Search

Behavior modeling has multiple applications in the intelligent environment domain. It has been used in different tasks, such as the stratification of different pathologies, prediction of the user actions and activities, or modeling the energy usage. Specifically, behavior prediction can be used to forecast the future evolution of the users and to identify those behaviors that deviate from the expected conduct. In this paper, we propose the use of embeddings to represent the user actions, and study and compare several behavior prediction approaches. We test multiple model (LSTM, CNNs, GCNs, and transformers) architectures to ascertain the best approach to using embeddings for behavior modeling and also evaluate multiple embedding retrofitting approaches. To do so, we use the Kasteren dataset for intelligent environments, which is one of the most widely used datasets in the areas of activity recognition and behavior modeling. This work was carried out with the financial support of FuturAAL-Ego (RTI2018-101045-A-C22) and FuturAAL-Context (RTI2018-101045-B-C21) granted by Spanish Ministry of Science, Innovation and Universities.

Different scales of the objects pose a great challenge for the segmentation of remote sensing images of special scenes. This paper focuses on the problem of large-scale variations of the target objects via a dynamical receptive field of the deep network. We construct a Gaussian dynamic convolution network by introducing a dynamic convolution layer to enhance remote sensing image understanding. Moreover, we propose a new Gaussian pyramid pooling (GPP) for multi-scale object segmentation. The proposed network can expand the size of the receptive field and improve its efficiency in aggregating contextual information. Experiments verify that our method outperforms the popular semantic segmentation methods on large remote sensing image datasets, including iSAID and LoveDA. Moreover, we conduct experiments to demonstrate that the Gaussian dynamic convolution works more effectively on remote sensing images than other convolutional layers.

Article number 2524 : The prediction of time series data applied to the energy sector (prediction of renewable energy production, forecasting prosumers’ consumption/generation, forecast of country-level consumption, etc.) has numerous useful applications. Nevertheless, the complexity and non-linear behaviour associated with such kind of energy systems hinder the development of accurate algorithms. In such a context, this paper investigates the use of a state-of-art deep learning architecture in order to perform precise load demand forecasting 24-h-ahead in the whole country of France using RTE data. To this end, the authors propose an encoder-decoder architecture inspired by WaveNet, a deep generative model initially designed by Google DeepMind for raw audio waveforms. WaveNet uses dilated causal convolutions and skip-connection to utilise long-term information. This kind of novel ML architecture presents different advantages regarding other statistical algorithms. On the one hand, the proposed deep learning model’s training process can be parallelized in GPUs, which is an advantage in terms of training times compared to recurrent networks. On the other hand, the model prevents degradations problems (explosions and vanishing gradients) due to the residual connections. In addition, this model can learn from an input sequence to produce a forecast sequence in a one-shot manner. For comparison purposes, a comparative analysis between the most performing state-of-art deep learning models and traditional statistical approaches is presented: Autoregressive-Integrated Moving Average (ARIMA), Long-Short-Term-Memory, Gated-RecurrentUnit (GRU), Multi-Layer Perceptron (MLP), causal 1D-Convolutional Neural Networks (1D-CNN) and ConvLSTM (Encoder-Decoder). The values of the evaluation indicators reveal that WaveNet exhibits superior performance in both forecasting accuracy and robustness.

Pulmonary Embolism (PE) is a respiratory disease caused by blood clots lodged in the pulmonary arteries, blocking perfusion, limiting blood oxygenation, and inducing a higher load on the right ventricle. Pulmonary embolism is diagnosed using contrast enhanced Computed Tomography Pulmonary Angiography (CTPA), resulting in a 3 D image where the pulmonary arteries appear as bright structures, and emboli appear as filling defects, with these often being difficult to see, especially in the subsegmental case. In comparison to an expert panel, the average radiologist has a sensitivity of between 77% and 94 % . Computer Aided Detection (CAD) is regarded as a promising system to detect emboli, but current algorithms are hindered by a high false positive rate. In this paper, we propose a novel methodology for emboli detection. Instead of finding candidate points and characterizing them, we find emboli directly on the whole image slice. Detections across different slices are merged into a single detection volume that is post-processed to generate emboli detections. The system was evaluated on a public PE database of 80 scans. On 20 test scans, our system obtained a per-embolus sensitivity of 68% at a regime of one false positive per scan, improving on state-of-the-art methods. We therefore conclude that our multi-slice emboli segmentation CAD for PE method is a valuable alternative to the standard methods of candidate point selection and classification.

Alzheimer’s disease (AD) constitutes a neurodegenerative pathology that presents mobility disorders as one of its earliest symptoms. Current smartphones integrate accelerometers that can be used to collect mobility data of Alzheimer’s patients. This paper describes a method that processes these accelerometer data and a convolutional neural network (CNN) that classifies the stage of the disease according to the mobility patterns of the patient. The method is applied in a case study with 35 Alzheimer’s patients, in which a classification success rate of 91% was obtained.

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures. This research is partially supported by the Spanish Ministry of Education, Culture and Sports under FPU fellowship with identifier FPU13/03917.

[EN] There is an increasing interest in the automatic digitization of medieval music documents. Despite efforts in this field, the detection of the different layers of information on these documents still poses difficulties. The use of Deep Neural Networks techniques has reported outstanding results in many areas related to computer vision. Consequently, in this paper, we study the so-called Convolutional Neural Networks (CNN) for performing the automatic document processing of music score images. This process is focused on layering the image into its constituent parts (namely, background, staff lines, music notes, and text) by training a classifier with examples of these parts. A comprehensive experimentation in terms of the configuration of the networks was carried out, which illustrates interesting results as regards to both the efficiency and effectiveness of these models. In addition, a cross-manuscript adaptation experiment was presented in which the networks are evaluated on a different manuscript from the one they were trained. The results suggest that the CNN is capable of adapting its knowledge, and so starting from a pre-trained CNN reduces (or eliminates) the need for new labeled data., This work was supported by the Social Sciences and Humanities Research Council of Canada, and Universidad de Alicante through grant GRE-16-04.