Comparison of multi-objective evolutionary algorithms in hybrid Kansei engineering system for product form design

Understanding the affective needs of customers is crucial to the success of product design. Hybrid Kansei engineering system (HKES) is an expert system capable of generating products in accordance with the affective responses. HKES consists of two subsystems: forward Kansei engineering system (FKES) and backward Kansei engineering system (BKES). In previous studies, HKES was based primarily on single-objective optimization, such that only one optimal design was obtained in a given simulation run. The use of multi-objective evolutionary algorithm (MOEA) in HKES was only attempted using the non-dominated sorting genetic algorithm-II (NSGA-II), such that very little work has been conducted to compare different MOEAs. In this paper, we propose an approach to HKES combining the methodologies of support vector regression (SVR) and MOEAs. In BKES, we constructed predictive models using SVR. In FKES, optimal design alternatives were generated using MOEAs. Representative designs were obtained using fuzzy c-means algorithm for clustering the Pareto front into groups. To enable comparison, we employed three typical MOEAs: NSGA-II, the Pareto envelope-based selection algorithm-II (PESA-II), and the strength Pareto evolutionary algorithm-2 (SPEA2). A case study of vase form design was provided to demonstrate the proposed approach. Our results suggest that NSGA-II has good convergence performance and hybrid performance; in contrast, SPEA2 provides the strong diversity required by designers. The proposed HKES is applicable to a wide variety of product design problems, while providing creative design ideas through the exploration of numerous Pareto optimal solutions.     

The capacity for pain empathy among urban Internet-addicted left-behind children in China: An event-related potential study

For the purpose of developing an event-related potential (ERP) method to study the differences in the capacity for pain empathy between urban Internet-addicted left-behind children and urban left-behind children with no such addiction, thirty participants (14 years of age) were selected from two middle schools in Chongqing, China to participate in the ERP experiment carried out over ten successive days in normal status. The study used the experimental paradigm of pain empathy experiment by Jackson, and 2 × 2 two-factor mixed experimental design. The results showed that for the N1 component (autonomic processing), the effect of pain was induced in both the Internet-addicted group and non-addicted group; this supports that the two groups of participants did not have differences during autonomic processing. The interaction between Internet addiction, non-addiction and pain was significant (for P2 and N2), i.e., the effect of pain was not significant in the Internet-addicted group but was significant in the non-addicted group. This finding supports that Internet addiction influenced the cognitive processing of empathy for pain in the urban left-behind children; P2 and N2 might reflect the cognitive processing and assessment of empathy for pain. During the last 550–850 ms, a larger LPC was induced in the two groups of participants for both pain and non-pain related images. This finding suggests that Internet addiction did not influence the processing since LPC reflected the reasonable judgment of participants, based on common sense, during the last experimental period. The final conclusion from the study was that Internet addiction influenced the capacity for pain empathy among urban left-behind children; in particular, it affected cognitive processing and assessment.     

A product configuration analysis method for emotional design using a personal construct theory

Identifying emotion-related product attributes (perceived by consumers) is no easy task in the realm of emotional design. Conventionally, this process relies heavily on the researchers who conduct the Kansei experiments selecting product attributes such as color, form, and texture for Kansei studies. However, in so doing, other product attributes that also play a vital role in product-emotion associations might be neglected by the researchers. More importantly, the identification of product attributes should be based on consumer's point of view (and feelings). Accordingly, a personal construct theory based product configuration analysis method is proposed in this work. The method develops the customer's mind map for each Kansei tag in order to capture replications of candidate products. A means-value chain is used to generate targets which are later compared with candidate products by consumers. The comparison results could suggest product attributes that are relevant to the desired Kansei. The proposed approach is presented and illustrated using a case study of Graffiti designs on notebooks. Results obtained are discussed. It appears that the proposed method is promising in identifying product attributes with desired Kansei impacts.     

