International Journal of Product Development (46 papers in press)
Xtreme Design A new approach for virtual innovation
by Caroline Heins, Daniel Jarr, Cornelius Herstatt
Abstract: Existing research regarding innovation widely assumes physical, in-person exchange. This cannot be guaranteed during a global pandemic like COVID-19, where people must work remotely, and are limited to virtual collaboration. Our paper is based on an exploratory action research in a multinational corporate operating in the material handling industry. We present a case study combining innovation methods with remote delivery. The action research was conducted between March and July 2020, and resulted in a novel approach for virtual innovation, which we call the Xtreme Design method. It has two advantages over traditional innovation methods: teams can innovate in a virtual remote work environment, and it is fast and cost efficient. We present the model and its elements, as well as the set of practices designed to realize it. For practitioners, the paper provides evidence and insights about the use of Xtreme Design to support the implementation of virtual innovation processes.
Keywords: INNOVATION; CASE STUDY; MANAGEMENT TOOL; VALUE; COVID-19; DESIGN THINKING; VIRTUAL INNOVATION.
A set-based-inspired design process supported by axiomatic design and interactive evolutionary algorithms
by Mikael Ström, Krister Wolff, Jeremy Jean-Jean, Göran Gustafsson, Ola Isaksson, Hans Johannesson
Abstract: This paper presents an approach towards a set-based design-inspired concept development process for products with a solution space consisting principally of different solution alternatives and parameterised variants of these. The hypothesis is that such a concept development process can be based on traditional synthesis methods, an SBD-inspired elimination strategy, axiomatic design and interactive evolutionary algorithms (IEAs) for the synthesis of solution candidates and the successive reduction of the solution space. Axiomatic design and its axioms are used to evaluate and eliminate unfeasible alternatives, whereas IEAs, combined with human judgement, are employed for the evaluation and elimination of variants. Stated criteria specifying a design problem can be of different kinds with different ontologies described by different authors. This study focuses on functional, constraining and qualitative criteria. Results from performed industrial case studies show that the proposed method can reduce the lead time in design work.
Keywords: concept development; set-based design; axiomatic design; interactive evolutionary algorithms; qualitative criterion.
What Makes a Product Manager? A Dynamic Capabilities View of Product Management
by David Finch, Nadège Levallet
Abstract: Todays dynamic environments require constant product innovation and have led to significant changes in product development processes and the product management (PM) function. Despite its strategic importance, we still lack clarity about the competencies needed to succeed in a PM role, and educational opportunities are limited in undergraduate academic and professional development contexts. Consequently, this study uses a content analysis method to examine the extent to which competency resources, as well as contextual factors (i.e., firm size, age, sector), impact the PM function. We explore our research questions through a dynamic capabilities perspective. Findings demonstrate that an organizations desired resources when recruiting PMs are indeed influenced by contextual factors and that meta-skill resources predominate, followed by PM task-specific and domain resources. We contribute to research and practice by providing guidance to PM educators and trainers as well as developing a conceptual model for future research.
Keywords: Product Management;rnProduct Development;rnProfessional Development;rnEducation.
Special Issue on: User Experience and Interaction Design for Smart Products
Multi-objective optimization method of human-computer interaction interface layout of music electronic products based on Adaptive Particle Swarm Optimization
by Gangling Liu
Abstract: Aiming at the problems of poor optimization effect in multi-objective optimization of human-computer interface layout of music electronic products, a multi-objective optimization method of human-computer interface layout of music electronic products based on adaptive particle swarm optimization is designed. Analyze the characteristics of interface layout structure, and determine the component layout level, layout parallax and split screen ratio as the optimization objectives; The fuzzy judgment results of multi-objective parameters are determined by fuzzy hierarchy, and the weight value is obtained; Analyze the basic principle of adaptive particle swarm optimization, set the adaptive particle radius and adaptive value, constantly update the adaptive particle position, build a multi-objective optimization model, and solve the optimal solution of the model through the objective function to complete the layout multi-objective optimization. The results show that the multi-objective optimization accuracy of the proposed method is higher than 90%.
Keywords: adaptive particle swarm optimization; Music electronic products; Human computer interaction interface; Multi-objective optimization; Adaptive particle radius; Fitness value.
Human computer interaction experience evaluation method of intelligent electronic product interface
by Hai-Xia Yan
Abstract: Aiming at the problems of large evaluation error and low correlation of evaluation indexes in the evaluation of human-computer interaction experience of intelligent electronic product interface, the evaluation method of human-computer interaction experience of intelligent electronic product interface is proposed. Firstly, the characteristic data of balance, conciseness and integrity of intelligent electronic product interface are extracted and preprocessed. Secondly, according to the divided experience dimension, the evaluation indexes of sensory experience, interactive experience and emotional experience are determined; The entropy value of the evaluation index is calculated through the score matrix to determine the weight of the evaluation index; Finally, the membership function is combined with the experience evaluation index weight set to build a fuzzy experience comprehensive evaluation model, and the evaluation results are modified by the correction function to realize the experience evaluation. The results show the evaluation method in this paper can effectively reduce the evaluation error.
Keywords: Intelligent electronic product interface; Human computer interaction experience; Dimension; Score matrix; Variation factor.
