arXiv subjects
Publications and source records attributed to Ali Ghaffari.
We present new additive results for DMP elements in a Banach algebra with involution. The necessary and sufficient conditions under which the sum of two DMP elements is DMP are investigated.
Driver drowsiness detection has been the subject of many researches in the past few decades and various methods have been developed to detect it. In this study, as an image-based approach with adequate accuracy, along with the expedite process, we applied YOLOv3 (You Look Only Once-version3) CNN (Convolutional Neural Network) for extracting facial features automatically. Then, LSTM (Long-Short Term Memory) neural network is employed to learn driver temporal behaviors including yawning and blinking time period as well as sequence classification. To train YOLOv3, we utilized our collected dataset alongside the transfer learning method. Moreover, the dataset for the LSTM training process is produced by the mentioned CNN and is formatted as a two-dimensional sequence comprised of eye blinking and yawning time durations. The developed dataset considers both disturbances such as illumination and drivers' head posture. To have real-time experiments a multi-thread framework is developed to run both CNN and LSTM in parallel. Finally, results indicate the hybrid of CNN and LSTM ability in drowsiness detection and the effectiveness of the proposed method.
Many routing protocols have been proposed to handle reliability and real-time routing energy efficiency for wireless sensor networks. In this paper we propose a new routing protocol with QoS based capabilities for WSNs. We used priority queues for improve real-time and non-real-time packets forwarding according to deadline of them. The protocol finds a best-cost, time-sensitive packet forwarding mechanism for real-time data with minimum consumption of the energy. In order to avoid of congestion in network our protocol drops those packets who can't reach their destination in specified time. For service quality assurance in reliability domain we used packet reception rate as an important parameter (PRR) in selecting of neighbor nodes. Simulation results show that our new approach how can provide quality of service parameters.
In this paper, among other things, we state and prove the mean ergodic theorem for amenable semigroup algebras.
Let $M(S)$ be the Banach algebra of all bounded regular Borel measures on a locally compact Hausdorff semitopological semigroup $S$ with variation norm and convolution as multiplication. We obtain necessary and sufficient conditions for $M(S)^{*}$ to have a topologically left invariant mean.
The purpose of this note is to describe some algebraic conditions on a Banach algebra which force it to be finite dimensional. One of the main results in Theorem~2 which states that for a locally compact group $G$, $G$ is compact if there exists a measure $μ$ in $\hbox{Soc}(L^{1}(G))$ such that $μ(G) \neq 0$. We also prove that $G$ is finite if $\hbox{Soc}(M(G))$ is closed and every nonzero left ideal in $M(G)$ contains a minimal left ideal.