Real-world Data Streams Research Articles

Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy.

Detecting frauds in credit card transactions is perhaps one of the best testbeds for computational intelligence algorithms. In fact, this problem involves a number of relevant challenges, namely: concept drift (customers' habits evolve and fraudsters change their strategies over time), class imbalance (genuine transactions far outnumber frauds), and verification latency (only a small set of transactions are timely checked by investigators). However, the vast majority of learning algorithms that have been proposed for fraud detection rely on assumptions that hardly hold in a real-world fraud-detection system (FDS). This lack of realism concerns two main aspects: 1) the way and timing with which supervised information is provided and 2) the measures used to assess fraud-detection performance. This paper has three major contributions. First, we propose, with the help of our industrial partner, a formalization of the fraud-detection problem that realistically describes the operating conditions of FDSs that everyday analyze massive streams of credit card transactions. We also illustrate the most appropriate performance measures to be used for fraud-detection purposes. Second, we design and assess a novel learning strategy that effectively addresses class imbalance, concept drift, and verification latency. Third, in our experiments, we demonstrate the impact of class unbalance and concept drift in a real-world data stream containing more than 75 million transactions, authorized over a time window of three years.

Parallel Continuous Preference Queries over Out-of-Order and Bursty Data Streams

Techniques to handle traffic bursts and out-of-order arrivals are of paramount importance to provide real-time sensor data analytics in domains like traffic surveillance, transportation management, healthcare and security applications. In these systems the amount of raw data coming from sensors must be analyzed by continuous queries that extract value-added information used to make informed decisions in real-time. To perform this task with timing constraints, parallelism must be exploited in the query execution in order to enable the real-time processing on parallel architectures. In this paper we focus on continuous preference queries, a representative class of continuous queries for decision making, and we propose a parallel query model targeting the efficient processing over out-of-order and bursty data streams. We study how to integrate punctuation mechanisms in order to enable out-of-order processing. Then, we present advanced scheduling strategies targeting scenarios with different burstiness levels, parameterized using the index of dispersion quantity. Extensive experiments have been performed using synthetic datasets and real-world data streams obtained from an existing real-time locating system. The experimental evaluation demonstrates the efficiency of our parallel solution and its effectiveness in handling the out-of-orderness degrees and burstiness levels of real-world applications.

Metacognitive learning approach for online tool condition monitoring

As manufacturing processes become increasingly automated, so should tool condition monitoring (TCM) as it is impractical to have human workers monitor the state of the tools continuously. Tool condition is crucial to ensure the good quality of products: Worn tools affect not only the surface quality but also the dimensional accuracy, which means higher reject rate of the products. Therefore, there is an urgent need to identify tool failures before it occurs on the fly. While various versions of intelligent tool condition monitoring have been proposed, most of them suffer from a cognitive nature of traditional machine learning algorithms. They focus on the how to learn process without paying attention to other two crucial issues: what to learn, and when to learn. The what to learn and the when to learn provide self regulating mechanisms to select the training samples and to determine time instants to train a model. A novel tool condition monitoring approach based on a psychologically plausible concept, namely the metacognitive scaffolding theory, is proposed and built upon a recently published algorithm, recurrent classifier (rClass). The learning process consists of three phases: what to learn, how to learn, when to learn and makes use of a generalized recurrent network structure as a cognitive component. Experimental studies with real-world manufacturing data streams were conducted where rClass demonstrated the highest accuracy while retaining the lowest complexity over its counterparts.

Unsupervised real-time anomaly detection for streaming data

We are seeing an enormous increase in the availability of streaming, time-series data. Largely driven by the rise of connected real-time data sources, this data presents technical challenges and opportunities. One fundamental capability for streaming analytics is to model each stream in an unsupervised fashion and detect unusual, anomalous behaviors in real-time. Early anomaly detection is valuable, yet it can be difficult to execute reliably in practice. Application constraints require systems to process data in real-time, not batches. Streaming data inherently exhibits concept drift, favoring algorithms that learn continuously. Furthermore, the massive number of independent streams in practice requires that anomaly detectors be fully automated. In this paper we propose a novel anomaly detection algorithm that meets these constraints. The technique is based on an online sequence memory algorithm called Hierarchical Temporal Memory (HTM). We also present results using the Numenta Anomaly Benchmark (NAB), a benchmark containing real-world data streams with labeled anomalies. The benchmark, the first of its kind, provides a controlled open-source environment for testing anomaly detection algorithms on streaming data. We present results and analysis for a wide range of algorithms on this benchmark, and discuss future challenges for the emerging field of streaming analytics.