An adaptive median filtering of visual product image based on gradient direction information
by Kai Liu
Abstract: In order to overcome the problems of long filtering process, low signal-to-noise ratio of output results and low integrity of image information in traditional image median filtering methods, a new research method of visual product image adaptive median filtering based on gradient direction information is proposed in this paper. Based on the digital representation of the visual product image, the gradient direction information method is used to extract the noise information in the visual product image, so as to improve the quality of image filtering. Finally, the adaptive median filtering of visual product image is completed by processing the median and extreme values of visual product image. The simulation results show that the filtering process of this method takes 0.25min-0.45min, the signal-to-noise ratio can reach 85dB, and the integrity of image information varies from 97.5% to 98.2%, which proves that it effectively realizes the design expectation.
Keywords: Gradient direction information; Visual product image; Adaptive median filter; Noise extraction.
An intermediate interpolation of VR glasses display animation based on hierarchical constraints
by Xu Zheng
Abstract: In order to solve the problem of long interpolation time in traditional methods, intermediate interpolation method of VR glasses display animation based on hierarchical constraints is proposed. Firstly, the corresponding relationship between the 3D objects of VR glasses display animation is analyzed. Secondly, the swing posture of the user's head is obtained, the virtual scene in the user's VR glasses display animation is adjusted, and the image parameters of the inbetween of VR glasses display animation are obtained; Finally, the visual feature points are obtained by using the automatic feature point extraction method, and the intermediate interpolation is realized according to the interpolation algorithm based on hierarchical constraints. The experimental results show that when the number of iterations is 80, the image region overlap rate of this method is only 1.9%, and when the number of animations is 100, the time of intermediate interpolation is only 112 ms.
Keywords: Hierarchical constraints; VR glasses; Display animation; Inbetween interpolation; Visual feature points.
Accuracy evaluation method of sports bracelet monitoring based on grey comprehensive clustering
by Ruyun Zou
Abstract: In order to improve the accuracy and timeliness of evaluation results, this paper designed an accuracy evaluation method of sports bracelet monitoring based on grey comprehensive clustering. Firstly, the iterative algorithm is used to process the sports bracelet data to avoid the loss or abnormality of data affecting the quality of evaluation results and evaluation time. Then, a fuzzy comprehensive evaluation model is established to reflect the prominent influence of different evaluation indexes, and the relative membership degree of evaluation indexes is calculated. Finally, grey comprehensive clustering algorithm is used to optimize the fuzzy comprehensive evaluation model to complete the evaluation of the monitoring accuracy of the sports bracelet. Experimental results show that the maximum accuracy of this method can reach 83%, the minimum time is only 0.8s, and the amount of data effectively processed reaches more than 1600MB, which proves that the design expectation is effectively realized.
Keywords: Grey comprehensive clustering; Sports bracelet; Monitoring accuracy; Monitoring data; Relative membership.
Finger tip positioning and tracking method of intelligent moving Bracelet based on Improved Kalman filter
by Honggang Zheng
Abstract: In order to overcome the problems of poor positioning accuracy and low tracking accuracy of traditional methods, this paper proposes an intelligent motion Bracelet fingertip positioning and tracking method based on Improved Kalman filter.Firstly, the bracelet signal filtering is realized by the least square method; The Z-score method is used to normalize the sensor pressure data to realize data preprocessing; Then, the rigid structure model of human hand bone is constructed, the posture of human hand is reconstructed, the coordinate system of human upper arm is obtained, and the positioning ability of fingertip is improved; Finally, the RSSI signal of fingertip is collected by sensor, and the improved Kalman filter is used to realize the positioning and tracking of fingertip of bracelet.The experimental results show that the positioning accuracy of this method is 97.9%, the tracking accuracy is 97.6%, and the fingertip positioning and tracking effect is good.
Keywords: KNN algorithm; Z-score method; Low pass filter; least square method.
Intelligent wristband human abnormal behavior recognition method based on machine vision
by Chunling Liu, Chun-bao Huo
Abstract: In order to overcome the problems of low recognition accuracy and high recall rate of traditional methods, an intelligent wristband human abnormal behavior recognition method based on machine vision is proposed.Firstly, the human behavior video in the smart wristband is obtained through intensive sampling, and the image feature descriptor is obtained according to regularization processing; The human abnormal behavior features are extracted by DT algorithm; Secondly, softmax classifier is introduced to classify the extracted human abnormal line features of intelligent wristband; The dense trajectory algorithm is used to extract the abnormal behavior characteristics of intelligent wristband human body, and the machine vision is introduced to recognize the abnormal behavior of intelligent wristband human body.The experimental results show that the recognition accuracy of this method is as high as 98.2%, and the recognition recall rate is only 4%, which shows that this method can effectively improve the recognition effect.
Keywords: SmartBand?Machine Vision?Softmax Classifier?Abnormal behavior?Weighted processing method.
Special Issue on: AI/Machine Learning Techniques as a Tool for Process Modelling and Product Design
Color offset compensation method of product packaging image based on color difference interpolation
by Zhao Lan
Abstract: In order to effectively improve the accuracy of image color offset compensation and reduce the compensation time, a color offset compensation method based on color difference interpolation is proposed in this paper. Based on bilinear chromatic aberration interpolation algorithm, the full resolution chromatic aberration signal of image is estimated preliminarily. After image filtering, the basic color data and gray balance data of the image are compared to obtain the color offset. Taking color block as the minimum unit of deviation compensation, the average value of extended color level interpolation was added to the single color level of the calibrated image to complete color offset compensation. Experimental results show that the maximum compensation time of the proposed method is only 29.6s, and the maximum MSE value of the compensation result is only 0.179, indicating that the proposed method has higher compensation accuracy.
Keywords: Chromatic interpolation algorithm; Linear filtering; Product packaging image; Color offset compensation.
Special Issue on: Recent Advances in Human-AI Interaction for Smart Products
A method for layout planning of product web UI visual interface based on clone selection algorithm
by Yanrong Wang, JinJin Chao, Xuemin Wang
Abstract: In order to overcome the problems of long time and low recall rate in traditional product webpage UI visual interface layout planning methods, the paper proposes a product webpage UI visual interface layout planning method based on clone selection algorithm. Define the clone selection algorithm and determine the population evolution process of the interface layout planning. Based on this, determine the operation operator of the visual interface layout planning clone selection algorithm, and design the web UI visual interface layout planning algorithm flow to realize the visual interface layout planning. The experimental results show that when the number of product interfaces is 100, the number of extreme points of the planning function is 103, the interface layout planning time is only 7s, and the data recall rate is as high as 96.5%. It can be shown that the method in this paper has a better visual interface layout planning effect.
Keywords: Clonal selection algorithm; Layout optimization; Local optimization; Visual interface.
Gesture interactive recognition method of moving equipment based on Virtual Reality Technology
by Yang Shen
Abstract: The existing interactive recognition methods for gesture recognition of moving equipment have poor recognition effect and low recognition accuracy, which lead to some limitations of gesture interactive recognition. Therefore, a gesture interactive recognition method for moving equipment based on virtual reality technology is proposed. Firstly, we collect and divide the hand gesture features of sports equipment, analyze the common hand gesture categories of sports equipment, and use virtual reality technology to preprocess the hand gesture interactive recognition data of sports equipment. After preprocessing, we complete the hand gesture interactive recognition of sports equipment based on virtual reality technology. The experimental results show that the accuracy of gesture recognition is more than 95%, and that of complex gesture recognition is more than 93%. Compared with the existing gesture recognition methods, this method has higher effectiveness and recognition accuracy, which fully meets the research requirements.
Keywords: virtual reality; sports equipment; gesture interaction; gesture recognition;.
Visual Perception Based Human-Computer Interaction Information Classification Method for Intelligent Products
by Liting Zhou, Xuan Li, Minmin Guo
Abstract: This paper proposes a new intelligent product human-computer interaction information classification method based on visual perception. Design smart product human-computer interaction information collection device to realize rapid and accurate collection of smart product human-computer interaction information, and fusion processing of the collected information. The ISA model is built according to the principle of visual perception, and the model is optimized by the gradient descent method. The optimized model is used to extract the information attribute characteristics, and the intelligent product human-computer interaction information classification is carried out according to the information attribute characteristics. The experimental results show that the accuracy of information classification of this method is always above 94.7%, and the average classification time is 0.53s, which verifies the superiority of the method.
Keywords: visual perception; Intelligent products; Man-machine interaction; Information classification; ISA model.
Gesture Recognition Method for Wearable Sports Devices Based on Sparse Representation
by Yuzhou Gao, Guoquan Ma
Abstract: In order to effectively solve the shortcomings of traditional gesture recognition methods for sports devices, such as high error rate and long recognition time, this paper designs a gesture recognition method for wearable sports devices based on sparse representation. A gesture model was constructed according to the gesture features of wearable sports devices, and the standard characteristic quantities of gestures were obtained. A sensor is then used to quickly collect a sample of the gesture. The sparse coefficient is obtained. Gestures were classified and processed according to the minimum residual value and sparse coefficient, so as to obtain accurate gesture recognition results of wearable sports devices. The simulation results show that the correct rate of gesture classification is always above 95.41%, the error rate of gesture recognition is always below 5.32%, and the recognition time is less than 0.8s, which proves that the method has achieved good practical application effect.
Keywords: Sparse representation; Wearable sports devices; Gesture recognition; Characteristic; Classification process.
Fault data extraction of human-computer interaction interface for music electronic products based on improved second generation wavelet algorithm
by JunFang Liang, JiWu Li
Abstract: In order to solve the problems of low extraction accuracy and high time cost in human-computer interface fault data extraction, a method of human-computer interface fault data extraction for music electronic products based on improved second generation wavelet algorithm is proposed. The probability of data encounter in the human-computer interaction interface of adjacent music electronic products is calculated, and the interface data is collected with the help of probability distribution function; Judging by the function interval of data points; The similar fault data points are processed by sliding window to complete fault data similarity fusion; The second generation wavelet algorithm is improved by discrete wavelet transform. The energy distribution of fault data in different frequency bands is extracted, and the fault data is extracted in different scale space and wavelet subspace. The results show that the highest accuracy of fault data extraction is about 95%.
Keywords: Improved Wavelet Algorithm for Generation 2; Music Electronics; Human-Computer Interface; Fault Data Extraction.
Human Gesture Interaction Recognition Algorithm Based on Augmented Reality in Smart Wristband Equipment
by Cuirong Zhao, Yan Chen
Abstract: In order to overcome the poor recognition effect of traditional gesture recognition methods, this paper proposes a human gesture interactive recognition algorithm based on augmented reality for intelligent wristband device. The moving window method is used to detect the human gesture change image, and the mean filter is used to smooth the gesture image. The human gesture features of smart wristband device are extracted by augmented reality technology, and the interactive recognition model of human gesture of smart wristband device is constructed. The virtual real synthesis technology is used to synthesize the real scene image and the virtual position according to the obtained spatial coordinates, Complete the human gesture interactive recognition of intelligent wristband device. Simulation results show that the recognition accuracy of the proposed method can reach 99.9%, and the recognition efficiency is significantly improved.
