Clothing Surface Research Articles

Automated detection and classification of concealed objects using infrared thermography and convolutional neural networks

This paper presents a study on the effectiveness of a convolutional neural network (CNN) in classifying infrared images for security scanning. Infrared thermography was explored as a non-invasive security scanner for stand-off and walk-through concealed object detection. Heat generated by human subjects radiates off the clothing surface, allowing detection by an infrared camera. However, infrared lacks in penetration capability compared to longer electromagnetic waves, leading to less obvious visuals on the clothing surface. ResNet-50 was used as the CNN model to automate the classification process of thermal images. The ImageNet database was used to pre-train the model, which was further fine-tuned using infrared images obtained from experiments. Four image pre-processing approaches were explored, i.e., raw infrared image, subject cropped region-of-interest (ROI) image, K-means, and Fuzzy-c clustered images. All these approaches were evaluated using the receiver operating characteristic curve on an internal holdout set, with an area-under-the-curve of 0.8923, 0.9256, 0.9485, and 0.9669 for the raw image, ROI cropped, K-means, and Fuzzy-c models, respectively. The CNN models trained using various image pre-processing approaches suggest that the prediction performance can be improved by the removal of non-decision relevant information and the visual highlighting of features.

Non-contact, portable, and stand-off infrared thermal imager for security scanning applications

In this article, we demonstrated the physical application of a portable infrared (IR) security scanning system for the non-contact and stand-off detection of target objects concealed underneath clothing. Such a system combines IR imaging and transfer learning with convolutional neural networks (CNNs) to enhance the detection of weak thermal signals and automate the classification of IR images. A mid-wavelength IR detector was used to record the real-time heat emitted from the clothing surface by human subjects. Concealed objects reduce the transmissivity of IR radiation from the body to the clothing surface, generally showing lower IR intensity compared to regions without objects. Due to limited resources for training data, the transfer learning approach was applied by fine-tuning a pre-trained CNN ResNet-50 model using the ImageNet database. Two image types were investigated here, i.e., raw thermal and Fuzzy-c clustered images. Receiver operating characteristic curves were built using a holdout set, showing an area-under-the-curve of 0.8934 and 0.9681 for the raw and Fuzzy-c clustered image models, respectively. The gradient-weighted class activation mapping visualization method was used to improve target identification, showing an accurate prediction of the object area. It was also found that complex clothing, such as those composed of materials of different transmissivity, could mislead the model in classification. The proposed IR-based detector has shown potential as a non-contact, stand-off security scanning system that can be deployed in diverse locations and ensure the safety of civilians.

Effects of wearing medical gowns at different temperatures on the physiological responses of female healthcare workers during the COVID-19 pandemic.

Using medical gowns with high protection against COVID-19 among healthcare workers (HCWs) may limit heat exchange, resulting in physiological challenges. This study aimed to compare the physiological and neurophysiological responses of female HCWs when using two typical medical gowns at different temperatures during the COVID-19 pandemic. Twenty healthy female HCWs participated in this study. Participants wore two types of medical gowns: Spunbond gown (SG) and laminate gown (LG). They walked on a treadmill in a controlled climate chamber for 30 minutes at three different temperatures (24, 28, and 32°C). Heart rate (HR), skin surface temperature (ST), clothing surface temperature (CT), ear temperature (ET), blood oxygen percentage (SaO2), galvanic skin response (GSR), and blood pressure were measured before and after walking on a treadmill. The study's results were analyzed using SPSS26. The study found that LG led to an average increase of 0.575°C in CT compared to SG at the same temperatures (P < 0.03). The average HR increased by 6.5 bpm in LG at 28°C compared to SG at a comfortable temperature (P = 0.01). The average ET in SG and GSR in LG at 32°C increased by 0.39°C and 0.25μS, respectively, compared to the comfortable temperature (P < 0.02). The study recommends maintaining a comfortable temperature range in hospitals to prevent physiological challenges among HCWs wearing medical gowns with high protection against COVID-19. This is important because using LG, compared to SG, at high temperatures can increase HR, ET, CT, and GSR.

