Bernardete Ribeiro

Nguyen Huu Phong, Bernardete Ribeiro

Recognizing human actions in video sequences, known as Human Action Recognition (HAR), is a challenging task in pattern recognition. While Convolutional Neural Networks (ConvNets) have shown remarkable success in image recognition, they are not always directly applicable to HAR, as temporal features are critical for accurate classification. In this paper, we propose a novel dynamic PSO-ConvNet model for learning actions in videos, building on our recent work in image recognition. Our approach leverages a framework where the weight vector of each neural network represents the position of a particle in phase space, and particles share their current weight vectors and gradient estimates of the Loss function. To extend our approach to video, we integrate ConvNets with state-of-the-art temporal methods such as Transformer and Recurrent Neural Networks. Our experimental results on the UCF-101 dataset demonstrate substantial improvements of up to 9% in accuracy, which confirms the effectiveness of our proposed method. In addition, we conducted experiments on larger and more variety of datasets including Kinetics-400 and HMDB-51 and obtained preference for Collaborative Learning in comparison with Non-Collaborative Learning (Individual Learning). Overall, our dynamic PSO-ConvNet model provides a promising direction for improving HAR by better capturing the spatio-temporal dynamics of human actions in videos. The code is available at https://github.com/leonlha/Video-Action-Recognition-Collaborative-Learning-with-Dynamics-via-PSO-ConvNet-Transformer.

Nguyen Huu Phong, Augusto Santos, Bernardete Ribeiro

Convolutional Neural Networks (ConvNets or CNNs) have been candidly deployed in the scope of computer vision and related fields. Nevertheless, the dynamics of training of these neural networks lie still elusive: it is hard and computationally expensive to train them. A myriad of architectures and training strategies have been proposed to overcome this challenge and address several problems in image processing such as speech, image and action recognition as well as object detection. In this article, we propose a novel Particle Swarm Optimization (PSO) based training for ConvNets. In such framework, the vector of weights of each ConvNet is typically cast as the position of a particle in phase space whereby PSO collaborative dynamics intertwines with Stochastic Gradient Descent (SGD) in order to boost training performance and generalization. Our approach goes as follows: i) [regular phase] each ConvNet is trained independently via SGD; ii) [collaborative phase] ConvNets share among themselves their current vector of weights (or particle-position) along with their gradient estimates of the Loss function. Distinct step sizes are coined by distinct ConvNets. By properly blending ConvNets with large (possibly random) step-sizes along with more conservative ones, we propose an algorithm with competitive performance with respect to other PSO-based approaches on Cifar-10 and Cifar-100 (accuracy of 98.31% and 87.48%). These accuracy levels are obtained by resorting to only four ConvNets -- such results are expected to scale with the number of collaborative ConvNets accordingly. We make our source codes available for download https://github.com/leonlha/PSO-ConvNet-Dynamics.

Nguyen Huu Phong, Bernardete Ribeiro

In this research, we present our findings to recognize American Sign Language from series of hand gestures. While most researches in literature focus only on static handshapes, our work target dynamic hand gestures. Since dynamic signs dataset are very few, we collect an initial dataset of 150 videos for 10 signs and an extension of 225 videos for 15 signs. We apply transfer learning models in combination with deep neural networks and background subtraction for videos in different temporal settings. Our primarily results show that we can get an accuracy of $0.86$ and $0.71$ using DenseNet201, LSTM with video sequence of 12 frames accordingly.

Nguyen Huu Phong, Bernardete Ribeiro

Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D images, these networks are used merely to learn and generate data sequentially rather than for image recognition tasks. In this study, we propose integrating an RNN as an additional layer when designing image recognition models. We also develop end-to-end multimodel ensembles that produce expert predictions using several models. In addition, we extend the training strategy so that our model performs comparably to leading models and can even match the state-of-the-art models on several challenging datasets (e.g., SVHN (0.99), Cifar-100 (0.9027) and Cifar-10 (0.9852)). Moreover, our model sets a new record on the Surrey dataset (0.949). The source code of the methods provided in this article is available at https://github.com/leonlha/e2e-3m and http://nguyenhuuphong.me.

Miguel Fernandes, Catarina Silva, Alberto Cardoso et al.

