Brazil

Context: in the field of machine learning models are trained to learn from data, however often the context at which a model is deployed changes, degrading the performances of trained models and giving rise to a problem called Concept Drift (CD), which is a change in data distribution.Motivation: CD has attracted attention in machine learning literature, with works proposing modification to well-known algorithms’ structures, ensembles, online learning and drift detection, but most of the CD literature regards classification, while regression drift is still poorly explored. Objetive: The goal of this work is to perform a comparative study of CD detectors in the context of regression. Results: we found that (i) PH, KSWIN and EDDM showed higher detection averages; (ii) the base learner has a strong impact in CD detection and (iii) the rate at which CD happens also affects the detection process. Conclusion: our experiments were executed in a framework that can easily be extended to include new CD detectors and base learners, allowing future studies to use it.

BRACIS 2021

A Comparative Study on Concept Drift Detectors for Regression

comparative study

concept drift detection

regression

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

technical paper

**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. **STIL** is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: **CE-IA**, **CE-IC** and **CE-PLN**.

To access the 10th Brazilian Conference on Intelligent Systems (**BRACIS**), you need to register for the conference.  Please visit the Conference official site to register

[Register now](http://c4ai.inova.usp.br/bracis2021/)

Register now

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. 
STIL is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: CE-IA, CE-IC and CE-PLN

Adding self-loops at each vertex of a graph improves the performance of quantum walks algorithms over loopless algorithms. Many works approach quantum walks to search for a single marked vertex. In this article, we experimentally address several problems related to quantum walk in the hypercube with self-loops to search for multiple marked vertices. We first investigate the quantum walk in the loopless hypercube. We saw that neighbor vertices are also amplified and that approximately $1/2$ of the system energy is concentrated in them. We show that the optimal value of $l$ for a single marked vertex is not optimal for multiple marked vertices. We define a new value of $l = (n/N)\cdot k$ to search multiple marked vertices. Next, we use this new value of $l$ found to analyze the search for multiple marked vertices non-adjacent and show that the probability of success is close to $1$. We also use the new value of $l$ found to analyze the search for several marked vertices that are adjacent and show that the probability of success is directly proportional to the density of marked vertices in the neighborhood. We also show that, in the case where neighbors are marked, if there is at least one non-adjacent marked vertex, the probability of success increases to close to $1$. The results found show that the self-loop value for the quantum walk in the hypercube to search for several marked vertices is $l = (n / N) \cdot k $.

Lackadaisical quantum walk in the hypercube to search for multiple marked vertices

Several hybrid approaches have been proposed to solve numerical constrained optimization problems. In this paper we present an Improved Interval Differential Evolution (I2DE) that uses structural information of the instance during the optimization process. We extend the math operations supported by a multi-interval core implementation that allows pruning infeasible solutions by using local consistency techniques and a backtrack-free local search. Furthermore, we propose a reformulation of interval evolutionary mutation strategies. A comprehensive experimental analysis is conducted over COCONUT and CEC2018 competition benchmarks and indicates that the hybridization between metaheuristics and constraint programming significantly improves the quality of the solutions. The experimental evaluation shows that our black-box version of I2DE outperformed several state-of-the-art solvers.

I2DE: Improved Interval Differential Evolution for Numerical Constrained Global Optimization

The extensive exploration of the Low Earth Orbit (LEO) has created a dangerous spacial environment, where space debris has threatened the feasibility of future operations. In this sense, Active Debris Removal (ADR) missions are required to clean up the space, deorbiting the debris with a spacecraft. ADR mission planning has been investigated in the literature by means of metaheuristic approaches, focused on maximizing the amount of removed debris given the constraints of the spacecraft. The state-of-the-art approach uses an inver-over and maximal open walk algorithms to solve this problem. However, that approach fails to deal with large instances and duration constraints. This work extends the state of the art, increasing its performance and modeling all the constraints. Experimental results evidence the improvements over the original approach, including the ability to run for scenarios with thousands of debris.

An Enhanced TSP-based Approach for Active Debris Removal Mission Planning

Deception is an essential behavior in many card games. Despite this fact, it is not trivial to capture the intent of a human strategist when making deceptive decisions. That is even harder when dealing with deception in card games, where components of uncertainty, hidden information, luck and randomness introduce the need of case-based decision making. Approaching this problem along with the investigation of the game of Truco, a quite popular game in Southern regions of South America, my presentation introduces an approach that combines active learning and Case-Based Reasoning (CBR) in which agents request a human specialist to review a reused game action retrieved from a case base containing played Truco hands. That happens when the agents are confronted with game situations that are identified as opportunities for deception. The goal is to actively capture problem-solving experiences in which deception can be used, and later employ such case knowledge in the enhancement of the deceptive capabilities of the Truco agents. Experimental results show that the use of the learned cases enabled different kinds of Truco agents to play more aggressively, being more deceptive and performing a larger number of successful bluffs.

Active Learning and Case-Based Reasoning for the Deceptive Play in the Card Game of Truco

Acceptability semantics for the frameworks of weighted argumentation can satisfy up to one of the principles of Quality Precedence, Cardinality Precedence or Compensation, which are pairwise incompatible. In this paper we define two new principles: Quality Compensation and Cardinality Compensation, which are weakened versions of Quality Precedence and Cardinality Precedence, respectively. We show that these new principles are compatible with Compensation and propose two new semantics: a T-conorm-based, which can satisfy Quality Compensation and a cumulative sum-based semantics, which satisfies Cardinality Compensation.

