• Journal of the Korean Statistical Society
• /
• v.23 no.2
• /
• pp.403-420
• /
• 1994

An economic design of the $\bar{X}-R$ chart using variable sample size (VSS) scheme is proposed in this paper. In this design the sample size at each sampling time changes according to the values of the previous two sample statistics, sample mean and range. The VSS scheme uses large sample if the sample statistics appear near inside the control limits and smaller sample otherwise. The set of process parameters, such as the sampling interval, control limits and the sample sizes, are chosen to minimize the expected cost per hour. The efficiency of the VSS scheme is compared to the fixed sample size one for cases where there is multiple of assignable causes. Percent reductions of the expected cost in the VSS design are calculated for some given sets of cost parameters. It is shown that the VSS scheme improves the confidence of the procedure and performs statistically better in terms of the number of false alarms and the average time to signal, respectively.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1557-1564
• /
• 2017

We take genomic sequences of high-dimensional low sample size (HDLSS) without ordering of response categories into account. When constructing an appropriate test statistics in this model, the classical multivariate analysis of variance (MANOVA) approach might not be useful owing to very large number of parameters and very small sample size. For these reasons, we present a pseudo marginal model based upon the Gini-Simpson index estimated via Bayesian approach. In view of small sample size, we consider the permutation distribution by every possible n! (equally likely) permutation of the joined sample observations across G groups of (sizes $n_1,{\ldots}n_G$). We simulate data and apply false discovery rate (FDR) and positive false discovery rate (pFDR) with associated proposed test statistics to the data. And we also analyze real SARS data and compute FDR and pFDR. FDR and pFDR procedure along with the associated test statistics for each gene control the FDR and pFDR respectively at any level ${\alpha}$ for the set of p-values by using the exact conditional permutation theory.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.7A
• /
• pp.696-701
• /
• 2006

In this paper, we analyze the performance of double-dwell hybrid initial acquisition in DS-UWB system via detection, miss, false alarm probabilities and mean acquisition time. In the analysis, we consider the effect of the acquisition sequence, and deployment scenario of the abundant multipath components over the small coverage of the piconet in DS-UWB system. Based on the simulation, we obtain various performance on the mean acquisition time by varying the parameters, such as the total number of hypotheses to be searched, subgroup size, and dwell time. Then, we suggest the optimum parameter set for the initial acquisition in DS-UWB system.

• Communications for Statistical Applications and Methods
• /
• v.23 no.6
• /
• pp.445-466
• /
• 2016

Nonparametric Bayesian methods have seen rapid and sustained growth over the past 25 years. We present a gentle introduction to the methods, motivating the methods through the twin perspectives of consistency and false consistency. We then step through the various constructions of the Dirichlet process, outline a number of the basic properties of this process and move on to the mixture of Dirichlet processes model, including a quick discussion of the computational methods used to fit the model. We touch on the main philosophies for nonparametric Bayesian data analysis and then reanalyze a famous data set. The reanalysis illustrates the concept of admissibility through a novel perturbation of the problem and data, showing the benefit of shrinkage estimation and the much greater benefit of nonparametric Bayesian modelling. We conclude with a too-brief survey of fancier nonparametric Bayesian methods.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.85-94
• /
• 2024

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.508-524
• /
• 2006

We present our experience of combining, in a realistic setting, a static analyzer with a statistical analysis. This combination is in order to reduce the inevitable false alarms from a domain-unaware static analyzer. Our analyzer named Airac(Array Index Range Analyzer for C) collects all the true buffer-overrun points in ANSI C programs. The soundness is maintained, and the analysis' cost-accuracy improvement is achieved by techniques that static analysis community has long accumulated. For still inevitable false alarms (e.g. Airac raised 970 buffer-overrun alarms in commercial C programs of 5.3 million lines and 737 among the 970 alarms were false), which are always apt for particular C programs, we use a statistical post analysis. The statistical analysis, given the analysis results (alarms), sifts out probable false alarms and prioritizes true alarms. It estimates the probability of each alarm being true. The probabilities are used in two ways: 1) only the alarms that have true-alarm probabilities higher than a threshold are reported to the user; 2) the alarms are sorted by the probability before reporting, so that the user can check highly probable errors first. In our experiments with Linux kernel sources, if we set the risk of missing true error is about 3 times greater than false alarming, 74.83% of false alarms could be filtered; only 15.17% of false alarms were mixed up until the user observes 50% of the true alarms.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.61-68
• /
• 2015

