A comparison of methods for assessing the thermal insulation value of children's schoolwear in Kuwait

In this study, three methods were used to determine the thermal insulation values of different school clothing worn by 6 to 17 year old girls and boys in Kuwait classrooms for both summer and winter seasons. The different clothing ensembles' insulations were determined by 1: measurement using adult-sized versions of the clothing on thermal manikins, 2: estimations from adult clothing data obtained from the standards tables in ISO 9920 and ASHRAE 55, and 3: calculations using a regression equation from McCullough et al. (1985) that was adapted to accommodate children's sizes for ages 6-17 years. Values for the clothing area factor, f(cl), were also determined by measurement and by using a prediction equation from ISO 9920. Results in this study suggested that the clothing insulation values found from the measured and adapted data were similar to the adult's data in standards tables for the same summer and winter seasons. Further, the effect of the insulation values on the different scholars' age groups were investigated using the clothing temperature rating technique and compared to the scholars' comfort temperature found in recent field studies. Results showed that the temperature ratings of the clothing using the three methods described above are close and in agreement with the scholars' comfort temperature. Though estimated and measured f(cl) data differed, the impact on the temperature ratings was limited. An observed secular change in the children's heights and weights in the last few decades implies that, for adolescents, the children's body surface areas are similar to those of adults, making the use of adult clothing tables even more acceptable. In conclusion, this study gives some evidence to support the applicability of using adults' data in ASHRAE 55 and ISO 9920 standards to assess the thermal insulation values of different children's clothing ensembles, provided that careful selection of the garments, ensembles material and design takes place.     

Thermal effects of steel toe caps in footgear

This study investigated cold weather safety footwear and the possible thermal effects of steel toe caps in footwear. Two models of boots were used. Both models were manufactured in two variants – with and without steel toe cap. The boot insulation was measured with an artificial, heated foot (AHF). One model was used in experiment with subjects (n=6). Cold exposure consisted of sitting for 60 min at −10°C. There were no differences between insulation levels of boots with and without steel cap for one boot model, but the differences were statistically significant for the second model showing slightly higher insulation values for the boot without steel cap. No significant differences due to insulation dissimilarities could be found from the measurements on subjects. Statistically significant differences were found for both models regarding the rate of change of heat loss from AHF when its location was changed from warm to cold and back to warm. The rise and decrease of heat loss from AHF depended on the rate of temperature change of the boots. The results showed that a faster change in heat loss from AHF occurred for boots without steel toe caps. Data from subjects seemed to confirm this by a somewhat faster, though not significant, rise in toe skin temperatures after cold exposure in boots without steel toe caps. The effect may be attributed to the higher mass and heat contents of the boots with steel toe cap.

Relevance to industry

Many jobs need additional protection of the toes or shins. The steel toe cap and its alleged cooling effect have been a frequent subject of complaints. This study discusses reasons that could explain the complaints, and presents a standard method for evaluating thermal properties of footwear.     

Benefit of heat acclimation is limited by the evaporative potential when wearing chemical protective clothing.

Heat acclimation-induced sweating responses have the potential of reducing heat strain for chemical protective garment wearers. However, this potential benefit is strongly affected by the properties of the garment. If the clothing ensemble permits sufficient evaporative heat dissipation, then heat acclimation becomes helpful in reducing heat strain. On the other hand, if the garment creates an impenetrable barrier to moisture, no benefit can be gained from heat acclimation as the additional sweating cannot be evaporated. Ten subjects were studied exercising on a treadmill while wearing two different chemical protective ensembles. Skin heat flux, skin temperature, core temperature, metabolic heat production and heart rate were measured. It was found that the benefit of heat acclimation is strongly dependent on the ability of the body to dissipate an adequate amount of heat evaporatively. The evaporative potential (EP), a measure of thermal insulation modified by moisture permeability, of the clothing ensemble offers a quantitative index useful to determine, a priori, whether heat acclimation would be helpful when wearing protective clothing system. The data show that when EP is < 15%, heat acclimation affords no benefit. An evaporative potential graph is created to aid in this determination.     