Applying Kansei engineering to design logistics services – A case of home delivery service

Home delivery service (HDS) has grown fast in recent years because more and more customers engage in Internet and television shopping. Moreover, due to the rising competition in the HDS sector, service providers need to put more concentration on the continual improvement and differentiation of service to maintain the competitive advantage. After experiencing the current services, customers are always expecting the new ones. Thus, the idea of new service design never ends. Designers always have to insight into the real feelings of customers so that they could design the new service, which is able to meet customers' expectation. Kansei engineering is a means to transform real voices of customers into the product and service design. This method is able to quantify the relationship between feelings represented by simple words and design elements. In this study, the Partial Least Square (PLS) is used to analyze the relationships between the real feelings of customers and characteristics of HDS. Finally, this study combines those characteristics, which are strongly related to important feelings, to obtain the original idea of new design of HDS.Relevance to industryAs stated in this abstract, our study offers an exemplification on applying Kansei engineering to design service in service industries. Specifically, along with the application of Kansei engineering, the research findings offer a technique for service design of service industries.     

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.     

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.     

A Y-channel design for improving zeta potential and surface conductivity measurements using the current monitoring method

This study presents a new Y-channel design for measuring the zeta potential and surface conductance of a solid-liquid pairing using the current monitoring technique. The new design improves the throughput and reliability of the testing apparatus since the displacement between two solutions can be repeated many times without interfering with the experiments. It also increases the accuracy of the measurement by producing sharper start and end transitions for the current–time plot of the solution displacement process. In this design, efforts have been made to minimize the effects of electrolysis, Joule heating and undesired pressure driven flow on the measurements. An improvement on the current–time slope analysis is also presented. The Y-channel design was validated by comparing zeta potential measurements to published results. The zeta potential of several biological buffers relevant to the microfluidic community in plasma treated PDMS/PDMS and PDMS/Glass microchannels are presented. Preliminary studies of surface conductivity measurements using the Y-channel design were also conducted and are briefly discussed.     

A method to optimize the scope of a software product platform based on end-user features

ContextDue to increased competition and the advent of mass customization, many software firms are utilizing product families – groups of related products derived from a product platform – to provide product variety in a cost-effective manner. The key to designing a successful software product family is the product platform, so it is important to determine the most appropriate product platform scope related to business objectives, for product line development.AimThis paper proposes a novel method to find the optimized scope of a software product platform based on end-user features.MethodThe proposed method, PPSMS (Product Platform Scoping Method for Software Product Lines), mathematically formulates the product platform scope selection as an optimization problem. The problem formulation targets identification of an optimized product platform scope that will maximize life cycle cost savings and the amount of commonality, while meeting the goals and needs of the envisioned customers’ segments. A simulated annealing based algorithm that can solve problems heuristically is then used to help the decision maker in selecting a scope for the product platform, by performing tradeoff analysis of the commonality and cost savings objectives.ResultsIn a case study, PPSMS helped in identifying 5 non-dominated solutions considered to be of highest preference for decision making, taking into account both cost savings and commonality objectives. A quantitative and qualitative analysis indicated that human experts perceived value in adopting the method in practice, and that it was effective in identifying appropriate product platform scope.     

A constructive design method for two-layer perceptrons and its applicatio to the design of modular neural networks

Abstract: A multilayer perceptron is known to be capable of approximating any smooth function to any desired accuracy if it has a sufficient number of hidden neurons. But its training, based on the gradient method, is usually a time consuming procedure that may converge toward a local minimum, and furthermore its performance is greatly influenced by the number of hidden neurons and their initial weights. Usually these crucial parameters are determined based on the trial and error procedure, requiring much experience on the designer's part.
In this paper, a constructive design method (CDM) has been proposed for a two-layer perceptron that can approximate a class of smooth functions whose feature vector classes are linearly separable. Based on the analysis of a given data set sampled from the target function, feature vectors that can characterize the function'well'are extracted and used to determine the number of hidden neurons and the initial weights of the network. But when the classes of the feature vectors are not linearly separable, the network may not be trained easily, mainly due to the interference among the hyperplanes generated by hidden neurons. Next, to compensate for this interference, a refined version of the modular neural network (MNN) has been proposed where each network module is created by CDM. After the input space has been partitioned into many local regions, a two-layer perceptron constructed by CDM is assigned to each local region. By doing this, the feature vector classes are more likely to become linearly separable in each local region and as a result, the function may be approximated with greatly improved accuracy by MNN. An example simulation illustrates the improvements in learning speed using a smaller number of neurons.     

