Data Preparation Steps Research Articles

Water Reservoir Control with Data Mining

This paper describes the development of a general operating policy for a water supply system using the methodology of data mining. To define an operating policy using this approach, both a single-reservoir and a multireservoir water system were modeled and optimized for a set of historical inflows. These optimization results defined the best possible performance for the systems with historical hindsight, and were used as input for the data mining process. The data mining algorithm then generated the set of control rules that gave the best historical operating policy. The data mining tool used in this work is based on the induction tree technique, C5.0, reported by Quinlan in 1993. However, the process of reservoir control rule extraction is not straightforward and requires several data preparation steps to enhance the performance of the data mining algorithm. To demonstrate the effectiveness of the rules developed through data mining, simulation runs of the system were performed. The results of these simulations were compared with simulation results using operating policies derived from linear regression. Another comparison between operating rules derived using different methodologies was performed for the multireservoir system where, in addition to data mining and regression-based rules, there were rules available from the U.K. Environment Agency (South West). The paper shows that “data-mined” rules come closest to the optimization results.

Bayesian learning for cardiac SPECT image interpretation

In this paper, we describe a system for automating the diagnosis of myocardial perfusion from single-photon emission computerized tomography (SPECT) images of male and female hearts. Initially we had several thousand of SPECT images, other clinical data and physician–interpreter’s descriptions of the images. The images were divided into segments based on the Yale system. Each segment was described by the physician as showing one of the following conditions: normal perfusion, reversible perfusion defect, partially reversible perfusion defect, fixed perfusion defect, defect showing reverse redistribution, equivocal defect or artifact. The physician’s diagnosis of overall left ventricular (LV) perfusion, based on the above descriptions, categorizes a study as showing one or more of eight possible conditions: normal, ischemia, infarct and ischemia, infarct, reverse redistribution, equivocal, artifact or LV dysfunction. Because of the complexity of the task, we decided to use the knowledge discovery approach, consisting of these steps: problem understanding, data understanding, data preparation, data mining, evaluating the discovered knowledge and its implementation. After going through the data preparation step, in which we constructed normal gender-specific models of the LV and image registration, we ended up with 728 patients for whom we had both SPECT images and corresponding diagnoses. Another major contribution of the paper is the data mining step, in which we used several new Bayesian learning classification methods. The approach we have taken, namely the six-step knowledge discovery process has proven to be very successful in this complex data mining task and as such the process can be extended to other medical data mining projects.

Tai-ji ID Automatic Closed-Loop Identification Package for Model Based Process Control

Tai-Ji ID is an identification software that carries out identification automatically from test design to model validation. Data collected from both open-loop and closed-loop operations can be used. Tai-Ji ID is developed for model based process control such as model predictive control (MPC) and linear robust control. Special attention is paid to deal with industrial processes which have complex dynamics, high disturbance level and many process variables. Tai-Ji ID is based on the so called ASYM method of identification. Tai-Ji ID is designed for process control engineers and process engineers who are involved in model based process control and monitoring. No specific knowledge on process identification is required in order to use Tai-Ji ID. On the other hand, users' knowledge on process unit operation can be incorporated in data preparation step and in model validation step during a Tai-Ji ID session.

Image-projection ion-beam lithography

Image-projection ion-beam lithography is an attractive alternative for submicron patterning because it may provide high throughput; it uses demagnification to gain advantages in reticle fabrication, inspection, and lifetime; and it enjoys the precise deposition characteristics of ions which cause essentially no collateral damage. This lithographic option involves extracting low-mass ions (e.g., He+ ) from a plasma source, transmitting the ions at low voltage through a stencil reticle, and then accelerating and focusing the ions electrostatically onto a resist-coated wafer. While the advantages of this technology have been demonstrated experimentally by the work of IMS (Austria), many difficulties still impede extension of the technology to the high-volume production of microelectronic devices. We report a computational study of a lithography system designed to address problem areas in field size, telecentricity, and chromatic and geometric aberration. We present a novel ion-column-design approach and conceptual ion-source and column designs which address these issues. We find that image-projection ion-beam technology should in principle meet high-volume-production requirements. The technical success of our present relatively compact-column design requires that a glow-discharge-based ion source (or equivalent cold source) be developed and that moderate further improvement in geometric aberration levels be obtained. Our system requires that image predistortion be employed during reticle fabrication to overcome distortion due to residual image nonlinearity and space-charge forces. This constitutes a software data preparation step, as do correcting for distortions in electron lithography columns and performing proximity-effect corrections. Areas needing further fundamental work are identified.