Loading...
Search for:
karimi-bavandpour--n
0.146 seconds
Total 4055 records
Class attention map distillation for efficient semantic segmentation
, Article 1st International Conference on Machine Vision and Image Processing, MVIP 2020, 19 February 2020 through 20 February 2020 ; Volume 2020-February , 2020 ; Kasaei, S ; Sharif University of Technology
IEEE Computer Society
2020
Abstract
In this paper, a novel method for capturing the information of a powerful and trained deep convolutional neural network and distilling it into a training smaller network is proposed. This is the first time that a saliency map method is employed to extract useful knowledge from a convolutional neural network for distillation. This method, despite of many others which work on final layers, can successfully extract suitable information for distillation from intermediate layers of a network by making class specific attention maps and then forcing the student network to mimic producing those attentions. This novel knowledge distillation training is implemented using state-of-the-art DeepLab and...
Class Attention Map Distillation In Semantic Segmentation
, M.Sc. Thesis Sharif University of Technology ; Kasaei, Shohreh (Supervisor)
Abstract
Semantic segmentation is the tash of labeling each pixel of an input image. It is one of the main problems in computer vision and plays an important role in scene understanding. State of the art methods of solving it are based on Convolutional Neural Networhs (CNNs). While many real world tasks like autodriving cars and robot navigation require fast and lightweight models, CNNs inherently tend to give beter accuracy when they are deeper and bigger, and this has raised interest in designing compact networks. Knowledge distillation is one of the popular methods of training compact networhs and helps to transfer a big and powerful network’s knowledge to a small and compact one. In this research...
Biologically inspired spiking neurons: Piecewise linear models and digital implementation
, Article IEEE Transactions on Circuits and Systems I: Regular Papers ; Volume 59, Issue 12 , 2012 , Pages 2991-3004 ; 15498328 (ISSN) ; Ahmadi, A ; Bavandpour, M ; Sharif University of Technology
2012
Abstract
There has been a strong push recently to examine biological scale simulations of neuromorphic algorithms to achieve stronger inference capabilities. This paper presents a set of piecewise linear spiking neuron models, which can reproduce different behaviors, similar to the biological neuron, both for a single neuron as well as a network of neurons. The proposed models are investigated, in terms of digital implementation feasibility and costs, targeting large scale hardware implementation. Hardware synthesis and physical implementations on FPGA show that the proposed models can produce precise neural behaviors with higher performance and considerably lower implementation costs compared with...
Implementation of Spiking Neural Networks on Memristive Crossbar Structure
, M.Sc. Thesis Sharif University of Technology ; Bagheri Shouraki, Saeed (Supervisor)
Abstract
Hardware implementation of Spiking Neural Networks (SNN) can bring about a fast and low cost neural network which has more biological support. Memristor nanodevices are most proposed devices for use as synapses to add dynamic learning to SNNs because of their nano-scale dimensions, low power consumption and memory property. One of the most important bottlenecks in the memristor crossbar based SNNs is system-level simulation of learning process due to its huge memristor equations that should be solved for each sample of time. Due to parallel computation capability of our simulation work, we simulate the circuit on single core CPU and then proposed high performance parallel platforms as...
Multi-disciplinary Analysis of Solar-Powered Unmanned Aerial Vehicles for Extended Endurance
, Article Arabian Journal for Science and Engineering ; 2024 ; 2193567X (ISSN) ; Saboohi, Z ; Karimi, N ; Sharif University of Technology
2024
Abstract
Drones are extensively utilized in numerous critical applications today, necessitating high flight endurance for many tasks. As a result, solar unmanned aerial vehicles (UAVs) have gained considerable attention from researchers. This study presents the design of two UAVs with distinct wing configurations, both equipped with an equal number of solar cells. A numerical approach is employed to model these UAVs and calculate their aerodynamic coefficients. The power required for sustained level flight is determined using established aerodynamic equations. Additionally, solar cells are simulated in MATLAB/Simulink to investigate the impact of solar radiation on cell output power, current, and...
A Low area overhead NBTI/PBTI sensor for SRAM memories
, Article IEEE Transactions on Very Large Scale Integration (VLSI) Systems ; Volume 25, Issue 11 , 2017 , Pages 3138-3151 ; 10638210 (ISSN) ; Rohbani, N ; Miremadi, S. G ; Sharif University of Technology
2017
Abstract
Bias temperature instability (BTI) is known as one serious reliability concern in nanoscale technologies. BTI gradually increases the absolute value of threshold voltage (Vth) of MOS transistors. The main consequence of Vth shift of the SRAM cell transistors is the static noise margin (SNM) degradation. The SNM degradation of SRAM cells results in bit-flip occurrences due to transient faults and should be monitored accurately. This paper proposes a sensor called write current-based BTI sensor (WCBS) to assess the BTI-aging state of SRAM cells. The WCBS measures BTI-induced SNM degradation of SRAM cells by monitoring the maximum write current shifts due to BTI. The observations show that the...