The impact of activity level on sweat accumulation and thermal comfort using different underwear

Abstract

The purpose of this study was to investigate the significance of work level and sweat production for the total amount accumulated and the location of the sweat in a three-layer ensemble as a function of material and textile construction. Furthermore, it was also an aim to investigate how this influenced thermoregulatory responses and thermal comfort during work and during a rest period. Long-legged/long-sleeved underwear manufactured from two different 100% fibre-type materials, polypropylene and wool, was tested as part of a three-layer clothing system. The underwear manufactured from 100% polypropylene was tested in two different knit constructions, a 1 -by-1 rib knit and a fishnet structure, and the woollen underwear in a 1 -by-1 rib knit construction. The test was performed on eight male subjects (T^a= I0°C, RH = 85%, V^a <0-lm/s), and comprised a twice-repeated bout of 40-min cycle exercise followed by 20 min rest. Each subject conducted two tests with the work level approximating 30% [Vdot]o₂ max and 40% [Vdot]o₂ max, respectively. Skin temperatures, rectal temperature, weight loss and humidity near the skin were recorded during the test. Total changes in body and clothing weight were measured separately. Furthermore, subjective ratings on thermal comfort and on sensation of temperature and humidity were collected. The results demonstrated that high heat and sweat production during work periods, leading to increased sweat accumulation, will give higher thermal discomfort ratings for rest periods as well as for work periods compared to intermittent work with lower work intensities. Distribution of accumulated sweat in the clothing ensemble after heavy sweating is dependent on the fibre type in the underwear. Further, it can be concluded that underwear construction clearly has an influence on the evaporation rate in a three-layer ensemble during work at a high activity level.     

A novel ensemble of classifiers that use biological relevant gene sets for microarray classification

Since the introduction of DNA microarray technology, there has been an increasing interest on clinical application for cancer diagnosis. However, in order to effectively translate the advances in the field of microarray-based classification into the clinic area, there are still some problems related with both model performance and biological interpretability of the results. In this paper, a novel ensemble model is proposed able to integrate prior knowledge in the form of gene sets into the whole microarray classification process. Each gene set is used as an informed feature selection subset to train several base classifiers in order to estimate their accuracy. This information is later used for selecting those classifiers comprising the final ensemble model. The internal architecture of the proposed ensemble allows the replacement of both base classifiers and the heuristics employed to carry out classifier fusion, thereby achieving a high level of flexibility and making it possible to configure and adapt the model to different contexts. Experimental results using different datasets and several gene sets show that the proposal is able to outperform classical alternatives by using existing prior knowledge adapted from publicly available databases.     

Transfer of radiative heat through clothing ensembles

A mathematical model was designed to calculate the temperature and dry heat transfer in the various layers of a clothing ensemble, and the total heat loss of a human who is irradiated for a certain fraction of his or her area. The clothing ensemble that is irradiated by an external heat source is considered to be composed of underclothing, trapped air, and outer fabric. The model was experimentally tested with heat balance methods, using subjects, varying the activity, wind, and radiation characteristics of the outer garment of two-layer ensembles. In two experiments the subjects could only give off dry heat because they were wrapped in plastic foil. The model appeared to be correct within about l°C (rms error) and l0Wm^?2 (rms error). In a third experiment, sweat evaporation was also taken into account, showing that the resulting physiological heat load of 10 to 30% of the intercepted additional radiation is compensated by additional sweating. The resulting heat strain was rather mild. It is concluded that the mathematical model is a valid tool for the investigation of heat transfer through two-layer ensembles in radiant environments.     

Pumping effects on thermal insulation of clothing worn by human subjects

This study was undertaken in order to analyse the importance of the pumping effect on clothing's thermal insulation. To enhance differences in heat exchanges due to the pumping effect, two sets of condition were fixed, minimizing either the convective or the radiative heat transfers. The results showed that: (i) the clothing insulation determined on a manikin, even if he is moving, is larger than the resultant clothing insulation for living subjects; (ii) the insulation is not the same for radiant heat or cold as for convective heat or cold;(iii) the pumping effect can increase or decrease the resultant clothing insulation; (iv) the clothing insulation is smaller in warmer conditions thanin cooler ones; (v) it becomes necessary to make a definite distinction between several kinds of clothing insulation; intrinsic or basic insulation against radiation and convection; effective insulation against radiation and convection taking into account only the heat flowing through the clothing fabric; resultant insulation taking into account the magnitude of the pumping effect when clothing is worn by living subjects     

