检索结果-内蒙古大学图书馆

Context aware 3d unet for brain tumor segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ahmad, Parvez Qamar, Saqib Shen, Linlin Saeed, Adnan National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China School of Hydropower and Information Technology Huazhong University of Science and Technology Wuhan430074 China

Deep convolutional neural network (CNN) achieves remarkable performance for medical image analysis. UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks, including brain tumor segmentation. The skip connection in the UNet architecture concatenates features from both encoder and decoder paths to extract multi-contexual information from image data. The multi-scaled features play an essential role in brain tumor segmentation. However, the limited use of features can degrade the performance of the UNet approach for segmentation. In this paper, we propose a modified UNet architecture for brain tumor segmentation. In the proposed architecture, we used densely connected blocks in both encoder and decoder paths to extract multi-contexual information from the concept of feature reusability. The proposed residual inception blocks (RIB) are used to extract local and global information by merging features of different kernel sizes. We validate the proposed architecture on the multimodal brain tumor segmentation challenges (BRATS) 2020 testing dataset. The dice (DSC) scores of the whole tumor (WT), tumor core (TC), and enhancement tumor (ET) are 89.12%, 84.74%, and 79.12%, respectively. Our proposed work is in the top ten methods based on the dice scores of the testing dataset. © 2020, CC-BY.

关键词： Tumors

A grouping approach based on non-uniform binary grid partitioning for crowd evacuation simulation

学校读者我要写书评

暂无评论

A grouping approach based on non-uniform binary grid partiti...

作者： Liu, Hong Li, Yan Li, Wenhao Lu, Dianjie Zhang, Guijuan School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China University of South Australia Adelaide Australia

Small social groups based on kinship or friendships are ubiquitous in human crowds. Therefore, the effect of social groups on crowd evacuations and that of crowd evacuations on social groups must be investigated. To simulate the group phenomenon when an emergency occurs, we propose an improved social force model that takes into account the social group relationship among the population, and based on our proposed model, a novel grouping algorithm predicated on non-uniform binary grid partitioning is put forward. The approach initially maps the individuals into the plane space, and then it adopts top-down binary grid partitioning iteratively until the divided grid contains only the individuals with relations;then, the values of the relation and density of the non-empty grid cells are calculated, and the grids are sorted according to these values. After sorting, selecting, merging, and forming the core grids, the other grids are merged to the core grids. We have compared the algorithm with the hierarchical classification algorithm and the grid-based algorithm. The results show that the accuracy, speed, and scalability are all advantages. We also establish a simulation platform to illustrate the proposed grouping algorithm and the improved social force model for crowd evacuation simulation. © 2018 John Wiley & Sons, Ltd.

关键词： Simulation platform

Location Privacy Protection Scheme Based on Location Services 2019

学校读者我要写书评

暂无评论

Location Privacy Protection Scheme Based on Location Service...

Proceedings of the 2019 the 9th International Conference on Communication and Network Security

作者： Chen Yang Wei Yan School of Software Dalian University of Foreign Languages Dalian China School of Computer Science and Technology Harbin Engineering University Harbin China Department of Information Liaoning Police College Dalian China School of Software Dalian University of Technology Dalian China

ISBN: (纸本)9781450376624

Location-based services (LBS) in the mobile internet applications are very important and provide a great convenience. However, at the same time it brings the threat of privacy leak. For location services, a location privacy protection scheme is proposed, which includes location hiding algorithm and query privacy protection algorithm. Q-Tree storage ensures that anonymous location units are as dispersed as possible. The point of interest (POI) with higher query probability is selected as the query content of anonymous location unit, which protects the user's query privacy. At the same time, private information retrieval technology (PIR) is used to provide users with higher privacy and security protection. Finally, the effectiveness of the scheme is proved by privacy analysis and experimental results.

关键词： K-anonymity Privacy Protection Location Service Q-Tree PIR

Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kong, Zhe Zhang, Wentian Liu, Feng Luo, Wenhan Liu, Haozhe Shen, Linlin Ramachandra, Raghavendra College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China Norwegian University of Science and Technology Gjøvik2818 Norway

Biometric systems are vulnerable to Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for the generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD. During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing generative loss. While De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. The source code of the proposed technique is available at https://***/kongzhecn/dfdm. Copyright © 2021, The Authors. All rights reserved.