Condition-Based Maintenance is pivotal in enabling the early detection of potential failures in engineering systems, where precise prediction of the Remaining Useful Life is essential for effective maintenance and operation. However, a predominant focus in the field centers on predicting the Remaining Useful Life using unprocessed or minimally processed data, frequently neglecting the intricate dynamics inherent in the dataset. In this work we introduce a novel methodology grounded in the analysis of statistical similarity within latent data from system components. Leveraging a specifically designed architecture based on a Vector Quantized Variational Autoencoder, we create a sequence of discrete vectors which is used to estimate system-specific priors. We infer the similarity between systems by evaluating the divergence of these priors, offering a nuanced understanding of individual system behaviors. The efficacy of our approach is demonstrated through experiments on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. Our validation not only underscores the potential of our method in advancing the study of latent statistical divergence but also demonstrates its superiority over existing techniques.

Nguyen Huu Phong, Bernardete Ribeiro

Capsule Networks face a critical problem in computer vision in the sense that the image background can challenge its performance, although they learn very well on training data. In this work, we propose to improve Capsule Networks' architecture by replacing the Standard Convolution with a Depthwise Separable Convolution. This new design significantly reduces the model's total parameters while increases stability and offers competitive accuracy. In addition, the proposed model on $64\times64$ pixel images outperforms standard models on $32\times32$ and $64\times64$ pixel images. Moreover, we empirically evaluate these models with Deep Learning architectures using state-of-the-art Transfer Learning networks such as Inception V3 and MobileNet V1. The results show that Capsule Networks can perform comparably against Deep Learning models. To the best of our knowledge, we believe that this is the first work on the integration of Depthwise Separable Convolution into Capsule Networks.

Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro et al.

The deployment of Machine Learning (ML) models is a difficult and time-consuming job that comprises a series of sequential and correlated tasks that go from the data pre-processing, and the design and extraction of features, to the choice of the ML algorithm and its parameterisation. The task is even more challenging considering that the design of features is in many cases problem specific, and thus requires domain-expertise. To overcome these limitations Automated Machine Learning (AutoML) methods seek to automate, with few or no human-intervention, the design of pipelines, i.e., automate the selection of the sequence of methods that have to be applied to the raw data. These methods have the potential to enable non-expert users to use ML, and provide expert users with solutions that they would unlikely consider. In particular, this paper describes AutoML-DSGE - a novel grammar-based framework that adapts Dynamic Structured Grammatical Evolution (DSGE) to the evolution of Scikit-Learn classification pipelines. The experimental results include comparing AutoML-DSGE to another grammar-based AutoML framework, Resilient ClassificationPipeline Evolution (RECIPE), and show that the average performance of the classification pipelines generated by AutoML-DSGE is always superior to the average performance of RECIPE; the differences are statistically significant in 3 out of the 10 used datasets.

Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro et al.

NeuroEvolution (NE) methods are known for applying Evolutionary Computation to the optimisation of Artificial Neural Networks(ANNs). Despite aiding non-expert users to design and train ANNs, the vast majority of NE approaches disregard the knowledge that is gathered when solving other tasks, i.e., evolution starts from scratch for each problem, ultimately delaying the evolutionary process. To overcome this drawback, we extend Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) to incremental development. We hypothesise that by transferring the knowledge gained from previous tasks we can attain superior results and speedup evolution. The results show that the average performance of the models generated by incremental development is statistically superior to the non-incremental average performance. In case the number of evaluations performed by incremental development is smaller than the performed by non-incremental development the attained results are similar in performance, which indicates that incremental development speeds up evolution. Lastly, the models generated using incremental development generalise better, and thus, without further evolution, report a superior performance on unseen problems.

Filipe Assunção, Nuno Lourenço, Penousal Machado et al.

This paper proposes a new extension to Deep Evolutionary Network Structured Evolution (DENSER), called Fast-DENSER++ (F-DENSER++). The vast majority of NeuroEvolution methods that optimise Deep Artificial Neural Networks (DANNs) only evaluate the candidate solutions for a fixed amount of epochs; this makes it difficult to effectively assess the learning strategy, and requires the best generated network to be further trained after evolution. F-DENSER++ enables the training time of the candidate solutions to grow continuously as necessary, i.e., in the initial generations the candidate solutions are trained for shorter times, and as generations proceed it is expected that longer training cycles enable better performances. Consequently, the models discovered by F-DENSER++ are fully-trained DANNs, and are ready for deployment after evolution, without the need for further training. The results demonstrate the ability of F-DENSER++ to effectively generate fully-trained DANNs; by the end of evolution, whilst the average performance of the models generated by F-DENSER++ is of 88.73%, the performance of the models generated by the previous version of DENSER (Fast-DENSER) is 86.91% (statistically significant), which increases to 87.76% when allowed to train for longer.

