The intermittent and uncontrollable power output from the ever-increasing renewable energy sources, require large amounts of operating reserves to retain the system frequency within its nominal range. Based on day-ahead load forecasts, many research works have proposed conventional and stochastic approaches to define their optimum margins for reliability enhancement at reasonable production cost. In this work, we aim at delivering real-time load forecasting to lower the operating-reserve requirements based on intra-hour weather update predictors. Based on critical predictors and their historical data, we train an artificial model that is able to forecast the load ahead with great accuracy. This is a feed-forward neural network with two hidden layers, which performs real-time forecasts with the aid of a predictive model control developed to update the recommendations intra-hourly and, assessing their impact and its significance on the output target, it corrects the imposed deviations. Performing daily simulations for an annual time-horizon, we observe that significant improvements exist in terms of decreased operating reserve requirements to regulate the violated frequency. In fact, these improvements can exceed 80% during specific months of winter when compared with robust formulations in isolated power systems.
Attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recognition in dyadic conversations. In this work, we introduce a novel attention mechanism capable of inferring the immensity of the effect of each past utterance on the current speaker emotional state. The proposed self-attention network captures the correlation patterns among consecutive encoder network states, thus enabling the robust and effective modeling of temporal dynamics over arbitrary long temporal horizons. We exhibit the effectiveness of our approach considering the challenging IEMOCAP benchmark. We show that, our devised methodology outperforms state-of-the-art alternatives and commonly used approaches, giving rise to promising new research directions in the context of Online Social Network (OSN) analysis tasks.
The provision of information encourages people to visit cultural sites more often. Exploiting the great potential of using smartphone cameras and egocentric vision, we describe the development of a robust artwork recognition algorithm to assist users when visiting an art space. The algorithm recognizes artworks under any physical museum conditions, as well as camera point of views, making it suitable for different use scenarios towards an enhanced visiting experience. The algorithm was developed following a multiphase approach, including requirements gathering, experimentation in a virtual environment, development of the algorithm in real environment conditions, implementation of a demonstration smartphone app for artwork recognition and provision of assistive information, and its evaluation. During the algorithm development process, a convolutional neural network (CNN) model was trained for automatic artwork recognition using data collected in an art gallery, followed by extensive evaluations related to the parameters that may affect recognition accuracy, while the optimized algorithm was also evaluated through a dedicated app by a group of volunteers with promising results. The overall algorithm design and evaluation adopted for this work can also be applied in numerous applications, especially in cases where the algorithm performance under varying conditions and end-user satisfaction are critical factors.
1 July 2017 in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
The Influenza type A virus can be considered as one of the most severe viruses that can infect multiple species with often fatal consequences to the hosts. The Haemagglutinin (HA) gene of the virus has the potential to be a target for antiviral drug development realised through accurate identification of its sub-types and possible the targeted hosts. In this paper, to accurately predict if an Influenza type A virus has the capability to infect human hosts, by using only the HA gene, is therefore developed and tested. The predictive model follows three main steps; (i) decoding the protein sequences into numerical signals using EIIP amino acid scale, (ii) analysing these sequences by using Discrete Fourier Transform (DFT) and extracting DFT-based features, (iii) using a predictive model, based on Artificial Neural Networks and using the features generated by DFT. In this analysis, from the Influenza Research Database, 30724, 18236 and 8157 HA protein sequences were collected for Human, Avian and Swine respectively. Given this set of the proteins, the proposed method yielded 97.36% (± 0.04%), 97.26% (± 0.26%), 0.978 (± 0.004), 0.963 (± 0.005) and 0.945 (±0.005) for the training accuracy validation accuracy, precision, recall and Mathews Correlation Coefficient (MCC) respectively, based on a 10-fold cross-validation. The classification model generated by using one of the largest dataset, if not the largest, yields promising results that could lead to early detection of such species and help develop precautionary measurements for possible human infections.