Loading...
Search for:
real-time-application
0.007 seconds
Total 51 records
Identity recognition based on convolutional neural networks using gait data
, Article 26th International Computer Conference, Computer Society of Iran, CSICC 2021, 3 March 2021 through 4 March 2021 ; 2021 ; 9781665412414 (ISBN) ; Lotfi, F ; Majdolhosseini, M ; Jafarian, M ; Taghirad, H. D ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2021
Abstract
As a critical part of any security system, identity recognition has become paramount among researchers. In this regard, several methods are presented while considering various sensors and data. In particular, gait data yields rich information about a person, including some exclusive moving patterns which can be utilized to distinguish between different individuals. On the other hand, convolutional neural networks are proved to be applicable for structured data, especially images. In this article, 12 markers are considered in gathering the gait data, each representing a lower-body joint location. Then, utilizing the gait data in a 2D tensor form, three different convolutional neural networks...
Frame Loss Error Concealment for H.264/AVC
, M.Sc. Thesis Sharif University of Technology ; Kasaei, Shohre (Supervisor)
Abstract
Due to fast growth of wireless mobile networks, video transmission over wireless media has been widely studied. As wireless networks are error prone, there is a high possibility of loss in sent packets. Since time limitations in real-time video applications should be met, the delay- related to resending packets -is not acceptable and the error should to be concealed at receiver side. In this thesis, with respect to different concealment methods, two new methods for temporal error concealment are proposed. In the first method, an optimized set of motion vectors is formed using motion vectors in surrounding blocks of the lost macro block, and then this set is searched for the best motion...
A fast Speaker Identification method using nearest neighbor distance
, Article International Conference on Signal Processing Proceedings, ICSP ; Volume 3 , 2012 , Pages 2159-2162 ; 9781467321945 (ISBN) ; Sameti, H ; Babaali, B ; Sharif University of Technology
2012
Abstract
By increasing the number of registered speakers in Speaker Identification (SI) systems, computation time for identifying an unknown speaker is significantly increased. This problem arises from the simple design of conventional methods. Due to this limitation, we cannot use conventional SI methods in real time applications. In this paper, we propose a two-step method to overcome this limitation. We use different identification methods for each step. In the first step we reduce the search space using Nearest Neighbor method. In the second step we identify the target speaker using the conventional GMM-based SI method. The experimental results show 3.4× speed-ups without any accuracy loss using...
A Hitchhiker's guide to computation offloading: Opinions from practitioners
, Article IEEE Communications Magazine ; Volume 55, Issue 7 , 2017 , Pages 193-199 ; 01636804 (ISSN) ; Yang, J ; Movaghar, A ; Hui, P ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2017
Abstract
Due to the increasing usage and capabilities of smart devices, mobile application developers build a large number of resource intensive applications, such as WAR applications. Even with the rapid development in hardware technology, the computing capability and battery capacity on wearable devices and smartphones still cannot meet the application demands with heavy computations and high battery drain. Pervasive computing addresses this problem by migrating applications to the resource providers external to mobile devices. The profitability of this method heavily depends on how to implement it and when to use it. Although there are many computation offloading systems proposed in the...
Efficient millimetre-wave imaging structure for detecting axially rotated objects
, Article IET Microwaves, Antennas and Propagation ; Volume 12, Issue 3 , 2018 , Pages 416-424 ; 17518725 (ISSN) ; Kavehvash, Z ; Shabany, M ; Sharif University of Technology
Institution of Engineering and Technology
2018
Abstract
An efficient multi-static millimetre-wave (MMW) imaging system is proposed with the aim of obtaining the information of an axially tilted object. It is known that a multi-static structure performs better than a mono-static array in detecting the reflected signal from axially tilted surfaces due to the specular reflection. Still, no efficient multi-static structure for the purpose of imaging tilted objects in view of the computational time, cost and image quality is proposed till now. The authors propose an efficient multi-static MMW imaging system tackle this issue with the minimum number of antennae. Furthermore, the small number of antennae in the proposed design and the proposed fast...