Keywords: Augmented Reality; Smart wristband device; Human gestures; Interactive recognition.
User experience evaluation method of sports product based on genetic algorithm
by Dong Wang, Xia Liu, Jun Zhuang
Abstract: Aiming at the low evaluation accuracy and long evaluation time of traditional sports product user experience evaluation methods, a genetic algorithm-based sports product user experience evaluation method is proposed. By constructing a sports product user experience evaluation index decision matrix, various experience evaluation indicators are obtained; the membership value of each experience evaluation index is calculated, and the numerical structure relationship of potential experience indicators is established; the largest characteristic root in the structure relationship is used as the potential experience indicator Establish different evaluation attribute matrices, calculate attribute parameter weights, construct evaluation models, output initial evaluation results, use genetic algorithm to optimize the initial evaluation results, establish objective optimization functions, and obtain the optimization results of objective functions, which is the final Evaluation results. The simulation results show that the proposed method has higher accuracy in evaluating the user experience of sports products, and the evaluation time is shorter.
Keywords: Genetic algorithm; Sports products; User experience; evaluation model.
Design of virtual reality cycling intelligent interaction system based on VR technology
by Xin Jiang
Abstract: Aiming at the problems of small touch sensing range of user interface, low user satisfaction and long system response time existing in the existing intelligent interactive system, this paper designs an intelligent interactive system of virtual reality bicycle riding based on VR technology. The user interface and image filter of the system hardware are optimized to realize 3D virtual modeling of cycling. On this basis, VR virtual technology is introduced to effectively integrate constraint factors of interactive components, so as to improve the authenticity of outdoor cycling simulation and realize intelligent interaction. The experimental results show that the touch sensing range of the studied system is between 145-185nm2, the user satisfaction tends to 1 infinitely, and the response time is less than 2.3s, indicating that the system has good intelligent interaction.
Keywords: VR technology; Virtual reality; Cycling; Interactive systems.
Design of human-computer interaction display terminal system for intelligent home products based on color vision analysis
by Wenjuan Liu
Abstract: Aiming at the traditional smart home product display terminal system ignoring the analysis of home color vision, resulting in the display terminal system having low human-computer interaction adaptability, long running time, and experience satisfaction checking, the paper designs a smart home product based on color vision analysis. Human-computer interaction display terminal system. Use the Internet of Things platform to design the overall architecture of the smart home system, and design the Internet of Things wireless communication chip to optimize the system hardware functions; use the color vision analysis method to extract the visual element characteristics of the smart home product display interface to complete the human-computer interactive display terminal system software design. Experimental results show that the human-computer interaction adaptability of the designed system is higher than 0.8, and the shortest response time is 0.25s, and the experience satisfaction is as high as 75%, which has good application advantages.
Keywords: Color vision; Smart home; Human-computer interaction; Display terminal; Internet of things; Color sequence.
Research on layout optimization of human-computer interaction interface of electronic music products based on ERP technology
by Jing Han
Abstract: Aiming at the problems of low user satisfaction and long optimization time existing in traditional methods, an ERP based human-computer interaction interface layout optimization method for electronic music products was proposed. Using ERP technology to design the electronic music human-computer interaction interface layout optimization framework, with the support of the architecture using the G1 method to determine the human-computer interaction interface to the importance of the goal on the layout, combined with the judgment results are expected to achieve the optimal layout of visual attention allocation as the objective function, the layout of the building based on visual attention allocation optimization model, particle swarm optimization is used to solve the model and the layout optimization results are obtained. Experimental results show that only less than 0.3% of users are dissatisfied with the system, and the optimization time is less than 300ms, indicating high user satisfaction and short optimization time.
Keywords: ERP technology; Electronic music products; human-computer interaction; Interface layout; Layout optimization.
An evaluation method for human-computer interaction interface of sports electronic products based on Naive Bayes algorithm
by Xiaolong Shi
Abstract: There are some problems in the evaluation method of human-computer interaction interface of sports electronic products, such as long evaluation time and relatively accurate evaluation of interactive interface. An evaluation method of human-computer interaction interface of sports electronic products based on Naive Bayes algorithm is proposed. Determined by Fisher method choice, sports man-machine interface evaluation index of electronic products, and through the MRMR method to product interface evaluation index data to eliminate redundant data, through comprehensive evaluation matrix to calculate weight of the man-machine interface evaluation index membership degree, with the help of naive bayes algorithm to calculate weight evaluation index of discrete, The comprehensive evaluation model of human-computer interaction interface is constructed to complete the evaluation of human-computer interaction interface of sports electronic products. Experimental results show that the shortest evaluation time of the proposed method is about 31 s, and the evaluation accuracy is always higher than 90%.
Keywords: Simple Bayesian algorithm; Fisher selection; Redundant data; Comprehensive evaluation model.