Effects of the clothing colors on heat transfer and thermal sensation under indoor solar radiation in winter

The clothing color could always produce different human heat transfer and thermal sensation under solar radiation. And this issue has already been scrutinized by a few studies in outdoor environment. As the natural lighting is becoming common in buildings, e.g. the large curtain walls in high-rise buildings, the direct solar radiation could also affect the indoor occupants. Consequently, effects of the clothing color on the human body could not be ignored. Unfortunately, very limited studies have been reported in this field. In order to acquire the contribution of the clothing color to the heat transfer and thermal sensation of the indoor occupants, experimental study was conducted in this paper. Firstly, considering the non-uniformity of direct solar radiation on the indoor occupants, the equations that were used to calculate the solar heat gain of different body segments and the clothing surface temperature were revised, respectively. Thereafter, an experimental study was conducted in a climate chamber in winter. Participants wore cloth with different colors when exposed to different solar radiation intensities, during which the mean skin temperature, heat transfer, and subjective evaluations were acquired. Results showed that the dark clothing led to the reduced total heat loss by 4.52%, compared with that of the light clothing, at the solar radiation intensity of 200 W/m2. And the mean thermal sensation vote (TSV) under dark clothing was 0.65 higher than that under the light clothing. Meanwhile, at the solar radiation of 400 W/m2, the total heat loss under dark clothing was 14.17% lower than that under the light clothing, and the mean TSV under the dark clothing was found to be 0.25 higher that under light clothing condition. The results implied that wearing the dark clothing could benefit the improvement of the indoor human thermal comfort at low solar radiation in winter. These findings could provide a few useful references for studies on indoor thermal comfort under the solar radiation.

A battery-free wireless body area network towards state perception under all-weather conditions

The integration of energy harvesting and sensing is core to the enhancement of intelligence and sustainability of wireless body area networks (WBANs). Much of the harvested energy from human motion carries rich state information. How to decouple this state information while harvesting energy is the key to constructing next-generation WBANs. Herein, we present a battery-free WBAN based on an all-in-one power generating and sensing system (A-PGSS) towards state perception under all-weather conditions. The A-PGSS consists of a flexible triboelectric nanogenerator (F-TENG), a solar cell and a low-power circuit. The F-TENG serves both as an energy harvester and a sensor. The multiple A-PGSSs that make up WBAN distributed on the clothing surface can harvest energy from human motion and sunlight. The low-power circuit is divided into two routes, one to manage and store energy for powering its own system, and the other to decouple, process, and send the state information carried in the electrical signal. The real-time state information can be remotely transferred and displayed on smartphones and computers, exhibiting excellent potential in wilderness expeditions and elderly healthcare. This work not only provides diverse options for developing multi-functional sensor nodes but also advances the practical application of novel battery-free WBANs.

Data-driven adaptive GM(1,1) time series prediction model for thermal comfort.

In this paper, the future prediction of predicted mean vote (PMV) index of indoor environment is studied. PMV is the evaluation index used in this paper to represent the thermal comfort of human body. According to the literature, the main environmental factors affecting PMV index are temperature, humidity, black globe temperature, wind speed, average radiation temperature, and clothing surface temperature, and there is a complex nonlinear relationship between the six variables. Due to the coupling relationship between the six parameters, the PMV formula can be simplified under specific conditions, reducing the monitoring of variables that are difficult to observe. Then, the improved grey system prediction model GM(1,1) with optimized selection dimension is used to predict the future time of PMV. Due to the irregularity, uncertainty and fluctuation of PMV values in time series, based on the original GM(1,1) time series prediction, an adaptive GM(1,1) improved model is proposed, which can continuously change with time series and enhance its prediction accuracy. By contrast, the improved GM(1,1) model can be derived from the sliding window of the adaptive model through changes in the dataset and get better model grades. It lays a foundation for the future research on the predicted index of PMV, so as to set and control the air conditioning system in advance, to meet the intelligence of modern intelligent home and humanized function of sensing human comfort.

Predicted Mean Vote of Subway Car Environment Based on Machine Learning

The thermal comfort of passengers in the carriage cannot be ignored. Thus, this research aims to establish a prediction model for the thermal comfort of the internal environment of a subway car and find the optimal input combination in establishing the prediction model of the predicted mean vote (PMV) index. Data-driven modeling utilizes data from experiments and questionnaires conducted in Nanjing Metro. Support vector machine (SVM), decision tree (DT), random forest (RF), and logistic regression (LR) were used to build four models. This research aims to select the most appropriate input variables for the predictive model. All possible combinations of 11 input variables were used to determine the most accurate model, with variable selection for each model comprising 102 350 iterations. In the PMV prediction, the RF model was the best when using the correlation coefficients square (R2) as the evaluation indicator (R2: 0.7680, mean squared error (MSE): 0.2868). The variables include clothing temperature (CT), convective heat transfer coefficient between the surface of the human body and the environment (CHTC), black bulb temperature (BBT), and thermal resistance of clothes (TROC). The RF model with MSE as the evaluation index also had the highest accuracy (R2: 0.7676, MSE: 0.2836). The variables include clothing surface area coefficient (CSAC), CT, BBT, and air velocity (AV). The results show that the RF model can efficiently predict the PMV of the subway car environment.

Appearance and conductivity of weft-knitted unibody positioning flexible sensor

PurposeThe purpose of this research is to propose a flexible sensor with a weft-knitted float stitch structure and to explore knitting techniques that allow conductive yarns to be skin-tight and less exposed, reducing production processes and increasing productivity. Study its electrical conductivity in different yarn materials, knit processes and deformation ranges. The analysis is compared to provide some basis for the design of the electrodes.Design/methodology/approachThe method includes five operations: (1) Analysis of the morphological appearance, tensile variation, fiber material properties and electrical conductivity of high-elastic and filament silver-plated conductive yarns. (2) Based on the knitting process of the floating yarn structure, three-dimensional modeling of the flexible sensor was carried out to explore the influence of knitting process changes on appearance characteristics. (3) The fabric samples are knitted by different silver-plated conductive yarns with different structures. Processing of experimental samples to finished size by advance shrinkage. (4) Measure the resistance of the experimental sample after the machine has been lowered and after pre-shrinking. Use the stretching machine to simulate a wearing experiment and measure the change in resistance of the sample in the 0–15% stretching range. (5) Analyze the influence factors on the conductive performance of the flexible sensor to determine whether it is suitable for textile flexible sensors.FindingsFor the float knitted flexible sensors, the floating wire projection is influenced by the elasticity of the fabric and the length of the floating wire. Compared to the plain knitted flexible sensors, it has less resistance variation and better electrical properties, making it suitable for making electrodes for textile structures. In addition, the knitting method is integrated with the intelligent monitoring clothing, which saves the process for the integration of the flexible sensor, realizes positioning and fixed-point knitting.Practical implicationsThe sensor technology of the designed weft-knitted float structure is varied and can be freely combined and designed in a wide range. Within the good electrical conductivity, the flexible sensor can realize integrated knitting, positioning monitoring, integrating into the appearance of clothing. It can also focus on the wearing experience of wearable products so that the appearance of the monitoring clothing is close to the clothes we wear in our daily life.Originality/valueIn this paper, an integrated positioning knitting flexible sensor based on the weft knitting float structure is studied. The improved knitting process allows the sensing contact surface to be close to the skin and reduces the integration process. The relationship between the exposure of the silver-plated yarn on the clothing surface and the electrical conductivity is analyzed. Within a certain conductive performance, reduces the exposed area of the conductive yarn on the clothing surface and proposes a design reference for the flexible sensor appearance.

Numerical Prediction of the Heat Transfer in Air Gap of Different Garment Models

Abstract This study aims to investigate the characteristics of heat transfer and its mechanism for styling a design garment differently, and to improve thermal comfort caused by clothing styling design, a computational fluid dynamics (CFD) approach has been used to perform numerical investigations of fluid flow and heat transfer across a clothing air gap. Relationships between the heat transfer from the body to clothing (computed by heat transfer equations) and the air gap were examined by body heat loss of different styles of garments. Also, the clothing temperature distribution of different garments was obtained and compared. Computed results reveal that the air gap can play a central role in the heat transfer from the body to the surface of different style garments. When the air gap is small enough, namely about 5 mm in the chest and bust of the X-type of clothing, the conductive heat flux can transfer through the air gap and reach the cloth surface easily, which will bring about the increase of temperature on the clothing surface. The decreasing air gap distance from 50 mm (O-type) to 10 mm (X-type) increases the convective heat flux by up to 25% on the waist. However, the airspeed will increase to greater numbers while the air gap decreases to narrow channels, and it will bring about fierce forced convection heat flux. So the heat transfer must be considered in the process of garment design, and the air gap should be kept at a suitable level. These findings can be used to improve the clothing’s thermal comfort or optimize the cloth structure.

Industrial sewing as a creative resource in the clothing Surface Design project

The production of clothing has several operational steps, such as industrial sewing, which is used on textile surfaces as a materialization resource, that is, the union of two or more layers of fabrics by sewing points that makes the object tridimensional. In this context, the research seeks to explore the possibilities of industrial sewing to be considered as a creative resource to generate innovative surfaces in clothing, anchored on three pillars: in the design approaches of Surface Design, in the technical aspects of industrial sewing and in characteristics of materials textiles. For this, an exploratory investigation was carried out, with application of experiments using four straight industrial sewing techniques in three grammages of fabrics. The results were categorized through the effects obtained on the surfaces as graphic, structural and graphic structural function, demonstrating to be a creative resource that can be explored at the beginning of the design of clothing products.

Research on the calculation method of dressing thermal resistance based on infrared thermal imaging technology

With the popularity of intelligent technology, it has become an important trend to control the air conditioning terminal equipment intelligently to build the comfortable indoor environment. Therefore, it is necessary to automatically collect environmental and individual parameters (metabolic rate and clothing thermal resistance) and calculate PMV to predict human thermal sensation in real time. In this process,environmental parameters can be automatically measured and uploaded by the device. The metabolic rate is related to human level of activity . However,clothing thermal resistance is affected by many factors such as environment and level of activity.Taking the clothing thermal resistance as a fixed value according to thermal comfort standards will lead to deviations in thermal sensation prediction. In addition, many Chinese dresses cannot be found corresponding thermal resistance value in the thermal standard. In view of this,this paper studies two algorithms to obtain clothing surface temperature and calculate clothing thermal resistance by taking thermal image of the dressed human body with the infrared thermal imager,and compare them with the method of finding the clothing thermal resistance database in thermal comfort standard.And then,we calculate the PMV(predicted mean vote) using clothing thermal resistance obtained by three methods.The results of PMV and the questionnaire(ASV) are compared to analyze the feasibility of these methods. The results show that the mean deviation between the PMV calculated by one algorithm and the ASV is 0.33 scale when sitting in single-layered dress in summer,and that is 0.45 scale when sitting in multi-layered dress in winter. The results of PMV is significantly correlated with ASV. All of these prove that clothing thermal resistance can be calculated by this non-contact method, and it can be benefit to obtain indoor human thermal sensation and adjust and control thermal environment intelligently.

The heat supply object thermal regime under conditions of gas infrared emitter and air exchange system joint operation

The paper presents the results of experimental studies on the formation of thermal comfort conditions in large premises with the joint operation of gas infrared emitters and air exchange ventilation system. The values of temperatures and heat fluxes on the clothing surface under natural and mixed convection conditions were obtained. It has been established that the air exchange system operation in the premises reduces the temperature drop of the person clothes surface, respectively, a more favorable temperature condition is achieved in the working area.

Optimal Stitch Forming Line Identification for Attaching Patches on Non-Developable Clothing Surfaces

In clothing design and manufacturing, the need to attach a foreground (such as an emblem or pocket) on the background (i.e., clothing surface) arises. For that, stitch forming line needs to be identified on the surface of the background that should be seamed with that of the foreground. Often, the shape of the background is non-developable thus the problem is not straightforward. In this paper we developed an optimization method to overlay the foreground on the background such that the planar deformation and the deformation variance of the foreground is minimized. We applied the optimization technique to various cases of developable and non-developable background cases and verified the optimization works as expected.

Heat transfer in 3-D air gap between garment and body surface

For the sake of investigating the heat transfer performance and its mechanism in body-air-cloth microclimate system and studying the influence of inflow air property and environment conditions, numerical calculations are carried out using computational fluid dynamics method. It is found that the body-clothing microclimate is highly influenced by the heat transfer and air gap distance between body and garment. The inflow cool air brings the convective heat flux from body surface to clothing inner surface which will result in the high temperature regions on the clothing. Moreover, the increase of air speed will accelerate this heat transfer evidently. Relatively, the decreasing of outside temperature takes into a big increasing of heat flux loss on the body and brings about high temperature gradient on the clothing surface. The findings of this study provide fundamental knowledge to improve microclimate between the body and clothing.

