Xianyi Zeng
Ensait, GEMTEX Laboratory, Faculty Member
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Focusing on the mechanism of "human-sport-clothing" system, this paper studies people-oriented sports comfort, and analyzes the influence of different tights combinations (i.e. tights and tights with different fabrics) and the... more
Focusing on the mechanism of "human-sport-clothing" system, this paper studies people-oriented sports comfort, and analyzes the influence of different tights combinations (i.e. tights and tights with different fabrics) and the effect of exercise status on the human body parts and overall comfort. In addition, because there are many impact indicators of comfort and the relationship is complicated, it is difficult for general models to deal with this relationship, which leads to the low accuracy of comfort prediction model. To solve this problem, this paper proposes an efficient intelligent prediction model, namely a new hybrid model based on PSO and CS algorithm. The results show that different fabric combinations have significant effects on local and overall comfort under different sports conditions. PSO-CS hybrid model is superior to PSO and CS model in predicting local and global comfort.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Currently, garment fit evaluation is one of the biggest bottlenecks for fashion design and manufacturing. In this paper, we proposed a garment fit prediction model using data learning technology, such as Back Propagation Artificial Neural... more
Currently, garment fit evaluation is one of the biggest bottlenecks for fashion design and manufacturing. In this paper, we proposed a garment fit prediction model using data learning technology, such as Back Propagation Artificial Neural Networks (BP-ANNs), Random Forest, Bayesian Classifier. The inputs of the proposed model are digital clothing pressures measured by virtual try-on; while the output of the model is one of the three fit conditions- tight, fit or loose. In order to acquire reliable learning data, virtual and real try-on experiments were carried out to collect input and output learning data respectively. After learning from the collected input and output experimental data, the proposed model can predict garment fit rapidly and automatically by inputting digital clothing pressures measured by virtual try-on. Test results showed that the prediction accuracies of data-learning-based garment fit evaluation methods are much better than that of traditional methods.
Research Interests:
In this study, we have explored and discussed the data mining-based solutions to apparel size assignment using approach principle, K-means clustering, and support vector machine, respectively. A case of mass customization for men's... more
In this study, we have explored and discussed the data mining-based solutions to apparel size assignment using approach principle, K-means clustering, and support vector machine, respectively. A case of mass customization for men's pants in China with 200 adult males were employed to validate and evaluate the solutions. After anthropometric data acquisition and preprocessing, three key body dimensions were identified based on hierarchical clustering, as well as their ranges and fit models. Sequentially, we calculated all the possible values of the distance between the target population and the fit models by the enumeration algorithm. Afterward, we assigned the garment sizes for the target population using the abovementioned data mining approaches. Lastly, the solution based on support machine was considered as the optimal solution for pants mass customization after being comprehensively assessed by the aggregate loss of fit, the number of poor fit, accommodation rate of ideal fi...
Research Interests:
Abstract Garment pattern-making is one of the most important parts in fashion design and production. However, the traditional pattern-making is an experience based work and very time-consuming. In this paper, we proposed a parametric... more
Abstract Garment pattern-making is one of the most important parts in fashion design and production. However, the traditional pattern-making is an experience based work and very time-consuming. In this paper, we proposed a parametric design method of garment pattern based on body dimensions. Based on this method, we constructed a jeans' pattern recommendation system. The input items of the proposed system are three geometric constraint parameters (jean silhouette type, length and waist height) and three-dimensional constraint parameters (human body stature, waist girth and hip girth); the output of the proposed system are jeans' patterns. Also, four adjustable parameters (jeans' length, waist height, knee and leg opening) are designed to adjust patterns generated by the proposed system. If the jeans' pattern is not satisfying after virtual or real try-on, the adjustable input parameters of the proposed system can be applied for adjustment until the patterns are acceptable. Our proposed system can combine traditional pattern-making methods to generate jeans’ patterns automatically and rapidly, hence improving pattern-making efficiency significantly.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
FDM technology used for printing functionalized layers on textiles brought new challenges such as the understanding and the improvement of the adhesion performance of the thermoplastic filaments on ...