Virtual display of intelligent human-computer interaction products based on attention matrix
by Lin Wang
Abstract: In order to solve the problems of low accuracy and poor effect of gesture recognition in traditional virtual display methods of intelligent human-computer interaction products, a virtual display method of intelligent human-computer interaction products based on attention matrix was proposed. Determine the NUI interaction mode, select the appropriate motion sensing interaction device Kinect, and use this device for gesture recognition. The information of intelligent human-computer interaction products such as gesture recognition results is saved through Array. The attention matrix of intelligent human-computer interaction products is established, the virtual display model of intelligent human-computer interaction products is constructed combined with the change of viewpoints, so as to realize the virtual display of products. Experimental results show that the accuracy of the proposed method can be maintained above 80% for difficult gesture recognition, and the accuracy of simple gesture recognition can reach 100%, and the virtual display effect of products is good.
Keywords: Attention matrix; Intelligent human-computer interaction; Product virtual display; Somatosensory interactive equipment; Array.
Special Issue on: Smart Products
An Interactive Method of Digital Fitness Equipment Based on Machine Learning
by Rui Zhang, Fang Liu, Cheng Wang
Abstract: Aiming at the problems of long operation time, high operation error rate and low user satisfaction in traditional methods, this paper proposes an interactive method of digital fitness equipment based on machine learning. Firstly, the paper designs an interactive platform for digital fitness equipment to collect user data. Then, the consistent convergence model is used to adjust the user's human-computer interaction requirements, the machine learning algorithm is used to design the digital fitness equipment, and the adaptive controller is used to control the user's human-computer interaction behavior. Finally, the human-computer interaction interface of digital fitness equipment is designed. The experimental results prove that the interactive interface operation time measured by the design method is short, the shortest time is only 2.51s; The error rate range of interactive interface operation is 0-0.7%, and user satisfaction is high, indicating that this method has a better application effect.
Keywords: machine learning; human-computer interaction; digital fitness equipment; consistent convergence; adaptive controller.
The 3D Animation Display of Smart Products Based on Hanoi Tower Recursive Algorithm
by Qiong Wang
Abstract: In the process of using traditional methods to display smart product 3D animation, the image is not preprocessed, resulting in poor animation display effect and low efficiency. Therefore, a smart product 3D animation display method based on the Hanoi Tower recursive algorithm is proposed. Using the weighted average method to grayscale the 3D image of the smart product, obtain the grayscale image, and combine the Harris corner detection method to extract the image feature points, and reconstruct the 3D image of the smart product based on the feature extraction results. The Hanoi Tower recursive algorithm is used to construct a 3D animation display model to realize the 3D animation display of smart products. The simulation results show that the 3D animation display image of the smart product of this method has higher clarity, higher display effect and higher display efficiency.
Keywords: Hanoi Tower; Recursive algorithm; Smart products; 3D animation display; Graying processing; Harris corner detection.
A fault diagnosis method of intelligent electronic equipment based on dynamic fusion
by Jun Qian, Kaijun Nie
Abstract: In order to overcome the problems of low accuracy of fault data extraction and long diagnosis time, a fault diagnosis method of intelligent electronic equipment based on dynamic fusion is proposed. Convolution neural network and long-term and short-term memory neural network are dynamically fused to extract the characteristic parameters of intelligent electronic equipment based on neural network. Combined with the principle of feature collection, the fault information of intelligent electronic equipment is collected, the covariance matrix of data noise data is constructed, the key noise is extracted, the noise reduction of fault data is completed, and the fault diagnosis of intelligent electronic equipment is carried out according to the results of fault information fusion and fuzzy kernel c-means clustering. The experimental results show that the highest accuracy of fault data extraction is about 95%, and the shortest time of sample fault data extraction is about 0.5s.
Keywords: Dynamic fusion; Intelligent electronic equipment; Noise interference degree; Fuzzy kernel c-means clustering; fault diagnosis.
Appearance design defect detection of rigid plastic products based on geometric feature extraction
by Jiang-lin Hua, Yuan-sheng Liu
Abstract: In order to overcome the problem of low geometric feature extraction accuracy and defect detection accuracy of traditional appearance design defect detection methods, a new appearance design defect detection method of rigid plastic products based on geometric feature extraction is proposed in this paper. This method first analyzes the types of design defects of rigid plastic products, and then extracts the defect area, the length and width of the defect area, the gradient characteristics and shape characteristics of the defect area. Based on the geometric feature extraction results, combined with Gaussian Laplace algorithm, the appearance design defects of rigid plastic products are detected. The experimental results show that compared with the traditional design defect detection methods, this method can accurately extract the geometric features of defects, so as to obtain more accurate defect detection results, and the maximum defect detection accuracy can reach 97%.
Keywords: Geometric feature extraction; Hard plastic products; Appearance design; defect detection.
Expression capture of virtual reality equipment based on expression weighted distance SLLE
by Shuitian Yan
Abstract: In order to overcome the problems of long time-consuming and high error in traditional expression capture methods, an expression capture method for virtual reality devices based on expression weighted distance SLLE is proposed. The LM algorithm is used to generate the virtual viewpoint of facial expression, and the adaptive weighted LDP method is used to process the facial expression features, remove the redundant information and retain the key features of the image. Considering the differences between different image types and viewpoints, the weighted distance SLLE method is used to capture facial expression images. Experimental results show that this method can effectively capture the viewpoint in facial expression, and the time is short and the expression capture error is small.
Keywords: expression weighted distance SLLE; virtual reality equipment; adaptive weighting; face viewpoint.
