Since a few years, audio signal processing has been focused on detecting audio events in general, and defining anomalous/outlier sounds in particular. The application of such an anomaly detection problem to audio surveillance systems is made possible thanks to the advances of anomaly detection techniques, in particular for highly unbalanced data. However, outdoor audio signals are characterized by a high degree of uncertainty, since there is no way to model each category of sound, whether normal or anomalous, in presence of background noise. Thus, this paper proposes a rare/anomalous sound event detection method for road traffic surveillance, which aims at detecting hazardous events, such as car accidents, in presence of traffic noise. To model uncertainty for anomaly detection, the suggested method combines deep reconstruction techniques, interval-valued type-2 fuzzy sets and interval comparison methods. First, the reconstruction error of the input audio segment is yielded by a deep variational autoencoder which is trained on normal data only. Based on this reconstruction error, a fuzzy membership function with pessimistic/lower and optimistic/upper components is calculated. Next, a probabilistic interval comparison method is used to compute the membership score, and thus to evaluate the interval-valued fuzzy sets. Finally, defuzzification is used to classify events as normal or anomalous. During this process, several types of linear or nonlinear membership functions are utilized to model uncertainty with respect to the input, i.e ., the VAE reconstruction error, or to the output, i.e ., the value of the primary membership. According to the results obtained, the proposed method outperforms the state-of-the-art one-class SVM for anomaly detection and the baseline VAE error thresholding method, when specific parameters are carefully set, such as the weights of the anomalous/normal subsets and the lower/upper bounds of the membership function's components. Furthermore, the proposed linear and nonlinear membership functions succeed to improve modeling uncertainty in audio signals by interval-valued type-2 fuzzy sets, with regard to: a) the input, i.e ., the VAE reconstruction error, and b) the primary membership value, respectively.

This paper introduces a novel approach, inspired by the principles of Quantum Computing, to address web bot detection in terms of real-time classification of an incoming data stream of HTTP request headers, in order to ensure the shortest decision time with the highest accuracy. The proposed approach exploits the analogy between the intrinsic correlation of two or more particles and the dependence of each HTTP request on the preceding ones. Starting from the a-posteriori probability of each request to belong to a particular class, it is possible to assign a Qubit state representing a combination of the aforementioned probabilities for all available observations of the time series. By leveraging the underlying mathematical details of superposition and entanglement on specific subsequences, it is possible to devise a measure of membership to each class, thus enabling the system to take a reliable decision when a sufficient level of confidence is met or to continue with additional observations. The results reported in this paper objectively show the effectiveness of our quantum-inspired algorithm which outperforms other state-of-the-art approaches, including our own one based on the Sequential Probability Ratio Test.

A large fraction of traffic on present-day Web servers is generated by bots — intelligent agents able to traverse the Web and execute various advanced tasks. Since bots’ activity may raise concerns about server security and performance, many studies have investigated traffic features discriminating bots from human visitors and developed methods for automated traffic classification . Very few previous works, however, aim at identifying bots on-the-fly, trying to classify active sessions as early as possible. This paper proposes a novel method for binary classification of streams of Web server requests in order to label each active session as “bot” or “human”. A machine learning approach has been developed to discover traffic patterns from historical usage data. The model, built on a neural network , is used to classify each incoming HTTP request and a sequential probabilistic analysis approach is then applied to capture relationships between subsequent HTTP requests in an ongoing session to assess the likelihood of the session being generated by a bot or a human, as soon as possible. A performance evaluation study with real server traffic data confirmed the effectiveness of the proposed classifier in discriminating bots from humans at early stages of their visits, leaving very few of them undecided, with very low number of false positives .

