Chrisila C. Pettey

Adaptive teaching strategy for online learning

Finding the optimal teaching strategy for an individual student is difficult even for an experienced teacher. Identifying and incorporating multiple optimal teaching strategies for different students in a class is even harder. This paper presents an Adaptive tutor for online Learning, AtoL, for Computer Science laboratories that identifies and applies the appropriate teaching strategies for students on an individual basis. The optimal strategy for a student is identified in two steps. First, a basic strategy for a student is identified using rules learned from a supervised learning system. Then the basic strategy is refined to better fit the student using models learned using an unsupervised learning system that takes into account the temporal nature of the problem solving process. The learning algorithms as well as the initial experimental results are presented.

Intelligent tutoring system for CS-I and II laboratory

A Web-based adaptive tutoring system which dynamically adapts to each students needs and gives a student immediate feedback is being developed for our CS-I and CS-II closed laboratories. The system currently contains the question tutor, the program tutor, and the course management components. The tutoring components help students learn programming concepts through hands-on, self-paced exercises. The course management component helps teachers prepare and maintain the lab materials. Experiments have been conducted to evaluate the effectiveness of this new tutoring system and promising preliminary results were obtained.

A hybrid conceptual clustering system

Conceptual clustering is used to organize observations into an abstract hierarchy which can be used to predict classes and/or attribute values. Typically this clustering has been done using either incremental or nonincrementallearning. Incremental learning suffers from the ordering problem, while nonincremental learning cannot handle a dynamic environment efficiently. This paper proposes a hybrid conceptual clustering system which uses two learning algorithms. The first stage is based on Genetic Algorithms and is used as a preprocessor for the second stage. The second stage is an incremental learning system. This hybrid conceptual clustering system overcomes the difficulties encountered by using either a nonincremental or an incremental learning system alone.

CPVM: customizable portable virtual machines

We present our experiences with a customizable portable virtual machine (CPVM) environment that makes it possible for students and professors to develop a customized, fully loaded, fully functional virtual machine that they can run on any computer that has a USB port or an ftp client without compromising the host. We also make available to students and faculty a copy of a portable virtual machine which provides compilers, window managers, and IDEs as well as the virtual operating system. This copy is identical to the environment found in our labs. CPVM has allowed students to use their personal Windows computers as if they were the Linux machines in the lab without having to install Linux. It has also enabled professors to effectively take their office environments with them to remote locations such as conferences. CPVM is composed of free, open-source software, and is available via anonymous ftp.

Improving the Performance of FLN by Using Similarity Measures and Evolutionary Algorithms

In this work, we show that the underlying inclusion measure used by fuzzy lattice neurocomputing classifiers can be extended to various similarity and distance measures often used in cluster analysis. We show that for some similarity measures, we can modify the measure to weigh the contribution of each attribute found in the data set. Furthermore, we show that evolutionary algorithms such as genetic algorithms, tabu search, particle swarm optimization, and differential evolution can be used to weigh the importance of each attribute and that this weighting can provide additional improvements over simply using the similarity measure. We provide evidence that these new techniques provide significant improvements by applying them to the Cleveland heart data.

A free, readily upgradeable, interactive tool for teaching encryption algorithms

There are rising concerns about data security in our society. Strong cryptographic systems provide a primary means of dealing with these concerns. Since encryption algorithms are an integral component of any cryptographic system, computer science students need to understand how encryption algorithms work. However, the complexity of encryption algorithms inhibits both authors and professors from providing multiple and/or dynamic examples. This paper describes a new pedagogical tool that provides interactive step by step demonstrations of the encryption processes for various algorithms on user defined strings and scalability to allow for the addition of future algorithms. This tool is ideal for professors and students because it shows error free step by step descriptions in an interactive environment. It is designed to be used in conjunction with a lecture or outside reading material. Furthermore, this tools object oriented nature allows the user to change the interface, add subsequent algorithms, and even incorporate the package into other software for actual encryption purposes. We have made the tool freely available on the web.

Can algotutor change attitudes toward algorithms

The ability to design an algorithm is one of the most important learning outcomes of a computer science program. Unfortunately, not only is learning how to design algorithms a challenging task, but many students believe that algorithm design is not an important part of problem solving. To address this challenge and hopefully change student attitudes, we developed AlgoTutor, a web-based algorithm development tutoring system. AlgoTutors primary components are the algorithm composer and the algorithm tracer. A third component, ProgramPad, was added to show the connection between algorithms and code. This paper presents the results of experiments that assessed AlgoTutors effectiveness in changing student attitudes about algorithm development. The results show that students who used AlgoTutor in CS-I were more likely to realize the importance of algorithm design in problem solving and to have confidence in their own algorithm development abilities.

A small and secure submission system for UNIX systems

Often the only choices available for submitting assignments are paper, diskette, or e-mail. Yet each of these media has major shortcomings. This paper delineates these shortcomings, reviews previous attempts at creating useful assignment submission systems, and describes a new submission system, named turnin. This UNIX-based submission system is attractive because it is small, simple, easy to maintain, and intuitive to use. One of the major problems addressed by the design of turnin is support for submission of files across multiple NFS mounted file systems. Other features include the ability to enforce due dates, keep files in secure locations, keep accurate time stamps for individual submissions, and provide feedback to students about the status of their individual submissions.

The Identification and Characterization of Workload Classes

In all areas of engineering, it is important to be able to accurately forecast how a system would react to some change. For instance, for a proposed new bridge design, what would be the effect of 10 large trucks simultaneously crossing the bridge? Or, for an existing parallel computer system, what would be the expected response time if three processors failed simultaneously? To be able to answer such performance prediction questions, an engineer needs a correct characterization of the current system.