Leveraging clustering approaches to solve the gray-sheep users problem in recommender systems

Recommender systems apply data mining and machine learning techniques for filtering unseen information and can predict whether a user would like a given item. This paper focuses on gray-sheep users problem responsible for the increased error rate in collaborative filtering based recommender systems. This paper makes the following contributions: we show that (1) the presence of gray-sheep users can affect the performance – accuracy and coverage – of the collaborative filtering based algorithms, depending on the data sparsity and distribution; (2) gray-sheep users can be identified using clustering algorithms in offline fashion, where the similarity threshold to isolate these users from the rest of community can be found empirically. We propose various improved centroid selection approaches and distance measures for the K-means clustering algorithm; (3) content-based profile of gray-sheep users can be used for making accurate recommendations. We offer a hybrid recommendation algorithm to make reliable recommendations for gray-sheep users. To the best of our knowledge, this is the first attempt to propose a formal solution for gray-sheep users problem. By extensive experimental results on two different datasets (MovieLens and community of movie fans in the FilmTrust website), we showed that the proposed approach reduces the recommendation error rate for the gray-sheep users while maintaining reasonable computational performance.     

Improved migration for mobile computing in distributed networks

A mobile ad hoc network (MANET) is a special type of wireless network in which a collection of mobile nodes with wireless network interfaces may form a temporary network, without the aids of any fixed infrastructure. Security has become a hot research topic in mobile ad hoc networks. In 1998, Volker and Mehrdad proposed a tree-based key management and access control scheme for the mobile agents to manage rights to access its own resources for the visited mobile nodes. Latter, Huang et al. showed that Volker and Mehrdad's scheme needs a large amount of storage and costs for managing and storing secret keys. Huang et al. further proposed a new and efficient scheme based on the elliptic curve cryptosystems to reduce costs and gain better efficiency. However, there is a security leak inherent in Huang et al.'s scheme that the malicious node can overstep his authority to access unauthorized information. This paper will propose a secure, robust, and efficient hierarchical key management scheme for MANETs. Some practical issues and solutions about dynamic key management are also considered and proposed. As compared with Huang et al.'s scheme, our proposed scheme can provide better security assurance, while requiring smaller key-size, lower computational complexities, and constant key management costs which is independent on the number of the confidential files and the visited nodes.     

PPREM: Privacy Preserving REvocation Mechanism for Vehicular Ad Hoc Networks

One of the critical security issues of Vehicular Ad Hoc Networks (VANETs) is the revocation of misbehaving vehicles. While essential, revocation checking can leak potentially sensitive information. Road Side Units (RSUs) receiving the certificate status queries could infer the identity of the vehicles posing the query. An important loss of privacy results from the RSUs ability to tie the checking vehicle with the query's target. We propose a Privacy Preserving Revocation mechanism (PPREM) based on a universal one-way accumulator. PPREM provides explicit, concise, authenticated and unforgeable information about the revocation status of each certificate while preserving the users' privacy.     

A measure of information gained through biometric systems

We propose a measure of information gained through biometric matching systems. Firstly, we discuss how the information about the identity of a person is derived from biometric samples through a biometric system, and define the “biometric system entropy” or BSE based on mutual information. We present several theoretical properties and interpretations of the BSE, and show how to design a biometric system which maximizes the BSE. Then we prove that the BSE can be approximated asymptotically by the relative entropy D(f_G(x)∥f_I(x)) where f_G(x) and f_I(x) are probability mass functions of matching scores between samples from individuals and among population. We also discuss how to evaluate the BSE of a biometric system and show experimental evaluation of the BSE of face, fingerprint and multimodal biometric systems.     

Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging

Early and accurate diagnosis of Parkinson’s disease (PD) is important for early management, proper prognostication and for initiating neuroprotective therapies once they become available. Recent neuroimaging techniques such as dopaminergic imaging using single photon emission computed tomography (SPECT) with ¹²³I-Ioflupane (DaTSCAN) have shown to detect even early stages of the disease. In this paper, we use the striatal binding ratio (SBR) values that are calculated from the ¹²³I-Ioflupane SPECT scans (as obtained from the Parkinson’s progression markers initiative (PPMI) database) for developing automatic classification and prediction/prognostic models for early PD. We used support vector machine (SVM) and logistic regression in the model building process. We observe that the SVM classifier with RBF kernel produced a high accuracy of more than 96% in classifying subjects into early PD and healthy normal; and the logistic model for estimating the risk of PD also produced high degree of fitting with statistical significance indicating its usefulness in PD risk estimation. Hence, we infer that such models have the potential to aid the clinicians in the PD diagnostic process.     

Probabilistic pseudo-morphology for grayscale and color images

Mathematical morphology offers popular image processing tools, successfully used for binary and grayscale images. Recently, its extension to color images has become of interest and several approaches were proposed. Due to various issues arising from the vectorial nature of the data, none of them imposed as a generally valid solution. We propose a probabilistic pseudo-morphological approach, by estimating two pseudo-extrema based on Chebyshev inequality. The framework embeds a parameter which allows controlling the linear versus non-linear behavior of the probabilistic pseudo-morphological operators. We compare our approach for grayscale images with the classical morphology and we emphasize the impact of this parameter on the results. Then, we extend the approach to color images, using principal component analysis. As validation criteria, we use the estimation of the color fractal dimension, color textured image segmentation and color texture classification. Furthermore, we compare our proposed method against two widely used approaches, one morphological and one pseudo-morphological.     

Pavement crack detection using hessian structure propagation

Pavement images are widely used in transportation agencies to detect cracks accurately so that the best proper plans of maintenance and rehabilitation could be made. Although crack in a pavement image is perceived because the intensity of crack pixels contrasts with that of the pavement background, there are still challenges in distinguishing cracks from complex textures, heavy noise, and interference. Unlike the intensity or the first-order edge feature of crack, this paper proposes the second-order directional derivative to characterize the directional valley-like structure of crack. The multi-scale Hessian structure is first proposed to analytically adapt to the direction and valley of cracking in the Gaussian scale space. The crack structure field is then proposed to mimic the curvilinear propagation of crack in the local area, which is iteratively applied at every point of the crack curve to infer the crack structure at the gaps and intersections. Finally, the most salient centerline of the crack within its curvilinear buffer is exactly located with non-maximum suppression along the perpendicular direction of crack. The experiments on large numbers of images of various crack types and with diverse conditions of noise, illumination and interference demonstrate the proposed method can detect pavement cracks well with an average Precision, Recall and F-measure of 92.4%, 88.4%, and 90.4% respectively. Also, the proposed method achieves the best performance of crack detection on the benchmark datasets among methods that also require no training and publicly offer the detection results for every image.     

基于相关向量机的高光谱图像解混方法

针对传统的高光谱数据解混方法中存在的解混精度不高、丰度图模糊的缺陷,提出一种基于相关向量机的高光谱图像解混方法(unmixing algorithm based on relevance vector machine,UARVM)。其核心思想是采用改进的一对余型的相关向量机将多分类问题转化为多个二分类的问题,且求取出每个样本所对应的归属类别的概率值,即丰度值来完成图像的解混。理论研究和仿真结果表明:相对于传统解混方法,UARVM解混精度高,丰度分布图效果好。     

Infra-chromatic bound for exact maximum clique search

Many efficient exact branch and bound maximum clique solvers use approximate coloring to compute an upper bound on the clique number for every subproblem. This technique reasonably promises tight bounds on average, but never tighter than the chromatic number of the graph.Li and Quan, 2010, AAAI Conference, p. 128–133 describe a way to compute even tighter bounds by reducing each colored subproblem to maximum satisfiability problem (MaxSAT). Moreover they show empirically that the new bounds obtained may be lower than the chromatic number.Based on this idea this paper shows an efficient way to compute related “infra-chromatic” upper bounds without an explicit MaxSAT encoding. The reported results show some of the best times for a stand-alone computer over a number of instances from standard benchmarks.