted Kansei words is determined by a threshold. If the score is less than the threshold, it indicates that the extracted Kansei words are not novel enough. This condition resulted to nonew terms of Kansei/novelty. Replace the current participant with lowest score (which has been calculated as depicted in Fig. 3) with new participant is expected to give ‘refreshment’ in discussion. New participant was assumed to add adequate probability of getting more novelties in the discussion. The knowledge flow of assessing the novelty is illustrated in Fig. 6. Start B i>k c(mi) ≥ e Double n(mi) =N1(mi), Int l Y c’(mi) =(c(mi)-e/ (1-e) i>l EOF? N c’(mi) =(c(mi)/e-1 <Equation > Double n’(mi)[] Double c’(mi)[] End B Support and confidence threshold are determined and become the parameter to choose the best rules to be used. A best rule indicates the best Kansei words to become the base of physical properties to be made for packaging. The customer’s psychological responses (in Kansei words) are more generally qualitative characteristics, and as a consequence it is difficult to measure. Those methods above abled us to answer the challenge to change the subject to quantified measurement. In order to transfer Kansei into design elements, qualitative psychological phenomena should be changed to quantified characteristics (linking Kansei with design technical specification) [10]. It is important to note that in high competitive markets, the Kansei/affective engineering approach has a purpose to enhance quality of life through customer satisfaction. Thus we have built the flow of Kansei words and its correlation to design elements in quantitative calculation. Double c(mi), k, j, e c(mi) = maxi≤j<i+kMj(mi) Let Ā = {F 1 , F 2 … Fn} be an item set. T is a nonempty item set such that T ⊆ Ā. Let A be a set of items. A combination of Kansei and design element T is said to contain A if A ⊆ T. An association rules as an implication of the form A → B which Kansei are Kansei words and B are design elements. The rule holds in the assessment set with support s that contain A and B (A ∩ B). This is taken to be the probability P(A ∩ B). The rule A → B has confidence c where c is the percentage of assessment containing A that also contain B. The equations can be seen as follows (3) and (4). Fig. 5. Flowchart for centrality and novelty calculation s = P( A ∩ B) = Kansei words Group of participants Y Novelty>Threshold? Replace participant Association rules New Design = s ( A | B) P= N total assesment contain A and B (3) total assesments total assesment contain A and B (4) total assesments that contain A IV. EXPERIMENTAL RESULT Fig. 6. Knowledge flow of novelty evaluation III. ASSOCIATION RULE MINING FOR DETERMINING PACKAGING DESIGN For the Kansei engineering domain is approached by using association rule mining method. By using association rule mining (ARM), we could identify association link or correlation between items from item set. Item set are part of frequent patterns that appear frequently in a data set [9]. Association rules results rule in form: if...then… or notated as Kansei → design. Relationship between Kansei words and design elements is an implication form where A as antecedent and B as consequent. A. Kansei Words Extraction Firstly, design factor based on consumer is need to be identified. Identification is approached by Kansei, where Kansei is measured by words that reveal feeling emotion named Kansei. 264 TABLE I LIST OF KANSEI WORDS ID Kansei Words F1 Attractive text F2 Attractive visual F3 Portability F4 Easy to open F5 Easy to close F6 Relieving thirsty F7 Nice picture F8 Attractive logo ICACSIS 2014 Fig. 7. Kansei Feature Map of example Kansei term set In the real system, all Kansei words are to be collected by discussions based on text (online discussions). As it has written above, participants and moderator are needed to become the actors of the system. Every term that tend to be the Kansei words be taken and become the term set of Kansei words. We chose 20 Kansei words that strongly related to the design of beverage packaging as a motivational example. By using key elements extraction (KEE) algorithm, we chose eight highest term score to be processed to the next phase. The result of the calculation is written in Table I. B. Novelty and Centrality Evaluation The evaluation of the characteristics of extracted Kansei words, centrality and novelty were measured and plotted to a XY scatter graph. This graph illustrates the feature map of the discussion, which is categorized in four classifications. The characteristics of message/terms are divided into four classifications: potential chances; topic triggers; topic followers; and trifles topic. These classifications concluded the characteristic of extracted Kansei words [8]. Each term is plotted with different color and shape for each participant. Every participant is allowed to express their ideas, emotion and respond about packaging. The characteristics could be identified by