Multi-armed bandit heterogeneous ensemble learning for imbalanced data

One of the most widely used approaches to the class-imbalanced issue is ensemble learning. The base classifier is trained using an unbalanced training set in the conventional ensemble learning approach. We are unable to select the best suitable resampling method or base classifier for the training set, despite the fact that researchers have examined employing resampling strategies to balance the training set. A multi-armed bandit heterogeneous ensemble framework was developed as a solution to these issues. This framework employs the multi-armed bandit technique to pick the best base classifier and resampling techniques to build a heterogeneous ensemble model. To obtain training sets, we first employ the bagging technique. Then, we use the instances from the out-of-bag set as the validation set. In general, we consider the basic classifier combination with the highest validation set score to be the best model on the bagging subset and add it to the pool of model. The classification performance of the multi-armed bandit heterogeneous ensemble model is then assessed using 30 real-world imbalanced data sets that were gathered from UCI, KEEL, and HDDT. The experimental results demonstrate that, under the two assessment metrics of AUC and Kappa, the proposed heterogeneous ensemble model performs competitively with other nine state-of-the-art ensemble learning methods. At the same time, the findings of the experiment are confirmed by the statistical findings of the Friedman test and Holm's post-hoc test.     

Evaporative resistance and sustainable work under heat stress conditions for two cloth anticontamination ensembles

When a work scenario in protective clothing is a nominal two hours of work followed by a short break, the level of heat stress must be limited to conditions of thermal equilibrium. By comparing changes in maximum sustainable work rate in a fixed environment, differences due to different protective clothing ensembles can be determined. To illustrate this principle, two protective clothing ensembles were examined. The Basic Ensemble was a cotton blend coverall over gym shorts with hard hat, gloves and full face mask respirator. The Enhanced Ensemble added a light weight, surgical scrub suit under the coveralls, plus a hood worn under the hard hat. Five young, acclimated males were the test subjects. Environmental conditions were fixed at T_db=32°C and T_pwb=26°C. After a physiological steady state was established at a low rate of work, treadmill speed was increased by 0.04 m/s every 5 min. The trial continued until thermal equilibrium was clearly lost. A critical treadmill speed was noted at the point thermal equilibrium was lost for each ensemble and subject. The drop in treadmill speed from the basic to enhanced ensemble was 11%. Based on measured values of average skin temperature and metabolic rate at the critical work rate and estimated values of clothing insulation, the average evaporative resistances for the basic and enhanced ensembles were 0.018 and 0.026 kPa m²/W, respectively.

Relevance to industry

Protective clothing decisions are based on the need to reduce the risk of skin contact with chemical or physical hazards. Sometimes over-protection of the skin results in a hazard secondary to the skin, such as heat stress. With or without over-protection, protective clothing decisions may affect the level of heat stress and result in lower rates of sustainable work. This paper illustrates the affects of a relatively small change in protective clothing requirements on the ability to work in the heat.     

Accurate ensemble pruning with PL-bagging

Ensemble pruning deals with the selection of base learners prior to combination in order to improve prediction accuracy and efficiency. In the ensemble literature, it has been pointed out that in order for an ensemble classifier to achieve higher prediction accuracy, it is critical for the ensemble classifier to consist of accurate classifiers which at the same time diverse as much as possible. In this paper, a novel ensemble pruning method, called PL-bagging, is proposed. In order to attain the balance between diversity and accuracy of base learners, PL-bagging employs positive Lasso to assign weights to base learners in the combination step. Simulation studies and theoretical investigation showed that PL-bagging filters out redundant base learners while it assigns higher weights to more accurate base learners. Such improved weighting scheme of PL-bagging further results in higher classification accuracy and the improvement becomes even more significant as the ensemble size increases. The performance of PL-bagging was compared with state-of-the-art ensemble pruning methods for aggregation of bootstrapped base learners using 22 real and 4 synthetic datasets. The results indicate that PL-bagging significantly outperforms state-of-the-art ensemble pruning methods such as Boosting-based pruning and Trimmed bagging.     

