There exist two major problems in weighted closed sequential patterns mining. The first is that only the weights of items are considered and they ignore the time-interval information of data elements during the mining...
详细信息
There exist two major problems in weighted closed sequential patterns mining. The first is that only the weights of items are considered and they ignore the time-interval information of data elements during the mining process;the second is that the existing weighted closed sequential pattern mining algorithms need to scan the sequence database many times or to construct numerous intermediate databases. To address these problems, we propose a memory-based algorithm, MIWCSpan (Memory Indexing for Weighted Closed Sequential pattern mining), for weighted closed sequential pattern mining. In the algorithm, we define a novel sequence weighting approach to find more interesting sequential patterns. Both the weight of sequence items and the time-interval of the data elements are considered in this approach. Moreover, an improved index set based on time-interval, p-iidx, is defined. The structure is a set of triples which store the pointer pointing to the sequence containing p, the time-interval of p in the sequence and the position where p occurs. In the mining process, MIWCSpan first scans the sequence database to read the database into memory. Then it adopts the find-then-index technique recursively to find the items which can constitute a weighted closed sequential pattern and construct p-iidx for the possible weighted closed sequential pattern. At last, the algorithm uses the close-detecting to mine the weighted closed sequential patterns efficiently. The experimental results show that MIWCSpan is better on running time, and it has good scalability.
In high-dimensional data space, because the data is sparse inherently, clusters tend to exist in different subspaces, which makes the traditional methods no longer suitable for use. In this paper, we present SCFES, a ...
详细信息
In high-dimensional data space, because the data is sparse inherently, clusters tend to exist in different subspaces, which makes the traditional methods no longer suitable for use. In this paper, we present SCFES, a subspace clustering algorithm based on finding effective spaces. First, we define the effective dimension. By calculating relative entropy we remove redundancy dimensions which affect clustering accuracy. Second, according to the data distribution in the effective dimensions, we get the effective intervals through merging adjacent intervals. The effective space is composed of effective intervals. Third, we extend the density estimator based on undirected acyclic connected graph by using weight so as to estimate the expectation of existing clusters in the space, at the same time combine it with the monotonicity of the clustering criterion mentioned in the CLIQUE algorithm to prune candidates. Consequently we get the effective spaces. Finally, we adopt the structure of sibling tree to store all the effective spaces and use DBSCAN algorithm based on density to generate maximal subspace clusters in some effective spaces. Experimental results show that SCFES effectively finds arbitrarily shaped and positioned clusters in different subspaces. Meanwhile SCFES has better clustering quality and scalability.
Neuronal oscillations in the gamma frequency range and spikes have been reported in many cortical areas in the information processing, but the role of spikes play in cortical processing remains unclear. The aim of thi...
详细信息
Neuronal oscillations in the gamma frequency range and spikes have been reported in many cortical areas in the information processing, but the role of spikes play in cortical processing remains unclear. The aim of this study was to examine the role of kainate in the generation of oscillatory field activity at gamma frequency in the hippocampal slice prepared from rat brain, and to determine the phase relationship between spikes and gamma oscillations. The kainate induced large amplitude field population spiking activity, which is correlated linearly with the field gamma oscillations. The relationship between timing of spikes and the phase of gamma oscillation was determined by an analysis of circular statistics. Further analysis with Rayleigh test revealed that the relationship of phase-locking between spikes and gamma rhythm is of statistical significance. These data demonstrate that kainate sensitive neuronal networks within hippocampus are able to generate gamma oscillations which are modulated by large amplitude population spikes and phase-locking of spikes to the gamma rhythm suggest the role of memory enhancement in the presence of Kainate receptor activation.
With eXtensible Markup Language (XML) becoming more and more popular, to avoid the redundancy, XML schema design has become an important issue. So the normalization of XML is a hotspot in research field. Similar to re...
详细信息
ISBN:
(纸本)9781467329637
With eXtensible Markup Language (XML) becoming more and more popular, to avoid the redundancy, XML schema design has become an important issue. So the normalization of XML is a hotspot in research field. Similar to relational database, this paper is database based with the goal of eliminating the data redundancy, to study the concepts of path expression in Document Type Definition (DTD). In this paper, XML is extended with functional dependency (XFD) and multi-valued dependency (XMVD), which are fundamental to semantic specification. And make formalized definitions on XFD and XMVD;Based on the concepts of XML tree and data dependency, it provides the description of key and redundancy. On the condition of the coexistence of XFD and XMVD, it further proposes the terms to meet the fourth normal form (4XNF) and provides theorem to determine the XML document tree which meets the above terms without redundancy, and the sound of the 4XNF is proved by experiment.
In the environment of the Internet of Things for heat meter, insecurity of the object name service (ONS) is likely to lead to the leakage of user privacy. In order to solve this problem, an identity authentication alg...
详细信息
In the environment of the Internet of Things for heat meter, insecurity of the object name service (ONS) is likely to lead to the leakage of user privacy. In order to solve this problem, an identity authentication algorithm is proposed. First, the certificate authority may generate parameters of elliptic curve and its own public key and private key, and announce the parameters and its own public key, so that the registered users can inquire and use them. Second, the client registers at the certificate authority. The certificate authority will generate the public key of the client and the evidence of the client's private key which is signed by private key of the certificate authority. If the generated evidence of private key passes verification of the client, the client will generate its own private key. When a client sends a query request to an ONS server, the ONS server will authenticate identity of the client. If the client gets through the authentication, the ONS server will respond to the query request. The experimental result shows that this algorithm has high security and can avoid the ONS server providing query service for illegitimate client, so as to ensure the security of user privacy.
Heavy metals are considered to be hazardous pollutants with toxic effects on plant and/or human health. Different techniques and methods (e.g., AAS, ICP-MS, ICP-OES) have been utilized for trace metals determination i...
详细信息
ISBN:
(纸本)9781622762088
Heavy metals are considered to be hazardous pollutants with toxic effects on plant and/or human health. Different techniques and methods (e.g., AAS, ICP-MS, ICP-OES) have been utilized for trace metals determination in the laboratory, but they are characterized by high costs, complex operation and long time consuming. The demand of rapid on-site screening and assessment of agricultural land contaminate induced by heavy metal is highly desirable. This paper reported a fast, inexpensive electrochemical analysis method for the simultaneous determination of cadmium (Cd) and lead (Pb) in soil samples. A simplified soil extraction procedure, using 0.11 molL-1 acetic acid and a 1 h ultrasonic agitation, had been used to fulfill the requirements of field-based screening usage. A disposable sensor, incorporating a three-electrode configuration (working electrode, reference electrode and counter electrode), had been fabricated by low cost screen-printing technology. The surface of graphite carbon working electrode was judiciously modified by multiwalled carbon nanotubes(MWCNTs)/Nafion/bismuth coating. Coupled with the portable electrochemical instrument, trace detection of heavy metal ions had been carried out by square wave anodic stripping voltammetry (SWASV) technique. The electrode exhibited good sensibility and stability in the electrochemical measurement. Linear responses were obtained in the range from 1 to 80 μgL-1 for both the metal ions at a preconcentration time of 180s, with detection limits of 0.5 μgL-1 for Cd(II) and 0.8 μgL -1 for Pb(II), respectively. The relative standard deviation is 1.9% and 2.3% for 20 μgL-1 each of Cd(II) and Pb(II). Soil samples were assayed by the proposed process and compared against standard ICP-MS analysis, the results showed good agreement between methods.
Synchronization decay of resting state EEG has shown that cognitive dysfunction in Alzheimer's disease (AD) was relevant to a loss of functional connectivity in intermediate frequency bands. The new S estimator (N...
