Differential privacy offers a promising solution to balance data utility and user privacy. This paper compares two prominent differential privacy tools-PyDP and IBM's diffprivlib-that are applied to a synthetic da...
详细信息
Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do ...
详细信息
Transfer learning is a valuable tool for the effective assistance of gastroenterologists in the powerful diagnosis of medical images with fast convergence. It also intends to minimize the time and estimated effort req...
详细信息
Transfer learning is a valuable tool for the effective assistance of gastroenterologists in the powerful diagnosis of medical images with fast convergence. It also intends to minimize the time and estimated effort required for improved gastrointestinal tract (GIT) diagnosis. GIT abnormalities are widely known to be fatal disorders leading to significant mortalities. It includes both upper and lower GIT disorders. The challenges of addressing GIT issues are complex and need significant study. Multiple challenges exist regarding computer-aided diagnosis (CAD) and endoscopy including a lack of annotated images, dark backgrounds, less contrast, noisy backgrounds, and irregular patterns. Deep learning and transfer learning have assisted gastroenterologists in effective diagnosis in various ways. The goal of proposed framework is the effective classification of endoscopic GIT images with enhanced accuracy. The proposed research aims to formulate a transfer learning-based deep ensemble model, accurately classifying GIT disorders for therapeutic purposes. The proposed model is based on weighted voting ensemble of the two state-of-the-art (STA) base models, NasNet-Mobile and EfficientNet. The extraction of regions of interest, specifically the sick portions, have been performed using images captured from endoscopic procedure. Performance evaluation of the proposed model is performed with cross-dataset evaluation. The datasets utilized include the training dataset HyperKvasir and two test datasets, Kvasir v1 and Kvasir v2. However, the dataset alone cannot create a robust model due to the unequal distribution of images across categories, making transfer learning a promising approach for model development. The evaluation of the proposed framework has been conducted by cross-dataset evaluation utilizing accuracy, precision, recall, Area under curve (AUC) score and F1 score performance metrics. The proposed work outperforms much of the existing transfer learning-based models giv
Community detection in multiplex networks has emerged as a crucial research area due to its ability to capture complex interactions across multiple layers of interconnected data. Despite significant advancements, exis...
详细信息
Community detection in multiplex networks has emerged as a crucial research area due to its ability to capture complex interactions across multiple layers of interconnected data. Despite significant advancements, existing methods often face critical challenges, including computational time, resolution limit, free parameter tuning, training models, etc. To overcome these limitations, this paper presents LCDMN (Layer-Coupled Diffusion for Multiplex Networks) algorithm designed for accurate and efficient community detection in multiplex networks. LCDMN employs dynamic scaling and layer coupling to adaptively identify community structures across diverse network configurations, offering improved resilience to network's density and structural ambiguity. LCDMN addresses the challenges of layer diversity by: (1) dynamically weighting layers based on critical parameters such as layer correlation, layer nodes activity variance, and attractiveness, (2) developing a robust node scoring method, (3) the aggregating layers of multiplex network into a single-layer, weighted graph, (4) employing a label diffusion approach with mechanisms for handling overlapping nodes, and (5) refining community structures through a dynamic merging process that adaptively adjusts layer contributions and community boundaries during execution, ensuring context-sensitive resolution of structural ambiguity. Nodes and edges are scored using network topology and structural metrics to efficiently incorporate in label diffusion process for detecting initial communities. The approach balances computational efficiency with precision, enabling the detection of cohesive and well-defined communities in complex networks. Experimental evaluations on real-world and synthetic multiplex networks demonstrate that LCDMN consistently outperforms state-of-the-art methods, such as Infomap, MDLPA, MPBTV, LART, DGFM3 and GenLouvain, in terms of Normalized Mutual Information (NMI), Adjusted Rand Index (ARI), and modularity.
The equipment digital twins (EDTs) for discrete manufacturing should be calibrated quickly to avoid irreversible physical damage to the equipment caused by biased control commands. Therefore, an online credibility ass...
详细信息
Accurate 3D modelling of grapevines is crucial for precision viticulture, particularly for informed pruning decisions and automated management techniques. However, the intricate structure of grapevines poses significa...
详细信息
Refactoring is the process of restructuring existing code without changing its external behavior while improving its internal structure. Refactoring engines are integral components of modern Integrated Development Env...
详细信息
As the technology node develops toward its physical limit, lithographic hotspot detection has become increasingly important and ever-challenging in the computer-aided design (CAD) flow. In recent years, convolutional ...
详细信息
The increasing demand for programmers has led to a surge in participants in programming courses, making it increasingly challenging for instructors to assess student code manually. As a result, automated programming a...
详细信息
暂无评论