Papers by Mostafa Rahimi Azghadi
Gender classification based on speech signal is an important task in variant fields such as conte... more Gender classification based on speech signal is an important task in variant fields such as content-based multimedia. In this paper we propose a novel and efficient method for gender classification based on neural network. In our work pitch feature of voice is used for classification between males and females. Our method is based on an MLP neural network. About 96 % of classification accuracy is obtained for 1 second speech segments.
Full-adders are the core element of the complex arithmetic circuits like addition, multiplication... more Full-adders are the core element of the complex arithmetic circuits like addition, multiplication, division and exponentiation. Regarding to this importance, new idea and investigations for constructing full-adders are required. As far as related literature is concerned, generality and ease of use, as well as voltage and transistor scaling are considerable advantages of CMOS logic design versus other design style such as CPL specially when cell-based design are targeted. This paper proposes a novel, symmetric and efficient design for a CMOS 1-bit full-adder. Besides, another fully symmetric full-adder has been presented. Results and simulations demonstrate that the proposed design leads to an efficient full-adder in terms of power consumption, delay and area in comparison to a well-known conventional full-adder design. The post-layout simulations have been done by HSPICE with nanometer scale transistors considering all parasitic capacitors and resistors.
Journal of Applied Sciences, 2007
Quantum-dot Cellular Automata (QCA) is a novel and potentially attractive technology for implemen... more Quantum-dot Cellular Automata (QCA) is a novel and potentially attractive technology for implementing computing architectures at the nano-scale. The basic Boolean primitive in QCA is the majority gate. In this study we present a novel design for QCA cells and another possible and unconventional scheme for majority gates. By applying these items, the hardware requirements for a QCA design can be reduced and circuits can be simpler in level and gate counts. As an example, a one bit QCA adder is constructed by applying our new scheme. Beside, we prove that how our reduction method decreases gate counts and levels in comparison to the other previous methods.
Triplet-based Spike Timing Dependent Plasticity (TSTDP) is a powerful synaptic plasticity rule th... more Triplet-based Spike Timing Dependent Plasticity (TSTDP) is a powerful synaptic plasticity rule that acts beyond conventional pair-based STDP (PSTDP). Here, the TSTDP is capable of reproducing the outcomes from a variety of biological experiments, while the PSTDP rule fails to reproduce them. Additionally, it has been shown that the behaviour inherent to the spike rate-based Bienenstock–Cooper–Munro (BCM) synaptic plasticity rule can also emerge from the TSTDP rule. This paper proposes an analogue implementation of the TSTDP rule. The proposed VLSI circuit has been designed using the AMS 0.35 μm CMOS process and has been simulated using design kits for Synopsys and Cadence tools. Simulation results demonstrate how well the proposed circuit can alter synaptic weights according to the timing difference amongst a set of different patterns of spikes. Furthermore, the circuit is shown to give rise to a BCM-like learning rule, which is a rate-based rule. To mimic an implementation environment, a 1000 run Monte Carlo (MC) analysis was conducted on the proposed circuit. The presented MC simulation analysis and the simulation result from fine-tuned circuits show that it is possible to mitigate the effect of process variations in the proof of concept circuit; however, a practical variation aware design technique is required to promise a high circuit performance in a large scale neural network. We believe that the proposed design can play a significant role in future VLSI implementations of both spike timing and rate based neuromorphic learning systems.
Gender classification based on speech signal is an important task in variant fields such as conte... more Gender classification based on speech signal is an important task in variant fields such as content-based multimedia. In this paper we propose a novel and efficient method for gender classification based on neural network. In our work pitch feature of voice is used for classification between males and females. Our method is based on an MLP neural network. About 96% of classification accuracy is obtained for 1 second speech segments.
Abstract Multiprocessor task scheduling plays a fundamental role in parallel applications and dis... more Abstract Multiprocessor task scheduling plays a fundamental role in parallel applications and distributed networks. All of the methods for this kind of scheduling are concerned with achieving optimal running time. In this way parallel execution of tasks on several processors based on precedence graph should be considered. In this study, first a new heuristic method has been introduced which improved the execution time of some precedence graphs.
Abstract: A method for decreasing the number of Quantum Dot Cells in Quantum Dot Cellular Automat... more Abstract: A method for decreasing the number of Quantum Dot Cells in Quantum Dot Cellular Automata (QCA) circuits is presented. The proposed method is based on physical relation and computing physical forces between electrons. Correctness of our method is proved using some simple physical proofs. Our method is useful when the QCA circuit has many inverter gates.
Abstract Spike Timing-Dependent Plasticity (STDP) is one of several plasticity rules that is beli... more Abstract Spike Timing-Dependent Plasticity (STDP) is one of several plasticity rules that is believed to play an important role in learning and memory in the brain. In conventional pair-based STDP learning, synaptic weights are altered by utilizing the temporal difference between pairs of pre-and post-synaptic spikes.
Abstract: Quantum-dot Cellular Automata (QCA) is one of the most attractive technologies for comp... more Abstract: Quantum-dot Cellular Automata (QCA) is one of the most attractive technologies for computing at nano-scale. The principle logic element in QCA is majority gate. In this paper, a novel design for 5-input majority gate is presented. A 5-input majority gate study has been proposed; however this study has changed the scheme of basic QCA cells. The new proposed device reduces cell counts and area and uses conventional form of QCA cells.
The Travelling Salesman Problem or the TSP is a representative of a large class of problems known... more The Travelling Salesman Problem or the TSP is a representative of a large class of problems known as combinatorial optimization problems. In the ordinary form of the TSP, a map of cities is given to the salesman and he has to visit all the cities only once to complete a tour such that the length of the tour is the shortest among all possible tours for this map.
Scheduling problem in multiprocessor, parallel and distributed systems are placed in NP-hard prob... more Scheduling problem in multiprocessor, parallel and distributed systems are placed in NP-hard problems arena. These scheduling problems are employed in different important applications such as information processing, whether forecasting, image processing, database systems, process control, economics, operation research, and other areas. The data for these applications should be disseminated on different processors.
Uploads
Papers by Mostafa Rahimi Azghadi