Hansenclever Bassani

Ph.D. in Computer Science and Assistant Professor at Universidade Federal de Pernambuco

contact: hfb@cin.ufpe.br
     

Research Areas

Machine Learning | Robotics | Computer Vision | Natural Language | Cognitive Science


Work

Mila Quebec Artificial Intelligence Institute
Visiting Researcher (2018-2019)

Universidade Federal de Pernambuco (UFPE)
Professor (2014-Current)

Instituto Federal de Educação, Ciência e Tecnologia de Pernambuco (IFPE)
Temporary Lecturer (2009 - 2011)


Teaching


Selected Research Projects

 

Social Mobile Robots with Dexterous Manipulation (2015 - Current)
Aluizio Fausto Ribeiro Araújo, Bruno José Torres Fernandes, Byron Leite Dantas Bezerra, Carmelo José Albanez Bastos Filho, Fernando Buarque de Lima Neto, Hansenclever de França Bassani, Jaelson Freire Brelaz de Castro, João Miguel da Costa Sousa, Judith Kelner, Paulo da Costa Luís da Fonseca Pinto, Sérgio Campello Oliveira
Funding:
- Conselho Nacional de Desenvolvimento Científico e Tecnológico - CNPq
- Fundação de Amparo a Ciência e Tecnologia do Estado de Pernambuco - FACEPE

Robotic Infrared Detection System for Real-Time Thermal Monitoring and Evaluation of Substation Equipment (2013 - 2016)
Aluizio Fausto Ribeiro Araújo, Hansenclever de França Bassani, Tsang Ing Ren, Daniel de Filgueiras Gomes, Orivaldo Vieira de Santana Junior, Diêgo João Costa Santiago
Funding:
- Companhia Hidro Elétrica do São Francisco - CHESF
- Agência Nacional de Energia Elétrica - ANEEL

Intelligent Systems for External Inspection of Underwalter and Underground Pipelines (2006 - 2008)
Aluizio Fausto Ribeiro Araújo, Fernando Buarque de Lima Neto, Hansenclever de França Bassani, Daniel de Filgueiras Gomes, Guilherme de Alencar Barreto, José Maria P. de Menezes Jr., Marcelo Pita
Funding:
- Petróleo Brasileiro S.A. — Petrobras
- Agência Nacional do Petróleo, Gás Natural e Biocombustíveis - ANP

Selected Publications

 

This article proposes a biologically inspired neurocomputational architecture which learns associations between words and referents in different contexts, considering evidence collected from the literature of Psycholinguistics and Neurolinguistics. The multi-layered architecture takes as input raw images of objects (referents) and streams of word’s phonemes (labels), builds an adequate representation, recognizes the current context, and associates label with referents incrementally, by employing a Self-Organizing Map which creates new association nodes (prototypes) as required, adjusts the existing prototypes to better represent the input stimuli and removes prototypes that become obsolete/unused. The model takes into account the current context to retrieve the correct meaning of words with multiple meanings. Simulations show that the model can reach up to 78% of word-referent association accuracy in ambiguous situations and approximates well the learning rates of humans as reported by three different authors in five Cross-Situational Word Learning experiments, also displaying similar learning patterns in the different learning conditions.
2019 - A Neural Network Architecture for Learning Word-Referent Associations in Multiple Contexts

Hansenclever Bassani, Aluizio Araujo

Neural Networks
PDF

In this paper, the task of unsupervised visual object categorization (UVOC) is addressed. We utilize a variant of Self-organizing Map (SOM) to cluster images in two different scenarios: disjoint (images from Caltech256) and non-disjoint (images from MSRC2) sets. First, we ran several tests to evaluate different image representation techniques: features obtained by a deep convolutional network were compared with those obtained by handcrafted methods, such as SIFT combined with a set of interest point detectors. As expected, we found that deep convolutional network features significantly outperformed its handcrafted counterparts. After choosing the best image representation technique, we compared the state-of-the-art image clustering algorithms with a SOM-based subspace clustering method that identifies automatically the relevant features in the high-dimensional image representations. The results have shown that our method achieves substantially lower clustering error than all competitors in several challenging testing settings.
2019 - Dynamic topology and relevance learning SOM-based algorithm for image clustering tasks

