Evolutionary circuit design for fast FPGA-based classification of network application protocols

The evolutionary design can produce fast and efficient implementations of digital circuits. It is shown in this paper how evolved circuits, optimized for the latency and area, can increase the throughput of a manually designed classifier of application protocols. The classifier is intended for high speed networks operating at 100 Gbps. Because a very low latency is the main design constraint, the classifier is constructed as a combinational circuit in a field programmable gate array (FPGA). The classification is performed using the first packet carrying the application payload. The improvements in latency (and area) obtained by Cartesian genetic programming are validated using a professional FPGA design tool. The quality of classification is evaluated by means of real network data. All results are compared with commonly used classifiers based on regular expressions describing application protocols.     

Corrective classification: Learning from data imperfections with aggressive and diverse classifier ensembling

Learning from imperfect (noisy) information sources is a challenging and reality issue for many data mining applications. Common practices include data quality enhancement by applying data preprocessing techniques or employing robust learning algorithms to avoid developing overly complicated structures that overfit the noise. The essential goal is to reduce noise impact and eventually enhance the learners built from noise-corrupted data. In this paper, we propose a novel corrective classification (C2) design, which incorporates data cleansing, error correction, Bootstrap sampling and classifier ensembling for effective learning from noisy data sources. C2 differs from existing classifier ensembling or robust learning algorithms in two aspects. On one hand, a set of diverse base learners of C2 constituting the ensemble are constructed via a Bootstrap sampling process; on the other hand, C2 further improves each base learner by unifying error detection, correction and data cleansing to reduce noise impact. Being corrective, the classifier ensemble is built from data preprocessed/corrected by the data cleansing and correcting modules. Experimental comparisons demonstrate that C2 is not only more accurate than the learner built from original noisy sources, but also more reliable than Bagging [4] or aggressive classifier ensemble (ACE) [56], which are two degenerated components/variants of C2. The comparisons also indicate that C2 is more stable than Boosting and DECORATE, which are two state-of-the-art ensembling methods. For real-world imperfect information sources (i.e. noisy training and/or test data), C2 is able to deliver more accurate and reliable prediction models than its other peers can offer.     

From classifiers to discriminators: A nearest neighbor rule induced discriminant analysis

The current discriminant analysis method design is generally independent of classifiers, thus the connection between discriminant analysis methods and classifiers is loose. This paper provides a way to design discriminant analysis methods that are bound with classifiers. We begin with a local mean based nearest neighbor (LM-NN) classifier and use its decision rule to supervise the design of a discriminator. Therefore, the derived discriminator, called local mean based nearest neighbor discriminant analysis (LM-NNDA), matches the LM-NN classifier optimally in theory. In contrast to that LM-NNDA is a NN classifier induced discriminant analysis method, we further show that the classical Fisher linear discriminant analysis (FLDA) is a minimum distance classifier (i.e. nearest Class-mean classifier) induced discriminant analysis method. The proposed LM-NNDA method is evaluated using the CENPARMI handwritten numeral database, the NUST603 handwritten Chinese character database, the ETH80 object category database and the FERET face image database. The experimental results demonstrate the performance advantage of LM-NNDA over other feature extraction methods with respect to the LM-NN (or NN) classifier.     

A learning classifier system for mazes with aliasing clones

Maze problems represent a simplified virtual model of the real environment and can be used for developing core algorithms of many real-world application related to the problem of navigation. Learning Classifier Systems (LCS) are the most widely used class of algorithms for reinforcement learning in mazes. However, LCSs best achievements in maze problems are still mostly bounded to non-aliasing environments, while LCS complexity seems to obstruct a proper analysis of the reasons for failure. Moreover, there is a lack of knowledge of what makes a maze problem hard to solve by a learning agent. To overcome this restriction we try to improve our understanding of the nature and structure of maze environments. In this paper we describe a new LCS agent that has a simpler and more transparent performance mechanism. We use the structure of a predictive LCS model, strip out the evolutionary mechanism, simplify the reinforcement learning procedure and equip the agent with the ability to Associative Perception, adopted from psychology. We then assess the new LCS with Associative Perception on an extensive set of mazes and analyse the results to discover which features of the environments play the most significant role in the learning process. We identify a particularly hard feature for learning in mazes, aliasing clones, which arise when groups of aliasing cells occur in similar patterns in different parts of the maze. We discuss the impact of aliasing clones and other types of aliasing on learning algorithms.     