Research Interests:
This research presented a novel method using 3D simulation methods to design customized garments for physically disabled people with scoliosis (PDPS). The proposed method is based on the virtual human model created from 3D scanning,... more
This research presented a novel method using 3D simulation methods to design customized garments for physically disabled people with scoliosis (PDPS). The proposed method is based on the virtual human model created from 3D scanning, permitting to simulate the consumer’s morphological shape with atypical physical deformations. Next, customized 2D and 3D virtual garment prototyping tools will be used to create products through interactions. The proposed 3D garment design method is based on the concept of knowledge-based design, using the design knowledge and process already applied to normal body shapes successfully. The characters of the PDPS and the relationship between human body and garment are considered in the prototyping process. As a visualized collaborative design process, the communication between designer and consumer is ensured, permitting to adapt the finished product to disabled people afflicted with severe scoliosis.
Research Interests:
PurposeThe knowledge of structural parameters of nonwovens media is poorly understood. The pores size distribution (PSD) function is one of those parameters. The difficulty is not only the understanding of the distribution of pores but... more
PurposeThe knowledge of structural parameters of nonwovens media is poorly understood. The pores size distribution (PSD) function is one of those parameters. The difficulty is not only the understanding of the distribution of pores but also the identification of pores geometry distribution (PGD) and their behaviour concerning the dynamic fluid transportation. The purpose of this paper is to present an efficient and reliable method based on image analysis which on one hand, performs the estimation of the PSD function and takes into account the geometric aspect of pores, and on the other hand, analyses liquid wicking in very thin filter media.Design/methodology/approachThe proposed methods, in this paper, are applied on thin filter media made of polyester. The samples have not sudden any treatment. The authors set up an optical test bed in order to observe the dynamic properties of the samples. Dynamic raw data about the liquid wicking are extracted directly from video sequences using...
Research Interests:
Research Interests:
The green peach aphid, Myzus persicae (Sulzer) (Hemiptera: Aphididae), is an agricultural pest that seriously infests many crops worldwide. This study used electrical penetration graphs (EPGs) and life table parameters to estimate the... more
The green peach aphid, Myzus persicae (Sulzer) (Hemiptera: Aphididae), is an agricultural pest that seriously infests many crops worldwide. This study used electrical penetration graphs (EPGs) and life table parameters to estimate the sublethal effects of cyantraniliprole and imidacloprid on the feeding behavior and hormesis of M. persicae The sublethal concentrations (LC30) of cyantraniliprole and imidacloprid against adult M. persicae were 4.933 and 0.541 mg L(-1), respectively. The feeding data obtained from EPG analysis indicated that the count probes and number of short probes (<3 min) were significantly increased when aphids were exposed to LC30 of imidacloprid-treated plants. In addition, the phloem-feeding behavior of M persicae was significantly impaired on fed tobacco plants treated with cyantraniliprole and imidacloprid at LC30 Analysis of life table parameters indicated that the growth and reproduction of F1 generation aphids were significantly affected when initial a...
Research Interests:
Data is the collection of facts and details which leads to create useful information for any organization after performing analysis [1]. The large volume of data generated via internet applications and thus the requirement of retrieving... more
Data is the collection of facts and details which leads to create useful information for any organization after performing analysis [1]. The large volume of data generated via internet applications and thus the requirement of retrieving most relevant information from data has become a priority. Recommendation system (RS) provides a path to deal with the large volume of data and to come out with potential insights for the business and end users.This paper explores to propose RS for customized garment using the hybrid filtering technique. Major activities like data collection, data modeling,data pre-processing, and data analysis over past transactions of customers purchase are explored. Collaboratively this paper explores the approach of building a system with implicit feedback.
Research Interests:
Research Interests:
Research Interests:
Robots will face a huge deployment in a very near future for people's everyday lives. Main objective is to reduce or eliminate safety and health risks inherent to physically demanding duty or risky work. The present paper focuses on... more
Robots will face a huge deployment in a very near future for people's everyday lives. Main objective is to reduce or eliminate safety and health risks inherent to physically demanding duty or risky work. The present paper focuses on unsafe and hazardous tasks performed by firefighters and aims at proposing organizational and technical tools to balance risk with the involvement of cooperative robots. A study has been conducted within the framework of the regional project SUCRé, dealing with Human-Robots Cooperation in hostile/severe environment. After a short presentation of the project, a Human-Centered Design approach is proposed, based on the implementation of rules defined by the Human-Machine Cooperation principles. Two human aspects have been addressed to design and control cooperation among several firefighters and robots: the cognitive and physiological aspects. A use case presents the implementation of such aspects to manage global and local cooperation.