Heitor Medeiros, Felipe Oliveira, Hansenclever Bassani, Aluizio Araujo

Computer Vision and Image Understanding
PDF

In the recent years, there is a growing interest in semi-supervised learning, since, in many learning tasks, there is a plentiful supply of unlabeled data, but insufficient labeled ones. Hence, Semi-Supervised learning models can benefit from both types of data to improve the obtained performance. Also, it is important to develop methods that are easy to parameterize in a way that is robust to the different characteristics of the data at hand. This article presents a new Self-Organizing Map (SOM) based method for clustering and classification, called Adaptive Local Thresholds Semi-Supervised Self-Organizing Map (ALTSS-SOM). It can dynamically switch between two forms of learning at training time according to the availability of labels, as in previous models, and can automatically adjust itself to the local variance observed in each data cluster. The results show that the ALTSS-SOM surpass the performance of other semisupervised methods in terms of classification, and other pure clustering methods when there are no labels available, being also less sensitive than previous methods to the parameters values.
2019 - A Semi-Supervised Self-Organizing Map with Adaptive Local Thresholds

Pedro Braga, Hansenclever Bassani

International Joint Conference on Neural Networks (IJCNN)
PDF

There has been an increasing interest in semi-supervised learning in the recent years because of the great number of datasets with a large number of unlabeled data but only a few labeled samples. Semi-supervised learning algorithms can work with both types of data, combining them to obtain better performance for both clustering and classification. Also, these datasets commonly have a high number of dimensions. This article presents a new semi-supervised method based on self-organizing maps (SOMs) for clustering and classification, called Semi-Supervised Self-Organizing Map (SS-SOM). The method can dynamically switch between supervised and unsupervised learning during the training according to the availability of the class labels for each pattern. Our results show that the SS-SOM outperforms other semi-supervised methods in conditions in which there is a low amount of labeled samples, also achieving good results when all samples are labeled.
2018 - A Semi-Supervised Self-Organizing Map for Clustering and Classification

Pedro Braga, Hansenclever Bassani

International Joint Conference on Neural Networks (IJCNN)
PDF

This paper introduces an incremental semantic mapping approach, with on-line unsupervised learning, based on Self-Organizing Maps (SOM) for robotic agents. The method includes a mapping module, which incrementally creates a topological map of the environment, enriched with objects recognized around each topological node, and a module of places categorization, endowed with an incremental unsupervised learning SOM with on-line training. The proposed approach was tested in experiments with real-world data, in which it demonstrates promising capabilities of incremental acquisition of topological maps enriched with semantic information, and for clustering together similar places based on this information. The approach was also able to continue learning from newly visited environments without degrading the information previously learned.
2018 - Incremental Semantic Mapping with Unsupervised On-line Learning

Ygor C. N. Sousa, Hansenclever Bassani

International Joint Conference on Neural Networks (IJCNN)
PDF

Time Series Motif Discovery (TSMD) is defined as searching for patterns that are previously unknown and appear with a given frequency in time series. Another problem strongly related with TSMD is Word Segmentation. This problem has received much attention from the community that studies early language acquisition in babies and toddlers. The development of biologically plausible models for word segmentation could greatly advance this field. Therefore, in this article, we propose the Variable Input Length Map (VILMAP) for Motif Discovery and Word Segmentation. The model is based on the Self-Organizing Maps and can identify Motifs with different lengths in time series. In our experiments, we show that VILMAP presents good results in finding Motifs in a standard Motif discovery dataset and can avoid catastrophic forgetting when trained with datasets with increasing values of input size. We also show that VILMAP achieves results similar or superior to other methods in the literature developed for the task of word segmentation.
2018 - Self-Organizing Maps with Variable Input Length for Motif Discovery and Word Segmentation

Raphael C. Brito, Hansenclever Bassani

International Joint Conference on Neural Networks (IJCNN)
PDF

When working with decomposition-based algorithms, an appropriate set of weights might improve quality of the final solution. A set of uniformly distributed weights usually leads to well-distributed solutions on a Pareto front. However, there are two main difficulties with this approach. Firstly, it may fail depending on the problem geometry. Secondly, the population size becomes not flexible as the number of objectives increases. In this paper, we propose the MOEA/D with Uniformly Randomly Adaptive Weights (MOEA/D-URAW) which uses the Uniformly Randomly method as an approach to subproblems generation, allowing a flexible population size even when working with many objective problems. During the evolutionary process, MOEA/D-URAW adds and removes subproblems as a function of the sparsity level of the population. Moreover, instead of requiring assumptions about the Pareto front shape, our method adapts its weights to the shape of the problem during the evolutionary process. Experimental results using WFG41-48 problem classes, with different Pareto front shapes, shows that the present method presents better or equal results in 77.5% of the problems evaluated from 2 to 6 objectives when compared with state-of-the-art methods in the literature.
2018 - MOEA/D with uniformly randomly adaptive weights

Lucas R. C. de Farias, Pedro Braga, Hansenclever Bassani, Aluizio Araujo

Genetic and Evolutionary Computation Conference
PDF

Subspace clustering is the task of identifying clusters in subspaces of the input dimensions of a given dataset. Noisy data in certain attributes cause difficulties for traditional clustering algorithms, because the high discrepancies within them can make objects appear too different to be grouped in the same cluster. This requires methods specially designed for subspace clustering. This paper presents our second approach to subspace and projected clustering based on self-organizing maps (SOMs), which is a local adaptive receptive field dimension selective SOM. By introducing a time-variant topology, our method is an improvement in terms of clustering quality, computational cost, and parameterization. This enables the method to identify the correct number of clusters and their respective relevant dimensions, and thus it presents nearly perfect results in synthetic datasets and surpasses our previous method in most of the real-world datasets considered.
2014 - Dimension Selective Self-Organizing Maps With Time-Varying Structure for Subspace and Projected Clustering

Hansenclever Bassani, Aluizio Araujo

IEEE Transactions on Neural Networks and Learning Systems
PDF

Awards

 

2018 - 3th place in the Very Small Size Soccer Category of the IRONCup 2018 - Brazil
André Luís Damázio de Sales Júnior, Caio Carvalho de Abreu e Lima, Carlos Henrique Caloete Pena, Cristiano Santos de Oliveira, David Riff de França Tenório, Esdras Barbosa Lima da Silva Júnior, Gabriel Marques Bandeira, Heitor Rapela Medeiros, João Gabriel Machado da Silva, João Lucas Oliveira Canhoto, José Nilton de Oliveira Lima Júnior, Juliana do nascimento Damurie da Silva, Lucas Henrique Cavalcanti Santos, Lucas Oliveira Maggi, Marvson Allan Pontes de Assis, Mateus Gonçalves Machado, Raphael Cândido Brito, Renato Sousa Bezerra, Roberto Costa Fernandes, Vinicius Bezerra Araújo da Silva, Hansenclever de Franca Bassani, Edna Natividade da Silva Barros
https://robocin.github.io/categories.html

2018 - 3th place in the IEEE Very Small Size RoboCup Soccer in the Latin American and Brazilian Robotics Competition (LARC/CBR), with the team RoboCIn
André Luís Damázio de Sales Júnior, Caio Carvalho de Abreu e Lima, Carlos Henrique Caloete Pena, Cristiano Santos de Oliveira, David Riff de França Tenório, Esdras Barbosa Lima da Silva Júnior, Gabriel Marques Bandeira, Heitor Rapela Medeiros, João Gabriel Machado da Silva, João Lucas Oliveira Canhoto, José Nilton de Oliveira Lima Júnior, Juliana do nascimento Damurie da Silva, Lucas Henrique Cavalcanti Santos, Lucas Oliveira Maggi, Marvson Allan Pontes de Assis, Mateus Gonçalves Machado, Raphael Cândido Brito, Renato Sousa Bezerra, Roberto Costa Fernandes, Vinicius Bezerra Araújo da Silva, Hansenclever de Franca Bassani, Edna Natividade da Silva Barros
https://robocin.github.io/categories.html

2017 - Prize of 3th Best Product in the Brazilian Congress of Informatics in Education (CBIE) with the website and app for Grading exams automaticaly
Hansenclever Bassani, Cicero Garrozi, André Tiba
https://gradepen.com