基于ARM的逻辑门电路手绘草图识别

针对电路草图识别主要在计算机上完成以及只能识别电路元件的问题,设计一个在ARM处理器和Linux系统上实现的逻辑门电路草图整图识别系统。采取在线识别的方式对触摸屏上输入的手绘笔画进行分段识别、组合、分类得到门电路的图元,按图元顺序建立图元列表,分割出逻辑门图元组合,重构门电路整图。实验证明该系统对逻辑门电路草图有很高的识别率。     

Improving the performance of the BioHEL learning classifier system

The identification of significant attributes is of major importance to the performance of a variety of Learning Classifier Systems including the newly-emerged Bioinformatics-oriented Hierarchical Evolutionary Learning (BioHEL) algorithm. However, the BioHEL fails to deliver on a set of synthetic datasets which are the checkerboard data mixed with Gaussian noises due to the fact the significant attributes were not successfully recognised. To address this issue, a univariate Estimation of Distribution Algorithm (EDA) technique is introduced to BioHEL which primarily builds a probabilistic model upon the outcome of the generalization and specialization operations. The probabilistic model which estimates the significance of each attribute provides guidance for the exploration of the problem space. Experiment evaluations showed that the proposed BioHEL systems achieved comparable performance to the conventional one on a number of real-world small-scale datasets. Research efforts were also made on finding the optimal parameter for the traditional and proposed BioHEL systems.     

Dynamic classifier selection for One-vs-One strategy: Avoiding non-competent classifiers

The One-vs-One strategy is one of the most commonly used decomposition technique to overcome multi-class classification problems; this way, multi-class problems are divided into easier-to-solve binary classification problems considering pairs of classes from the original problem, which are then learned by independent base classifiers.The way of performing the division produces the so-called non-competence. This problem occurs whenever an instance is classified, since it is submitted to all the base classifiers although the outputs of some of them are not meaningful (they were not trained using the instances from the class of the instance to be classified). This issue may lead to erroneous classifications, because in spite of their incompetence, all classifiers' decisions are usually considered in the aggregation phase.In this paper, we propose a dynamic classifier selection strategy for One-vs-One scheme that tries to avoid the non-competent classifiers when their output is probably not of interest. We consider the neighborhood of each instance to decide whether a classifier may be competent or not. In order to verify the validity of the proposed method, we will carry out a thorough experimental study considering different base classifiers and comparing our proposal with the best performer state-of-the-art aggregation within each base classifier from the five Machine Learning paradigms selected. The findings drawn from the empirical analysis are supported by the appropriate statistical analysis.     

CLAPP: A self constructing feature clustering approach for anomaly detection

The term internet of things is a buzz word these days and as per Google survey conducted recently, it has even dominated the buzz word big data predominantly. However, IoT area is still not matured and is throwing light on lot of research issues towards the data mining researchers. Security in IoT throws several challenges because of limited resources. In this context, IoT gains importance once again from data miners towards anomaly mining or intrusion detection. Intrusion detection is classified as NP-class in the literature even today. Algorithms addressing privacy and security issues in IoT must consider the complexities involved and hence require re-attention from all researchers. One more problem faced when judging for intrusion is the use of high dimensionality, classifier choice, and distance measure. For example, the traditional distance measure, such as Euclidean misjudges the similarity. In this paper, the objective is to design a fuzzy membership function to address both dimensionality and anomaly mining so as reduce the computational complexity and increase computational accuracies of classifier algorithms. We validate the proposed measure using several experimentations on NSL-KDD and DARPA datasets using kNN, J48 and CANN using Gaussian measure. Improved accuracies of classifiers on U2R and R2L attacks have been recorded in the experimental results obtained for experiments conducted.     

基于线性判别分析的Choquet积分的符号模糊测度提取

在解决分类问题时,建立在Choquet积分上的分类器以其非线性和不可加性的特点,扮演着越来越重要的角色。由于Choquet积分中的符号模糊测度可以描述各特征对结果的影响,因此Choquet积分在解决数据分类及融合 问题方面具有显著的优势。但是,关于Choquet积分符号模糊测度值的求解,学术界一直缺乏有效的方法。目前最常用的方法是遗传算法,但是遗传算法在解决符号模糊测度值的优化问题时存在算法较为复杂、耗时较长等缺陷。由于符号模糊测度值在Choquet积分分类器中是决定性的重要参数,因此设计出一种有效的符号模糊测度提取方法十分必要。文中提出基于线性判别分析的Choquet积分符号模糊测度的提取方法,推导出在分类问题下Choquet积分的符号模糊测度值的解析式表达,其能够有效、快速地得出关键性参数。分别在人工数据集及基准实际数据集上进行测试与验证,实验结果表明所提方法能有效解决Choquet积分分类器中符号模糊测度的优化问题。     

结合密集神经网络与长短时记忆模型的中文识别

文本图像识别是计算机视觉领域一项重要任务,而其中的中文识别因种类繁多、结构复杂以及类间相近等特点很具挑战性.为改善这一问题,使用文本行端到端的识别模型.首次提出利用密集卷积神经网络（DenseNet）提取文本图像底层特征,同时避免手工设计、统计图像特征的繁琐;将整行图像特征直接送入双向长短时记忆模型（BLSTM）进行局部相关性分析,减少字符定位分割这一步骤;最后采用时域连接模型（CTC）解码获得识别的文本信息.实验表明所提出的模型可以高效的进行图像文本行的识别,并对图像的多种形变具有较好的鲁棒性.