scholarly journals FAU-Net: Fixup Initialization Channel Attention Neural Network for Complex Blood Vessel Segmentation

2020 ◽  
Vol 10 (18) ◽  
pp. 6280
Author(s):  
Dongjin Huang ◽  
Liwen Yin ◽  
Hao Guo ◽  
Wen Tang ◽  
Tao Ruan Wan
Keyword(s):  
Blood Vessel ◽  
Medical Image Segmentation ◽  
Experimental Results ◽  
Data Sets ◽  
Central Research ◽  
Attention Network ◽  
Multiple Feature ◽  
Network Flexibility ◽  
Crucial Information ◽  
Residual Block

Medical image segmentation based on deep learning is a central research issue in the field of computer vision. Many existing segmentation networks can achieve accurate segmentation using fewer data sets. However, they have disadvantages such as poor network flexibility and do not adequately consider the interdependence between feature channels. In response to these problems, this paper proposes a new de-normalized channel attention network, which uses an improved de-normalized residual block structure and a new channel attention module in the network for the segmentation of sophisticated vessels. The de-normalized network sends the extracted rough features to the channel attention network. The channel attention module can explicitly model the interdependence between channels and pay attention to the correlation with crucial information in multiple feature channels. It can focus on the channels with the most association with vital information among multiple feature channels, and get more detailed feature results. Experimental results show that the network proposed in this paper is feasible, is robust, can accurately segment blood vessels, and is particularly suitable for complex blood vessel structures. Finally, we compared and verified the network proposed in this paper with the state-of-the-art network and obtained better experimental results.

scholarly journals DV-DVFS: merging data variety and DVFS technique to manage the energy consumption of big data processing

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Hossein Ahmadvand ◽  
Fouzhan Foroutan ◽  
Mahmood Fathy
Keyword(s):  
Big Data ◽  
Energy Consumption ◽  
Processing Time ◽  
Experimental Results ◽  
The Other ◽  
Data Sets ◽  
Multiple Sources ◽  
Evaluation Phase ◽  
Dynamic Voltage ◽  
Processing Resources

AbstractData variety is one of the most important features of Big Data. Data variety is the result of aggregating data from multiple sources and uneven distribution of data. This feature of Big Data causes high variation in the consumption of processing resources such as CPU consumption. This issue has been overlooked in previous works. To overcome the mentioned problem, in the present work, we used Dynamic Voltage and Frequency Scaling (DVFS) to reduce the energy consumption of computation. To this goal, we consider two types of deadlines as our constraint. Before applying the DVFS technique to computer nodes, we estimate the processing time and the frequency needed to meet the deadline. In the evaluation phase, we have used a set of data sets and applications. The experimental results show that our proposed approach surpasses the other scenarios in processing real datasets. Based on the experimental results in this paper, DV-DVFS can achieve up to 15% improvement in energy consumption.

scholarly journals Graph contextualized attention network for predicting synthetic lethality in human cancers

2021 ◽  
Author(s):  
Yahui Long ◽  
Min Wu ◽  
Yong Liu ◽  
Jie Zheng ◽  
Chee Keong Kwoh ◽  
...  
Keyword(s):  
Synthetic Lethality ◽  
Critical Role ◽  
Design Feature ◽  
Cost Effective ◽  
Attention Network ◽  
New Genes ◽  
Lab Experiments ◽  
Proposed Model ◽  
Multiple Feature ◽  
Wet Lab

Abstract Motivation Synthetic Lethality (SL) plays an increasingly critical role in the targeted anticancer therapeutics. In addition, identifying SL interactions can create opportunities to selectively kill cancer cells without harming normal cells. Given the high cost of wet-lab experiments, in silico prediction of SL interactions as an alternative can be a rapid and cost-effective way to guide the experimental screening of candidate SL pairs. Several matrix factorization-based methods have recently been proposed for human SL prediction. However, they are limited in capturing the dependencies of neighbors. In addition, it is also highly challenging to make accurate predictions for new genes without any known SL partners. Results In this work, we propose a novel graph contextualized attention network named GCATSL to learn gene representations for SL prediction. First, we leverage different data sources to construct multiple feature graphs for genes, which serve as the feature inputs for our GCATSL method. Second, for each feature graph, we design node-level attention mechanism to effectively capture the importance of local and global neighbors and learn local and global representations for the nodes, respectively. We further exploit multi-layer perceptron (MLP) to aggregate the original features with the local and global representations and then derive the feature-specific representations. Third, to derive the final representations, we design feature-level attention to integrate feature-specific representations by taking the importance of different feature graphs into account. Extensive experimental results on three datasets under different settings demonstrated that our GCATSL model outperforms 14 state-of-the-art methods consistently. In addition, case studies further validated the effectiveness of our proposed model in identifying novel SL pairs. Availability Python codes and dataset are freely available on GitHub (https://github.com/longyahui/GCATSL) and Zenodo (https://zenodo.org/record/4522679) under the MIT license.

scholarly journals Improved minimum-minimum roughness algorithm for clustering categorical data

2021 ◽  
Vol 8 (10) ◽  
pp. 43-50
Author(s):  
Truong et al. ◽  
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Hierarchical Clustering ◽  
Categorical Data ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Experimental Results ◽  
Data Sets ◽  
Top Down ◽  
Hierarchical Clustering Algorithm

Clustering is a fundamental technique in data mining and machine learning. Recently, many researchers are interested in the problem of clustering categorical data and several new approaches have been proposed. One of the successful and pioneering clustering algorithms is the Minimum-Minimum Roughness algorithm (MMR) which is a top-down hierarchical clustering algorithm and can handle the uncertainty in clustering categorical data. However, MMR tends to choose the category with less value leaf node with more objects, leading to undesirable clustering results. To overcome such shortcomings, this paper proposes an improved version of the MMR algorithm for clustering categorical data, called IMMR (Improved Minimum-Minimum Roughness). Experimental results on actual data sets taken from UCI show that the IMMR algorithm outperforms MMR in clustering categorical data.

scholarly journals Collaborative Filtering Recommendation Using Nonnegative Matrix Factorization in GPU-Accelerated Spark Platform

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Bing Tang ◽  
Linyao Kang ◽  
Li Zhang ◽  
Feiyan Guo ◽  
Haiwu He
Keyword(s):  
Collaborative Filtering ◽  
Processing Speed ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Experimental Results ◽  
Computational Time ◽  
Data Sets ◽  
Heterogeneous Cluster ◽  
The Matrix

Nonnegative matrix factorization (NMF) has been introduced as an efficient way to reduce the complexity of data compression and its capability of extracting highly interpretable parts from data sets, and it has also been applied to various fields, such as recommendations, image analysis, and text clustering. However, as the size of the matrix increases, the processing speed of nonnegative matrix factorization is very slow. To solve this problem, this paper proposes a parallel algorithm based on GPU for NMF in Spark platform, which makes full use of the advantages of in-memory computation mode and GPU acceleration. The new GPU-accelerated NMF on Spark platform is evaluated in a 4-node Spark heterogeneous cluster using Google Compute Engine by configuring each node a NVIDIA K80 CUDA device, and experimental results indicate that it is competitive in terms of computational time against the existing solutions on a variety of matrix orders. Furthermore, a GPU-accelerated NMF-based parallel collaborative filtering (CF) algorithm is also proposed, utilizing the advantages of data dimensionality reduction and feature extraction of NMF, as well as the multicore parallel computing mode of CUDA. Using real MovieLens data sets, experimental results have shown that the parallelization of NMF-based collaborative filtering on Spark platform effectively outperforms traditional user-based and item-based CF with a higher processing speed and higher recommendation accuracy.

scholarly journals Certified B Corporations and Benefit Corporations

Management ◽  
2021 ◽  
Keyword(s):  
Theoretical Work ◽  
The United States ◽  
Data Sets ◽  
Central Research ◽  
Legal Form ◽  
Exemplary Teaching ◽  
For Profit ◽  
Theoretical Perspectives ◽  
Research Themes ◽  
Benefit Corporations

Over the past decade, Certified B Corporations and Benefit Corporations, commonly known as B Corps, have emerged as a global phenomenon. Both organizational forms are for-profit businesses. Whereas Certified B Corporations have been accredited for their environmental, social, and governance (ESG) practices, Benefit Corporations are a new legal form, currently available in thirty-eight states and jurisdictions in the United States (US) as well as in British Columbia (Canada), Colombia, Ecuador, and Italy. Both types were promulgated by B Lab, a US-based nonprofit organization. Founded in 2006 in the suburbs of Philadelphia, Pennsylvania, B Lab has sought to institutionalize business as a force for good. At present, certification is available to any business worldwide, and approximately 3,700 companies in seventy-four countries are currently certified. Prominent Certified B Corporations include Ben & Jerry’s, Danone North America, and Patagonia. Examples of Benefit Corporations include Data.World, Kickstarter, and Plum Organics. Overall, the B Corp movement’s radical aspiration to redefine business has garnered substantial attention from policymakers, media, businesses, nongovernmental organizations (NGOs), and academe. This article provides an overview of burgeoning scholarly work—ranging from general references and cutting-edge theoretical work to accumulating empirical findings and key pedagogical resources. A core focus is on enumerating the variety of theoretical perspectives that have been taken and the central research themes in extant work, including interdisciplinary publications. We close by discussing exemplary teaching materials and introducing other resources, such as the B Academics research community and available data sets for research.

An Efficient Framework for Vietnamese Sentiment Classification

2020 ◽  
Author(s):  
Cuong V. Nguyen ◽  
Khiem H. Le ◽  
Anh M. Tran ◽  
Binh T. Nguyen
Keyword(s):  
Product Quality ◽  
Sentiment Analysis ◽  
New Products ◽  
Classification Problem ◽  
Research Community ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Data Sets ◽  
Online Retailers

With the booming development of E-commerce platforms in many counties, there is a massive amount of customers’ review data in different products and services. Understanding customers’ feedbacks in both current and new products can give online retailers the possibility to improve the product quality, meet customers’ expectations, and increase the corresponding revenue. In this paper, we investigate the Vietnamese sentiment classification problem on two datasets containing Vietnamese customers’ reviews. We propose eight different approaches, including Bi-LSTM, Bi-LSTM + Attention, Bi-GRU, Bi-GRU + Attention, Recurrent CNN, Residual CNN, Transformer, and PhoBERT, and conduct all experiments on two datasets, AIVIVN 2019 and our dataset self-collected from multiple Vietnamese e-commerce websites. The experimental results show that all our proposed methods outperform the winning solution of the competition “AIVIVN 2019 Sentiment Champion” with a significant margin. Especially, Recurrent CNN has the best performance in comparison with other algorithms in terms of both AUC (98.48%) and F1-score (93.42%) in this competition dataset and also surpasses other techniques in our dataset collected. Finally, we aim to publish our codes, and these two data-sets later to contribute to the current research community related to the field of sentiment analysis.

The LBF R-Tree

2010 ◽  
pp. 1-27
Author(s):  
Todd Eavis
Keyword(s):  
Hilbert Space ◽  
Data Warehousing ◽  
Experimental Results ◽  
Data Sets ◽  
Space Filling ◽  
Fully Integrated ◽  
Space Filling Curve ◽  
Filling Curve ◽  
Common User ◽  
Tree Performance

In multi-dimensional database environments, such as those typically associated with contemporary data warehousing, we generally require effective indexing mechanisms for all but the smallest data sets. While numerous such methods have been proposed, the R-tree has emerged as one of the most common and reliable indexing models. Nevertheless, as user queries grow in terms of both size and dimensionality, R-tree performance can deteriorate significantly. Moreover, in the multi-terabyte spaces of today’s enterprise warehouses, the combination of data and indexes ? R-tree or otherwise ? can produce unacceptably large storage requirements. In this chapter, the authors present a framework that addresses both of these concerns. First, they propose a variation of the classic R-tree that specifically targets data warehousing architectures. Their new LBF R-tree not only improves performance on common user-defined range queries, but gracefully degrades to a linear scan of the data on pathologically large queries. Experimental results demonstrate a reduction in disk seeks of more than 50% relative to more conventional R-tree designs. Second, the authors present a fully integrated, block-oriented compression model that reduces the storage footprint of both data and indexes. It does so by exploiting the same Hilbert space filling curve that is used to construct the LBF R-tree itself. Extensive testing demonstrates compression rates of more than 90% for multi-dimensional data, and up to 98% for the associated indexes.

scholarly journals Pyramid Predictive Attention Network for Medical Image Segmentation

2019 ◽  
Vol E102.A (9) ◽  
pp. 1225-1234 ◽  
Author(s):  
Tingxiao YANG ◽  
Yuichiro YOSHIMURA ◽  
Akira MORITA ◽  
Takao NAMIKI ◽  
Toshiya NAKAGUCHI
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Attention Network

scholarly journals Scene Recognition Based on Recurrent Memorized Attention Network

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2038
Author(s):  
Xi Shao ◽  
Xuan Zhang ◽  
Guijin Tang ◽  
Bingkun Bao
Keyword(s):  
Recognition Accuracy ◽  
State Of The Art ◽  
Classification Performance ◽  
Scene Recognition ◽  
Experimental Results ◽  
Scene Classification ◽  
Attention Network ◽  
Attention Model ◽  
Scene Image ◽  
Object Based

We propose a new end-to-end scene recognition framework, called a Recurrent Memorized Attention Network (RMAN) model, which performs object-based scene classification by recurrently locating and memorizing objects in the image. Based on the proposed framework, we introduce a multi-task mechanism that contiguously attends on the different essential objects in a scene image and recurrently performs memory fusion of the features of object focused by an attention model to improve the scene recognition accuracy. The experimental results show that the RMAN model has achieved better classification performance on the constructed dataset and two public scene datasets, surpassing state-of-the-art image scene recognition approaches.

Ensemble Pruning for Data Dependant Learners

2011 ◽  
Vol 135-136 ◽  
pp. 522-527 ◽  
Author(s):  
Gang Zhang ◽  
Shan Hong Zhan ◽  
Chun Ru Wang ◽  
Liang Lun Cheng
Keyword(s):  
Unlabeled Data ◽  
Experimental Results ◽  
Clear Relationship ◽  
Data Sets ◽  
Ensemble Pruning ◽  
Generalization Ability ◽  
Learning Framework ◽  
Single Instance ◽  
Better Than ◽  
Individual Kernel

Ensemble pruning searches for a selective subset of members that performs as well as, or better than ensemble of all members. However, in the accuracy / diversity pruning framework, generalization ability of target ensemble is not considered, and moreover, there is not clear relationship between them. In this paper, we proof that ensemble formed by members of better generalization ability is also of better generalization ability. We adopt learning with both labeled and unlabeled data to improve generalization ability of member learners. A data dependant kernel determined by a set of unlabeled points is plugged in individual kernel learners to improve generalization ability, and ensemble pruning is launched as much previous work. The proposed method is suitable for both single-instance and multi-instance learning framework. Experimental results on 10 UCI data sets for single-instance learning and 4 data sets for multi-instance learning show that subensemble formed by the proposed method is effective.

Sign in / Sign up

Export Citation Format

Share Document