Object detection is an essential capability for performing complex tasks in robotic applications. Today, deep learning (DL) approaches are the basis of state-of-the-art solutions computer vision, where they provide very high accuracy albeit with computational costs. Due to physical limitations platforms, embedded devices not as powerful desktop computers, and adjustments have be made models before transferring them This work benchmarks object devices. Furthermore, some hardware selection...

As a consequence of the projected world population growth, meat consumption is expected to grow. Therefore, production needs be improved, although it cannot done at any cost. Maintaining health and welfare status animals optimal levels has traditionally been main concern farmers, more recently, consumers. In this article Poultry Chain Management (PCM) platform presented. It aims collecting data across different phases poultry chain. The collection not only contributes determine quality each...

Recent studies show that energy consumption of buildings has dramatically increased over the last decade, accounting for more than 35% global use. However, with proper operation, significant savings can be achieved. Demand response is envisioned as a key enabler this operation enhancement, it may contribute to reduction demand peaks and maximization renewable exploitation while mitigating potential problems grid stability. In article, system based on artificial intelligence solves complex...

Spaces and elements in the built environment have emerged as platforms where materializations of observations actuations promise to be very profitable. The advent Internet Things (IoT) paves way address this challenge but heterogeneity represented knowledge about se artifact systems poses a real problem. Ontologies can considered part solution overcome IoT’s inherent hurdles. A wise option promoted by recent approaches is design networks complementary ontologies. However, different points...

Fulfilling occupants' comfort whilst reducing energy consumption is still an unsolved problem in most of tertiary buildings. However, the expansion Internet Things (IoT) and Knowledge Discovery Databases (KDD) techniques lead to research this matter. In paper EEPSA (Energy Eff iciency Prediction Semantic Assistant) process presented, which leverages Web Technologies (SWT) enhance KDD for achieving efficiency buildings while maintaining levels. This guides data analyst through different...

It is well known that peak demand nowadays has a negative impact on energy grid capital, operational cost and environmental aspects. Specially due to the carbon-intense generation plants are deployed address these demands. Demand side management activities such as curtailment or load reallocation, have huge potential match with supply for better of their disparity. This particularly true residential buildings which still largely untapped sector. Since renewable sources (e.g. solar wind...

Achieving a comfortable thermal situation within buildings with an efficient use of energy remains still open challenge for most buildings. In this regard, IoT (Internet Things) and KDD (Knowledge Discovery in Databases) processes may be combined to address these problems, even though data analysts feel overwhelmed by heterogeneity volume the considered. Data could benefit from application assistant that supports them throughout process aids discover which are relevant variables matter at...

Outlier detection in the preprocessing phase of Knowledge Discovery Databases (KDD) processes has been a widely researched topic for many years. However, identifying potential outlier cause still remains an unsolved challenge even though it could be very helpful determining what actions to take after detecting it. Furthermore, conventional methods might overlook outliers certain complex contexts. In this article, Semantic Technologies are used contribute overcoming these problems by...

Although the maturity of technologies based on Artificial Intelligence (AI) is rather advanced nowadays, their adoption, deployment and application are not as wide it could be expected. This attributed to many barriers, among which lack trust users stands out. Accountability a relevant factor progress in this trustworthiness aspect, allows determine causes that derived given decision or suggestion made by an AI system. article focuses accountability specific branch AI, statistical machine...

Efficient management of building energy plays a vital role and is becoming the trend forfuture generation buildings. In this context, expansion Internet Things (IoT)the advent new (Linked) Open Data (LOD) or Big technologies, Knowledge Discovery in Databases (KDD) techniques will lead to achieve goal. However, integration data coming from different sources heterogeneous formats not trivial question. paper, problem reflected on real world use case. After finding classical solution overcome...

The agricultural industry and regulatory organizations define strategies build tools products for plant protection against pests. To identify different plants their related pests avoid inconsistencies between such organizations, an agreed shared classification is necessary. In this regard, the European Mediterranean Plant Protection Organization (EPPO) has been working on defining maintaining a harmonized coding system (EPPO codes). EPPO codes are easy way of referring to specific organism...

RESPOND proposes an Artificial Intelligent (AI) system to assist residential consumers that would like make use of Demand Response (DR) and incorporate it into their energy management systems. The proposed considers the forecast consumption based on data acquired. This work compares results obtained by different forecasting methods using Root Mean Square Error (RMSE) as a measure performance. ARIMA, Linear Regression (LR), Support Vector (SVR) k-Nearest Neighbors (KNN) models are tested, is...

Machine Learning (ML) models are key enablers for the implementation of different energy-efficiency strategies in buildings. There a variety frameworks that facilitate development ML models, but it is necessary to move into environment their deployment and exploitation. Furthermore, performance tends degrade over time. Consequently, they need be regularly evaluated upgraded ensure robustness overall solution. The seamless exploitation, adaptation evolution still an open issue nowadays, this...