Loading...
Search for:
computational-speed
0.014 seconds
Solving the Network Design Problem by Surrogate Functions and Lower and Upper Bounds on the Objective Function at Different Levels of Budget
, M.Sc. Thesis Sharif University of Technology ; Poorzahedy, Hossein (Supervisor)
Abstract
The purpose of this research is to provide a method for finding a “good” solution to the network design problem with less computational efforts, faster than the existing conventional methods of solving this problem. Network design problem is the problem of selecting a subset of projects from a set of alternative projects so that to optimize the objective function (e.g., the total travel time in the network) subject to the set of existing constraints (e.g., budget). Due to the combinatorial and non-convex nature of the problem, its solution could be very cumbersome and time-consuming. Various methods have been proposed to solve this problem efficiently, providing good solutions at high...
Self-attention equipped graph convolutions for disease prediction
, Article 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, 8 April 2019 through 11 April 2019 ; Volume 2019-April , 2019 , Pages 1896-1899 ; 19457928 (ISSN) ; 9781538636411 (ISBN) ; Krishna, S. A ; Shekarforoush, S ; Kortuem, K ; Albarqouni, S ; Navab, N ; Sharif University of Technology
IEEE Computer Society
2019
Abstract
Multi-modal data comprising imaging (MRI, fMRI, PET, etc.) and non-imaging (clinical test, demographics, etc.) data can be collected together and used for disease prediction. Such diverse data gives complementary information about the patient's condition to make an informed diagnosis. A model capable of leveraging the individuality of each multi-modal data is required for better disease prediction. We propose a graph convolution based deep model which takes into account the distinctiveness of each element of the multi-modal data. We incorporate a novel self-attention layer, which weights every element of the demographic data by exploring its relation to the underlying disease. We demonstrate...
Proposal af a New Approach to Improve Communication and Computation Efficiency of Federated Edge Learning with Heterogeneous Resources
, M.Sc. Thesis Sharif University of Technology ; Hesabi, Shahin (Supervisor)
Abstract
In practice, to implement Federated learning on edge networks, devices must repeatedly transmit their trained models to the edge server through wireless links to update the global model; Due to the heterogeneity in the Federated Edge learning system, such as lack of power, some devices may not be able to connect to the base station and reduce the performance of the trained model or, if connected, impose a large delay on the learning process. To overcome the mentioned challenge, we propose a Collaborative Federated learning framework. In this framework, some devices can participate in Federated learning without connecting to the base station; In this way, devices that are not able to...
Simulation of the multi-purpose gamma irradiator dose distribution based on the GEANT4 and GPU system
, Article Journal of Instrumentation ; Volume 16, Issue 7 , 2021 ; 17480221 (ISSN) ; Hosseini, S. A ; Sharif University of Technology
IOP Publishing Ltd
2021
Abstract
Gamma irradiation systems are used extensively in the industry in order to sterilize medical devices, disinfect hygienic products and increase the shelf life of agricultural products. The method of gamma irradiation is superior to the older methods of heat or chemical treatment because it is by far a simpler operation. In this method, only one parameter, the exposure time is controlled, whereas in the other mentioned methods five or six different parameters need to be controlled. The design of irradiation systems generally includes the size and the location of products, and the arrangement of source rack pencils. In order to optimize the design of the gamma irradiation systems, it is needed...
Modeling, simulation, and optimal initiation planning for needle insertion into the liver
, Article Journal of Biomechanical Engineering ; Volume 132, Issue 4 , 2010 ; 01480731 (ISSN) ; Ahmadian, M. T ; Janabi Sharifi, F ; Sharif University of Technology
2010
Abstract
Needle insertion simulation and planning systems (SPSs) will play an important role in diminishing inappropriate insertions into soft tissues and resultant complications. Difficulties in SPS development are due in large part to the computational requirements of the extensive calculations in finite element (FE) models of tissue. For clinical feasibility, the computational speed of SPSs must be improved. At the same time, a realistic model of tissue properties that reflects large and velocity-dependent deformations must be employed. The purpose of this study is to address the aforementioned difficulties by presenting a cost-effective SPS platform for needle insertions into the liver. The study...