Brazil

Novelty detection is an important topic in data stream classification, as it is responsible for identifying the emergence of new concepts, new patterns, and outliers. It becomes necessary when the true label of an instance is not available right after its classification. The time between the classification of an instance and the arrival of its true label is called latency. This is a common scenario in data streams applications. However, most classification algorithms do not consider such a problem and assume that there will be no latency. On the other hand, a few methods in the literature cope with the existence of infinite latency and novelty detection in data streams. In this work, however, we focus on the scenario where the true labels will be available to the system after a certain time, called intermediate latency. Such a scenario is present in the stock market and weather datasets. Moreover, aiming for more flexible learning to deal with the uncertainties inherent in data streams, we consider the use of fuzzy set theory concepts. Therefore, we propose a method for classification and novelty detection in data streams called Fuzzy Classifier with Novelty Detection for data streams (FuzzCND). Our method uses an ensemble of fuzzy decision trees to perform the classification of new instances and applies the concepts of fuzzy set theory to detect possible novelties. The experiments showed that our approach is promising in dealing with the emergence of new concepts in data streams and inaccuracies in the data.

BRACIS 2020

A Fuzzy Approach For Classification and Novelty Detection in Data Streams Under Intermediate Latency

novelty detection and fuzzy.

data streams

classification

The 9th Brazilian Conference on Intelligent Systems (BRACIS), the 16h Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), and the 12th Concurso de Teses e Dissertações em Inteligência Artificial e Computacional (CTDIAC) was held from 20 to 23 October, 2020.

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence - SBIA (22 editions), and the Brazilian Symposium on Neural Networks - SBRN (13 editions). ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. CTDIAC is a satellite event whose goals are to disseminate and award the best dissertations and theses (MSc and PhDs concluded in Brazilian universities from June 2018 to May 2020) in Artificial and Computational Intelligence areas.

In this year, the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) will be held in conjunction with BRACIS 2020. This sysposium aims at integrating researchers, practitioners, developers, students and users to present their research results, to discuss ideas, and to exchange techniques, tools, and practical experiences – related to the Data Mining and Machine Learning areas.

technical paper

Presentation will be about the paper entitled FT-BlinGui: a fuzzy-based wearable device system to avoid visually impaired collision in real time. There are several technological applications and computational techniques for detection and prevention of obstacles. To provide a more efficient perception of obstacles in dynamic scenarios, the fuzzy systems embedded in technological applications have been presented as an efficient approach. Was investigated the applicability of the fuzzy time series for the forecasting collision with obstacles. The time series analyzed was obtained through a wearable device that detects, in real time, obstacles for the visually impaired. Simulation results demonstrate that FT-BlinGui can provide a collision-avoidance alerting system for wearable devices as a result of Fuzzy Time Series forecasting.



FT-BlinGui: a fuzzy-based wearable device system to avoid visually impaired collision in real time

Aggregation functions are employed to combine inputs that are typically interpreted as degrees of membership in fuzzy sets, degrees of preference, strength of evidence or support of a hypothesis. The behavior of each aggregation function can be associated to the area of distributive justice, which refers to fairness in the way data are distributed. Two important theories of distributive justice commonly considered are the utilitarianism and egalitarianism, but some alternative theories, as the sufficientarianism, has gained attention recently. This paper presents three different versions of sufficientarianism as aggregation functions: the weak, axiological and strong sufficientarianism. Additionally, we introduce new logical properties related to the sufficientarianism and show which of these new aggregation functions satisfy them. In particular, we prove the axiological aggregation functions introduced here satisfy an important logical property whereas the weak sufficientarian functions do
not. On the other hand, we also show the strong sufficientarian aggregation
functions may lead to the loss of logical properties.

Aggregation with Weak, Axiological and Strong Sufficientarian Functions

An ensemble method should cleverly combine a group of base classifiers to yield an improved classifier. The majority vote is an example of a methodology used to combine classifiers in an ensemble method. In this paper, we propose to combine classifiers using an associative memory model. Precisely, we introduce ensemble methods based on recurrent correlation associative memories (RCAMs) for binary classification problems. We show that an RCAM-based ensemble classifier can be viewed as a majority vote classifier whose weights depend on the similarity between the base classifiers and the resulting ensemble method. More precisely, the RCAM-based ensemble combines the classifiers using a recurrent consult and vote scheme. Furthermore, computational experiments confirm the potential application of the RCAM-based ensemble method for binary classification problems.


Ensemble of Binary Classifiers Combined Using Recurrent Correlation Associative Memories

Link prediction is an online social network (OSN) analysis task whose objective is to identify pairs of non-connected nodes that have a high probability of getting connected in the near future. Recently proposed link prediction methods consider topological data from OSN past states (i.e., snapshots that depict the structure of the network at certain moments in the past). Although those past states-based methods retrieve information that describes how the network's topology was at the events of link emergence (i.e., moments when the existing edges were created), they do not take into account contextual data concerning those events. Hence, they take the chance to disregard information about the circumstances that may have influenced the appearance of old edges, and that could be useful to predict the creation of new ones. To remedy this issue, this work extends a past states-based method so that it retrieves both topological and contextual data from the events of edge emergence and combines them to predict links. The extended method presented promising results on experimental data. Overall, it overcame the original method in five different scenarios from five co-authorship OSN frequently used for link prediction method evaluation.

