检索结果-内蒙古大学图书馆

Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation

Knowledge-Based Systems 2025年 324卷

作者： Qiangguo Jin Hui Cui Junbo Wang Changming Sun Yimiao He Ping Xuan Linlin Wang Cong Cong Leyi Wei Ran Su School of Software Northwestern Polytechnical University Shaanxi China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China Department of Computer Science and Information Technology La Trobe University Melbourne Australia CSIRO Data61 Sydney Australia Department of Computer Science School of Engineering Shantou University Guangdong China Shandong Cancer Hospital and Institute Shandong First Medical University and Shandong Academy of Medical Sciences Shandong China Australian Institute of Health Innovation (AIHI) Macquarie University Australia School of Software Shandong University Shandong China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University Macao Special Administrative Region of China School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China

Semi-supervised learning (SSL) has attracted considerable attention in medical image processing. The latest SSL methods use a combination of consistency regularization and pseudo-labeling to achieve remarkable success. However, most existing SSL studies focus on segmenting large organs, neglecting the challenging scenarios where there are numerous tumors or tumors of small volume. Furthermore, the extensive capabilities of data augmentation strategies, particularly in the context of both labeled and unlabeled data, have yet to be thoroughly investigated. To tackle these challenges, we introduce a straightforward yet effective approach, termed iterative pseudo-labeling based adaptive copy-paste supervision (IPA-CP), for tumor segmentation in CT scans. IPA-CP incorporates a two-way uncertainty based adaptive augmentation mechanism, aiming to inject tumor uncertainties present in the mean teacher architecture into adaptive augmentation. Additionally, IPA-CP employs an iterative pseudo-label transition strategy to generate more robust and informative pseudo labels for the unlabeled samples. Extensive experiments on both in-house and public datasets show that our framework outperforms state-of-the-art SSL methods in medical image segmentation. Ablation study results demonstrate the effectiveness of our technical contributions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistic Chinese New Word Recognition by Combing Supervised and Unsupervised Learning

Statistic Chinese New Word Recognition by Combing Supervised...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Fei Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

This paper proposed a method using statistic methods with untagged and tagged data to detect Chinese new words. Chinese sentences have no blank to segment the characters to build words. So Chinese word segmentation has been a hot research field for a long time. Chinese word segmentation needs tagged data and dictionary. The dictionary should always be updated, thus ththereere will be less out of vocabulary words in the model. It will cost a lot of time to collect new words manually, and it has many limitations such as the mount of the words. Term frequency, pointwise mutual information and entropy are applied to detect new Chinese new words. They are based on the untagged data by statistic methods. Hidden markov model is used to segment Chinese sentences and detect new words. Hidden markov model need tagged data to train the model. Hidden markov model can learn the probability of a character's position of a word such as begin, middle, end or single. We combine these two methods: one method to use the untagged data and an other to use the tagged data. The untagged data has many resources and it does't cost any human operation, but it is not so accurate. The tagged data is tagged by human, so it is accurate and reliable, but it takes a lot time to tag it, only a few of data is free to use to train the method. In short, we try to use tagged data and untagged data at the same time by combing pointwise mutual information, entropy and hidden markov model. The experiment shows the new word candidates number is reduced from 306% to 173% compared to the training dictionary number, but the real words number is only reduced 4%.

关键词： Entropy Hidden Markov models Mutual information Dictionaries Big Data Frequency measurement Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

STATISTICAL FUSION-BASED TRANSFER LEARNING FOR HYPERSPECTRAL IMAGE CLASSIFICATION

STATISTICAL FUSION-BASED TRANSFER LEARNING FOR HYPERSPECTRAL...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Xiaomei Liu Sen Jia Meng Xu Jiasong Zhu College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Hyperspectral images (HSIs) has practical applications in many fields. In practical scenarios, machine learning often fails to handle changes between training (source) and testing (target) input distributions due to domain shifts. A big challenge in hyperspectral image classification is the small size of labeled data for classifier learning. We always face the situation that an HSI scene is not labeled all or with very limited number of labeled pixels, but we have sufficient labeled pixels in another HSI scene with similar land cover classes. In this paper, we propose a simple and effective method for domain adaptation called statistical fusion to minimize domain shifts by aligning the second-order and fourth-order statistics of source and target distributions. After two hyperspectral scenes are transformed into the similar property-space, any traditional HSI classification approaches can be used, and experimental results have validated the generalization of the proposed method.

关键词： Training Hyperspectral imaging Predictive models Testing Task analysis Correlation

来源：评论

学校读者我要写书评

暂无评论

Using MTD and SDN-based Honeypots to Defend DDoS Attacks in IoT

Using MTD and SDN-based Honeypots to Defend DDoS Attacks in ...

引用

Computing, Communications and Applications Conference (ComComAp)

作者： Xupeng Luo Qiao Yan Mingde Wang Wenyao Huang College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728119731

ISBN: (纸本)9781728119748

With the rapid development of Internet of Things (IoT), distributed denial of service (DDoS) attacks become the important security threat of the IoT. Characteristics of IoT, such as large quantities and simple function, which have easily caused the IoT devices or servers to be attacked and be turned into botnets for launching DDoS attacks. In this paper, we use software-defined networking (SDN) to develop moving target defense (MTD) architecture that increases uncertainty because of ever changing attack surface. In addition, we deploy SDN-based honeypots to mimic IoT devices, luring attackers and malwares. Finally, experimental results show that combination of MTD and SDN-based honeypots can effectively hide network asset from scanner and defend against DDoS attacks in IoT.

关键词： computer crime IP networks Internet of Things Servers Malware Botnet

来源：评论

学校读者我要写书评

暂无评论

Corrections to “A Human-in-the-Loop Probabilistic CNN-Fuzzy Logic Framework for Accident Prediction in Vehicular Networks” [Jul 21 15496-15503]

引用

IEEE Sensors Journal 2022年第10期22卷 10031-10031页

作者： Muhammad Usman Anil Carie Chettupally Bhaskar Marapelli Hayat Dino Bedru Kamanashish Biswas Faculty of Computing Engineering and Science University of South Wales Pontypridd U.K. School of Computer Science VIT-AP Amaravathi India Software Engineering Department College of Computing and Informatics Wolkite University Wolkite Ethiopia School of Software Dalian University of Technology Dalian China Department of Computer Science Engineering Central South University Changsha China Peter Faber Business School Australian Catholic University Brisbane QLD Australia

In the above article [1] , the surname Chettupally of the author Anil Carie Chettupally was inadvertently omitted from the authors list when the article was originally published.

关键词： Probabilistic logic Deep learning Accidents Convolutional neural networks Fuzzy logic Human in the loop Accidents

来源：评论

学校读者我要写书评

暂无评论

Escape from Escape Analysis of Golang

Escape from Escape Analysis of Golang

引用

IEEE/ACM International Conference on software engineering: software engineering in Practice Track (ICSE-SEIP)

作者： Cong Wang Mingrui Zhang Yu Jiang Huafeng Zhang Zhenchang Xing Ming Gu KLISS BNRist School of Software Tsinghua University Beijing China Compiler and Programming Language Lab Huawei Technologies Hangzhou China College of Engineering and Computer Science ANU Canberra Australia

ISBN: (数字)9781450371230

ISBN: (纸本)9781728165240

Escape analysis is widely used to determine the scope of variables, and is an effective way to optimize memory usage. However, the escape analysis algorithm can hardly reach 100% accurate, mistakes of which can lead to a waste of heap memory. It is challenging to ensure the correctness of programs for memory *** this paper, we propose an escape analysis optimization approach for Go programming language (Golang), aiming to save heap memory usage of programs. First, we compile the source code to capture information of escaped variables. Then, we change the code so that some of these variables can bypass Golang's escape analysis mechanism, thereby saving heap memory usage and reducing the pressure of memory garbage collection. Next, we present a verification method to validate the correctness of programs, and evaluate the effect of memory optimization. We implement the approach to an automatic tool and make it open-source 1 . For evaluation, we apply our approach to 10 open-source projects. For the optimized Golang code, the heap allocation is reduced by 8.88% in average, and the heap usage is reduced by 8.78% in average. Time consumption is reduced by 9.48% in average, while the cumulative time of GC pause is reduced by 5.64% in average. We also apply our approach to 16 industrial projects in Bytedance Technology. Our approach successfully finds 452 optimized cases which are confirmed by developers.

关键词： Optimization Memory management Heuristic algorithms computer languages Open source software Tools software engineering

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Parameters for Post-Processing Consumer Photos via Machine Learning

Optimizing the Parameters for Post-Processing Consumer Photo...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Linlin Bie Xu Wang Jari Korhonen College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Photo sharing in social media is a part of everyday life for many, as inexpensive cameras integrated in smartphones are widely available. Unfortunately, low cost consumer devices are often prone to capture artifacts, and this is why there is a growing demand for automatic post-processing to enhance the image quality. Due to the wide range of distortions in non-professional photography, automatic selection of the post-processing methods and parameters is a challenging problem. In this paper, we present a subjective study based on rank-ordering method, comparing the subjective preferences between photos processed with different parameters for image sharpening and denoising. The subjective results are used as a basis to derive the ground truth values for the post-processing parameters for different photos. Then, we apply a pre-trained convolutional neural network (CNN) to extract a set of features from photos, used as input to a regression model to predict the optimal post-processing parameters. Test results show that the learning-based approach can predict post-processing parameters with a satisfactory accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Left Ventricle Motion Estimation Based on Unsupervised Recurrent Neural Network

Left Ventricle Motion Estimation Based on Unsupervised Recur...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Ziyu Gan Jiangyue Tang Xuan Yang College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Left ventricle (LV) motion estimation plays an essential role in understanding the pathology of heart diseases and diagnosing and treatment of heart diseases. In this paper, we propose a recurrent registration network (R~2Net) with convolutional neural networks (CNNs) to estimate the motion of left ventricle using cardiac MR image sequences. Our R~2Net network is composed of a CNN, a function compositor, and a spatial transformer. The CNN is an asymmetric U-net architecture, which evaluates the correspondence between two images and outputs the sparse deformation field between two input images. Consecutive images are input to the CNN, and consecutive deformation fields are estimated. The compositor composites two deformation fields at adjacent time points together to generate a composited deformation field. The transformer warps the cardiac MR image at ED using the composited deformation field, and generates a deformed image. By composting successive deformation fields one-by-one, the final deformation field between ED and ES is estimated. We define a loss function without ground truth and train the R~2Net in an unsupervised way. Moreover, the bending energy is introduced to the loss function to impose the deformation field smooth and topology-preserving. Our method is evaluated using public datasets. Experimental results show that our method outperforms the state-of-the-art researches in respect of several evaluation metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Base Station Positioning in Single-Tiered Wireless Sensor Networks

Base Station Positioning in Single-Tiered Wireless Sensor Ne...

引用

IEEE International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)

作者： Xinchen Li Huan Cai Gang Liu Kezhong Lu College of Computer Science & Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

In wireless sensor networks, sensor nodes collect data from the surrounding environment and transfer it to the base station. If a sensor node cannot communicate with the base station directly, it needs to select one of the senor nodes that it can communicate with and transfer the data to it. The above process will go on until the data arrive at the base station. It may cause too many relays during the process in which the data are transferred to the base station. Some nodes may quickly run out of energy and cause the entire wireless network to fail. We build a breadth-first search spanning tree which is rooted in base station according to the connected relation between the sensor nodes and the base station. When sensor nodes transfer the data to the base station, the data follow the path between the node and root in the spanning tree towards the base station. This algorithm guarantees the number of relays in the process and the total energy consumption of the wireless sensor network are the least. Thus the choice of the base station position is vital to the energy consumption of the whole wireless sensor network. This paper proposes an algorithm for the base station placement that finds the optimal base station position by using computation geometry according to the relative relation between the senor nodes. In contrast to the grid computing we are familiar, this algorithm greatly reduces the computing time required by finding the optimal position of base station.

关键词： Base stations Energy consumption Layout Wireless sensor networks Relays Approximation algorithms Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Parallel Multi-Core GZIP Compressor in HDFS

FPGA-Based Parallel Multi-Core GZIP Compressor in HDFS

引用

IEEE International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)

作者： Haoxin Luo Ye Cai Qiuming Luo Rui Mao College of Computer Science & Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

With the development of Big Data, data storage has been exposed to more challenges. Data compression which can save both storage and network bandwidth, is a very important technology to deal with the challenges. In this paper, we present an end-to-end, complete, high-throughput parallel multi-core GZIP compressor in FPGA for HDFS. The GZIP compressor is designed by the scalable architecture, which supports to increase throughput by expanding multiple compression cores based on systolic array architecture. We implemented and evaluated the hardware compressor in Alpha Data Adm-Pcie-KU3 FPGA board, utilizing RIFFA for data transfers over PCI Express. According to the evaluation results, up to 16-cores compressor can be implemented and the peak compression throughput exceeds 1.1 GB/s. It is 70X speedup compared with the software compression solution. When we load the hardware compressor into HDFS, the performance of HDFS is twice as much as that without loading the compressor.

关键词： Throughput Hardware Field programmable gate arrays software Dictionaries Arrays

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：