Low level feature detection in human vision

Influential models of edge detection have generally supposed that an edge is detected at peaks in the 1st derivative of the luminance profile, or at zero-crossings in the 2nd derivative. However, when presented with blurred triangle-wave images, observers consistently marked edges not at these locations, but at peaks in the 3rd derivative. This new phenomenon, termed ‘Mach edges’ persisted when a luminance ramp was added to the blurred triangle-wave. Modelling of these Mach edge detection data required the addition of a physiologically plausible filter, prior to the 3rd derivative computation. A viable alternative model was examined, on the basis of data obtained with short-duration, high spatial-frequency stimuli. Detection and feature-making methods were used to examine the perception of Mach bands in an image set that spanned a range of Mach band detectabilities. A scale-space model that computed edge and bar features in parallel provided a better fit to the data than 4 competing models that combined information across scale in a different manner, or computed edge or bar features at a single scale. The perception of luminance bars was examined in 2 experiments. Data for one image-set suggested a simple rule for perception of a small Gaussian bar on a larger inverted Gaussian bar background. In previous research, discriminability (d’) has typically been reported to be a power function of contrast, where the exponent (p) is 2 to 3. However, using bar, grating, and Gaussian edge stimuli, with several methodologies, values of p were obtained that ranged from 1 to 1.7 across 6 experiments. This novel finding was explained by appealing to low stimulus uncertainty, or a near-linear transducer.

Iterative subspace analysis based on feature line distance

Nearest feature line-based subspace analysis is first proposed in this paper. Compared with conventional methods, the newly proposed one brings better generalization performance and incremental analysis. The projection point and feature line distance are expressed as a function of a subspace, which is obtained by minimizing the mean square feature line distance. Moreover, by adopting stochastic approximation rule to minimize the objective function in a gradient manner, the new method can be performed in an incremental mode, which makes it working well upon future data. Experimental results on the FERET face database and the UCI satellite image database demonstrate the effectiveness.

Feature LDA:a supervised topic model for automatic detection of web API documentations from the web

Web APIs have gained increasing popularity in recent Web service technology development owing to its simplicity of technology stack and the proliferation of mashups. However, efficiently discovering Web APIs and the relevant documentations on the Web is still a challenging task even with the best resources available on the Web. In this paper we cast the problem of detecting the Web API documentations as a text classification problem of classifying a given Web page as Web API associated or not. We propose a supervised generative topic model called feature latent Dirichlet allocation (feaLDA) which offers a generic probabilistic framework for automatic detection of Web APIs. feaLDA not only captures the correspondence between data and the associated class labels, but also provides a mechanism for incorporating side information such as labelled features automatically learned from data that can effectively help improving classification performance. Extensive experiments on our Web APIs documentation dataset shows that the feaLDA model outperforms three strong supervised baselines including naive Bayes, support vector machines, and the maximum entropy model, by over 3% in classification accuracy. In addition, feaLDA also gives superior performance when compared against other existing supervised topic models.

Feature analysis of spammers in social networks with active honeypots:a case study of Chinese microblogging networks

In this poster we presented our preliminary work on the study of spammer detection and analysis with 50 active honeypot profiles implemented on Weibo.com and QQ.com microblogging networks. We picked out spammers from legitimate users by manually checking every captured user's microblogs content. We built a spammer dataset for each social network community using these spammer accounts and a legitimate user dataset as well. We analyzed several features of the two user classes and made a comparison on these features, which were found to be useful to distinguish spammers from legitimate users. The followings are several initial observations from our analysis on the features of spammers captured on Weibo.com and QQ.com. ¦The following/follower ratio of spammers is usually higher than legitimate users. They tend to follow a large amount of users in order to gain popularity but always have relatively few followers. ¦There exists a big gap between the average numbers of microblogs posted per day from these two classes. On Weibo.com, spammers post quite a lot microblogs every day, which is much more than legitimate users do; while on QQ.com spammers post far less microblogs than legitimate users. This is mainly due to the different strategies taken by spammers on these two platforms. ¦More spammers choose a cautious spam posting pattern. They mix spam microblogs with ordinary ones so that they can avoid the anti-spam mechanisms taken by the service providers. ¦Aggressive spammers are more likely to be detected so they tend to have a shorter life while cautious spammers can live much longer and have a deeper influence on the network. The latter kind of spammers may become the trend of social network spammer. © 2012 IEEE.

