Search

Brain tumor detection and classification are crucial tasks in medical imaging and play a vital role in the treatment planning process. This abstract presents a method for brain tumor treatment using Convolutional Neural Networks (CNNs). CNNs are deep learning models that have shown remarkable success in various computer vision tasks, including medical image analysis. The proposed approach leverages the power of CNNs to automatically learn discriminative features from Magnetic Resonance (MR) brain images. The dataset used in this study consists of pre-processed MR images of patients with different types of brain tumors. These images are labeled with ground truth information indicating the presence and type of tumor. The CNN model is trained using a large set of labeled MR images, allowing it to learn complex patterns and features that distinguish healthy brain tissue from tumor regions. The training process involves iterative optimization of the network's parameters, guided by a loss function that measures the dissimilarity between predicted and actual tumor labels. Once trained, the CNN model can be used for tumor detection and classification on new, unseen MR brain images. Given an input image, the model analyzes its features and outputs a prediction indicating the presence of a tumor and its type if detected. This information can assist medical professionals in diagnosing and planning appropriate treatment strategies. To evaluate the effectiveness of the proposed approach, extensive experiments are conducted on a diverse set of MR brain images. The experimental results demonstrate the potential of CNNs in achieving high accuracy and robustness in brain tumor detection and classification tasks. [ABSTRACT FROM AUTHOR]

Deregulation of Electricity market has not only led to increase in competition among generators, but also reduced electricity prices. It has introduced several issues in the market; two of them are congestion management and market power. Due to open transmission access all the participants have equal right to access transmission network. However, they have to bear the costs incurred to accommodate their transaction. The cost allocation is still a problem to be tackled efficiently. The prevailing problem is how to allocate the congestion cost among the market participants. An efficient and fair allocation of congestion cost would result in smooth operation of transmission system. It also helps in tackling congestion and market power. This paper proposes a novel approach using Aumann Shapley (AS) method of game theory for congestion cost allocation in a deregulated electricity market. The results obtained using proposed method are compared with uplift and nodal pricing methods for IEEE 14 bus system, New England 39 bus system and 75 bus Indian power system (practical data). This comparison illustrates the pros and cons of each method. [ABSTRACT FROM AUTHOR]