Hyoung-joo Lee

Virtual metrology for run-to-run control in semiconductor manufacturing

In semiconductor manufacturing processes, run-to-run (R2R) control is used to improve productivity by adjusting process inputs run by run. A process will be controlled based on information obtained during or after a process, including metrology values of wafers. Those metrology values, however, are usually available for only a small fraction of sampled wafers. In order to overcome the limitation, one can use virtual metrology (VM) to predict metrology values of all wafers, based on sensor data from production equipments and actual metrology values of sampled wafers. In this paper, we develop VM prediction models using various data mining techniques. We also develop a VM embedded R2R control system using the exponentially weighted moving average (EWMA) scheme. The experiments consist of two parts: (1) verifying VM prediction models with actual production equipments data, and (2) conducting simulations of the R2R control system. Our VM prediction models are found to be accurate enough to be directly implemented in actual manufacturing processes. The simulation results show that the VM embedded R2R control system improves productivity.

A virtual metrology system for semiconductor manufacturing

Nowadays, the semiconductor manufacturing becomes very complex, consisting of hundreds of individual processes. If a faulty wafer is produced in an early stage but detected at the last moment, unnecessary resource consumption is unavoidable. Measuring every wafers quality after each process can save resources, but it is unrealistic and impractical because additional measuring processes put in between each pair of contiguous processes significantly increase the total production time. Metrology, as is employed for product quality monitoring tool today, covers only a small fraction of sampled wafers. Virtual metrology (VM), on the other hand, enables to predict every wafers metrology measurements based on production equipment data and preceding metrology results. A well established VM system, therefore, can help improve product quality and reduce production cost and cycle time. In this paper, we develop a VM system for an etching process in semiconductor manufacturing based on various data mining techniques. The experimental results show that our VM system can not only predict the metrology measurement accurately, but also detect possible faulty wafers with a reasonable confidence.

Retraining a keystroke dynamics-based authenticator with impostor patterns

In keystroke dynamics-based authentication, novelty detection methods are used since only the valid users patterns are available when a classifier is first constructed. After a while, however, impostors keystroke patterns become available from failed login attempts. We propose to employ the retraining framework where a novelty detector is retrained with the impostor patterns to enhance authentication accuracy. In this paper, learning vector quantization for novelty detection and support vector data description are retrained with the impostor patterns. Experimental results show that retraining improves the authentication performance and that learning vector quantization for novelty detection outperforms other widely used novelty detectors.

Evolution of multimass globular clusters in the Galactic tidal field with the effects of velocity anisotropy

ABSTRA C T We study the evolution of globular clusters with mass spectra under the influence of the steady Galactic tidal field, including the effects of velocity anisotropy. Similarly to singlemass models, velocity anisotropy develops as the cluster evolves, but the degree of anisotropy is much smaller than in isolated clusters. Except for very early epochs of the cluster evolution, the velocity distributions of nearly all mass components become tangentially anisotropic at the outer parts. We examine how the mass function (MF) changes in time. Specifically, we find that the power-law index of the MF decreases monotonically with the total mass of the cluster, in agreement with previous findings based on isotropic models or N-body studies. This is also consistent with the behaviour of the observed slopes of MFs for a limited number of clusters. We attempt to compare our results with multimass King models, although it is almost impossible to fit the entire density profiles for all mass components. When the MF is fixed, the central densities of individual components show significant differences between Fokker‐Planck and King models. We obtain ‘best-fitting’ multimass King models, for which the central density of individual components as well as the total density distribution agrees with the Fokker‐Planck models by adjusting the MF. The MFs obtained in this way closely resemble the MF within the half-mass radius of the Fokker‐Planck result. Also, we find that the local MFs predicted by Fokker‐Planck calculations vary more rapidly with radius than best-fitting multimass King models. The projected velocity profiles for anisotropic models show significant flattening toward the tidal radius compared with the isotropic model. This is caused by the fact that the tangential velocity dispersion becomes dominant at the outer parts. Such a behaviour of velocity profile appears to be consistent with the observed profiles of the collapsed cluster M15.

Machine learning-based novelty detection for faulty wafer detection in semiconductor manufacturing

Since semiconductor manufacturing consists of hundreds of processes, a faulty wafer detection system, which allows for earlier detection of faulty wafers, is required. statistical process control (SPC) and virtual metrology (VM) have been used to detect faulty wafers. However, there are some limitations in that SPC requires linear, unimodal and single variable data and VM underestimates the deviations of predictors. In this paper, seven different machine learning-based novelty detection methods were employed to detect faulty wafers. The models were trained with Fault Detection and Classification (FDC) data to detect wafers having faulty metrology values. The real world semiconductor manufacturing data collected from a semiconductor fab were tested. Since the real world data have more than 150 input variables, we employed three different dimensionality reduction methods. The experimental results showed a high True Positive Rate (TPR). These results are promising enough to warrant further study.

Improving authentication accuracy using artificial rhythms and cues for keystroke dynamics-based authentication

Keystroke dynamics-based authentication (KDA) is to verify a users identity using not only the password but also keystroke dynamics. With a small number of patterns available, data quality is of great importance in KDA applications. Recently, the authors have proposed to employ artificial rhythms and tempo cues to improve data quality: consistency and uniqueness of typing patterns. This paper examines whether improvement in uniqueness and consistency translates into improvement in authentication performance in real-world applications. In particular, we build various novelty detectors using typing patterns based on various strategies in which artificial rhythms and/or tempo cues are implemented. We show that artificial rhythms and tempo cues improve authentication accuracies and that they can be applicable in practical authentication systems.

Response modeling with support vector regression

Response modeling has become a key factor to direct marketing. In general, there are two stages in response modeling. The first stage is to identify respondents from a customer database while the second stage is to estimate purchase amounts of the respondents. This paper focuses on the second stage where a regression, not a classification, problem is solved. Recently, several non-linear models based on machine learning such as support vector machines (SVM) have been applied to response modeling. However, there is a major difficulty. A typical training dataset for response modeling is so large that modeling takes very long, or, even worse, modeling may be impossible. Therefore, sampling methods have been usually employed in practice. However a sampled dataset usually leads to lower accuracy. In this paper, we employed an @e-tube based sampling for support vector regression (SVR) which leads to better accuracy than the random sampling method.

On-line novelty detection using the Kalman filter and extreme value theory

Novelty detection is concerned with identifying abnormal system behaviours and abrupt changes from one regime to another. This paper proposes an on-line (causal) novelty detection method capable of detecting both outliers and regime change points in sequential time-series data. Our approach is based on a Kalman filter in order to model time-series data and extreme value theory is used to compute a novelty measure in a principled manner. The proposed approach is shown to be effective via experiments on several real-world data sets.

The novelty detection approach for different degrees of class imbalance

We show that the novelty detection approach is a viable solution to the class imbalance and examine which approach is suitable for different degrees of imbalance. In experiments using SVM-based classifiers, when the imbalance is extreme, novelty detectors are more accurate than balanced and unbalanced binary classifiers. However, with a relatively moderate imbalance, balanced binary classifiers should be employed. In addition, novelty detectors are more effective when the classes have a non-symmetrical class relationship.

Application of LVQ to novelty detection using outlier training data

We propose to use learning vector quantization (LVQ) in novelty detection where a few outliers exist in training data. The codebook update of original LVQ is modified and the scheme to determine a threshold for each codebook is proposed. Experimental results on artificial and real-world problems are quite promising.