检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yu, Qian Qi, Lei Zhou, Luping Wang, Lei Yin, Yilong Shi, Yinghuan Wang, Wuzhang Gao, Yang School of Data and Computer Science Shandong Women's University Jinan250300 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing211189 China The School of Electrical and Information Engineering University of Sydney NSW2006 Australia The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia The School of Soft Shandong University Jinan250100 China Department of Respiratory and Critical Care Medicine Shandong Chest Hospital Jinan250013 China

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://***/Qianyu1226/*** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies

arXiv

引用

arXiv 2021年

作者： Shen, Yu Li, Yang Zheng, Jian Zhang, Wentao Yao, Peng Li, Jixiang Yang, Sen Liu, Ji Cui, Bin Key Lab of High Confidence Software Technologies Peking University China Institute of Computational Social Science Peking University Qingdao China School of Computer Science and Engineering Beihang University China Kuaishou Technology China Data Platform TEG Tencent Inc. China Mila - Québec AI Institute Canada HEC Montréal Canada

Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run slowly, zero-cost proxies run extremely fast but are less promising. Therefore, it’s of great potential to accelerate NAS via those zero-cost proxies. The existing method has two limitations, which are unforeseeable reliability and one-shot usage. To address the limitations, we present ProxyBO, an efficient Bayesian optimization (BO) framework that utilizes the zero-cost proxies to accelerate neural architecture search. We apply the generalization ability measurement to estimate the fitness of proxies on the task during each iteration and design a novel acquisition function to combine BO with zero-cost proxies based on their dynamic influence. Extensive empirical studies show that ProxyBO consistently outperforms competitive baselines on five tasks from three public benchmarks. Concretely, ProxyBO achieves up to 5.41× and 3.86× speedups over the state-ofthe-art approaches REA and BRP-NAS. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

MC-Blur: A Comprehensive Benchmark for Image Deblurring

arXiv

引用

arXiv 2021年

作者： Zhang, Kaihao Wang, Tao Luo, Wenhan Ren, Wenqi Stenger, Björn Liu, Wei Li, Hongdong Yang, Ming-Hsuan College of Engineering and Computer Science Australian National University Canberra Australia State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Sun Yat-sen University Guangzhou China Rakuten Institute of Technology Setagaya Tokyo Japan Tencent Data Platform Shenzhen China School of Engineering University of California at Merced MercedCA United States

Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods perform in the case of multiple types of blur. For in-depth performance evaluation, we construct a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors. The images in the proposed MC-Blur dataset are collected using other techniques: averaging sharp images captured by a 1000-fps high-speed camera, convolving Ultra-High-Definition (UHD) sharp images with large-size kernels, adding defocus to images, and real-world blurry images captured by various camera models. Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity. These benchmarking results provide a comprehensive overview of the advantages and limitations of current deblurring methods, revealing our dataset’s advances. The dataset is available to the public at https://***/HDCVLab/MC-Blur-dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Crowd Counting for Static Images: A Survey of Methodology

Crowd Counting for Static Images: A Survey of Methodology

引用

第三十九届中国控制会议

作者： Ying Luo Jinhu Lu Baochang Zhang School of Automation Science and Electrical Engineering Beihang University Shenyuan Honors College Beihang University School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environmentand Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang University

Crowd counting for static images is one of the typical application fields of image processing. it is essential to direct crowd analysis for public security purposes under the background of a rapidly growing social environment. Crowd counting for static images involves crucial challenges such as occlusions, scale variations, scene perspective distortions and diverse crowd distributions. It has now become an independent research hotspot. This paper investigates the literature of crowd counting tasks, summarizes the evolution of counting approaches, compares and analyzes traditional methods and current trends of CNN estimation-based counting, and then evaluates common datasets for crowd counting tasks. Conclusions concerning summarizations and prospects are made.

关键词： Crowd counting crowd analysis pattern recognition computer vision

来源：评论

学校读者我要写书评

暂无评论

Android malware family classification and characterization using CFG and DFG 13

Android malware family classification and characterization u...

