Hadi Farahani

Neda Rahimpour Anaraki, Alireza Azadbakht, Maryam Tahmasbi et al.

Recently, there has been a high demand for accelerating and improving the detection of automatic cadastral mapping. As this problem is in its starting point, there are many methods of computer vision and deep learning that have not been considered yet. In this paper, we focus on deep learning and provide three geometric post-processing methods that improve the quality of the work. Our framework includes two parts, each of which consists of a few phases. Our solution to this problem uses instance segmentation. In the first part, we use Mask R-CNN with the backbone of pre-trained ResNet-50 on the ImageNet dataset. In the second phase, we apply three geometric post-processing methods to the output of the first part to get better overall output. Here, we also use computational geometry to introduce a new method for simplifying lines which we call it pocket-based simplification algorithm. For evaluating the quality of our solution, we use popular formulas in this field which are recall, precision and F-score. The highest recall we gain is 95 percent which also maintains high Precision of 72 percent. This resulted in an F-score of 82 percent. Implementing instance segmentation using Mask R-CNN with some geometric post-processes to its output gives us promising results for this field. Also, results show that pocket-based simplification algorithms work better for simplifying lines than Douglas-Puecker algorithm.

Doratossadat Dastgheib, Hadi Farahani

We propose a doxastic Łukasiewicz logic \textbf{BŁ} that is sound and complete with respect to the class of Kripke-based models in which atomic propositions and accessibility relations are both infinitely valued in the standard MV-algebra [0,1]. We also introduce some extensions of \textbf{BŁ} corresponding to axioms \textbf{D}, \textbf{4}, and \textbf{T} of classical epistemic logic. Furthermore, completeness of these extensions are established corresponding to the appropriate classes of models.

Aref Moqadam Mehr, Saeed Reza Kheradpisheh, Hadi Farahani

Biological neurons use spikes to process and learn temporally dynamic inputs in an energy and computationally efficient way. However, applying the state-of-the-art gradient-based supervised algorithms to spiking neural networks (SNN) is a challenge due to the non-differentiability of the activation function of spiking neurons. Employing surrogate gradients is one of the main solutions to overcome this challenge. Although SNNs naturally work in the temporal domain, recent studies have focused on developing SNNs to solve static image categorization tasks. In this paper, we employ a surrogate gradient descent learning algorithm to recognize twelve human hand gestures recorded by dynamic vision sensor (DVS) cameras. The proposed SNN could reach 97.2% recognition accuracy on test data.

Hadi Farahani

In this paper, a quantum version of classical alternating bit protocol is proposed. This protocol provides a reliable method to transmit the secret quantum data via a noisy quantum channel while the entanglement between particles is not broken. Our protocol is based on quantum teleportation and superdense coding. By assuming that the participants can distinguish the alternating qubit from other messages and also the assumption that data can be resent unlimited times, an abstraction of this protocol can be derived. Using the quantum process algebra \textit{full} $qACP$, we show that the proposed protocol is correct, so the desired external behaviour of the protocol is guaranteed.