Piecewise regression model construction with sample efficient regression tree (SERT) and applications to semiconductor yield analysis

Forward stepwise regression analysis selects critical attributes all the way with the same set of data. Regression analysis is, however, not capable of splitting data to construct piecewise regression models. Regression trees have been known to be an effective data mining tool for constructing piecewise models by iteratively splitting data set and selecting attributes into a hierarchical tree model. However, the sample size reduces sharply after few levels of data splitting causing unreliable attribute selection. In this research, we propose a method to effectively construct a piecewise regression model by extending the sample-efficient regression tree (SERT) approach that combines the forward selection in regression analysis and the regression tree methodologies. The proposed method attempts to maximize the usage of the dataset's degree of freedom and to attain unbiased model estimates at the same time. Hypothetical and actual semiconductor yield-analysis cases are used to illustrate the method and its effective search for critical factors to be included in the dataset's underlying model.     

Affect, generalization, and the perception of risk.

Investigated the role of affect in judgments of risk in 4 experiments. 557 Ss were recruited on college campuses and read paragraphs modeled after newspaper reports that described fatal or nonfatal accidents or (Exp III) positive events. Ss were later asked to estimate the chances of specific fatal or nonfatal accidents happening to them and/or to the population in general. Experimental manipulations of affect induced by report of a tragic event produced a pervasive increase in Ss' estimates of the frequency of many risks and other undesirable events. Contrary to expectation, the effect was independent of the similarity between the report and the estimated risk: An account of a fatal stabbing did not increase the frequency estimate of homicide more than the estimates of unrelated risks such as natural hazards. An account of a happy event that created positive affect produced a comparable global decrease in judged frequency of risks. (12 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Tight Bounds for Distributed Minimum-Weight Spanning Tree Verification

This paper introduces the notion of distributed verification without preprocessing. It focuses on the Minimum-weight Spanning Tree (MST) verification problem and establishes tight upper and lower bounds for the time and message complexities of this problem. Specifically, we provide an MST verification algorithm that achieves simultaneously $\tilde{O}(m)$ messages and $\tilde{O}(\sqrt{n} + D)$ time, where m is the number of edges in the given graph G, n is the number of nodes, and D is G’s diameter. On the other hand, we show that any MST verification algorithm must send $\tilde{\varOmega}(m)$ messages and incur $\tilde{\varOmega}(\sqrt{n} + D)$ time in worst case. Our upper bound result appears to indicate that the verification of an MST may be easier than its construction, since for MST construction, both lower bounds of $\tilde{\varOmega}(m)$ messages and $\tilde{\varOmega}(\sqrt{n} + D)$ time hold, but at the moment there is no known distributed algorithm that constructs an MST and achieves simultaneously $\tilde{O}(m)$ messages and $\tilde{O}(\sqrt{n} + D)$ time. Specifically, the best known time-optimal algorithm (using ${\tilde{O}}(\sqrt {n} + D)$ time) requires O(m+n ^3/2) messages, and the best known message-optimal algorithm (using ${\tilde{O}}(m)$ messages) requires O(n) time. On the other hand, our lower bound results indicate that the verification of an MST is not significantly easier than its construction.     

Labeling Schemes for Dynamic Tree Networks

Distance labeling schemes are composed of a marker algorithm for labeling the vertices of a graph with short labels, coupled with a decoder algorithm allowing one to compute the distance between any two vertices directly from their labels (without using any additional information). As applications for distance labeling schemes concern mainly large and dynamically changing networks, it is of interest to study distributed dynamic labeling schemes. The current paper considers the problem on dynamic trees, and proposes efficient distributed schemes for it. The paper first presents a labeling scheme for distances in the dynamic tree model, with amortized message complexity O(log² n) per operation, where n is the size of the tree at the time the operation takes place. The protocol maintains O(log² n) bit labels. This label size is known to be optimal even in the static scenario. A more general labeling scheme is then introduced for the dynamic tree model, based on extending an existing static tree labeling scheme to the dynamic setting. The approach fits a number of natural tree functions, such as distance, separation level, and flow. The main resulting scheme incurs an overhead of an O(log n) multiplicative factor in both the label size and amortized message complexity in the case of dynamically growing trees (with no vertex deletions). If an upper bound on n is known in advance, this method yields a different tradeoff, with an O(log² n/log log n) multiplicative overhead on the label size but only an O(log n/log log n) overhead on the amortized message complexity. In the fully dynamic model the scheme also incurs an increased additive overhead in amortized communication, of O(log² n) messages per operation.     