Conflict resolution maneuvers based on genetic algorithm modified webs
, Article 2009 IEEE Aerospace Conference, Big Sky, MT, 7 March 2009 through 14 March 2009 ; 2009 ; 1095323X (ISSN); 9781424426225 (ISBN) ; Alaeddini, A ; Sharif University of Technology
2009
Abstract
In this paper, the problem of designing optimal conflict-free maneuvers for planar multiple aircraft encounters is studied. The maneuvers propose suitable heading changes for aircraft in a cooperative manner. The new mathematical approach provides optimal trajectories to resolve a wide variety of conflicts, especially in the presence of high-altitude Clear Air Turbulence (CAT). The proposed approach effectively uses Genetic Algorithms (GA), together with modified webs, to quickly find conflict-resolving maneuvers. Different case studies show the method is fast enough to be used for real-time applications when resolving conflicts involving two aircraft. It is also efficient enough to resolve...
Analyzing and Improving the Real Time Routing in Software Defined Network
, Ph.D. Dissertation Sharif University of Technology ; Jahangir, Amir Hossein (Supervisor)
Abstract
Software defined network (SDN) is an emerging network architecture in which the network control is directly programmed and separated from the forwarding plane. The SDN is a suitable and adaptable infrastructure for the requirements of new networks such as the Internet of Things and the fifth generation of mobile phones. In real time systems, tasks that miss their deadline are considered worthless or useless. Nowadays, real time applications in the SDN platform have diversified and will continue to expand in the future. SDN should be able to support real time communications like traditional networks, and even better. Therefore, from a designer’s or analyst’s point of view of such networks, it...
Energy efficient and high speed error control scheme for real time wireless sensor networks
, Article International Journal of Distributed Sensor Networks ; Vol. 2014 , 2014 ; Movaghar, A ; Sabaei, M ; Sharif University of Technology
Abstract
Reliability and energy consumption are two of the main constraints in wireless sensor networks (WSNs). In this paper, a novel energy efficient and high speed error control scheme is introduced that is based on the Redundant Residue Number System (RRNS) allowing real-time application of WSNs. The proposed approach employs a new 3-moduli set {22n+1, 2 2n1-1, 2n- 1 } and an efficient reverse converter which relies on the Mixed Radix Conversion (MRC) algorithm and achieves significant improvements both in terms of conversion delay and hardware design. In order to obtain error controllability, two-redundant-moduli set 23n+1 - 1, 24n+1 - 1 is also added to the main 3-moduli set. The theoretical...
Cellular Memristive Dynamical Systems (CMDS)
, Article International Journal of Bifurcation and Chaos ; Vol. 24, issue. 5 , May , 2014 ; Soleimani, H ; Bagheri-Shouraki, S ; Ahmadi, A ; Abbott, D ; Chua, L. O ; Sharif University of Technology
Abstract
This study presents a cellular-based mapping for a special class of dynamical systems for embedding neuron models, by exploiting an efficient memristor crossbar-based circuit for its implementation. The resultant reconfigurable memristive dynamical circuit exhibits various bifurcation phenomena, and responses that are characteristic of dynamical systems. High programmability of the circuit enables it to be applied to real-time applications, learning systems, and analytically indescribable dynamical systems. Moreover, its efficient implementation platform makes it an appropriate choice for on-chip applications and prostheses. We apply this method to the Izhikevich, and FitzHugh-Nagumo neuron...
Locality aware P2P overlay architecture for live video streaming
, Article 2012 6th International Symposium on Telecommunications, IST 2012 ; 2012 , Pages 650-655 ; 9781467320733 (ISBN) ; Akbari, B ; Rabiee, H. R ; Salehi, M ; Sharif University of Technology
2012
Abstract
Recently, using Peer-to-Peer (P2P) overlay architectures have become a popular approach for live video streaming over the Internet. Since the peers in these systems are geographically distributed, the communication between them imposes huge redundant traffic into the Internet. One solution to address this problem is utilizing the locality aware algorithms to optimize the neighbor selection policy. However, for real-time applications like live video streaming we need to consider the trade-off between localizing the traffic and service quality. In this paper, we propose a novel pure P2P framework through two phases; (1) Local tracker selection, and (2) Overlay mesh construction. We introduce...
