Biometric classifier update using online learning: A case study in near infrared face verification

The performance of a large scale biometric system may deteriorate over time as new individuals are continually enrolled. To maintain an acceptable level of performance, the classifier has to be re-trained offline in batch mode using both existing and new data. The process of re-training can be computationally expensive and time consuming. This paper presents a new biometric classifier update algorithm that incrementally re-trains the classifier using online learning and progressively establishes a decision hyperplane for improved classification. The proposed algorithm incorporates soft labels and granular computing in the formulation of a 2ν$\nu$-Online Granular Soft Support Vector Machine (SVM) to re-train the classifier using only the new data. Granular computing makes it adaptive to local and global variations in data distribution, while soft labels provide resilience to noise. Each time data is acquired, new support vectors that are linearly independent are added and existing support vectors that do not improve the classifier performance are removed. This constrains the size of the support vectors and significantly reduces the training time without compromising the classification accuracy. The efficacy of the proposed online learning strategy is validated in a near infrared face verification application involving different covariates. The results obtained on a heterogeneous near infrared face database of 328 subjects show that in all experiments using different feature extraction and classification algorithms the proposed online 2ν$\nu$-Granular Soft Support Vector Machine learning approach is 2–3 times faster while achieving a high level of accuracy similar to offline training using all data.     

An online core vector machine with adaptive MEB adjustment

Support vector machine (SVM) is a widely used classification technique. However, it is difficult to use SVMs to deal with very large data sets efficiently. Although decomposed SVMs (DSVMs) and core vector machines (CVMs) have been proposed to overcome this difficulty, they cannot be applied to online classification (or classification with learning ability) because, when new coming samples are misclassified, the classifier has to be adjusted based on the new coming misclassified samples and all the training samples. The purpose of this paper is to address this issue by proposing an online CVM classifier with adaptive minimum-enclosing-ball (MEB) adjustment, called online CVMs (OCVMs). The OCVM algorithm has two features: (1) many training samples are permanently deleted during the training process, which would not influence the final trained classifier; (2) with a limited number of selected samples obtained in the training step, the adjustment of the classifier can be made online based on new coming misclassified samples. Experiments on both synthetic and real-world data have shown the validity and effectiveness of the OCVM algorithm.     

An RBF neural network-based adaptive control for SISO linearisable nonlinear systems

An RBF neural network-based adaptive control is proposed for Single-Input and Single-Output (SISO) linearisable nonlinear systems in this paper. It is shown that a SISO nonlinear system is first linearised by using the differential geometric approach in the state space, and the linearised nonlinear system is then treated as a partially known system. The known dynamics are used to design a nominal feedback controller to stabilise the nominal system, and an adaptive RBF neural network-based compensator is then designed to compensate for the effects of uncertain dynamics. The main function of the RBF neural network in this work is to adaptively learn the upper bound of the system uncertainty, and the output of the neural network is then used to adaptively adjust the gain of the compensator so that the strong robustness with respect to unknown dynamics can be obtained, and the tracking error between the plant output and the desired reference signal can asymptotically converge to zero. A simulation example is performed in support of the proposed scheme.     

Knowledge hoarding and user acceptance of online discussion board systems in eLearning: A case study

This paper aims to reveal the determinants of the effectiveness of online discussion board systems (ODBSs) in eLearning environments to foster the interactions among the learners and/or instructors. A case in which an ODBS failed to foster the interactions among learners/instructors for knowledge sharing is introduced and hypotheses to explain the failure are developed based on thorough literature review in technology acceptance model (TAM) and knowledge hoarding. The hypotheses are tested via statistical analysis on the data collected from a questionnaire survey against the students who actually involved in the case study. The result shows that the low perceived usefulness of the ODBS by the students played major role in the failure of the system. Also it is hinted that network externalities as an intrinsic motivator is more effective than extrinsic motivators to increase the students’ activities on the ODBS. Finally the paper provides the designers of eLearning systems with advice for successful operation of ODBS in eLearning.     

A differentiated one-class classification method with applications to intrusion detection

Intrusion detection has become an indispensable tool to keep information systems safe and reliable. Most existing anomaly intrusion detection techniques treat all types of attacks as equally important without any differentiation of the risk they pose to the information system. Although detection of all intrusions is important, certain types of attacks are more harmful than others and their detection is critical to protection of the system. This paper proposes a new one-class classification method with differentiated anomalies to enhance intrusion detection performance for harmful attacks. We also propose new extracted features for host-based intrusion detection based on three viewpoints of system activity such as dimension, structure, and contents. Experiments with simulated dataset and the DARPA 1998 BSM dataset show that our differentiated intrusion detection method performs better than existing techniques in detecting specific type of attacks. The proposed method would benefit even other applications in anomaly detection area beyond intrusion detection.     

