Product design enhancement using apparent usability and affective quality

In this study, apparent usability and affective quality were integrated in a design framework called the Usability Perception and Emotion Enhancement Model (UPEEM). The UPEEM was validated using structural equation modeling (SEM). The methodology consists of four phases namely product selection, attribute identification, design alternative generation, and design alternative evaluation. The first stage involved the selection of a product that highly involves the consumer. In the attribute identification stage, design elements of the product were identified. The possible values of these elements were also determined for use in the experimentation process. Design of experiments was used to identify how the attributes will be varied in the design alternative stage and which of the attributes significantly contribute to affective quality, apparent usability, and desirability in the design evaluation stage. Results suggest that product attributes related to form are relevant in eliciting intense affect and perception of usability in mobile phones especially those directly related to functionality and aesthetics. This study considered only four product attributes among so many due to the constraints of the research design employed. Attributes related to aesthetic perception of a product enhance apparent usability such as those related to dimensional ratios.     

An image evaluation approach for parameter-based product form and color design

The parameter-based technique provides an efficient and valid means of constructing 3-D geometric models in many CAD software systems. However, its use is generally restricted to the design of mechanical components with regular configurations, and it is not ideally suited to product form and color design. This paper proposes a rapid conceptual design approach, which creates color-rendered forms and combines parameter-based features with fuzzy neural network theorems and gray theory to predict their image evaluation. Two evaluation models (Evaluation Model I and Evaluation Model II) are developed and applied in a case study of an electronic door lock design. Model I uses a fuzzy neural network to predict the overall image, while Model II uses a gray clustering operation for the color image evaluation and two fuzzy neural networks for the form image evaluation and the overall image evaluation. The results show that the image prediction capability of Model II is superior to that of Model I (RMSE: 0.062 versus 0.105). Furthermore, the overall image evaluation is dominated by the door lock's color rather than by its form (RMSE: 0.071 versus 0.162). The dominance of color in determining the image evaluation may be due to the specified image words, form evolution restrictions, or the membership grade ranges of the test color samples and the test form samples, etc. Having established the superiority of Model II, it is applied to develop a consultative design interface integrated with a professional CAD system in order to demonstrate the effectiveness of the proposed product design and image evaluation approach. The design system presented in this study enables a designer to predict the likely image tendencies of a designed product without the need to create and test a prototype model. Hence, he or she can make any design parameter modifications necessary to ensure that the finished product meets its specified image goals.     

Supply chain network design using an integrated neuro-fuzzy and MILP approach: A comparative design study

In this study, an integrated supply chain (SC) design model is developed and a SC network design case is examined for a reputable multinational company in alcohol free beverage sector. Here, a three echelon SC network is considered under demand uncertainty and the proposed integrated neuro-fuzzy and mixed integer linear programming (MILP) approach is applied to this network to realize the design effectively. Matlab 7.0 is used for neuro-fuzzy demand forecasting and, the MILP model is solved using Lingo 10.0. Then Matlab 7.0 is used for artificial neural network (ANN) simulation to supply a comparative study and to show the applicability and efficiency of ANN simulation for this type of problem. By evaluating the output data, the SC network for this case is designed, and the optimal product flow between the factories, warehouses and distributors are calculated. Also it is proved that the ANN simulation can be used instead of analytical computations because of ensuring a simplified representation for this method and time saving.     

A support vector regression based prediction model of affective responses for product form design

In this paper, a state-of-the-art machine learning approach known as support vector regression (SVR) is introduced to develop a model that predicts consumers’ affective responses (CARs) for product form design. First, pairwise adjectives were used to describe the CARs toward product samples. Second, the product form features (PFFs) were examined systematically and then stored them either as continuous or discrete attributes. The adjective evaluation data of consumers were gathered from questionnaires. Finally, prediction models based on different adjectives were constructed using SVR, which trained a series of PFFs and the average CAR rating of all the respondents. The real-coded genetic algorithm (RCGA) was used to determine the optimal training parameters of SVR. The predictive performance of the SVR with RCGA (SVR–RCGA) is compared to that of SVR with 5-fold cross-validation (SVR–5FCV) and a back-propagation neural network (BPNN) with 5-fold cross-validation (BPNN–5FCV). The experimental results using the data sets on mobile phones and electronic scooters show that SVR performs better than BPNN. Moreover, the RCGA for optimizing training parameters for SVR is more convenient for practical usage in product form design than the timeconsuming CV.     

