Energy consumption of mobile apps has become an important consideration as the underlying devices are constrained by battery capacity. Display represents a significant portion of an app's energy consumption. However, developers lack techniques to identify the user interfaces in their apps for which energy needs to be improved. In this paper, we present a technique for detecting display energy hotspots -user interfaces of a mobile app whose energy consumption is greater than optimal. Our technique leverages display power modeling and automated display transformation techniques to detect these hotspots and prioritize them for developers. In an evaluation on a set of popular Android apps, our technique was very accurate in both predicting energy consumption and ranking the display energy hotspots. Our approach was also able to detect display energy hotspots in 398 Android market apps, showing its effectiveness and the pervasiveness of the problem. These results indicate that our approach represents a potentially useful technique for helping developers to detect energy related problems and reduce the energy consumption of their mobile apps.
In situ testing techniques have become an important means of ensuring the reliability of embedded systems after they are deployed in the field. However, these techniques do not help testers optimize the energy consumption of their in situ test suites, which can needlessly waste the limited battery power of these systems. In this work, we extend prior techniques for test suite minimization in such a way as to allow testers to generate energy-efficient, minimized test suites with only minimal modifications to their existing work flow. We perform an extensive empirical evaluation of our approach using the test suites provided for real world applications. The results of the evaluation show that our technique is effective at generating, in less than one second, test suites that consume up to 95% less energy while maintaining coverage of the testing requirements.
To effectively overcome the cycle-skipping issue in full waveform inversion (FWI), we developed a deep neural network (DNN) approach to predict the absent low-frequency components by exploiting the hidden physical relation connecting the low- and the high-frequency data. To efficiently solve this challenging nonlinear regression problem, two novel strategies were proposed to design the DNN architecture and to optimize the learning process: (1) dual data feed structure; (2) progressive transfer learning. With the dual data feed structure, not only the high-frequency data, but also the corresponding beat tone data are fed into the DNN to relieve the burden of feature extraction. The second strategy, progressive transfer learning, enables us to train the DNN using a single evolving training dataset. Within the framework of the progressive transfer learning, the training dataset continuously evolves in an iterative manner by gradually retrieving the subsurface information through the physics-based inversion module, progressively enhancing the prediction accuracy of the DNN and propelling the inversion process out of the local minima. The synthetic numerical experiments suggest that, without any a priori geological information, the low-frequency data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.