by Qiancheng Wang and Hongyan Guan
Original Research
In this paper, we propose a new class of orthogonal F- type contractive mappings, and prove one common fixed point theorem in complete orthogonal b- metric spaces. We also provide an example that supports our result.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 77-82. DOI: 10.12691/ajams-11-2-6
Pub. Date: September 08, 2023
299 Views10 Downloads
by Dalia K. A. A. Rizk, Hoda M. Hosny, Michael Gr. Voskoglou, El-Sayed M. El-Horbaty and Abdel-Badeeh M. Salem
Original Research
A range of healthcare and medical sectors can benefit from the intelligent concepts, approaches, techniques, and algorithms provided by artificial intelligence (AI) paradigms. AI could streamline patient flow or treatment strategies and give doctors virtually all the data they require to make wise medical and healthcare decisions. Healthcare is just beginning to undergo a significant change because of AI, starting with the creation of treatment strategies and moving through the augmentation of repetitive tasks through medication management or drug research. It can be used in a wide range of contexts, including data management, drug research, diabetic treatment, and digital consultation. Furthermore, the benefits of AI enable the investigation of enormous datasets by algorithms in situations like those involving inaccessible geographic regions. Most other emerging technologies fall under the general heading of AI. Due to their significance in identifying patients with chronic diseases, their capacity to identify risk scenarios, and their ability to foster the development of novel remedies, these new technologies must be integrated into healthcare. As a result, a set of rules that are too complex and extensive for a human programmer to handle is given into an AI software to detect the similarities. The main objective of this paper is to analyze the major known AI algorithms and to show their usage with healthcare services.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 70-76. DOI: 10.12691/ajams-11-2-5
Pub. Date: August 31, 2023
343 Views2 Downloads
by Navoda Hettige and WMND Basnayake
Original Research
Time series forecasting holds a vital significance across diverse domains; however, accurately predicting the future is challenging due to the inherent complexity and non-linear nature of the data. One promising strategy for tackling non-linear time series data is the utilization of hybrid models, which have the potential to enhance forecasting accuracy. In this research paper, a comparative study is conducted, focusing on different approaches to horizontally partition data and fit Long short-term memory artificial neural network models (LSTM ANN). By using simulated data, this study effectively evaluates the efficacy of these approaches. The results demonstrate that DWT-LSTM, EEMD-LSTM, and CEEMDAN-LSTM techniques outperformed the EMD-LSTM and Threshold-LSTM models.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 63-69. DOI: 10.12691/ajams-11-2-4
Pub. Date: August 22, 2023
871 Views10 Downloads
by K. Prudhvi
In this paper, we obtain fixed point theorem for OWC (Occasionally Weakly Compatible) self-mappings satisfying a generalized contractive type condition in CMS (Cone Metric Space). Our results are generalizing and improving some of the well known comparable results existing in this literature.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 61-62. DOI: 10.12691/ajams-11-2-3
Pub. Date: April 24, 2023
463 Views1 Downloads
by Marcel Julmard Ongoumaka Yandza
Original Research
In this paper, we present a new method to solve some mathematics problems such as integral calculus, derivative calculus and differential equations. The method consists to transform an analytic problem or function to a real number. This real number obtained represents the Function Number. After finding the Function Number solution, it is also possible to transform it to a semi-analytic function which represents the definitive solution of the problem. We qualify the solution as semi-analytic solution because to solve the problem, we make some approximations. So, the semi-analytic function obtained is an approximate analytic solution. This method is simple and concise. It gives strong approximate solutions near to the real solutions.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 50-60. DOI: 10.12691/ajams-11-2-2
Pub. Date: April 10, 2023
925 Views2 Downloads
by Sanjib Ghosh and Muhammad Alamgir Islam
Original Research
Abstract Heart disease is a fatal human disease that rapidly increases globally in developed and underdeveloped countries and causes death. This disease's timely and accurate diagnosis is essential for avoiding patient harm and preserving their lives. This study compared the classifier’s performance in three stages: complete attributes, class balance, and after-feature selection. For class balancing using SMOTE (Synthetic Minority Oversampling Technique) and Elastic Net feature selection algorithm has been used to select suitable features from the available dataset. In this study, justification of performance, the authors have used Logistic Regression (LR), K-nearest neighbor (KNN), Support vector machine (SVM), Random Forest (RF), Adaboost (AB), Artificial neural network (ANN), and Multilayer perceptron (MLP). It has been found that the performance increased ANN and LR after class balance and was unchanged in SVM and MLP. The classification accuracies of the top two classification algorithms, i.e., RF and Adaboost, on full features were 99% and 94%, respectively. After applying feature selection algorithms, the classification accuracy of RF slightly decreases from 99% to 92%. The accuracy of Adaboost decreases from 94% to 83%. However, the performance of classifiers increased after class balance and feature selection, such as KNN, SVM, and MLP. After class balancing and feature selection, we observed that the SVM classifier performs best.
American Journal of Applied Mathematics and Statistics. 2023, 11(2), 35-49. DOI: 10.12691/ajams-11-2-1
Pub. Date: April 05, 2023
1230 Views11 Downloads