Magnetic resonance imaging is the most generally utilized imaging methodology that permits radiologists to look inside the cerebrum using radio waves and magnets for tumor identification. However, it is tedious and complex to identify the tumorous and nontumorous regions due to the complexity in the tumorous region. Therefore, reliable and automatic segmentation and prediction are necessary for the segmentation of brain tumors. This paper proposes a reliable and efficient neural network variant, i.e., an attention-based convolutional neural network for brain tumor segmentation. Specifically, an encoder part of the UNET is a pre-trained VGG19 network followed by the adjacent decoder parts with an attention gate for segmentation noise induction and a denoising mechanism for avoiding overfitting. The dataset we are using for segmentation is BRATS’20, which comprises four different MRI modalities and one target mask file. The abovementioned algorithm resulted in a dice similarity coefficient of 0.83, 0.86, and 0.90 for enhancing, core, and whole tumors, respectively.

No abstract

No abstract

Wireless sensor networks (WSNs) have been applied in networking devices, and a new problem has emerged called source-location privacy (SLP) in critical security systems. In wireless sensor networks, hiding the location of the source node from the hackers is known as SLP. The WSNs have limited battery capacity and low computational ability. Many state-of-the-art protocols have been proposed to address the SLP problems and other problems such as limited battery capacity and low computational power. One of the popular protocols is random path routing (RPR), and in random path routing, the system keeps sending the message randomly along all the possible paths from a source node to a sink node irrespective of the path’s distance. The problem arises when the system keeps sending a message via the longest route, resulting because of high battery usage and computational costs. This research paper presents a novel networking model referred to as calculated random path routing (CRPR). CRPR first calculates the top three shortest paths, and then randomly sends a token to any of the top three shortest calculated paths, ensuring the optimal tradeoff between computational cost and SLP. The proposed methodology includes the formal modeling of the CRPR in Colored Petri Nets. We have validated and verified the CRPR, and the results depict the optimal tradeoff.