Nguyen Huu Phong, Bernardete Ribeiro

Capsule Networks (CN) offer new architectures for Deep Learning (DL) community. Though its effectiveness has been demonstrated in MNIST and smallNORB datasets, the networks still face challenges in other datasets for images with distinct contexts. In this research, we improve the design of CN (Vector version) namely we expand more Pooling layers to filter image backgrounds and increase Reconstruction layers to make better image restoration. Additionally, we perform experiments to compare accuracy and speed of CN versus DL models. In DL models, we utilize Inception V3 and DenseNet V201 for powerful computers besides NASNet, MobileNet V1 and MobileNet V2 for small and embedded devices. We evaluate our models on a fingerspelling alphabet dataset from American Sign Language (ASL). The results show that CNs perform comparably to DL models while dramatically reducing training time. We also make a demonstration and give a link for the purpose of illustration.

Nguyen Huu Phong, Bernardete Ribeiro

Image recognition using Deep Learning has been evolved for decades though advances in the field through different settings is still a challenge. In this paper, we present our findings in searching for better image classifiers in offline and online environments. We resort to Convolutional Neural Network and its variations of fully connected Multi-layer Perceptron. Though still preliminary, these results are encouraging and may provide a better understanding about the field and directions toward future works.

Filipe Rodrigues, Stanislav S. Borysov, Bernardete Ribeiro et al.

Public special events, like sports games, concerts and festivals are well known to create disruptions in transportation systems, often catching the operators by surprise. Although these are usually planned well in advance, their impact is difficult to predict, even when organisers and transportation operators coordinate. The problem highly increases when several events happen concurrently. To solve these problems, costly processes, heavily reliant on manual search and personal experience, are usual practice in large cities like Singapore, London or Tokyo. This paper presents a Bayesian additive model with Gaussian process components that combines smart card records from public transport with context information about events that is continuously mined from the Web. We develop an efficient approximate inference algorithm using expectation propagation, which allows us to predict the total number of public transportation trips to the special event areas, thereby contributing to a more adaptive transportation system. Furthermore, for multiple concurrent event scenarios, the proposed algorithm is able to disaggregate gross trip counts into their most likely components related to specific events and routine behavior. Using real data from Singapore, we show that the presented model outperforms the best baseline model by up to 26% in R2 and also has explanatory power for its individual components.

Filipe Rodrigues, Mariana Lourenço, Bernardete Ribeiro et al.

The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state-of-the-art approaches.

Filipe Assunção, Nuno Lourenço, Penousal Machado et al.

Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology (e.g., number of layers, type of layers), but also tunes hyper-parameters, such as, learning parameters or data augmentation parameters. The automatic design is achieved using a representation with two distinct levels, where the outer level encodes the general structure of the network, i.e., the sequence of layers, and the inner level encodes the parameters associated with each layer. The allowed layers and range of the hyper-parameters values are defined by means of a human-readable Context-Free Grammar. DENSER was used to evolve ANNs for CIFAR-10, obtaining an average test accuracy of 94.13%. The networks evolved for the CIFA--10 are tested on the MNIST, Fashion-MNIST, and CIFAR-100; the results are highly competitive, and on the CIFAR-100 we report a test accuracy of 78.75%. To the best of our knowledge, our CIFAR-100 results are the highest performing models generated by methods that aim at the automatic design of Convolutional Neural Networks (CNNs), and are amongst the best for manually designed and fine-tuned CNNs.

Jorge Rivero, Bernardete Ribeiro, Ning Chen et al.

