检索结果-内蒙古大学图书馆

A Deep learning study on osteosarcoma detection from histological images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Anisuzzaman, D.M. Barzekar, Hosein Tong, Ling Luo, Jake Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Health Informatics and Administration University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States

In the U.S, 5-10% of new pediatric cases of cancer are primary bone tumors. The most common type of primary malignant bone tumor is osteosarcoma. The intention of the present work is to improve the detection and diagnosis of osteosarcoma using computer-aided detection (CAD) and diagnosis (CADx). Such tools as convolutional neural networks (CNNs) can significantly decrease the surgeon’s workload and make a better prognosis of patient conditions. CNNs need to be trained on a large amount of data in order to achieve a more trustworthy performance. In this study, transfer learning techniques, pre-trained CNNs, are adapted to a public dataset on osteosarcoma histological images to detect necrotic images from non-necrotic and healthy tissues. First, the dataset was preprocessed, and different classifications are applied. Then, Transfer learning models including VGG19 and Inception V3 are used and trained on Whole Slide Images (WSI) with no patches, to improve the accuracy of the outputs. Finally, the models are applied to different classification problems, including binary and multi-class classifiers. Experimental results show that the accuracy of the VGG19 has the highest, 96%, performance amongst all binary classes and multiclass classification. Our fine-tuned model demonstrates state-of-the-art performance on detecting malignancy of Osteosarcoma based on histologic images. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

MultiNet with Transformers: A Model for Cancer Diagnosis Using Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Barzekar, Hosein Patel, Yash Tong, Ling Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Health Informatics and Administration University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States

Cancer is a leading cause of death in many countries. An early diagnosis of cancer based on biomedical imaging ensures effective treatment and a better prognosis. However, biomedical imaging presents challenges to both clinical institutions and researchers. Physiological anomalies are often characterized by slight abnormalities in individual cells or tissues, making them difficult to detect visually. Traditionally, anomalies are diagnosed by radiologists and pathologists with extensive training. This procedure, however, demands the participation of professionals and incurs a substantial cost. The cost makes large-scale biological image classification impractical. In this study, we provide unique deep neural network designs for multiclass classification of medical images, in particular cancer images. We incorporated transformers into a multiclass framework to take advantage of data-gathering capability and perform more accurate classifications. We evaluated models on publicly accessible datasets using various measures to ensure the reliability of the models. Extensive assessment metrics suggest this method can be used for a multitude of classification tasks. © 2023, CC BY.

关键词： Computer aided diagnosis

Federated dynamic neural network for deep MIMO detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Yuwen Gao, Feifei Xue, Jiang Zhou, Ting Xu, Zongben Department of Automation Tsinghua University Beijing100084 China The National Engineering Laboratory for Big Data Analytics Xi'an International Academy for Mathematics and Mathematical Technology School of Mathematics and Statistics Xi'an Jiaotong University Xi'an710049 China The Shanghai Advanced Research Institute CAS Shanghai Frontier Innovation and Research Institute Shanghai201210 China

In this paper, we develop a dynamic detection network (DDNet) based detector for multiple-input multiple-output (MIMO) systems. By constructing an improved DetNet (IDetNet) detector and the OAMPNet detector as two independent network branches, the DDNet detector performs sample-wise dynamic routing to adaptively select a better one between the IDetNet and the OAMPNet detectors for every samples under different system conditions. To avoid the prohibitive transmission overhead of dataset collection in centralized learning (CL), we propose the federated averaging (FedAve)-DDNet detector, where all raw data are kept at local clients and only locally trained model parameters are transmitted to the central server for aggregation. To further reduce the transmission overhead, we develop the federated gradient sparsification (FedGS)-DDNet detector by randomly sampling gradients with elaborately calculated probability when uploading gradients to the central server. Based on simulation results, the proposed DDNet detector consistently outperforms other detectors under all system conditions thanks to the sample-wise dynamic routing. Moreover, the federated DDNet detectors, especially the FedGS-DDNet detector, can reduce the transmission overhead by at least 25.7% while maintaining satisfactory detection accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： MIMO systems

Learnable Convolutional Attention Network for Knowledge Graph Completion

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Shang, Bin Zhao, Yinliang Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Shaanxi Xi’an710049 China

Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in knowledge graph completion (KGC), which aims to solve the incompleteness of knowledge graphs (KGs). However, GCNs based KGC models tend to stack redundant information when one entity have several noisy neighbors. GATs based KGC models may focus on certain neighbors and lead to weakening of structural information. Furthermore, relations in KGs have their specific semantics and should be considered when aggregating neighbor information (message passing). To address the above limitations, we propose a learnable convolutional attention network for knowledge graph completion named LCA-KGC. LCA-KGC introduces a knowledge graph convolutional attention network by using the convolution operation before the attention mechanism to ensure the structural information acquisition and avoid the redundant information stacking. Furthermore, to complete the autonomous switching of GNNs types and eliminate the necessity of pre-validating the local structure of KGs, LCA-KGC designs a learnable knowledge graph convolutional attention network by comprising three types of GNNs in one learnable formulation. Moreover, a learnable message function is proposed to emphasize relational semantics when aggregating neighbor information. Extensive experiments on standard KG datasets validate the effectiveness of the proposed innovations, and LCA-KGC achieves state-of-the-art (SOTA) performance compared to existing approaches (e.g., compared to SOTA approaches, LCA-KGC improves MRR from 0.360 to 0.372 on FB15k-237 dataset, and Hits@3 from 0.561 to 0.581 on YAGO3-10 dataset). © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Leveraging High-Order Similar Nodes and Structural Correlation for Attention-Based Graph Embedding

学校读者我要写书评

暂无评论

Leveraging High-Order Similar Nodes and Structural Correlati...