Web traffic on e-business sites is increasingly dominated by artificial agents (Web bots) which pose a threat to the website security, privacy, and performance. To develop efficient bot detection methods and discover reliable e-customer behavioural patterns, the accurate separation of traffic generated by legitimate users and Web bots is necessary. This paper proposes a machine learning solution to the problem of bot and human session classification, with a specific application to e-commerce. The approach studied in this work explores the use of unsupervised learning (k-means and Graded Possibilistic c-Means), followed by supervised labelling of clusters, a generative learning strategy that decouples modelling the data from labelling them. Its efficiency is evaluated through experiments on real e-commerce data, in realistic conditions, and compared to that of supervised learning classifiers (a multi-layer perceptron neural network and a support vector machine). Results demonstrate that the classification based on unsupervised learning is very efficient, achieving a similar performance level as the fully supervised classification. This is an experimental indication that the bot recognition problem can be successfully dealt with using methods that are less sensitive to mislabelled data or missing labels. A very small fraction of sessions remain misclassified in both cases, so an in-depth analysis of misclassified samples was also performed. This analysis exposed the superiority of the proposed approach which was able to correctly recognize more bots, in fact, and identified more camouflaged agents, that had been erroneously labelled as humans.

We introduce an analysis method for electroencephalography (EEG) data, focused on event-related potentials (ERPs). Our approach is unsupervised and makes use of a fuzzy clustering algorithm based on the possibilistic framework and includes a data-driven noise and artifact rejection phase. Our contribution provides a general analysis tool, applicable to any ERP dataset, which can uncover the dataset's internal structure. The fuzzy clustering algorithm is the core of our method, since its fine-grained membership grades how much a sample belongs to a given cluster, making the method applicable even when groups have a certain overlap. Prior to the clustering step, we apply weights to the feature vectors, optimizing them in order to enhance the variance within the dataset, and we extract time-window-interval-based features inspired by interval arithmetic. We apply the data processing workflow to the analysis of a set of ERPs recorded during an emotional Go/NoGo task. We evaluate the performance of the unsupervised analysis by computing a measure based on the clusterization rate of trials in different experimental conditions. The results of the studied dataset show that the proposed method obtains a difference of clusterization rate of 69% in Go versus NoGo trials, when weights and interval features are applied to the data, improving previous work not including weights and interval features, which had a rate of 31%. Furthermore, when compared with the standard fuzzy c-means, our proposed possibilistic clustering algorithm outperforms it in terms of the clusterization rate. We also examine the effect of preprocessing the data with independent component analysis and removing noise-related components and observe that this does not improve significantly the obtained results. These findings demonstrate that our proposed method provides a valuable data processing workflow robust to EEG artifacts and able to produce a clustering that is coherent with the experimental conditions represented in the ERP dataset.

Data streams have arisen as a relevant topic during the last few years as an efficient method for extracting knowledge from big data. In the robust layered ensemble model (RLEM) proposed in this paper for short-term traffic flow forecasting, incoming traffic flow data of all connected road links are organized in chunks corresponding to an optimal time lag. The RLEM model is composed of two layers. In the first layer, we cluster the chunks by using the Graded Possibilistic c-Means method. The second layer is made up by an ensemble of forecasters, each of them trained for short-term traffic flow forecasting on the chunks belonging to a specific cluster. In the operational phase, as a new chunk of traffic flow data presented as input to the RLEM, its memberships to all clusters are evaluated, and if it is not recognized as an outlier, the outputs of all forecasters are combined in an ensemble, obtaining in this a way a forecasting of traffic flow for a short-term time horizon. The proposed RLEM model is evaluated on a synthetic data set, on a traffic flow data simulator and on two real-world traffic flow data sets. The model gives an accurate forecasting of the traffic flow rates with outlier detection and shows a good adaptation to non-stationary traffic regimes. Given its characteristics of outlier detection, accuracy, and robustness, RLEM can be fruitfully integrated in traffic flow management systems.

In this paper, we study a kernel extension of the classic possibilisticc-means. In the proposed extension, we implicitly map input patterns into a possibly high-dimensional space by means of positive semidefinite kernels. In this new space, we model the mapped data by means of the possibilistic clustering algorithm. We study in more detail the special case where we model the mapped data using a single cluster only, since it turns out to have many interesting properties. The modeled memberships in kernel-induced spaces yield a modeling of generic shapes in the input space. We analyze in detail the connections to one-class support vector machines and kernel density estimation, thus, suggesting that the proposed algorithm can be used in many scenarios of unsupervised learning. In the experimental part, we analyze the stability and the accuracy of the proposed algorithm on some synthetic and real datasets. The results show high stability and good performances in terms of accuracy.

MicroRNAs are a class of short, non-coding RNA regulating the expression of genes involved in several biological processes. This paper addresses the computational identification of target genes for microRNAs, in particular those involved in the development of prostate cancer. The available tools, in particular the miRanda program, need to be validated against biological evidence. We identify several refinement of the algorithm, and provide an optimization of the parameters involved, by means of a genetic algorithm, so as to maximize the adherence of results to biological evidence. The increased selectivity of the method may also be used to guide experimental validation in a more focused direction.

Forecasting the tide level in the Venezia lagoon is a very compelling task. In this work we propose a new approach to the learning of tide level time series based on the local learning procedure of Bottou and Vapnik, by considering the use of a fuzzy method for the selection of the closest patterns to the one to forecast. We made use also as learners of Support Vector Machines and of their ensembles based on Bagging and AdaBoost. The obtained forecasts of 500 randomly selected tide levels seem to be quite promising. Good performances are also noticed for forecasts of a set of 80 tide levels corresponding to exceptional periods with high tide and sea variabilities. The obtained forecasts of 80 selected tide levels compare very favorably with those of the baseline linear regressor model.

Linear fuzzy clustering is a useful tool for knowledge discovery in databases (KDD), and several modifications have been proposed in order to analyze real world data. This paper proposes a new approach for estimating local linear models, in which linear fuzzy clustering is performed by selecting variables that are useful for extracting correlation structure in each cluster. The new clustering model uses two types of memberships. One is the conventional membership that represents the degree of membership of each sample in each cluster. The other is the additional parameter that represents the relative responsibility of each variable for estimation of local linear models. The additional membership takes large values when the variable has close relationship with local principal components, and is calculated by using the graded possibilistic approach. Numerical experiments demonstrate that the proposed method is useful for identifying local linear model taking typicality of each variable into account.

Genomic data are often characterized by small cardinality and high dimensionality. For those data, a feature selection procedure could highlight the relevant genes and improve the classification results. In this paper we propose a wrapper approach to gene selection in classification of gene expression data using simulated annealing and SVM. The proposed approach can do global combinatorial searches through the space of possible input subsets, can handle cases with numerical, categorical or mixed inputs, and is able to find (sub-)optimal subsets of input variables giving very low classification errors. The method has been tested on the publicly available data sets Leukemia by Golub et al. and Colon by Alon at al. The experimental results highlight the capacity of the method to select minimal sets of relevant genes.

In the fuzzy clustering literature, two main types of membership are usually considered: A relative type, termed probabilistic, and an absolute or possibilistic type, indicating the strength of the attribution to any cluster independent from the rest. There are works addressing the unification of the two schemes. Here, we focus on providing a model for the transition from one schema to the other, to exploit the dual information given by the two schemes, and to add flexibility for the interpretation of results. We apply an uncertainty model based on interval values to memberships in the clustering framework, obtaining a framework that we term graded possibility. We outline a basic example of graded possibilistic clustering algorithm and add some practical remarks about its implementation. The experimental demonstrations presented highlight the different properties attainable through appropriate implementation of a suitable graded possibilistic model. An interesting application is found in automated segmentation of diagnostic medical images, where the model provides an interactive visualization tool for this task

Linear fuzzy clustering is a useful tool for knowledge discovery in databases (KDD), and several modifications have been proposed in order to analyze real world data. This paper proposes a new approach for estimation of local linear models, in which linear fuzzy clustering is performed by selecting variables in each cluster. The new clustering model uses two types of memberships. One is the conventional membership that represents the degree of membership of each sample. The other is the additional parameter that represents the responsibility of each variable and is given by the graded possibilistic approach. Numerical experiments demonstrate the characteristics of the proposed technique

Clustering algorithms in biomedical disciplines are usually selected between two main families, k-means and agglomerative hierarchical clustering. These methods are well studied and well established. However, both categories have some drawbacks related to data dimensionality (for partitional algorithms) and to the bottom-up structure (for hierarchical algorithms). To overcome these limitations, we present a hierarchical clustering algorithm based on a completely different principle, which is the analysis of shared farthest neighbors. The principle of operation and the rationale are illustrated, and experimental results on different data sets are presented.

The human leukocyte antigens (HLA) system consists of three regions in the human genome. In transplantation, the match between donor's and receiver's HLA is critical for histocompatibility. HLA typing problem consists in the donor's and receiver's HLA systems matching. We describe the image analysis module of a decision supporting system supporting the application of the oligonucleotide microarray technology to the HLA typing. The decision supporting system is based on a fuzzy modeling approach that allows the biologist to describe and classify the probe activations using its language and concepts in a natural way, and, at the same time, supports a robust interactive image filtering with the usage of a fuzzy basis functions network.

This paper presents the graded possibilistic model. After reviewing some clustering algorithms derived from c-Means, we provide a unified perspective on these clustering algorithms, focused on the memberships rather than on the cost function. Then the concept of graded possibility is introduced. This is a partially possibilistic version of the fuzzy clustering model, as compared to Krishnapuram and Keller's possibilistic clustering. We outline a basic graded possibilistic clustering algorithm and highlight the different properties attainable by means of experimental demonstrations.

The paper addresses the issue of assessing the importance of input variables with respect to a given dichotomic classification problem. Both linear and non-linear cases are considered. In the linear case, the application of derivative-based saliency yields a commonly adopted ranking criterion. In the nonlinear case, the method is extended by introducing a resampling technique and by clustering the obtained results for stability of the estimate. The work is preliminary, and many properties and options are to be investigated in future research.

We consider a popular approach to multicategory classification tasks: a two-stage system based on a first classifier with rejection followed by a nearest-neighbor classifier. Patterns which are not rejected by the first classifier are classified according to its output. Rejected patterns are passed to the nearest-neighbor classifier together with the top-h ranking classes returned by the first classifier. The nearest-neighbor classifier, looking at patterns in the top-h classes, classifies the rejected pattern. An editing strategy for the nearest-neighbor reference database, controlled by the first classifier, is also considered. We analyze this system. Moreover, we formally relate the response time of the system to the rejection rate of the first classifier and to the other system parameters. The error-response time trade-off is also discussed. Finally, we experimentally study two instances of the system applied to the recognition of handwritten digits. In one system, the first classifier is a fuzzy basis functions network, while in the second system it is a feed-forward neural network. Classification results as well as response times for different settings of the system parameters are reported for both systems.

We present a new learning machine model for classification problems, based on decompositions of multiclass classification problems in sets of two-class subproblems, assigned to nonlinear dichotomizers that learn their task independently of each other. The experimentation performed on classical data sets, shows that this learning machine model achieves significant performance improvements over MLP, and previous classifiers models based on decomposition of polychotomies into dichotomies. The theoretical reasons of the good properties of generalization of the proposed learning machine model are explained in the framework of the statistical learning theory.

The pattern recognition problem in RICH counters concerns the identification of an unknown number of imperfect roughly-circular rings made of a low number of discrete points in presence of background. We present some preliminary results obtained using the Possibilistic C-Spherical Shell algorithm. In particular, we show that the algorithm is very tolerant and robust to noise (outliers rate) level. Moreover, for complex images full of rings, we introduce an iterative scheme that greatly improves performance. Also, the rings are not required to be complete, arcs are sufficient to recognize the underlying rings.

Decomposition methods for multiclass classification problems constitute a powerful framework to improve generalization capabilities of a large set of learning machines, including support vector machines and multi-layer perceptrons. We present a review of the main decomposition approach to classification and an experimental comparison of One-Per-Class (OPC), Correcting Classifiers (CC) and Error Correcting Output Codes (ECOC) decomposition methods implemented using multi-layer perceptrons as dichotomizers. The results show that CC and ECOC outperform OPC over the considered data sets.