Hindawi Publishing CorporationAbstract and Applied AnalysisVolume 2013, Article ID 524720, 2 pageshttp://dx.doi.org/10.1155/2013/524720
EditorialArtificial Intelligence and Data Mining:Algorithms and Applications
Jianhong (Cecilia) Xia,1 Fuding Xie,2 Yong Zhang,3 and Craig Caulfield4
1 Curtin University, Perth, WA, Australia2 School of Urban and Environmental Sciences, Liaoning Normal University, Dalian, China3 School of Computer and Information Technology, Liaoning Normal University, Dalian, China4 Edith Cowan University, Perth, WA, Australia
Correspondence should be addressed to Jianhong (Cecilia) Xia; [email protected]
Artificial intelligence and data mining techniques have beenused in many domains to solve classification, segmentation,association, diagnosis, and prediction problems. The overallaim of this special issue is to open a discussion amongresearchers actively working on algorithms and applications.The issue covers a wide variety of problems for computationalintelligence, machine learning, time series analysis, remotesensing image mining, and pattern recognition. After a rig-orous peer review process, 20 papers have been selected from38 submissions. The accepted papers in this issue addressedthe following topics: (i) advanced artificial intelligence anddata mining techniques; (ii) computational intelligence indynamic and uncertain environments; (iii) machine learningon massive datasets; (iv) time series data analysis; (v) Spatialdata mining: algorithms and applications.
Among them, there are six papers on new algorithmmodel design and optimisation. In “Dictionary learning basedon nonnegative matrix factorization using parallel coordinatedescent” by Z. Tang et al., the authors propose a novelmethod for learning a nonnegative, overcomplete dictionaryfor sparse representation of nonnegative signals. In “A cost-sensitive ensemble method for class-imbalanced datasets” byY. Zhang and D. Wang, a cost-sensitive ensemble methodis developed to solve imbalanced data classification. Theproposed method is based on cost-sensitive support vectormachine (SVM) and query by committee (QBC). In “Visiontarget tracker based on incremental dictionary learning andglobal and local classification” by Y. Yang et al., a robust
global and local classification algorithm for visual targettracking in uncertain environment is suggested based onsparse representation. In “Analysis of similarity/dissimilarityof DNA sequences based on chaos game representation” by W.Deng and Y. Luan, the authors construct three kinds of CGRspaces and describe a DNA sequence by CGR-walk model.As an application, the authors compare the similarity/dis-similarity of exon-1 of 𝛽-globin genes for nine species. In“A real-valued negative selection algorithm based on grid foranomaly detection” by R. Zhang et al., a GB-RNSA algorithmis proposed for anomaly detection. In “An enhanced Wu-Huberman algorithm with pole point selection strategy” by Y.Sun and S. Ding, a novel pole point selection strategy for theWu-Huberman algorithm is developed to filter pole points byintroducing a sparse rate.
Several authors deal with different aspects of time seriesanalysis. In “Piecewise trend approximation: a ratio-based timeseries representation” by J. Dan et al., a time series repre-sentation PTA is developed to improve the efficiency oftime series data mining in high dimensional large databases.In “A dynamic fuzzy cluster algorithm for time series” byM. Ji et al., a dynamic fuzzy cluster (DFC) is proposedbased on improved a Fuzzy C-Means (FCM) algorithm andkey points. The proposed algorithm works by determiningthose time series whose class labels are vague and furtherpartitions them into different clusters over time. In “A newstrategy for short-term load forecasting” by Y. Yang et al., ahybrid model based on the seasonal ARIMA model and BP
2 Abstract and Applied Analysis
neural network is presented to improve the short-term loadforecasting accuracy.
Papers collected in this special issue also focus on spatialdata mining: algorithms and applications. In “Ecologicalvulnerability assessment integrating the spatial analysis tech-nology with algorithms: a case of the wood-grass ecotone ofNortheast China” by Z. Qiao et al., an assessment model ofecological vulnerability is developed using the analyticalhierarchy process and a spatial analysis method. In “Algo-rithms and applications in grass growth monitoring” by J. Liuet al., a double logistic function-fitting algorithm is usedto retrieve phenophases for grasslands in Northern Chinafrom a consistently processed Moderate Resolution ImagingSpectroradiometer (MODIS) dataset, and the accuracy ofthe satellite-based estimates is assessed using field phenologyobservations. Results show that the proposed method isvalid for accurately identifying vegetation phenology. In“The sustainable island development evaluation model and itsapplication based on the nonstructural decision fuzzy set” byQ.Wang et al., the authors discuss and establish a sustainabledevelopment indicator systemandmodel and adopt a entropymethod and the nonstructural decision fuzzy set theoreticalmodel to determine the weight of the evaluating indicators.In “Spatiotemporal simulation of tourist town growth basedon the cellular automata model: the case of Sanpo town inHebei province” by J. Yang et al., the authors use a tourismurbanization growth model to simulate and predict thespatiotemporal growth of Sanpo town in Hebei province. In“Model for the assessment of seawater environmental qualitybased on multiobjective variable fuzzy set theory” by L. Ke andH. Zhou, a model based on a multiobjective variable fuzzyset theory is presented to evaluate seawater environmentalquality. In “Seismic design value evaluation based on checkingrecords and site geological conditions using artificial neuralnetworks” by T. Kerh et al., several improved computationalneural network models are proposed to evaluate seismicdesign values based on checking records and site geologicalconditions.
Finally, other applied problems are also considered. Forexample, in “Crude oil price prediction based on a dynamiccorrecting support vector regression machine” by L. Shu-rongand G. Yu-lei, a new accurate method of predicting crude oilprices is presented, which is based on an 𝜀-support vectorregression (𝜀-SVR)machinewith a dynamic correction factorovercoming forecasting errors. The authors also propose ahybrid RNA genetic algorithm (HRGA) with the positiondisplacement idea of bare bones particle swarm optimization(PSO) changing the mutation operator. In “Mathematicalmodel based on BP neural network algorithm for the deflectionidentification of storage tank and calibration of tank capacitychart” by C. Li et al., the proposed method has betterperformance in terms of tank capacity chart calibrationaccuracy compared with other existing approaches and hasa strong practical significance. In “A study on coastlineextraction and its trend based on remote sensing image datamining” by Y. Zhang et al., data mining theory is appliedto the pretreatment of remote sensing images. In “Land usepatch generalization based on semantic priority” by J. Yanget al., the authors establish a neighborhood analysis model
and patch features and simplify the narrow zones and thefeature sidelines. In “Nonstationary INAR(1) process with qth-order autocorrelation innovation” by K. Yu et al., an integer-valued random walk process with qth-order autocorrelationis discussed.
Acknowledgments
The guest editors of this special issue would like to expresstheir thanks to the authors who have submitted papers forconsideration and the referees of the submitted papers.
![Nonnegative Tensor Factorization for Source Separation of ... · [Rafii, Liutkus, & Pardo 2014] NMF can handle many types of repetition: Method. Nonnegative tensor factorization](https://static.documents.pub/doc/80x56/5f73cd6a4279576c155c076c/nonnegative-tensor-factorization-for-source-separation-of-raii-liutkus.jpg)
![Some Recent Advances in Nonnegative Matrix Factorization and … · 2013. 11. 21. · [GG10] G., Glineur, Using Underapproximations for Sparse Nonnegative Matrix Factorization, Pattern](https://static.documents.pub/doc/80x56/5fe39a16fd4e890a280aa921/some-recent-advances-in-nonnegative-matrix-factorization-and-2013-11-21-gg10.jpg)
