scholarly journals On-Demand Deep Model Compression for Mobile Devices

2018 ◽  
Author(s):  
Sicong Liu ◽  
Yingyan Lin ◽  
Zimu Zhou ◽  
Kaiming Nan ◽  
Hui Liu ◽  
...  
Keyword(s):  
Mobile Devices ◽  
On Demand ◽  
Model Compression ◽  
Deep Model

scholarly journals Deep model compression for mobile platforms: A survey

2019 ◽  
Vol 24 (6) ◽  
pp. 677-693 ◽  
Author(s):  
Kaiming Nan ◽  
Sicong Liu ◽  
Junzhao Du ◽  
Hui Liu
Keyword(s):  
Mobile Platforms ◽  
Model Compression ◽  
Deep Model

scholarly journals Noncooperative 802.11 MAC Layer Fingerprinting and Tracking of Mobile Devices

2017 ◽  
Vol 2017 ◽  
pp. 1-21 ◽  
Author(s):  
Pieter Robyns ◽  
Bram Bonné ◽  
Peter Quax ◽  
Wim Lamotte
Keyword(s):  
Mobile Devices ◽  
Mobile Device ◽  
Peer To Peer ◽  
Mitigation Strategies ◽  
The Other ◽  
Entropy Analysis ◽  
Mac Layer ◽  
Music Festival ◽  
On Demand ◽  
802.11 Mac

We present two novel noncooperative MAC layer fingerprinting and tracking techniques for Wi-Fi (802.11) enabled mobile devices. Our first technique demonstrates how a per-bit entropy analysis of a single captured frame allows an adversary to construct a fingerprint of the transmitter that is 80.0 to 67.6 percent unique for 50 to 100 observed devices and 33.0 to 15.1 percent unique for 1,000 to 10,000 observed devices. We show how existing mitigation strategies such as MAC address randomization can be circumvented using only this fingerprint and temporal information. Our second technique leverages peer-to-peer 802.11u Generic Advertisement Service (GAS) requests and 802.11e Block Acknowledgement (BA) requests to instigate transmissions on demand from devices that support these protocols. We validate these techniques using two datasets, one of which was recorded at a music festival containing 28,048 unique devices and the other at our research lab containing 138 unique devices. Finally, we discuss a number of countermeasures that can be put in place by mobile device vendors in order to prevent noncooperative tracking through the discussed techniques.

AdaptVoD - An Adaptive Video-on-Demand Platform for Mobile Devices

2011 ◽  
Author(s):  
Rafael Fernandes Lopes ◽  
Carlos Danilo Miranda Regis ◽  
Waslon Terllizzie Araujo Lopes ◽  
Marcelo Sampaio de Alencar
Keyword(s):  
Mobile Devices ◽  
Video On Demand ◽  
On Demand ◽  
Adaptive Video

scholarly journals COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning

2019 ◽  
Author(s):  
Wenxiao Wang ◽  
Cong Fu ◽  
Jishun Guo ◽  
Deng Cai ◽  
Xiaofei He
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Computational Cost ◽  
Cross Layer ◽  
Optimal Solutions ◽  
Deep Convolutional Neural Networks ◽  
Model Compression ◽  
Deep Model ◽  
Network Compression ◽  
Novel Algorithm

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify layer-wise pruning ratios. 3) They are prone to generate sub-optimal solutions because they neglect the inequality between reducing parameters and reducing computational cost. Reducing the same number of parameters in different positions in the network may reduce different computational cost. To address the above problems, we develop a novel algorithm named as COP (correlation-based pruning), which can detect the redundant filters efficiently. We enable the cross-layer filter comparison through global normalization. We add parameter-quantity and computational-cost regularization terms to the importance, which enables the users to customize the compression according to their preference (smaller or faster). Extensive experiments have shown COP outperforms the others significantly. The code is released at https://github.com/ZJULearning/COP.

Implantação do Serviço de IPTV em uma rede acadêmica: Um Estudo de Caso na Faculdade Católica do Tocantins

2021 ◽  
Vol 3 (5) ◽  
pp. 3230-3240
Author(s):  
Aline Diniz De Oliveira ◽  
Joaquim Pires De Oliveira ◽  
Kayllah Cunha Dos Santos ◽  
Stéphany Moraes Martins ◽  
Umbelina Macedo Dos Santos Filha
Keyword(s):  
Mobile Devices ◽  
Video Streaming ◽  
Communication Networks ◽  
Video On Demand ◽  
The Internet ◽  
Digital Television ◽  
Web Page ◽  
On Demand ◽  
Vod Server

Soluções baseadas em redes de comunicação podem ser aplicadas nas mais diversas áreas, tais como a Televisão Digital e comunicação entre dispositivos móveis. O presente artigo se propõe a descrever os estudos e experimentos realizados no desenvolvimento de um servidor IPTV na Faculdade Católica do Tocantins (FACTO) para distribuir conteúdo institucional na Internet, utilizando um servidor Video on Demand (VoD) e uma página web como meio de acesso ao streaming de vídeo disponibilizados pelo servidor.   Solutions based on communication networks can be applied in the most diverse areas, such as Digital Television and communication between mobile devices. This paper proposes to describe the studies and experiments carried out in the development of an IPTV server at Faculdade Católica do Tocantins (FACTO) to distribute institutional content on the Internet, using a Video on Demand (VoD) server and a web page as a means to access the video streaming made available by the server.

Sign in / Sign up

Export Citation Format

Share Document