Dynamic adaptation of online ensembles for drifting data streams

The success of data stream mining techniques has allowed decision makers to analyze their data in multiple domains, ranging from monitoring network intrusion to financial markets analysis and online sales transactions exploration. Specifically, online ensembles that construct accurate models against drifting data streams have been developed. Recently, there has been a surge in interest in mobile (or so-called pocket) data stream mining, aiming to construct near real-time models for data stream mining applications that run on mobile devices. In such a setting, it follows that the computational resources are limited and that there is a need to adapt analytics to map the resource usage requirements. Consequently, the resultant models should not only be highly accurate, but they should also adapt swiftly to changes. In addition, the data mining techniques should be fast, scalable, and efficient in terms of resource allocation. It then becomes important to consider Return on Investment (ROI) issues such as storage requirements and memory utilization. This paper introduces the Adaptive Ensemble Size (AES) algorithm, an extension of the Online Bagging method, to address these issues. Our AES method dynamically adapts the sizes of ensembles, based on ROI usage patterns. We illustrate our approach by analyzing the performances against both synthetic and real-world data streams. The results, when comparing our AES algorithm with the state-of-the-art, indicate that we are able to obtain a high Return on Investment (ROI) and to swiftly adapt to change, without compromising on the predictive accuracy.

Time-weighted counting for recently frequent pattern mining in data streams

How can we discover interesting patterns from time-evolving high-speed data streams? How to analyze the data streams quickly and accurately, with little space overhead? How to guarantee the found patterns to be self-consistent? High-speed data stream has been receiving increasing attention due to its wide applications such as sensors, network traffic, social networks, etc. The most fundamental task on the data stream is frequent pattern mining; especially, focusing on recentness is important in real applications. In this paper, we develop two algorithms for discovering recently frequent patterns in data streams. First, we propose TwMinSwap to find top-k recently frequent items in data streams, which is a deterministic version of our motivating algorithm TwSample providing theoretical guarantees based on item sampling. TwMinSwap improves TwSample in terms of speed, accuracy, and memory usage. Both require only O(k) memory spaces and do not require any prior knowledge on the stream such as its length and the number of distinct items in the stream. Second, we propose TwMinSwap-Is to find top-k recently frequent itemsets in data streams. We especially focus on keeping self-consistency of the discovered itemsets, which is the most important property for reliable results, while using O(k) memory space with the assumption of a constant itemset size. Through extensive experiments, we demonstrate that TwMinSwap outperforms all competitors in terms of accuracy and memory usage, with fast running time. We also show that TwMinSwap-Is is more accurate than the competitor and discovers recently frequent itemsets with reasonably large sizes (at most 5–7) depending on datasets. Thanks to TwMinSwap and TwMinSwap-Is, we report interesting discoveries in real world data streams, including the difference of trends between the winner and the loser of U.S. presidential candidates, and temporal human contact patterns.

Adaptive Clustering for Dynamic IoT Data Streams

The emergence of the Internet of Things (IoT) has led to the production of huge volumes of real-world streaming data. We need effective techniques to process IoT data streams and to gain insights and actionable information from real-world observations and measurements. Most existing approaches are application or domain dependent. We propose a method which determines how many different clusters can be found in a stream based on the data distribution. After selecting the number of clusters, we use an online clustering mechanism to cluster the incoming data from the streams. Our approach remains adaptive to drifts by adjusting itself as the data changes. We benchmark our approach against state-of-the-art stream clustering algorithms on data streams with data drift. We show how our method can be applied in a use case scenario involving near real-time traffic data. Our results allow to cluster, label, and interpret IoT data streams dynamically according to the data distribution. This enables to adaptively process large volumes of dynamic data online based on the current situation. We show how our method adapts itself to the changes. We demonstrate how the number of clusters in a real-world data stream can be determined by analyzing the data distributions.