A study on the preliminary ship design method using deterministic approach and probabilistic approach including hull form

This paper describes a preliminary ship design method using deterministic approach and probabilistic approach in the process of hull form design. In the deterministic approach, an interdisciplinary ship design method integrates principal dimension decisions and hull form variations in the preliminary ship design stage. Integrated ship design, as presented in this paper, has the distinctive feature that these parameters are evaluated simultaneously. Conversely, in sequential design, which is based on the traditional preliminary ship design process, hull form designs and principal dimension decisions are determined separately and sequentially. The current study adopts the first method to enhance the design quality in the early design stage. Furthermore, a probabilistic approach is applied to ship design to resolve uncertainties in design information more efficiently than a deterministic approach would.     

Turbine stage design aided by artificial intelligence methods

We propose a general, efficient system for designing turbine cascades and stages in real 3D-flow conditions. The presented algorithms involve application of evolutionary algorithms, as well as Artificial Neural Networks. Results of the design process are shown to be highly optimised in terms of efficiency, whereas computation time is reduced by several orders of magnitude in comparison to methods relying on Computational Fluid Dynamics calculations.     

Automatic design support and image evaluation of two-coloured products using colour association and colour harmony scales and genetic algorithm

Colour plays a key role in determining a consumer’s response to a product’s appearance. Accordingly, this study proposes an automatic design support system which enables a designer either to emulate the colour scheme of a two-coloured product and then to determine its corresponding image perception, or to search for the two-colour combination which most closely meets the required image perception. The proposed system combines a gray theory-based colour-association evaluation method and a colour-harmony-based aesthetic evaluation method to design and evaluate different product-colour schemes. Since colour-harmony theories cannot be implemented directly using the additive primaries (i.e. R (Red), G (Green) and B (Blue)) used in most computer-based colour emulations, this study develops a RGB-based colour-association and colour-harmony measurement scheme to evaluate the image perception of a particular product-colour scheme. In an inverse process, a genetic algorithm is applied to search for the near-optimal colour combination which satisfies the specified product colour-association goal and achieves a high degree of colour harmony. Various case studies involving the design and evaluation of a two-coloured thermos flask are provided for illustration purposes to demonstrate the effectiveness of the proposed method.     

Constructing a hybrid Kansei engineering system based on multiple affective responses: Application to product form design

This study proposes an expert system, which is called hybrid Kansei engineering system (HKES) based on multiple affective responses (MARs), to facilitate the development of product form design. HKES is consists of two sub-systems, namely forward Kansei engineering system (FKES) and backward Kansei engineering system (BKES). FKES is utilized to generate product alternatives and BKES is utilized to predict affective response of new product designs. Although the idea of HKES and similar hybrid systems have already been applied in various fields, such as product design, engineering design, and system optimization, most of existing methodologies are limited by searching optimal design solutions using single-objective optimization (SOO), instead of multi-objective optimization (MOO). Hence the applicability of HKES is limited while adapting to real-world problems, such as product form design discussed in this paper. To overcome this shortcoming, this study integrates the methodologies of support vector regression (SVR) and multi-objective genetic algorithm (MOGA) into the scheme of HEKS. BKES was constructed by training SVR prediction model of every single affective response (SAR). The form features of these product samples were treated as input data while the average utility scores obtained from all the consumers were used as output values. FKES generates optimal design alternatives using the MOGA-based searching method according to MARs specified by a product designer as the system supervisor. A case study of mobile phone design was given to demonstrate the analysis results. The proposed HKES based on MARs can be applied to a wide variety of product design problems, as well as other MOO problems involving with subjective human perceptions.     

The modified fuzzy art and a two-stage clustering approach to cell design

This study presents a new pattern recognition neural network for clustering problems, and illustrates its use for machine cell design in group technology. The proposed algorithm involves modifications of the learning procedure and resonance test of the Fuzzy ART neural network. These modifications enable the neural network to process integer values rather than binary valued inputs or the values in the interval [0, 1], and improve the clustering performance of the neural network. A two-stage clustering approach is also developed in order to obtain an informative and intelligent decision for the problem of designing a machine cell. At the first stage, we identify the part families with very similar parts (i.e., high similarity exists in their processing requirements), and the resultant part families are input to the second stage, which forms the groups of machines. Experimental studies show that the proposed approach leads to better results in comparison with those produced by the Fuzzy ART and other similar neural network classifiers.     

Auto-tune system using single-run relay feedback test and model-based controller design

In this paper, a systematic approach for auto-tune of PI/PID controller is proposed. A single run of the relay feedback experiment is carried out to characterize the dynamics including the type of damping behavior, the ultimate gain, and ultimate frequency. Then, according to the estimated damping behavior, the process is classified into two groups. For each group of processes, model-based rules for controller tuning are derived in terms of ultimate gains and ultimate frequencies. To classify the processes, the estimation of an apparent deadtime is required. Two artificial neural networks (ANNs) that characterize this apparent deadtime using the ATV data are thus included to facilitate this estimation of this apparent deadtime. The model-based design for this auto-tuning makes uses of parametric models of FOPDT (i.e. first-order-plus-dead-time) and of SOPDT (i.e. second-order-plus-dead-time) dynamics. The results from simulations show that the controllers thus tuned have satisfactory results compared with those from other methods.     