Experimental determination of the worker’s clothing surface temperature during the ceramic gas heater operation

Providing regulated comfortable thermal conditions for workers and engineers working in large-sized industrial premises is a rather energy-consuming process in many cases. It is necessary to heat not only large volumes of air very often, but also the enclosing structures. One of the most promising options for reducing energy costs is the use of gas infrared heaters as heat sources. However, such radiant heaters are still little used, because no relationship has been established between the characteristics of the heat supply object – the operating one and the parameters of the radiator. The purpose of the study is to establish, based on the results of the experimental studies, the functional relationships of the surface temperature of the worker’s clothing and the parameters of a typical gas infrared heater. The experiments have been carried out to register the temperature fields of the material surface of the working model, as well as in the immediate vicinity of the model. A substantially inhomogeneous distribution of the temperatures of the surface of the fabric of the model’s clothing has been established depending on the orientation of this surface relative to the direction of the radiation flux. Based on the results of the experiments, the conclusions have been drawn about the regularities of heat transfer of a heat supply object – working with the external environment under the operating conditions of gas infrared heater (GIH). Recommendations for the formation of thermal conditions for those working with radiant heating were formulated.

A non-linear view transformations model for cross-view gait recognition

Gait has emerged as an important biometric feature which is capable of identifying individuals at distance without requiring any interaction with the system. Various factors such as clothing, shoes, and walking surface can affect the performance of gait recognition. However, cross-view gait recognition is particularly challenging as the appearance of individual’s walk drastically changes with the change in the viewpoint. In this paper, we present a novel view-invariant gait representation for cross-view gait recognition using the spatiotemporal motion characteristics of human walk. The proposed technique trains a deep fully connected neural network to transform the gait descriptors from multiple viewpoints to a single canonical view. It learns a single model for all the videos captured from different viewpoints and finds a shared high-level virtual path to project them on a single canonical view. The proposed deep neural network is learned only once using the spatiotemporal gait representation and applied to testing gait sequences to construct their view-invariant gait descriptors which are used for cross-view gait recognition. The experimental evaluation is carried out on two large benchmark cross-view gait datasets, CASIA-B and OU-ISIR large population, and the results are compared with current state-of-the-art methods. The results show that the proposed algorithm outperforms the state-of-the-art methods in cross-view gait recognition.

Thermal Imaging and Physiological Analysis of Cold-Climate Caribou-Skin Clothing

Protective clothing is essential for human existence in the Arctic, and caribou-skin clothing has played a pivotal role for millennia. Although people with northern experience often extol caribou-skin clothing, few scientific studies have investigated its properties. We used infrared thermal imaging in a pilot study to compare authentic caribou-skin clothing sewn by traditional Inuit seamstresses with two other types of cold-weather clothing: a standard-issue, Canadian army, winter uniform and an ensemble of modern retail clothing designed for extreme cold (a down anorak and snowmobile pants). To make the comparison, two subjects sequentially wore the three types of clothing—caribou skin, army uniform, and modern retail—in a still air, uniform thermal environment (where radiant temperatures of all environmental surfaces were equal to air temperature) at −21°C to −23°C (−6°F to −10°F). Thermal imaging quantifies the temperature of the outer surface of clothing, thereby providing key, functionally relevant information on the interface where clothing and environment meet. Under otherwise similar conditions, a low clothing surface temperature indicates superior clothing performance and a reduced rate of heat loss from the body to the environment. Caribou-skin clothing was similar to modern extreme-cold retail clothing: the whole-body composite surface temperature of our subjects wearing caribou-skin clothing was −22.1°C to −22.7°C, compared with −21.6°C in both subjects wearing the modern retail clothing. The army winter uniform (−18.9°C to −20.0°C) was inferior. These quantitative results were mirrored by the subjects’ subjective impressions. A particular advantage of thermal imaging is that it pinpoints locations in clothing where heat leaks occur. Although the two types of modern clothing exhibited heat leaks at zippered structures (even though fully closed), the caribou-skin clothing evaded such heat leaks by lacking such structures, because it is donned over the head. The integral hood characteristic of a caribou-skin parka was also superior in comparison to the detachable hood of the army uniform.

