Yazar "Dash, Ranjan Kumar" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Fine-tuned support vector regression model for stock predictions
    (Springer London Ltd, 2023) Dash, Ranjan Kumar; Nguyen, Tu N.; Cengiz, Korhan; Sharma, Aditi
    In this paper, a new machine learning (ML) technique is proposed that uses the fine-tuned version of support vector regression for stock forecasting of time series data. Grid search technique is applied over training dataset to select the best kernel function and to optimize its parameters. The optimized parameters are validated through validation dataset. Thus, the tuning of this parameters to their optimized value not only increases model's overall accuracy but also requires less time and memory. Further, this also minimizes the model from being data overfitted. The proposed method is used to analysis different performance parameters of stock market like up-to-daily and up-to-monthly return, cumulative monthly return, its volatility nature and the risk associated with it. Eight different large-sized datasets are chosen from different domain, and stock is predicted for each case by using the proposed method. A comparison is carried out among the proposed method and some similar methods of same interest in terms of computed root mean square error and the mean absolute percentage error. The comparison reveals the proposed method to be more accurate in predicting the stocks for the chosen datasets. Further, the proposed method requires much less time than its counterpart methods.
  • Küçük Resim Yok
    Öğe
    A new and reliable intelligent model for deployment of sensor nodes for IoT applications
    (Pergamon-Elsevier Science Ltd, 2022) Dash, Ranjan Kumar; Cengiz, Korhan; Alshehri, Yasser Ali; Alnazzawi, Noha
    To ensure reliable Internet of Things (IoT) applications, this study provides a new intelligent deployment technique for sensor nodes. The proposed intelligent deployment technique places sensor nodes in appropriate locations to achieve high levels of connectivity and, as a result, boost the WSN's overall reliability. To generate optimal sensor node coordinate positions, a modified version of the Expectation-Maximization method is utilized as a machine learning technique. Following that, each node's neighbours are determined, and links between them are built using the K-Nearest neighbour algorithm. Then, to assess the reliability of WSN, a novel algorithm is proposed. The proposed algorithms are all well-illustrated with appropriate examples. When the algorithms provided in this research are compared to certain existing methods in terms of node positioning accuracy (10%), network connectivity (10%), and estimated dependability values (5%), it is clear that the suggested strategy outperforms them in every way.