Prediction method for outliers over data stream based on sparse representation

2010 ◽  
Vol 30 (11) ◽  
pp. 2956-2958
Author(s):  
Xue-song XU ◽  
Ling-juan LI ◽  
Li-wei GUO
Keyword(s):  
Sparse Representation ◽  
Data Stream ◽  
Prediction Method

Software Defect Prediction Based on Cost-Sensitive Dictionary Learning

2019 ◽  
Vol 29 (09) ◽  
pp. 1219-1243 ◽  
Author(s):  
Hongyan Wan ◽  
Guoqing Wu ◽  
Mali Yu ◽  
Mengting Yuan
Keyword(s):  
Sparse Representation ◽  
Dictionary Learning ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Prediction Method ◽  
Elastic Net ◽  
Defect Prediction ◽  
Software Defect Prediction ◽  
Software Defect ◽  
Software Modules

Software defect prediction technology has been widely used in improving the quality of software system. Most real software defect datasets tend to have fewer defective modules than defective-free modules. Highly class-imbalanced data typically make accurate predictions difficult. The imbalanced nature of software defect datasets makes the prediction model classifying a defective module as a defective-free one easily. As there exists the similarity during the different software modules, one module can be represented by the sparse representation coefficients over the pre-defined dictionary which consists of historical software defect datasets. In this study, we make use of dictionary learning method to predict software defect. We optimize the classifier parameters and the dictionary atoms iteratively, to ensure that the extracted features (sparse representation) are optimal for the trained classifier. We prove the optimal condition of the elastic net which is used to solve the sparse coding coefficients and the regularity of the elastic net solution. Due to the reason that the misclassification of defective modules generally incurs much higher cost risk than the misclassification of defective-free ones, we take the different misclassification costs into account, increasing the punishment on misclassification defective modules in the procedure of dictionary learning, making the classification inclining to classify a module as a defective one. Thus, we propose a cost-sensitive software defect prediction method using dictionary learning (CSDL). Experimental results on the 10 class-imbalance datasets of NASA show that our method is more effective than several typical state-of-the-art defect prediction methods.

An adaptive prediction method based on data stream mining for future driving cycle of vehicle

2020 ◽  
pp. 095440702097315
Author(s):  
Cong Liu ◽  
Yong Chen ◽  
Li Zhao
Keyword(s):  
Data Stream ◽  
Prediction Accuracy ◽  
Transition Probability ◽  
Prediction Method ◽  
Current Control ◽  
Driving Cycle ◽  
Streaming Data ◽  
Data Stream Mining ◽  
Stream Mining ◽  
Driving Cycles

Due to complex and changeable driving cycles in urban roads, it is a challenging task for most of the current control strategies utilized in vehicles to adapt to the driving environment. At the same time, hardware requirements for storing and processing a massive amount of streaming data are increasing, which lead to excessive accumulated errors and high computational cost. To deal with this problem, an innovative prediction method, which is based on Markov chain and data stream mining, is proposed to predict the future driving cycle of vehicles. State transition probability matrix is updated in real time with data stream mining technology, and every time a new record arrives, the expired record is replaced by the new arrived one in the memory, and both state division and the sizes of the sliding window can be adjusted adaptively based on prediction accuracy for the changing driving cycles. The results show that the proposed method is more suitable for predicting changing driving cycles, which is able to maintain better prediction accuracy than the traditional method. In addition, based on the proposed method, the memory space utilized for storing temporary records were saved largely, and the calculation resource required was reduce.

Selection of a leading edge noise prediction method for PNoise

2018 ◽  
pp. 214-223
Author(s):  
AM Faria ◽  
MM Pimenta ◽  
JY Saab Jr. ◽  
S Rodriguez
Keyword(s):  
Wind Turbine ◽  
Turbine Blades ◽  
Prediction Method ◽  
Leading Edge ◽  
Wind Farms ◽  
Broadband Noise ◽  
Turbulence Energy ◽  
Noise Prediction ◽  
Migration Routes ◽  
Turbulent Inflow

Wind energy expansion is worldwide followed by various limitations, i.e. land availability, the NIMBY (not in my backyard) attitude, interference on birds migration routes and so on. This undeniable expansion is pushing wind farms near populated areas throughout the years, where noise regulation is more stringent. That demands solutions for the wind turbine (WT) industry, in order to produce quieter WT units. Focusing in the subject of airfoil noise prediction, it can help the assessment and design of quieter wind turbine blades. Considering the airfoil noise as a composition of many sound sources, and in light of the fact that the main noise production mechanisms are the airfoil self-noise and the turbulent inflow (TI) noise, this work is concentrated on the latter. TI noise is classified as an interaction noise, produced by the turbulent inflow, incident on the airfoil leading edge (LE). Theoretical and semi-empirical methods for the TI noise prediction are already available, based on Amiet’s broadband noise theory. Analysis of many TI noise prediction methods is provided by this work in the literature review, as well as the turbulence energy spectrum modeling. This is then followed by comparison of the most reliable TI noise methodologies, qualitatively and quantitatively, with the error estimation, compared to the Ffowcs Williams-Hawkings solution for computational aeroacoustics. Basis for integration of airfoil inflow noise prediction into a wind turbine noise prediction code is the final goal of this work.

Sign in / Sign up

Export Citation Format

Share Document