Effects of the design parameters of multimodel adaptive control on the performance of a flexible transmission system
, Article International Journal of Adaptive Control and Signal Processing ; Volume 15, Issue 3 , 2001 , Pages 335-352 ; 08906327 (ISSN) ; Landau, I. D ; Motee, N ; Sharif University of Technology
2001
Abstract
Design parameters selection in the multimodel adaptive control based on switching and tuning will be investigated. Some design parameters like number of fixed and adaptive models, forgetting factor and minimum time delay between switchings will be considered. A recently developed parameter adaptation algorithm based on closed-loop output error will be compared with the classical least-squares prediction error algorithm in the multimodel adaptive control. The effects of these parameters on the performance in tracking and in regulation of a flexible transmission system will be studied via several simulation examples
Deterioration Detection in Historical Buildings with Different Materials Based on Novel Deep Learning Methods with Focusing on Isfahan Historical Bridges
, Article International Journal of Architectural Heritage ; Volume 18, Issue 6 , 2024 , Pages 981-993 ; 15583058 (ISSN) ; Valibeig, N ; Rabiee, H. R ; Sharif University of Technology
2024
Abstract
Historical bridges comprise part of any society’s history, culture, and identity and reveal the manufacturing technology of hydraulic structures at their time. Nevertheless, these structures deteriorate because of their materials, the passage of time, and natural factors. Because of drought in the past two decades, historic bridges in Isfahan have faced consecutive wet-dry cycles, resulting in further defects in bridges. Moreover, stone materials in the bases and brick materials in the bodies of bridges have made detecting defects more complex, requiring experts for each material. Additionally, insufficient attention to these defects or human errors in their proper detection can affect their...
A thermodynamic-based large deformation viscoplastic constitutive relationship for asphalt concrete compaction
, Article International Journal of Solids and Structures ; Volume 165 , 2019 , Pages 192-216 ; 00207683 (ISSN) ; Darabi, M. K ; Tabatabaee, N ; Sharif University of Technology
Elsevier Ltd
2019
Abstract
This research proposes a large deformation, time-dependent viscoplastic constitutive relationship to enhance the prediction of the compaction degree of asphalt concrete materials under laboratory and field conditions. A large-deformation thermodynamic-based framework is presented. The Helmholtz free energy and rate of energy dissipation functions were assumed to derive rate-dependent constitutive relationships to relate multi-axial state of stresses to the recoverable and non-recoverable deformation response of asphalt concrete during compaction. A straightforward method that allows the calibration of the proposed model against laboratory compaction data (e.g., data from Superpave Gyratory...
A computational approach to heat transfer and ablation in space capsule insulation
, Article Case Studies in Thermal Engineering ; Volume 53 , 2024 ; 2214157X (ISSN) ; Razmjooei, M ; Karimi, N ; Golmakani, A ; Sharif University of Technology
2024
Abstract
In this article, the heat transfers and ablation phenomena of thermal insulations utilized in manned space capsules are investigated. In this regard, by collecting and solving the equations related to ablation insulations, a computer program has been developed that is able to predict the thermal response of these insulations under various operating conditions. This approach considers mass and heat transfer equations in two-dimensional solid bodies. To solve these equations, finite volume method and implicit formulation for time dependence have been used. The reaction equation, written in the form of Arrhenius, is solved using the Runge-Kutta method, and the density and the flux of the gas...
Reducing traffic congestion and increasing sustainability in special urban areas through one-way traffic reconfiguration
, Article Transportation ; 2021 ; 00494488 (ISSN) ; Ghadirifaraz, B ; Shetab Boushehri, S. N ; Hosseininasab, S. M ; Rafiei, N ; Sharif University of Technology
Springer
2021
Abstract
In the contemporary sustainable urban set up, one of the critical issues adversely affecting the quality of life in urban areas and inflicting immense costs on cities is traffic congestion. Traffic congestion is an outgrowth of increased traffic flow in certain locations of large cities. Recently, urban decision-makers and transportation planners resort to one-way traffic system as an effective traffic management strategy, which has a profound effect on reducing traffic congestion and improving traffic flow, leading to urban sustainability. In the present paper, the authors endeavored to develop a novel methodological framework based on optimization techniques in order to mitigate traffic...