Labeling Schemes for Tree Representation

This paper deals with compact label-based representations for trees. Consider an n-node undirected connected graph G with a predefined numbering on the ports of each node. The all-ports tree labeling ℒ _all gives each node v of G a label containing the port numbers of all the tree edges incident to v. The upward tree labeling ℒ _up labels each node v by the number of the port leading from v to its parent in the tree. Our measure of interest is the worst case and total length of the labels used by the scheme, denoted M _up (T) and S _up (T) for ℒ _up and M _all (T) and S _all (T) for ℒ _all . The problem studied in this paper is the following: Given a graph G and a predefined port labeling for it, with the ports of each node v numbered by 0,…,deg (v)−1, select a rooted spanning tree for G minimizing (one of) these measures. We show that the problem is polynomial for M _up (T), S _up (T) and S _all (T) but NP-hard for M _all (T) (even for 3-regular planar graphs). We show that for every graph G and port labeling there exists a spanning tree T for which S _up (T)=O(nlog log n). We give a tight bound of O(n) in the cases of complete graphs with arbitrary labeling and arbitrary graphs with symmetric port labeling. We conclude by discussing some applications for our tree representation schemes. A preliminary version of this paper has appeared in the proceedings of the 7th International Workshop on Distributed Computing (IWDC), Kharagpur, India, December 27–30, 2005, as part of Cohen, R. et al.: Labeling schemes for tree representation. In: Proceedings of 7th International Workshop on Distributed Computing (IWDC), Lecture Notes of Computer Science, vol. 3741, pp. 13–24 (2005). R. Cohen supported by the Pacific Theaters Foundation. P. Fraigniaud and D. Ilcinkas supported by the project “PairAPair” of the ACI Masses de Données, the project “Fragile” of the ACI Sécurité et Informatique, and by the project “Grand Large” of INRIA. A. Korman supported in part by an Aly Kaufman fellowship. D. Peleg supported in part by a grant from the Israel Science Foundation.     

General compact labeling schemes for dynamic trees

Let F be a function on pairs of vertices. An F-labeling scheme is composed of a marker algorithm for labeling the vertices of a graph with short labels, coupled with a decoder algorithm allowing one to compute F(u, v) for any two vertices u and v directly from their labels. As applications for labeling schemes concern mainly large and dynamically changing networks, it is of interest to study distributed dynamic labeling schemes. This paper investigates labeling schemes for dynamic trees. We consider two dynamic tree models, namely, the leaf-dynamic tree model in which at each step a leaf can be added to or removed from the tree and the leaf-increasing tree model in which the only topological event that may occur is that a leaf joins the tree. A general method for constructing labeling schemes for dynamic trees (under the above mentioned dynamic tree models) was previously developed in Korman et al. (Theory Comput Syst 37:49–75, 2004). This method is based on extending an existing static tree labeling scheme to the dynamic setting. This approach fits many natural functions on trees, such as distance, separation level, ancestry relation, routing (in both the adversary and the designer port models), nearest common ancestor etc.. Their resulting dynamic schemes incur overheads (over the static scheme) on the label size and on the communication complexity. In particular, all their schemes yield a multiplicative overhead factor of Ω(log n) on the label sizes of the static schemes. Following (Korman et al., Theory Comput Syst 37:49–75, 2004), we develop a different general method for extending static labeling schemes to the dynamic tree settings. Our method fits the same class of tree functions. In contrast to the above paper, our trade-off is designed to minimize the label size, sometimes at the expense of communication. Informally, for any function k(n) and any static F-labeling scheme on trees, we present an F-labeling scheme on dynamic trees incurring multiplicative overhead factors (over the static scheme) of on the label size and on the amortized message complexity. In particular, by setting for any , we obtain dynamic labeling schemes with asymptotically optimal label sizes and sublinear amortized message complexity for the ancestry relation, the id-based and label-based nearest common ancestor relation and the routing function. Supported in part at the Technion by an Aly Kaufman fellowship.     

Automated Meta-Control for Adaptable Real-Time Software

The software meta-controller is an online agent responsible for dynamically adapting an application's software configuration, e.g. altering operational modes and migrating tasks, to best accommodate varying runtime circumstances. In distributed real-time applications such adaptations must be carried out in a manner which maintains the schedulability of all critical tasks while maximizing some notion of system value for all other tasks. For large-scale real-time applications, considering all possible adaptations at the task-level is computationally intractable. This paper presents an automated aggregate approach to software meta-control, appropriate for large-scale distributed real-time systems. The aggregate automated meta-control problem is still NP-hard, but it has very practical approximate solutions. Introduced, here, are two very-effective approximation algorithms, QDP and GG, with very reasonable polynomial time complexity. Both algorithms also provide us with upper bounds for optimum system values, useful for deriving absolute, albeit somewhat pessimistic, measures of actual performance. Extensive Monte Carlo analysis is used to illustrate that expected performance for both algorithms is generally suboptimal by no more than a few percent. Our flexible software meta-control model is also shown to be readily applied to a wide range of time-sensitive applications.     

Development of adolescent reading comprehension in language 1 and language 2: A longitudinal analysis of constituent components.

This study investigated the relationship between reading comprehension development of 389 adolescents in their dominant language (Language 1 [L1], Dutch) and a foreign language (Language 2 [L2], English). In each consecutive year from Grades 8 through 10, a number of measurements were taken. Students' reading comprehension, their linguistic knowledge (vocabulary and grammar knowledge) and processing efficiency (speed of word recognition and sentence comprehension) in both languages, and their metacognitive knowledge about reading were assessed. The relative strengths of the effects of these components of reading were analyzed to distinguish among 3 hypotheses about the relationship between L1 and L2 reading comprehension: the transfer hypothesis, the threshold hypothesis, and the processing efficiency hypothesis. The transfer hypothesis predicts a strong relationship between L1 and L2 reading comprehension and a strong effect of metacognitive knowledge on L2 reading comprehension, whereas the threshold and processing efficiency hypotheses predict a more important role of language-specific knowledge and processing skills. Results support the transfer hypothesis, although language-specific knowledge and fluency also contribute to L2 reading performance. (PsycINFO Database Record (c) 2010 APA, all rights reserved)