abstract: Mobile ad hoc networks (MANETs) have attracted attention for mission critical applications. This dissertation investigates techniques of statistical monitoring and control for overhead reduction in a proactive MANET routing protocol. Proactive protocols transmit overhead periodically. Instead, we propose that the local conditions of a node should determine this transmission decision. While the goal is to minimize overhead, a balance in the amount of overhead transmitted and the performance achieved is required. Statistical monitoring consists of techniques to determine if a characteristic has shifted away from an in-control state. A basic tool for monitoring is a control chart, a time-oriented representation of the characteristic. When a sample deviates outside control limits, a significant change has occurred and corrective actions are required to return to the in-control state. We investigate the use of statistical monitoring of local conditions in the Optimized Link State Routing (OLSR) protocol. Three versions are developed. In A-OLSR, each node uses a Shewhart chart to monitor betweenness of its two-hop neighbourhood. Betweenness is a social network metric that measures a node's influence; betweenness is larger when a node has more influence. Changes in topology are associated with changes in betweenness. We incorporate additional local node conditions including speed, density, packet arrival rate, and number of flows it forwards in A+-OLSR. Response Surface Methodology (RSM) is used to optimize timer values. As well, the Shewhart chart is replaced by an Exponentially Weighted Moving Average (EWMA) chart, which is more sensitive to small changes in the characteristic. It is known that control charts do not work as well in the presence of correlation. Hence, in A*-OLSR the autocorrelation in the time series is removed and an Auto-Regressive Integrated Moving Average (ARIMA) model found; this removes the dependence on node speed. A*-OLSR also extends monitoring to two characteristics concurrently using multivariate cumulative sum (MCUSUM) charts. The protocols are evaluated in simulation, and compared to OLSR and its variants. The techniques for statistical monitoring and control are general and have great potential to be applied to the adaptive control of many network protocols. / Dissertation/Thesis / Ph.D. Computer Science 2012

When unsafe conditions arise in a workplace, they may result in employee accidents and fatalities. However, if these problems are detected early, new hazard controls and safety initiatives can be introduced in order to actively reduce or prevent the occurrence of these events. Unfortunately, many safety systems currently monitor and report data that has been aggregated over long time periods, making it difficult to realize and respond to pattern shifts in a timely manner. When monitoring a process over time, a commonly used tool is statistical process control charting. Traditionally used in manufacturing, control charts indicate a deviation from historically "normal" or "in-control" behavior and have become increasingly common in healthcare and public health monitoring. This dissertation studies the use of control charts to monitor the frequency of occupational safety incidents, with the overarching goal of investigating the effects of data aggregation on the detection performance of these charts. Specifically, this dissertation 1) qualitatively establishes the need for more frequent monitoring of safety incidents; 2) investigates the comparative performance of control charts with aggregated and non-aggregated data for the detection of increased accident frequency, using a case study with data from an industrial partner; 3) more generally compares the performance of these charts for a Poisson process with a range of simulated process shifts; and 4) discusses the potential future challenges of including accident severity in quantitative safety monitoring systems. The comprehensive results indicate that lower degrees of data aggregation are preferred, and suggestions for better data collection and employee communication practices are offered to aid the transition for companies. / Ph. D.

