Abstract
Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.

Abstract
The use of Wireless Sensor Network (WSN) based technologies is an attractive solution for large-scale sensing applications (wide area deployment), such as environmental monitoring, precision agriculture and industrial automation. IEEE 802.15.4/ZigBee standards are the most used communication protocols for WSN technologies, where the cluster-tree topology is pointed out as a suitable topology to support the implementation of large-scale WSNs. These networks are usually scheduled to prioritise convergecast (upstream) traffic generated from sensor nodes toward the sink node. However, this scheduling pattern results in higher delays for control messages (downstream traffic). Within this context, this paper proposes a Hybrid Beacon Scheduling (Fast-HyBeS) scheme to enable the periodic reconfiguration of cluster-tree WSNs. The underlying idea is to periodically schedule a downstream opportunity window, to allow a faster dissemination of control messages. This opportunity window follows a top-down scheduling approach that prioritises the downstream traffic. Simulation results show that the use of Fast-HyBeS can significantly decrease the end-to-end communication delay for control messages, when compared to the use of static convergecast scheduling schemes. Moreover, the simulation results also highlight that the Fast-HyBeS has a negligible impact upon end-to-end communication delays of the monitoring traffic.

Abstract
Sensory tests are quality assurance tools commonly used to measure and/or detect the presence of abnormal characteristics perceived through the senses in lots of raw material and final products in many manufacturing and food industries. In this paper two acceptance sampling plans for sensory evaluation are designed, and an illustration of the performance of such plans applied to a real data set is presented.

Abstract
Agent-based systems, an approach derived from distributed artificial intelligence, have been introduced for designing large complex systems. They are also suitable to solve challenging problems in industrial environments, being an appropriate technology for realizing cyber-physical systems. In such configuration, they need to interface with automation and control devices. However, until now there is no widely accepted practice nor pattern to interface the software agents with the automation functions. This work addresses this issue and introduces corresponding integration patterns in order to achieve full interoperability and reusability. This work, therefore, provides a methodology for mapping existing practices into a set of generic templates and also discusses the applicability of the proposed approach to different industrial application domains. © 2018 IEEE.

Abstract
Technological evolutions lead to changes in production processes; the Fourth Industrial Revolution has been called Industry 4.0, as it integrates Cyber-Physical Systems and the Internet of Things into supply chains. Large complex networks are the core structure of Industry 4.0: any node in a network can demand a task, which can be answered by one node or a set of them, collaboratively, when they are connected. In this paper, the aim is to verify how (i) network's connectivity (average degree) and (ii) the number of levels covered in nodes search impacts the total of production tasks completely performed in the network. To achieve the goal of this paper, two hypotheses were formulated and tested in a computer simulation environment developed based on a modeling and simulation study. Results showed that the higher the network's average degree is (their nodes are more connected), the greater are the number of tasks performed; in addition, generally, the greater are the levels defined in the search for nodes, the more tasks are completely executed. This paper's main limitations are related to the simulation process, which led to a simplification of production process. The results found can be applied in several Industry 4.0 networks, such as additive manufacturing and collaborative networks, and this paper is original due to the use of simulation to test this kind of hypotheses in an Industry 4.0 production network.

Abstract