Initial placement methods for Haitian adult ESOL students : the NYS place test plus profile data compared to subjective assessment

Few valid and reliable placement procedures are available to assess the English language proficiency of adults who enroll in English for Speakers of Other Languages (ESOL) programs. Whereas placement material exists for children and university ESOL students, the needs of students in adult community education programs have not been adequately addressed. Furthermore, the research suggests that a number of variables, such as, native language, age, prior schooling, length of residence, and employment are related to second language acquisition. Numerous studies contribute to our understanding of the relationship of these factors to second language acquisition of Spanish-speaking students. Again, there is a void in the research investigating the factors affecting second language acquisition and consequently, appropriate placement of Haitian Creole-speaking students. This study compared a standardized instrument, the NYS Place Test, used alone and in combination with a writing sample in English, to subjective judgement of a department coordinator for initial placement of Haitian adult ESOL students in a community education program. The study also investigated whether or not consideration of student profile data improved the accuracy of the test. Finally, the study sought to determine if a relationship existed between student profile data and those who withdrew from the program or did not enter a class after registering. Analysis of the data by crosstabulation and chi-square revealed that the standardized NYS Place Test was at least as accurate as subjective department coordinator placement and that one procedure could be substituted for li other. Although the writing sample in English improved accuracy of placement by the NYS test, the results were not significant. Of the profile variables, only length of residence was found to be significantly related to accuracy of placement using the NYS Place Test. The number of incorrect placements was higher for those students who lived in the host country from twenty-five to one hundred ten months. A post hoc analysis of NYS test scores according to level showed that those learners who placed in level three also had a significantly higher incidence of incorrect placements. No significant relationship was observed between the profile variables and those who withdrew from the program or registered but did not enter a class.

Dynamic data retrieval on the world wide web

Methods for accessing data on the Web have been the focus of active research over the past few years. In this thesis we propose a method for representing Web sites as data sources. We designed a Data Extractor data retrieval solution that allows us to define queries to Web sites and process resulting data sets. Data Extractor is being integrated into the MSemODB heterogeneous database management system. With its help database queries can be distributed over both local and Web data sources within MSemODB framework. Data Extractor treats Web sites as data sources, controlling query execution and data retrieval. It works as an intermediary between the applications and the sites. Data Extractor utilizes a two-fold "custom wrapper" approach for information retrieval. Wrappers for the majority of sites are easily built using a powerful and expressive scripting language, while complex cases are processed using Java-based wrappers that utilize specially designed library of data retrieval, parsing and Web access routines. In addition to wrapper development we thoroughly investigate issues associated with Web site selection, analysis and processing. Data Extractor is designed to act as a data retrieval server, as well as an embedded data retrieval solution. We also use it to create mobile agents that are shipped over the Internet to the client's computer to perform data retrieval on behalf of the user. This approach allows Data Extractor to distribute and scale well. This study confirms feasibility of building custom wrappers for Web sites. This approach provides accuracy of data retrieval, and power and flexibility in handling of complex cases.

Improving Resource Management in Virtualized Data Centers using Application Performance Models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity. We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.