A novel approach using incremental under sampling for data stream mining

<abstract> <p>Data stream mining is every popular in recent years with advanced electronic devices generating continuous data streams. The performance of standard learning algorithms has been compromised with imbalance nature present in real world data streams. In this paper, we propose an algorithm known as Increment Under Sampling for Data streams (IUSDS) which uses an unique under sampling technique to almost balance the data sets to minimize the effect of imbalance in stream mining process. The experimental analysis conducted suggests that the proposed algorithm improves the knowledge discovery over benchmark algorithms like C4.5 and Hoeffding tree in terms of standard performance measures namely accuracy, AUC, precision, recall, F-measure, TP rate, FP rate and TN rate.</p> </abstract>

Fast affinity propagation clustering based on incomplete similarity matrix

Affinity propagation (AP) is a recently proposed clustering algorithm, which has been successful used in a lot of practical problems. Although effective in finding meaningful clustering solutions, a key disadvantage of AP is its efficiency, which has become the bottleneck when applying AP for large-scale problems. In the literature, most of the methods proposed to improve the efficiency of AP are based on implementing the message-passing on a sparse similarity matrix, while neither the decline in effectiveness nor the improvement in efficiency is theoretically analyzed. In this paper, we propose a two-stage fast affinity propagation (FastAP) algorithm. Different from previous work, the scale of the similarity matrix is first compressed by selecting only potential exemplars, then further reduced by sparseness according to k nearest neighbors. More importantly, we provide theoretical analysis, based on which the improvement of efficiency in our method is controllable with guaranteed clustering performance. In experiments, two synthetic data sets, seven publicly available data sets, and two real-world streaming data sets are used to evaluate the proposed method. The results demonstrate that FastAP can achieve comparable clustering performances with the original AP algorithm, while the computational efficiency has been improved with a several-fold speed-up on small data sets and a dozens-of-fold on larger-scale data sets.

An evolutionary algorithm for clustering data streams with a variable number of clusters

Several algorithms for clustering data streams based on k-Means have been proposed in the literature. However, most of them assume that the number of clusters, k, is known a priori by the user and can be kept fixed throughout the data analysis process. Besides the difficulty in choosing k, data stream clustering imposes several challenges to be addressed, such as addressing non-stationary, unbounded data that arrive in an online fashion. In this paper, we propose a Fast Evolutionary Algorithm for Clustering data streams (FEAC-Stream) that allows estimating k automatically from data in an online fashion. FEAC-Stream uses the Page–Hinkley Test to detect eventual degradation in the quality of the induced clusters, thereby triggering an evolutionary algorithm that re-estimates k accordingly. FEAC-Stream relies on the assumption that clusters of (partially unknown) data can provide useful information about the dynamics of the data stream. We illustrate the potential of FEAC-Stream in a set of experiments using both synthetic and real-world data streams, comparing it to four related algorithms, namely: CluStream-OMRk, CluStream-BkM, StreamKM++-OMRk and StreamKM++-BkM. The obtained results show that FEAC-Stream provides good data partitions and that it can detect, and accordingly react to, data changes.

Anomaly detection for smartphone data streams

Smartphones centralize a great deal of users’ private information and are thus a primary target for cyber-attack. The main goal of the attacker is to try to access and exfiltrate the private information stored in the smartphone without detection. In situations where explicit information is lacking, these attackers can still be detected in an automated way by analyzing data streams (continuously sampled information such as an application’s CPU consumption, accelerometer readings, etc.). When clustered, anomaly detection techniques may be applied to the data stream in order to detect attacks in progress. In this paper we utilize an algorithm called pcStream that is well suited for detecting clusters in real world data streams and propose extensions to the pcStream algorithm designed to detect point, contextual, and collective anomalies. We provide a comprehensive evaluation that addresses mobile security issues on a unique dataset collected from 30 volunteers over eight months. Our evaluations show that the pcStream extensions can be used to effectively detect data leakage (point anomalies) and malicious activities (contextual anomalies) associated with malicious applications. Moreover, the algorithm can be used to detect when a device is being used by an unauthorized user (collective anomaly) within approximately 30 s with 1 false positive every two days.