引用

13th International Symposium on Theoretical Aspects of software engineering, TASE 2019

作者： Xu, Zhiwu Ren, Kerong Song, Fu College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Information Science and Technology ShanghaiTech University Shanghai China

ISBN: (纸本)9781728133423

Android malware has become a serious threat for our daily life, and thus there is a pressing need to effectively mitigate or defend against them. Recently, many approaches and tools to analyze Android malware have been proposed to protect legitimate users from the threat. However, most approaches focus on malware detection, while only a few of them consider malware classification or malware characterization. In this paper, we propose an extension of CDGDroid to classifying and characterizing Android malware families automatically. We first perform static analysis used in CDGDroid to extract control-flow graphs and data-flow graphs on the instruction level. Then we encode the graphs into matrices, and use them to build the family classification models via deep learning. For family characterization, we extract the n-gram sequences from the graphs, which are filtered according to the weights of the classification model built for the target family. And then we construct a vector space model and select the top-k sequences as a characterization of the target family. We have conducted some experiments to evaluate our approach and have identified that the family classification model taking the horizontal combination of CFG and DFG as features offers the best performance in terms of accuracy among all the models. Compared with CDGDroid, Drebin and many antivirus tools gathered in VirusTotal, our family classification model gives a better performance. Finally, We have also conducted experiments on family characterization, and the experimental results have shown that our characterization can capture the malicious behaviors of the testing families. © 2019 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

A real-time feedback approach based on semantic clustering for poverty alleviation problem

A real-time feedback approach based on semantic clustering f...

引用

2019 IEEE International Conferences on Ubiquitous Computing and Communications and data science and Computational Intelligence and Smart Computing, Networking and Services, IUCC/DSCI/SmartCNS 2019

作者： Peng, Zizhen Peng, Guobei Mo, Zhiyi Pang, Guangyao Zheng, Zongyuan Wei, Xiang Department of Mechanical and Electrical Engineering WuZhou Vocational College WuZhou543002 China School of Computer Electronics and Information Guangxi University Nanning530004 China School of Data Science and Software Engineering Wuzhou University Wuzhou543002 China

ISBN: (纸本)9781728152097

Poverty has always been one of the most acute social problems in the world. In order to eradicate poverty, the Chinese government has invested a lot of manpower and material resources, and promised to lead all poor areas and poor people into a well-off society by 2020. In this process, the county government as the main battlefield of poverty alleviation, the complex work of poverty alleviation has brought considerable pressure to grass-roots cadres and helping cadres. For the sake of improving the efficiency of support work, we propose a real-time feedback approach based on semantic clustering for poverty alleviation problem, through which we can build a bridge between grass-roots cadres and decision makers. In this method, we first use a fast label extraction method to quickly extract important feature words from the complicated help information. Secondly, we use unsupervised text clustering method to identify important poverty alleviation problems from these feature words, so as to provide a reference for the poverty alleviation workers to carry out their work in an orderly and targeted manner. The experimental results for different regions show that the poverty alleviation problem identified by our proposed method can reflect regional characteristics. © 2019 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

A locality sensitive hashing based collaborative service offloading method in cloud-edge computing 3rd

A locality sensitive hashing based collaborative service off...

引用

3rd International Conference on Cyberspace data and Intelligence, Cyber DI 2019, and the International Conference on Cyber-Living, Cyber-Syndrome, and Cyber-Health, CyberLife 2019

作者： Lin, Wenmin Xu, Xiaolong Huang, Qihe Dai, Fei Qi, Lianyong Li, Weimin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China School of Big Data and Intelligence Engineering Southwest Forestry University Yunnan China School of Information Science and Engineering Qufu Normal University Jining China School of Computer Engineering and Technology Shanghai University Shanghai China

ISBN: (纸本)9789811519246

Benefiting by the big data produced by ever increasing IoT devices, big data services are gaining popular attention in many areas. However, general IoT terminals are unable to execute these services due to the exponentially growing data and the limited computing resources. And a possible solution is to execute the services on remote cloud data centers. However, transferring all data to remote cloud for process brings huge energy consumption and congestion on the backends under high load conditions. The development of edge servers makes it possible to handle some simple tasks on edge servers. Towards this end, it is imperative to design a collaborative service offloading scheme to process data of complex big data services on both edge servers and clouds. In this paper, to protect user’s privacy and quickly decide offloading destination for big data services, we propose a locality sensitive hashing based allocating strategy called Loyal. Loyal relies on E2LSH technique to hash and encrypt the sensitive data information. In addition, Loyal is able to retrieve suitable service that can be offloaded to the ES in a short time. Finally, the performance of Loyal is presented by simulation experiment. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Based Sleeping Cell Detection in Cloud Radio Access Networks

Ensemble Learning Based Sleeping Cell Detection in Cloud Rad...

