Sharif Digital Repository

This letter presents a novel method based on sparsity, to solve the problem of deinterleaving pulse trains. The proposed method models the problem of deinterleaving pulse trains as an underdetermined system of linear equations. After determining the mixing matrix, we find sparsest solution of an underdetermined system of linear equations using basis pursuit denoising. This method is superior to previous ones in a number of aspects. First, spurious and missing pulses would not cause any performance reduction in the algorithm. Second, the algorithm works well despite the type of pulse repetition interval modulation that is used. Third, the proposed method is able to separate similar... 

Communication overhead is one of the major performance bottlenecks in large-scale distributed computing systems, in particular for machine learning applications. Conventionally, compression techniques are used to reduce the load of communication by combining intermediate results of the same computation task as much as possible. Recently, via the development of coded distributed computing (CDC), it has been shown that it is possible to enable coding opportunities across intermediate results of different computation tasks to further reduce the communication load. We propose a new scheme, named compressed coded distributed computing (in short, compressed CDC), which jointly exploits the above... 

In this study, artificial neural network (ANN) was used to model the hot deformation behavior of 7075 aluminum alloy during compression test, in the strain rate range of 0.0003-1 s-1 and temperature range of 200-450 C. The inputs of the model were temperature, strain rate, and strain, while the output of the model was the flow stress. The feed-forward back-propagation network with two hidden layers was built and successfully trained at different deformation domains by Levenberg-Marquardt training algorithm. Comparative analysis of the results obtained from the hyperbolic sine, the power law constitutive equations, and the ANN shows that the newly developed ANN model has a better performance... 

In this work, an optimum multilayer perceptron neural network is developed to model the correlation between hot working parameters (temperature, strain rate and strain) and flow stress of IN625 alloy. Three variations of standard back propagation algorithm (Broyden, Fletcher, Goldfarb and Shanno quasi-Newton, Levenberg-Marquardt and Bayesian) are applied to train the model. The results show that, in this case, the best performance, minimum error and shortest converging time are achieved by the Levenberg-Marquardt training algorithm. Comparing the predicted values and the experimental values reveals that a well trained network is capable of accurately calculating the flow stress of the alloy... 

In the event of a BLEVE, the overpressure wave can cause important effects over a certain area. Several thermodynamic assumptions have been proposed as the basis for developing methodologies to predict both the mechanical energy associated to such a wave and the peak overpressure. According to a recent comparative analysis, methods based on real gas behavior and adiabatic irreversible expansion assumptions can give a good estimation of this energy. In this communication, the Artificial Neural Network (ANN) approach has been implemented to predict the BLEVE mechanical energy for the case of propane and butane. Temperature and vessel filling degree at failure have been considered as input... 

Autoencoders have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while failing to regenerate the anomalous data. Based on this assumption, one could utilize the AE for novelty detection. However, it is known that this assumption does not always hold. Such an AE can often perfectly reconstruct the anomalous data due to modeling low-level and generic features in the input. We propose a novel training algorithm for the AE that facilitates learning more semantically meaningful features to address this problem. For this purpose, we exploit the fact that adversarial robustness... 

Reservoir computing is a machine learning approach that enables us to use recurrent neural networks without involving the complexity of training algorithms and make hardware implementation possible. We present a novel photonic architecture of a reservoir computer that employs a nonlinear node and a resonator to implement a virtual recurrent neural network. This resonator behaves as an echo generator component that substitutes the delay line in delaybased reservoir computers available in the literature. The virtual neural network formed in our implementation is fundamentally different from the delay-based reservoir computers. Different virtual architectures based on the FSR and the Finesse of... 

Sensors are one of the most vital instruments in Nuclear Power Plants (NPPs), and operators and safety systems monitor and analyze various parameters reported by them. Failure to detect sensors malfunctions or anomalies would lead to the considerable consequences. In this research, a new method based on thermal–hydraulic simulation by RELAP5 code and Feed-Forward Neural Networks (FFNN) is introduced to detect faulty sensors and estimate their correct value. For design an efficient neural net, seven feature selectors (i.e., Information gain, ReliefF, F-regression, mRMR, Plus-L Minus-R, GA, and PSO), three sigmoid activation functions (i.e., Logistic, Tanh and Elliot), and three training... 

Control of powered lower limb prostheses has a locomotion mode-dependent structure which demands a pattern recognizer that can classify the current locomotion mode and also detect transitions between them in an appropriate time. In order to achieve this goal, this paper presents a Fuzzy sequential locomotion mode recognition system to classify daily locomotion modes including level- walking, stair climbing, slope walking, standing and sitting using low-cost mechanical sensors. Since these signals have a quasi-periodic nature, using sequential pattern recognition tools, such as Hidden Markov Model(HMM) improves the recognition performance considering they use sequences of information to make...