Double fingerprint accurate identification method of intelligent door lock based on spatio-temporal information feature fusion
by Liuping Cai, Fenghui Huang
Abstract: Aiming at the problems of low recognition accuracy and large feature extraction error in the dual fingerprint recognition of intelligent door lock, a dual fingerprint accurate recognition method of intelligent door lock based on spatio-temporal information feature fusion is proposed. Set the standardized form of dual fingerprint image, calculate the gray mean and variance of fingerprint image, and complete fingerprint image preprocessing; According to the coordinate relationship of the dual fingerprint direction field of the intelligent door lock, the dual fingerprint block of the intelligent door lock is divided, and the feature extraction is completed by solving the gradient value of the dual fingerprint block. The temporal and spatial features of fingerprint images are fused, and the fusion results are corrected with the help of calibration function to complete accurate fingerprint identification. The results show that the recognition accuracy of the proposed method is good.
Keywords: spatiotemporal information feature fusion; Intelligent door lock; Double fingerprint; Equalization; Calibration function.
A real-time acquisition method of local change features of 3D animation considering product design
by Weijia Chai, Zhiqiang Yue
Abstract: In order to improve the poor matching effect of traditional feature acquisition methods, a real-time feature acquisition method of 3d animation local changes considering product design is proposed in this paper. Firstly, the local variation characteristics of the animation are described according to the product design concept. Then, the information transferred in the design of the product is analyzed, and the anti-noise ability of the change feature descriptor is fitted by gaussian difference function. Finally, the expression factor of product appearance is transformed into the extreme point information of the change feature, and the extreme point equation of the local change feature is obtained. The real-time collection of local variation features is realized by considering product design rules. The results show that the matching effect of the proposed method is 200 dimensions higher than that of traditional methods, and the recognition rate is 40%~10% higher than that of traditional methods.
Keywords: product design; 3D animation; Local variation characteristics; Real-time acquisition; Data collection; Sampling method.
Research on secure storage data access control of smart TV based on blockchain
by Jianxin Qiu
Abstract: In order to solve the problems of low data security, access control accuracy and long data query time existing in traditional data access control methods, this paper proposes a secure storage data access control of smart TV based on blockchain. Firstly, the naive Bayesian algorithm is used to calculate the posterior probability according to the data safety level; Secondly, the category corresponding to the maximum posterior probability is regarded as the category of the data, and the data classification is realized by iterative calculation; Finally, on the basis of data classification, different categories of smart TV secure storage data access control are realized through ciphertext encryption, data decryption, access policy update and other steps based on blockchain. Experimental results show that the method has high data security, the average accuracy of data access control is 96.3%, and the data query time is always less than 0.5s.
Keywords: Blockchain; Smart TV; Secure storage of data; Access control; Naive Bayesian algorithm; Ciphertext encryption; Data decryption.
A Color Enhancement Method of Plane Image Based on the Interactive Interface of Mobile Smart Devices
by Jianjun Wang
Abstract: When using the existing methods to enhance the image color of the interactive interface of mobile intelligent devices, there are some problems, such as long enhancement time, easy to produce image distortion and so on. Therefore, a color enhancement method for planar image of interactive interface of mobile intelligent device is proposed. The target image is collected by image sensor, the plane image is transformed from high-dimensional subspace to low-dimensional subspace, the linear map is established, the projection distance between each single pixel in the image to be processed is obtained, and the image is processed by local dimension reduction method to complete the preprocessing; The histogram method is used to adaptively adjust the dark area in the interface, and the enhancement is completed by mapping function and median filter method. The results show that this method has low image distortion rate and short time in image enhancement processing.
Keywords: mobile smart device; interactive interface; plane image; color enhancement; image acquisition.
Special Issue on: User Experience for Advanced Human-Computer Interaction
Visual communication method of graphic language in industrial product design
by Fang Wang, Huaxi Chen
Abstract: In order to improve the ideality of product design effectively, enhance its market attraction and competitiveness and obtain greater economic benefits, the paper designs the visual communication method of graphic language in industrial product design. Through the analysis of industrial product design characteristics, principles and practical problems, the interview method and qualitative analysis method are used to explore the reasons for the low impact of product packaging. Then brainstorming method is used to quantitatively analyze the unique selling points of products, and select graphic language elements, and then construct industrial product packaging graphic language and its scene, to realize the visual communication design of industrial product graphic language. The experimental results show that the design satisfaction of this method is high, the competitiveness index of product packaging is 90%, the attractiveness index is 0.7, and it can obtain more economic benefits of industrial products.
Keywords: Industrial products; Visual communication; Graphic Language; Qualitative analysis; Brainstormingrnrn.
Color difference detection method of product packaging based on local enhancement
by Hua Song
Abstract: In order to overcome the problem of high detection absolute error rate and complexity of detection time in traditional methods, this paper proposes a method of color difference detection based on local enhancement. The projection value of the color area block of the outer packaging is determined. The threshold segmentation method is used to detect the color difference of the outer packaging of the product. The difference pixels are extracted by local enhancement method to detect the color difference of the outer packaging. The results show that the average accuracy of the method is 98.6%, the time of color difference detection is only 6S, and the absolute error rate of color difference detection is 0.26%. This method can effectively reduce the complexity of detection time, reduce the absolute error rate of detection, and improve the correct identification rate of color difference of outer packaging.
Keywords: Binarization energy map; threshold segmentation method; local enhancement; feature extraction.
Adaptive adjustment method of intelligent industrial product dimension accuracy
by Keke Yang
Abstract: In order to overcome the problems of low precision and long time in the traditional method of adjusting the accuracy of external dimensions, this paper proposes an adaptive adjusting method for the accuracy of external dimensions of intelligent industrial products. The car model of industrial product dimension accuracy is constructed. After predicting and adjusting the parameters adaptively, the intelligent industrial product dimension error is detected, and the calculation process of dimension coefficient correction factor is determined. By describing the grinding process of industrial products, the residual vector in the adjustment process is determined to realize the adaptive adjustment of intelligent product dimension accuracy. The experimental results show that the adjustment time is only 1.5s, and the relative error and absolute error are close to zero. The method in this paper can improve the accuracy and effect of dimension adjustment, and reduce the time-consuming of industrial product dimension adjustment.
Keywords: CAR model; adjustment parameter; residual vector; correction factor.
Defect detection method of product appearance design based on visual communication model
by Tiesheng Liu
Abstract: In order to overcome the problems of low detection accuracy and efficiency in traditional product appearance design defect detection methods, a product appearance design defect detection method based on visual communication model was proposed. The X-ray visual inspection system is used to collect the image of product appearance design, and the method of superposition of multiple images and histogram equalization are used to denoise and enhance the defect image of product appearance design. Gabor transform is used to extract the features of the preprocessed defect image. According to the extraction results, VR virtual reality reconstruction method is used to construct the visual inspection model of product appearance design defects, and the defect detection of product appearance design is realized. The simulation results show that the proposed method has better detection results and improves the detection efficiency. The shortest detection time is only 5s.
Keywords: Visual communication; Appearance; Modeling design; defect detection; Integral projection method; Gabor transform.
Personalized recommendation of smart home products based on convolution neural network
by Xiaoyuan Luo, Jun Liu
Abstract: In order to solve the problems of high recommendation error and long recommendation time in traditional personalized recommendation methods for smart home products, a new personalized recommendation method for smart home products based on convolution neural network is proposed. The attributes of smart home products are superimposed, and the square root of the attribute weight vector and all components are calculated. Determine the relationship between the attributes and important factors of smart home products to be recommended, and complete the weight calculation of smart home product recommendation. The personalized recommendation model of smart home products is constructed, and the convolution neural network is used to obtain the global optimal solution of the personalized recommendation model, so as to realize the personalized recommendation of smart home products. The experimental results show that the minimum error of the proposed method is about 0.3%, and the recommendation time is less than 15s.
Keywords: Smart home products; personalized recommendation; product attributes; convolution neural network.
Product design difference perception model based on visual communication technology
by Yinyin Wang
Abstract: In order to overcome the problems of high output error rate and low signal-to-noise ratio in the current product appearance design difference perception model, a product appearance design difference perception model based on visual communication technology is proposed and designed. Based on the data analysis of product appearance design difference perception, the basic information of difference perception is introduced to adjust the overall image information of product appearance design, and the product appearance design difference perception model is set based on visual communication technology, so as to achieve the purpose of design research of the overall model. The experimental results show that the output error rate of the designed model is small, the average output error is 3.08%, the peak signal-to-noise ratio is high, and the highest peak signal-to-noise ratio is 47.2. It shows that the designed model meets the needs of improving the effect of product appearance design.
Keywords: Visual communication technology; product appearance; appearance design; design difference perception model.
User Experience Measurement Methods of E-commerce Products Based on Cloud Model
by Ming Yang
Abstract: Traditional e-commerce product user experience measurement methods have the problems of poor measurement effect and low user experience satisfaction. This paper proposes a cloud based e-commerce product user experience measurement method. This paper uses the hierarchical structure model to build the e-commerce product user experience measurement index system to obtain the e-commerce product user experience index. Determine the proportion of indicators to complete the construction of cloud model; Calculates the cloud drop expected value, expected entropy and super entropy in the cloud model, and transforms the e-commerce product user experience measurement index weight coefficient into normal cloud to realize the e-commerce product user experience degree Quantity. Though the results show the measure accuracy is about 98% , and the measurement time is less than 2 s.
Keywords: Cloud model; E-commerce products; User experience; Weight coefficient; Fuzzy comprehensive metric.
Real time information sharing model of product supply chain based on Internet of things
by Yanrong Wang, JinJin Chao, Ying Li
Abstract: In order to overcome the problems of poor information security and low sharing efficiency existing in the traditional product supply chain information real-time sharing model, this paper proposes a new product supply chain information real-time sharing model based on Internet of things technology. Set the information double chain storage mode, calculate the data writing speed of the Internet of things, determine the optimal block size of the product supply chain through the difficulty control algorithm, and optimize the anti tampering ability of the model to the information when there are attacks in the supply chain. Using the supply chain technology to establish the underlying peer-to-peer network, the dual chain storage of regional product information data sharing, building product information real-time sharing model. Experimental results show that compared with the traditional model, this model has higher security and sharing efficiency, and the sharing efficiency is always above 90%.
Keywords: Internet of things technology; Product supply chain; Information real-time sharing; Model building; tamper proof; Difficulty control algorithm.