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jing-Hong Wang Chang-Xin Li Jia-Teng Yang College of Computer and Cyber Security Hebei Normal University Shijiazhuang China Hebei Key Laboratory of Network and Information Security Hebei Normal University Shijiazhuang China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Security Hebei Normal University Shijiazhuang China Hebei Polytechnic Institute Shijiazhuang China

Graph Attention Network (GAT) is a popular method for graph embedding as they effectively leverage attention mechanisms to aggregate first-order neighborhood node information. However, they have limitations in their ability to consider high-order neighborhood nodes and structural information. Directly incorporating high-order neighborhood node information into traditional GAT may result in over-smoothing. To address this challenge, in this paper, we propose a joint attention graph embedding model based on similar networks and structural correlation. secondly, we introduce the concept of structural correlation to the original graph attentional method, and consider not only node content feature but also joint node topological structure feature when calculating the attention score. Finally, the graph attention mechanism module performs feature extraction to generate embedding representations of the nodes. The proposed algorithm achieved an accuracy of 85.7%, 74.30%, and 84.10% on the Cora, Citeseer, and Pubmed datasets respectively in node classification tasks. This represents an improvement of 2.70%, 3.94%, and 2.60% respectively compared to the traditional graph attention model. It can be seen that the proposed method can obtain a better representation of node embedding.

关键词：

Differential Privacy-based Avatar Update in Cooperative Intelligent Transportation System Metaverse

学校读者我要写书评

暂无评论

Differential Privacy-based Avatar Update in Cooperative Inte...

International Conference on Computer and Communications (ICCC)

作者： Salabat Khan Fei Luo Mansoor Khan Insaf Ullah Farhan Amin Shamsher Ullah Mussadiq Abdul Rahim School of Computer and Enformation Engineering Qilu Institute of Technology Jinan China School of Computing and Information Technology Great Bay University Dongguan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China Institute for Analytics and Data Science University of Essex Colchester UK School of Computer Science and Engineering Yeungnam University South Korea National Engineering Laboratory for Big Data Shenzhen University Shenzhen China King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Metaverse is the next generation and the successor to the Internet. Various sectors allocated capital to adapt the metaverse due to its inherent importance. Cooperative Intelligent Transportation Systems (C-ITS) is one of the important sectors that can benefit from metaverse adaptation and integration. The C-ITS and metaverse integration give rise to new use cases and cyber attacks. However, traditional Pseudonym Certificate (PCert) authentication based on Vehicular Public Key Infrastructure (VPKI) cannot meet the new use cases and thwart cyber attacks. We present a Differential Privacy (DP)-based PCert and avatar update model to ensure the privacy of end-devices (e.g., vehicles) in the C-ITS metaverse. The proposed DP-based model adds noise to avatar attributes (e.g., color, behavior) to prevent avatar linkage during the PCert update process. Our method ensures that PCerts and avatars cannot be linked to end-devices and the previous PCerts and avatars. We simulate the DP-based method to investigate it in terms of privacy, latency, color distortion, and adversarial success rate, and the results show that DP-based is effective and practical for avatar updates.

关键词： Privacy Metaverse Avatars Computational modeling Authentication Public key Color Colored noise Intelligent transportation systems Cyberattack

Noise-Tolerant Learning for Audio-Visual Action Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

Distributed Local Bayesian Network for Gene Regulatory Network Reconstruction

学校读者我要写书评

暂无评论

Distributed Local Bayesian Network for Gene Regulatory Netwo...

International Conference on big data Computing and Communications (bigCOM)

作者： Luxuan Qu Zhiqiong Wang Yueyang Huo Yuezhou Zhou Junchang Xin Wei Qian College of Medicine and Biological Information Engineering Northeastern University Shenyang China College of Medicine and Biological Information Engineering Northeastern University Neusoft Research of Intelligent Healthcare Technology Co. Ltd. Shenyang China School of Computer Science and Engineering Key Laboratory of Big Data Management and Analytics (Liaoning Province) Northeastern University Shenyang China College of Engineering The University of Texas at El Paso El Paso USA

ISBN: (数字)9781728182759

ISBN: (纸本)9781728182766

Gene regulatory network provides an effective way to study functional genomes. Reconstruction of gene regulatory network can better help us to reveal the regulatory relationship and complex mechanism between genes, thus exploring the essence of biological systems and lives. At present, the modeling methods of gene regulatory network either solve the problem of accuracy or scale of gene regulatory network by optimizing the model or combining various models. However, with the continuous increase of network scale and the computational complexity, the reconstruction of the network has exceeded the ability of single machine. Thus, we presented the Distributed Local Bayesian Network (D-LBN) method based on MapReduce framework to solve this problem. D-LBN is based on LBN algorithm which uses mutual information method, k-nearest neighbor algorithm, Bayesian network model and conditional mutual information method to reconstruct gene regulatory network. D-LBN realizes distributed computing using MapReduce framework at the step of regulatory direction learning with Bayesian network model to achieve the purpose of reconstructing large-scale gene regulatory network. Experiments based on two scales of dataset is done to verify the performance of D-LBN in reconstructing gene regulatory network at different scales. The results show that D-LBN is consistent with LBN in evaluation index and much more efficient than LBN on large-scale network reconstruction. And the scale of the network that can be reconstructed is also greatly improved.

关键词： Bayes methods Computational modeling Mutual information Mathematical model Biological system modeling Entropy

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting