Arthur Tay

Mining multiple comprehensible classification rules using genetic programming

Genetic programming (GP) has emerged as a promising approach to deal with the classification task in data mining. This paper extends the tree representation of GP to evolve multiple comprehensible IF-THEN classification rules. We introduce a concept mapping technique for the fitness evaluation of individuals. A covering algorithm that employs an artificial immune system-like memory vector is utilized to produce multiple rules as well as to remove redundant rules. The proposed GP classifier is validated on nine benchmark data sets, and the simulation results confirm the viability and effectiveness of the GP approach for solving data mining problems in a wide spectrum of application domains.

Dual stage actuator control in hard disk drive - a review

This paper provides a comprehensive review of various methods suggested over the past few years to design controller for dual-actuated servomechanism in hard disk drives. Main challenges in the design are explained, and different methods are compared based on these factors.

Optimal predictive control with constraints for the processing of semiconductor wafers on bake plates

An optimal control scheme is designed to improve repeatability by minimizing the loading effects induced by the common processing condition of placement of a semiconductor wafer at ambient temperature on a large thermal-mass bake plate at processing temperature. The optimal control strategy is a model-based method using linear programming to minimize the worst-case deviation from a nominal temperature set point during the load disturbance condition. This results in a predictive controller that performs a predetermined heating sequence prior to the arrival of the wafer as part of the resulting feedforward/feedback strategy to eliminate the load disturbance. This procedure is based on an empirical model generated from data obtained during closed-loop operation. It is easy to design and implement for conventional thermal processing equipment. Experimental results are performed for a commercial conventional bake plate and depict an order-of-magnitude improvement in the settling time and the integral-square temperature error between the optimal predictive controller and a feedback controller for a typical load disturbance.

The intelligent alarm management system

Nuisance alarms often clutter and obscure a process plant operators view of critical information, with potentially severe consequences. The intelligent alarm management system (IAMS) suppresses nuisance alarms and provides valuable advisory information to help the operator focus quickly on important alarm information and take correct, quick actions. Test results show that IAMS effectively suppresses nuisance alarms, making alarm systems more helpful.

Dynamic Game Difficulty Scaling Using Adaptive Behavior-Based AI

Games are played by a wide variety of audiences. Different individuals will play with different gaming styles and employ different strategic approaches. This often involves interacting with nonplayer characters that are controlled by the game AI. From a developers standpoint, it is important to design a game AI that is able to satisfy the variety of players that will interact with the game. Thus, an adaptive game AI that can scale the difficulty of the game according to the proficiency of the player has greater potential to customize a personalized and entertaining game experience compared to a static game AI. In particular, dynamic game difficulty scaling refers to the use of an adaptive game AI that performs game adaptations in real time during the game session. This paper presents two adaptive algorithms that use ideas from reinforcement learning and evolutionary computation to improve player satisfaction by scaling the difficulty of the game AI while the game is being played. The effects of varying the learning and mutation rates are examined and a general rule of thumb for the parameters is proposed. The proposed algorithms are demonstrated to be capable of matching its opponents in terms of mean scores and winning percentages. Both algorithms are able to generalize well to a variety of opponents.

Using the OPC standard for real-time process monitoring and control

In recent years, the use of software engineering tools for the process industry has increased substantially, accelerating research and development work. However, such tools are essentially limited in their connectivity to other systems and applications. Its therefore challenging to integrate the diverse, components developed using these tools so that they can seamlessly communicate locally and remotely. Accomplishing this integration is nonetheless essential, particularly as process control applications grow larger and more complex. We propose an open, nonproprietary, plug-and-play system (ONPS) for real-time process monitoring and control. Based on the object linking and embedding for process control (OPC) standard, ONPS provides a standard method for individual process monitoring and process control software to interact and share data.

Estimation of wafer warpage profile during thermal processing in microlithography

Wafer warpage is common in microelectronics processing. Warped wafers can affect device performance, reliability, and linewidth control in various processing steps. Early detection will minimize cost and processing time. We propose in this article an in situ approach for estimating wafer warpage profile during the thermal processing steps in the microlithography process. The average air gap between wafer and bake-plate at multiple locations of a multizone bake-plate can be estimated and a profile can be obtained by joining these points. Experimental results demonstrate the feasibility and repeatability of the approach. This is a major improvement over our previously developed approach, in which only the average warpage could be obtained. The proposed approach requires no extra processing steps and time, as compared to conventional off-line methods.

Design and implementation of a distributed evolutionary computing software

Although evolutionary algorithm is a powerful optimization tool, its computation cost involved in terms of time and hardware resources increases as the size or complexity of the problem increases. One promising approach to overcome this limitation is to exploit the inherent parallelism of evolutionary algorithms by creating an infrastructure necessary to support distributed evolutionary computing using existing Internet and hardware resources. This paper presents a Java-based distributed evolutionary computing software (Paladin-DEC), which enhances the concurrent processing and performance of evolutionary algorithms by allowing inter-communications of subpopulations among various computers over the Internet. Such a distributed system enables individuals to migrate among multiple subpopulations according to some patterns to induce diversity of elite individuals periodically, in a way that simulates the species evolve in natural environment. The Paladin-DEC software is capable of keeping data integrity throughout the computation, and is incorporated with the features of robustness, security, fault tolerance, and work balancing. The effectiveness and advantages of the Paladin-DEC are illustrated upon two case studies of drug scheduling in cancer chemotherapy and searching probe sets of yeast genome.

An In Situ Approach to Real-Time Spatial Control of Steady-State Wafer Temperature During Thermal Processing in Microlithography

We proposed an in situ method to control the steady-state wafer temperature uniformity during thermal processing in microlithography. Thermal processing of wafer in the microlithography sequence is conducted by the placement of the wafer on the bake-plate for a given period of time. A physical model of the thermal system is first developed by considering energy balances on the system. Next, by monitoring the bake-plate temperature and fitting the data into the model, the temperature of the wafer can be estimated and controlled in real-time. This is useful as production wafers usually do not have temperature sensors embedded on it, these bake-plates are usually calibrated based on test wafers with embedded sensors. However, as processes are subjected to process drifts, disturbances, and wafer warpages, real-time correction of the bake-plate temperatures to achieve uniform wafer temperature at steady state is not possible in current baking systems. Any correction is done based on run-to-run control techniques which depends on the sampling frequency of the wafers. Our approach is real-time and can correct for any variations in the desired steady-state wafer temperature. Experimental results demonstrate the feasibility of the approach

Resist film uniformity in the microlithography process

With the trends toward smaller feature size, one of the challenge is to control the resist thickness and uniformity to a tight tolerance in order to minimize thin film interference effects on the critical dimensions. In this paper, we propose a new approach to improve resist thickness control and uniformity through the soft-bake process. Using an array of thickness sensors, a multizones bakeplate and a sliding mode control algorithm, the temperature distribution of the bakeplate is manipulated in real-time to reduce the resist thickness nonuniformity. The sliding mode control algorithm is implemented in a cascaded control structure so that the bake temperature is constrained. This is to prevent decomposition of the photoactive compound in the resist. We have experimentally demonstrated an improvement in the resist thickness uniformity across individual wafers and from wafer-to-wafer. The cascaded control structure using a sliding mode control algorithm provides a simpler and faster implementation of the thickness control strategy and makes it more suitable for real-time application. There is about 75 times reduction in the computation time and a resist thickness nonuniformity of less than 10 /spl Aring/ is achieved.