The detection of patterns in monitoring data of vital signs is of great importance for adequate bedside decision support in critical care. Currently used alarm systems, which are based on fixed thresholds and independ...
详细信息
The detection of patterns in monitoring data of vital signs is of great importance for adequate bedside decision support in critical care. Currently used alarm systems, which are based on fixed thresholds and independency assumptions, are not satisfactory in clinical practice. Time series techniques such as AR-models consider autocorrelations within the series, which can be used for pattern recognition in the data. For practical applications in intensive care the data analysis has to be automated. An important issue is the suitable choice of the model order which is difficult to accomplish online. In a comparative case-study we analyzed 34564 univariate time series of hemodynamic variables in critically ill patients by autoregressive models of different orders and compared the results of pattern detection. AR(2)-models seem to be most suitable for the detection of clinically relevant patterns, thus affirming that treating the data as independent leads to false alarms. Moreover, using AR(2)-models affords only short estimation periods. These findings for pattern detection in intensive care data are of medical importance as they justify a preselection of a model order, easing further automated statistical online analysis.
In the present paper, a novel method is provided to detect significant daily consumption patterns and to obtain scaling laws to predict consumption patterns for groups of homogeneous users. The first issue relies on t...
详细信息
In the present paper, a novel method is provided to detect significant daily consumption patterns and to obtain scaling laws to predict consumption patterns for groups of homogeneous users. The first issue relies on the use of Self-Organizing Map to gain insights about the initial assumption of distinct homogeneous consumption groups and to find additional clusters based on calendar dates. Non-dimensional pattern detection is performed on both residential and non-residential connections, with data provided by one-year measurements of a large-size smart water network placed in Naples (Italy). The second issue relies on the use of the variance function to explain the dependence of aggregated variance on the mean and on the number of aggregated users. Equations and related parameters' values are provided to predict mean dimensional daily patterns and variation bands describing water consumption of a generic set of aggregated users.
This paper presents a methodology which is able to: (1) synthesize a class of biomolecular sequences into a probabilistic pattern known as a random sequence for that class and (2) use the random sequence to search and...
详细信息
This paper presents a methodology which is able to: (1) synthesize a class of biomolecular sequences into a probabilistic pattern known as a random sequence for that class and (2) use the random sequence to search and detect subsequences pertaining to that class from a much longer sequence. The detection is achieved through an optimal matching of the random sequence against segments of the search sequence. Since the random sequence contains probabilistic characteristics of many sequences in the class, its comparison with search sequence segments is much more reliable than between two single sequences. The paper presents both the basic notion as well as an algorithm of the synthesis process. It also describes an experiment for detecting transfer RNA sequences embedded in a long DNA sequence derived from bovine mitochondrial genome. The successful detection is based on the optimal matching of the DNA sequence segments with the random sequence synthesized from 12 transfer RNA sequences. Copyright (C) 1996 pattern Recognition Society. Published by Elsevier Science
The two dimensional movement tracks of STAT92E(06346) mutant and two control strains (Oregon red (OR) and TM3) of Drosophila melonogaster were continuously observed with image processors. Subsequently Self-Organizing ...
详细信息
The two dimensional movement tracks of STAT92E(06346) mutant and two control strains (Oregon red (OR) and TM3) of Drosophila melonogaster were continuously observed with image processors. Subsequently Self-Organizing Map (SOM) was implemented to patterning of responding behaviors of the tested specimens. Movement behaviors were accordingly revealed in different strains and sex. SOM showed difference in degree of grouping in behaviors in different genotypes. Visualization through SOM further characterized the clusters of specimens with the variables regarding activities and spatial information. The study demonstrated that techniques in data mining in artificial neural networks could be a useful tool for analyzing complex behaviors induced by changes in genetic information. (c) 2006 Published by Elsevier B.V.
Most of the matched filtering techniques that have been used for pattern recognition have manipulated amplitude and phase information. Light, however, has another principal type of information that has not yet been us...
详细信息
Most of the matched filtering techniques that have been used for pattern recognition have manipulated amplitude and phase information. Light, however, has another principal type of information that has not yet been used for pattern recognition. mie propose a matched filtering technique which manipulates the polarization of light and shows the merits of using polarization information. The amplitude transmittance of input images is coded into the two-dimensional orientation distribution of linearly polarized light. A polarization spatial filter, which can change the light polarization two-dimensionally, is designed by considering the polarization distribution of the Fourier transform of an image to be detected which is polarization-coded. The proposed technique shows a better capacity to discriminate gray-scale images than do the conventional matched altering techniques.
