DECSI - Artigos publicados em periódicos
URI permanente para esta coleçãohttp://www.hml.repositorio.ufop.br/handle/123456789/5263
Navegar
69 resultados
Resultados da Pesquisa
Item On network backbone extraction for modeling online collective behavior.(2022) Ferreira, Carlos Henrique Gomes; Ferreira, Fabrício Murai; Silva, Ana Paula Couto da; Trevisan, Martino; Vassio, Luca; Drago, Idilio; Mellia, Marco; Almeida, Jussara Marques deCollective user behavior in social media applications often drives several important online and offline phenomena linked to the spread of opinions and information. Several studies have focused on the analysis of such phenomena using networks to model user interactions, represented by edges. However, only a fraction of edges contribute to the actual investigation. Even worse, the often large number of non-relevant edges may obfuscate the salient interactions, blurring the underlying structures and user communities that capture the collective behavior patterns driving the target phenomenon. To solve this issue, researchers have proposed several network backbone extraction techniques to obtain a reduced and representative version of the network that better explains the phenomenon of interest. Each technique has its specific assumptions and procedure to extract the backbone. However, the literature lacks a clear methodology to highlight such assumptions, discuss how they affect the choice of a method and offer validation strategies in scenarios where no ground truth exists. In this work, we fill this gap by proposing a principled methodology for comparing and selecting the most appropriate backbone extraction method given a phenomenon of interest. We characterize ten state-of-the-art techniques in terms of their assumptions, requirements, and other aspects that one must consider to apply them in practice. We present four steps to apply, evaluate and select the best method(s) to a given target phenomenon. We validate our approach using two case studies with different requirements: online discussions on Instagram and coordinated behavior in WhatsApp groups. We show that each method can produce very different backbones, underlying that the choice of an adequate method is of utmost importance to reveal valuable knowledge about the particular phenomenon under investigation.Item Watershed-ng : an extensible distributed stream processing framework.(2016) Rocha, Rodrigo; Hott, Bruno; Dias, Vinícius; Ferreira, Renato; Meira Júnior, Wagner; Guedes Neto, Dorgival OlavoMost high-performance data processing (a.k.a. big data) systems allow users to express their computation using abstractions (like MapReduce), which simplify the extraction of parallelism from applications. Most frameworks, however, do not allow users to specify how communication must take place: That element is deeply embedded into the run-time system abstractions, making changes hard to implement. In this work, we describe Wathershed-ng, our re-engineering of the Watershed system, a framework based on the filter–stream paradigm and originally focused on continuous stream processing. Like other big-data environments, Watershed provided object-oriented abstractions to express computation (filters), but the implementation of streams was a run-time system element. By isolating stream functionality into appropriate classes, combination of communication patterns and reuse of common message handling functions (like compression and blocking) become possible. The new architecture even allows the design of new communication patterns, for example, allowing users to choose MPI, TCP, or shared memory implementations of communication channels as their problem demands. Applications designed for the new interface showed reductions in code size on the order of 50% and above in some cases. The performance results also showed significant improvements, because some implementation bottlenecks were removed in the re-engineering process.Item A fix-and-optimize heuristic for the ITC2021 sports timetabling problem.(2022) Fonseca, George Henrique Godim da; Toffolo, Túlio Ângelo MachadoThis paper addresses the general and challenging Sports Timetabling Problem proposed during the International Timetabling Competition of 2021 (ITC2021). The problem is expressed in a flexible format which enables modeling a number of real-world constraints that often occur in Sports Timetabling. An integer programming (IP) formulation and a fix-and-optimize heuristic are proposed to address the problem. The fix-and-optimize approach uses the IP formulation to heuristically decompose the problem into sub-problems and efficiently search on very large neighborhoods. The diverse ITC2021 benchmark instances were used to evaluate the proposed methods. The formulation resulted in proven optimal solutions for two instances. However, it failed to produce feasible solutions for most instances. The proposed fix-and-optimize, which uses an automatic sub-problem size calibration strategy, resulted in feasible solutions for 37 out of the 45 ITC2021 instances. Among these solutions, four are the best known in the literature. The proposed approach participated in the ITC2021 and was one of the finalists.Item Animação gráfica da marcha humana a partir de dados do Kinect.(2021) Leite, Edmo de Oliveira; Assis, Gilda Aparecida de; Yared, Glauco Ferreira GazelA análise da marcha humana a partir de dados biométricos tem aplicações em áreas como segurança, robótica bioinspirada e saúde. Sensores de movimento de baixo custo, como o Kinect, têm permitido a aquisição de dados biométricos da marcha em ambientes terrestres. Entretanto, esses equipamentos têm limitações que podem impactar na qualidade dos dados. Nesse cenário, diferentes técnicas de processamento de sinais podem ser aplicadas para reduzir o ruído. A visualização desses dados, originais ou processados, muitas vezes é realizada na forma de gráficos, tendo utilidade limitada para profissionais não experientes na análise de sinais. Nesse sentido, a visualização dos dados da marcha em um modelo tridimensional pode contribuir para melhorar a decisão dos profissionais, principalmente da saúde. Este trabalho tem como objetivo realizar a animação da marcha humana em um modelo tridimensional, a partir dos dados coletados pelo sensor Kinect 2.0. Para reduzir o ruído dos dados, foi realizado um pré-processamento com filtros de média móvel e Butterworth. Foram elaborados vídeos das animações conforme as vistas isométrica e lateral, que foram incorporados em um questionário on-line e avaliados em uma pesquisa de campo sobre artificialidade/naturalidade da animação, utilizando-se a técnica de pontuação média de opinião (mean opinion score [MOS]). Um total de 22 participantes, estudantes de computação, respondeu ao questionário on-line. A análise de variância simples (analysis of variance [Anova]) one way mostrou que os vídeos a partir das vistas isométrica e lateral processados com filtro de média móvel (janela = 15 e repetições = 3) que obtiveram maiores valores da métrica MOS foram avaliados como significativamente mais naturais do que outros vídeos, processados ou não.Item Multiobjective planning of indoor Wireless Local Area Networks using subpermutation-based hybrid algorithms.(2023) Lima, Marlon Paolo; Takahashi, Ricardo Hiroshi Caldeira; Vieira, Marcos Augusto Menezes; Carrano, Eduardo GontijoWireless Local Area Network (WLAN) has become the most popular technology for mobile Internet access in recent decades. This manuscript presents a novel approach, based on hybrid optimization algorithms, for planning WLANs. Two objective functions are optimized: to maximize network load balance and signal-to-noise ratio. In addition, constraints related to coverage, customer, and equipment demand are considered. A key aspect of the proposed algorithm is its new representation/decoding scheme, based on subpermutations, which considerably reduces the search space dimension. This structure guarantees feasibility of the obtained solutions and increases the computational efficiency of the method. Several tests were performed in two scenarios, one of them using real data from a large-scale WLAN. When compared to other three approaches, such results show that the proposed method provides solutions that reduce costs and improve the WLAN throughput.Item Embedded real-time feature extraction for electrode inversion detection in telemedicine electrocardiograms.(2020) Torres, Vitor Angelo Maria Ferreira; Silva, D. A.C.; Torres, Luiz Carlos Bambirra; Braga, Mateus Taulois; Cardoso, Mathues B. R.; Lino, Vinicius Terra; Torres, Frank Sill; Braga, Antônio de PáduaEarly detection of technical errors in medical examinations, especially in remote locations, is of utmost importance in order to avoid invalid measurements that would require costly and time consuming repeti- tions. This paper proposes a highly efficient method for the identification of an erroneous inversion of the measuring electrodes during a multichannel electrocardiogram. Therefore, a widely applied approach for heart beat detection is modified and approximated feature extraction techniques are employed. In con- trast to existing works, the improved heart beat identification requires no removal of baseline wandering and no amplitude related thresholds. Furthermore, a piecewise linear approximation of the baseline and basic calculations are sufficient for extracting the cardiac axis, which allows the construction of a clas- sifier capable of quickly detecting electrode reversals. Our implementation indicates that the proposed method has minimal hardware costs and is able to operate in real-time on a simple micro-controller.Item Width optimization of RBF kernels for binary classification of support vector machines : a density estimation-based approach.(2019) Menezes, Murilo V. F.; Torres, Luiz Carlos Bambirra; Braga, Antônio de PáduaKernels are often used for modelling non-linear data, developing a main role in models like the SVM. The optimization of its parameters to better fit each dataset is a frequently faced challenge: A bad choice of kernel parameters often implies a poor model. This problem is usually worked out using exhaustive search approaches, such as cross-validation. These methods, however, do not take into account existent information on data arrangement. This paper proposes an alternative approach, based on density estimation. By making use of density estimation methods to analyze the dataset structure, it is proposed a function over the kernel parameters. This function can be used to choose the parameters that best suit the data.Item A novel hybrid feature selection algorithm for hierarchical classification.