This thesis presents a series of studies into the responses of people to outdoor thermal conditions experienced over all seasons in the United Kingdom. The aim was to investigate practical methods for predicting human responses to outside weather conditions, which would be useful in predicting effects on human comfort and health. The studies involved both laboratory experiments and field trials. One particular aspect of outside conditions, not usually investigated in laboratory studies, is the contribution of solar radiation. Single subject and thermal manikin studies were used to determine the contribution of solar radiation to human response. In addition to this, a total of 168 subjects responses were recorded during trials at the Loughborough University weather station compound. (latitude 52.47N and longitude 01.11W). The trials were distributed between July 2007 and October 2008. This provided a comprehensive data-base for the evaluation of thermal indices. The thesis is divided into four parts. Part one provides an introduction to the subject and a comprehensive literature review. It also describes equipment, calibration procedures and methods used. Part two quantified the contribution of solar radiation to the heat load on a person. A human subject and a heated thermal manikin were exposed to outdoor thermal conditions, while in light clothing and (for the person) conducting a step test. They were then exposed to identical conditions in a thermal chamber, but without the contribution of the sun. The conditions outside were 23˚C air temperature, 42˚C mean radiant temperature and 54% relative humidity with an average air velocity of 0.75 ms-1. The difference in sweat rate (person) and heat required (manikin) between outdoor and indoor conditions were used to estimate the contribution of the sun. Using three different analyses estimates were 14 Wm-2, 35 Wm-2 and 50 Wm-2 depending upon the assumptions made. Part three describes current thermal indices that can be used to assess the effects of weather conditions on people. It also presents the results of weather station measurements over the time period considered. In chapters 8 and 9 field trials are described which capture both the thermal conditions and human physiological and subjective responses to those conditions. Chapter 10 uses the data collected to provide an evaluation of current thermal indices for predicting human responses. The range of air temperature and relative humidity (at 2 pm) over a year was -2˚C to 29˚C and 34% to 95% respectively. Wind speed varied and was greater in winter and spring than in summer and autumn. Solar radiation was influenced by the altitude of the sun which depended upon season. Mean solar radiation increased from December to June and decreased from June to December. The subjective and physiological responses for 130 people (65 males and 65 females) over a range of outdoor weather conditions are presented. Physiological responses for females generally showed a stronger relationship with environmental variables and subjective responses than those for males. The subjective and physiological responses of four groups (one in each season of the year - involving a total of 38 people), are presented. It was found that there were significant individual differences in response. Part four provides a suggestion for an improved thermal index. The PMV (Predicted Mean Vote) out of four thermal indices (WBGT, PMV, WCI/tch and Twc) had the strongest relationship with environmental variables and physiological responses but had a weak relationship with subjective responses. A PMVoutdoors index was developed to improve the prediction of subjective responses for the outdoor conditions investigated. Conclusions and recommendations for future research are provided.

In this dissertation, we introduce three projects in machine learning and reliability applications after the general introductions in Chapter 1. The first project concentrates on the multivariate sensory data, the second project is related to the bivariate recurrent process, and the third project introduces thermal index (TI) estimation in accelerated destructive degradation test (ADDT) data, in which an R package is developed. All three projects are related to and can be used to solve certain reliability problems. Specifically, in Chapter 2, we introduce a clustering method for multivariate functional data. In order to cluster the customized events extracted from multivariate functional data, we apply the functional principal component analysis (FPCA), and use a model based clustering method on a transformed matrix. A penalty term is imposed on the likelihood so that variable selection is performed automatically. In Chapter 3, we propose a covariate-adjusted model to predict next event in a bivariate recurrent event system. Inspired by geyser eruptions in Yellowstone National Park, we consider two event types and model their event gap time relationship. External systematic conditions are taken account into the model with covariates. The proposed covariate adjusted recurrent process (CARP) model is applied to the Yellowstone National Park geyser data. In Chapter 4, we compare estimation methods for TI. In ADDT, TI is an important index indicating the reliability of materials, when the accelerating variable is temperature. Three methods are introduced in TI estimations, which are least-squares method, parametric model and semi-parametric model. An R package is implemented for all three methods. Applications of R functions are introduced in Chapter 5 with publicly available ADDT datasets. Chapter 6 includes conclusions and areas for future works. / Doctor of Philosophy / This dissertation focuses on three projects that are all related to machine learning and reliability. Specifically, in the first project, we propose a clustering method designated for events extracted from multivariate sensory data. When the customized event is corresponding to reliability issues, such as aging procedures, clustering results can help us learn different event characteristics by examining events belonging to the same group. Applications include diving behavior segmentation based on vehicle sensory data, where multiple sensors are measuring vehicle conditions simultaneously and events are defined as vehicle stoppages. In our project, we also proposed to conduct sensor selection by three different penalizations including individual, variable and group. Our method can be applied for multi-dimensional sensory data clustering, when optimal sensor design is also an objective. The second project introduces a covariate-adjusted model accommodated to a bivariate recurrent event process system. In such systems, events can occur repeatedly and event occurrences for each type can affect each other with certain dependence. Events in the system can be mechanical failures which is related to reliability, while next event time and type predictions are usually of interest. Precise predictions on the next event time and type can essentially prevent serious safety and economy consequences following the upcoming event. We propose two CARP models with marginal behaviors as well as the dependence structure characterized in the bivariate system. We innovate to incorporate external information to the model so that model results are enhanced. The proposed model is evaluated in simulation studies, while geyser data from Yellowstone National Park is applied. In the third project, we comprehensively discuss three estimation methods for thermal index. They are the least-square method, parametric model and semi-parametric model. When temperature is the accelerating variable, thermal index indicates the temperature at which our materials can hold up to a certain time. In reality, estimating the thermal index precisely can prolong lifetime of certain product by choosing the right usage temperature. Methods evaluations are conducted by simulation study, while applications are applied to public available datasets.