Bandwidth Optimization for Real-Time Online and Mobile Applications

Author(s):  
Ahmed Mokhtar A. Mansour ◽  
Mona A. M. Fouad
2019 ◽  
Vol 1 (1) ◽  
pp. 450-465 ◽  
Author(s):  
Abhishek Sehgal ◽  
Nasser Kehtarnavaz

Deep learning solutions are being increasingly used in mobile applications. Although there are many open-source software tools for the development of deep learning solutions, there are no guidelines in one place in a unified manner for using these tools toward real-time deployment of these solutions on smartphones. From the variety of available deep learning tools, the most suited ones are used in this paper to enable real-time deployment of deep learning inference networks on smartphones. A uniform flow of implementation is devised for both Android and iOS smartphones. The advantage of using multi-threading to achieve or improve real-time throughputs is also showcased. A benchmarking framework consisting of accuracy, CPU/GPU consumption, and real-time throughput is considered for validation purposes. The developed deployment approach allows deep learning models to be turned into real-time smartphone apps with ease based on publicly available deep learning and smartphone software tools. This approach is applied to six popular or representative convolutional neural network models, and the validation results based on the benchmarking metrics are reported.


2003 ◽  
Vol 52 (2) ◽  
pp. 166-180 ◽  
Author(s):  
E. Nett ◽  
S. Schemmer

2011 ◽  
Vol 10 (3) ◽  
pp. 58-67 ◽  
Author(s):  
Sean J. Barbeau ◽  
Rafael A. Perez ◽  
Miguel A. Labrador ◽  
Alfredo J. Perez ◽  
Philip L. Winters ◽  
...  

2016 ◽  
Vol 34 (2_suppl) ◽  
pp. 157-157 ◽  
Author(s):  
Daniel Xiao Yang ◽  
Jackson Thea ◽  
Yi An ◽  
James B. Yu

157 Background: The use of digital health technology, including mobile applications, in the clinical setting is becoming increasingly more prevalent. Such technology is currently being explored as clinical research tools. While the side effects of prostate radiotherapy are well documented after treatment, there remains a paucity of data on patient-reported outcomes and changes in quality of life (QOL) during the treatment period. Therefore, mobile applications represent a practical platform to enable patient reporting in real-time during prostate radiotherapy. Methods: Using an existing open source code framework (Apple ResearchKit), we developed a novel mobile application that enables prostate cancer patients to report, either during or immediately following daily radiation treatment, changes in urinary, bowel, sexual, and hormonal QOL domains. The mobile application utilizes validated questions from the Expanded Prostate Index Composite for Clinical Practice (EPIC-CP) Survey, and allows for survey responses to be tracked over time throughout the treatment period and at routine follow up. Results: For the initial phase of our study, we are currently piloting the mobile application at a single institution with a goal of accruing 50 patients. Study results will be compared to data from traditional surveys, which are available at follow-up but impracticable for real-time symptom reporting. By ASCO 2016 Genitourinary Cancers Symposium, we plan to begin the second phase of our study where any patient can enroll online through a mobile software distribution platform (Apple App Store). Conclusions: We demonstrate the feasibility of using a mobile application to enable patients to report quality of life changes in real-time during prostate radiotherapy. Moreover, our application facilitates clinical trials where patient data collection can be automated and completed at scale. Future prospective studies are planned to evaluate validity of clinical trial data gathered through such methodology.


2015 ◽  
Vol 2015 ◽  
pp. 1-9
Author(s):  
Yao-Chung Fan ◽  
Hsueh-Wen Tseng

With the popularity of mobile devices, numerous mobile applications have been and will continue to be developed for various interesting usage scenarios. Riding this trend, recent research community envisions a novel information retrieving and information-sharing platform, which views the users with mobile devices, being willing to accept crowdsourcing tasks ascrowd sensors. With the neat idea, a set of crowd sensors applications have emerged. Among the applications, the geospatial information systems based on crowd sensors show significant potentials beyond traditional ones by providing real-time geospatial information. In the applications, user positioning is of great importance. However, existing positioning techniques have their own disadvantages. In this paper, we study using pervasive Wi-Fi access point as user position indicators. The major challenge for using Wi-Fi access point is that there is no mechanism for mapping observed Wi-Fi signals to human-defined places. To this end, our idea is to employ crowdsourcing model to perform place name annotations by mobile participants to bridge the gap between signals and human-defined places. In this paper, we propose schemes for effectively enabling crowdsourcing-based place name annotation, and conduct real trials with recruited participants to study the effectiveness of the proposed schemes. The experiment results demonstrate the effectiveness of the proposed schemes over existing solutions.


Indoor Navigation system is gaining lot of importance these days. It is particularly important to locate places inside a large university campus, Airport, Railway station or Museum. There are many mobile applications developed recently using different techniques. The work proposed in this paper is focusing on the need of visually challenged people while navigating in indoor environment. The approach proposed here implements the system using Beacon. The application developed with the system gives audio guidance to the user for navigation.


Author(s):  
S. Titova ◽  
B. Siryi

Augmented reality (AR) is the integration of digital information with the user’s environment in real time. AR software use in many different ways and for the needs of cartography too. This technology may be useful for the development of navigational mobile applications and actions with static (paper) maps. There are two main operating modalities for implementation of augmented reality in applications: by markers and by the positioning of customer and surrounding objects (by azimuths determination between customer’s device and real objects). The first way is applied for static maps when another way is applied for navigational mobile applications. Augmented reality provides at least six opportunities, which create better options for working with design and content of maps for cartographers. This technology also provides the new experience in the work on maps for customers. The advantages of using augmented reality in cartography are the partial equation of static maps to geographical information systems, adaptability of cartographic images to the needs of users, improving the quality of design and content possibilities of maps and making actions with maps more attractive for customers. However, this technology is not without disadvantages, which connected with the development of AR-applications and requirements to smartphones. In addition, this article reveals aspects of the creation of augmented maps in cartographic companies.


Sign in / Sign up

Export Citation Format

Share Document