In order to transform the usage data into appropriate information that can improve the products through design modification, a method based on convolution neural network is proposed for user experience evaluation modeling, which can make full use of the usage data to establish the mapping relationship between the user information and the product engineering requirements. Firstly, the time-series usage data was converted into a series of data units by sliding window technique, and a convolution neural network architecture suitable for user experience evaluation model was established. Then, the optimal hyper parameters was selected and the over fitting problem of the model was improved by K-fold cross validation analysis. Finally, the validity of the proposed method was demonstrated by a case study of smart phone user experience evaluation modeling. The results indicated that the proposed method can automatically extract effective features from raw usage data, which can used for user experience evaluation prediction. Thus, the proposed method can decrease the dependence of the users and designers when modeling, which can help designers to assess the product performance in real time and accurately and provide support information for design decisions through usage data.
YAN Bo,ZHANG Lei,CHU Xuening
. User Experience Evaluation Modeling Based on
Convolutional Neural Network[J]. Journal of Shanghai Jiaotong University, 2019
, 53(7)
: 844
-851
.
DOI: 10.16183/j.cnki.jsjtu.2019.07.011
［1］罗仕鉴, 潘云鹤. 产品设计中的感性意象理论、技术与应用研究进展［J］. 机械工程学报, 2007, 43(3): 8-13.
LUO Shijian, PAN Yunhe. Review of theory, key technologies and its application of perceptual image in product design［J］. Journal of Mechanical Engineering, 2007, 43(3): 8-13.
［2］XIONG Y, LI Y, PAN P, et al. A regression-based Kansei engineering system based on form feature lines for product form design［J］. Advances in Mechanical Engineering, 2016, 8(7): 168781401665610.
［3］LIM S, TUCKER C S. A Bayesian sampling method for product feature extraction from large-scale textual data［J］. Journal of Mechanical Design, 2016, 138(6): 061403.
［4］BORDAGARAY M, DELL’OLIO L, IBEAS A, et al. Modelling user perception of bus transit quality considering user and service heterogeneity［J］. Transportmetrica A: Transport Science, 2014, 10(8): 705-721.
［5］CHEN M C, CHANG K C, HSU C L, et al. Applying a Kansei engineering-based logistics service design approach to developing international express services［J］. International Journal of Physical Distribution & Logistics Management, 2015, 45(6): 618-646.
［6］倪敏娜, 孙志宏, 王梓, 等. 面向产品造型感性意象评价的BP神经网络模型的应用［J］. 东华大学学报, 2016, 42(4): 604-607.
NI Minna, SUN Zhihong, WANG Zi, et al. Applied research on BP neural network of Kansei images and elements modeling for the evaluation of product design［J］. Journal of Donghua University, 2016, 42(4): 604-607.
［7］ZHOU F, JIAO R J, LINSEY J S. Latent customer needs elicitation by use case analogical reasoning from sentiment analysis of online product reviews［J］. Journal of Mechanical Design, 2015, 137(7): 071401.
［8］KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks ［J］. Advances in Neural Information Processing Systems, 2012, 25(2): 1097-1105.
［9］HECHT-NIELSEN R. Theory of the backpropagation neural network［C］//International Joint Conference on Neural Networks. IEEE, 2002, 1: 593-605.
［10］YOUNG S R, ROSE D C, KARNOWSKI T P, et al. Optimizing deep learning hyper-parameters through an evolutionary algorithm［C］//Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments. ACM, 2015: 1-5.
［11］BOTTOU L. Stochastic gradient descent tricks［M］.Neural Networks: Tricks of the Trade. Springer Berlin Heidelberg, 2012: 421-436.
［12］BOTEV A, LEVER G, BARBER D. Nesterov’s accelerated gradient and momentum as approximations to regularised update descent［C］//International Joint Conference on Neural Networks. IEEE, 2017: 1899-1903.
［13］LE Q V, NGIAM J, COATES A, et al. On optimization methods for deep learning［C］//Proceedings of the 28th International Conference on International Conference on Machine Learning. Omnipress, 2011: 265-272.
［14］HADGU A T, NIGAM A, DIAZ-AVILES E. Large-scale learning with AdaGrad on Spark［C］//IEEE International Conference on Big Data. IEEE, 2015: 2828-2830.
［15］OOI K B, TAN G W H. Mobile technology acceptance model: An investigation using mobile users to explore smartphone credit card［J］. Expert Systems with Applications, 2016, 59: 33-46.
［16］卢淑华. 社会统计学［M］. 第四版.北京大学出版社, 2009.
LU Shuhua. Social statistics［M］. 4th edition. Peking University Press, 2009.
［17］MUKHOPADHYAY S C. Wearable sensors for human activity monitoring: A review［J］. IEEE Sensors Journal, 2015, 15(3): 1321-1330.
［18］杜党党, 贾晓亮, 郝超博. 基于遗传过程神经网络算法的航空发动机健康状态图谱化预测方法［J］. 计算机集成制造系统, 2015, 21(11): 2980-2987.
DU Dangdang, JIA Xiaoliang, HAO Chaobo. Graphics prediction method for health states of aero engines based on GA-PNN［J］. Computer Integrated Manufacturing Systems, 2015, 21(11): 2980-2987.
