Ebook: Design Studies and Intelligence Engineering
The technologies applied in design studies vary from basic theories to more application-based systems. Intelligence engineering also plays a significant role in design sciences such as computer-aided industrial design, human factor design, and greenhouse design, and intelligent engineering technologies such as computational technologies, sensing technologies, and video detection encompass both theory and application perspectives. Being multidisciplinary in nature, intelligence engineering promotes cooperation, exchange and discussion between organizations and researchers from diverse fields.
This book presents the proceedings of DSIE 2022, the International Symposium on Design Studies and Intelligence Engineering, held in Hangzhou, China, on 29 & 30 October 2022. This annual conference proves a platform for professionals and researchers from industry and academia to exchange and discuss recent advances in the field of design studies and intelligence engineering, inviting renowned experts from around the world to speak on their specialist topics, and allowing for in-depth discussion with presenters. The 189 submissions received were each carefully reviewed by 3 or 4 referees, and the 62 papers accepted for presentation and publication were selected based on their scores. Papers cover a very wide range of topics, from the design of a bachelor apartment, or a children’s backpack for healthy spine development, to interpretable neural symbol learning methods and design elements extraction from point-cloud datasets using deep enhancement learning.
Offering a varied overview of recent developments in design and intelligence engineering, this book will be of interest to all those working in the field.
The technology applied in design studies varies from basic theories to more application-based systems. Intelligent engineering also plays a significant role in design sciences such as computer-aided industrial design, human factor design, and greenhouse design, and these intelligence engineering technologies also include topics from both theoretic and application perspectives, such as computational technologies, sensing technologies and video detection. The annual International Symposium on Design Studies and Intelligence Engineering (DSIE) aims to promote cooperation between organizations and researchers in these fields, invite renowned professors from around the world to speak on these topics in greater depth, and allow for the in-depth discussion of technical presentations with the presenters.
A total of 189 submissions were reviewed for this collection of papers on design studies and intelligent engineering. The conference chairs selected papers based on the scores given by three or four referees, after which 62 papers were accepted for publication in this issue. The 2022 International Symposium on Design Studies and Intelligence Engineering (DSIE2022) was held in Hangzhou, China on October 29–30, 2022, and provided a platform for all professionals and researchers from industry and academia to present and discuss recent advances in the field of design studies and intelligence engineering. DSIE 2022 was sponsored by Zhejiang Sci-Tech University and co-sponsored by the Chinese Mechanical Engineering Society-Industrial Design, the Aurel Vlaicu University of Arad, Techno India College of Technology, and Tanta University.
We would like to thank all contributors for their efforts in submitting their manuscripts on time. We would also like to express our gratitude to the reviewers for their support, and acknowledge their contribution to the timely completion of this volume.
Lakhmi C. Jain
Valentina Emilia Balas
The paper aims to construct a framework for museums’ cultural and creative product design and summarize the potential gaps in this field. To achieve this goal, the author used a literature review method integrated with a systematic review and bibliometric analysis. In the analysis stage, the paper identified two significant aspects and seven themed clusters of design research and discovered four primary potential gaps that need to be filled in the future.
To apply user experience theory to traditional cultural apps, to study the differences in user experience of several typical traditional cultural apps, and to propose targeted strategies for the design of traditional cultural apps.
From the three aspects of user’s sensory experience, interactive experience and emotional experience when using traditional cultural apps, analyze, compare and study the sensory experience, interactive characteristics and user psychology of several typical traditional cultural apps, and summarize the similarities and differences of different apps Points and advantages and disadvantages, summarize the design methods and strategies of traditional cultural apps based on user experience.
In the design of traditional cultural apps, it is necessary to fully consider the user’s experience in the three aspects of sensory, interaction and emotion, improve the sense of immersion, content diversification and design refinement, and design a good product model to achieve user goals. Meet user needs, optimize user experience, and improve user stickiness.
To provide a more optimized design method for the furniture design of single apartment by combining the user demand, space distribution and CMF design. To meet the needs of single apartment furniture users in many aspects, including physical, psychological, social, self-development, etc. By analyzing the needs of furniture users in bachelor apartment and the application of CMF design method in furniture, taking IKEA furniture as an example, the importance of the combination of furniture design and CMF design method in bachelor apartment is clarified. This paper puts forward the design methods of sensory needs, interaction needs and cultural needs of bachelor apartment furniture, and expounds its design and application, so as to provide new design ideas and methods for the design of bachelor apartment furniture, in order to realize the empty-nest youths pursuit of quality life.
Recent research advances on fabric dyeing have focused on modeling the relationship between dye concentrations and the final color on fabrics. The emerging techniques in related studies have great potential to evolve the traditional dyeing industry to manufacture much more smartly. Given that dyeing is a complex process regulated by many factors, one of the challenging problems in the aforementioned techniques is to maintain the modeling accuracy at acceptable level. Other than developing high-performance algorithms and model architectures, it is also important to include effective data pre-processing techniques in modeling. In this paper, we show that conducting log-transform to the industrial dyeing data can greatly improve the performance of industrial dyeing recipe models. Such observations are confirmed on modeling tasks using different formats of color as input and different types of loss function in the model training. These findings may provide useful implications for related studies for the dyeing industry.
The research starts from the thinking and analysis paradigm of “problem-reaction-response”, through the interpretation and reconstruction of existing problems, and the “opportunity” to respond from the crisis. Finally, through the ascension of digital technology, the reshaping of industries across borders, and the empowerment of living states, we will break through the dimension of mere human and technological experience and return traditions to everyday life, thus exploring the construction of a new cultural ecology and innovation system on the basis of digital ecology.
Deep learning (DL) is difficult to provide explanations verified by non-technical audiences such as end-users or domain experts. This paper uses symbolic knowledge in the form of an expert knowledge graph, and proposes an interpretable neural-symbol learning (RF-YOLOv5) method, designed to learn symbols and deep representations. Finally, the deep learning representation and knowledge map are integrated in the learning process, so as a good basis for interpretability. Among them, the RF-YOLOv5 method involves specific two aspects of interpretation, respectively in reasoning and training time (1) YOLOv5-EXPLANet: experts alignment explained part of the auxiliary network architecture, combined convolutional neural network, using symbol representation, and (2) interpretable artificial intelligence training process, correct and guide the DL process and such symbol representation form of knowledge graph. The camera is placed above the refrigerator to detect the variety of ingredients, and then used in the RF-YOLOv5 method recommended by Zhejiang cuisine recipes, and demonstrates that using our method can improve interpretability while improving interpretability.
With the popularization of green concept, urban vegetable planting is gradually rising. After the development of urban planting products in recent years, different development directions and strategies such as intelligent planting machines, planting cabinets and urban farms have been distinguished. Different from the traditional planting environment, the balcony glass room in the city is similar to a small greenhouse, and there are many factors to be considered for urban planting. Therefore, there are greater challenges for the design of planting products. For the multi factor product exploration, this paper will use AHP-TOPSIS method to establish the evaluation model of urban small-scale planting products, and sort the three main development directions of small-scale urban planting products according to the evaluation model, so as to provide some reference and suggestions for the development direction and design practice of urban small-scale planting products.
In order to explore the design strategy of participatory design approach in the design of external human-machine interface (eHMI), this paper at the theoretical level researches the relevant literature and typical interfaces of eHMIs, and sorts out the basic concepts of explicit human-vehicle interaction features theory. Through the user participatory design method, we summarized the key design points of the eHMI and produced a design prototype, and optimized the prototype according to the participatory design experimental results and actual needs to obtain a design solution. The design was tested and evaluated at the practical level, and a strategy for user participation in the design of the external human-machine interface was concluded. The results show that the participatory design approach can improve the usability and acceptance of eHMIs, reduce the cognitive differences in the presentation of interface content, and provide a reference for the design of out-of-vehicle HCI in future work.
