Search

To enhance the accuracy of learning models, it becomes imperative to train them on more extensive datasets. Unfortunately, access to such data is often restricted because data providers are hesitant to share their data due to privacy concerns. Hence, it is critical to develop obfuscation techniques that empower data providers to transform their datasets into new ones that ensure the desired level of privacy. In this paper, we present an approach where data providers utilize a neural network based on the autoencoder architecture to safeguard the sensitive components of their data while preserving the utility of the remaining parts. More specifically, within the autoencoder framework and after the encoding process, a classifier is used to extract the private feature from the dataset. This feature is then decorrelated from the other remaining features and subsequently subjected to noise. The proposed method is flexible, allowing data providers to adjust their desired level of privacy by changing the noise level. Additionally, our approach demonstrates superior performance in achieving the desired trade-off between utility and privacy compared to similar methods, all while maintaining a simpler structure. [ABSTRACT FROM AUTHOR]

The present study investigates the interaction between two alkylating agent drugs, cyclophosphamide (CP) and mechlorethamine (MC), with Single-Wall carbon nanotubes (SWCNTs) and Boron Nitride nanotubes (BNNTs). Calculations have been performed by using methods of quantum mechanics and molecular mechanics. The effects of different solvents on the interaction of CP and MC with SWCNTs and BNNTs within the Onsager self-consistent reaction field (SCRF) model, as well as the effects of temperature on the stability of the interactions between the compounds in various solvents have been investigated. Thermodynamic parameters, Frontier Molecular Orbitals (FMOs), and Total Density of States (DOS) of the title compounds have been evaluated by using theoretical calculations. Moreover, the interaction of CP and MC with SWCNTs and BNNTs have been examined through AMBER, OPLS, CHARMM, and MM+ force fields through the molecular mechanic (MM) method. The Monte Carlo simulation of CP and MC structures connected to carbon and boron nitride nanotubes in Water, Methanol, Ethanol, DMSO, and Chloroform solvents showed that Chloroform is the most stable solvent for simulation with the lowest energy, which is directly attributed to dielectric constant. Studies show that the results of Monte Carlo, molecular mechanics, and quantum mechanics are consistent with each other in terms of thermodynamic properties and conformer populations. [ABSTRACT FROM AUTHOR]

Despite the spatial effects of tourist attractions in promoting smart growth principles in tourist cities, it is necessary to pay attention to the spatial synergy between tourist attractions in order to control their destructive spatial effects and realize sustainable development (SD) in tourist cities. In this research, based on smart growth measures, the necessity of spatial synergy between tourist attractions in sustainable neighborhood development is explained using innovative spatial statistical analysis methods at the scale of 469 neighborhood units of Mashhad city. The findings of the research confirm significant synergistic effect of tourist attractions on urban smart growth indicators and composite indicator of smart growth of the surrounding neighborhood units. On the other hand, lack of spatial synergy between Mashhad’s main tourist attraction in the city center and other tourist attractions leads to unbalanced residential and activity development and unbalanced distribution of tourism services. This issue prevents integrated realization of smart growth and SD of all neighborhood units in Mashhad. [ABSTRACT FROM AUTHOR]