Development of a Data-Driven Predictive Model of Clothing Thermal Insulation Estimation by Using Advanced Computational Approaches

Clothing condition was selected as a key human-subject-relevant parameter which is dynamically changed depending on the user’s preferences and also on climate conditions. While the environmental components are relatively easier to measure using sensor devices, clothing value (clo) is almost impossible to visually estimate because it varies across building occupants even though they share constant thermal conditions in the same room. Therefore, in this study we developed a data-driven model to estimate the clothing insulation value as a function of skin and clothing surface temperatures. We adopted a series of environmental chamber tests with 20 participants. A portion of the collected data was used as a training dataset to establish a data-driven model based on the use of advanced computational algorithms. To consider a practical application, in this study we minimized the number of sensing points for data collection while adopting a wearable device for the user’s convenience. The study results revealed that the developed predictive model generated an accuracy of 88.04%, and the accuracy became higher in the prediction of a high clo value than in that of a low value. In addition, the accuracy was affected by the user’s body mass index. Therefore, this research confirms that it is possible to develop a data-driven predictive model of a user’s clo value based on the use of his/her physiological and ambient environmental information, and an additional study with a larger dataset via using chamber experiments with additional test participants is required for better performance in terms of prediction accuracy.

Thermal Comfort-Based Personalized Models with Non-Intrusive Sensing Technique in Office Buildings

Heating, ventilation and air-conditioning (HVAC) systems play a key role in shaping the built environment. However, centralized HVAC systems cannot guarantee the provision of a comfortable thermal environment for everyone. Therefore, a personalized HVAC system that aims to adapt thermal preferences has drawn much more attention. Meanwhile, occupant-related factors like skin temperature have not had standardized measurement methods. Therefore, this paper proposes to use infrared thermography to develop individual thermal models to predict thermal sensations using three different feature sets with the random forest (RF) and support vector machine (SVM). The results have shown the correlation coefficients between clothing surface temperature and thermal sensation are 11% and 3% higher than those between skin temperature and thermal sensation of two subjects, respectively. With cross-validation, SVM with a linear kernel and penalty number of 1, as well as RF with 50 trees and the maximum tree depth of 3 were selected as the model configurations. As a result, the model trained with the feature set, consisting of indoor air temperature, relative humidity, skin temperature and clothing surface temperature, and with linear kernel SVM has achieved 100% recall score on test data of female subjects and 95% recall score on that of male subjects.

Investigation of industrial contamination of protective clothing at oil industry sector

The article presents the research results of the interaction of the protective clothes surface with polluting components of production facilities of the oil and oil refining industry. The development direction of an oil-resistant clothing segment is proved. The aggressive components of the production environment of the oil sector are substantiated with respect to the protective functions of special clothes. Oil and petroleum products lead to a change in the properties of textile materials. This depends on the concentration of aggressive components in the structure of textile materials. The research results of the interaction of petroleum products with a textile composition of a woven structure with protective properties are presented. Based on the study of 50 suits that have passed the operational cycle of one season, restrictions are established on the areas of the clothing surface of uneven protection. Clothing zones risk-affected loss of protective effect is established. The results of experimental studies of the concentration of petroleum products in textile materials after chemical purification based on the method of gas capillary chromatography are presented. It was found that the main component with a high concentration of pollutants is hydrocarbons from C14H30 Tetradecane to C36H74 Hexatriacontane. The average values of the concentration of hydrocarbons on the purified samples for the main parts of the clothing surface were established. Using the methods of acoustic emission, the experimental level of contact activity of the permeability of the liquid phase of crude oil in the structure of woven textiles at the boundary of media is established. The effect of the saturation of protective clothing by the petroleum fractions on its strength has been experimentally evaluated. The chemical compositions of the active phases were identified on the basis of experimental data. This is the contact materials of industrial pollution at oil refining facilities. Recommendations have been developed to improve the system of individual protection of man during interaction with a polluting environment taking into account chemically aggressive components.