Previous work on moving object mobile group pattern mining defined and proposed algorithms for mobile group mining based on their individual movement data. Movement data is expected to be widely available owing to the increasing popularity of tractable mobile devices on the cutting edge. However, existing approaches of mobile group pattern mining do not consider temporal dimension. Considering that human beings often act as a group according to some temporal features such as routine activities, in this thesis, we engage in the discovery of valid mobile groups that pertain to the some temporal patterns. In our research, we introduce the calendar-based representation mechanism to be our representation of temporal dimension. Taking the calendar patterns into account, we define a new problem called calendar-based mobile group mining problem and develop efficient algorithms for the problem. The proposed algorithms are evaluated via synthetic location data generated by a sensible data generator.

As the mobile communication devices become popular, getting the location data of various objects is more convenient than before. Mobile groups that exhibit spatial and temporal proximities can be used for marketing, criminal detection, and ecological studies, just to name a few. Although nowadays the most advanced position equipments are capable of achieving a high accuracy with the measurement error less than 10 meters, they are still expensive. Positioning equipments using different technologies incur different amount of measurement errors ranging from 10 meters to a few hundred meters. In this thesis, we examine the impact of measurement errors on the accuracy of identified valid mobile groups and apply Kalman Filter and RTS smoothing as the one-way and two-way correction to correct the measurement data. In most settings, the corrected location data yield more accurate valid mobile groups. However, when the measurement error is small and users do not make abrupt change in their speed, mining mobile groups directly on the measurement data, however, yield better results.

As the advances of communication techniques, some services related to location information came into existence successively. On such application is on finding out the mobile groups that exhibit spatial and temporal proximities called mobile group mining. Although there exists positioning devices that are capable of achieving a high accuracy with low measurement error. Many consumer-grades, inexpensive positioning devices that incurred various extent of higher measurement error are much more popular. In addition, some natural factors such as temperature, humidity, and pressure may have influences on the precision of position measurement. Worse, moving objects may sometimes become untraceable voluntarily or involuntarily. In this thesis, we extend the previous work on mobile group mining and adopt Kalman filter to correct the noisy data and predict the missing data. Several methods based on Kalman filter that correct/predict either correction data or pair-wise distance data. These methods have been evaluated using synthetic data generated using IBM City Simulator. We identify the operating regions in which each method has the best performance.

Mobile group II introns are retroelements that insert site-specifically into DNA target sites by a process called retrohoming. Retrohoming is mediated by a ribonucleoprotein particle (RNP) that contains both the intron RNA and the intronencoded protein (IEP). My dissertation focuses on two mobile group II introns: Lactococcus lactis Ll.LtrB and Escherichia coli EcI5, which belong to structural subclasses IIA and CL/IIB1, respectively. Previous studies showed that the Ll.LtrB IEP, denoted LtrA protein, is pole localized in E. coli. First, I found that active LtrA protein is associated with E. coli membrane fractions, suggesting that LtrA pole localization might reflect association with a membrane receptor. Second, I found that EcI5 is highly active in retrohoming in E. coli and obtained a comprehensive view of its DNA target site recognition by selection experiments. I found that EcI5 recognizes DNA target sequences by using both the IEP and base pairing of the intron RNA, with the IEP having different target specificity than for other mobile group II introns. A computer algorithm based on the empirically determined DNA recognition rules enabled retargeting of EcI5 to integrate at ten different sites in the chromosomal lacZ gene at frequencies up to 98% without selection. Finally, I developed methods for gene targeting in the frog Xenopus laevis by using Ll.LtrB RNPs for site-specific DNA modification in isolated sperm nuclei, followed by in vitro fertilization to generate genetically modified animals. The site-specific integrations were efficient enough to detect in fifty sperm nuclei for a multiple copy target site, the Tx1 transposon, and several hundred sperm nuclei for protein-encoding genes. Based on these results, I obtained transgenic tadpoles with sitespecific Tx1 integrations by simple screening. To facilitate screening for embryos with targeted integrations in protein-encoding genes, I constructed an intron carrying a GFPRAM (Retrotransposition-Activated Marker). By using this GFP-RAM with introns containing randomized sequences that base pair with the target DNA, I obtained tadpoles with intron integrations at different genomic locations, including protein-encoding genes. The methods for using group II introns for targeted sperm DNA modification in X. laevis may be applicable to other animals. / text

In recent years, with the popularization of the mobile devices, more and more location-based applications have been developed. As a result, location data of various objects is widely available. Identifying object groups that tend to move together is an emerging research topic. Existing approaches for identifying mobile group patterns assume the existence of raw location data which records a given object¡¦s position at every equal-spaced time point. However, a moving object may become disconnected voluntarily or involuntarily from time to time, and thus this assumption may not always valid. In this research, we describe the locations of moving object as a (non-continuous) trajectory function. Based on the new model, we re-define the mobile group mining problem and develop efficient algorithms for mining mobile groups. The proposed algorithms are evaluated via synthetic data generated by IBM City Simulator.

In the past few years, due to the development of the mobile devices and the improvement of database technology, the geometric information has become widely available. Identifying object groups based on spatial-temporal dimension is an emerging research topic. Previous work has incorporating the spatial and temporal information pertaining to moving objects in finding mobile groups. Considering that mobile groups tend to exhibit some calendar-like temporal features, we define a new temporal presentation mechanism called flexible calendar pattern, which allows users to specify the desired calendar patterns at a coarse level. In addition, we developed efficient algorithms for mining mobile groups pertaining some user-specified flexible calendar pattern. The proposed algorithms are evaluated via the synthetic data generated by IBM City Simulator. The results show that our approaches prove to perform more efficiently than other intuitive approaches.

In this paper, we present a novel approach to mine moving object group patterns from object movement database. At first, our approaches summarize the raw data in the source object movement database into trajectories, and then discover valid 2-groups mainly from the trajectory-based object movement database. We propose two trajectory conversion methods, namely linear regression and vector conversion. We further propose a trajectory based mobile group mining algorithm that is intended to reduce the overhead of mining 2-Group Patterns. The use of trajectories allows valid 2-groups to be mined using smaller number of summarized records (in trajectory model) and examining smaller number of candidate 2-groups. Finally, we conduct series of comprehensive experiments to evaluate and compare the performances of the proposed methods with existing approaches that use source object movement database or other summarization techniques. The experimental results demonstrate the superior performance of our proposed approach.