Abstract

Abstract
Complex optimization scheduling problems frequently arise in the manufacturing and transport industries, where the goal is to find a schedule that minimizes the total amount of time (or cost) required to complete all the tasks. Since it is a critical factor in many industries, it has been, historically, a target of the scientific community. Mathematically, these problems are modelled with Job Shop scheduling approaches. Benchmark results to solve them are achieved with evolutionary algorithms. However, they still present some limitations, mostly related to execution times and the difficulty to generalize to other problems. Deep Reinforcement Learning is poised to revolutionise the field of artificial intelligence. Chosen as one of the MIT breakthrough technologies, recent developments suggest that it is a technology of unlimited potential which shall play a crucial role in achieving artificial general intelligence. This paper puts forward a state-of-the-art review on Job Shop Scheduling, Evolutionary Algorithms and Deep Reinforcement Learning. It also proposes a novel architecture capable of solving Job Shop Scheduling optimization problems using Deep Reinforcement Learning. © 2020, Springer Nature Switzerland AG.

Abstract

Abstract
Visual coherence between virtual and real objects is a major issue in creating convincing augmented reality (AR) applications. To achieve this seamless integration, actual light conditions must be determined in real time to ensure that virtual objects are correctly illuminated and cast consistent shadows. In this paper, we propose a novel method to estimate daylight illumination and use this information in outdoor AR applications to render virtual objects with coherent shadows. The illumination parameters are acquired in real time from context-aware live sensor data. The method works under unprepared natural conditions. We also present a novel and rapid implementation of a state-of-the-art skylight model, from which the illumination parameters are derived. The Sun's position is calculated based on the user location and time of day, with the relative rotational differences estimated from a gyroscope, compass and accelerometer. The results illustrated that our method can generate visually credible AR scenes with consistent shadows rendered from recovered illumination.

Abstract
As the usage of head-mounted displays (HMD) increases, it is important to establish best usage practices to ensure the appropriate use of Virtual Reality (VR) equipment. Among the factors that can contribute to a better user experience are exposure time, the content type and the gender of the user. This study evaluates the impact of these variables on users' Sense of Presence and Cybersickness when visualising 360 content using HMDs. Two types of 360 content (captured video vs. virtual environment) were evaluated across four different exposure times (1, 3, 5 and 7 min). Regarding Sense of Presence, the results revealed a statistically significant difference for Content Type, Gender, and Content Type x Gender. Regarding Cybersickness, no statistically significant results were found for any of the independent variables. Overall, the results encourage the use of synthesized environments for a female audience; for non-interactive environments, captured environments are more effective than synthesized environments; and exposure time is not a concern for experiences lasting between 1 and 7 min.

Abstract
With the thriving of different natural interaction paradigms-such as gesture-based interfaces-it becomes important to understand how these novel interfaces can influence users' performance when it comes to their age. Recent advances made in human-computer interaction allow us to manipulate digital contents more intuitively; however, no work has yet been reported that systematically evaluates how gestural interfaces may influence the performance of different user groups. Different optical sensors, which allow human body acquisition with reliable accuracy, have been released, and with the appearance of such controllers for gesture recognition, it becomes important to understand if different age-related groups display similar performance levels concerning gestural interaction, or, on the other hand, if specific sensors could induce better results than others when dealing with users of different age brackets. In this article, we compare two gesture-sensing devices (Microsoft Kinect and Leap Motion) using the Fitts' law model to evaluate target acquisition performance, with relation to three user groups: children, young adults and older adults. This case study involved 60 participants that were asked to perform a simple continuous selection task as quickly and accurately as possible using one of the devices for gestural recognition. Indeed, performance results showed statistically significant differences among the age groups in the selection task accomplished. However, when considering the users' performance with regard to both input devices compared side by side, there were no significant differences in each group of users. We believe this situation could imply that the device itself might not have influenced the users' performance, but actually the users' age might. The participants feedback was interesting on account of their behaviors and preferences: Although there are no significant differences in performance, there could be when it comes to user preference.