Visual domain adaptation aims to learn robust models for the test data by knowledge transferring from a training data where the training and test sets are from different distributions. Existing approaches attempt to solve domain shift problem with either adaptation across domains or performing low-rank constraints. In this paper, we propose a two-phases unsupervised approach referred as image reconstruction Error minimization via Distribution Adaptation and low-rank constraint (EDA), which benefits from both the distribution adaptation and the low-rank constraints to tackle distribution mismatch across domains. In the first phase, our proposed approach projects the training and test data onto a common subspace in which the marginal and conditional distribution differences of domains are minimized. Moreover, EDA benefits from domain invariant clustering to discriminate between various classes of data. In the second phase, for preserving data structure in the shared subspace, EDA minimizes the data reconstruction Error using low-rank and sparse constraints. Overall, EDA solves the domain mismatch problem in cubic time complexity. The proposed approach is evaluated on variety of visual benchmark datasets and its performance is compared with the other state-of-the-art domain adaptation methods. The average accuracy of EDA on 32 experiments is determined 68. 33% where outperforms other state-of-the-art domain adaptation methods with 4. 28% improvement.

Supportive policies on wheat crops to achieve food security have always been considered by the concerned policy-makers, but only in the short term. The Iranian governments subsidize wheat consumption within a framework of the Affordable Food Policy as well as the supportive pricing policies, subsidizing production inputs, and insurance for wheat production. Presently, the government is also the sole buyer and seller of wheat in the country. This study aimed at evaluating the government policies in the wheat market during 2000-2016, considering the continuity and increasing costs of support programs for wheat producers and consumers. For this purpose, the modeling results showed that the supply and demand elasticity values in Iran market were invalid and had to be evaluated using a model Error. The economists might only use supply and demand elasticity values with low Errors to model the welfare and an acceptable market situation; otherwise, based on model Error, welfare calculations, or production and consumption losses would be invalid. For solving this problem, a new model based on the complicated Iran market was investigated, analyzed and verified. . .

Due to the importance of fault detection in maintaining the performance and immunity of control process, various methods have been proposed where as well as fault detection, the robustness of the system with respect to uncertainty and disturbance has been also discussed. In this regard a compromise between Error sesitivity of the system and its robustness should be considered. One of the proposed methods is based on transformation of robust fault detection problem to a standard H¥ model-matching one. In this paper after the selection of a proper reference model for the robust fault detection problem, a residual generator will be considered on the basis of an H¥ minimization of the difference between reference model the realastic residual generator using LMI technics. A design example has been chosen to demonstrate the effectiveness of the proposed approach.

Domain adaptation can transfer knowledge from a training set (source domain) to a test set (target domain), promoting the performance of the model learned from the training set. In addition, sparse coding makes the learned model more succinct and easy to manipulate. However, the existence of the distribution mismatch across the source and target domains reduce the performance of model. In this paper, we propose an unsupervised domain adaptation model to minimize the prediction Error of image classification. Sample reweighting is utilized to handle redundant and useless information of source data in the new representation. Moreover, the difference of the conditional distributions across the source and target domains is reduced along with the subspace alignment. Our proposed approach learns a sparse domain-invariant classifier in a latent subspace with preserving the structure of the input data. Extensive experiments demonstrate that our proposed approach shows 4. 49% improvement in classification accuracy on real-world datasets compared to state-of-the-art machine learning and domain adaptation methods.

Solar energy forecasting is necessary due to its variable and fluctuating nature, but it is also a challenge to predict accurately behaviour of solar irradiation. To capture this, the proposed methodology uses an ensemble model combined with Error minimization and CEEMDAN Pre-processing technique. In this paper, data of two locations are used to predict short term forecasting of solar irradiation using seven developed models based on the proposed procedure. The use of hourly forecasting, CEEMDAN method, Error minimization and ensemble hybrid model enhance the anti-interference capability of all developed model. Four-year data of New Delhi and Ahmedabad is used and sourced from NSRDB website. Out of all the proposed models CEEMDAN-CNN-BiLSTM-MLP with CEEMDAN_IMF_18 configured signal processing approach achieved least average RMSE, n-RMSE and MAE of both locations with values 13.215 W/m2, 7.13% and 8.605 W/m2 respectively and have maximum average R2 (99.205%). When compared to persistence model, proposed model with this configuration was able to outperform with average percentage improvement 87.63%, 86.78%, 87.17% and 17.875% in terms of  , ,  and   respectively. The proposed model outperforms existing techniques for solar irradiation forecasting, demonstrating greater efficiency and reliability, making it a valuable reference for future performance optimization.

There is an increasing trend towards the engineering characteristics and utility of proteins in order to the industrial, biotechnological and biopharmaceutical applications. Lots of protein manipulations can be achieved through site directed mutagenesis. It is expensive and time consuming to analyze the effect of mutation by getting an X-ray structure of mutant proteins. The use of predictive computational methods has become more prevalent in recent years leading to decrease the cost of experiments. Therefore, it is needed and common to predict the influence of engineering on protein structure with molecular dynamics (MD) simulation before going to the experiment. In this work, the software “MiniMutate” has been developed which can do a single mutation in a protein structure. Mutant coordinate file which is generated after the local and the global minimization with molecular dynamics program NAMD will be returned as the output. This file can be used as an input of MD simulation packages. In comparison to similar software at WHATIF server, MiniMutate can do mutation in a specific chain that user is selected, the important option which is lacking on WHAT IF, and with minimizing mutant structure it can be more precision than the WHAT IF output. In addition, this software can be used to construct missing side chains from PDB file. The software is freely available at: http://bioinf.modares.ac.ir/software/minimutate/.