Thesis (M. Sc. (Computer Science))--University of Pretoria, 2000. / Summaries in Afrikaans and English. Includes bibliographical references.
Clustering is a fundamental data mining tool that aims to divide data into groups of similar items. Intuition about clustering reflects the ideal case -- exact data sets endowed with flawless dissimilarity between individual instances. In practice however, these cases are in the minority, and clustering applications are typically characterized by noisy data sets with approximate pairwise dissimilarities. As such, the efficacy of clustering methods necessitates robustness to perturbations. In this paper, we address foundational questions on perturbation robustness, studying to what extent can clustering techniques exhibit this desirable characteristic. Our results also demonstrate the type of cluster structures required for robustness of popular clustering paradigms. / A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science. / Summer Semester 2017. / May 4, 2017. / Includes bibliographical references. / Margareta Ackerman, Professor Co-Directing Thesis; Gary Tyson, Professor Co-Directing Thesis; Sonia Haiduc, Committee Member; Peixiang Zhao, Committee Member.
Gemaehlich, Donald J.
Typescript (photocopy). / Digitized by Kansas Correctional Industries
Detecting Prominent Features and Classifying Network Traffic for Securing Internet of Things Based on Ensemble MethodsJanuary 2019 (has links)
abstract: Rapid growth of internet and connected devices ranging from cloud systems to internet of things have raised critical concerns for securing these systems. In the recent past, security attacks on different kinds of devices have evolved in terms of complexity and diversity. One of the challenges is establishing secure communication in the network among various devices and systems. Despite being protected with authentication and encryption, the network still needs to be protected against cyber-attacks. For this, the network traffic has to be closely monitored and should detect anomalies and intrusions. Intrusion detection can be categorized as a network traffic classification problem in machine learning. Existing network traffic classification methods require a lot of training and data preprocessing, and this problem is more serious if the dataset size is huge. In addition, the machine learning and deep learning methods that have been used so far were trained on datasets that contain obsolete attacks. In this thesis, these problems are addressed by using ensemble methods applied on an up to date network attacks dataset. Ensemble methods use multiple learning algorithms to get better classification accuracy that could be obtained when the corresponding learning algorithm is applied alone. This dataset for network traffic classification has recent attack scenarios and contains over fifteen attacks. This approach shows that ensemble methods can be used to classify network traffic and detect intrusions with less training times of the model, and lesser pre-processing without feature selection. In addition, this thesis also shows that only with less than ten percent of the total features of input dataset will lead to similar accuracy that is achieved on whole dataset. This can heavily reduce the training times and classification duration in real-time scenarios. / Dissertation/Thesis / Masters Thesis Computer Science 2019
Chen, Hsinchun, Lynch, K.J., Basu, K., Ng, Tobun Dorbin
Artificial Intelligence Lab, Department of MIS, University of Arizona / This Blackboard-based design uses a neural-net spreading-activation algorithm to traverse multiple thesauri. Guided by heuristics, the algorithm activates related terms in the thesauri and converges on the most pertinent concepts.
Chen, Hsinchun, Buntin, P., She, Linlin, Sutjahjo, S., Sommer, C., Neely, D.
Artificial Intelligence Lab, Department of MIS, University of Arizona / For our research, we investigated a different problem-solving scenario called game playing, which is unstructured, complex, and seldom-studied. We considered several real-life game-playing scenarios and decided on greyhound racing. The large amount of historical information involved in the search poses a challenge for both human experts and machine-learning algorithms. The questions then become: Can machine-learning techniques reduce the uncertainty in a complex game-playing scenario? Can these methods outperform human experts in prediction? Our research sought to answer these questions.
Chen, Hsinchun, Nunamaker, Jay F., Orwig, Richard E., Titkova, Olga
Artificial Intelligence Lab, Department of MIS, University of Arizona / A prototype tool classifies output from an electronic meeting system into a manageable list of concepts, topics, or issues that a group can further evaluate. In an experiment with output from GroupSystems electronic meeting system, the tool's recall ability was comparable to that of a human facilitator, but took roughly a sixth of the time.
Bailey, Charles W.
A multimedia computer system is one that can create, import, integrate, store, retrieve, edit, and delete two or more types of media materials in digital form, such as audio, image, full-motion video, and text information. This paper surveys four possible types of multimedia computer systems: hypermedia, multimedia database, multimedia message, and virtual reality systems. The primary focus is on advanced multimedia systems development projects and theoretical efforts that suggest long-term trends in this increasingly important area.
Estimating drug/plasma concentration levels by applying neural networks to pharmacokinetic data setsTolle, Kristin M., Chen, Hsinchun, Chow, Hsiao-Hui January 2000 (has links)
Artificial Intelligence Lab, Department of MIS, University of Arizona / Predicting blood concentration levels of pharmaceutical agents in human subjects can be made difficult by missing data and variability within and between human subjects. Biometricians use a variety of software tools to analyze pharmacokinetic information in order to conduct research about a pharmaceutical agent. This paper is the comparison between using a feedforward backpropagation neural network to predict blood serum concentration levels of the drug tobramycin in pediatric cystic fibrosis and hemotologicâ oncologic disorder patients with the most commonly used software for analysis of pharmacokinetics, NONMEM. Mean squared standard error is used to establish the comparability of the two estimation methods. The motivation for this research is the desire to provide clinicians and pharmaceutical researchers a cost effective, user friendly, and timely analysis tool for effectively predicting blood concentration ranges in human subjects.
The Intelligent Reference Information System Project: A Merger of CD-ROM LAN and Expert System TechnologiesBailey, Charles W. January 1992 (has links)
The University Libraries of the University of Houston created an experimental Intelligent Reference Information System (IRIS) over a two-year period. A ten-workstation CD-ROM LAN was implemented that provided access to nineteen citation, full-text, graphic, and numeric databases. An expert system, Reference Expert, was developed to assist users in selecting appropriate printed and electronic reference sources. This expert system was made available on both network and stand-alone workstations. Three research studies were conducted.
Page generated in 0.1054 seconds