Comparison of ANN approach with 2D and 3D hydrodynamic models for simulating estuary water stage

Accurately predicting tidal levels, including tidal and freshwater discharge effects, is important for human activities in estuaries. The traditional harmonic analysis method and numerical modeling are usually adopted to simulate and predict estuary water stages. This study applied artificial neural networks (ANNs) as an alternative modeling approach to simulate the water stage time-series of the Danshui River estuary in northern Taiwan. We compared this approach with vertical (laterally averaged) 2D and 3D hydrodynamic models. Five ANN models were constructed to simulate the water stage time-series at the Shizi Tou, Taipei Bridge, Rukuoyan, Xinhai Bridge, and Zhongzheng Bridge locations along the Danshui River estuary. ANN models can preserve nonlinear characteristics between input and output variables and are superior to physical-based hydrodynamic models during the training phase. The simulated results reveal that the vertical 2D and 3D hydrodynamic models could not capture the observed water stages during an input of high freshwater discharge from upstream boundaries, while the ANN could match the observed water stage. However, during the testing phase, the ANN approach was slightly inferior to the 2D and 3D models at the Xinhai Bridge, Zhongzheng Bridge, and Rukouyan locations. Our results show that the ANN was able to predict the water stage time-series with reasonable accuracy, suggesting that ANNs can be a valuable tool for estuarine management.     

Least-cost design of singly and doubly reinforced concrete beam using genetic algorithm optimized artificial neural network based on Levenberg–Marquardt and quasi-Newton backpropagation learning techniques

In this work, least-cost design of singly and doubly reinforced beams with uniformly distributed and concentrated load was done by incorporating actual self-weight of beam, parabolic stress block, moment–equilibrium and serviceability constraint besides other constraints. Also, this design expertise was incorporated into a genetically optimized artificial neural network based on steepest descent, Levenberg–Marquardt, and quasi-Newton backpropagation learning techniques. The initial solution for the optimization procedure was obtained using limit state design as per IS: 456-2000.     

Integrating engineering design and analysis using a multi-representation approach

With the present gap between CAD and CAE, designers are often hindere in their efforts to explore design alternatives and ensure product robustness. This paper describes the multi-representation architecture (MRA)—a design-analysis integration strategy that views CAD-CAE integration as an information-intensive mapping between design models and analysis models. The MRA divides this mapping into subproblems using four information representations: solution method models (SMMs), analysis building blocks (ABBs), product models (PMs), and product model-based analysis models (PBAMs). A key distinction is the explicit representation of design-analysis associativity as PM-ABB idealization linkages that are contained in PBAMs.The MRA achieves flexibility by supporting different solution tools and design tools, and by accommodating analysis models of diverse discipline, complexity and solution method. Object and constraint graph techniques provide modularity and rich semantics.Priority has been given to the class of problems termedroutine analysis—the regular use of established analysis models in product design. Representative solder joint fatigue case studies demonstrate that the MRA enables highly automated routine analysis for mixed formula-based and finite element-based models. Accordingly, one can employ the MRA and associated methodology to create specialized CAE tools that utilize both design information and general purpose solution tools.Nomenclature MRA multi-representation architecture - SMM solution method model - ABB analysis building block - PM product model - PBAM product model-based analysis model - ABB-SMM transformation - idealization relation between design and analysis attributes - PM-ABB associativity linkage indicating usage of one or more _i eislab. eislab. gatech. edu.     

基于遗传算法优化神经网络的产品造型设计评价

为全面科学地评定、筛选最佳设计方案,借助遗传算法的全局寻优能力对BP神经网络进行优化,构建混合GA‐BP算法,并将其应用于笔记本产品造型设计评价中。在建立笔记本造型二级指标评价体系的基础上,利用18款设计方案中的15款对混合GA‐BP评价系统进行训练,利用其余3款设计方案对训练后的系统进行验证。验证结果表明,模拟值与实际值的相对误差分别为3?6％、－1?7％和2?8％,显示了较高的精度,反映了混合GA‐BP产品造型设计评价系统能对设计方案进行科学的评价。     

Product concept evaluation and selection using data mining and domain ontology in a crowdsourcing environment

