Abstract
Developing and optimizing software applications for high performance and energy efficiency is a very challenging task, even when considering a single target machine. For instance, optimizing for multicore-based computing systems requires in-depth knowledge about programming languages, application programming interfaces (APIs), compilers, performance tuning tools, and computer architecture and organization. Many of the tasks of performance engineering methodologies require manual efforts and the use of different tools not always part of an integrated toolchain. This paper presents Pegasus, a performance engineering approach supported by a framework that consists of a source-to-source compiler, controlled and guided by strategies programmed in a Domain-Specific Language, and an autotuner. Pegasus is a holistic and versatile approach spanning various decision layers composing the software stack, and exploiting the system capabilities and workloads effectively through the use of runtime autotuning. The Pegasus approach helps developers by automating tasks regarding the efficient implementation of software applications in multicore computing systems. These tasks focus on application analysis, profiling, code transformations, and the integration of runtime autotuning. Pegasus allows developers to program their strategies or to automatically apply existing strategies to software applications in order to ensure the compliance of non-functional requirements, such as performance and energy efficiency. We show how to apply Pegasus and demonstrate its applicability and effectiveness in a complex case study, which includes tasks from a smart navigation system.

Abstract

Abstract
The internet is used by the majority of the world's population. Many of its contents are free for consumers, supported by digital marketing investment. The current large online population can render digital marketing campaigns inefficient for brands buying ads if the right message is not reaching the right audience. Customer Data Platforms (CDPs) enables brands to collect first-party data about their customers and leverage it to reach the right audience, without sharing private customer data with third parties. This paper documents how CDPs work, by detailing their main components as patterns and relating them as a pattern language. The language is composed of five patterns: Event Tracking, ID Matching, User Profile Storage, Segmentation, and Activation. The pattern language can be used by marketeers and engineers in digital marketing as an introduction or reference to how CDPs are designed and work. © 2022 ACM.

Abstract
Typical VR interactions can be tiring, including standing up, walking, and mid-air gestures. Such interactions result in decreased comfort and session duration compared with traditional non-VR interfaces, which may, in turn, reduce productivity. Nevertheless, current approaches often neglect this aspect, making the VR experience not as promising as it can be. As we see it, desk VR experiences provide the convenience and comfort of a desktop experience and the benefits of VR immersion, being a good compromise between the overall experience and ergonomics. In this work, we explore navigation techniques targeted at desk VR users, using both controllers and a large multi-touch surface. We address travel and orientation techniques independently, considering only continuous approaches for travel as these are better suited for exploration and both continuous and discrete approaches for orientation. Results revealed advantages for a continuous controller-based travel method and a trend for a dragging-based orientation technique. Also, we identified possible trends towards task focus affecting overall cybersickness symptomatology.

Abstract
Access to early myoelectric training can be a crucial step in mastering prosthesis control. Controlling a prothesis is a cognitively demanding task with high rejection rates. Serious games not only provide patients with an opportunity to train their myoelectric control, but also help maintain their engagement throughout the extensive rehabilitation process. This work proposes a novel serious game design to train machine learning based myoelectric control, implemented in the form of a music-based app. The prototype of the game was evaluated by seven able-bodied participants and three clinical professionals with regard to system usability and motivation. Results showed positive outcomes in motivation, and a need for specific system usability improvements. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract