The recent developments in electric vehicle (EV) necessities the requirement of a human intervention free charging system for safe and reliable operation. Wireless power transfer (WPT) technology shows promising options to automate the charging process with user convenience. However, the operation of the WPT system is designed to operate at a high-frequency (HF) range, which requires proper control and modulation technique to improve the performance of power electronic modules. This paper proposes a dead-time (DT) integrated Pulse Density Modulation (PDM) technique to provide better control with minimal voltage and current ripples at the switches. The proposed technique is investigated using a LCC-LCL compensated WPT system, which predominantly affects the high-frequency voltage and current ripples. The performance analysis is studied at different density conditions to explore the impact of the integrated PDM approach. Moreover, the PDM technique gives better control over the power transfer at different levels of load requirement. The simulation and experimental analysis was performed for a 3.7 kW WPT prototype test system under different modes of operation of the high-frequency power converters. Both the simulated and experimental results demonstrate that the proposed PDM technique effectively enhances the efficiency of the HF inverter while significantly reducing output current ripples, power dissipation and improving the overall WPT system efficiency to 92%, and leading to a reduction in the power loss in the range of 10% to 20%. This leads to improved overall system control and performance.

With the rampant growth of the global population and the increasing need for agricultural products, farmers confront a critical hurdle of ensuring an adequate supply of water resources for irrigation to meet these escalating demands. Amid limited water resources, farmers must embrace innovative solutions and efficient water management practices in the era of Agriculture 4.0 turning this concept into a tangible reality to meet the growing demand for efficient farming practices. By integrating Artificial Intelligence (AI) and the Internet of Things (IoT) to gather and analyze agricultural data, we now have the capability to make more accurate and informed decisions in agriculture. In this, an innovative and adaptable irrigation system is introduced which prioritizes efficiency and cost-effectiveness by minimizing resource consumption. This strategy leverages the capabilities of Machine Learning (ML) algorithms to elevate the level of agricultural intelligence. By employing a suite of sensors, including those for soil moisture, temperature, and rainfall, within an environment conducive to prolonged plant growth, the collected data to construct SVM models findings indicate that SVM outperforms other models (LR, NN, NB) with an impressive recognition rate of 98.5% and a minimal root mean square error (RMSE) of 0.10. Through this system, crop irrigation is achieved with a high level of precision, entirely automated, and without the need for human intervention. As a result, this technology leads to a substantial reduction in water consumption, up to 50%.

This paper analyzes Step Density Modulation (SDM) technique for high-frequency inverters in Wireless Power Transfer(WPT) systems for Electric Vehicle (EV) charging. While Pulse Density Modulation (PDM) is commonly used to control high-frequency inverters, it faces limitations in managing current ripple, leading to electromagnetic interference (EMI), reduced power transfer efficiency, and system performance degradation. Step Density Modulation is proposed as an advanced alternative to PDM, offering dynamic pulse density adjustments in discrete stages to align with inverter switching characteristics. This approach minimizes the effects of dead time, significantly reducing current ripple and harmonic distortion, thereby enhancing waveform quality and system efficiency. A comprehensive mathematical model compares current ripple magnitude, harmonic spectrum, and inverter delay time for both modulation techniques. MATLAB simulations, validated through hardware prototype implementation on a 5 kW WPT EV charger, demonstrate that SDM reduces current ripple by up to 30% compared to PDM. The hardware prototype confirms smoother inverter output, improved power stability, and increased efficiency, establishing SDM as a reliable and practical solution for enhancing WPT systems in EV charging applications.

The second most common cause of cancer today is a tumour. To detect tumours like brain tumour, the medical field needs a quick, automated, effective, and reliable technique. A crucial part of treatment is detection. Doctors keep a patient out of danger if accurate tumour detection is possible. This application makes use of several image processing methods. Using this application, doctors are able to properly treat a large number of tumour patients and save their lives. Simply put, a tumour is an accumulation of uncontrolledly expanding cells. The development of brain tumour cells causes brain failure because they eventually eat up all the nutrients meant for healthy cells and tissues. To determine the location and size of the patient's brain tumour, doctors manually review the patient's MR images of the brain. This is time-consuming and results in inaccurate tumour detection. A tumour is an uncontrollably expanding mass of tissue. A Deep Learning architecture that combines CNN (Convolution Neural Network), also referred to as NN (Neural Network), and VGG can be used to identify brain tumours. Transfer learning. Its main strength is the model's ability to predict whether a tumor is present in an image. Returning is yes if the cancer is present and no if it is not.

The cascaded H-bridge (CHB) inverter offers a significant advantage in its straightforward modular design. In a recent study, a unified multilevel inverter incorporating a unique H-bridge component was proposed. This innovative topology has been further refined to include switching devices and DC-link voltage inputs, enabling the generation of a multitude of voltage steps. This advancement is specifically aimed at enhancing control over both active and reactive power for individual DC voltage sources within a photovoltaic module, ultimately improving power quality and system reliability. The study also presents an original control strategy and proportional pulse width modulation techniques tailored for CHB multilevel inverters in grid-connected systems, where each H-bridge module can deliver variable power levels.

Every economy depends on agriculture, and research in this area is primarily focused on boosting food supply and quality while minimizing costs and maximizing profit. Numerous factors can have an impact on tomato pricing, which serve as a crucial indicator of market trends for vegetables. Making educated decisions could be facilitated by predicting tomato average prices. To forecast the typical prices of tomatoes, we used the Support Vector Machine (SVM) model together with polynomial feature modification in this study. For our projections, we used the ‘Minimum’ and ‘Maximum’ pricing attributes. To guarantee consistency and improved performance, the dataset was standardized. With crossvalidation, we used a Grid Search technique to refine the parameters of our SVM model. The Mean Squared Error (MSE) and R2 score metrics were used to assess the model's performance. Our findings were shown graphically by scatter plots that contrasted real and forecasted prices and a histogram that showed the prediction errors. The SVM model has the potential to forecast average tomato prices when used in conjunction with polynomial feature transformation and parameter optimization. The agricultural industry's stakeholders may use this technique to gather knowledge of price trends and guide their decisions. More research may be done to increase prediction accuracy by incorporating more features and using other algorithm.