Reducing traffic congestion and increasing sustainability in special urban areas through one-way traffic reconfiguration
, Article Transportation ; Volume 49, Issue 1 , 2022 , Pages 37-60 ; 00494488 (ISSN) ; Ghadirifaraz, B ; Shetab Boushehri, S. N ; Hosseininasab, S. M ; Rafiei, N ; Sharif University of Technology
Springer
2022
Abstract
In the contemporary sustainable urban set up, one of the critical issues adversely affecting the quality of life in urban areas and inflicting immense costs on cities is traffic congestion. Traffic congestion is an outgrowth of increased traffic flow in certain locations of large cities. Recently, urban decision-makers and transportation planners resort to one-way traffic system as an effective traffic management strategy, which has a profound effect on reducing traffic congestion and improving traffic flow, leading to urban sustainability. In the present paper, the authors endeavored to develop a novel methodological framework based on optimization techniques in order to mitigate traffic...
The lake urmia environmental disaster in Iran: a look at aerosol pollution
, Article Science of the Total Environment ; Volume 633 , 2018 , Pages 42-49 ; 00489697 (ISSN) ; Khaghani, A ; MacDonald, A. B ; Nguyen, P ; Karimi, N ; Heidary, P ; Karimi, N ; Saemian, P ; Sehatkashani, S ; Tajrishy, M ; Sorooshian, A ; Sharif University of Technology
2018
Abstract
Lake Urmia (LU) once was the second largest hypersaline lake in the world, covering up to 6000 km2, but has undergone catastrophic desiccation in recent years resulting in loss of 90% of its area and extensive coverage by playas and marshlands that represent a source of salt and dust. This study examines daily Aerosol Optical Depth (AOD) data from the Moderate Resolution Imaging Spectroradiometer (MODIS) between 2001 and 2015 over northwestern Iran, which encompasses LU. Intriguingly, salt emissions from the LU surface associated with ongoing desiccation do not drive the study region's AOD profile, whereas pollution transported from other regions and emissions around LU are more important....
Modeling the effect of process variations on the delay and power of the digital circuit using fast simulators
, Article 2013 21st Iranian Conference on Electrical Engineering, ICEE 2013 ; 2013 , 14-16 May ; 9781467356343 (ISBN) ; Soleimani, H ; Ahmadi, A ; Bavandpour, M ; Zwolinski, M ; Sharif University of Technology
2013
Abstract
Process variation has an increasingly dramatic effect on delay and power as process geometries shrink. Even if the amount of variation remains the same as in previous generations, it accounts for a greater percentage of process geometries as they get smaller. So an accurate prediction of path delay and power variability for real digital circuits in the current technologies is very important; however, its main drawback is the high runtime cost. In this paper, we present a new fast EDA tool which accelerates Monte Carlo based statistical static timing analysis (SSTA) for complex digital circuit. Parallel platforms like Message Passing Interface and POSIX® Threads and also the GPU-based CUDA...
Development of a stress-mode sensitive viscoelastic constitutive relationship for asphalt concrete: experimental and numerical modeling
, Article Mechanics of Time-Dependent Materials ; 2016 , Pages 1-35 ; 13852000 (ISSN) ; Tabatabaee, N ; Jahanbakhsh, H ; Jahangiri, B ; Sharif University of Technology
Springer Netherlands
2016
Abstract
Asphalt binder is responsible for the thermo-viscoelastic mechanical behavior of asphalt concrete. Upon application of pure compressive stress to an asphalt concrete specimen, the stress is transferred by mechanisms such as aggregate interlock and the adhesion/cohesion properties of asphalt mastic. In the pure tensile stress mode, aggregate interlock plays a limited role in stress transfer, and the mastic phase plays the dominant role through its adhesive/cohesive and viscoelastic properties. Under actual combined loading patterns, any coordinate direction may experience different stress modes; therefore, the mechanical behavior is not the same in the different directions and the asphalt...
