Abstract

Abstract
IntroductionHypoxia is defined as a critically low-oxygen condition of water, which, if prolonged, can be harmful to fish and many other aquatic species. In the context of ocean salmon fish farming, early detection of hypoxia events is critical for farm managers to mitigate these events to reduce fish stress, however in complex natural systems accurate forecasting tools are limited. The goal of this research is to use a machine learning approach to forecast oxygen concentration and predict hypoxia events in marine net-pen salmon farms.MethodsThe developed model is based on gradient boosting and works in two stages. First, we apply auto-regression to build a forecasting model that predicts oxygen concentration levels within a cage. We take a global forecasting approach by building a model using the historical data provided by sensors at several marine fish farms located in eastern Canada. Then, the forecasts are transformed into binary probabilities that indicate the likelihood of a low-oxygen event. We leverage the cumulative distribution function to compute these probabilities.Results and discussionWe tested our model in a case study that included several cages across 14 fish farms. The experiments suggest that the model can detect future hypoxic events with a commercially acceptable false alarm rate. The resulting probabilistic predictions and oxygen concentration forecasts can help salmon farmers to prioritize resources, and reduce harm to crops.

Abstract
Virtual assistants offer a new type of solution to handle interaction between human and machine and can be applied in various business contexts such as Industry or Education. When designing and building a virtual assistant the developers must ensure a set of parameters to achieve a good solution. Various platforms and frameworks emerged to allow developers to create virtual assistant solutions easier and faster. This paper provides a review of available platforms and frameworks used by authors to create their own solutions in different areas. Big tech companies like Google with Dialogflow, IBM with Watson Assistant and Microsoft with Bot Framework, present mature solutions to build virtual assistants that provide to the developer all components of the basic architecture to build a fast and solid solution. Open-Source solutions focus on providing to the developer the main components to build a virtual assistant, namely language understanding and response generation.

Abstract
This research aims to analyze the positioning theory and discourse within Sao Paulo's Place Branding from 2014 to 2019, investigating the symbolic representations employed by the Sao Paulo Tourism Bureau to emphasize its branding endeavors. The methodology employed a framework based on Semprini's [10] Project/Manifestation approach and Discourse Analysis. The impetus behind this study arises from the substantial investments made by cities to craft comprehensive disclosure strategies and establish place branding for their respective regions. We observed aspects of Communication and DigitalMarketing in the three promotional videos produced by SPTuris in 2014, 2017, and 2019, which underwent meticulous analysis. Our findings unveiled a consistent thematic discourse despite shifts in political administration. The 2014 video accentuated multiculturalism and cosmopolitanism, while the 2017 edition highlighted experiential marketing, business, consumption, and cosmopolitan elements. Remarkably, the 2019 presentation featured images emphasizing receptivity. Themes such as Culture, Arts, and Gastronomy were recurrent across all videos. The scrutinized discourse reaffirms Sao Paulo's capital as a trendsetter within Brazil.

Abstract
Predictive Maintenance applications are increasingly complex, with interactions between many components. Black -box models are popular approaches based on deep -learning techniques due to their predictive accuracy. This paper proposes a neural -symbolic architecture that uses an online rule -learning algorithm to explain when the black -box model predicts failures. The proposed system solves two problems in parallel: (i) anomaly detection and (ii) explanation of the anomaly. For the first problem, we use an unsupervised state-of-the-art autoencoder. For the second problem, we train a rule learning system that learns a mapping from the input features to the autoencoder's reconstruction error. Both systems run online and in parallel. The autoencoder signals an alarm for the examples with a reconstruction error that exceeds a threshold. The causes of the signal alarm are hard for humans to understand because they result from a non-linear combination of sensor data. The rule that triggers that example describes the relationship between the input features and the autoencoder's reconstruction error. The rule explains the failure signal by indicating which sensors contribute to the alarm and allowing the identification of the component involved in the failure. The system can present global explanations for the black box model and local explanations for why the black box model predicts a failure. We evaluate the proposed system in a real -world case study of Metro do Porto and provide explanations that illustrate its benefits.

Abstract
The global push for environmental sustainability is driving substantial changes in power systems, prompting extensive grid upgrades. Policies and initiatives worldwide aim to reduce CO2 emissions, with a focus on increasing reliance on Renewable Energy Sources (RESs) and electrifying transportation. However, the geographical variability and uncertainties of RESs directly impact power generation and distribution, necessitating adjustments in transmission system planning and operation. This paper presents a Transmission Expansion Planning (TEP) model using the 2021 Texas snowstorm as a benchmark scenario, incorporating wind and solar energy penetration while addressing associated uncertainties. Climate Change (CC) and Extreme Weather Events (EWE) are integrated into the set of scenarios aiming at evaluating the proposed method's effectiveness. Comparisons in extreme operative conditions highlight the importance of network reliability and security, emphasizing the significance of merged grids. All simulations are conducted using the ACTIVSg2000 synthetic test system, which emulates the ERCOT grid, with comparisons made between TEP scenarios considering and disregarding CC and EWEs, supporting the concept of umbrella protection.