基于支持向量数据描述的异常检测方法

提出了一种基于支持向量数据描述算法的异常检测方法。该方法将入侵检测看作是一种单值分类问题,建立正常行为的支持向量描述模型,通过该模型可以检测各种已知和未知的攻击行为。该方法是一种无监督的异常检测方法,能够在包含噪声的数据集进行模型训练,降低了训练集的要求。在KDD CUP99标准入侵检测数据集上进行实验,并与无监督聚类异常检测实验结果相比较,证实该方法能够获得较高检测率和较低误警率。     

Observer‐based adaptive neural control for a class of nonlinear singular systems

The problem of observer‐based adaptive neural control via output feedback for a class of uncertain nonlinear singular systems is studied in this article. The nonlinear singular systems can be regarded as two subsystems that are coupled with each other: differential subsystem and algebraic subsystem. The differential systems can be nonstrict feedback structures. To guarantee that the singular system is regular and impulse‐free, two new conditions are proposed. By the conditions, the linear controller and observer, which are used to estimate the immeasurable state variables, are obtained. Then, an output feedback scheme through adaptive neural backstepping is proposed to ensure that all states of the closed‐loop system are semiglobally uniformly ultimately bounded and converge to a small neighborhood of the origin. Simulation examples illustrate the effectiveness of the presented method.     

不确定非线性系统全局渐近自适应神经网络控制

针对一类控制增益为一般函数形式的不确定仿射非线性系统,提出一种能够确保全局渐近稳定的自适应神经控制(adaptiveneural control,ANC)方法.为了保证神经网络逼近的适用性,设计一种可变控增益的比例微分(proportionaldifferential,PD)控制器以全局镇定被控对象.利用状态变换解决由未知控制增益函数导致的控制奇异问题.提出一种连续的自适应鲁棒控制项实现闭环系统的渐近跟踪.与现有的全局渐近跟踪ANC方法相比较,本文方法不仅简化了PD增益的选择,而且减轻了控制输入的颤振问题.仿真结果表明了本文方法的有效性.     

非线性时滞系统的稳定自适应控制

针对模型不确定性的连续时间时滞系统，提出了一种新的神经网络自适应控制。系统的辨识模型是由神经网络和系统的已知信息组合构成，在此基础上，建立时滞系统的预测模型。基于神经网络预测模型的自适应控制器能够实现期望轨线的跟踪，理论上证明了闭环系统的稳定性。连续搅拌釜式反应器仿真结果表明了该控制方案的有效性。     

Using online consumer reviews as a source for demographic recommendations: A case study using online travel reviews

Online consumer reviews play an important role in the decision to purchase services online, mainly due to the rich information source they provide to consumers in terms of evaluating “experience”-type products and services that can be booked using the Internet, with online travel services being a significant example. However, different types of travelers assess each quality indicator differently, depending on the type of travel they engage in, and not necessarily their cultural or age background (e.g. solo travelers, young couples with children etc.). In this study, we present architecture for a demographic recommendation system, based on a user-defined hierarchy of service quality indicator importance, and classification of traveler types. We use an algebraic approach to ascertain preferences from a large dataset that we obtained from the popular travel website Booking.com using a web crawler and compared with the customer-constructed preference matrix. Interestingly, the architecture of the evaluated recommendation system takes into account already defined demand characteristics of the hotels (such as the number of reviews of specific consumer types compared to the total number of reviews) in order to provide an example architecture for a recommendation system based on user-defined preference criteria.     

Towards effective online review systems in the Chinese context: A cross-cultural empirical study

Online reviews, as one kind of quality indicator of products or service, are becoming increasingly important in influencing purchase decisions of prospective consumers on electronic commerce websites. With the fast growth of the Chinese e-commerce industry, it is thus indispensable to design effective online review systems for e-commerce websites in the Chinese context, by taking into account cultural factors. In this paper, we conduct two empirical studies on online reviews. Firstly, we study how culture differences across countries (i.e., China and the USA) impact the way in which consumers provide online reviews. Secondly, we investigate the impact of online reviews on product sales in the Chinese context, and show that directly copying the ideas of successful online review systems in the USA will deteriorate the effectiveness of the systems in China. Finally, we propose several suggestions for the development of effective online review systems in the Chinese context based on the results of our two empirical studies and the findings in previous studies.     

An empirical study of information contribution to online feedback systems: A motivation perspective

Online feedback systems (OFSs) are increasingly available on online shopping websites; they allow consumers to post their ratings and consumption reviews for products. We employed motivation theory and a goal attainment perspective to model a set of motivating and inhibiting factors that could influence a consumer's intention to contribute to an OFS. Our experiment, which involved 168 university students, showed that a consumer's intention to contribute product reviews is influenced by perceived satisfaction gained in helping other consumers, perceived satisfaction gained in influencing the merchant, perceived probability of enhancing self-image, and perceived executional costs. In addition, the presence of an economic rewarding mechanism was found to promote a contribution when a consumer's perceived probability of enhancing self-image was relatively high or when perceived cognitive cost was relatively low. Implications of our findings are discussed.     

无监督自适应入侵检测系统研究

提出了一种基于组件的无监督自适应入侵检测系统,各组件既相互独立又相互协同工作。在完成入侵检测的同时,能根据审计数据自动生成检测模型,并将生成的模型自动分配到各检测器。由于不需要人为标识数据,因此能显著降低入侵检测系统的开发成本,提高了入侵检测系统的适应性和检测率。     

Observer-based synergetic adaptive neural network control for a class of discrete-time nonlinear systems with dead-zone

In this paper, the observer-based synergetic adaptive neural network control method is designed for a class of discrete-time systems with dead-zone. A macro-variable is introduced by a synergetic approach to control theory and neural networks are utilised to estimate unmeasured states and unknown functions in the system. Furthermore, by employing an adaptive design procedure and Lyapunov stability theory, the closed-loop system stability is guaranteed, and the desired system performance is achieved simultaneously. Finally, some simulation results are given to prove the validity of the developed control method.     

Robust adaptive neural control for a class of uncertain MIMO nonlinear systems

In this paper, a novel robust adaptive neural control scheme is proposed for a class of uncertain multi-input multi-output nonlinear systems. The proposed scheme has the following main features: (1) a kind of Hurwitz condition is introduced to handle the state-dependent control gain matrix and some assumptions in existing schemes are relaxed; (2) by introducing a novel matrix normalisation technique, it is shown that all bound restrictions imposed on the control gain matrix in existing schemes can be removed; (3) the singularity problem is avoided without any extra effort, which makes the control law quite simple. Besides, with the aid of the minimal learning parameter technique, only one parameter needs to be updated online regardless of the system input–output dimension and the number of neural network nodes. Simulation results are presented to illustrate the effectiveness of the proposed scheme.     

On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Classifiers based on radial basis function neural networks have a number of useful properties that can be exploited in many practical applications. Using sample data, it is possible to adjust their parameters (weights), to optimize their structure, and to select appropriate input features (attributes). Moreover, interpretable rules can be extracted from a trained classifier and input samples can be identified that cannot be classified with a sufficient degree of “certainty”. These properties support an analysis of radial basis function classifiers and allow for an adaption to “novel” kinds of input samples in a real-world application. In this article, we outline these properties and show how they can be exploited in the field of intrusion detection (detection of network-based misuse). Intrusion detection plays an increasingly important role in securing computer networks. In this case study, we first compare the classification abilities of radial basis function classifiers, multilayer perceptrons, the neuro-fuzzy system NEFCLASS, decision trees, classifying fuzzy-k-means, support vector machines, Bayesian networks, and nearest neighbor classifiers. Then, we investigate the interpretability and understandability of the best paradigms found in the previous step. We show how structure optimization and feature selection for radial basis function classifiers can be done by means of evolutionary algorithms and compare this approach to decision trees optimized using certain pruning techniques. Finally, we demonstrate that radial basis function classifiers are basically able to detect novel attack types. The many advantageous properties of radial basis function classifiers could certainly be exploited in other application fields in a similar way.     

Composite adaptive dynamic surface control using online recorded data

This paper presents an online recorded data‐based design of composite adaptive dynamic surface control for a class of uncertain parameter strict‐feedback nonlinear systems, where both tracking errors and prediction errors are applied to update parametric estimates. Differing from the traditional composite adaptation that utilizes identification models and linear filters to generate filtered modeling errors as prediction errors, the proposed composite adaptation integrates closed‐loop tracking error equations in a moving time window to generate modified modeling errors as prediction errors. The time‐interval integral operation takes full advantage of online recorded data to improve parameter convergence such that the application of both identification models and linear filters is not necessary. Semiglobal practical asymptotic stability of the closed‐loop system is rigorously established by the time‐scales separation and Lyapunov synthesis. The major contribution of this study is that composite adaptation based on online recorded data is achieved at the presence of mismatched uncertainties. Simulation results have been provided to verify the effectiveness and superiority of this approach. Copyright © 2016 John Wiley & Sons, Ltd.     

Distributed adaptive neural network control for a class of heterogeneous nonlinear multi-agent systems subject to actuation failures

In this paper, the cooperative adaptive consensus tracking problem for heterogeneous nonlinear multi-agent systems on directed graph is addressed. Each follower is modelled as a general nonlinear system with the unknown and nonidentical nonlinear dynamics, disturbances and actuator failures. Cooperative fault tolerant neural network tracking controllers with online adaptive learning features are proposed to guarantee that all agents synchronise to the trajectory of one leader with bounded adjustable synchronisation errors. With the help of linear quadratic regulator-based optimal design, a graph-dependent Lyapunov proof provides error bounds that depend on the graph topology, one virtual matrix and some design parameters. Of particular interest is that if the control gain is selected appropriately, the proposed control scheme can be implemented in a unified framework no matter whether there are faults or not. Furthermore, the fault detection and isolation are not needed to implement. Finally, a simulation is given to verify the effectiveness of the proposed method.