در مؤسسات مالی، بانک‌ها و مؤسسات کارآفرینی که تسهیلات اشتغال به مشتریان خود پرداخت می‌کنند، مسائل متعددی را قبل از اعطای تسهیلات مورد بررسی قرار می‌دهند. در این میان، مهم‌ترین و پراهمیت‌ترین موضوع برای یک سیستم مالی، ارزیابی توان مشتریان در بازپرداخت تسهیلات می‌باشد. انتخاب درست متقاضیان تسهیلات، با استفاده از روش‌های سنتی انجام می‌شود که این روش‌ها مستعد خطا می‌باشند. امروزه با توسعه یادگیری ماشین، می‌توان انتخاب درست متقاضیان را با دقت بیشتری انجام داد. این مطالعه با هدف رفع کاستی‌های مطالعات پیشین، یک مدل تصمیم‌گیری توسعه‌یافته با در نظر گرفتن الگوهایی از مشتریان موفق و غیر موفق در 4 حوزه مختلف پیش‌بینی وضعیت نظارت، وضعیت تسهیلات، مدت‌زمان فعالیت و تعداد اشتغال ایجادشده، ارائه شده است. در این مطالعه، یک پایگاه داده جامع بر پایه استانداردهای موجود جمع‌آوری‌شده و یک مدل شبکه عصبی عمیق برای استخراج ویژگی‌ها از داده‌های ورودی، طراحی شده است. با توسعه روش پیشنهادی و راه‌یابی مطالعه حاضر به حوزه‌های کاربردی و عملی، می‌توان متقاضیان مطلوب تسهیلات را به‌صورت خودکار و با صحت بیشتری ارزیابی و انتخاب نمود. تفاصيل المقالة

Landslide susceptibility analysis is beneficial information for a wide range of applications. We aimed to explore and compare three machine learning (ML) techniques, namely the random forests (RF), support vector machine (SVM) and multiple layer neural networks (MLP) for landslide susceptibility assessment in the Ahar county of Iran. To achieve this goal, 10 landslide occurrence-related influencing factors were pondered. A sum of 266 locations with landslide potentiality was recognized in the context of the study, and the Pearson correlation technique utilized in order to select the influencing factors in landslide models. The association between landslides and conditioning factors was also evaluated using a probability certainty factor (PCF) model. Three landslide models (SVM, RF, and MLP) were structured by the training dataset. Lastly, the receiver operating characteristic (ROC) and statistical procedures were employed to validate and contrast the predictive capability of the obtained three models. The findings of the study in terms of the Pearson correlation technique method for the importance ranking of conditioning factors in the context area uncovered that slope, aspect, normalized difference vegetation index (NDVI), and elevation have the highest impact on the occurrence of the landslide. All in all, the MLP model had the utmost rate of prediction capability (85.22 %), after which, the SVM model (78.26 %) and the RF model (75.22 %) demonstrated the second and third rates. Besides, the study revealed that benefiting the optimal machine with the proper selection of the techniques could facilitate landslide susceptibility modeling. تفاصيل المقالة

Signature identification plays an important role in many areas such as banking, administrative and judicial systems. For this purpose, in this paper, an automatic intelligent framework is developed by combining a deep pre-trained network with a recurrent neural network. The results of the proposed model were evaluated on several valid datasets and collected datasets. Since there was no suitable Persian signature dataset, we collected a Persian signature dataset based on US ASTM guidelines and standards, which can be very effective and profound for deep approaches. Due to the very promising results of the proposed model in comparison with recent studies and conventional methods, to evaluate the resistance of the proposed model to different noises, we added Gaussian Noise, Salt and Pepper Noise, Speckle Noise, and Local var Noise in different SNRs to the raw data. The results show that the proposed model can still be resistant to a wide range of SNRs; So at 15 dB, the accuracy of the proposed method is still above 90%. تفاصيل المقالة