On the Refinement of Compensation-based Semantics for Weighted Argumentation Frameworks

We introduce an interrogation mark ? in ASPIC+ languages as a plausibility operator to enhance any defeasible conclusion does not have the same status as an irrefutable one. The resulting framework, dubbed ASPIC?, is tailored to make a distinction between strong inconsistencies and weak inconsistencies. The aim is to avoid the former and to tolerate the latter. This means the extensions obtained from the ASPIC? framework are free of strong conflicts, but tolerant to weak conflicts. Then, in the current study, we show ASPIC? satisfy reasonable properties. In particular, we focus on the property that a conflict between two arguments should not interfere with the acceptability of other unrelated arguments. With this purpose in mind, we prove under which conditions the important principles of Non-interference and Crash-Resistance hold in ASPIC?.

ASPIC? and the Postulates of Non-Interference and Crash-Resistance

We propose in this paper a framework of prioritised logic programs (PLP) to represent priority information explicitly in a program. Differently of others approaches, we do not restrain the preference relation only to literals, but to sets of literals. As consequence, we can express in PLPs sophisticated forms of preferences without changing the programs or introducing new atoms to obtain artificially the intended preferences. Besides, inspired by various developments in the literature on preference, we present a comprehensive and systematic treatment to deal with preferences in logic programming. In fact, we introduced 32 different criteria (semantics) to establish preference between partial stable models as well as those semantics whose definition depends on partial stable models. We show some properties of our framework; in particular, we guarantee these semantics for PLP generalise their counterparts for logic programs without preferences.

A Systematic Approach to Define Semantics for Prioritised Logic Programs

Value-based health care management models require a precise accounting of health indexes such as risk events monitoring, clinical conditions, patient handling and outcomes. Currently this accounting is performed by manually reading and searching through electronic health records for these indexes. Our research proposes a way to make this an autonomous task that is performed by a computer using a portuguese free-text concept classifier model based on ontologies. To validate our model we tested it on digital clinical records from 191 patients under ischemic stroke care. We have selected 30 management indexes to be identified in these texts. Our model reached, on average 56,8 % of f1-score, varying from 5,83 % to 94,78 % f1-score across different management indexes.

Ontology based classification of electronic health records to support value-based health care

Tactical asset allocation is an essential method for defining a profitable portfolio for a given period. An analyst usually creates a tactical asset portfolio through technical analysis, a process subjective to the analyst's knowledge and interpretations. Another aspect that can directly influence the quality of a portfolio is the number of assets considered for analysis. Human analysts tend to focus on a pre-defined group of assets, limiting choices, and, consequently, the possibility of better results. This work proposes the Stock Network Portfolio Allocation (SNPA) algorithm for the automatic recommendation of a stock portfolio, aiming to maximize profit and minimize risk. The proposed method considers a possibly large set of assets represented as a complex network. In which the nodes represent assets, and the edges stand for the correlation between their returns. Portfolio allocation is done through a random walk on the stock network, selecting, in the end, the most visited nodes (stocks). We conducted investment simulations on Brazilian stocks from the IBrX100 index, for 24 month periods, from Jan. 2018 to Dec. 2019. We compare the results with portfolio strategies: Ibovespa index (IBOV), classic Markowitz’s mean-variance portfolio (MV), Mean Absolute Deviation (MAD) portfolio, Conditional Value at Risk (CVaR), and Hierarchical Risk Parity (HRP). The Shape Ratio (SR), Maximum Drawdown (MDD), and Cumulated Wealth (CW) were used as performance metrics. The SNPA algorithm demonstrated its effectiveness, presenting a CW of 236.3%, being 203.5% above MV portfolio; 181.7% above CVaR portfolio; 175.6% above MAD portfolio, 184.6% above IBOV index, and 165.1% above HRP. SNPA also surpassed the benchmarks considering the performance metrics SR and MDD, with values 0.67 and -1.37 respectively, the best results among the benchmarks were observed by the HRP strategy, with 0.48 in SR index, and MV with -1.39 in MDD index.

Tactical Asset Allocation through Random Walk on Stock Network

Semi-supervised learning has received attention from researchers, as it allows one to exploit the structure of unlabeled data to achieve competitive classification results with much fewer labels than supervised approaches. The Local and Global Consistency (LGC) algorithm is one of the most well-known graph-based semi-supervised (GSSL) classifiers. Notably, its solution can be written as a linear combination of the known labels. The coefficients of this linear combination depend on a parameter𝛼, determining the decay of the reward over time when reaching labeled vertices in a random walk. In this work, we discuss how removing the self-influence of a labeled instance may be beneficial, and how it relates to leave-one-out error. Moreover, we propose to minimize this leave-one-out loss with automatic differentiation. Within this framework, we propose methods to estimate label reliability and diffusion rate. Optimizing the diffusion rate is more efficiently accomplished with a spectral representation. Results show that the label reliability approach competes with robust L1-norm methods and that removing diagonal entries reduces the risk of overfitting and leads to suitable criteria for parameter selection.

Premium content

A Comparative Study on Concept Drift Detectors for Regression

Downloads

Next from BRACIS 2021

Lackadaisical quantum walk in the hypercube to search for multiple marked vertices

Similar lecture

Emerging Relation Network and Task Embedding for Multi-Task Regression Problems

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES