We address the problem of monitoring and identification of correlated burst patterns in multi-stream time series databases.
We follow a two-step methodology: first we identify the burst sections in our data and subsequently we store them for easy
retrieval in an efficient in-memory index. The burst detection scheme imposes a variable threshold on the examined data and
takes advantage of the skewed distribution that is typically encountered in many applications. The detected bursts are compacted
into burst intervals and stored in an interval index. The index facilitates the identification of correlated bursts by performing
very efficient overlap operations on the stored burst regions. We present the merits of the proposed indexing scheme through
a thorough analysis of its complexity. We also manifest the real-time response of our burst indexing technique, and demonstrate
the usefulness of the approach for correlating surprising volume trading events using historical stock data of the NY stock
exchange. While the focus of this work is on financial data, the proposed methods and data-structures can find applications
for anomaly or novelty detection in telecommunication, network traffic and medical data. 相似文献
Abstract-In this paper we present a fast new fully dynamic algorithm for the st-mincut/max-flow problem. We show how this algorithm can be used to efficiently compute MAP solutions for certain dynamically changing MRF models in computer vision such as image segmentation. Specifically, given the solution of the max-flow problem on a graph, the dynamic algorithm efficiently computes the maximum flow in a modified version of the graph. The time taken by it is roughly proportional to the total amount of change in the edge weights of the graph. Our experiments show that, when the number of changes in the graph is small, the dynamic algorithm is significantly faster than the best known static graph cut algorithm. We test the performance of our algorithm on one particular problem: the object-background segmentation problem for video. It should be noted that the application of our algorithm is not limited to the above problem, the algorithm is generic and can be used to yield similar improvements in many other cases that involve dynamic change. 相似文献
Recent studies have employed simple linear dynamical systems to model trial-by-trial dynamics in various sensorimotor learning tasks. Here we explore the theoretical and practical considerations that arise when employing the general class of linear dynamical systems (LDS) as a model for sensorimotor learning. In this framework, the state of the system is a set of parameters that define the current sensorimotor transformation-the function that maps sensory inputs to motor outputs. The class of LDS models provides a first-order approximation for any Markovian (state-dependent) learning rule that specifies the changes in the sensorimotor transformation that result from sensory feedback on each movement. We show that modeling the trial-by-trial dynamics of learning provides a substantially enhanced picture of the process of adaptation compared to measurements of the steady state of adaptation derived from more traditional blocked-exposure experiments. Specifically, these models can be used to quantify sensory and performance biases, the extent to which learned changes in the sensorimotor transformation decay over time, and the portion of motor variability due to either learning or performance variability. We show that previous attempts to fit such models with linear regression have not generally yielded consistent parameter estimates. Instead, we present an expectation-maximization algorithm for fitting LDS models to experimental data and describe the difficulties inherent in estimating the parameters associated with feedback-driven learning. Finally, we demonstrate the application of these methods in a simple sensorimotor learning experiment: adaptation to shifted visual feedback during reaching. 相似文献
Examined the graduate school origins of authors of Journal of Counseling Psychology (JCP) articles in Volumes 15–28 to extend a previous analysis of Volumes 1–24 by the 3rd author et al (1969). Comparisons of the 2 14-yr periods reveal that some universities retained the same or similar ranks across both periods, some declined in importance as sources of authors, and others emerged as major sources of JCP authors. (6 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved) 相似文献
Changes occurring in the friction and wear mechanisms during a load-carrying capacity test, lubricated with cetane containing a carboxylic acid, were investigated. The changes in wear scar/track appearance and oxide coverage/composition were analyzed during every load stage.The main conclusions were as follows:
The breakdown in the protective oxide layer formed on the opposing steel surfaces was found to be the prerequisite for initiation of seizure.
The seizure load achieved during load-carrying capacity testing quantifies the ability of the test fluid to prevent transition to the adhesive wear regime.
The most severe surface damage was found to occur during the first few seconds after test initiation. Desorption of the adsorbed lubricant film and the subsequent removal of the naturally occurring thin oxide layer results in the initial period of adhesive wear.
Partial recovery to a state of acceptable friction occurs after the period of initial seizure. During this period, the surface coverage by the adsorption lubricant molecules and the oxide coverage are sufficient to prevent severe adhesive wear from occurring. Wear is primarily a combination of oxidative, abrasive, and fatigue wear (all possible in the regions of mixed friction and boundary lubrication).
Final lubricant breakdown and eventual seizure are initiated when the oxide removal rate exceeds the oxide formation rate resulting in severe adhesive wear followed by seizure.