铁路信号基于电缆径路图自动识别的室外电缆配线图生成算法*

析了铁路信号工程设计中从电缆径路图到室外电缆配线图的生成原理和电缆径路图中电缆连接结构,给出了与该结构对应的树型定义和数据结构的列表定义,提出一种基于该数据结构的电缆连接自动识别算法和室外电缆配线图自动生成算法。     

A novel approach to product modularity and product disassembly with the consideration of 3R-abilities

In recent years, the production of electrical and electronic equipment (EEE) has been one of the fastest growing areas of manufacturing. The recent European Community waste EEE directives aim to promote the recycling, reuse and reduction (3R) of such waste. The 3Rs are becoming increasingly important, due to current strict environmental regulations. However, research to enhance 3R-abilities with better design presents some difficulties: there is no present analysis of the impact of each of the 3Rs and analytical methods are often too complicated, so there is a need for practical and simple guidelines. To resolve these issues, this paper presents a novel approach that considers the relationships between product components and identifies the ideal product disassembly pattern and modularity by constructing a component matrix, with regard to product disassembly. The product disassembly, which identifies modules and disassembly pattern, also initiates a strategy to enhance 3R-abilities. Two cases are presented to show the effectiveness of the proposed approach.     

A unified method for the design of telecommunication services

This paper describes a method for the design of telecommunication services. The method is aimed specifically at Integrated Broadband Communications (IBC) services, and describes two perspectives to the design of applications: the external perspective and the internal perspective. An external perspective is one that enables the whole application to be viewed for the purposes of the design of communication support. An internal perspective is one that enables consideration of only part of the application from the point of view of a human communicating entity. The use of the method is illustrated with respect to a tourism application.     

Creation of a unit block library of architectures for use in assembled scaffold engineering

Guided tissue regeneration is gaining importance in the field of orthopaedic tissue engineering as need and technology permits the development of site-specific engineering approaches. Computer Aided Design (CAD) and Finite Element Analysis (FEA) hybridized with manufacturing techniques such as Solid Freeform Fabrication (SFF), is hypothesized to allow for virtual design, characterization, and production of scaffolds optimized for tissue replacement. However, a design scope this broad is not often realized due to limitations in preparing scaffolds both for biological functionality and mechanical longevity. To aid scientists in fabrication of a successful scaffold, we propose characterization and documentation of a library of micro-architectures, capable of being seamlessly merged according to the mechanical properties (stiffness, strength), flow perfusion characteristics, and porosity, determined by the scientist based on application and anatomic location. The methodology is discussed in the sphere of bone regeneration, and examples of catalogued shapes are presented. Similar principles may apply for other organs as well.     

A function-oriented biologically analogical approach for constructing the design concept of smart product in Industry 4.0

The development of the Industry 4.0 paradigm and the advancement of information technology have aroused new consumer requirements for smart products that are capable of context awareness and autonomous control. Nature holds huge potential for inspiring innovative design concepts that can meet the ever-growing need for smart products since biology perceive and interact with their living environment for survival. However, to date, very few studies have explored the application of natural wisdom in building innovative design concepts for smart products. This paper proposes a function-oriented design approach for smart products, by analogizing to biological prototypes. To do so, a unified functional representation, based on the Function–behavior–structure (FBS) ontology, is proposed to abstract biological prototypes, followed by a fuzzy triangular numbers-based algorithm designed to locate appropriate biological prototypes as analogical sources for smart product development. Moreover, functional innovative strategies and a hybrid design process are formulated to develop design concepts of smart products, by integrating several existing engineering design methods. Finally, an illustrative design case of a smart natural resource collecting system is used to demonstrate the workability of the proposed method.     

A unique algorithm for the assessment and improvement of job satisfaction by resilience engineering: Hazardous labs

There are many potential dangers in laboratories of universities. Hence it should be focused on the actions and decisions of the individuals who work in the labs. Resilience Engineering (RE), the ability to recover quickly after an upset, is known as an important feature of a complex system which handles hazardous technical operations. In response to the need for the betterment of health, safety, and environment (HSE) at work; it is felt necessary to study the RE aspects if an unexpected events occurs. The main purpose of this study is to determine the role and effect of RE in improving job satisfaction and occupational safety in laboratories of universities. This study also presents an intelligent algorithm for assessing and improving job satisfaction in laboratories filled with hazardous materials by means of HSE and RE. In doing so, questionnaires related to HSE and RE are filled in by laboratory operators. The average result of each HSE and RE category is considered as input and job satisfaction as output for the proposed algorithm. An integrated neuro-fuzzy algorithm to find optimal solution is developed and tested for the purpose of this study. Also, results are tested and verified by regression analysis. Finally, with the help of Normal probability technique, outlier laboratories will be identified. The results are improved by means of RE as an input. This is one of the first studies introducing an intelligent algorithm for the improvement of job satisfaction by means of RE and HSE in hazardous laboratories.     

