Zeev Barzily | ORT Braude College (original) (raw)

Papers by Zeev Barzily

Springer eBooks, Aug 10, 2006

A method for assessing cluster stability is presented in this paper. We hypothesize that if one u... more A method for assessing cluster stability is presented in this paper. We hypothesize that if one uses a “consistent” clustering algorithm to partition several independent samples then the clustered samples should be identically distributed. We use the two sample energy test approach for analyzing this hypothesis. Such a test is not very efficient in the clustering problems because outliers in the samples and limitations of the clustering algorithms heavily contribute to the noise level. Thus, we repeat calculating the value of the test statistic many times and an empirical distribution of this statistic is obtained. We choose the value of the “true” number of clusters as the one which yields the most concentrated distribution. Results of the numerical experiments are reported.

Naval Research Logistics Quarterly, Dec 1, 1976

Journal of Statistical Planning and Inference, 1981

Abstract : Several statistical methods--principal component analysis, orthogonal factor analysis,... more Abstract : Several statistical methods--principal component analysis, orthogonal factor analysis, classification, and clustering techniques--are tailored and combined into a system designed to digest high-dimensional vectors of data on operational readiness of Navy ships. Such data consist of large numbers of scores for individual ships assigned by experts. The purpose of the data reduction system is to provide a robust method of representing the data by a small number of scores that are meaningfully related to the original scores and that allow classification and clustering of the ships into homogeneous groups on relevant readiness scales. Simulated data drawn from mixtures of specified multivariate normal populations have been used to test the ability of the system to recover individual populations and to detect trends over time.

: Twenty-seven data sets (evaluations) of the MCCRES are analyzed from the point of view of the c... more : Twenty-seven data sets (evaluations) of the MCCRES are analyzed from the point of view of the category structure introduced by Brazily. Due to the specific designs of the evaluations, the statistical data are complicated by missing observations (nonapplicable requirements). This creates a problem of analyzing dependent bernoulli trials with different numbers of observations in different cells. A quasi-Bayesian model is introduced and estimators of the structural parameters are studied. (Author)

: This paper considers some practical aspects of an application of finite source (machine repair)... more : This paper considers some practical aspects of an application of finite source (machine repair) queueing models. Exact models for small calling populations are developed to investigate (a) transient effects; (b) the effect of assuming population items operate continuously, when, in fact, they may be idle a portion of the time; and (c) the effect of having population items with unequal failure rates, but assuming all items fail at the population average values. Implications from the small population models and from models which bound and approximate larger population sizes are discussed.

: The Marine Corps Combat Readiness Evaluation System (MCCRES) uses simulated combat to evaluate ... more : The Marine Corps Combat Readiness Evaluation System (MCCRES) uses simulated combat to evaluate the readiness of Marine Corps units. Resulting data provide vital inputs to command and management at all levels. The present paper proposes a new way to interpret results from MCCRES evaluations of infantry battalions. The basis is a categorization scheme for requirements which leads to an accurate and easily implementable method for orienting remedial training. (Author)

Abstract : It is desired to find the spares inventory level and number of repair channels necessa... more Abstract : It is desired to find the spares inventory level and number of repair channels necessary to guarantee a prespecified service level for a population of items that randomly fail and have exponential repair times. Steady state solutions are attainable from finite source queueing theory. This paper looks at transient effects and the speed of convergence to steady state. (Author)

Abstract : The Marine Corps Combat Readiness Evaluation System (MCCRES) is designed to evaluate t... more Abstract : The Marine Corps Combat Readiness Evaluation System (MCCRES) is designed to evaluate the state of readiness of Marine units. The present report describes MCCRES and suggests a method for analyzing the data obtained. The analysis determines the weaknesses and strengths of units, helps plan future evaluations, and serves as a tool for planning of training programs. (Author)

Abstract : The determination of a stopping rule for the detection of the time of an increase in t... more Abstract : The determination of a stopping rule for the detection of the time of an increase in the success probability of a sequence of independent Bernoulli trials is discussed. Both success probabilities are assumed unknown. A Bayesian approach is applied; the distribution of the location of the shift in the success probability is assumed geometric and the success probabilities are assumed to have a known joint prior distribution. The costs involved are penalties for late or early stoppings. The nature of the optimal dynamic programming solution is discussed and a procedure for obtaining a suboptimal stopping rule is determined. The results indicate that the detection procedure is quite effective. (Author)

Abstract : This paper studies the average speed of a fast car moving in a stream of slow vehicles... more Abstract : This paper studies the average speed of a fast car moving in a stream of slow vehicles on a two-lane highway. Arrivals of the slow vehicles are assumed to follow a Poisson process and the test car arrives independently of the slow vehicles. The highway is assumed to consist of sections in which passing is possible and sections in which passing is impossible; the lengths of these sections are random variables. Two passing mechanisms are studied: the first assumes that the duration of a passing maneuver is a random variable while in the second passings are instantaneous. (Author)

Abstract : The paper presents two numerical procedures. The first procedure determines the distri... more Abstract : The paper presents two numerical procedures. The first procedure determines the distribution of the time a customer spends in the waiting line, and the second determines the distribution of the length of a busy period. The service time of a customer may depend on the number of customers previously served in the busy period in which he is served. The results are obtained via recursive numerical integrations. (Author)

Abstract : This paper considers some practical aspects of an application of finite source (machin... more Abstract : This paper considers some practical aspects of an application of finite source (machine repair) queueing models. Exact models for small calling populations are developed to investigate (a) transient effects; (b) the effect of assuming population items operate continuously, when, in fact, they may be idle a portion of the time; and (c) the effect of having population items with unequal failure rates, but assuming all items fail at the population average values. Implications from the small population models and from models which bound and approximate larger population sizes are discussed.

