Mario Garcia

Learn how to develop software using the toy LEGO Mindstorms

The use of the toy LEGO Mindstorms has been used more often in engineering and computer sciences courses in several countries. Undergraduate students at Texas A&M University-Corpus Christi implemented seven robotics applications as the final project for the Software Analysis and Design course. The students applied the knowledge acquired in other courses such as Software Engineering, Databases, and several programming courses. The students used Microsoft Project for the planning phase and the CASE tool Visible Analyst for the design phase. At the end of the semester there was a robot competition. Two projects are described in this paper.

PUMPX: an expert system for pump diagnosis

Diagnosing problems with centrifugal pumps usually requires personnel with extensive experience or education. Centrifugal pumps represent the largest power consumption of any type of liquid movers in industrialized countries. Diagnosis of problems with recommendations from a computerized assistant would be highly useful. This paper describes the implementation of PUMPX, an expert system for diagnosis of pump problems and for recommendation of corrective action. Four main symptoms are included: vibration/noise, high temperature, leaks and low performance. The use of this program can lead to utilization of lower experience personnel for diagnosis and can be used for training. The correct and timely diagnosis and correction of pump problems will lead to reduced power consumption and avoid unnecessary expenditures for upgrades.

Detecting Simulated Attacks in Computer Networks Using Resilient Propagation Artificial Neural Networks

In a large network, it is extremely difficult for an administrator or security personnel to detect which computers are being attacked and from where intrusions come. Intrusion detection systems using neural networks have been deemed a promising solution to detect such attacks. The reason is that neural networks have some advantages such as learning from training and being able to categorize data. Many studies have been done on applying neural networks in intrusion detection systems. This work presents a study of applying resilient propagation neural networks to detect simulated attacks. The approach includes two main components: the Data Pre- processing module and the Neural Network. The Data Pre- processing module performs normalizing data function while the Neural Network processes and categorizes each connection to find out attacks. The results produced by this approach are compared with present approaches.