Multi-objective Full Model Selection in temporal databases: Optimizing time and performance

Author(s):  
Nancy Perez-Castro ◽  
Hector Gabriel Acosta-Mesa ◽  
Efren Mezura-Montes ◽  
Hugo Jair Escalante
2014 ◽  
Vol 71 (1) ◽  
pp. 95-105
Author(s):  
Alejandro Rosales-Pérez ◽  
Jesús A. González ◽  
Carlos A. Reyes-García ◽  
Carlos A. Coello Coello

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 117795-117812
Author(s):  
Nima Khodadadi ◽  
Mahdi Azizi ◽  
Siamak Talatahari ◽  
Pooya Sareh

Author(s):  
Nancy Perez-Castro ◽  
Aldo Marquez-Grajales ◽  
Hector Gabriel Acosta-Mesa ◽  
Efren Mezura-Montes

2021 ◽  
Author(s):  
Aakriti Tarun Sharma

The process of converting a behavioral specification of an application to its equivalent system architecture is referred to as High Level-Synthesis (HLS). A crucial stage in embedded systems design involves finding the trade off between resource utilization and performance. An exhaustive search would yield the required results, but would take a huge amount of time to arrive at the solution even for smaller designs. This would result in a high time complexity. We employ the use of Design Space Exploration (DSE) in order to reduce the complexity of the design space and to reach the desired results in less time. In reality, there are multiple constraints defined by the user that need to be satisfied simultaneously. Thus, the nature of the task at hand is referred to as Multi-Objective Optimization. In this thesis, the design process of DSP benchmarks was analyzed based on user defined constraints such as power and execution time. The analyzed outcome was compared with the existing approaches in DSE and an optimal design solution was derived in a shorter time period.


2018 ◽  
Vol 20 (4) ◽  
pp. 864-885 ◽  
Author(s):  
Younggu Her ◽  
Chounghyun Seong

Abstract Multi-objective calibration can help identify parameter sets that represent a hydrological system and enable further constraining of the parameter space. Multi-objective calibration is expected to be more frequently utilized, along with the advances in optimization algorithms and computing resources. However, the impact of the number of objective functions on modeling outputs is still unclear, and the adequate number of objective functions remains an open question. We investigated the responses of model performance, equifinality, and uncertainty to the number of objective functions incorporated in a hierarchical and sequential manner in parameter calibration. The Hydrological Simulation Program – FORTRAN (HSPF) models that were prepared for bacteria total maximum daily load (TMDL) development served as a mathematical representation to simulate the hydrological processes of three watersheds located in Virginia, and the Expert System for Calibration of HSPF (HSPEXP) statistics were employed as objective functions in parameter calibration experiments. Results showed that the amount of equifinality and output uncertainty overall decreased while the model performance was maintained as the number of objective functions increased sequentially. However, there was no further significant improvement in the equifinality and uncertainty when including more than four objective functions. This study demonstrated that the introduction of an adequate number of objective functions could improve the quality of calibration without requiring additional observations.


Sign in / Sign up

Export Citation Format

Share Document