حسین عباسی مهر

The Stack Overflow website is one of the most popular communities used by millions of programmers. If we consider a question and its corresponding answers as a knowledge unit on the Stack Overflow website, then there are different semantic relationships between two knowledge units, which include duplicate, direct, and indirect relationships with the proposed question. Recognizing different categories of semantic relationship between knowledge units in Stack Overflow can significantly improve the effectiveness and efficiency of information search. In this study, a hybrid approach based on deep learning methods and traditional similarity criteria is presented to detect the relationship between questions. In particular, two deep network architectures are presented, the first architecture consists of a long short-term memory network as well as a cosine similarity calculation layer. The second architecture is an extension of the first architecture by adding an attention mechanism. The proposed approach was evaluated on a dataset of Java programming language contining 40000 questions. The obtained results show that in terms of F1, Recall and Precision, the proposed model performs better than the existing models. Specifically, the model proposed in this article has a 17.3% improvement in terms of F1 measure compared to the best current model. Also, the results of the experiments show that using the pre-trained word embedding model significantly improves the performance of the presented models.

In a business environment where there is fierce competition between companies, accurate demand forecasting is vital. If we collect customer demand data at discrete points in time, we obtain a demand time series. As a result, the demand forecasting problem can be formulated as a time series forecasting task. In the context of time series forecasting, deep learning methods have demonstrated good accuracy in predicting complex time series. However, the excellent performance of these methods is dependent on the amount of data available. For this purpose, in this study, we propose to use time series augmentation techniques to improve the performance of deep learning methods. In this study, three new methods have been used to test the effectiveness of the proposed approach, which are: 1) Long short-term memory, 2) Convolutional network 3) Multihead self-attention mechanism. This study also uses a multi-step forecasting approach that makes it possible to predict several future points in a forecasting operation. The proposed method is applied to the actual demand data of a furniture company. The experimental results show that the proposed approach improves the forecasting accuracy of the methods used in most different prediction scenarios