Mobile Device Based Outdoor Navigation with On-Line Learning Neural Network: A Comparison with Convolutional Neural Network

Zheng, Zejia; Weng, Juyang

doi:10.1109/cvprw.2016.9

Cited by 15 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond indoor localization, there also exist several research works that apply deep learning in outdoor scenarios. For example, Zheng and Weng introduce a lightweight developmental network for outdoor navigation applications on mobile devices [321]. Compared to CNNs, their architecture requires 100 times fewer weights to be updated, while maintaining decent accuracy.…”

Section: Ez-sleepmentioning

confidence: 99%

Deep Learning in Mobile and Wireless Networking: A Survey

Zhang

Patras

Haddadi

2019

IEEE Commun. Surv. Tutorials

1,335

838

View full text Add to dashboard Cite

The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure. Upcoming 5G systems are evolving to support exploding mobile traffic volumes, real-time extraction of fine-grained analytics, and agile management of network resources, so as to maximize user experience. Fulfilling these tasks is challenging, as mobile environments are increasingly complex, heterogeneous, and evolving. One potential solution is to resort to advanced machine learning techniques, in order to help manage the rise in data volumes and algorithm-driven applications. The recent success of deep learning underpins new and powerful tools that tackle problems in this space.In this paper we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas. We first briefly introduce essential background and state-of-theart in deep learning techniques with potential applications to networking. We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems. Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains. Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.

show abstract

Section: Ez-sleepmentioning

confidence: 99%

Deep Learning in Mobile and Wireless Networking: A Survey

Zhang

Patras

Haddadi

2019

IEEE Commun. Surv. Tutorials

1,335

838

View full text Add to dashboard Cite

show abstract

“…The left-brain function processor consists of an array of the von Neumann-type processing cores, while the right-brain function processor is the neural network processor. The energy-efficient DCNN [49], RNN [50], SDCNN [51] or SNN [52] network, memristive neuroprocessor [53,54] can be adopted as the right brain-inspired processor. The two kinds of the processors can be reconfigured between each other by reconfigurable circuit techniques.…”

Section: Future Neuromorphic Vision Chipsmentioning

confidence: 99%

Neuromorphic vision chips

2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

The paper reviews the progress of neuromorphic vision chip research in decades. It focuses on two kinds of the neuromorphic vision chips: frame-driven (FD) and event-driven (ED) vision chips. The FD and ED vision chips are very different from each other in system architecture, image sensing, image information coding, image processing algorithm, design methodology. The vision chips can overcome serial data transmission and processing bottlenecks in traditional image processing systems. They can perform the high speed image capture and real-time image processing operations. This paper selects two typical chips from the two kinds of vision chips, respectively, and introduces their architectures, image sensing schemes, image processing processors and system operation. The FD neuromorphic reconfigurable vision chip comprises a high speed image sensor, a processing element array and self-organizing map neural network. The FD vision chip has the advantages in image resolution, static object detection, time-multiplex image processing, and chip area. The ED neuromorphic vision chip system is based on address-event-representation image sensor and event-driven multi-kernel convolution network. The ED vision chip has the advantages in fast sensing, low communication bandwidth, brain-like processing, and high energy efficiency. Finally, this paper discusses the architecture and the challenges of the future neuromorphic vision chip and indicates that the reconfigurable vision chip with left-and right-brain functions integrated in the three dimensional (3D) large-scale integrated circuit (LSI) technology becomes a trend of the research on the vision chip.

show abstract

“…For example, in 2017 the number of micro master programs on international online learning platforms reached 35, number of the X Series programs -40; number of vocationally certified programs -17; Use of interactive MOOC elements for blended learning in order to achieve educational goals. [11] Policy of any university related to online courses aims at expanding educational [2; 19; 24], personal, and communicative [38] capabilities of the students in the course of education, and the cutting of education costs. Use of massive online courses allows universities to solve staff, methodology, and logistical support problems related to the educational process.…”

Section: Introductionmentioning

confidence: 99%

“…Many university policies related to online courses are now aimed at expanding educational provision (Bangert, 2005; Larionova et al, 2016; Morris and Stommel, 2013), especially in relation to personal and communicative (Yin et al, 2017; Zheng and Weng, 2016) capabilities of students. The use of MOOCs allows universities to ‘reconfigure’ issues of staffing, methodology, and logistical support related to educational processes.…”

Section: Introductionmentioning

confidence: 99%

Russian perspectives of online learning technologies in higher education: An empirical study of a MOOC

Larionova

Brown

Bystrova

et al. 2018

Research in Comparative and International Education

View full text Add to dashboard Cite

With the advent and rapid growth of massive open online courses (MOOCs) in the world education market in the last decade, online learning technologies are becoming increasingly widespread not only in the non-formal education sector but also in higher and supplementary vocational education. The use of MOOCs for implementing educational programs at the universities opens wide opportunities in terms of expanding the educational choice of students, the development of virtual academic mobility, reducing the cost of educational services, and improving the accessibility of education. However, the effectiveness of using different online learning technologies in the educational process of universities and the consequences of their widespread adoption has not been sufficiently explored.In this research a comparative analysis based on an empirical study of the application of different online-learning models in the educational process within a university was carried out. An experiment was undertaken in which different groups of students of the Ural Federal University were encouraged to master some disciplines in the framework of a blended learning model and an online learning model with tutoring support. The results of the pilot study were compared with the training results of a control group of students who mastered the same disciplines in a traditional taught format. It was shown that both models using MOOCs in the educational process demonstrated greater effectiveness in comparison with the traditional model; both in terms of educational outcomes of students and in terms of their satisfaction with the learning process. For engineering and technical disciplines, there is no statistically significant difference in using blended or online learning technologies, whereas for humanitarian disciplines, where the communicative component of the learning process is significant, the blended learning technology produced better results. Conclusions of the empirical research can be useful for heads of educational organizations and teachers in the modernization of the educational process, improving teaching methods, and increasing the effectiveness of new educational technologies. The results of the research will also be used for implementing the State Priority Project "The Modern Digital Educational Environment of the Russian Federation".

show abstract

Mobile Device Based Outdoor Navigation with On-Line Learning Neural Network: A Comparison with Convolutional Neural Network

Cited by 15 publications

References 9 publications

Deep Learning in Mobile and Wireless Networking: A Survey

Deep Learning in Mobile and Wireless Networking: A Survey

Neuromorphic vision chips

Russian perspectives of online learning technologies in higher education: An empirical study of a MOOC

Contact Info

Product

Resources

About