Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Seyed Mehdi Iranmanesh is active.

Publication


Featured researches published by Seyed Mehdi Iranmanesh.


ieee systems conference | 2016

Robustness of cooperative forward collision warning systems to communication uncertainty

Seyed Mehdi Iranmanesh; Ehsan Moradi-Pari; Yaser P. Fallah; Sushanta Das; Muhammad Rizwan

Cooperative collision avoidance systems rely on communication between vehicles to detect possibility of collision. In this paper, we present a systematic approach to study the performance of emerging communication based vehicle safety systems. Examples of such systems include forward collision warning (FCW) application. We employ a co-simulation tool that we have developed jointly in collaboration with industry partners for this purpose. The tool allows joint study of the safety application and its underlying communication system. We utilize this tool and study the impact of communication uncertainties on a new variation of the FCW algorithm that has been designed by the team. In this paper, the impact of communication loss and the choice of signal communication logic are examined. It is shown that the relationship between communication loss and accuracy of hazard detection algorithm is non-linear. It is also shown that employing error-dependent communication logic will yield considerable gains in communication or accuracy of tracking and hazard detection. Network awareness in communication logic is also demonstrated to be beneficial in high communication loss situations.


conference on information sciences and systems | 2017

Polar coding for achieving the capacity of marginal channels in nonbinary-input setting

Amirsina Torfi; Sobhan Soleymani; Seyed Mehdi Iranmanesh; Hadi Kazemi; Rouzbeh A. Shirvani; Vahid Tabataba Vakili

Achieving information-theoretic security using explicit coding scheme in which unlimited computational power for eavesdropper is assumed, is one of the main topics is security consideration. It is shown that polar codes are capacity achieving codes and have a low complexity in encoding and decoding. It has been proven that polar codes reach to secrecy capacity in the binary-input wiretap channels in symmetric settings for which the wiretappers channel is degraded with respect to the main channel. The first task of this paper is to propose a coding scheme to achieve secrecy capacity in asymmetric nonbinary-input channels while keeping reliability and security conditions satisfied. Our assumption is that the wiretap channel is stochastically degraded with respect to the main channel and message distribution is unspecified. The main idea is to send information set over good channels for Bob and bad channels for Eve and send random symbols for channels that are good for both. In this scheme the frozen vector is defined over all possible choices using polar codes ensemble concept. We proved that there exists a frozen vector for which the coding scheme satisfies reliability and security conditions. It is further shown that uniform distribution of the message is the necessary condition for achieving secrecy capacity.


neural information processing systems | 2017

Few-Shot Adversarial Domain Adaptation

Saeid Motiian; Quinn Jones; Seyed Mehdi Iranmanesh; Gianfranco Doretto


international conference on biometrics | 2018

Deep Cross Polarimetric Thermal-to-Visible Face Recognition

Seyed Mehdi Iranmanesh; Ali Dabouei; Hadi Kazemi; Nasser M. Nasrabadi


arXiv: Computer Vision and Pattern Recognition | 2018

Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition.

Hadi Kazemi; Sobhan Soleymani; Ali Dabouei; Seyed Mehdi Iranmanesh; Nasser M. Nasrabadi


neural information processing systems | 2018

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

Hadi Kazemi; Sobhan Soleymani; Fariborz Taherkhani; Seyed Mehdi Iranmanesh; Nasser M. Nasrabadi


international conference on biometrics | 2018

Fingerprint Distortion Rectification Using Deep Convolutional Neural Networks

Ali Dabouei; Hadi Kazemi; Seyed Mehdi Iranmanesh; Jeremy M. Dawson; Nasser M. Nasrabadi


arxiv:eess.AS | 2018

Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification.

Sobhan Soleymani; Ali Dabouei; Seyed Mehdi Iranmanesh; Hadi Kazemi; Jeremy M. Dawson; Nasser M. Nasrabadi


arXiv: Computer Vision and Pattern Recognition | 2018

ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction.

Ali Dabouei; Sobhan Soleymani; Hadi Kazemi; Seyed Mehdi Iranmanesh; Jeremy M. Dawson; Nasser M. Nasrabadi


arXiv: Computer Vision and Pattern Recognition | 2018

Deep Sketch-Photo Face Recognition Assisted by Facial Attributes.

Seyed Mehdi Iranmanesh; Hadi Kazemi; Sobhan Soleymani; Ali Dabouei; Nasser M. Nasrabadi

Collaboration


Dive into the Seyed Mehdi Iranmanesh's collaboration.

Top Co-Authors

Avatar

Hadi Kazemi

West Virginia University

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Amirsina Torfi

University College of Engineering

View shared research outputs
Top Co-Authors

Avatar

Amirsina Torfi

University College of Engineering

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge