Search

Dynamic modern healthcare systems rely heavily on the contributions of computer scientists. The diagnosis process is a team effort involving many people: patients, their families, healthcare providers, researchers, and policymakers. Computer technology plays a crucial role in supporting this effort by providing a number of essential services to all of these groups. In the early stages of many diseases, a diagnosis can be made automatically using a computer-aided system, with some degree of certainty. This paper presents a hybrid optimal deep learning-based model for tuberculosis disease recognition using MRI images. Several deep learning models are combined to extract the most relevant features from MRI images. In particular, we establish a combination between vision transformer (ViTs) and Efficient-Net models in order to maximize classification accuracy. We conducted experiments to investigate the accuracy of the proposed model using the Shenzhen and Montgomery data set, and found that it yielded substantially more accurate and better results than the state of-the-art works. [ABSTRACT FROM AUTHOR]

Over the last few years, the amount of available information has increased exponentially in all professional fields, including the medical field. Modern-day patients have access to a wealth of medical information, whether it be from brochures, newspapers, television campaigns, or internet documents. To facilitate and accelerate the search for medical information, more precise systems have been implemented, such as visual question-and-answer systems. A visual question-and-answer system is designed to provide direct and precise answers to questions asked in natural language. In this context, we propose an optimal deep neural network model based on an adaptive optimization algorithm, which takes medical images and natural language questions as input, then provides precise answers as output. Our model starts by classifying medical questions following an embedding phase. We then use a deep learning model for visual and textual feature extraction and emergence. In this paper, we aim to maximize the accuracy rate and minimize the number of epochs in order to accelerate the process. This is a multi-objective optimization problem. The selection of deep learning model parameters, such as epoch number and batch size, is an essential step in improving the model, thus, we use an adaptive genetic algorithm to determine the optimal deep learning parameters. Finally, we propose a dense layer for answer retrieval. To evaluate our model, we used the ImageCLEF 2019 VQA data set. Our model outperforms existing visual question-and-answer systems and offers a significantly higher retrieval accuracy rate. [ABSTRACT FROM AUTHOR]

Solar irradiance prediction is an essential one in providing renewable energy proficiently. The solar irradiance plays a major role in solar power system, solar thermal system, and photovoltaic grid-connected system, owing to uncertainty and variability. Conventional data analysis approaches are complex for demonstrating superior generalization. Therefore, the resource planners are flexible in accommodating these uncertainties while executing planning. To enhance the performance of solar irradiance forecasting, a new Variant Input Scoring Optimized Recurrent Neural Network (VIS-ORNN) is developed. The suggested approach includes two stages that are data collection and three stage simulation. At first, the data are gathered from the various meteorological standard dataset. Then, the prediction begins with feeding data directly to the ORNN. Here, the parameters of RNN are optimized with the help of Adaptive Escaping Energy-based Harris Hawks Coyote Optimization (AEE-HHCO) algorithm. Thus, the first score prediction is obtained. In the second phase, the first order statistical features act as an input, and it is given to the same ORNN, in which the second score is determined. In the third phase, the deep features are extracted by Convolutional Neural Network (CNN) that is subjected to the same ORNN for attaining the score. Finally, the final simulation is determined by taking the average of three prediction models. From the experimental results, while taking the MAE, the suggested AEE-HHCO-ORNN method has correspondingly secured 34.3% enhanced than PSO-ORNN, 7.7% enhanced than WOA-ORNN, 21.7% enhanced than COA-ORNN and 26.5% enhanced than HHO-ORNN. Thus, the simulation outcomes reveal that the offered method ensures maximum accuracy while validating with other baseline methodologies. [ABSTRACT FROM AUTHOR]