Research Interests:
Abstract This paper aims to propose an interpretable knowledge-based decision support system (IKBDSS) that will assist physicians to predict the risk level of a disease. Our system enables to integrate both historical cases extracted from... more
Abstract This paper aims to propose an interpretable knowledge-based decision support system (IKBDSS) that will assist physicians to predict the risk level of a disease. Our system enables to integrate both historical cases extracted from database and opinions provided by different experts in order to set up a medical knowledge base and provide relevant advises by inferring from the knowledge base. To present various experts’ opinions, the Multi-granularity Linguistic Term Sets (MLTS) model is used to address the ambiguity and intangibility of knowledge. Our work mainly focuses on knowledge acquisition, similarity degree calculation and consistency checking process. It is worth mentioning that a criterion weights calculation method is introduced to objectively obtain the weights based on knowledge from experts, rather than subjectively predefined. The developed system leads to a better performance in specificity, sensitivity and F 1 score compared to other methods in the literature. To conclude, our work contributes to: (1) The development of a medical decision support system to combine clinical records and domain knowledge to predict diagnosis. (2) The decision-making process ensures interpretability, which increases the reliability of our system in terms of being a decision supporter. (3) The criterion weights are calculated based on the professional knowledge presented in MLTS form, and this process improves the capacity of providing diagnostic recommendations.
Research Interests:
The modern textile/clothing industry is facing a great number of challenges related to sustainability. These challenges include environmental disasters and hazards to human health caused by toxic materials, resource exhaustion (water,... more
The modern textile/clothing industry is facing a great number of challenges related to sustainability. These challenges include environmental disasters and hazards to human health caused by toxic materials, resource exhaustion (water, energy, raw materials), and social impacts caused by delocalization, counterfeiting and other elements. In order to develop the industry in a sustainable and optimal way when producing new textile products, industrial companies need to optimize their production organization by minimizing risks not only at levels of materials and processes but also in the whole international textile supply chain. In this paper, a method is proposed for developing a sustainable textile supply chain by selecting the most relevant materials and suppliers. The criteria of sustainable development include environment protection, recycling capacity, energy saving, human health and safety, and social impacts. Some evaluation criteria have been normalized by recognized internati...
Research Interests:
Fetal movement is an important indicator showing fetal health. Classically, ultrasound and pregnant women's subjective perception are the most popular methods for detecting fetal movements. However, ultrasound is available in... more
Fetal movement is an important indicator showing fetal health. Classically, ultrasound and pregnant women's subjective perception are the most popular methods for detecting fetal movements. However, ultrasound is available in hospitals only, causing inconvenience to pregnant women. The pregnant women's subjective perception is strongly related to her personal experience and level of attention, which is uncertain and not accurate enough. In this paper, we propose a wearable technology-based system in order to detect fetal movements conveniently and accurately. The system includes an intelligent garment integrating a number of multi-scale sensors connected each other, a standardized cloud computing platform on which medical diagnosis is realized using a medical expert system. For this purpose, we realize two electronic devices, ready to be integrated into a garment and permitting to collect typical signals on fetal movements. Based on the measured signals, we propose a method combining wavelet analysis and band-pass filter in order to extract relevant features on fetal movements.
Research Interests:
ABSTRACT This paper, which deals with the forecasting of nonwovens end-uses, is divided in two parts. The first part presents optimized methods for measuring the structures of nonwovens. The raw data are extracted directly from 3D images... more
ABSTRACT This paper, which deals with the forecasting of nonwovens end-uses, is divided in two parts. The first part presents optimized methods for measuring the structures of nonwovens. The raw data are extracted directly from 3D images of the accurate ...
Research Interests:
Research Interests:
This paper shows how a control strategy consisting of a 3 layer artificial neural network is realized for driving the external caracteristics of a system or an environment to the desired values withcut modelizing mathematically the... more
This paper shows how a control strategy consisting of a 3 layer artificial neural network is realized for driving the external caracteristics of a system or an environment to the desired values withcut modelizing mathematically the system. During the control, the performance evaluation is
Research Interests:
In this paper, we present a general approach for helping designers to develop new human centered industrial products using intelligent techniques. First, we characterize and evaluate consumer perception on industrial products, which is... more
In this paper, we present a general approach for helping designers to develop new human centered industrial products using intelligent techniques. First, we characterize and evaluate consumer perception on industrial products, which is composed of two levels: basic perception independent of the socio-cultural context of these products, and complex socio-cultural concepts integrated into these products. The related human evaluation data
Research Interests:
Research Interests: Engineering and Denim
Selection of supplier is the integral and most challenging part of supply chain management in fashion industry as its performance is largely dependent on effective supplier selection process. Multitude of information from the customers’... more
Selection of supplier is the integral and most challenging part of supply chain management in fashion industry as its performance is largely dependent on effective supplier selection process. Multitude of information from the customers’ and market’s perspective has to be considered before making the decisions in regard to supplier selection. Data mining methods have found many applications in fashion supply chain management. However, decision making related to supplier selection lacks the application of data mining methods. It warrants an automated decision support system wherein machine learning models can be trained on historical customer order data to predict best suppliers or recommend new ones depending on the degree of matching between suppliers’ capabilities and the product order features. In this paper, our work revolves around the research question of how we can predict suppliers based on historical customer order data by using data mining methods. Our aim was to predict supplier by applying classification models on the historical customer order data. We applied four machine learning classification models and the research findings suggest that these models can be employed for the decision making concerning supplier prediction. This study can contribute to the development of automated decision support system which is reliable and efficient for the supplier prediction.
Research Interests:
Research Interests:
How to interpret the relationship between the low-level features, such as some statistical characteristics of color and texture, and the high-level aesthetic properties, such as warm or cold, soft or hard, has been a hot research topic of... more
How to interpret the relationship between the low-level features, such as some statistical characteristics of color and texture, and the high-level aesthetic properties, such as warm or cold, soft or hard, has been a hot research topic of neuroaesthetics. Contrary to the black-box method widely used in the fields of machine learning and pattern recognition, we build a white-box model with the hierarchical feed-forward structure inspired by neurobiological mechanisms underlying the aesthetic perception of visual art. In the experiment, the aesthetic judgments for 8 pairs of aesthetic antonyms are carried out for a set of 151 visual textures. For each visual texture, 106 low-level features are extracted. Then, ten more useful and effective features are selected through neighborhood component analysis to reduce information redundancy and control the complexity of the model. Finally, model building of the beauty appreciation of visual textures using multiple linear or nonlinear regressi...
Research Interests:
Optimal ergonomic design for consumer goods (such as garments and furniture) cannot be perfectly realised because of imprecise interactions between products and human models. In this paper, we propose a new body classification method that... more
Optimal ergonomic design for consumer goods (such as garments and furniture) cannot be perfectly realised because of imprecise interactions between products and human models. In this paper, we propose a new body classification method that integrates human skeleton features, expert experience, manual measurement methods, and statistical analysis (principal component analysis and K-means clustering). Taking the upper body of young males as an example, the proposed method enables the classification of upper bodies into a number of levels at three key body segments (the arm root [seven levels], the shoulder [five levels], and the torso [below the shoulder, eight levels]). From several experiments, we found that the proposed method can lead to more accurate results than the classical classification methods based on three-dimensional (3D) human model and can provide semantic knowledge of human body shapes. This includes interpretations of the classification results at these three body segments and key feature point positions, as determined by skeleton features and expert experience. Quantitative analysis also demonstrates that the reconstruction errors satisfy the requirements of garment design and production.Practitioner Summary: The acquisition and classification of anthropometric data constitute the basis of ergonomic design. This paper presents a new method for body classification that leads to more accurate results than classical classification methods (which are based on human body models). We also provide semantic knowledge about the shape of human body. The proposed method can also be extended to 3D body modelling and to the design of other consumer products, such as furniture, seats, and cars.
Research Interests:
The research in this paper aims to set up a new consumer profile definition method based on fuzzy technology and fuzzy AHP. The result of the study could be applied to garment recommendation systems for a special consumer. Consumer... more
The research in this paper aims to set up a new consumer profile definition method based on fuzzy technology and fuzzy AHP. The result of the study could be applied to garment recommendation systems for a special consumer. Consumer profiles are chosen as research objects. The fuzzy technology and fuzzy AHP are applied in this research, which aims to provide a new method of using fuzzy technology and fuzzy AHP to define consumer profiles. We define tall–short and fat–thin by fuzzy technology and set up the weights of consumer profile by fuzzy AHP methods. The fuzzy technology and fuzzy AHP are applied for building consumer profiles that can be used for a consumer-oriented intelligent garment recommendation system.
Research Interests:
This paper proposes a new wearable system for firefighter protection. This system is composed of a lightweight garment integrating a number of sensors measuring the wearer's physiological state and a microcontroller permitting to... more
This paper proposes a new wearable system for firefighter protection. This system is composed of a lightweight garment integrating a number of sensors measuring the wearer's physiological state and a microcontroller permitting to gather all measured data and make data-based prediction on the wearer's health state, stress and fatigue, etc. The proposed wearable system can continuously monitor key health features using the selected sensors accurately placed at the key positions of the garment. For ensuring wearer's comfort and close contact between sensors and the human body in order to optimize signal quality, the garment that we designed is made of a selected knitted textile structure and fit the specific body morphology. Also, a number of conductive threads have been used to connect the sensors and the microcontroller inside the garment. After the stages of data preprocessing and data fusion, by learning from the measures of the sensors integrated into the garment, a local decision support system has been created for linking fatigue or stress states to the measured physiological signals. In this way, this high level of information can be transmitted to the command center, permitting to make relevant global decisions for offering a better protection of firefighters.
Research Interests:
Research Interests:
Garment opening is strongly related to the daily life quality of physically disabled people with scoliosis (PDPSs). This research proposes a kinesiological evaluation method to investigate the influence of garment opening positions in... more
Garment opening is strongly related to the daily life quality of physically disabled people with scoliosis (PDPSs). This research proposes a kinesiological evaluation method to investigate the influence of garment opening positions in dressing activities of PDPSs. For this purpose, dressing activities are firstly deconstructed into several motions. The performance of different garment opening positions is represented by the performance of the wearer carrying out different motions in dressing activities. The proposed evaluation method is based on the Completion Level (CL), which includes both physical and psychological indicators: Motion Standard Time (MST), Motion Difficulty Degree (MDD) and Motion Independence Degree (MID). MST is a physical indicator regarding the standard time to complete a motion in the dressing activities. It reflects the physical autonomy of the wearer in the dressing activity. MDD and MID are psychological indicators, which are developed to evaluate the psych...
Research Interests:
This research puts forward a novel knowledge-supported design process for obtaining personalized ready-to-wear garment products aimed at consumers with atypical morphology by using a virtual a three-dimensional-to-two-dimensional... more
This research puts forward a novel knowledge-supported design process for obtaining personalized ready-to-wear garment products aimed at consumers with atypical morphology by using a virtual a three-dimensional-to-two-dimensional (3D-to-2D) design method. The proposed design process starts with designing a personalized garment block, which is then extended into the desired ready-to-wear garment style. The garment block is obtained by using a virtual 3D-to-2D design method. The extension and sizing of the garment block pattern into desired ready-to-wear garment patterns is performed in a 2D environment using classic methods. The proposed design solution begins with a personalized garment block, thus avoiding the complicated operations of simulating a 3D garment directly in the virtual environment. The proposed design process can be fully digitalized, which ensures the involvement of the consumer throughout the design. By repeatedly running the sequence of Design – Display – Evaluatio...
Research Interests:
Abstract: Fabric-hand evaluation is one of the key features and measures in textile material selection for fashion design. Fabric-hand evaluation requires considering multiple criteria with in a group of evaluators. The evaluation process... more
Abstract: Fabric-hand evaluation is one of the key features and measures in textile material selection for fashion design. Fabric-hand evaluation requires considering multiple criteria with in a group of evaluators. The evaluation process often involves fuzziness in the ...
Research Interests:
Research Interests:
With the booming development of the Internet and AI (Artificial Intelligence), smart clothing has emerged to meet consumers’ personalized needs in healthcare, work, entertainment, etc., and has rapidly become a hotspot in the clothing... more
With the booming development of the Internet and AI (Artificial Intelligence), smart clothing has emerged to meet consumers’ personalized needs in healthcare, work, entertainment, etc., and has rapidly become a hotspot in the clothing industry and research field. However, as smart clothing gets popular, sustainability issues are becoming increasingly prominent during its development and circulation. To explore the status quo of the sustainable development of smart clothing, from the perspective of the industry chain, this paper discusses its challenges during raw material supply, design, manufacturing, storage, logistics and recycling. Based on these challenges and the characteristics of smart clothing and the future trend of the apparel industry, some countermeasures are put forward from three aspects: design, raw material and supply chain management. This review aims to arouse the reflection of practitioners and provide feasible suggestions for the healthy and lasting development ...