One of the main problems in Network Intrusion Detection comes from constant rise of new attacks, so that not enough labeled examples are available for the new classes of attacks. Traditional Machine Learning approaches hardly address such problem. This can be overcome with Zero-Shot Learning, a new approach in the field of Computer Vision, which can be described in two stages: the Attribute Learning and the Inference Stage. The goal of this paper is to propose a new Inference Stage algorithm for Network Intrusion Detection. In order to attain this objective, we firstly put forward an experimental setup for the evaluation of the Zero-Shot Learning in Network Intrusion Detection related tasks. Secondly, a decision tree based algorithm is applied to extract rules for generating the attributes in the AL stage. Finally, using a representation of a Zero-Shot Class as a point in the Grassmann manifold, an explicit formula for the shortest distance between points in that manifold can be used to compute the geodesic distance between the Zero-Shot Classes which represent the new attacks and the Known Classes corresponding to the attack categories. The experimental results in the datasets KDD Cup 99 and NSL-KDD show that our approach with Zero-Shot Learning successfully addresses the Network Intrusion Detection problem.

Filipe Assunção, Nuno Lourenço, Penousal Machado et al.

Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs composed of more than one hidden-layer. On the other, there is no way to evolve networks with more than one output neuron. To properly evolve ANNs with more than one hidden-layer and multiple output nodes there is the need to know the number of neurons available in previous layers. In this paper we introduce Dynamic Structured Grammatical Evolution (DSGE): a new genotypic representation that overcomes the aforementioned limitations. By enabling the creation of dynamic rules that specify the connection possibilities of each neuron, the methodology enables the evolution of multi-layered ANNs with more than one output neuron. Results in different classification problems show that DSGE evolves effective single and multi-layered ANNs, with a varying number of output neurons.

Jorge Luis Rivero Pérez, Bernardete Ribeiro

Network intrusion detection is one of the most visible uses for Big Data analytics. One of the main problems in this application is the constant rise of new attacks. This scenario, characterized by the fact that not enough labeled examples are available for the new classes of attacks is hardly addressed by traditional machine learning approaches. New findings on the capabilities of Zero-Shot learning (ZSL) approach makes it an interesting solution for this problem because it has the ability to classify instances of unseen classes. ZSL has inherently two stages: the attribute learning and the inference stage. In this paper we propose a new algorithm for the attribute learning stage of ZSL. The idea is to learn new values for the attributes based on decision trees (DT). Our results show that based on the rules extracted from the DT a better distribution for the attribute values can be found. We also propose an experimental setup for the evaluation of ZSL on network intrusion detection (NID).

Gonçalo Oliveira, Xavier Frazão, André Pimentel et al.

Brand recognition is a very challenging topic with many useful applications in localization recognition, advertisement and marketing. In this paper we present an automatic graphic logo detection system that robustly handles unconstrained imaging conditions. Our approach is based on Fast Region-based Convolutional Networks (FRCN) proposed by Ross Girshick, which have shown state-of-the-art performance in several generic object recognition tasks (PASCAL Visual Object Classes challenges). In particular, we use two CNN models pre-trained with the ILSVRC ImageNet dataset and we look at the selective search of windows `proposals' in the pre-processing stage and data augmentation to enhance the logo recognition rate. The novelty lies in the use of transfer learning to leverage powerful Convolutional Neural Network models trained with large-scale datasets and repurpose them in the context of graphic logo detection. Another benefit of this framework is that it allows for multiple detections of graphic logos using regions that are likely to have an object. Experimental results with the FlickrLogos-32 dataset show not only the promising performance of our developed models with respect to noise and other transformations a graphic logo can be subject to, but also its superiority over state-of-the-art systems with hand-crafted models and features.

Jorge Luis Rivero Perez, Bernardete Ribeiro, Carlos Morell Perez

With the massive data challenges nowadays and the rapid growing of technology, stream mining has recently received considerable attention. To address the large number of scenarios in which this phenomenon manifests itself suitable tools are required in various research fields. Instance-based data stream algorithms generally employ the Euclidean distance for the classification task underlying this problem. A novel way to look into this issue is to take advantage of a more flexible metric due to the increased requirements imposed by the data stream scenario. In this paper we present a new algorithm that learns a Mahalanobis metric using similarity and dissimilarity constraints in an online manner. This approach hybridizes a Mahalanobis distance metric learning algorithm and a k-NN data stream classification algorithm with concept drift detection. First, some basic aspects of Mahalanobis distance metric learning are described taking into account key properties as well as online distance metric learning algorithms. Second, we implement specific evaluation methodologies and comparative metrics such as Q statistic for data stream classification algorithms. Finally, our algorithm is evaluated on different datasets by comparing its results with one of the best instance-based data stream classification algorithm of the state of the art. The results demonstrate that our proposal is better