In this paper, a new approach for increasing the approximation accuracy with the use of computational intelligence tools is described. It is based on the compatible use of the neural-like structure of the Successive Geometric Transformations Model and the inputs polynomial extension. To implement such an extension, second degree Wiener polynomial is used. This combination improves the method accuracy for solving various tasks, such as classification and regression, including short-term and long-term prediction, dynamic pricing, as well as image recognition and image scaling, e-commerce. Due to the use of SGTM neural-like structure, the high speed of the system is maintained in both training and using modes. The simulation of the described approach is carried out on real data, the time results of the neural-like structure work and the accuracy results (MAPE, RMSE, R) are given. A comparison of the operation of the method with existing ones, such as Support vector regression, Classic linear SGTM neural-like structure, Linear regression (using Stochastic Gradient Descent), Random Forest, Multilayer Perceptron, AdaBoost are made. The advantages of the developed approach, in particular with regard to the highest accuracy among existing ones were experimentally established.
9 September 2022 in Computers in Biology and Medicine
This study discusses using Japanese candlestick (JC) patterns to predict future price movements in financial markets. The history of candlestick trading dates back to the 17th century and involves the analysis of patterns formed during JC trading. Candlestick patterns are practical tools for the technical analysis of traders in financial markets. They may serve as indicators of traders’ documents of a potential change in market sentiment and trend direction. This study aimed to predict the following candle-trend-based JC charts using convolutional neural networks (CNNs). In order to enhance the accuracy of predicting the directional movement of subsequent financial candlesticks, a rich dataset has been constructed by following a structured three-step process, and a CNN model has been trained. Initially, the dataset was analyzed, and sub-charts were generated using a sliding window technique. Subsequently, the Ta-lib library was used to identify whether predefined patterns were present within the windows. The third phase involved the classification of each window’s directional tendency, which was substantiated by employing various technical indicators to validate the direction of the trend. Following the data preparation and analysis phases, a CNN model was developed to extract features from sub-charts and facilitate precise predictions effectively. The experimental results of this approach demonstrated a remarkable predictive accuracy of up to 99.3%. Implementing cross-validation techniques is essential to verify the reliability and overall performance of the model. To achieve this goal, the dataset was divided into several small subsets. Subsequently, the model was trained and evaluated multiple times using different combinations of these subsets. This method allows for a more accurate assessment of the model’s predictive capabilities by examining its performance on unseen data.
10 June 2013 in Electronic Notes in Discrete Mathematics
An electrical plan drawing–sometimes called a wiring diagram or electrical drawing–consists of lines and symbols. Electrical plan drawings are prepared on 2D architectural floor plans using Computer-Aided Design and/or Drafting (CAD) programs. The placement/drawing of electrical power symbols–such as sockets, lights, and switches–is the first step of an electrical plan drawing. For this purpose, a smart system has been developed in this study to automatically draw/place electrical power symbols in appropriate locations. The system is based on the detection and classification/recognition of furnishing (decorative) symbols in the floor plans. We have created a furnishing symbol dataset drawing on dozens of architectural plan drawings that contain symbols of the most commonly used tools in floor plans, such as furniture, appliances, plumbing, doors, and windows. We used a Deep Convolutional Neural Network (D-CNN) with transfer learning–Inception-v3 model– to classify furnishing symbols. We tested the model on 20 real floor plans and achieved a very satisfactory accuracy of 97.05% in furnishing symbol classification. The symbol drawing step, which is the first step of drawing the electrical plan, was automated using the work developed, thus achieving the aim of saving time and labour. Experimental studies show the effectiveness of the proposed automated system.
18 September 2019 in Turkish Journal of Electrical Engineering and Computer Sciences