Human health and quality of life are negatively impacted by apnea, an increasingly prevalent sleep disorder. For monitoring and managing sleep apnea’s side effects and consequences, accurate automatic algorithms for detecting sleep apnea are crucial. In this paper, deep transfer learning methods are employed for the detection of OSA events from Electrocardiograph (ECG) and Photoplethysmography (PPG) signals. ResNet34 is a deep learning model based on convolutional neural networks (CNNs). Transfer learning algorithms such as AlexNet, VGG16, VGG19 and ResNet50 are implemented. In order to train the ResNet34 model data augmentation, optimal learning rate finding, and fine-tuning are used. To obtain generalizable models, a training set of data is divided into three sets: a validation set for adjusting hyperparameters and improving generalizability, and a test set for evaluating generalizability on unknown data. Deep transfer learning models have the best accuracy, sensitivity, specificity, precision, and F1 score with 97.86±1.24%, 99.65%, 97.12%, 98.16% and 98.90% respectively. It can assist sleep lab technicians in screening patients for OSA events continuously through PPG and ECG signals.
Nowadays in UAV and remote sensing image processing area, rotated object detection has been attached more and more attentions. However, there are few studies of this based on Transformer, which is much stronger than CNN for feature extraction. Moreover, the well-developed IoU based loss function in horizontal object detection area is not well fits with rotated objects. In this paper, we argue that Transformer of pyramid structure called Swin-Transformer is an effective alternative of CNN. Specifically, the finetuned Swin-Transformer with Relatively Position Encoding (RPE) performed much better than other backbones generally used. Moreover, the new kind of IoU loss called Gaussian Estimate Loss (GE Loss) that use gaussian kernel to model object is applied in our model. It can increase the precious of the model. This loss is in contract to other Gaussian modeling loss function for adding direction vector that can solve the difficulty of testing objects close to square. Experiments on DOTA dataset achieved 84.99% map, which indicates that and our experiment shows that these improvements of our model are effective.
The low resolution of infrared images makes it more difficult to detect objects, and the quality of detection results obtained by the CNN based object detection model are worse for few-shot problems. Two-stage Fine-tune Approach (TFA) is effective to improve the precision of detection for few-shot problems. Because of the category imbalance of training samples, TFA has the problem of misclassification. To solve this problem, TFA with similarity contrast (SC-TFA) is proposed. The VOVNetv2 is used as the backbone network to improve the detection accuracy. The similarity contrast detection head is added to the detection module to improving the classify performance. And both cosine similarity and Euclidean distance are used as the similarity measure in the contrast loss function. The effectiveness of the improved TFA for the few-shot problem is verified on the VOC dataset and the infrared ship dataset. The average precision of the novel categories (nAP) of SC-TFA on VOC dataset and the infrared ship dataset reaches 54.92% and 41.1% respectively, which is 4.7% and 3.4% higher than TFA.
The purpose is to analyze the constructive approach of virtual digital display and its research status from the technical perspective, and to provide strategic ideas for the development of virtual digital exhibition. The methodology firstly starts from the concept of virtual digital exhibition, collects and organizes the application areas of virtual digital exhibition; secondly, identifies the composition of virtual digital exhibition system categories and technical support, summarizes the advantages and disadvantages of different categories of digital exhibition; points out the limitations of the current existence, outlines the challenges of the research and puts forward development suggestions. The conclusion outlines the virtual digital display building methods and presentation forms, analyzes the characteristics and development trends of the three building types, and enhances the presentation forms of virtual displays.
The imagery colors of traditional ethnic costumes are unique and have great reference value for modern design. In this paper, 3 representative minority costume images of Miao, Tibetan, and Korean were respectively selected as imagery sources, and 20 different structure types of patterns were chosen as the object to be colored. Image pre-processing, adaptive color extraction, and multi-dimensional features extraction were executed to build a color nexus network model. Based on the color parsing results, an algorithm for color migration of clothing images was designed and developed, which could output multiple types of color schemes. The overall rating of each color scheme was compared to introduce the optimal scheme. Also, the experimental part tested the effect of the color schemes in various scenarios. The average pre-processing time cost of a single image is 0.05 seconds, the output time of the color network diagram is 0.38 seconds, and the output time of a single-color scheme is 1.44 seconds. The study can quickly provide an auxiliary decision for contemporary pattern color design.
In order to reduce the interference of stripe signal on the density automatic measurement of woven fabric and extend the the application scope, an adaptive Gaussian Notch Filtering (GNF) algorithm based on Fast Fourier transform is proposed. In the pre-proceesing stage, the Fourier transform was utilized to transform the woven fabric bitmap to spectral image, as to obtain the spectral characteristics of the striped fabric. The improved GNF algorithm was used to identify the peak of stripe signal, which determined the bandwidth radius and locate the stripe bright area. Based on the fused Fourier and GNF spectral map, interference frequency information was accurately removed and spatial map was restored to approximate pure color fabric image. Finally, the Morlet wavelet is utilized to analysis the density of the striped printed fabric. The experimental results show that the average subjective-objective consistency rate (AS-OCR) of the designed sample is 99.34%, and the range is 97.33%∼100%. The AS-OCR of the actual sample is 98.73%, ranging from 95.00% to 100%. The proposed method can effectively obtain the density of stripe printed woven fabric and expand the application scope of fabric density automatic detection.
To make 3D visual texture effect of surface with bare eye in the plane thickness of micron-level, based on Fresnel optics principle, for conventional free-form surfaces, the continuous surface “collapse” method of reducing the thickness of the Fresnel lens is prone to large areas of visible segmentation planes and the problems that the visual effects of the designed micro-textures are difficult to predict. In this paper, a unit texture construction method is proposed, which differentiates the free-form surface into square mesh cells whose size is smaller than the smallest size that can be recognized by human eyes. The micro-surface in each element is approximately treated as a square column with inclined plane at the top, and the normal vector of the inclined plane is close to the synthetic normal vector of the micro-surface. Then, according to the limit of the design thickness, the inclined plane column is “collapsed” to ensure that one end of the inclined plane touches the bottom, and the height difference of the inclined plane in the unit is less than the designed thickness. Finally, the light source is set for the completed gray image file. The brightness of each point in the image file is inversely proportional to the angle between the point normal vector and the light source, and the visual dynamic rendering effect of the overall scheme simulation is obtained by rotating the light source. The validity of the proposed method and the effectiveness of the simulation results are verified.
In order to fast identify and realistic simulate embroidery art, the respective texture characteristics of basic stitch in Simulation embroidery were extracted and preferred. Concretely, three feature extraction methods – gray co-occurrence matrix method (GLCM), Tamura method and gray difference statistics method (GDS), are combined to extract the features of embroidery needlework, and the best respected characteristics were compared and verified. Results shows that the best feature combination of needle texture in this paper is energy standard deviation, energy mean, standard deviation of moment of inertia, and mean of moment of inertia, which is defined as energy-moment of inertia feature. The proposed method effectively solves the inaccurate problem with single feature in the recognition of needle texture features, can be help for needlework recognition and virtual simulation.
Under the background of my country’s “9073” pension model, for the elderly who are recovering at home to more actively and effectively carry out hand function rehabilitation training; based on the self-efficacy theory, this paper discusses its application in the design of hand rehabilitation training instruments for the elderly. Apply, analyze and study the self-efficacy of elderly hand rehabilitation patients, and build a user model based on this, and finally produce corresponding solutions and complete product design and implementation, stimulate and enhance their self-driven potential and self-efficacy value, and provide the elderly with a sense of self-efficacy. The product design of human hand rehabilitation aids provides an innovative idea.
Melanoma is the most deadly form of cancer which is easily curable if detected at the earlier stage. The main objective of this paper is to classify the Melanoma and Non-melanoma using dermoscopy images from the Med Node Dataset. The images are enhanced by bottomhat filter, and then segmentation is done by two methods 1. Morphological Operations, 2. Otsu Thresholding. The features extracted from the segmented lesions are ABCD features, Statistical features and is given to the classifier. The classification is done by Machine Learning Algorithms (FFNN, SVM, KNN). The performance is analysed by the sensitivity, specificity, accuracy, Positive predictive value, negative predictive value and manually by Total Dermatoscopy Score (TDS) for 9 different classification cases. The best among the cases is 96.7% accuracy is for FFNN algorithm.