基于密度峰值的聚类集成

聚类集成的目的是为了提高聚类结果的准确性、稳定性和鲁棒性.通过集成多个基聚类结果可以产生一个较优的结果.本文提出了一个基于密度峰值的聚类集成模型,主要完成三个方面的工作: 1）在研究已有的各聚类集成算法和模型后发现各基聚类结果可以用密度表示; 2）使用改进的最大信息系数（Rapid computation of the maximal information coefficient,RapidMic）表示各基聚类结果之间的相关性,使用这种相关性来衡量原始数据在经过基聚类器聚类后相互之间的密度关系; 3）改进密度峰值（Density peaks,DP）算法进行聚类集成.最后,使用一些标准数据集对所设计的模型进行评估.实验结果表明,相比经典的聚类集成模型,本文提出的模型聚类集成效果更佳.     

传感器温度场零干扰设计

传感器的检测元件和补偿元件在工作时存在温度干扰问题.温度干扰会降低传感器的灵敏度,影响输出信号的准确性.为解决这一问题,采用有限元方法对传感器温度场进行了分析,根据分析结果进行优化设计:改变基板结构,增加隔热槽,加强定向散热.然后,根据改进后方案重新建立有限元模型进行模拟,结果表明,元件间温度干扰大大减少,证明新方案是...     

基于信息熵更新权重的数据流集成分类算法

在动态的数据流中,由于其不稳定性以及存在概念漂移等问题,集成分类模型需要有及时适应新环境的能力.目前通常使用监督信息对基分类器的权重进行更新,以此来赋予符合当前环境的基分类器更高的权重,然而监督信息在真实数据流环境下无法立即获得.为了解决这个问题,文中提出了一种基于信息熵更新基分类器权重的数据流集成分类算法.首先使用随...     

基于遗传规划和集成学习的恶意软件检测

近年来恶意软件不断地发展变化,导致单一检测模型的准确率较低,使用集成学习组合多种模型可以提高检测效果,但集成模型中基学习器的准确性和多样性难以平衡。为此,提出一种基于遗传规划的集成模型生成方法,遗传规划可以将特征处理和构建集成模型两个阶段集成到单个程序树中,解决了传统恶意软件集成检测模型难以平衡个体准确率和多样性的问题。该方法以集成模型的恶意软件检出率作为种群进化依据,保证了基学习器的准确性;在构建集成模型时自动选择特征处理方法、分类算法和优化基学习器的超参数,通过输入属性扰动和算法参数扰动增加基学习器的多样性,根据优胜劣汰的思想进化生成具有高准确性和多样性的最优集成模型。在EMBER数据集上的结果表明,最优集成模型的检测准确率达到了98.88%;进一步的分析表明,该方法生成的模型具有较高的多样性和可解释性。     

Optimization of functionally graded metallic foam insulation under transient heat transfer conditions

The problem of minimizing the maximum temperature of a structure insulated by a functionally graded metal foam insulation under transient heat conduction is studied. First, the performance of insulation designed for steady-state conditions is compared with uniform solidity insulation. It is found that the optimum steady-state insulation performs poorly under transient conditions. Then, the maximum structural temperature of a two-layer insulation with constant solidity for each layer is minimized by varying the solidity profile for a given total thickness and mass. It is found that the cooler inner layer of the optimal design has high solidity, while the hotter outer layer has low solidity. This is in contrast to the steady-state optimum, where the solidity profile is the reverse.     

Feature-subspace aggregating: ensembles for stable and unstable learners

This paper introduces a new ensemble approach, Feature-Subspace Aggregating (Feating), which builds local models instead of global models. Feating is a generic ensemble approach that can enhance the predictive performance of both stable and unstable learners. In contrast, most existing ensemble approaches can improve the predictive performance of unstable learners only. Our analysis shows that the new approach reduces the execution time to generate a model in an ensemble through an increased level of localisation in Feating. Our empirical evaluation shows that Feating performs significantly better than Boosting, Random Subspace and Bagging in terms of predictive accuracy, when a stable learner SVM is used as the base learner. The speed up achieved by Feating makes feasible SVM ensembles that would otherwise be infeasible for large data sets. When SVM is the preferred base learner, we show that Feating SVM performs better than Boosting decision trees and Random Forests. We further demonstrate that Feating also substantially reduces the error of another stable learner, k-nearest neighbour, and an unstable learner, decision tree.     

Effects of wearing aircrew protective clothing on physiological and cognitive responses under various ambient conditions

Heat stress can be a significant problem for pilots wearing protective clothing during flights, because they provide extra insulation which prevents evaporative heat loss. Heat stress can influence human cognitive activity, which might be critical in the flying situation, requiring efficient and error-free performance. This study investigated the effect of wearing protective clothing under various ambient conditions on physiological and cognitive performance. On several occasions, eight subjects were exposed for 3 h to three different environmental conditions; 0 degrees C at 80% RH, 23 degrees C at 63% RH and 40 degrees C at 19% RH. The subjects were equipped with thermistors, dressed as they normally do for flights (including helmet, two layers of underwear and an uninsulated survival suit). During three separate exposures the subjects carried out two cognitive performance tests (Vigilance test and DG test). Performance was scored as correct, incorrect, missed reaction and reaction time. Skin temperature, deep body temperature, heart rate, oxygen consumption, temperature and humidity inside the clothing, sweat loss, subjective sensation of temperature and thermal comfort were measured. Rises in rectal temperature, skin temperature, heart rate and body water loss indicated a high level of heat stress in the 40 degrees C ambient temperature condition in comparison with 0 degrees C and 23 degrees C. Performance of the DG test was unaffected by ambient temperature. However, the number of incorrect reactions in the Vigilance test was significantly higher at 40 degrees C than at 23 degrees C (p = 0.006) or 0 degrees C (p = 0.03). The effect on Vigilance performance correlated with changes in deep-body temperature, and this is in accordance with earlier studies that have demonstrated that cognitive performance is virtually unaffected unless environmental conditions are sufficient to change deep body temperature.     

基于异构分类器集成的增量学习算法

将集成学习的思想引入到增量学习之中可以显著提升学习效果,近年关于集成式增量学习的研究大多采用加权投票的方式将多个同质分类器进行结合,并没有很好地解决增量学习中的稳定-可塑性难题。针对此提出了一种异构分类器集成增量学习算法。该算法在训练过程中,为使模型更具稳定性,用新数据训练多个基分类器加入到异构的集成模型之中,同时采用局部敏感哈希表保存数据梗概以备待测样本近邻的查找;为了适应不断变化的数据,还会用新获得的数据更新集成模型中基分类器的投票权重;对待测样本进行类别预测时,以局部敏感哈希表中与待测样本相似的数据作为桥梁,计算基分类器针对该待测样本的动态权重,结合多个基分类器的投票权重和动态权重判定待测样本所属类别。通过对比实验,证明了该增量算法有比较高的稳定性和泛化能力。     

基于SVM混合集成的信用风险评估模型

准确的信用风险评估可以降低金融机构的风险。为了进一步提高信用风险评估模型的预测准确率,将基于SVM的集成学习模型应用到信用风险评估问题中,提出了一种混合集成策略,称作RSA。RSA是随机子集模型和AdaBoost两种流行策略的合成,能提高组合成员分类器的多样性,从而提高集成学习模型的预测准确率。模型在两组公开信用数据集上进行了应用,实验结果表明基于RSA的SVM的集成学习模型可以作为信用风险评估的有效模型。     

A two-stage minimax concave penalty based method in pruned AdaBoost ensemble

AdaBoost is a highly effective ensemble learning method that combines several weak learners to produce a strong committee with higher accuracy. However, similar to other ensemble methods, AdaBoost uses a large number of base learners to produce the final outcome while addressing high-dimensional data. Thus, it poses a critical challenge in the form of high memory-space consumption. Feature selection methods can significantly reduce dimensionality in regression and have been established to be applicable in ensemble pruning. By pruning the ensemble, it is possible to generate a simpler ensemble with fewer base learners but a higher accuracy. In this article, we propose the minimax concave penalty (MCP) function to prune an AdaBoost ensemble to simplify the model and improve its accuracy simultaneously. The MCP penalty function is compared with LASSO and SCAD in terms of performance in pruning the ensemble. Experiments performed on real datasets demonstrate that MCP-pruning outperforms the other two methods. It can reduce the ensemble size effectively, and generate marginally more accurate predictions than the unpruned AdaBoost model.