Our goal in the present study was to understand how emoticons are used in text messaging and, in particular, how genders differed in the frequency and variety of emoticons used via this medium. Previous research has found small and sundry differences in emotive expression online suggesting that technology has closed the gender gap. However, the data collected in these studies were public. In this study, we collected real portions of private communications data from individuals’ smartphones over a 6-month period. SMS messages, in general, were not used very much overall, with only 4% of all messages containing at least one emoticon. Still, differences between genders manifested in the amount and variety of emoticons used. Females sent more messages with emoticons; however, surprisingly, males used a more diverse range of emoticons. 相似文献
In adding syntax to statistical machine translation, there is a tradeoff between taking advantage of linguistic analysis and allowing the model to exploit parallel training data with no linguistic analysis: translation quality versus coverage. A number of previous efforts have tackled this tradeoff by starting with a commitment to linguistically motivated analyses and then finding appropriate ways to soften that commitment. We present an approach that explores the tradeoff from the other direction, starting with a translation model learned directly from aligned parallel text, and then adding soft constituent-level constraints based on parses of the source language. We argue that in order for these constraints to improve translation, they must be fine-grained: the constraints should vary by constituent type, and by the type of match or mismatch with the parse. We also use a different feature weight optimization technique, capable of handling large amount of features, thus eliminating the bottleneck of feature selection. We obtain substantial improvements in performance for translation from Arabic to English. 相似文献
The purpose of this study was to review the distinction between formative- and reflective-indicator measurement models, articulate a set of criteria for deciding whether measures are formative or reflective, illustrate some commonly researched constructs that have formative indicators, empirically test the effects of measurement model misspecification using a Monte Carlo simulation, and recommend new scale development procedures for latent constructs with formative indicators. Results of the Monte Carlo simulation indicated that measurement model misspecification can inflate unstandardized structural parameter estimates by as much as 400% or deflate them by as much as 80% and lead to Type I or Type II errors of inference, depending on whether the exogenous or the endogenous latent construct is misspecified. Implications of this research are discussed. (PsycINFO Database Record (c) 2011 APA, all rights reserved) 相似文献
Nitrogen dioxide (NO2) removal efficiency of a biotrikling filter was evaluated under different operating conditions. Activated alumina (AA) was
used as the immobilization matrix for Thiobacillus denitrificans (T. denitrificans) in the biotrickling filter. Batch studies were conducted to find out the degradation kinetics of nitrate and nitrite for
a concentration range of 600–10,000 mg/L expressed as nitrogen. Nitrite exhibited maximum degradation rate followed by nitrate.
Electron acceptor in the form of NO2 gas showed least removal efficiency. Bio-kinetic parameters for T. denitrificans, by utilizing nitrate and nitrite as electron acceptors, were also evaluated. The μmax (Maximum specific growth rate) and YT (Yield coefficient) values for T. denitrificans in the presence of nitrate and nitrite were 1.03 h−1, 0.275 and 0.63 h−1, 0.1316 respectively. Column study was conducted to find the adsorption and desorption potential of activated alumina. The
adsorbed NO2 from AA could easily be desorbed using distilled water with an efficiency of 76±0.8%. Once fed batch studies were conducted
to evaluate the NO2 removal efficiency by a biotrickling filter. With an influent NO2 gas concentration of 2,735 ppm, the reactor could achieve a removal efficiency of 99% within 2 min from gas phase and within
96 h from the liquid phase, with an average biomass concentration of 200 mg/g of AA. The mechanism of NO2 gas removal in the biotrickling filter seems to be the dissolution of NO2 in water to form NO3−, conversion of NO3− to NO2−, and finally to N2 gas. 相似文献
Recent progress in both low pretilt and high pretilt defect-free C1 surface stabilized ferroelectric liquid crystal (SSFLC) devices for e-paper application is reviewed. First, by using numerical calculation to investigate the balance between surface azimuthal anchoring energy and bulk elastic energy within the confined chevron layer geometry of C1 and C2, we found it is possible to achieve a zigzag-free C1 state by low azimuthal anchoring alignment with a low pretilt angle. The critical azimuthal anchoring coefficient for defect-free C1 state is calculated. Its relationship with elastic constants, chevron angle, and surface topography effect are also discussed. Second, by using 5° oblique SiO deposition alignment, a defect-free, large memory angle, high contrast ratio, and bistable C1 SSFLC display, which has potential for electronic paper applications has also been developed. The electro-optical properties and bistability of this device have been investigated. Various aspects of defect control are also discussed. 相似文献