30 April 2024 in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
The current research endeavors to evaluate the efficacy of regression-based machine learning algorithms through an assessment of their performance using diverse metrics. The focus of our study involves the implementation of the breast cancer Wisconsin (Diagnostic) dataset, employing both the random forest and gradient-boosting regression algorithms. In our comprehensive performance analysis, we utilized key metrics such as Mean Squared Error (MSE), R-squared, Mean Absolute Error (MAE), and Coefficient of Determination (COD), supplemented by additional metrics. The evaluation aimed to gauge the algorithms' accuracy and predictive capabilities. Notably, for continuous target variables, the gradient-boosting regression model emerged as particularly noteworthy in terms of performance when compared to other models. The gradient-boosting regression model exhibited remarkable results, highlighting its superiority in handling the breast cancer dataset. The model achieved an impressively low MSE value of 0.05, indicating minimal prediction errors. Furthermore, the R-squared value of 0.89 highlighted the model's ability to explain the variance in the data, affirming its robust predictive power. The Mean Absolute Error (MAE) of 0.14 reinforced the model's accuracy in predicting continuous outcomes. Beyond these core metrics, the study incorporated additional measures to provide a comprehensive understanding of the algorithms' performance. The findings underscore the potential of gradient-boosting regression in enhancing predictive accuracy for datasets with continuous target variables, particularly evident in the context of breast cancer diagnosis. This research contributes valuable insights to the ongoing exploration of machine learning algorithms, providing a basis for informed decision-making in medical and predictive analytics domains.
1 January 2024 in The International Arab Journal of Information Technology
30 August 2024 in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
Accurate forecasting of wind speed is crucial for the efficient operation of wind energy systems. As a time-series concern, wind forecasting may help determine how much electricity a proposed wind farm might produce annually. The majority of forecasting techniques perform differently depending on seasonal and trends variation. For this reason, time series data frequently have seasonal and nonlinear trend components eliminated in order to simplify wind forecasting approach. The application function used to remove the seasonality and trend determines accuracy. The proposed method begins by identifying and extracting underlying trends from historical wind speed data, segmenting the time series into distinct trend-based components. This paper proposes a hybrid method for predicting time series. A method for clustering data has been designed that identifies clusters of time series data with similar trend components. Statistical procedures, such as generalized autoregressive and autoregressive integrated moving average scoring approaches, are used to each individual cluster after the appropriate clusters of related trend components have been identified. Ultimately, the components that are made are combined. The datasets collected from the NREL site. The experiment demonstrates that when compared to current statistical approaches, the cluster-based forecasting approach performs better. This research makes contribution towards the field of renewable energy forecasting by providing a robust and scalable method for wind speed prediction, which can be integrated into existing energy management systems for improving the efficiency and stability of wind energy generation. The research paper examines the trend features of time series data of wind employing the suggested hybrid technique on wind forecasting. Performance calculated in terms of RMSE and MAE shows that the proposed technique succeeds as compared to other state of the art techniques.
30 December 2023 in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
With the current increase in wireless technology, spectrum is becoming scarce. By equitably allocating frequency bands to unlicensed and licensed clients, the cognitive radio network (CRN) reduces issue of growing inadequate utilization and spectrum scarcity. Secondary users (SUs) and unlicensed users are given the opportunity to impulsively exploit the licensed users allotted free spectrum under CRN. The rendezvous procedure, in which SUs gather on widely used channels and create trustworthy linkages for efficient communication, is the key step in the creation of CRN. Considering the dynamic context of CRNs, rendezvous methods that depend with the presumption of common control channel (CCC) across SUs are less effective and impractical. Thus, the rendezvous among SUs is often accomplished via the channel hopping (CH) approach without CCC assistance, also known as blind rendezvous. The complete asynchronous symmetric rendezvous (CASR) technique presented in this paper ensures that SUs will rendezvous in a finite amount of time without the need for time synchronization. The CASR method uses the SU's MAC address as a means of generating a unique identifier (ID) and creating a CH sequence by dynamically adjusting the ID in accordance with the number of accessible channels for communicating. The CASR method was successful in achieving rendezvous assurance while maintaining an acceptable time to rendezvous by utilizing the distinct ID of each SU. The effectiveness of the CASR technique is theoretically evaluated and empirically tested through several simulation studies. According to simulation studies, CASR technique outperforms existing rendezvous techniques when considering of average time-to-rendezvous.