Link prediction in social networks: an edge creation history retrieval-based method that combines topological and contextual data

Unbalanced community structures is a common phenomenon when representing real-world systems using Complex Networks; however, not all community detection model can correctly identify communities of different sizes. In this paper, we propose a community detection technique focusing on the detection of unbalanced communities. The method augments the Particle Competition model: a bio-inspired technique that employs a set of particles (random walkers) into the network to compete for its nodes. However, the detection of unbalanced communities in the original Particle Competition is impossible because every particle shares the same ability to defend and attack nodes. The proposed model introduces a second stage into the system, named Regularization, which explicitly handles the detection of unbalanced communities. This mechanism uses the neighborhood of the nodes to create a custom preference guide for each particle, specifically tailored to the community of the particle. As a result, the model can precisely detect unbalanced community structures. Furthermore, the model achieves higher accuracy and faster computational speed compared to the original Particle Competition model.

Particle Competition for Unbalanced Community Detection in Complex Networks

One of the main challenges in Machine Learning and Data Mining fields is the treatment of large Data Streams in the presence of Concept Drifts. This paper presents two families of ensemble algorithms designed to adapt to abrupt and gradual concept drifts. The families Fast Stacking of Ensembles boosting the Old (FASEO) and Fast Stacking of Ensembles boosting the Best (FASEB) are adaptations of the Fast Adaptive Stacking of Ensembles (FASE) algorithm to improve run-time, without presenting a significant decrease in terms of accuracy when compared to the original FASE. In order to achieve a more efficient model, adjustments were made in the update strategy and voting procedure of the ensemble. To evaluate the methods, Naive Bayes (NB) and Hoeffding Tree (HT) are used, as learners, to compare the performance of the algorithms on artificial and real-world data-sets. An experimental investigation with a total of 32 experiments and the application of Friedman and Bonferroni-Dunn statistical tests showed the families FASEO and FASEB are more efficient than FASE with respect to execution time in many experiments, also some methods achieving better accuracy results.


Comparative study of Fast Stacking Ensembles families algorithms

Incremental machine learning algorithms have been effective alternatives to deal with stream data.
The Hoeffding Tree framework is one of the most successful solutions for supervised online prediction tasks.
Although online regression tasks are present in several forms, and in many real-life problems, most of the research efforts have been devoted to classification.
Existing regression tree solutions have strong limitations, mainly regarding their memory usage and running time.
Hence, a new algorithm able to address these aspects in Hoeffding Tree Regressors is a relevant research issue.
We propose 2CS, a correlation-guided strategy to speed up Hoeffding Tree Regressor training.
2CS is conceptually simple and works by avoiding the exhaustive evaluation of all possible features as split candidates, as occurs in the existing solutions.
Moreover, 2CS can be easily merged into existing incremental tree solutions and online tree ensembles algorithms, such as bagging and boosting.
Throughout an extensive experimental evaluation, we show that the induction of 2CS-based models can be significantly faster than the traditional Hoeffding Tree Regressor algorithms, whereas retaining similar predictive power and memory use.

2CS: Correlation-guided Split Candidate\\Selection in Hoeffding Tree Regressors

Ontologies are used in Information Systems to manage and share knowledge pertaining to different domains, considering it is common that one particular piece of knowledge is modeled individually into different ontologies. Alignment processes are carried out towards interoperability; however, the results are not effective in most cases, requiring manual repair and review by domain experts. Thus, this work introduces a repair and review tool for the alignment of ontologies with the goal
of assisting experts in the alignment repair tasks. Using the technology acceptance model, a proof of concept was made to analyze the perception by domain experts regarding the tool’s usefulness, ease, and intention of use. From statistical analyses in terms of reliability, default path, inference, and correlation, it has been found that study participants had a positive perception of the tool’s usefulness and ease in the tasks of ontology alignment repair. Therefore, the tool and its functionalities
proved to be useful towards assisting domain experts in their tasks of reducing the semantic heterogeneity among ontologies pertaining to the same domain through alignment repair.

A Useful Tool to Support the Ontology Alignment Repair

Most ensemble methods for classification and regression tasks are based on a simple naive technique such as bagging, where all models' outputs are combined in a single last label. But in this paper, we evaluate a meta-learning approach that for each instance a different subset of classifiers is chosen.

Downloads

Next from BRACIS 2020

FT-BlinGui: a fuzzy-based wearable device system to avoid visually impaired collision in real time

Similar lecture

Data Streams are Time Series: Challenging Assumptions

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from BRACIS 2020

FT-BlinGui: a fuzzy-based wearable device system to avoid visually impaired collision in real time

Similar lecture

Data Streams are Time Series: Challenging Assumptions

Downloads