User Experience Evaluation of Intelligent Sports Bracelet Based on Multi-factor Fusion
by Wei Liu, Zhen Liu
Abstract: In order to overcome the problems of the traditional methods, such as the low accuracy of calculating the weight of evaluation factors, the high error rate of evaluation and the long output time of evaluation results, a user experience evaluation method based on multi-factor fusion was proposed. Building intelligent motion bracelet user experience evaluation system, determine various evaluation factors relative to the membership degree of evaluation factor set, to construct judgment matrix, get the weights of preliminary results, the weighting results are consistency check, get the final weight calculation results, and the multi-factor fusion method was used to construct intelligent motion bracelet user experience evaluation model, get the final user experience evaluation result. Experimental results show that the calculation accuracy of the weight of evaluation factors is more than 94%, the error rate of evaluation varies from 0 to 2%, and the average output time of evaluation results is 0.62s.
Keywords: Multi-factor fusion; Intelligent sports bracelet; User experience evaluation; Evaluation factor set; weighting.
Evaluation method of smart bracelet health monitoring accuracy based on multi-level data fusion
by Weicheng Ma, Yanfei Lv
Abstract: In the process of smart Bracelet health monitoring, there are some problems, such as low efficiency of accuracy evaluation and high fusion error rate. An accuracy evaluation method of smart Bracelet health monitoring based on multi-level data fusion. The intelligent bracelet is monitored by information collection, information judgment and information display. The v1.1 temperature acquisition sensor and pulse sensor are selected to measure the temperature, heart rate and blood oxygen saturation. The cloud design and fuzzy information clustering method are used to realize the effective integration of multi-level data and information, and the maximum likelihood estimation model of the health index of the intelligent bracelet is established to obtain the intelligent information Evaluation results of the accuracy of health monitoring of bracelet. The experimental results show that the accuracy evaluation efficiency of the proposed method is always above80%, and the fusion error rate is always below 0.1%.
Keywords: Multi-level data fusion; smart bracelet; health monitoring; accuracy evaluation.
Product 3D virtual display scene modeling based on augmented reality technology
by Heng Luo
Abstract: In order to overcome the problems of low precision and long time in traditional methods, a 3D virtual display scene modeling method based on augmented reality technology is proposed. The 3D virtual display scene image of the product is obtained by camera, and the 3D virtual display scene coordinate is obtained by using the 3D registration technology in augmented reality. The real product scene image and virtual position are synthesized in virtual reality according to the acquired 3D space coordinates, and the geometric distortion phenomenon generated in the synthesis process is corrected. After the correction, the 3D virtual display scene coordinates are obtained, the product scene image is binary processing, the product image contour is extracted, and the 3D virtual display scene of the product is generated. The simulation results show that the modeling accuracy of this method is kept at 95%, and the modeling time is only 4s.
Keywords: Augmented reality technology; 3D virtual; display scene; 3D registration technology; anti perspective transformation method.
Fast fusion method of virtual image of product shape based on progressive fill line algorithm
by Yang Luo, Yan Wang
Abstract: In order to overcome the problems of low precision and speed in the existing fast fusion methods of virtual image of product shape, a new fast fusion method of virtual image of product shape based on progressive fill line algorithm is proposed in this paper. The progressive filling line algorithm is used to fill the virtual image holes of product shape, and dibr technology is introduced to reconstruct the image position and restore the image color. Finally, the fuzzy minimum error threshold algorithm and Ostu algorithm are used to calculate the optimal threshold and global threshold of the product shape virtual image features, so as to realize the rapid fusion of product shape virtual image. The experimental results show that the design method can ensure the fusion accuracy and clarity of virtual image of product shape, and the shortest fusion time is 7ms.
Keywords: Progressive fill line algorithm; time-varying illumination; product shape; virtual image; image fusion.
Study on spatial layout evaluation of game UI interface based on grey interval clustering
by Zuhui You
Abstract: In order to overcome the problems of time-consuming and low accuracy of traditional evaluation methods, a new evaluation method of game UI spatial layout based on grey interval clustering is proposed. This paper analyzes the relevant content of the game UI interface, integrates the interval gray degree and gray theory, designs the gray interval whitening weight function and gray interval clustering process. On this basis, according to the gray interval category of the index sample to be evaluated, combined with its gray interval category, the spatial layout of the game UI interface is evaluated. The experimental results show that the time-consuming of the evaluation result generation process varies from 0.60min to 0.79min, the accuracy of the evaluation result varies from 92.5% to 94.6%, and it has stronger adaptive ability, which proves the effectiveness of the method.
Keywords: Game UI interface; interface spatial layout; grey interval clustering; spatial layout evaluation.
Monitoring method of use frequency of sports electronic products based on non-uniform sampling
by Yujie Wei
Abstract: In order to overcome the problems of slow response speed of monitoring instruction, poor anti-interference effect and large error of monitoring results, this paper proposes a frequency monitoring method for sports electronic products based on non-uniform sampling. The frequency information of sports electronic products is collected by non-uniform sampling, and the noise reduction processing is carried out by using the average operator filter to obtain reliable output results. Finally, the monitoring procedure is started to complete the monitoring of the frequency of sports electronic products. The experimental results show that the response time of the monitoring instruction is 3.0s-3.8s, the error of the monitoring results varies from 4.2% to 4.7%, which proves that the method has faster response speed and higher effectiveness to the monitoring instruction, and has stronger anti-interference effect in the monitoring process, which indicates that the method has higher application advantages.
Keywords: Sports electronic products; frequency of product use; frequency monitoring; nonuniform sampling; average operator filter.