This dissertation focuses on two topics in multivariate statistics. The first part develops an inference procedure and fast computation tool for the modal clustering method proposed by Li et al. (2007). The modal clustering, based on the kernel density estimate, clusters data using their associations within a single mode, with the final number of clusters equaling the number of modes, otherwise known as the modality of the distribution of the data. This method provides a flexible tool for clustering data of low to moderate dimensions with arbitrary distributional shapes. In contrast to Li and colleagues, we expand their method by proposing a procedure that determines the number of clusters in the data. A test statistic and its asymptotic distribution are derived to assess the significance of each mode within the data. The inference procedure is tested on both simulated and real data sets. In addition, an R computing package is developed (Modalclust) that implements the modal clustering procedure using parallel processing which dramatically increases computing speed over the previously available method. This package is available on the Comprehensive R Archive Network (CRAN). The second part of this dissertation develops methods of statistical monitoring of clinical trials with multiple co-primary endpoints, where success is defined as meeting both endpoints simultaneously. In practice, a group sequential design method is used to stop trials early for promising efficacy, and conditional power is used for futility stopping rules. In this dissertation we show that stopping boundaries for the group sequential design with multiple co-primary endpoints should be the same as those for studies with single endpoints. Lan and Wittes (1988) proposed the B-value tool to calculate the conditional power of single endpoint trials and we extend this tool to calculate the conditional power for studies with multiple co-primary endpoints. We consider the cases of two-arm studies with co-primary normal and binary endpoints and provide several examples of implementation with simulated trials. A fixed-weight sample size re-estimation approach based on conditional power is introduced. Finally, we discuss the possibility of blinded interim analyses for multiple endpoints using the modality inference method introduced in the first part.

The thesis is divided into two parts, theoretical and empirical. In the first, the author explains the important terms for processing the empirical part. He deals with the theory of fire and summary of the general rules. He also deals with finding out the causes of fire and the computer program "Statistical monitoring of events", all the data were taken here. The chapter provides a general overview of el. devices, classification, history and possible danger. A very important of this part is the division of el. initiators explain. the terms such as el. short circuit, impedance, el. spark, el. arc, overcurrent, car-el. and its application in vehicles. Separately the author deals with atmospheric and ESD. The first objective was to analyze the causes of fires from el. devices in the South Bohemian Region (SBR). The second objective was the proposal of arrangements to improve the situation. The author determined two hypotheses: 1. The most common cause of fires of el. devices in the SBR is the el. short circuit. 2. The most frequent fires of el. devices in the SBR are the fires of vehicles. At the end of the first part, the author outlined the methodology. For processing the empirical part , he chose a quantitative research. The research was carried out by using the one-dimensional statistical analysis of data. The author created the list of literary sources based on literature gained from research libraries, the Fire Rescue Service (FRS) of the SBR, territorial department Strakonice and el. sources available on the internet. All the data the author gained SME of the FRS of the SBR. Within empirical part, the author first carried out the overall statistics of fires from el. initiators. The results show that in the period of 2009 - 2013 there was an increase in number of fires from el. initiators from 7,14 % to 14,97 %, it means more than double compared to a total amount of all fires, which have a decreasing tendency. Then he deals with proportions among particular initiators of fire. These data indicate that the most abundant initiator is car-el. and its application in vehicles. Other significant initiators are el. short circuit and impedance. Other initiators carry a much smaller proportion of the total number of fires. Then follow damages and salvage values caused. Salvage values in each of the monitored years are far greater than the damages, about 80 %. The author continues with the amount of people killed and injured, there is a big difference. Throughout the given period there were 5 people killed in fires from el. initiators, 51 people injured. For the total fires are numbers logically higher, in years 2009 - 2013 were 363 people injured and 51 killed. Then follows a part in which the author deals with individual initiators represented by el. short circuit, impedance, el. spark, el. arc, overcurrent, car-el. and its application in vehicles, atmospheric discharge and ESD. In the empirical part, there are also included initiators, which cannot be further specified. After processing the gained statistical data it comes to the discussion, in which the author analyzes particular tables and graphs, problems, which occurred with their solution and expresses to previously established hypotheses. The first hypothesis was refuted, the second confirmed. The author proposed measures to improve the situation, as there was detected a lack of security measures. The results of the thesis will be a contribution to the FRS of the Czech Republic, especially to the Prevention Department, pedagogical purposes or the general public in the context of preventive educational activities. After implementation of any of my proposals, using the same research it is possible to determine whether the implementation of the proposal has a positive impact on the number of fires, injured and killed people or on an amount of damages in the coming years.