List of Articles یادگیری عمیق

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - Comparing A Hybridization of Fuzzy Inference System and Particle Swarm Optimization Algorithm with Deep Learning to Predict Stock Prices
  Majid Abdolrazzagh-Nezhad mahdi kherad
  20.1001.1.27170411.1398.11.41.5.0
  Predicting stock prices by data analysts have created a great business opportunity for a wide range of investors in the stock markets. But the fact is difficulte, because there are many affective economic factors in the stock markets that they are too dynamic and compl More

  Predicting stock prices by data analysts have created a great business opportunity for a wide range of investors in the stock markets. But the fact is difficulte, because there are many affective economic factors in the stock markets that they are too dynamic and complex. In this paper, two models are designed and implemented to identify the complex relationship between 10 economic factors on the stock prices of companies operating in the Tehran stock market. First, a Mamdani Fuzzy Inference System (MFIS) is designed that the fuzzy rules set of its inference engine is found by the Particle Swarm Optimization Algorithm (PSO). Then a Deep Learning model consisting of 26 neurons is designed wiht 5 hidden layers. The designed models are implemented to predict the stock prices of nine companies operating on the Tehran Stock Exchange. The experimental results show that the designed deep learning model can obtain better results than the hybridization of MFIS-PSO, the neural network and SVM, although the interperative ability of the obtained patterns, more consistent behavior with much less variance, as well as higher convergence speed than other models can be mentioned as significant competitive advantages of the MFIS-PSO model Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - An efficient Two Pathways Deep Architecture for Soccer Goal Recognition towards Soccer Highlight Summarization
  Amirhosein Zangane Mehdi Jampour Kamran Layeghi
  20.1001.1.27170414.1400.13.49.5.5
  In this paper, an automated method has been presented using a dual-path deep learning architecture model for the problem of soccer video analysis and it emphasizes the gate recognition as one of the most important elements of the goal event that is the most important so More

  In this paper, an automated method has been presented using a dual-path deep learning architecture model for the problem of soccer video analysis and it emphasizes the gate recognition as one of the most important elements of the goal event that is the most important soccer game event. The proposed architecture is considered as an extended form of the VGG 13-layer model in which a dual-path architectural model has been defined. For recognizing the gate in the first path using the proposed architectural model, the model is trained by the training dataset. But in the second path, the training dataset is first examined by a screening system and the best images containing features different from the features of the first path are selected. In another word, features of a network similar to the first path, but after passing through the screening system are generated in the second path. Afterwards, the feature vectors generated in two paths are combined to create a global feature vector, thus covering different spaces of the gate recognition problem. Different evaluations have been performed on the presented method. The evaluation results represent the improved accuracy of gate recognition using the proposed dual-path architectural model in comparison to the basic model. A comparison of proposed method with other existing outcomes also represents the improved accuracy of the proposed method in comparison to the published results. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - A Novel Multi-Step Ahead Demand Forecasting Model Based on Deep Learning Techniques and Time Series Augmentation
  Hossein Abbasimehr Reza Paki
  20.1001.1.27170411.1401.14.53.1.1
  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 formula More

  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 Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  4 - Synthesizing an image dataset for text detection and recognition in images
  Fatemeh Alimoradi Farzaneh Rahmani Leila Rabiei Mohammad Khansari Mojtaba Mazoochi
  20.1001.1.27170411.1401.14.53.5.5
  Text detection in images is one of the most important sources for image recognition. Although many researches have been conducted on text detection and recognition and end-to-end models (models that provide detection and recognition in a single model) based on deep lear More

  Text detection in images is one of the most important sources for image recognition. Although many researches have been conducted on text detection and recognition and end-to-end models (models that provide detection and recognition in a single model) based on deep learning for languages such as English and Chinese, the main obstacle for developing such models for Persian language is the lack of a large training data set. In this paper, we design and build required tools for synthesizing a data set of scene text images with parameters such as color, size, font, and text rotation for Persian. These tools are used to generate a large still varied data set for training deep learning models. Due to considerations in synthesizing tools and resulted variety of texts, models do not depend on synthesis parameters and can be generalized. 7603 scene text images and 39660 cropped word images are synthesized as sample data set. The advantage of our method over real images is to synthesize any arbitrary number of images, without the need for manual annotations. As far as we know, this is the first open-source and large data set of scene text images for Persian language. Manuscript profile