Recommender systems help users deal with information overload by providing tailored item suggestions to them. The recommendation of news is often considered to be challenging, since the relevance of an article for a user can depend on a variety of factors, including the user’s short-term reading interests, the reader’s context, or the recency or popularity of an article. Previous work has shown that the use of Recurrent Neural Networks is promising for the next-in-session prediction task, but has certain limitations when only recorded item click sequences are used as input. In this work, we present a contextual hybrid, deep learning based approach for session-based news recommendation that is able to leverage a variety of information types. We evaluated our approach on two public datasets, using a temporal evaluation protocol that simulates the dynamics of a news portal in a realistic way. Our results confirm the benefits of considering additional types of information, including article popularity and recency, in the proposed way, resulting in significantly higher recommendation accuracy and catalog coverage than other session-based algorithms. Additional experiments show that the proposed parameterizable loss function used in our method also allows us to balance two usually conflicting quality factors, accuracy and novelty.

Hydroelectric power stations are responsible for renewable energy generation, especially in countries with many rivers such as Brazil. It is very important to have good estimates of the hydrological flow in order to determine whether thermoelectric power plants should begin operation, an event that would increase the costs of electricity and also have aterrible environmental impact. The monthly flow of a river was estimated using two recurrent neural networks techniques: Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results were compared with other articles that had the same structure and used the same data: the Rio Grande river in the Furnas and Camargos dam.

Data normalization for use in Artificial Neural Networks often requires extensive statistical analysis. This paper presents an initial investigation of a case study involving credit card fraud detection, where Cluster Analysis was applied to data normalization. Early results obtained from the use of Artificial Neural Networks and Cluster Analysis on fraud detection has shown that neuronal inputs can be reduced by clustering attributes.

This research presents a WSN computer system model applied to precision irrigation, specifically for conditions in which sensor nodes may be located far from the coordinator. The proposed model is based on a tailored hardware and software aiming to extend both sensor nodes and WSN lifetime. The coordinator is aware of its sensor nodes’ available energy and such feature enables estimating the remaining lifetime of each sensor node. The so-called Sensor nOdes’ system for data acqUisition of Long range (SOUL) is the conceptual model for a sensor node hardware and software system design, concerning energy management and messages grouping, improving both sensor nodes and network lifetime. The sensor nodes were employed to monitor soil moisture and thus the SOUL computer system model was validated in field conditions. Sensor nodes lifetime was increased by 5.7 times when compared to a conventional use.

According to the FAA Order 8110.49, there are two distinct types of databases used in airborne systems and equipment: Aeronautical Databases (AD) and Parameter Data Items (PDI). Although the database development processes in the RTCA DO-178C and the RTCA DO-200B have many similarities, the use of the DO-200B is limited to navigation, terrain, obstacle, and airport map databases. This paper provides some scenarios for database verification using the RTCA DO-178C and the RTCA DO-200B standards, including the usage of Tool Qualification, when processes are eliminated, reduced, or automated by the use of software tools without reviewing the output produced by such tools.

In recent years, we have seen a wide use of Artificial Intelligence (AI) applications in the Internet and everywhere. Natural Language Processing and Machine Learning are important sub-fields of AI that have made Chatbots and Conversational AI applications possible. Those algorithms are built based on historical data in order to create language models, however historical data could be intrinsically discriminatory. This article investigates whether a Conversational AI could identify offensive language and it will show how large language models often produce quite a bit of unethical behavior because of bias in the historical data. Our low-level proof-of-concept will present the challenges to detect offensive language in social media and it will discuss some steps to propitiate strong results in the detection of offensive language and unethical behavior using a Conversational AI.