RACER: accurate and efficient classification based on rule aggregation approach

Neural Computing and Applications - Rule-based classification is one of the most important topics in the field of data mining due to its wide applications. This article presents a novel rule-based...     

Secure computation of hidden Markov models and secure floating-point arithmetic in the malicious model

Hidden Markov model (HMM) is a popular statistical tool with a large number of applications in pattern recognition. In some of these applications, such as speaker recognition, the computation involves personal data that can identify individuals and must be protected. We thus treat the problem of designing privacy-preserving techniques for HMM and companion Gaussian mixture model computation suitable for use in speaker recognition and other applications. We provide secure solutions for both two-party and multi-party computation models and both semi-honest and malicious settings. In the two-party setting, the server does not have access in the clear to either the user-based HMM or user input (i.e., current observations) and thus the computation is based on threshold homomorphic encryption, while the multi-party setting uses threshold linear secret sharing as the underlying data protection mechanism. All solutions use floating-point arithmetic, which allows us to achieve high accuracy and provable security guarantees, while maintaining reasonable performance. A substantial part of this work is dedicated to building secure protocols for floating-point operations in the two-party setting, which are of independent interest.     

Adsorption ability of oxidized multiwalled carbon nanotubes towards aqueous Ce(III) and Sm(III)

The aim of the present work was to investigate the adsorption of Ce(III) and Sm(III) onto multiwalled carbon nanotubes (MWCNTs) oxidized with concentrate nitric acid. The effects of solution pH, adsorbent dosage, and contact time were studied by batch technique. Langmuir, Freundlich and D-R isotherms were used to describe the adsorption behavior of Ce(III) and Sm(III) by oxidized MWCNTs, and the experimental results fitted Freundlich model well. The maximum uptake capacities (q _m ) calculated by applying the Langmuir equation for samarium and cerium ions were found to be 89.28 and 92.59 (mg/g), respectively. A comparison of the kinetic models and the overall experimental data was best fitted by the pseudo second-order kinetic model. The calculated thermodynamic parameters (ΔG^o, ΔH^o, and ΔS^o) showed that the adsorption for Ce(III) and Sm(III) is feasible, spontaneous and exothermic at 30–60 °C. Moreover, more than 70% of Ce(III) and Sm(III) adsorbed onto Oxidized MWCNTs could be desorbed with HNO₃.     

Collaborative team formation using brain drain optimization: a practical and effective solution

In the area of professional social networks, collaborative team formation with its NP-hard nature, has attracted the attention of many researchers. The purpose of this study is to find a collaborative team which covers required skills and minimizes the communication cost among team members. To solve this problem, BRADO (BRAin Drain Optimization), a recently-proposed meta-heuristic swarm-based algorithm which simulates the brain drain phenomenon, has been utilized. In order to evaluate BRADO, it has been applied in extensive experiments to the DBLP and IMDb datasets. Results demonstrate the effectiveness and superiority of the BRADO algorithm in comparison with PSO, GA, ICA, RarestFirst and EnhancedSteiner algorithms. Our findings lead us to believe that the BRADO algorithm can be a promising method in the context of team formation problem.     

Evolving artificial neural network structure using grammar encoding and colonial competitive algorithm

Generalization performance of support vector machines (SVM) with Gaussian kernel is influenced by its model parameters, both the error penalty parameter and the Gaussian kernel parameter. After researching the characteristics and properties of the parameter simultaneous variation of support vector machines with Gaussian kernel by the parameter analysis table, a new area distribution model is proposed, which consists of optimal straight line, reference point of area boundary, optimal area, transition area, underfitting area, and overfitting area. In order to improve classification performance of support vector machines, a genetic algorithm based on change area search is proposed. Comparison experiments show that the test accuracy of the genetic algorithm based on change area search is better than that of the two-linear search method.