Independent component analysis and feature extraction of financial time series

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Dynamical embedding and feature extraction of electroencephalographic data

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Tissue transglutaminase:a mediator and predictor of chronic allograft nephropathy?

Background. The precise mechanisms underlying the development of chronic allograft nephropathy (CAN) and the associated renal fibrosis remain uncertain. The protein-crosslinking enzyme, tissue transglutaminase (tTg), has recently been implicated in renal fibrosis. Methods. We investigated the involvement of tTg and its crosslink product, [epsilon]-([gamma]-glutamyl) lysine, in 23 human kidney allografts during the early posttransplantation period and related these to changes of CAN that developed in 8 of them. Sequential biopsies were investigated using immunohistochemical, immunofluorescence, and in situ enzyme activity techniques. Results. From implantation, tTg (+266%) and [epsilon]-([gamma]-glutamyl) lysine crosslink (+256.3%) staining increased significantly (P <0.001) in a first renal biopsy performed within 3 months from transplantation. This was paralleled by elevated tTg in situ activity. The eight patients who developed CAN had further increases in immunostainable tTg (+197.2%, P <0.001) and [epsilon]-([gamma]-glutamyl) lysine bonds (+465%, P <0.01) that correlated with interstitial fibrosis (r=0.843, P =0.009 and r=0.622, P =0.05, respectively). The staining for both was predominantly located within the mesangium and the renal interstitium. Both implantation and first biopsies showed tTg and [epsilon]-([gamma]-glutamyl) lysine crosslinking levels in patients who developed CAN to be twice the levels of those with stable renal function. Cox regression analysis suggested the intensity of the early tTg staining was a better predictor of inferior allograft survival that other histologic markers (hazard ratio=4.48, P =0.04). Conclusions. tTg and [epsilon]-([gamma]-glutamyl) lysine crosslink correlated with the initiation and progression of scarring on sequential biopsies from renal-allograft recipients who experienced CAN. Elevated tTg may offer an early predictor of the development of CAN, whereas tTg manipulation may be an attractive therapeutic target

Rotation invariant iris feature extraction using Gaussian Markov random fields with non-separable wavelet

Rotation invariance is important for an iris recognition system since changes of head orientation and binocular vergence may cause eye rotation. The conventional methods of iris recognition cannot achieve true rotation invariance. They only achieve approximate rotation invariance by rotating the feature vector before matching or unwrapping the iris ring at different initial angles. In these methods, the complexity of the method is increased, and when the rotation scale is beyond the certain scope, the error rates of these methods may substantially increase. In order to solve this problem, a new rotation invariant approach for iris feature extraction based on the non-separable wavelet is proposed in this paper. Firstly, a bank of non-separable orthogonal wavelet filters is used to capture characteristics of the iris. Secondly, a method of Markov random fields is used to capture rotation invariant iris feature. Finally, two-class kernel Fisher classifiers are adopted for classification. Experimental results on public iris databases show that the proposed approach has a low error rate and achieves true rotation invariance. © 2010.

Feature Extraction for Classification in the Data Mining Process

Dimensionality reduction is a very important step in the data mining process. In this paper, we consider feature extraction for classification tasks as a technique to overcome problems occurring because of “the curse of dimensionality”. Three different eigenvector-based feature extraction approaches are discussed and three different kinds of applications with respect to classification tasks are considered. The summary of obtained results concerning the accuracy of classification schemes is presented with the conclusion about the search for the most appropriate feature extraction method. The problem how to discover knowledge needed to integrate the feature extraction and classification processes is stated. A decision support system to aid in the integration of the feature extraction and classification processes is proposed. The goals and requirements set for the decision support system and its basic structure are defined. The means of knowledge acquisition needed to build up the proposed system are considered.

A dynamic feature information model for integrated manufacturing planning and optimization

This paper presents a new, dynamic feature representation method for high value parts consisting of complex and intersecting features. The method first extracts features from the CAD model of a complex part. Then the dynamic status of each feature is established between various operations to be carried out during the whole manufacturing process. Each manufacturing and verification operation can be planned and optimized using the real conditions of a feature, thus enhancing accuracy, traceability and process control. The dynamic feature representation is complementary to the design models used as underlining basis in current CAD/CAM and decision support systems. © 2012 CIRP.

Visualisation of heterogeneous data with simultaneous feature saliency using Generalised Generative Topographic Mapping

Most machine-learning algorithms are designed for datasets with features of a single type whereas very little attention has been given to datasets with mixed-type features. We recently proposed a model to handle mixed types with a probabilistic latent variable formalism. This proposed model describes the data by type-specific distributions that are conditionally independent given the latent space and is called generalised generative topographic mapping (GGTM). It has often been observed that visualisations of high-dimensional datasets can be poor in the presence of noisy features. In this paper we therefore propose to extend the GGTM to estimate feature saliency values (GGTMFS) as an integrated part of the parameter learning process with an expectation-maximisation (EM) algorithm. The efficacy of the proposed GGTMFS model is demonstrated both for synthetic and real datasets.

Generalized KPCA by adaptive rules in feature space

Principal component analysis (PCA) is well recognized in dimensionality reduction, and kernel PCA (KPCA) has also been proposed in statistical data analysis. However, KPCA fails to detect the nonlinear structure of data well when outliers exist. To reduce this problem, this paper presents a novel algorithm, named iterative robust KPCA (IRKPCA). IRKPCA works well in dealing with outliers, and can be carried out in an iterative manner, which makes it suitable to process incremental input data. As in the traditional robust PCA (RPCA), a binary field is employed for characterizing the outlier process, and the optimization problem is formulated as maximizing marginal distribution of a Gibbs distribution. In this paper, this optimization problem is solved by stochastic gradient descent techniques. In IRKPCA, the outlier process is in a high-dimensional feature space, and therefore kernel trick is used. IRKPCA can be regarded as a kernelized version of RPCA and a robust form of kernel Hebbian algorithm. Experimental results on synthetic data demonstrate the effectiveness of IRKPCA. © 2010 Taylor & Francis.

A framework for automatic feature extraction from airborne light detection and ranging data

Recent advances in airborne Light Detection and Ranging (LIDAR) technology allow rapid and inexpensive measurements of topography over large areas. Airborne LIDAR systems usually return a 3-dimensional cloud of point measurements from reflective objects scanned by the laser beneath the flight path. This technology is becoming a primary method for extracting information of different kinds of geometrical objects, such as high-resolution digital terrain models (DTMs), buildings and trees, etc. In the past decade, LIDAR gets more and more interest from researchers in the field of remote sensing and GIS. Compared to the traditional data sources, such as aerial photography and satellite images, LIDAR measurements are not influenced by sun shadow and relief displacement. However, voluminous data pose a new challenge for automated extraction the geometrical information from LIDAR measurements because many raster image processing techniques cannot be directly applied to irregularly spaced LIDAR points. ^ In this dissertation, a framework is proposed to filter out information about different kinds of geometrical objects, such as terrain and buildings from LIDAR automatically. They are essential to numerous applications such as flood modeling, landslide prediction and hurricane animation. The framework consists of several intuitive algorithms. Firstly, a progressive morphological filter was developed to detect non-ground LIDAR measurements. By gradually increasing the window size and elevation difference threshold of the filter, the measurements of vehicles, vegetation, and buildings are removed, while ground data are preserved. Then, building measurements are identified from no-ground measurements using a region growing algorithm based on the plane-fitting technique. Raw footprints for segmented building measurements are derived by connecting boundary points and are further simplified and adjusted by several proposed operations to remove noise, which is caused by irregularly spaced LIDAR measurements. To reconstruct 3D building models, the raw 2D topology of each building is first extracted and then further adjusted. Since the adjusting operations for simple building models do not work well on 2D topology, 2D snake algorithm is proposed to adjust 2D topology. The 2D snake algorithm consists of newly defined energy functions for topology adjusting and a linear algorithm to find the minimal energy value of 2D snake problems. Data sets from urbanized areas including large institutional, commercial, and small residential buildings were employed to test the proposed framework. The results demonstrated that the proposed framework achieves a very good performance. ^

