13 March 2025 in IEEE Access
This article covers a second-order sliding mode control-based scheme for the closed loop control of DC-DC buck converters. The proposed control technique adjusts online the sliding surface of the second-order sliding mode controller to enhance the dynamic performance of the closed loop system. The sliding surface adjustment is achieved by a fuzzy logic inference system based on sliding variables. While maintaining its simplicity concerning design and implementation, the controller makes sure the system achieves the design requirements in terms of improved dynamic performance, stability, and robustness. Theoretical analysis confirms the global finite-time error convergence of the buck converter system. The performance of this novel control approach is compared with that of the conventional second-order sliding mode controller with a pre-defined sliding surface using SIMULINK based simulations for a buck converter model. From the analysis of the simulation results, it is concluded that the proposed controller provides a remarkable improvement in the dynamic performance of the buck converter control system compared with the conventional second-order sliding mode controller with a pre-defined sliding surface.
1 September 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
For agricultural productivity and food security to be guaranteed, early detection and treatment of illnesses are crucial. Machine learning (ML) and deep learning (DL) approaches can be used to precisely and successfully identify plant leaf diseases. A heterogeneous dataset comprising photos of both healthy and diseased leaves such as bacterial blights, fungal infections, and viral manifestations provides the foundation for the model building and training. Accuracy, precision, recall, and F1-score are the measures used to assess the model's performance. ML techniques are helpful in the identification and extraction of pertinent information from plant leaf pictures, whereas DL techniques in general, and convolutional neural networks (CNN), in particular, are remarkable at learning complex hierarchical representations. Therefore, DL architectures like CNN are utilized in conjunction with ML approaches like support vector machines (SVM), decision trees, and random forests to extract complicated patterns and attributes from leaf pictures. This research provides an extensive analysis of the performance and application of DL and ML approaches recently applied to the early identification of leaf diseases in different crops.
1 September 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
This research work designs a variant of second-order sliding mode control scheme, making use of varying sliding surface inferred using a fuzzy inference system. The varying sliding surface is an effective strategy to improve controller performance. A surface with a relative degree of two is first built by accounting for the uncertainties and perturbances of the system. Thereafter, in order to enhance the dynamics of the system being controlled, a varying sliding surface based on a straightforward double input-single output fuzzy logic inference architecture is proposed. The controller ensures system's reaching conditions, and also the stability and robustness. The designed control scheme is studied in comparison with a sliding mode controller of second order having a constant surface of sliding using SIMULINK based simulation for a nonlinear system. The comparison shows that the proposed strategy exhibits an improved dynamic performance than the conventional sliding mode control of second order having a constant surface of sliding.
1 September 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Pandemics, such as coronavirus disease COVID-19 are known to cause massive damage to the world's economic growth and their impacts are serious and influence across every aspect of social structure. The most inevitable factor in responding to the disaster of pandemics is the right management in terms of allocating a limited vaccine supply. The focus of this research work is to utilize a fuzzy logic inference system in the allocation of vaccine doses to the regional authorities by a central authority. The objective is obtained by designing a system based on fuzzy logic that considers the spread rate as the input to infer the vaccination rate of the local population. This system makes it possible for sufficient doses of vaccines to be allotted to the prioritized regions where the severity of the spread rate is a concern and vaccines are not held up in regions where the severity of the spread rate is lesser. The designed system is verified using MATLAB software, which shows that this method can ensure an effective and efficient allocation of vaccination in the local regions and aid the fight against the disastrous spread of the disease.
1 October 2024 in International Journal of Electrical and Computer Engineering (IJECE)
This paper deals with a novel decision-making scheme for inferring the allocation of vaccines to the provincial health care authorities by the central health care authority of a country in pandemic scenarios. This novel scheme utilizes a fuzzy logic-based inference scheme that utilizes the spread rate and population of a province as inputs to infer the vaccination rate. The proposed scheme is evaluated on the coronavirus disease (COVID-19) data from six southern states of India during the first week of October 2020, collected from the database maintained by the Government of India. The findings demonstrate that the suggested plan, which takes population and spread rate into account, makes sure that enough vaccination doses are distributed to the provinces with a larger spread rate with a higher priority, and that immunizations are not delayed in provinces with controlled spread rates. Also, in due course, all territories will appropriately distribute enough vaccine supply to control the spread. Therefore, this plan strengthens the efforts to control the pandemic outbreaks by ensuring the proper and balanced delivery of vaccines in a timely, efficient, and objective manner.