We discuss a new approach for the proof of the Levy-Khintchine formula for the V -infinitely divi... more We discuss a new approach for the proof of the Levy-Khintchine formula for the V -infinitely divisible laws. Our proof is based on a description of the conditionally positive definite functions as positive functionals on semi-normed algebras of suitable test functions. In the framework of this approach we obtain integral representations of the common continuous positive definite functions and the logarithms of characteristic functions of the ordinary infinitely divisible and V -infinitely divisible distribution.

2014 Ninth International Conference on Availability, Reliability and Security, 2014

Stochastic modeling in image analysis aims to represent the images features in a small number of ... more Stochastic modeling in image analysis aims to represent the images features in a small number of parameters so as to recognize the source producing the images. In this paper we address the image segmentation problem in the case of significantly differ segments' sizes. A probabilistic model dealing the distribution of gray level in the observed image is based on the Gaussian Mixture Model identifying each component a segment. According to the general segmentation methodology for multi-modal gray levels images we presume that every region-of-interest attaches to a distinct substantial mode of the empirical distribution of gray levels. So, the number of the components is evaluated via a new resampling procedure involving the Expectation-Maximization algorithm used in order to estimate the significant histograms picks. Stable states of our model are associated within of the proposed method with the "true" segments quantities specified by the appropriate components' quantities. Numerical experiments demonstrate the high ability of the proposed method.

Journal of Applied Probability, 1979

An approximate model for the study of platoon formation on two-lane highways is discussed in deta... more An approximate model for the study of platoon formation on two-lane highways is discussed in detail. The model assumes that the two-lane highway is divided in each traffic direction into alternating road sections of fixed lengths. The passing in one type of section is unrestricted and the passing in the other one is prohibited. It is assumed that there are slow and fast vehicles on the highway and that inputs follow independent Poisson processes. The results include the distribution of the number of vehicles in a platoon and the average speed of a typical fast vehicle.

Gene, 2013

We have shown, in a previous paper, that tandem repeating sequences, especially triplet repeats, ... more We have shown, in a previous paper, that tandem repeating sequences, especially triplet repeats, play a very important role in gene evolution. This result led to the formulation of the following hypothesis: most of the genomic sequences evolved through everlasting acts of tandem repeat expansions with subsequent accumulation of changes. In order to estimate how much of the observed sequences have the repeat origin we describe the adaptation of a text segmentation algorithm, based on dynamic programming, to the mapping of the ancient expansion events. The algorithm maximizes the segmentation cost, calculated as the similarity of obtained fragments to the putative repeat sequence. In the first application of the algorithm to segmentations of genomic sequences, a significant difference between the natural sequences and the corresponding shuffled sequences is detected. The natural fragments are longer and more similar to the putative repeat sequences. As our analysis shows, the coding sequences allow for repeats only when the size of the repeated words is divisible by three. In contrast, in the non-coding sequences, all repeated word sizes are present. It was estimated, that in Escherichia coli K12 genome, about 35.5% of sequence can be detectably traced to original simple repeat ancestors. The results shed light on the genomic sequence organization, and strongly confirm the hypothesis about the crucial role of triplet expansions in gene origin and evolution.

Computers & Operations Research, 1974

Scope and purpose-This article deals with public urban bus transport. It is concerned with design... more Scope and purpose-This article deals with public urban bus transport. It is concerned with designing route systems and determining optimum bus frequencies. Because of the enormous number of possibilities for bus routes, manual techniques for selecting and evaluating them cannot possibly take account of all promising alternatives. Since public transport is necessarily, to some extent, competitive with auto travel, it is important that it optimize passenger convenience within fixed cost constraints. This convenience is expressed in terms of travel time and bus crowding. The algorithms and programs described here have been run on data from the City of Haifa, Israel and have provided useful results.

ijpam.eu

... Peter Soreanu1, Zeev (Vladimir) Volkovich2, Zeev Barzily3, Mati Golani4 § 1,2,3,4Department o... more ... Peter Soreanu1, Zeev (Vladimir) Volkovich2, Zeev Barzily3, Mati Golani4 § 1,2,3,4Department of Sfotware Engineering Ort Braude College PO Box ... at all the layers of the protocol stack: Application, Transport, Network, Data Link (mostly Media Access Control-MAC) and Physical ...