cluster every terms score in the discussion. In Fig. 7 it can be seen there are two clusters (marked with red circle and green rectangle). Red circle shows that the discussion has high novelty but low on centrality. Some participant gives new terms but other participants were not intending to responds or repeat the words. Green rectangle shows that some participants only give some trifles terms, which means the terms do not have novelty and other participants did not respond to these terms. The mutual conversation among participants will affect the total characteristic of discussion. Typically this discussion is tending to be novel, which is have potential changes for the next discussions and design element either. This potency is what companies are seeking to innovate their packaging to be different with competitors. Beside characteristics, participants’ behaviors could also be observed by analyzing their score. As figured in example graph above, Participants 2 mentioned some terms with high novelties and Participant 5 has high centralities. Participant 5 might have mentioned new terms but he/she have the courage to main his/her opinion. The potency of novelty could be maximized by eliminating low score participants and replaced with new participants to increase the novelty and centrality level. 265 ICACSIS 2014 C. Experimental Dataset Data sets that deployed in this paper are Kansei words and design elements are based on investigation of direct survey from beverage industry. In addition, the beverage packaging design elements were taken from previous research. Kansei was measured by Kansei words. This is quite reliable because customer will judge soft drink product by words that express a feeling and judgment towards the products. Every single type of beverages has its own Kansei words and need to be translated. In this paper we choose soft drink beverage as the domain of the research. We are considering the visualization aspect in packaging design element and represents people perception in choosing the right product. confidence and support. The result of the system can be seen on Fig. 7. ID In this calculation phase, Kansei words as are depicted in Table I. The motivating example dataset of soft drink packaging design element are listed in Table II. The design elements were symbolized as (V1, V2… Vn) to ease the calculation and writing expression. Design elements below became the main functional characteristic that should have been found physically in packaging. The dataset was modified to align with the case discussed. In the real system, design element was selected by spreading questionnaire to respondents with variety of ages, occupation, and education backgrounds. In this research, we highlighted the emotional feeling or Kansei. The products assessments are resulted in Table III. D. Association Rule Mining of Packaging Design System was then evaluated to get knowledge between Kansei words and design element that shows the words. In real system, knowledge is collected from respondents using questionnaires. An association rule is one of techniques in data mining to determine the relationship among items in dataset. One of our contributions to ease the calculation of packaging design identification is Kanpack 0.1. This application contains extracted Kansei words from discussion analysis (Table I) and existing physical design elements (Table II). Kanpack 0.1 provides association rule mining algorithm to find best packaging design rules. As an example, it can be seen on Record 1 on Table III that respondent choose attractive text, attractive visual, easy to open, easy to close, relieving thirsty, nice picture and attractive logo as Kansei words of soft drink packaging. Size, protection, opening and resealing, recyclable and company name were selected from design elements. This choice is defined as item set from Record 1 and so on until Record 11 (Table III). Those results are defined as input for rules searching with software Kanpack 0.1 (Fig. 6). The rules were used to map the correlation between Kansei words and design elements. The output of this dialogue window is to determine item sets and calculate the 266 TABLE II LIST OF DESIGN ELEMENTS Design Element V1 Shape V2 Size V3 Color V4 Brand V5 Protection V6 Text V7 Illustration V8 Ingredients V9 Design material V10 Storage V11 Opening and resealing V12 Foldable V13 Refillable V14 Recyclable V15 Company name TABLE III SELECTED KANSEI WORDS AND BEVERAGES DESIGN ELEMENT No. Kansei Words Design Element 1. F1, F2, F4, F5, F6, F7, F8 V2, V5, V11, V14, V15 2. F1, F2, F3, F4, F5, F7 V4, V7, V10, V14, V15 3. F3, F4, F5, F6, F7 V4, V5, V9, V14 4. F1, F2, F3, F5, F6, F7, F8 V2, V6, V9, V14, V15 5. F5, F6 V2, V7, V9, V8, V12 6. F1, F2, F3, F5, F6, F7 V2, V6, V9, V12, V4 7. F4, F7 V3, V7, V9, V13, V8 8. F1, F5, F6, F7, F8 V1, V6, V9, V13, V4 9. F5, F6 V4, V5, V9, V13, V15 10. F1, F2, F3, F4, F5, F6, F7 V1, V5, V9, V14, V8 11. F1, F4, F5, F6, F7, F8 V1, V6, V9, V13, V10 Fig. 6. User interface of Kanpack Application ICACSIS 2014 Fig. 7. Report design elements of Kanpack The findings showed that support and confidence are used in a’priori algorithm application. A`priori is a classic algorithm for frequent item set mining and association rule. ID support and confidence score indicates that the relations between those two attributes are stronger. The rules means if the company would like to enhance the portability of the packaging, they should consider the material and recyclability of their product packaging. These calculation resulted best Kansei or customer preferences combined with packaging design element to build attractive and innovative design. Technically, this proposed methodology has specific contribution in retrieving customer’s perception and attractiveness. Existing methodology like questionnaires (AHP) and Quality Function Deployment only measure the importance of some features and closed question which respondent could not add more opinions. By using KE approach and this proposed methodology, participants of discourse are able to mention new concepts and ideas as the core objectives of finding new design. Items 101 V4, V7, V10, V14, V15 102 V4, V5,V9, V14 103 V2, V6, V9, V14, V15 104 V2, V6, V9, V12, V4 105 V1, V5, V9, V14, V8 Item set Support {V1} 1 {V9}* 4 {V10} 1 {V12} 1 {V14}* 3 {V15} 2 Item set V9, V14 V. Support 3 Fig. 8. A`priori algorithm illustration for selecting design element The name of the algorithm is based on the fact that the algorithm uses prior knowledge of frequent item set properties [11]. The A`priori mechanism of this evaluating system is depicted on Fig 8. For example, the chosen Kansei words are portability (F3). There are five assessment from respondent that including portability. These assessments were eliminated with threshold equals 75%. The remaining combination is V9 and V14 with confidence score are 75%. Based on association rules, this rule has support score equals 20% and confidence score equals to 75%. This score indicates the probability of associated Kansei words and packaging design element. Higher CONCLUSION Extracting key elements of packaging design with Key Element Extraction to solve the difficulties in extracting linguistic-implicit words terms set become one of our contribution for information extraction. In this paper we proposed new methodology of extracting Kansei words from a focus group discussion analysis and build an evaluation system of Kansei engineering to see the best innovation of packaging design elements. The extracted Kansei words were characterized as Kansei Feature Map to show the characteristic of terms set using novelty and centrality calculation. This map is expected to become the base to inference the how innovative the Kansei words are. Final approach was composed by using association rules mining to see correlation between extracted Kansei words and packaging physical properties (design element). Support and confidence score become the parameter to conclude the best rules of design packaging. This information extraction system was straightly effective to decide most representative customer preferences for packaging design. The analysis and calculation method will bring easier and validated result with computational approach in designing packaging, particularly for fast moving consumer goods (FMCG). For further improvement, there should have a deeper analysis threshold determination of novelty and centrality. The novelty and centrality of design should involve expertise in art and packaging design both from artist, industry and research center. REFERENCES [1] [2] 267 Trott P. Innovation Management and New Product Development. England: Prentice Hall. 2005: 415 Nagamichi M, Lokman A. Innovation of Kansei Engineering. CRC Press. Boca Raton: 2011. ICACSIS 2014 [3] [4] [5] Barnes C, Childs T and Lillford S. Kansei/Affective Engineering for the European Fast-Moving Consumer Goods Industry. CRC Press. Boca Raton: 2011. Nagamichi M. Kansei/Affective Engineering and History of Kansei/Affective Engineering in the World. CRC Press. Boca Raton: 2011. Johan, V.N., S. Raharja, E. G. Sa’id, and T. Djatna. Evaluation System of Rattna Chair Design using Kansei Engineering. Dissertation. Bogor Agriculutral University. International Conference on Enterprise Information System (ICEIS 2007). 2007. [8] Han J, Kamber M, Pei J. Data Mining Concepts and Techniques. Massaschuschets: Elsevier Inc. 2012: 246. [9] Okamoto R H. Kansei, Quality, and Quality Function Deployment. CRC Press. Boca Raton: 2011. [10] Han J, Kamber M, Pei J. Data Mining Concepts and Techniques. Massaschuschets: Elsevier Inc. 2012: 248. Ohsawa Y, Yada K. Data Mining for Design and Marketing. Chapman & Hall. New York: 2009 [6] Trott P. Innovation Management and New Product Development. England: Prentice Hall. 2005: 370. [7] Imafuji, N Y et al. Delineating topic and discussant transitions in online collbaorative environments. Proceeding of the 9th 268