A method of sampling and analysis is proposed to detect pattern parameters in plant populations from 2-dimensional data. The use of aerial photographs to find the coordinates of trees [Quercus rotundifolia] and the me...
详细信息
A method of sampling and analysis is proposed to detect pattern parameters in plant populations from 2-dimensional data. The use of aerial photographs to find the coordinates of trees [Quercus rotundifolia] and the measurements of plant-to-all-plants distances yields conditioned probability spectra which can be interpreted in terms of pattern parameters. Two artificial populations and a set of real data have been analyzed to test the accuracy of the method.
Existing distance measures of time series such as the euclidean distance, DTW, and EDR are inadequate in handling certain degrees of amplitude shifting and scaling variances of data items. We propose a novel distance ...
详细信息
Existing distance measures of time series such as the euclidean distance, DTW, and EDR are inadequate in handling certain degrees of amplitude shifting and scaling variances of data items. We propose a novel distance measure of time series, Spatial Assembling Distance (SpADe), that is able to handle noisy, shifting, and scaling in both temporal and amplitude dimensions. We further apply the SpADe to the application of streaming pattern detection, which is very useful in trend-related analysis, sensor networks, and video surveillance. Our experimental results on real time series data sets show that SpADe is an effective distance measure of time series. Moreover, high accuracy and efficiency are achieved by SpADe for continuous pattern detection in streaming time series.
This paper studies continuous pattern detection over large evolving graphs, which plays an important role in monitoring-related applications. The problem is challenging due to the large size and dynamic updates of gra...
详细信息
This paper studies continuous pattern detection over large evolving graphs, which plays an important role in monitoring-related applications. The problem is challenging due to the large size and dynamic updates of graphs, the massive search space of pattern detection and inconsistent query results on dynamic graphs. This paper first introduces a snapshot isolation requirement, which ensures that the query results come from a consistent graph snapshot instead of a mixture of partial evolving graphs. Second, we propose an SSD (single sink directed acyclic graph) plan friendly to vertex-centric-distributed graph processing frameworks. SSD plan can guide the message transformation and transfer among graph vertices, and determine the satisfaction of the pattern on graph vertices for the sink vertex. Third, we devise strategies for major steps in the SSD evaluation, including the location of valid messages to achieve snapshot isolation, AO-List to determine the satisfaction of transition rule over dynamic graph, and message-on-change policy to reduce outgoing messages. The experiments on billion-edge graphs using Giraph, an open source implementation of Pregel, illustrate the efficiency and effectiveness of our method.
We propose Fast Generalized Subset Scan (FGSS), a new method for detecting anomalous patterns in general categorical data sets. We frame the pattern detection problem as a search over subsets of data records and attri...
详细信息
We propose Fast Generalized Subset Scan (FGSS), a new method for detecting anomalous patterns in general categorical data sets. We frame the pattern detection problem as a search over subsets of data records and attributes, maximizing a nonparametric scan statistic over all such subsets. We prove that the nonparametric scan statistics possess a novel property that allows for efficient optimization over the exponentially many subsets of the data without an exhaustive search, enabling FGSS to scale to massive and high-dimensional data sets. We evaluate the performance of FGSS in three real-world application domains (customs monitoring, disease surveillance, and network intrusion detection), and demonstrate that FGSS can successfully detect and characterize relevant patterns in each domain. As compared to three other recently proposed detection algorithms, FGSS substantially decreased run time and improved detection power for massive multivariate data sets.
Data-agnostic management of today's virtualized and cloud IT infrastructures motivates statistical inference from unstructured or semi-structured data. We introduce a universal approach to the determination of sta...
详细信息
ISBN:
(纸本)9783901882517;9781467352291
Data-agnostic management of today's virtualized and cloud IT infrastructures motivates statistical inference from unstructured or semi-structured data. We introduce a universal approach to the determination of statistically relevant patterns in unstructured data, and then showcase its application to log data of a Virtual Center (VMware's virtualization management software). The premise of this study is that the unstructured data can be converted into events, where an event is defined by time, source, and a series of attributes. Every event can have any number of attributes but all must have a time stamp and optionally a source of origination (be it a server, a location, a business process, etc.) The statistical relevance of the data can then be made clear via determining the joint and prior probabilities of events using a discrete probability computation. From this we construct a Directed Virtual Graph with nodes representing events and the branches representing the conditional probabilities between two events. Employing information-theoretic measures the graphs are reduced to a subset of relevant nodes and connections. Moreover, the information contained in the unstructured data set is extracted from these graphs by detecting particular patterns of interest.
暂无评论