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Zhao Ming Chuan Sun Xiuhua Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9781728180861

ISBN: (纸本)9781728180878

Sleeping cell problem refers to the degradation or unavailability of network services without triggered alarm, which is one of the most critical issues in current mobile networks. This problem is generally not detectable by the operators but only revealed after users' complaints occur. Therefore, it leads to the degradations of network performance in the service provision in the long run. To address this problem, we introduce a cloud-based sleeping cell detection platform into radio access networks (RANs) to detect the sleeping cells and deal with them automatically. In the cloud RANs (C-RANs), we combine and improve different methods employed in the pioneering studies in this field, and creatively use labeled training data and ensemble learning method for improving the accuracy. Particularly, we utilize expert optimization experience for further improving the detection framework. To evaluate the proposed ensemble learning based sleeping cell detection framework, we use a time-series dataset of Key Performance Indicator (KPI) in a real-world network. Trace-driven evaluation results show that the proposed framework can achieve up to 14.38% and 20.50% improvements compared with two existing schemes, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The mechanism of bone healing after traumatic brain injury

Brain‐X

引用

Brain‐X 2023年第3期1卷

作者： Yuan Xiong Wenbin Zhong Bobin Mi School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singapore Singapore Department of Orthopedics Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan Hubei China Contribution: Data curation Resources Software Supervision Writing - original draft Contribution: Data curation Software Supervision Writing - original draft Contribution: Conceptualization Investigation Supervision Validation Visualization Writing - review & editing

A growing body of evidence suggests that patients who experience traumatic brain injuries (TBIs) exhibit significantly shorter healing periods compared to those with isolated fractures. However, the precise underlying mechanism behind this phenomenon remains unclear. Recent studies have shed light on the potential role of hormonal signals and neural circuits originating in the hypothalamus, which play vital roles in regulating the skeletal system. Despite these advances, there is a lack of comprehensive research summarizing the crucial role of bone healing in TBIs and the underlying mechanisms. This review aimed to explore the underlying mechanisms responsible for the accelerated bone healing observed in TBI patients, with a specific focus on the intricate crosstalk between TBI and bone remodeling. Additionally, we comprehensively discuss and summarize the beneficial effects of TBI on the skeletal system and examine the TBI-induced signaling pathways that result in accelerated fracture healing and bone remodeling. By dissecting these pathways, we aim to identify potential targets for intervention and bone repair promotion.

关键词： bone crosstalk mechanisms TBI

来源：评论

学校读者我要写书评

暂无评论

TCMKG: A Deep Learning Based Traditional Chinese Medicine Knowledge Graph Platform

TCMKG: A Deep Learning Based Traditional Chinese Medicine Kn...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Ziqiang Zheng Yongguo Liu Yun Zhang Chuanbiao Wen Knowledge and Data Engineering Laboratory of Chinese Medicine School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Medical Information Engineering Chengdu University of Traditional Chinese Medicine Chengdu China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

As an effective and novel knowledge management technology, knowledge graph can provide a new way for the inheritance and development of traditional Chinese medicine (TCM). However, the construction of the knowledge graph of TCM is still mainly based on structured data at present. With the accumulation of literatures and electronic medical records, a large amount of knowledge is stored in unstructured texts which urgently needs to be extracted for learning. In this study, we extract TCM core concepts and build ontology layer by analyzing the process of TCM diagnosis and treatment. Then we use deep learning to extract entities and their relations for building TCM knowledge graph from unstructured data. Finally, we build an end-to-end platform TCMKG based on knowledge graph, which can provide functions such as knowledge retrieval, visualization and data management for helping the learning and sharing of TCM knowledge.

关键词： Ontologies data visualization Semantics data mining Medical diagnostic imaging Crawlers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：