Development of a stress-mode sensitive viscoelastic constitutive relationship for asphalt concrete: experimental and numerical modeling
, Article Mechanics of Time-Dependent Materials ; Volume 21, Issue 3 , 2017 , Pages 383-417 ; 13852000 (ISSN) ; Tabatabaee, N ; Jahanbakhsh, H ; Jahangiri, B ; Sharif University of Technology
Springer Netherlands
2017
Abstract
Asphalt binder is responsible for the thermo-viscoelastic mechanical behavior of asphalt concrete. Upon application of pure compressive stress to an asphalt concrete specimen, the stress is transferred by mechanisms such as aggregate interlock and the adhesion/cohesion properties of asphalt mastic. In the pure tensile stress mode, aggregate interlock plays a limited role in stress transfer, and the mastic phase plays the dominant role through its adhesive/cohesive and viscoelastic properties. Under actual combined loading patterns, any coordinate direction may experience different stress modes; therefore, the mechanical behavior is not the same in the different directions and the asphalt...
An optimal fractional order controller for an AVR system using particle swarm optimization algorithm
, Article 2007 Large Engineering Systems Conference on Power Engineering, LESCOPE'07, Montreal, QC, 10 October 2007 through 12 October 2007 ; January , 2007 , Pages 244-249 ; 9781424415830 (ISBN) ; Zamani, M ; Sadati, N ; Parniani, M ; Sharif University of Technology
2007
Abstract
Application of Fractional Order PID (FOPID) controller to an Automatic Voltage Regulator (AVR) is presented and studied in this paper. An FOPID is a PID whose derivative and integral orders are fractional numbers rather than integers. Design stage of such a controller consists of determining five parameters. This paper employs Particle Swarm Optimization (PSO) algorithm to carry out the aforementioned design procedure. A novel cost function is defined to facilitate the control strategy over both the time-domain and the frequencydomain specifications. Comparisons are made with a PID controller from standpoints of transient response, robustness and disturbance rejection characteristics. It is...
Development of an optimal process for friction stir welding based on GA-RSM hybrid algorithm
, Article Frattura ed Integrita Strutturale ; Volume 12, Issue 44 , April , 2018 , Pages 106-122 ; 19718993 (ISSN) ; Berto, F ; Karimi, N ; Ghoreishi, S. M. N ; Fakoor, M ; Mokari, M ; Sharif University of Technology
Gruppo Italiano Frattura
2018
Abstract
Performance of Friction Stir Welding (FSW) as a solid-state process is approved in several engineering applications, especially aluminum industries. Identification of mechanical behavior of the associated welded zone is necessary due to these extensive applications of FSW. In this study, considering the effect of rotational and forward speed of welding tool on the mechanical properties of welded region, a hybrid optimization method based on combination of Genetic Algorithm (GA) and Response Surface Method (RSM) named here as GA-RSM is proposed to achieve maximum tensile and ultimate strength. The results of GA-RSM are validated by per-forming necessary experimental tests on two wide-used...
Wettability alteration and oil recovery by spontaneous imbibition of low salinity brine into carbonates: Impact of Mg2+, SO4 2− and cationic surfactant
, Article Journal of Petroleum Science and Engineering ; Volume 147 , 2016 , Pages 560-569 ; 09204105 (ISSN) ; Al-Maamari, R. S ; Ayatollahi, S ; Mehranbod, N ; Sharif University of Technology
Elsevier B.V
2016
Abstract
A large amount of the discovered oil reserves are reserved in carbonate formations, which are mostly naturally fractured oil-wet. Wettability alteration towards more water-wet state reduces the capillary barrier, hence improving the oil recovery efficiency in such reservoirs. In this study, wettability alteration towards favorable wetting state was investigated by combining modified low salinity brine with surfactant during water flooding. The diluted brine was modified by increasing the concentration of Mg2+ and SO4 2−, individually as well as both ions in combination. Different brine formulations were tested experimentally through the observations of contact angle measurements and...
Mechanistic study of wettability alteration of oil-wet calcite: The effect of magnesium ions in the presence and absence of cationic surfactant
, Article Colloids and Surfaces A: Physicochemical and Engineering Aspects ; Volume 482 , October , 2015 , Pages 403-415 ; 09277757 (ISSN) ; Al Maamari, R. S ; Ayatollahi, S ; Mehranbod, N ; Sharif University of Technology
Elsevier
2015
Abstract
Over 60% of the world's discovered oil reserves are held in carbonate reservoirs, which are mostly naturally fractured. Conventional water flooding results in low oil recovery efficiency in these reservoirs as most of them are oil-wet. On account of negative capillary forces, injected brine cannot penetrate simply into an oil-wet matrix of fractured formations to force the oil out. Wettability alteration of the rock surface to preferentially more water-wet state has been extensively studied using both smart water and surfactants separately. This study aims to study the effects of Mg2+ as one of the most important wettability influencing ions on the wetting properties of oil-wet carbonate...