Fast feature-based template matching, based on efficient keypoint extraction
, Article Advanced Materials Research, 8 July 2011 through 11 July 2011 ; Volume 341-342 , July , 2012 , Pages 798-802 ; 10226680 (ISSN) ; 9783037852521 (ISBN) ; Soltanian, M ; Sharif University of Technology
2012
Abstract
In order to improve the performance of feature-based template matching techniques, several research papers have been published. Real-time applications require the computational complexity of keypoint matching algorithms to be as low as possible. In this paper, we propose a method to improve the keypoint detection stage of feature-based template matching algorithms. Our experiment results show that the proposed method outperforms keypoint matching techniques in terms of speed, keypoint stability and repeatability
Offline replication and online energy management for hard real-time multicore systems
, Article CSI Symposium on Real-Time and Embedded Systems and Technologies, RTEST 2015, 7 October 2015 through 8 October 2015 ; October , 2015 , Page(s): 1 - 7 ; 9781467380478 (ISBN) ; Safari, S ; Ansari, M ; Salehi, M ; Ejlali, A ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2015
Abstract
For real-time embedded systems, energy consumption and reliability are two major design concerns. We consider the problem of minimizing the energy consumption of a set of periodic real-time applications when running on a multi-core system while satisfying given reliability targets. Multi-core platforms provide a good capability for task replication in order to achieve given reliability targets. However, careless task replication may lead to significant energy overhead. Therefore, to provide a given reliability level with a reduced energy overhead, the level of replication and also the voltage and frequency assigned to each task should be determined cautiously. The goal of this paper is to...
Real-time impulse noise suppression from images using an efficient weighted-average filtering
, Article IEEE Signal Processing Letters ; Volume 22, Issue 8 , 2015 , Pages 1050-1054 ; 10709908 (ISSN) ; Hessar, F ; Marvasti, F ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2015
Abstract
In this letter, we propose a method for real-time high density impulse noise suppression from images. In our method, we first apply an impulse detector to identify the corrupted pixels and then employ an innovative weighted-average filter to restore them. The filter takes the nearest neighboring interpolated image as the initial image and computes the weights according to the relative positions of the corrupted and uncorrupted pixels. Experimental results show that the proposed method outperforms the best existing methods in both PSNR measure and visual quality and is quite suitable for real-time applications
Near-optimal trajectories to manage landing sequence in the vicinity of controlled aerodromes
, Article Journal of Aircraft ; Volume 47, Issue 1 , 2010 , Pages 129-140 ; 00218669 (ISSN) ; Nabavi, S. Y ; Sharif University of Technology
Abstract
A comprehensive approach is proposed to manage landing sequences and their associated trajectories for an arbitrary number of aircraft in the vicinity of a controlled aerodrome. The current approach, similar to that of "first come, first served," could consider different types of priorities as well as emergencies. The approach is especially useful to combine unstructured free-flight trajectories with structured ones during the approach phase of the flight A comprehensive cost function considers the relative size of all aircraft together with their relative speeds and flight directions. This helps optimize the amount of fuel consumption while respecting separation minima. Resulting...
A robust sparse representation based face recognition system for smartphones
, Article 2015 IEEE Signal Processing in Medicine and Biology Symposium - Proceedings, 12 December 2015 ; 2015 ; 9781509013500 (ISBN) ; Joneidi, M ; Rezaeifar, S ; Baradaran Shokouhi, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2015
Abstract
Many research works have been done in face recognition during the last years that indicates the importance of face recognition systems in many applications including identity authentication. In this paper we propose an approach for face recognition which is suitable for unconstrained image acquisition and has a low computational cost. Since in practical applications such as in smartphones, imaging conditions are not limited to existing images in the database, robustness of the recognition algorithm is very important. Here a sparse representation framework is proposed which achieves some degree of robustness. Using double sparse representation the high computational cost of sparsity-based...
