Mysun Mashira

Segmenting polyps in colonoscopy images is essential for the early identification and diagnosis of colorectal cancer, a significant cause of worldwide cancer deaths. Prior deep learning based models such as Attention based variation, UNet variations and Transformer-derived networks have had notable success in capturing intricate features and complex polyp shapes. In this study, we have introduced the DeepLabv3++ model which is an enhanced version of the DeepLabv3+ architecture. It is designed to improve the precision and robustness of polyp segmentation in colonoscopy images. We have utilized The proposed model incorporates diverse separable convolutional layers and attention mechanisms within the MSPP block, enhancing its capacity to capture multi-scale and directional features. Additionally, the redesigned decoder further transforms the extracted features from the encoder into a more meaningful segmentation map. Our model was evaluated on three public datasets (CVC-ColonDB, CVC-ClinicDB, Kvasir-SEG) achieving Dice coefficient scores of 96.20%, 96.54%, and 96.08%, respectively. The experimental analysis shows that DeepLabV3++ outperforms several state-of-the-art models in polyp segmentation tasks. Furthermore, compared to the baseline DeepLabV3+ model, our DeepLabV3++ with its MSPP module and redesigned decoder architecture, significantly reduced segmentation errors (e.g., false positives/negatives) across small, medium, and large polyps. This improvement in polyp delineation is crucial for accurate clinical decision-making in colonoscopy.

Edge Computing and the Internet of Things (IoT) have recently experienced significant growth and transformed how data is processed and analyzed. Edge computing improves efficiency and reduces latency by processing data locally. However, transmitting data efficiently while conserving energy is still a major issue today, especially considering the volume and redundancy of data. The computational capacity and memory of edge gateways in the network's edge layers are limited, making it challenging to process data effectively. As a result, data transmission often becomes inefficient. To address this issue, our research introduces an energy-efficient architecture for edge gateways in the edge layer. This architecture leverages data deduplication and compression techniques for IoT data transmission from edge to cloud. The research's unique deduplication algorithm eliminates duplicate data, while the Lempel Ziv 4 compression algorithm compresses large data sets effectively. This method not only reduces energy consumption but also minimizes memory usage, facilitating quicker and more efficient data transmission. Consequently, this approach significantly alleviates energy consumption challenges and limited data processing capabilities in the edge layer.