Digital life has augmented the human horizons, code-driven systems have spread to more than half of the world's inhabitants owing to ambient information and connectivity. Successful combination integration of huma...
详细信息
Nowadays, one-step multi-view clustering algorithms attract many interests. The main issue of multi-view clustering approaches is how to combine the information extracted from the available views. A popular approach i...
详细信息
ISBN:
(纸本)9783031064333;9783031064326
Nowadays, one-step multi-view clustering algorithms attract many interests. The main issue of multi-view clustering approaches is how to combine the information extracted from the available views. A popular approach is to use view-based graphs and/or a consensus graph to describe the different views. We introduce a novel one-step graph-based multi-view clustering approach in this study. Our suggested method, in contrast to existing graph-based one-step clustering methods, provides two major novelties to the method called Nonnegative Embedding and Spectral Embedding (NESE) proposed in the recent paper [1]. To begin, we use the cluster label correlation to create an additional graph in addition to the graphs associated with the data space. Second, the cluster-label matrix is constrained by adopting some restrictions to make it more consistent. The effectiveness of the proposed method is demonstrated by experimental results on many public datasets.
作者:
Mahesha, Y.Nagaraju, C.Mrit
Department of Computer Science and Engineering Mandya Karnataka India The Nie
Department of Electronics and Communication Mysore Karnataka India
In this paper, we propose a machinelearning method to detect Congenital Heart Diseases using a palm pattern known as axial triradius. An Axial triradius is one of the features of palm whose position can be used to de...
详细信息
Digital imageprocessing has numerous applications in many sectors of the world. It expands from initial information registration into methods and thoughts combining patternrecognition, computer vision, and machine l...
详细信息
While urad bean is an important grain crop in several locations, it is frequently plagued by a number illness that has a devastating effect on harvest yields and quality. Using Convolutional Neural Net- works (CNNs) w...
详细信息
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transfor...
详细信息
ISBN:
(纸本)9783031064333;9783031064326
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the model, allowing it to learn using far fewer free parameters, using only 28k training samples. A comprehensive ablation study confirms the importance of a hybrid CNN + Transformer architecture and the role of the feedback connections, which iteratively refine the internal representation until a stable prediction is obtained. In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.
Chronic Kidney diseases are increasing at an alarming rate in present days. The prediction of kidney disease consume more time as it involves a lot of laboratory tests. Traditionally, the health care domain relies on ...
详细信息
ISBN:
(纸本)9781665476560
Chronic Kidney diseases are increasing at an alarming rate in present days. The prediction of kidney disease consume more time as it involves a lot of laboratory tests. Traditionally, the health care domain relies on the centralized data, which may lead the system to have significant risks and difficulties. The proposed model involves uses federated learning, a machinelearning technique that involves training an algorithm on multiple decentralized data. The model uses imageprocessing technique, where the scanned image of the kidney is given as the input. The image, upon various pre-processing techniques identifies the affected area of the kidney. The affected area is also marked in color and the values of accuracy, efficiency, specificity and sensitivity are found to be higher than the existing systems. The output of the single image is again given to training dataset to increase the accuracy precisely, which is a part of the federated learning.
In this work, we propose a hybrid method for image segmentation based on the selection of four extreme points (leftmost, rightmost, top and bottom pixels at the object boundary), combining Deep Extreme Cut, a connecti...
详细信息
ISBN:
(数字)9783030766573
ISBN:
(纸本)9783030766566;9783030766573
In this work, we propose a hybrid method for image segmentation based on the selection of four extreme points (leftmost, rightmost, top and bottom pixels at the object boundary), combining Deep Extreme Cut, a connectivity constraint for the extreme points, a marker-based color classifier from automatically estimated markers and a final relaxation procedure with the boundary polarity constraint, which is related to the extension of Random Walks to directed graphs as proposed by Singaraju et al. Its second constituent element presents theoretical contributions on how to optimally convert the 4 point boundary-based selection into connected region-based markers for image segmentation. The proposed method is able to correct imperfections from Deep Extreme Cut, leading to considerably improved results, in public datasets of natural images, with minimal user intervention (only four mouse clicks).
Commencing with an exposition on the fundamental tenets underpinning cancer diagnosis, elucidating the sequential phases integral to the diagnostic procedure, and delving into the conventional classification methodolo...
详细信息
ISBN:
(数字)9798350355338
ISBN:
(纸本)9798350355345
Commencing with an exposition on the fundamental tenets underpinning cancer diagnosis, elucidating the sequential phases integral to the diagnostic procedure, and delving into the conventional classification methodologies wielded by medical professionals, this abstract will embark on a comprehensive exploration. Within these pages, readers will embark on a historical odyssey through the annals of cancer classification methodologies, providing insights into their evolution over time. While these established techniques serve as stalwarts in the realm of cancer diagnosis, their effectiveness is tinged with limitations. Furthermore, we shall furnish a succinct compendium of pivotal evaluation metrics, tailored to cater to diverse audiences, encompassing the receiver operating characteristic curve (ROC curve), the area under the ROC curve (AUC), and the F1 *** light of the deficiencies associated with earlier techniques, there arises an escalating demand for more sophisticated and discerning approaches to cancer diagnosis. Enter the realm of artificial intelligence, poised to chart a transformative trajectory in the landscape of diagnostic tools. In particular, the potential resonance of deep neural networks beckons as an avenue for intelligent image analysis, promising unprecedented strides in diagnostic precision. Our discourse shall unravel the intricacies of pre-processing, image segmentation, and post-processing techniques within the foundational framework of machinelearning applied to medical imaging, illuminating the path towards enhanced diagnostic capabilities.
Sign language recognition is now possible because of the advancements in processors, computer vision, imageprocessing, machine and deep learning techniques. This development has made it feasible to interpret sign lan...
详细信息
暂无评论