IJISA Vol. 12, No. 1, Feb. 2020
Cover page and Table of Contents: PDF (size: 213KB)
Warts are noncancerous benign tumors caused by the Human Papilloma Virus (HPV). The success rates of cryotherapy and immunotherapy, two common treatment methods for cutaneous warts, are 44% and 72%, respectively. The treatment methods, therefore, fail to cure a significant percentage of the patients. This study aims to develop a reliable machine learning model to accurately predict the success of immunotherapy and cryotherapy for individual patients based on their demographic and clinical characteristics. We employed support vector machine (SVM) classifier utilizing a dataset of 180 patients who were suffering from various types of warts and received treatment either by immunotherapy or cryotherapy. To balance the minority class, we utilized three different oversampling methods- synthetic minority oversampling technique (SMOTE), borderline-SMOTE, and adaptive synthetic (ADASYN) sampling. F-score along with sequential backward selection (SBS) algorithm were utilized to extract the best set of features. For the immunotherapy treatment method, SVM with radial basis function (RBF) kernel obtained an overall classification accuracy of 94.6% (sensitivity = 96.0%, specificity = 89.5%), and for the cryotherapy treatment method, SVM with polynomial kernel obtained an overall classification accuracy of 95.9% (sensitivity = 94.3%, specificity = 97.4%). The obtained results are competitive and comparable with the congeneric research works available in the literature, especially for the immunotherapy treatment method, we obtained 4.6% higher accuracy compared to the existing works. The developed methodology could potentially assist the dermatologists as a decision support tool by predicting the success of every unique patient before starting the treatment process.[...] Read more.
Approach to the analysis of nonlinear dynamic systems structural identifiability (SI) under uncertainty proposed. This approach has a difference from methods applied to SI estimation of dynamic systems in the parametrical space. Structural identifiability interpreted as of the structural identification possibility a nonlinear system part. We show that the input has S-synchronization property for the solution of the SI task. The identifiability method based on the analysis of structures. The input parameter effect on the possibility of the system SI estimation is studied.[...] Read more.
This article demonstrates the implementation of the proposed algorithm for computer modeling of redundant measurement methods to solve problems to improve the accuracy of measurements of a controlled quantity with a nonlinear and unstable transformation function. Improving accuracy is achieved by processing the results of redundant measurements which are an array of data according to the proposed measurement equations. In addition, the article presents the possibility of determining the time variation of the parameters of the transformation function. A comparative analysis of the results of computer simulation of redundant and direct methods with unstable parameters of the linear and nonlinear sensor transformation functions is carried out. It was proved that, in the case of an increase in deviations of the parameters of the transformation function from the nominal values, the use of redundant methods provides a significantly higher measurement accuracy compared to direct methods. This became possible due to the automatic elimination of the systematic component of the error of the measurement result due to a change in the parameters of the transformation function under the influence of destabilizing factors. It was also found that, in contrast to direct methods, methods of redundant measurements allow working with a nonlinear transformation function without additional linearization or dividing it into linear sections, which also contributes to increased accuracy.
In general, the application of the proposed approach in the modeling system proves its effectiveness and feasibility.
Thus, there is reason to argue about the prospects of redundant measurements in the field of improving accuracy with a nonlinear and unstable transformation function, as well as the possibility of identifying deviations of the parameters of the transformation function from their nominal values.
Digital integer and fractional order integrators and differentiators are very important blocks of digital signal processing. In many situations, integer order integrators and differentiators are not sufficient to model all kind of dynamics. For such systems, fractional order operators give better solution. This paper is based on design of a new family of fractional order integrators and differentiators using various approximation techniques. Here, digital fractional order integrators are designed by direct discretization method using different techniques like continued fraction expansion, Taylor series expansion, and rational Chebyshev approximation on the transfer function of Jain-Gupta-Jain second order integrator. Their response in frequency domain is compared. The frequency response of the proposed integrators with highest efficiency is also compared with the existing ones. It is proved that rational Chebyshev approximation based integrators have highest efficiency among them. The fractional order differentiators are also designed using proposed integrators. It is concluded that proposed family of fractional order operators show remarkable improvement in frequency response compared to all the existing ones over the entire Nyquist frequency range.[...] Read more.
The batch back prorogation algorithm is anew style for weight updating. The drawback of the BBP algorithm is its slow learning rate and easy convergence to the local minimum. The learning rate and momentum factor are the are the most significant parameter for increasing the efficiency of the BBP algorithm. We created the dynamic learning rate and dynamic momentum factor for increasing the efficiency of the algorithm. We used several data set for testing the effects of the dynamic learning rate and dynamic momentum factor that we created in this paper. All the experiments for both algorithms were performed on Matlab 2016 a. The stop training was determined ten power -5. The average accuracy training is 0.9909 and average processing time improved of dynamic algorithm is 430 times faster than the BBP algorithm. From the experimental results, the dynamic algorithm provides superior performance in terms of faster training with highest accuracy training compared to the manual algorithm. The dynamic parameters which created in this paper helped the algorithm to escape the local minimum and eliminate training saturation, thereby reducing training time and the number of epochs. The dynamic algorithm was achieving a superior level of performance compared with existing works (latest studies).[...] Read more.