An asymmetric checkpointing and rollback error recovery scheme for embedded processors
, Article 23rd IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems, DFT 2008, Boston, MA, 1 October 2008 through 3 October 2008 ; October , 2008 , Pages 445-453 ; 15505774 (ISSN) ; Miremadi, S. G ; Ejlali, A ; Sharif University of Technology
2008
Abstract
This paper presents a checkpointing scheme for rollback error recovery, called Asymmetric Checkpointing and Rollback Recovery (ACRR) which stores the processor states in an asymmetric manner. In this way, error recovery latency and the number of checkpoints are reduced to increase the probability of timely task completion for soft real-time applications. To evaluate the ACRR, this scheme was studied analytically. The analytical results show that the recovery latency is reduced as non-uniformity of the checkpoint increases. As a case study, the ACRR is implemented and simulated on a behavioral VHDL model of LEON2 processor. The simulation results follow the results obtained in the analytical...
ADIAN: A distributed intelligent ad-hoc network
, Article 8th International Conference on Distributed Computing and Networking, ICDCN 2006, Guwahati, 27 December 2006 through 30 December 2006 ; Volume 4308 LNCS , 2006 , Pages 27-39 ; 03029743 (ISSN); 9783540681397 (ISBN) ; Ghassem Sani, G ; Rabiee, H ; Ghanbari, M ; Dehghan, M ; Sharif University of Technology
2006
Abstract
Mobile Ad-hoc Networks are networks that have a dynamic topology without any fixed infrastructure. To transmit information in ad-hoc networks, we need robust protocols that can cope with constant changes in the network topology. The known routing protocols for mobile ad-hoc networks can be classified in two major categories: proactive routing protocols and reactive routing protocols. Proactive routing protocols keep the routes up-to-date to reduce delay in real-time applications but they have high control overhead. The control overhead in reactive routing protocols is much less than proactive routing protocols; however, the routes are discovered on demand, which is not suitable for real-time...
Dynamic iranian sign language recognition using an optimized deep neural network: An implementation via a robotic-based architecture
, Article International Journal of Social Robotics ; 2021 ; 18754791 (ISSN) ; Taheri, A ; Meghdari, A. F ; Boroushaki, M ; Alemi, M ; Sharif University of Technology
Springer Science and Business Media B.V
2021
Abstract
Sign language is a non-verbal communication tool used by the deaf. A robust sign language recognition framework is needed to develop Human–Robot Interaction (HRI) platforms that are able to interact with humans via sign language. Iranian sign language (ISL) is composed of both static postures and dynamic gestures of the hand and fingers. In this paper, we present a robust framework using a Deep Neural Network (DNN) to recognize dynamic ISL gestures captured by motion capture gloves in Real-Time. To this end, first, a dataset of fifteen ISL classes was collected in time series; then, this dataset was virtually augmented and pre-processed using the “state-image” method to produce a unique...
Robust fuzzy rough set based dimensionality reduction for big multimedia data hashing and unsupervised generative learning
, Article Multimedia Tools and Applications ; Volume 80, Issue 12 , 2021 , Pages 17745-17772 ; 13807501 (ISSN) ; Majidi, B ; Adabi, S ; Patra, J. C ; Movaghar, A ; Sharif University of Technology
Springer
2021
Abstract
The amount of high dimensional data produced by visual sensors in the smart environments and by autonomous vehicles is increasing exponentially. In order to search and model this data for real-time applications, the dimensionality of the data should be reduced. In this paper, a novel dimensionality reduction algorithm based on fuzzy rough set theory, called Centralized Binary Mapping (CBM), is proposed. The fuzzy CBM kernel is used for extracting the central elements and the memory cells from the blocks of high dimensional data. The proposed applications of CBM in this paper include hashing and generative modelling of multimedia big data. The robustness of the proposed CBM based hashing...
R2T-DSDN: reliable real-time distributed controller-based SDN
, Article Journal of Supercomputing ; Volume 77, Issue 11 , 2021 , Pages 12420-12457 ; 09208542 (ISSN) ; Jahangir, A. H ; Sharif University of Technology
Springer
2021
Abstract
Software-defined network (SDN) is an emerging network architecture in which the network control task is separated from packet forwarding. This architecture can be considered as a suitable infrastructure for fifth-generation mobile network (5G) and Internet of things due to its flexibility and dynamism. In real-time networks, time-sensitive packets that miss their deadlines are considered useless or less worthy. As with traditional networks, SDN is expected to support real-time communications and handle a variety of failures (including local controller, switch, and link failures) simultaneously. This study focuses on real-time communication of time-sensitive applications that operate on...