-
حرية الوصول المقاله
1 - Designing a Model for Predicting Corporate Bankruptcy Using Ensemble Learning Techniques
Hossein Eghbali Alimohamad AhmadvandThe bankruptcy of corporations causes huge losses for investors, managers, creditors, employees, suppliers, and customers. If someone understands the reason for the corporate's bankruptcy, then he can save the corporate from certain death with the necessary planning. Th أکثرThe bankruptcy of corporations causes huge losses for investors, managers, creditors, employees, suppliers, and customers. If someone understands the reason for the corporate's bankruptcy, then he can save the corporate from certain death with the necessary planning. Therefore, bankruptcy forecasting is the most important prerequisite for bankruptcy prevention. Due to this issue, the main aim of this article is the prediction of the economic bankrupt-cy of corporations in the Tehran Stock Exchange using group machine learn-ing algorithms. Financial ratios have been used as independent variables and healthy and bankrupt corporations as research dependent variables. The statistical population of the study is the information of financial statements of corporations on the Tehran Stock Exchange from the years 2004 to 2021. In this study, sampling is not used and corporations include two groups healthy and bankrupt. The bankrupt and non-bankrupt groups are selected based on the threshold of the Springate model. The research findings indicate that the accuracy of predicting the bankruptcy of corporations in the group learning model by stacking method is higher than other used models where the AUC and Accuracy Ratio were 0.9276 and 0.8247, respectively. تفاصيل المقالة -
حرية الوصول المقاله
2 - Ensemble Learning Improvement through Reinforcement Learning Idea
Mohammad Savargiv Behrooz Masoumi Mohammadreza KeyvanporEnsemble learning is one of the learning methods to create a strong classifier through the integration of basic classifiers that includes the benefits of all of them. Meanwhile, weighting classifiers in the ensemble learning approach is a major challenge. This challenge أکثرEnsemble learning is one of the learning methods to create a strong classifier through the integration of basic classifiers that includes the benefits of all of them. Meanwhile, weighting classifiers in the ensemble learning approach is a major challenge. This challenge arises from the fact that in ensemble learning all constructor classifiers are considered to be at the same level of distinguishing ability. While in different problem situations and especially in dynamic environments, the performance of base learners is affected by the problem space and data behavior. The solutions that have been presented in the subject literature assumed that problem space condition is permanent and static. While for each entry in real, the situation has changed and a completely dynamic environment is created. In this paper, a method based on the reinforcement learning idea is proposed to modify the weight of the base learners in the ensemble according to problem space dynamically. The proposed method is based on receiving feedback from the environment and therefore can adapt to the problem space. In the proposed method, learning automata is used to receive feedback from the environment and perform appropriate actions. Sentiment analysis has been selected as a case study to evaluate the proposed method. The diversity of data behavior in sentiment analysis is very high and it creates an environment with dynamic data behavior. The results of the evaluation on six different datasets and the ranking of different values of learning automata parameters reveal a significant difference between the efficiency of the proposed method and the ensemble learning literature. تفاصيل المقالة -
حرية الوصول المقاله
3 - A Semi-Supervised Human Action Learning
Mohsen Tavana Mohammad Mohammadi Hamid ParvinExploiting multimodal information like acceleration and heart rate is a promising method to achieve human action recognition. A semi-supervised action recognition approach AUCC (Action Understanding with Combinational Classifier) using the diversity of base classifiers أکثرExploiting multimodal information like acceleration and heart rate is a promising method to achieve human action recognition. A semi-supervised action recognition approach AUCC (Action Understanding with Combinational Classifier) using the diversity of base classifiers to create a high-quality ensemble for multimodal human action recognition is proposed in this paper. Furthermore, both labeled and unlabeled data are applied to obtain the diversity measure from multimodal human action recognition. Any classifiers can be applied by AUCC as its base classifier to create the human action recognition model, and the diversity of classifier ensemble is embedded in the error function of the model. The model’s error is decayed and back-propagated to the basic classifiers through each iteration. The basic classifiers’ weights are acquired during creation of the ensemble to guarantee the appropriate total accuracy of the model. Considerable experiments have been done during creation of the ensemble. Extensive experiments show the effectiveness of the offered method and suggest its superiority of exploiting multimodal signals. تفاصيل المقالة -