In recent times, the median filtering (MF) detector as a forensic tool for the recovery of forgery images' processing history has concerned broad interest. For the classification of MF image, MF detector should be designed with smaller feature set and higher detection ratio. This paper presents a novel method for the detection of MF in altered images. It is transformed from BMP to several kinds of MF image by the median window size. The difference distribution values are computed according to the window sizes and then the values construct the feature set same as the MF window size. For the MF detector, the feature set transformed to the model specification which is computed using latent growth modeling (LGM). Through experiments, the test image is classified by the discriminant into two classes: the true positive (TP) and the false negative (FN). It confirms that the proposed algorithm is to be outstanding performance when the minimum distance average is 0.119 in the confusion of TP and FN for the effectivity of classification.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.1
• /
• pp.123-128
• /
• 2018

In this paper, we propose a multi-vehicle object detection algorithm using feature point matching that tracks efficient vehicle objects. The proposed algorithm extracts the feature points of the vehicle using the FAST algorithm for efficient vehicle object tracking. And True if the feature points are included in the image segmented into the 5X5 region. If the feature point is not included, it is processed as False and the corresponding area is blacked to remove unnecessary object information excluding the vehicle object. Then, the post processed area is set as the maximum search window size of the vehicle. And A minimum search window using the outermost feature points of the vehicle is set. By using the set search window, we compensate the disadvantages of the search window size of mean-shift algorithm and track vehicle object. In order to evaluate the performance of the proposed method, SIFT and SURF algorithms are compared and tested. The result is about four times faster than the SIFT algorithm. And it has the advantage of detecting more efficiently than the process of SUFR algorithm.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.1
• /
• pp.3-10
• /
• 2017

Counting Bloom filters (CBFs) have been popularly used in many network algorithms and applications for the membership queries of dynamic sets, since CBFs can provide delete operations, which are not provided in a standard 1-bit vector Bloom filter. However, because of the counting functions, a CBF can have overflows and accordingly false negatives. CBFs composed of 4-bit counters are generally used, but the 4-bit CBF wastes memory spaces by allocating 4 bits for every counter. In this paper, we propose a simple alternative of a 4-bit CBF named ternary Bloom filter (TBF). In the proposed TBF structure, if two or more elements are mapped to a counter in programming, the counters are not used for insertion or deletion operations any more. When the TBF consumes the same amount of memory space as a 4-bit CBF, it is shown through simulation that the TBF provides a better false positive rate than the CBF as well as the TBF does not generate false negatives.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.2
• /
• pp.385-395
• /
• 2018

With the development of Internet, cyber attack has become a major threat. To detect cyber attacks, intrusion detection system(IDS) has been widely deployed. But IDS has a critical weakness which is that it generates a large number of false alarms. One of the promising techniques that reduce the false alarms in real time is machine learning. However, there are problems that must be solved to use machine learning. So, many machine learning approaches have been applied to this field. But so far, researchers have not focused on features. Despite the features of IDS alerts are important for performance of model, the approach to feature is ignored. In this paper, we propose new feature set which can improve the performance of model and can be extracted from a single alarm. New features are motivated from security analyst's know-how. We trained and tested the proposed model applied new feature set with real IDS alerts. Experimental results indicate the proposed model can achieve better accuracy and false positive rate than SVM model with ordinary features.