For product design and development, crowdsourcing shows huge potential for fostering creativity and has been regarded as one important approach to acquiring innovative concepts. Nevertheless, prior to the approach could be effectively implemented, the following challenges concerning crowdsourcing should be properly addressed: (1) burdensome concept review process to deal with a large amount of crowd-sourced design concepts; (2) insufficient consideration in integrating design knowledge and principles into existing data processing methods/algorithms for crowdsourcing; and (3) lack of a quantitative decision support process to identify better concepts. To tackle these problems, a product concept evaluation and selection approach, which comprises three modules, is proposed. These modules are respectively: (1) a data mining module to extract meaningful information from online crowd-sourced concepts; (2) a concept re-construction module to organize word tokens into a unified frame using domain ontology and extended design knowledge; and (3) a decision support module to select better concepts in a simplified manner. A pilot study on future PC (personal computer) design was conducted to demonstrate the proposed approach. The results show that the proposed approach is promising and may help to improve the concept review and evaluation efficiency; facilitate data processing using design knowledge; and enhance the reliability of concept selection decisions.     

Realization of emergent behavior in collective autonomous mobile agents using an artificial neural network and a genetic algorithm

This paper proposes a pursuit system that utilizes the artificial life concept where autonomous mobile agents emulate the social behavior of animals and insects and realize their group behavior. Each agent contains sensors to perceive other agents in several directions, and decides its behavior based on the information obtained by these sensors. In this paper, a neural network is used for behavior decision controlling. The input of the neural network is decided by the existence of other agents, and the distance to the other agents. The output determines the directions in which the agent moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behavior adequately fit the goal and can express group behavior. The validity of the system is verified through simulation. Also in this paper, we have observed the agents emergent behavior during simulation.This paper was supported by WonKwang University in 2004.     

Developing a design support system for the exterior form of running shoes using partial least squares and neural networks

The function of sport shoes is to improve sport performance and reduce sports-related injuries. They are commercial products developed by combining sports technology and marketing activities. Numerous studies on research and development, material application, production process improvements, and human physiological measurements for the sport shoe market exist. However, few studies have conducted an in-depth investigation on the design of forms and external appearance for sports shoes.     

Fault diagnosis of spur bevel gear box using artificial neural network (ANN), and proximal support vector machine (PSVM)

Vibration signals extracted from rotating parts of machineries carries lot many information with in them about the condition of the operating machine. Further processing of these raw vibration signatures measured at a convenient location of the machine unravels the condition of the component or assembly under study. This paper deals with the effectiveness of wavelet-based features for fault diagnosis of a gear box using artificial neural network (ANN) and proximal support vector machines (PSVM). The statistical feature vectors from Morlet wavelet coefficients are classified using J48 algorithm and the predominant features were fed as input for training and testing ANN and PSVM and their relative efficiency in classifying the faults in the bevel gear box was compared.     

Choosing knowledge management strategies by using a combined ANP and DEMATEL approach

Numerous companies are expecting their knowledge management (KM) to be performed effectively in order to leverage and transform the knowledge into competitive advantages. However, here raises a critical issue of how companies can better evaluate and select a favorable KM strategy prior to a successful KM implementation. The KM strategy selection is a kind of multiple criteria decision-making (MCDM) problem, which requires considering a large number of complex factors as multiple evaluation criteria. A robust MCDM method should consider the interactions among criteria. The analytic network process (ANP) is a relatively new MCDM method which can deal with all kinds of interactions systematically. Moreover, the Decision Making Trial and Evaluation Laboratory (DEMATEL) not only can convert the relations between cause and effect of criteria into a visual structural model, but also can be used as a way to handle the inner dependences within a set of criteria. Hence, this paper proposes an effective solution based on a combined ANP and DEMATEL approach to help companies that need to evaluate and select KM strategies. Additionally, an empirical study is presented to illustrate the application of the proposed method.     

Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach

Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often physically incapacitated. Mel-Frequency Cepstral Coefficients (MFCCs) have been proven to be an appropriate representation of dysarthric speech, but the question of which MFCC-based feature set represents dysarthric acoustic features most effectively has not been answered. Moreover, most of the current dysarthric speech recognisers are either speaker-dependent (SD) or speaker-adaptive (SA), and they perform poorly in terms of generalisability as a speaker-independent (SI) model. First, by comparing the results of 28 dysarthric SD speech recognisers, this study identifies the best-performing set of MFCC parameters, which can represent dysarthric acoustic features to be used in Artificial Neural Network (ANN)-based ASR. Next, this paper studies the application of ANNs as a fixed-length isolated-word SI ASR for individuals who suffer from dysarthria. The results show that the speech recognisers trained by the conventional 12 coefficients MFCC features without the use of delta and acceleration features provided the best accuracy, and the proposed SI ASR recognised the speech of the unforeseen dysarthric evaluation subjects with word recognition rate of 68.38%.