The longitudinal influence of physical activity on adolescent alcohol use

The purpose of this research was to explore the influence of physical activity on depressive symptomatology and adolescent alcohol use during an underexplored transition from middle school to high school. The study initiative is supported by the fact that research has shown a unique and simultaneous decrease in physical activity (CDC, 2010), increase in depressive symptomatology (SAMHSA, 2010) and increase in alcohol use (USDHHS, 2011) during middle adolescence. A risk and resilience framework was used in efforts to conceptualize how these variables may be inter-related. Data from waves I and II of the National Longitudinal Study of Adolescent Health (Add Health, Bearman et al., 1997; Udry, 1997) was used (N = 2,054; aged 13–15 years). The sample was ethnically and racially diverse (58.2% White, 24% African American, 11.7% Hispanic, and 6.1% other). Structural equation models were developed to test the potential influence physical activity has on adolescent alcohol use (e.g., frequency of alcohol use and binge alcohol use) and whether any of the relationship was mediated by depressive symptomatology or varied as a function of gender. Results demonstrated that there was a significant influence of structured physical activity (e.g., sports) on adolescent alcohol use. However, contrary to the proposed hypothesis, engaging in structured physical activity appeared to contribute to greater binge drinking among adolescents. Instead of demonstrating a protective feature, the findings suggest that engaging in structured physical activity places adolescents at risk for binge drinking. Furthermore, no significant relationships, positive or negative, were found for the influence of physical activity (structured and unstructured) on frequency of alcohol use. The findings regarding mediation revealed binge drinking as a mediator between physical activity (structured) and depressive symptomatology. These findings provide support for research, practice, and policy initiatives focused on developing a more comprehensive understanding of alcohol use drinking behaviors, physical activity involvement, and depressive symptomatology among adolescents, which this study demonstrates are all associated with one another. Results represent an initial step toward evaluating these relationships at a much younger age.

Enhanced skip -list search algorithm in 3-layer mediator framework

The Three-Layer distributed mediation architecture, designed by Secure System Architecture laboratory, employed a layered framework of presence, integration, and homogenization mediators. The architecture does not have any central component that may affect the system reliability. A distributed search technique was adapted in the system to increase its reliability. An Enhanced Chord-like algorithm (E-Chord) was designed and deployed in the integration layer. The E-Chord is a skip-list algorithm based on Distributed Hash Table (DHT) which is a distributed but structured architecture. DHT is distributed in the sense that no central unit is required to maintain indexes, and it is structured in the sense that indexes are distributed over the nodes in a systematic manner. Each node maintains three kind of routing information: a frequency list, a successor/predecessor list, and a finger table. None of the nodes in the system maintains all indexes, and each node knows about some other nodes in the system. These nodes, also called composer mediators, were connected in a P2P fashion. ^ A special composer mediator called a global mediator initiates the keyword-based matching decomposition of the request using the E-Chord. It generates an Integrated Data Structure Graph (IDSG) on the fly, creates association and dependency relations between nodes in the IDSG, and then generates a Global IDSG (GIDSG). The GIDSG graph is a plan which guides the global mediator how to integrate data. It is also used to stream data from the mediators in the homogenization layer which connected to the data sources. The connectors start sending the data to the global mediator just after the global mediator creates the GIDSG and just before the global mediator sends the answer to the presence mediator. Using the E-Chord and GIDSG made the mediation system more scalable than using a central global schema repository since all the composers in the integration layer are capable of handling and routing requests. Also, when a composer fails, it would only minimally affect the entire mediation system. ^