A CSP approach for the network of product lifecycle constraints consistency in a collaborative design context

In this paper, we are considering that the design process can be modelled in the form of a constraint satisfaction problem (CSP). CSP modelling or resolution has proved its efficiency within the framework of single-designer design. We propose to extend the functions of CSP to the context of multi-concept design of the same artefact. We define CoCSP as cooperative constraint satisfaction problem including the actors of the design problem. We are presenting the operating principles of an algorithm for the real-time management of design decisions, based on a model described in the form of a CoCSP for the integration of supply-chain constraints. This algorithm enables the number of design decisions rejected at a given moment in design to be kept to a minimum. The algorithm forms the core of a prototype for an unsupervised, generic constraint-based collaborative design system. Our aim is to produce a platform centred on the notion of constraints that will enable a product design problem to be modelled and solved by integrating supply-chain constraints as far upstream as possible.     

A time-frequency convolutional neural network for the offline classification of steady-state visual evoked potential responses

A new convolutional neural network architecture is presented. It includes the fast Fourier transform between two hidden layers to switch the signal analysis from the time domain to the frequency domain inside the network. This technique allows the signal classification without any special pre-processing and uses knowledge from the problem in the network topology. The first step allows the creation of different spatial and time filters. The second step is dedicated to the signal transformation in the frequency domain. The last step is the classification. The system is tested offline on the classification of EEG signals that contain steady-state visual evoked potential (SSVEP) responses. The mean recognition rate of the classification of five different types of SSVEP response is 95.61% on a time segment length of 1 s. The proposed strategy outperforms other classical neural network architecures.     

Design,realization and user evaluation of the SmartVortex Visual Query System for accessing data streams in industrial engineering applications

Objective: In this paper we present a Visual Query System, which allows users to graphically build queries over data streams and traditional relational data. The Visual Query System runs on top of a DSMS (Data Stream Management System).Methods: The system has been designed and implemented following the user-centered design approach. Two different releases of the system have been incrementally and iteratively designed and evaluated. The first release has been evaluated using heuristic evaluation. The second release, whose design was a refinement based on the results of the foregoing heuristic evaluation, was evaluated by several users. Moreover, a comparative evaluation involving users has been conducted on the second release.Results: The paper presents the visual query system, and the results ofthe various evaluations.Conclusion: Visual Query Systems for data streams are an effective tool for industrial engineers in querying and analyzing data streams from equipments.Practice and implications: The proposed visual query system has been employed in real industrial scenarios in order to visually query and analyze data streams produced by industrial machines.     

Naming the pain in requirements engineering: A design for a global family of surveys and first results from Germany

ContextFor many years, we have observed industry struggling in defining a high quality requirements engineering (RE) and researchers trying to understand industrial expectations and problems. Although we are investigating the discipline with a plethora of empirical studies, they still do not allow for empirical generalisations.ObjectiveTo lay an empirical and externally valid foundation about the state of the practice in RE, we aim at a series of open and reproducible surveys that allow us to steer future research in a problem-driven manner.MethodWe designed a globally distributed family of surveys in joint collaborations with different researchers and completed the first run in Germany. The instrument is based on a theory in the form of a set of hypotheses inferred from our experiences and available studies. We test each hypothesis in our theory and identify further candidates to extend the theory by correlation and Grounded Theory analysis.ResultsIn this article, we report on the design of the family of surveys, its underlying theory, and the full results obtained from Germany with participants from 58 companies. The results reveal, for example, a tendency to improve RE via internally defined qualitative methods rather than relying on normative approaches like CMMI. We also discovered various RE problems that are statistically significant in practice. For instance, we could corroborate communication flaws or moving targets as problems in practice. Our results are not yet fully representative but already give first insights into current practices and problems in RE, and they allow us to draw lessons learnt for future replications.ConclusionOur results obtained from this first run in Germany make us confident that the survey design and instrument are well-suited to be replicated and, thereby, to create a generalisable empirical basis of RE in practice.