International Journal of Product Development (8 papers in press)

Regular Issues

• Smart Product's Human-Computer Interaction Voice Recognition Method based on a Novel Feedforward Network Learning Algorithm  
  by Lian Xue, Chengsong Hu 
  Abstract: To avoid the impact of noise factors in speech recognition and improve the effectiveness of speech recognition, this paper proposes an intelligent product human-computer interaction speech recognition method based on a novel feedforward network learning algorithm. According to the dependent variable transformation relationship of nonlinear functions, a feedforward neural network speech recognition model is constructed. This model utilizes the dependent variable transformation mechanism of nonlinear functions to more flexibly simulate the complex mapping relationship between speech signals and recognition results. A semi-supervised loss function is introduced into the model training, and stochastic gradient descent is used for iterative optimization to achieve human-computer interaction speech recognition. Experiments have proven that the speech recognition accuracy of the method in this paper remains above 90%, and the speech recognition delay remains below 1 second, indicating good recognition performance, reliability, and application performance.
  Keywords: Feedforward network learning algorithm; Intelligent product human-computer interaction; Speech recognition; network model.
  DOI: 10.1504/IJPD.2025.10073285
   
  
• Designing a Myoelectric Prosthetic Arm for Trans-Radial Amputation based on Indonesian Anthropometric Data  
  by Sarika Zuhri, Suhendrianto Suhendrianto, Friesca Erwan 
  Abstract: Trans-radial amputation patients commonly use a prosthetic arm to replace the loss of a body part, specifically the hand. However, Indonesian users expressed concerns about high prices, non-ergonomic sizes, and inappropriate designs, leading to a lack of confidence. This study aims to design a myoelectric prosthetic arm tailored to Indonesian anthropometric data, incorporating static and dynamic measurements obtained from the Indonesian anthropometric database and prior research on ergonomic-based product design. Employing SolidWorks CAD, the study analyses the measurements to determine appropriate hand dimensions and inform the design elements for prototyping. The study develops technical drawings for product design and a myoelectric prosthetic arm aligned with Indonesian anthropometric data. A comparison of two market-available brands emphasises competitive features, focusing on appropriate sizing and ergonomic considerations. The study recommends exploring user acceptance, affordability through engineering economic analysis, and ethical implications as extended research beyond the current scope.
  Keywords: myoelectric prosthetic arm; trans-radial amputation; anthropometric data; Indonesian anthropometrics; ergonomics.
  DOI: 10.1504/IJPD.2025.10073414
   
  
• Adaptive Colour Compensation Method for Human-Computer Interaction Interface Images based on Colour Attenuation Prior  
  by Xueying Xu 
  Abstract: To address the issues of low contrast and information entropy in traditional colour compensation methods, this paper proposes a novel adaptive colour compensation method for Human-Computer Interaction (HCI) interface images based on colour attenuation prior. First, filtering algorithms are employed to denoise the original HCI interface image. Next, a linear model of image depth is established using colour attenuation prior, and Gaussian filtering is applied to images with varying scene depths. Then, the semi-quadratic splitting method is used to calculate the transmittance value of each pixel in the HCI interface image. Finally, adaptive Gamma correction weights are applied to perform colour compensation in the RGB colour space. Experimental results demonstrate that the proposed method achieves an average contrast of 76.56 and an information entropy range of 7.88.0, indicating excellent performance.
  Keywords: Human-computer interaction interface image; Colour attenuation prior; Linear model; Gaussian filtering; Gamma correction weight; Colour compensation.
  DOI: 10.1504/IJPD.2025.10073476
   
  
• Fuzzy Comprehensive Evaluation of User Experience Quality in Human-computer Interaction Interface under Visual Communication  
  by Chunhui Liu 
  Abstract: In order to overcome the problems of low indicator coverage, internal consistency, and accuracy in traditional methods, a fuzzy comprehensive evaluation method of user experience quality in human-computer interaction interface under visual communication is proposed. After extracting the visual communication features of human-computer interaction interface, preliminary evaluation indicators for user experience quality of human-computer interaction interface were determined. Grey correlation analysis method was used to screen the indicators, and a human-computer interaction interface user experience quality indicator system was built. Combined with C-OWA operator weighting method and fuzzy comprehensive evaluation, relevant evaluation results for user experience quality of human-computer interaction interface were obtained. The experimental results show that the maximum coverage rate of the evaluation indicators of the proposed method is 98.75%, the maximum internal consistency of the evaluation indicators is 0.98, and the evaluation accuracy is between 95.3% and 97.7%.
  Keywords: Visual communication; Human-computer interaction interface; User experience quality; Fuzzy comprehensive evaluation; C-OWA operator weighting method.
  DOI: 10.1504/IJPD.2025.10073477
   
  
• The Trajectory Planning Method for Industrial Robot Work Operation based on Spline Interpolation Algorithm  
  by Juchen Li, Dongsheng Ma 
  Abstract: In order to shorten the trajectory running time of industrial robots and reduce operating errors, a spline interpolation algorithm based method for industrial robot work trajectory planning is proposed. Firstly, a trajectory planning function for industrial robots is constructed using B-spline curves. Secondly, based on the curvature extremum point segmentation B-spline, independent S-shaped velocity planning, Simpson integration method is used to calculate the curve length and determine the time span. Again, the S-shaped speed planning strategy is adopted to implement independent speed configuration for segmented trajectories of industrial robots, achieving smooth transition speed control. Finally, calculate the Cartesian coordinates of the interpolation points for the trajectory of the industrial robot to complete the planning of the running trajectory. The test results show that the method proposed in this paper can shorten the trajectory running time to within 2 seconds and reduce the trajectory error to within 0.3 cm.
  Keywords: Spline interpolation algorithm; Industrial robot; Work operation trajectory; Trajectory planning.
  DOI: 10.1504/IJPD.2025.10073478
   
  
• Digital Marketing Strategy Optimisation of E-commerce Products Considering User Needs  
  by Shuang Li, Xueqin Ge 
  Abstract: To overcome various problems such as low market share, return on investment, and customer satisfaction in traditional methods, a digital marketing strategy optimisation method of e-commerce products considering user needs has been proposed. This paper analyses the current situation and challenges of digital marketing of e-commerce products, in order to determine the significance of user needs in digital marketing of e-commerce products. Based on the problems existing in digital marketing strategies of e-commerce products, the optimisation of digital marketing strategies is completed by strengthening the breadth and depth of data collection, using advanced data analysis techniques, segmenting users, promoting customized content, focusing on optimising user experience, optimising interaction and participation, etc. The case analysis results show that the maximum market share of the enterprise under the application of the proposed method is 1.47%, the maximum return on investment is 28.7%,and customer satisfaction ranges from 0.84 to 0.93
  Keywords: User needs; E-commerce products; Digital; Marketing strategy optimization; Segmenting users.
  DOI: 10.1504/IJPD.2025.10073479
   
  
• Method for Recognising the Ignition Point Target Position of Intelligent Fire Extinguishing Robot based on Machine Vision  
  by Lei Zhang, Baochen Yang, Tianshu Pang, Wenlian Guo 
  Abstract: In order to improve the accuracy of ignition point target location recognition and shorten the recognition time, a machine vision based intelligent fire extinguishing robot ignition point target location recognition method is proposed. Firstly, a binocular stereo vision system based on machine vision is used to capture images of the ignition point. Secondly, background noise is reduced through image segmentation, and occlusion is processed using normalised colour difference segmentation and linear projection methods. Finally, using Shannon entropy mutual information theory combined with colour moment feature extraction method, accurate recognition of the ignition point target position is achieved by quantifying the amount of image information and evaluating the degree of information sharing between image regions. The outcomes of the experiments reveal that the technique for pinpointing the ignition point's target location, as outlined in the paper, consistently achieves an accuracy level exceeding 95%. Additionally, the peak recognition duration is under 3 seconds.
  Keywords: Machine vision; Intelligent fire extinguishing robot; Ignition point; Target location recognition; Machine vision; Intelligent fire extinguishing robot; Ignition point; Target location recognition.
  DOI: 10.1504/IJPD.2025.10073480
   
  
• Global Matching Method for Virtual Reality Image of Intelligent Product based on SIFT Algorithm and Wavelet Transform  
  by Wei Zhang, QiLong LI 
  Abstract: In order to improve the accuracy and efficiency of image global matching, the research on intelligent product virtual reality image global matching method based on SIFT algorithm and wavelet transform is carried out. This method first completes the virtual reality image acquisition and grayscale processing of intelligent products, then decomposes the virtual reality image of intelligent products based on wavelet transform algorithm, and finally analyzes the low-frequency approximate sub quantum image obtained based on SIFT algorithm to complete the global image matching. The experimental results show that the proposed method can be applied to the global matching of virtual reality images of intelligent products, and its matching accuracy is more than 95%, and the time consumption is between 874~1092ms, and the application effect is good.
  Keywords: SIFT algorithm; Intelligent products; Global image matching.
  DOI: 10.1504/IJPD.2025.10073481