Loading...
Search for:
real-time-processing
0.01 seconds
Detection of Confidentiality Violation by Short Term Advanced Persistent Threats based on Data Stream Correlation
, M.Sc. Thesis Sharif University of Technology ; Amini, Morteza (Supervisor)
Abstract
Advanced Persistent Threats (APTs) by multi step , low-level and sometimes slowmoving behaviors try to hiding malicious behaviors. These attacks are complex, costly and the attacker violates the security policy explicitly or implicitly by distributing his or her behavior to multi agents and infiltrate trusted subjects. One of the challenges is the discovery of these attacks in the early stages of the attack and before the complete violation of confidentiality. the lack of deep intercepting of events, content with intrusion detection systems warnings, the lack of simultaneous tracking of host and network-level events and the lack of real-time processing is limitations of existing detection...
Facial Expression Recognition Using a Mobile Camera
, M.Sc. Thesis Sharif University of Technology ; Jamzad, Mansour (Supervisor)
Abstract
Detecting emotions and facial expressions, as a means of nonverbal communication between human and machines, has attracted a great deal of attention in recent decades with the developments in artificial intelligence and acknowledging the ties between robotics and future human life. Human face plays a key role in his communications and processing it in a video source for the sake of mood recognition could be employed in different applications such as improving human and machine communication and analysis of emotions in different circumstances. Facial expression detection is useful in understanding not only momentary emotions, but also mental activities, social interactions and psychological...
Steganalysis of internet data, a feasibility study
, Article 2011 International Symposium on Computer Networks and Distributed Systems, CNDS 2011, Tehran, 23 February 2011 through 24 February 2011 ; 2011 , Pages 61-66 ; 9781424491544 (ISBN) ; Khalilian, H ; Ghaemmaghami, S ; Sharif University of Technology
2011
Abstract
This paper addresses the feasibility of applying realtime steganalysis to the Internet data. To reach a practical solution, we have employed offline procedures to minimize the volume of the data to be processed by an online real-time system. Possible offline services that can be provided to an online system then led us to appropriate network designs for the online system. To go into detail of the online systems, we have carefully analyzed some well-known, state-of-the-art steganalysis algorithms and estimated their processing power and memory requirements. Some formulas are derived to relate the network bit rate with the number of the processing units, their processing power, and memory...
Estimation of water coverage ratio in low temperature PEM-fuel cell using deep neural network
, Article IEEE Sensors Journal ; Volume 20, Issue 18 , May , 2020 , Pages 10679-10686 ; Alasty, A ; Boroushaki, M ; Khodsiani, M. H ; Hasheminasab, M. R ; Kermani, M. J ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2020
Abstract
Proton exchange membrane fuel cell (PEMFC) is a rich source of renewable energy. A non-destructive prediction method is needed to determine the content of water in the PEMFC. In the gas channel of a transparent PEMFC, water is detected with image processing. This method has a high computational cost and is sensitive to the initial position of the camera and ambient lighting. In this paper, the deep neural network (DNN) has been trained to learn the transparent PEMFC's labeled images as a way to determine the content of water, limit human interference and employed in a real-time process. This DNN model is a virtual sensor for measuring the water coverage ratio. To produce the label of images,...