关键词： Supervised learning

Architecture information communication in two OSS projects: The why, who, when, and what

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bi, Tingting Ding, Wei Liang, Peng Tang, Antony School of Computer Science Wuhan University Wuhan430072 China Faculty of Information and Technology Monash University MelbourneVIC3166 Australia Faculty of Science Engineering and Technology Swinburne University of Technology MelbourneVIC3122 Australia Software and Services Research Group Vrije Universiteit Amsterdam Amsterdam1101 Netherlands Key Laboratory of Earthquake Geodesy Institute of Seismology China Earthquake Administration China

Architecture information is vital for Open Source software (OSS) development, and mailing list is one of the widely used channels for developers to share and communicate architecture information. This work investigates the nature of architecture information communication (i.e., why, who, when, and what) by OSS developers via developer mailing lists. We employed a multiple case study approach to extract and analyze the architecture information communication from the developer mailing lists of two OSS projects, ArgoUML and Hibernate, during their development life-cycle of over 18 years. Our main findings are: (a) architecture negotiation and interpretation are the two main reasons (i.e., why) of architecture communication;(b) the amount of architecture information communicated in developer mailing lists decreases after the first stable release (i.e., when);(c) architecture communications centered around a few core developers (i.e., who);(d) and the most frequently communicated architecture elements (i.e., what) are Architecture Rationale and Architecture Model. There are a few similarities of architecture communication between the two OSS projects. Such similarities point to how OSS developers naturally gravitate towards the four aspects of architecture communication in OSS development. © 2021, CC BY.

关键词： Open source software

RF-WTI: Wood Types Identification based on Commodity RFID Devices

学校读者我要写书评

暂无评论

RF-WTI: Wood Types Identification based on Commodity RFID De...

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Xiangmao Chang Xianghui Zhang Muhammad Waqas Isa Weiwei Wu Yan Li Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Computer Science and Engeneering Southeast University Nanjing China Information and Engineering Nanjing University of Finance and Economics Nanjing China

ISBN: (数字)9781728199160

ISBN: (纸本)9781728192369

The identification of wood is an important problem both in industrial manufacturing and in people's daily life. Traditional methods based on experts are laborious. New technologies based on computer visions rely on high-quality cross section images. In this paper, we take the first attempt to identify the wood type based on commodity RFID devices. A system named RF-WTI is proposed. The main idea of RF-WTI is that different wood types result in different signal changes when RF signals pass through the wood. Specifically, after collecting the changes of Received Signal Strength (RSS) and phase when RFID signals pass through the wood, a feature that is unique for the wood is derived. Then RF-WTI applies a Bayesian neural network to identify wood types. Experimental results show that RF-WTI achieves 92.33% average accuracy for identifying 12 different types of wood.

关键词： RF signals Neural networks Bayes methods Sensors Manufacturing Object recognition Radiofrequency identification

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Holste, Gregory Zhou, Yiliang Wang, Song Jaiswal, Ajay Lin, Mingquan Zhuge, Sherry Yang, Yuzhe Kim, Dongkyun Nguyen-Mau, Trong-Hieu Tran, Minh-Triet Jeong, Jaehyup Park, Wongi Ryu, Jongbin Hong, Feng Verma, Arsh Yamagishi, Yosuke Kim, Changhyun Seo, Hyeryeong Kang, Myungjoo Celi, Leo Anthony Lu, Zhiyong Summers, Ronald M. Shih, George Wang, Zhangyang Peng, Yifan Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Department of Population Health Sciences Weill Cornell Medicine New YorkNY10065 United States School of Information Systems Carnegie Mellon University PittsburghPA15213 United States Department of Electrical Engineering and Computer Science Massachussetts Institute of Technology CambridgeMA02139 United States School of Computer Science Carnegie Mellon University PittsburghPA15213 United States University of Science VNU-HCM Ho Chi Minh City70000 Viet Nam KT Research & Development Center KT Corporation Seoul06763 Korea Republic of Department of Software and Computer Engineering Ajou University Suwon16499 Korea Republic of Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China Wadhwani Institute for Artificial Intelligence Mumbai400079 India Division of Radiology and Biomedical Engineering Graduate School of Medicine The University of Tokyo Tokyo113-0033 Japan BioMedical AI Team AIX Future R&D Center SK Telecom Seoul04539 Korea Republic of Seoul National University Seoul02504 Korea Republic of Department of Mathematical Sciences Seoul National University Seoul02504 Korea Republic of Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA02139 United States Division of Pulmonary Critical Care and Sleep Medicine Beth Israel Deaconess Medical Center BostonMA02215 United States Department of Biostatistics Harvard T.H. Chan School of Public Health BostonMA02115 United States National Center for Biotechnology Information National Library of Medicine BethesdaMD20894 United States Clinical Center National Institutes of Health BethesdaMD20892 United States Department of Radiology Weill Cornell Medicine New YorkNY10065 United States

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" – there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification. © 2023, CC BY-NC-SA.

关键词： computer aided diagnosis

Reducing Delay Penalty of Multiple Concurrent software Projects based on Overtime Planning

学校读者我要写书评

暂无评论

Reducing Delay Penalty of Multiple Concurrent Software Proje...

IEEE/ACM International Conference on Automated software engineering - Workshops (ASE Workshops)

作者： Wei Zhang Yun Yang Xiao Liu School of Computer Science and Technology School of Software Anhui University East China University of Technology Hefei China Nanchang China School of Software and Electrical Engineering School of Computer Science and Technology Swinburne University of Technology Anhui University Melbourne Australia Hefei China School of Information Technology Deakin University Geelong Australia

ISBN: (数字)9781450381284

ISBN: (纸本)9781728172958

For software projects, significant delays can result in heavy penalty which may end up with project costs exceeding their budgets. As a consequence, employees, i.e., software developers, are often requested to work overtime in order to reduce or even eliminate the delays. By doing so, overtime payment may often be introduced and excessive overtime payment can also easily swallow company profit which may even lead to serious overdraft Hence software manager needs to decide who should work overtime and how much overtime they would take in order to control the cost. This means that it is important to investigate how to reduce or eliminate the overall penalties by taking multiple concurrent software projects into account. In practice, there is normally a number of available employees with same or similar skills and domain knowledge from other similar concurrent projects. In addition, they have different skill *** rescheduling those employees with appropriate overtime may be feasible to find a solution which can reduce or eliminate the penalties of delayed software projects. Since this kind of scheduling is a typical NP-hard problem, a novel generic strategy is proposed to help select appropriate employees and determine how much overtime to be assigned to the delayed activities. The new strategy combines the features of Ant Colony Optimization algorithm and Tabu strategy and includes four rules to reduce the search space. A set of comprehensive generic experiments is carried out in order to evaluate the performance of the proposed strategy in a general manner. In addition, three real world software project instances are also utilized to evaluate our strategy The results demonstrate that our strategy is effective which outperforms the other representative strategies which are applied successfully at software project scheduling.

关键词： software engineering Germanium Conferences 6G mobile communication

Feature Location Benchmark for Decomposing and Reusing Android Apps

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tang, Yutian Zhou, Hao Xu, Zhou Luo, Xiapu Cai, Yan Zhang, Tao Department of Computing Hong Kong Polytechnic University Hong Kong School of Big Data and Software Engineering Chongqing University China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Faculty of Information Technology Macau University of Science and Technology China

software reuse enables developers to reuse architecture, programs and other software artifacts. Realizing a systematical reuse in software brings a large amount of benefits for stakeholders, including lower maintenance efforts, lower development costs, and time to market. Unfortunately, currently implementing a framework for large-scale software reuse in Android apps is still a huge problem, regarding the complexity of the task and lacking of practical technical support from either tools or domain experts. Therefore, proposing a feature location benchmark for apps will help developers either optimize their feature location techniques or reuse the assets created in the benchmark for reusing. In this paper, we release a feature location benchmark, which can be used for those developers, who intend to compose software product lines (SPL) and release reuse in apps. The benchmark not only contributes to the research community for reuse research, but also helps participants in industry for optimizing their architecture and enhancing modularity. In addition, we also develop an Android Studio plugin named caIDE for developers to view and operate on the benchmark. Copyright © 2020, The Authors. All rights reserved.

关键词： computer software reusability