详细信息
Synchronization decay of resting state EEG has shown that cognitive dysfunction in Alzheimer's disease (AD) was relevant to a loss of functional connectivity in intermediate frequency bands. The new S estimator (NSE) proposed recently by us quantifies synchronization between neuronal signals at multiple *** paper meant to explore the behavior of synchronization of multichannel EEG in AD and healthy normal controls at rest, and preliminarily make clear the clinical significance of the NSE in AD *** (EEG) were recorded from 10 AD patients and 12 age-matched healthy normal controls (NC). NSE values were computed both across the all frequency band and separately in the delta, theta, alpha, beta (including beta1, beta2 and beta3), and gamma bands. The Mini-Mental Status Examination (MMSE) was used to assess the symptom severity of AD patients and *** values in the beta1 and beta2 bands were significantly lower in AD patients than in NC. NSE values in the alpha and beta1 bands were positively correlated with the MMSE scores in all participants (AD and NC). In AD patients, NSE values in the alpha, beta1 and beta2 bands were also positively correlated with MMSE *** results suggest that NSE values are a useful correlate of EEG synchronization in AD patients.
Recently, query processing based on uncertain data is becoming research focuses. Cluster-based superseding nearest neighbor (CSNN) query algorithm on uncertain data is proposed in this paper. We divide the instances o...
详细信息
Recently, query processing based on uncertain data is becoming research focuses. Cluster-based superseding nearest neighbor (CSNN) query algorithm on uncertain data is proposed in this paper. We divide the instances of each object into k clusters by applying the clustering algorithm k-means, and then store these clustered objects in R-tree like index structures. Ranked list will be retrieved through traversing R-tree, which could include instances, clusters, or objects. While unfolding the ranked list, the superseding graph G will be constructed gradually based on the superseding relationship. The final result sets will be found through pruning and validating the superseding graph G. Finally, the experimental results show that the algorithm is efficient and effective.
Neuronal oscillations in the theta frequency range and spikes have been reported in many cortical areas in the information processing, but the role of spikes play in cortical processing remains unclear. The aim of thi...
详细信息
Neuronal oscillations in the theta frequency range and spikes have been reported in many cortical areas in the information processing, but the role of spikes play in cortical processing remains unclear. The aim of this study was to examine the role of DHPG in the generation of oscillatory field activity at theta frequency in the medical septal diagonal band of Broca (MSDB) slice prepared from rat brain, and to determine the phase relationship between spikes and theta oscillations. The DHPG induced large amplitude field population spiking activity, which is correlated linearly with the field theta oscillations. The relationship between timing of spikes and the phase of theta oscillation was determined by an analysis of circular statistics. Further analysis with Rayleigh test revealed that the relationship of phase-locking between spikes and theta rhythm is of statistical significance. These data demonstrate that DHPG-sensitive neuronal networks within medial septum are able to generate theta oscillations which are modulated by large amplitude population spikes and phase-locking of spikes to the theta rhythm suggest the role of memory enhancement in the presence of mGluR1 activation.
Algorithms based on row enumeration always scan and construct conditional transposed tables, which increases the execution time and space cost. To address this problem, we adopt the DAG (Directed Acyclic Graph) to com...
详细信息
Algorithms based on row enumeration always scan and construct conditional transposed tables, which increases the execution time and space cost. To address this problem, we adopt the DAG (Directed Acyclic Graph) to compress the dataset to save the memory space. In DAG, each node is related to a rowid, and each two nodes have a corresponding directed edge which stores the common items of the two rowids. Each row is given an integer according to its coming order and the DAG follows that order. A directed acyclic graph records the relation between rows and items by doing AND(&) operation with the nodes' binary code of the edges. We also present DAGHDDM which is a new approach for mining frequent closed itemsets in high dimensional datasets. In this algorithm, we adopt the BitTable to compress the dataset firstly, and then construct DAG according to the BitTable. We increase the same items of the adjacent edges to implement pattern growth, traverse the DAG in reversal way and adopt a close-checking method to generate all frequent closed itemsets. It scans the dataset only once and does not generate candidate itemsets. The experimental results show that the proposed DAGHDDM algorithm can decrease the cost of time.
暂无评论