A Support System for Clustering Data Streams with a Variable Number of Clusters

Many algorithms for clustering data streams that are based on the widely used k -Means have been proposed in the literature. Most of these algorithms assume that the number of clusters, k , is known and fixed a priori by the user. Aimed at relaxing this assumption, which is often unrealistic in practical applications, we propose a support system that allows not only estimating the number of clusters automatically from data but also monitoring the process of the data-stream clustering. We illustrate the potential of the proposed system by means of a prototype that implements eight algorithms for clustering data streams, namely, Stream LSearch-OMR k , Stream LSearch-B k M, Stream LSearch-IOMR k , Stream LSearch-IB k M, CluStream-OMR k , CluStream-B k M, StreamKM++-OMR k , and StreamKM++−B k M. These algorithms are combinations of three state-of-the-art algorithms for clustering data streams with fixed k , namely, Stream LSearch, CluStream, and StreamKM++, with two algorithms for estimating the number of clusters, which are Ordered Multiple Runs of k -Means (OMR k ) and Bisecting k -Means (B k M). We experimentally compare the performance of these algorithms using both synthetic and real-world data streams. Analyses of statistical significance suggest that the algorithms that are based on OMR k yield the best data partitions, while the algorithms that are based on B k M are more computationally efficient. Additionally, StreamKM++−OMR k and Stream LSearch-IB k M provide the best tradeoff relationship between accuracy and efficiency.

On Differentially Private Longest Increasing Subsequence Computation in Data Stream

Many important applications require a continuous computation of statistics over data streams. Activities monitoring, surveillance and fraud detections are some settings where it is crucial for the ...

The ubiquitous self-organizing map for non-stationary data streams

The Internet of things promises a continuous flow of data where traditional database and data-mining methods cannot be applied. This paper presents improvements on the Ubiquitous Self-Organized Map (UbiSOM), a novel variant of the well-known Self-Organized Map (SOM), tailored for streaming environments. This approach allows ambient intelligence solutions using multidimensional clustering over a continuous data stream to provide continuous exploratory data analysis. The average quantization error and average neuron utility over time are proposed and used to estimating the learning parameters, allowing the model to retain an indefinite plasticity and to cope with changes within a multidimensional data stream. We perform parameter sensitivity analysis and our experiments show that UbiSOM outperforms existing proposals in continuously modeling possibly non-stationary data streams, converging faster to stable models when the underlying distribution is stationary and reacting accordingly to the nature of the change in continuous real world data streams.

Novel class detection in data streams using local patterns and neighborhood graph

Data stream classification is one of the most challenging areas in the machine learning. In this paper, we focus on three major challenges namely infinite length, concept-drift and concept-evolution. Infinite length causes the inability to store all instances. Concept-drift is the change in the underlying concept and occurs in almost every data stream. Concept-evolution, in fact, is the arrival of novel classes and is an undeniable phenomenon in most real world data streams. There are lots of researches about data stream classification, but most of them focus on the first two challenges and ignore the last one. In this paper, we propose new method based on ensembles whose classifiers use local patterns to enhance the accuracy. Local pattern is a group of Boolean features which have local influence on ordinal and categorical features. Also, in order to enhance the accuracy of novel class detection we construct a neighborhood graph among novel class candidates and analyze connected components of the constructed graph. Experiments on both real and synthetic benchmark data sets show the superiority of the proposed method over the related state-of-the-art techniques.

E-Tree: An Efficient Indexing Structure for Ensemble Models on Data Streams

Ensemble learning is a common tool for data stream classification, mainly because of its inherent advantages of handling large volumes of stream data and concept drifting. Previous studies, to date, have been primarily focused on building accurate ensemble models from stream data. However, a linear scan of a large number of base classifiers in the ensemble during prediction incurs significant costs in response time, preventing ensemble learning from being practical for many real-world time-critical data stream applications, such as Web traffic stream monitoring, spam detection, and intrusion detection. In these applications, data streams usually arrive at a speed of GB/second, and it is necessary to classify each stream record in a timely manner. To address this problem, we propose a novel Ensemble-tree (E-tree for short) indexing structure to organize all base classifiers in an ensemble for fast prediction. On one hand, E-trees treat ensembles as spatial databases and employ an R-tree like height-balanced structure to reduce the expected prediction time from linear to sub-linear complexity. On the other hand, E-trees can be automatically updated by continuously integrating new classifiers and discarding outdated ones, well adapting to new trends and patterns underneath data streams. Theoretical analysis and empirical studies on both synthetic and real-world data streams demonstrate the performance of our approach.

Incremental and decremental active learning for optimized self-adaptive calibration in viscose production

In viscose production, it is important to monitor three process parameters as part of the spin bath in order to assure a high quality of the final product: the concentrations of H2SO4, Na2SO4 and ZnSO4. NIR-spectroscopy is a fast analytical method applicable to conditions of industrial production and is capable of determining those concentrations. The collective composition of the spin bath varies in the industrial process, which implies changes in the matrix of the aforementioned analytes. Thus, conventional static chemometric models, which are trained based on collected calibration spectra from Fourier transform near infrared (FT-NIR) measurements, show a quite imprecise behavior when predicting the concentrations of new on-line data. In this paper, we are presenting a methodology which is able to cope with on-line self-calibration and -adaptation demands in order to compensate high system dynamics, reflected in conceptual changes in the mappings between NIR spectra and target concentrations. The methodology includes intelligent strategies for actively selecting those samples which should be accumulated into and excluded from the current data window in order to optimize the generalization performance of calibration models (thus termed as incremental and decremental active learning stages) while keeping the number of update cycles (and thus required target measurements) as low as possible. This follows the company requirements in terms of necessary cost reduction. Experiments on real-world data streams from viscose production process show that the new self-calibration methods are able to significantly reduce the number of update cycles while still keeping the predictive quality of the calibration models high (below 5% errors) for H2SO4 and Na2SO4. Incremental active learning is able to smoothen and improve the overall quality of the predictions, while decremental active learning achieves a lower number of medium to large prediction errors.

Self-adaptive and local strategies for a smooth treatment of drifts in data streams

In this paper, we are dealing with a new concept for handling drifts in data streams during the run of on-line, evolving modeling processes in a regression context. Drifts require a specific attention in evolving modeling methods, as they usually change the underlying data distribution making previously learnt model parameters and structure outdated. Our approach comes with three new stages for an appropriate drift handling: (1) drifts are not only detected, but also quantified with a new extended version of the Page-Hinkley test; (2) we integrate an adaptive forgetting factor changing over time and which steers the degree of forgetting in dependency of the current drift intensity in the data stream; (3) we introduce local forgetting factors by addressing the different local regions of the feature space with a different forgetting intensity; this is achieved by using fuzzy model architecture within stream learning whose structural components (fuzzy rules) provide a local partitioning of the feature space and furthermore ensure smooth transitions of drift handling topology between neighboring regions. Additionally, our approach foresees an early drift recognition variant, which relies on divergence measures, indicating the degree of divergence in local parts of the feature space separately already before the global model error may start to rise significantly. Thus, it can be seen as an attempt regarding drift prevention on global model level. The new approach is successfully evaluated and compared with fixed forgetting and no forgetting on high-dimensional real-world data streams, including different types of drifts.

Enabling Lazy Learning for Uncertain Data Streams

Lazy learning concept is performing the k-nearest neighbor algorithm, Is used to classification and similarly to clustering of k-nearest neighbor algorithm both are based on Euclidean distance based algorithm. Lazy learning is more advantages for complex and dynamic learning on data streams. In this lazy learning process is consumes the high memory and low prediction Efficiency .this process is less support to the data stream applications. Lazy learning stores the trained data and the inductive process is different until a query is appears, In the data stream applications, the data records flow is continuously in huge volume of data and the prediction of class labels are need to be made in the timely manner. In this paper provide the systematic solution to overcome the memory and efficiency. In this paper proposed a indexing techniques it is dynamically maintained the historical or outdated data stream records. In this paper proposed the tree structure i.e. Novel lazy tree simply called Lazy tree or L-tree.it is the height balanced tree or performing the tree traversing techniques to maintain the trained data. These are help to reduce the memory consumption and prediction it also reduces the time complexity. L-tree is continuously absorb the newly coming stream records and discarded the historical. They are dynamically changes occurred in data streams efficiency for prediction. They are experiments on the real world data streams and uncertain data streams. In this paper experiment on the uncertain data streams .Our experimented uncertain data streams and real world data streams are obtained from UCI Repository.

Urban Sensor Data Streams: London 2013

It is posited that, through the integration of data services in cities can be transformed. In particular, it is thought that pervasive and ubiquitous networked embedded sensing systems can contribute to this transformation. This can be achieved through the exploitation of resultant sensor data stream. In order to effectively consider this hypothesis, it is necessary to investigate and understand the current art of pervasive and ubiquitous sensing in the city, and the resultant data streams. We provide an objective summary review of the urban sensing landscape, across multiple services and sectors. The scope of the review is limited to the city of London, which is often regarded as one of the most technologically advanced and digitized cities in the World. We catalogue the technological, spatiotemporal and representational characteristics of these open real-world sensor data streams, and how they came to existence.