(2021) Lima, Helen de Cássia Sousa da Costa; Otero, Fernando Esteban Barril; Merschmann, Luiz Henrique de Campos; Souza, Marcone Jamilson FreitasFeature selection is a widespread preprocessing step in the data mining field. One of its purposes is to reduce the number of original dataset features to improve a predictive model’s performance. Despite the benefits of feature selection for the classification task, to the best of our knowledge, few studies in the literature address feature selection for the hierarchical classification context. This paper proposes a novel feature selection method based on the general variable neighborhood search metaheuristic, combining a filter and a wrapper step, wherein a global model hierarchical classifier evaluates feature subsets. We used twelve datasets from the proteins and images domains to perform computational experiments to validate the effect of the proposed algorithm on classification performance when using two global hierarchical classifiers proposed in the literature. Statistical tests showed that using our method for feature selection led to predictive performances that were consistently better than or equivalent to that obtained by using all features with the benefit of reducing the number of features needed, which justifies its efficiency for the hierarchical classification scenario.Item A shape-aware retargeting approach to transfer human motion and appearance in monocular videos.(2021) Gomes, Thiago Luange; Martins, Renato José; Ferreira, João Pedro Moreira; Azevedo, Rafael Augusto Vieira de; Torres, Guilherme Alvarenga; Nascimento, Erickson Rangel doTransferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision. Despite the advances from recent image-to-image translation approaches, there are several transferring contexts where most end-to-end learning-based retargeting methods still perform poorly. Transferring human appearance from one actor to another is only ensured when a strict setup has been complied, which is generally built considering their training regime’s specificities. In this work, we propose a shape-aware approach based on a hybrid image-based rendering technique that exhibits competitive visual retargeting quality compared to state-of-the-art neural rendering approaches. The formulation leverages the user body shape into the retargeting while considering physical constraints of the motion in 3D and the 2D image domain. We also present a new video retargeting benchmark dataset composed of different videos with annotated human motions to evaluate the task of synthesizing people’s videos, which can be used as a common base to improve tracking the progress in the field. The dataset and its evaluation protocols are designed to evaluate retargeting methods in more general and challenging conditions. Our method is validated in several experiments, comprising publicly available videos of actors with different shapes, motion types, and camera setups. The dataset and retargeting code are publicly available to the community at: https://www.verlab.dcc.ufmg.br/retargeting-motion.Item Learning to dance : a graph convolutional adversarial network to generate realistic dance motions from audio.(2021) Ferreira, João Pedro Moreira; Coutinho, Thiago Malta; Gomes, Thiago Luange; Silva Neto, José Francisco da; Azevedo, Rafael Augusto Vieira de; Martins, Renato José; Nascimento, Erickson Rangel doSynthesizing human motion through learning techniques is becoming an increasingly popular approach to alleviating the requirement of new data capture to produce animations. Learning to move naturally from music, i.e., to dance, is one of the more complex motions humans often perform effortlessly. Each dance movement is unique, yet such movements maintain the core characteristics of the dance style. Most approaches addressing this problem with classical convolutional and recursive neural models un- dergo training and variability issues due to the non-Euclidean geometry of the motion manifold struc- ture. In this paper, we design a novel method based on graph convolutional networks to tackle the problem of automatic dance generation from audio information. Our method uses an adversarial learn- ing scheme conditioned on the input music audios to create natural motions preserving the key move- ments of different music styles. We evaluate our method with three quantitative metrics of generative methods and a user study. The results suggest that the proposed GCN model outperforms the state-of- the-art dance generation method conditioned on music in different experiments. Moreover, our graph- convolutional approach is simpler, easier to be trained, and capable of generating more realistic mo- tion styles regarding qualitative and different quantitative metrics. It also presented a visual movement perceptual quality comparable to real motion data. The dataset and project are publicly available at: https://www.verlab.dcc.ufmg.br/motion-analysis/cag2020.