Art exhibitions are for promoting social aesthetic education. As the information carrier of exhibition culture, exhibition materials play a role in the dissemination of aesthetic education between the tangible and the intangible. Based on the long-life design philosophy, the textual research continued the exhibition’s lifecycle through innovative creative design after the exhibition. Reconstructing the design symbols of cultural derivatives guided the development of cultural derivative design experiments with PVC inkjet cloth as the object. The evolution from “waste product” to “product” and then to “commodity” was completed, which opened up an innovative path for exhibition culture to further enhance social aesthetic education, while also broadening the opportunities for researchers engaged in long-life design and green design.
As a kind of protective clothing, anti-stab clothing is also known as anti-knife clothing, which has the functions of anti-cutting, anti-stabbing, wear resistance and anti-theft. Ultra-high molecular weight polyethylene (UHMWPE) has good wear resistance, tear resistance, cutting resistance, impact resistance, light resistance and other excellent properties, can resist acid and alkali corrosion, continuous friction, UV resistance, in various harsh environments It can withstand the test and is one of the high-quality fibers commonly used in stab-resistant clothing. In this paper, ultra-high molecular weight polyethylene (UHMWPE) is mainly used to prepare high-strength knitted fabrics and woven fabrics. Plain, twill and satin fabrics are used in woven fabrics, and 1+1 rib and plain knitted fabrics are used in knitted fabrics.
Recent research has focused on learning 3D data through deep learning and improving geometric processing methods. Two aspects distinguish deep learning of point clouds from deep learning of images. A core aspect of the point cloud data is that it is disordered in comparison to the 2D image, so when designing the network, we need to consider how to deal with it. Reinforcement learning maximizes the expectation of cumulative rewards. The point cloud data was used for modeling and applied to the sole surface construction to achieve better results.
Today, movie piracy is greatly affecting the economic growth of the film industry. Hence, combatting piracy is critical in averting losses for the film producers. This paper aimed to develop an anti-piracy model composed of a real time pirated video degradation system and a piracy activity estimation system, which in turn are based on Thermogram analysis and an ARDUINO programmed IR LEDs array. In the pirate estimating system, the Cubic SVM model is trained to classify the thermal images acquired from the theatre environment into normal and abnormal classes. An accuracy of about 99.9% is achieved in real time while testing for piracy actions. The proposed piracy discouraging system is programmed to real time degrade the quality of pirated video and to invisibly watermark the pirated video with the theatre name, date, and time information. The distortion created by our prototype system is evaluated by recording the video displayed on screen using different mobile cameras and the corresponding pirated video quality is compared objectively and subjectively. Based on the subject’s quality rating, it was found that the system has created enough degradation in the visual quality of pirated video to discourage piracy.
With the deepening of digital technology, the role of smart home in improving people’s life quality and safety is increasingly prominent. Also, the elderly participate in social interaction through new technologies also plays a positive role in maintaining mental health. However, the attitudes of elderly toward to the new technologies especially actual use experience may different from what researchers expect. The authors carried out the users-assisted experience research via the self-developed digital twin remote collaboration system. We invited 12 seniors who aged from 57 to 73 that to have experiments and interviews. During the experiment, the elderly was assisted by our system, and the experience was compared with the intelligent mobile devices which they familiar with. The interview investigated the users’ feedback before, after and during the experiment, and according to the results to summarize the elderly’s concerns about the remote collaboration. The results turn out that digital twin can be more effective in helping seniors, and they have a positive attitude toward smart technology, and don’t want to been treated differently.
Diet management has become a common concern in daily life. Most of the current related designs provide accurate calorie estimates and personalized diet recommendations, which does not touch the core of management – how to make this behavior active and sustainable. This study introduces the concept of Positive Design, constructs a three-step design path which is applied in practice, aiming to give long-term happiness to diet management and promote users’ active adherence. The vital step is to invite target users and designers to join in collaborative work, identify and filter eight conflict dilemmas which are worthy of study. Positive design is a new theoretical perspective based on positive psychology. The final scheme produced in this paper aims to explore the application of this method in diet management design, and also provide a certain reference for subsequent research.