حرية الوصول المقاله
4 - Combining Classifier Guided by Semi-Supervision
Mohammad Mohammadi Hamid Parvin Eshagh Faraji Sajad ParvinThe article suggests an algorithm for regular classifier ensemble methodology. The proposed methodology is based on possibilistic aggregation to classify samples. The argued method optimizes an objective function that combines environment recognition, multi-criteria agg أکثرThe article suggests an algorithm for regular classifier ensemble methodology. The proposed methodology is based on possibilistic aggregation to classify samples. The argued method optimizes an objective function that combines environment recognition, multi-criteria aggregation term and a learning term. The optimization aims at learning backgrounds as solid clusters in subspaces of the high-dimensional feature-space via an unsupervised learning including an attribute discrimination component. The unsupervised clustering component assigns degree of typicality to each data pattern in order to identify and reduce the effect of noisy or outlaid data patterns. Then, the suggested technique obtains the best combination parameters for each background. The experimentations on artificial datasets and standard SONAR dataset demonstrate that our classifier ensemble does better than individual classifiers in the ensemble. تفاصيل المقالة -
حرية الوصول المقاله
5 - Two-level Ensemble Deep Learning for Traffic Management using Multiple Vehicle Detection in UAV Images
Zeinab Ghasemi Darehnaei Seyed Mohammad Jalal Rastegar Fatemi Seyed Mostafa Mirhassani Majid FouladianEnvironmental monitoring via vehicle detecting using unmanned aerial vehicle (UAV) images is a challenging task, due to small-size, low-resolution, and large-scale variation of the objects. In this paper, a two-level ensemble deep learning (named 2EDL) based on Faster R أکثرEnvironmental monitoring via vehicle detecting using unmanned aerial vehicle (UAV) images is a challenging task, due to small-size, low-resolution, and large-scale variation of the objects. In this paper, a two-level ensemble deep learning (named 2EDL) based on Faster R-CNN (regional-based convolutional neural network) is introduced for multiple vehicle detection in UAV images. We use three CNN models (VGG16, ResNet50, and GoogLeNet) that have already pre-trained on huge auxiliary data as feature extraction tools, combined with five learning models (KNN, SVM, MLP, C4.5 Decision Tree, and Naïve Bayes), resulting 15 different base learners in two levels. The final class is obtained via a majority vote rule ensemble of these 15 models into five vehicle classes (car, van, truck, bus, trailer) or “no-vehicle”. Simulation results on the AU-AIR dataset of UAV images show the superiority of the proposed 2EDL technique against existing methods, in terms of the total accuracy, and FPR-FNR trade-off. تفاصيل المقالة -
حرية الوصول المقاله
6 - توسعه یک رویکرد جدید یادگیری جمعی برای انتخاب پورتفوی سهام با استفاده از ماشین بردار پشتیبان چند کلاسه و الگوریتم ژنتیک
نسرین باقری مزرعه امیر دانشور مهدی معدنچی زاجامروزه در بازارهای مالی حجم و سرعت معاملات افزایش چشمگیری یافتهاست و دچار تغییر و تحولات گستردهای شدهاست. تعیین استراتژی مناسب برای خرید و فروش در بورس اوراق بهادار وقتی با روندهای افزایشی وکاهشی یا نوسانی مواجه هستند بسیار مهم میباشد .لذا برای انتخاب یک استراتژی م أکثرامروزه در بازارهای مالی حجم و سرعت معاملات افزایش چشمگیری یافتهاست و دچار تغییر و تحولات گستردهای شدهاست. تعیین استراتژی مناسب برای خرید و فروش در بورس اوراق بهادار وقتی با روندهای افزایشی وکاهشی یا نوسانی مواجه هستند بسیار مهم میباشد .لذا برای انتخاب یک استراتژی مناسب، استفاده از مدلهای پیچیده فراابتکاری استفاده میشود. در این تحقیق تلاش می-شـود تا با توسعه روش جدید انتخاب و بهینهسازی پرتفوی سهام مبتنی بر الگوریتم یادگیری جمعی و ژنتیک به منظور انتخاب بهترین استراتژی معاملاتی برای کسب بازدهی بیشتر و ریسک کمتر استفاده کرد. برای پیش بینی بازده و دریافت سیگنال خرید از ترکیب الگوریتم ماشین بردار پشتیبان شش کلاسه(SVM) و برای بهینهسازی قواعد معاملاتی از الگوریتم پویای ژنتیک استفاده شدهاست. برای بهبود دقت طبقهبندی بازده در این تحقیق از روشهای یادگیری جمعی شامل Bagging، یکی از الگوریتمهای مبتنی بر Ensemble Learning استفاده شده است .دادههای مربوط به هر سهم و متغیرهای بنیادی، در یک بازه زمانی روزانه بین سالهای 1390 تا 1399 به عنوان دادههای آموزش و آزمون استفاده میشود. نتایج بدست آمده درمقایسه با روشهای سنتی نتایج امیدوارکنندهای داشتهاست. تفاصيل المقالة