检索结果-内蒙古大学图书馆

IEEE International conference on Bioinformatics and Biomedicine (BIBM)

作者： Shasha Liu Yan Li Xiaohu Li Guitao Cao MOE Research Center for Software/Hardware Co-Design Engineering East China Normal University Shanghai China

ISBN: (纸本)9781665429825

Semi-supervised learning has achieved many successes in medical image segmentation since it reduces the costs of manually annotating by leveraging abundant unlabeled data. However, these semi-supervised methods lack attention to ambiguous regions (e.g., some edges or corners around the targets), which may lead to meaningless and unreliable guidance. In this paper, we propose a novel semi-supervised segmentation method called Shape-aware Multi-task Learning (SMTL) to address the above issue. Our multi-task framework includes three tasks namely i) the main task for segmentation ii) one auxiliary task for signed distance regression iii) another auxiliary task for contour detection. The multi-task framework jointly predicts probabilistic segmentation maps, signed distance maps (SDMs) and edge maps to collect complementary information in the existing target label. Specifically, these two auxiliary tasks explicitly enforce shape-priors on the segmentation output to generate more accurate masks. Moreover, we design a region-attention-based adversarial learning strategy that enforces the consistency of two auxiliary tasks prediction distributions on the unlabeled and labeled data to make a meaningful and reliable guidance. We evaluate our SMTL on the datasets of the 2018 Atrial Segmentation Challenge and the 2017 Liver Tumor Segmentation Challenge. The results demonstrate that our SMTL achieves improvements and outperforms the state-of-the-art semi-supervised methods.

关键词： Image segmentation Three-dimensional displays Image edge detection Semisupervised learning Multitasking Reliability engineering Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Performance and Reliability Optimization for High-Density Flash-Based Hybrid Ssds

SSRN

引用

SSRN 2022年

作者： Luo, Longfei Li, Shicheng Lv, Yina Shi, Liang Software/Hardware Co-design Engineering Research Center Ministry of Education The School of Computer Science and Technology East China Normal University Shanghai200062 China

Hybrid SSDs that integrate both large-capacity flash and high-performance flash have become the mainstream of the existing SSD architectures. Two or more flash modes have been supported to satisfy the complex and changeable application requirements, such as single-level-cell (SLC) mode and quad-level-cell (QLC) mode, which can be adaptively switched. However, our empirical studies show that the combination is not well-designed in existing hybrid architectures. We conduct experiments on different scenarios to study the performance and reliability of real hybrid SSDs. Three interesting findings about performance collapse, performance fluctuation, and read disturb of QLC region can be obtained. To solve these problems, this paper proposed HyFlex, including three novel schemes. First, a velocity-based I/O scheduling (VIS) scheme is a novel data placement scheme to avoid performance corrupt. Second, a garbage collection aware capacity tuning (GCT) scheme is a novel flash-mode management scheme to avoid burst performance degradation. Third, a read disturb-aware data migration (DAM) scheme is a novel data migration scheme to alleviate the read disturb of the QLC region. The experiments are conducted on an existing simulator with hybrid SSD extensions. Experimental results show that HyFlex achieves encouraging performance and reliability optimization. © 2022, The Authors. All rights reserved.

关键词： Refuse collection

来源：评论

学校读者我要写书评

暂无评论

FastClothGNN: Optimizing message passing in Graph Neural Networks for accelerating real-time cloth simulation

引用

Graphical Models 2025年 139卷

作者： Yang Zhang Kailuo Yu Xinyu Zhang Software Engineering Institute East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai China Engineering Research Center for Software/Hardware Co-design Technology and Application (MoE) Shanghai China

We present an efficient message aggregation algorithm FastClothGNN for Graph Neural Networks (GNNs) specifically designed for real-time cloth simulation in virtual try-on systems. Our approach reduces computational redundancy by optimizing neighbor sampling and minimizing unnecessary message-passing between cloth and obstacle nodes. This significantly accelerates the real-time performance of cloth simulation, making it ideal for interactive virtual environments. Our experiments demonstrate that our algorithm significantly enhances memory efficiency and improve the performance both in training and in inference in GNNs. This optimization enables our algorithm to be effectively applied to resource-constrained, providing users with more seamless and immersive interactions and thereby increasing the potential for practical real-time applications.

关键词： Cloth simulation Virtual try-on Graph Neural Networks Message passing

来源：评论

学校读者我要写书评

暂无评论

Using surrounding text of formula towards more accurate mathematical information retrieval 33

Using surrounding text of formula towards more accurate math...

引用

33rd International conference on software engineering and Knowledge engineering, SEKE 2021

作者： Chen, Cheng Dai, Yifan Shen, Yuqi Cai, Jinfang Chen, Liangyu Engineering Research Center of Software Hardware Co-Design Technology and Application East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Institute of Vocational and Adult Education East China Normal University Shanghai China

ISBN: (纸本)1891706527

Formula retrieval is an important research topic in Mathematical Information Retrieval (MIR). Most studies have focused on comparing formulae to determine the similarity between mathematical documents. However, two similar formulae may appear in completely different knowledge domains and have different meanings. Based on N-ary Tree-based Formula Embedding Model (NTFEM), we introduce a new hybrid retrieval model combining formula with its surrounding text for more accurate retrieval. Using keywords extraction technology, we extract keywords from text around the formula which can supplement the semantic information of formula. Then we get the representation vectors of keywords by FastText N-gram embedding model, and the representation vectors of formulae by NTFEM. Finally, documents are first sorted according to the similarity of keywords, and then the ranking results are optimized by formula similarity. Experimental results show that the accuracy of top-10 results is at least 20% higher than that of NTFEM and can be 50% in some specific topics. © 2021 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Novel Fault Diagnosis Method Based on Ensemble Feature Selection in The Industrial IoT Scenario

A Novel Fault Diagnosis Method Based on Ensemble Feature Sel...

引用

IEEE International conference on Systems, Man and Cybernetics

作者： Huadong Xu Minghua Zhu Bo Xiao Yunzhou Qiu MOE Engineering Research Center for Software/Hardware Co-Design Technology and Application East China Normal University Shanghai China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665442084

Fault diagnosis as a research hotspot in the field of prognostics and health management (PHM) has attracted the attention of academia and industry. Deep learning is widely used in academia due to its strong self-learning ability. However, as a "black-box" model, the features extracted by deep learning have poor interpretability which can’t be understood by IoT devices. In this paper, we propose a novel fault diagnosis method based on ensemble feature selection. We separately evaluate our method on the four-fault hydraulic components, which are derived from the real-world hydraulic time series data sets. The results show that compared with the deep learning method the proposed method can greatly reduce the complexity of the model without much reduction accuracy. Meanwhile, the balanced ensemble feature selection method we proposed is better than traditional ensemble methods such as union, intersection, and weighted linear aggregation. After testing, the method we proposed can be applied to the industrial IoT fault diagnosis.

关键词： Fault diagnosis Deep learning Industries Time series analysis Hydraulic systems Filtering algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Strategies for Intelligent Registration of IoT Devices

Strategies for Intelligent Registration of IoT Devices

引用

IEEE conference on Wireless communications and Networking

作者： Wenjing Yue Xianzhong Liu School of Software Engineering East China Normal University Shanghai China Software/Hardware Co-design Engineering Research Center MOE Shanghai China

The heterogeneity of the underlying devices introduced significant technical challenges for interoperability in the Internet of Things (IoT), as a rapidly increasing landscape of IoT devices. A unified form of device registration is an important method to shield the heterogeneity. However, most solutions were to focus on the abstraction of device data. Notably, device description information is also necessary. For example, we can deploy the operation temperature of the device in its range to ensure normal operation of the device. However, the device description information registration methods mainly rely on developers entering manually, which causes inefficiency and high information error rate under the cases of many devices. Therefore, it is necessary to develop an excellent strategy for the intelligent registration of IoT *** this paper, we proposed the device intelligent registration strategy by a semantic ontology-based IoT device registration middleware (IDRM): (1) It achieves automatic registration by using automatic recognition and ontology matching of banner information from device application protocol. (2) It realizes registration with converting manual submitted by device vendor users into ontology-based device information. Our experimental results show that IDRM implements Plug-and-Play (PnP) for devices by providing an intelligent registration strategy to shield the heterogeneity of underlying devices.

关键词： Temperature distribution Protocols Semantics Reinforcement learning Manuals Ontologies Information retrieval

来源：评论

学校读者我要写书评

暂无评论

DCFG: Discovering Directional counterFactual Generation for Chest X-rays

DCFG: Discovering Directional CounterFactual Generation for ...

引用

IEEE International conference on Bioinformatics and Biomedicine (BIBM)

作者： Yan Li Shasha Liu Chunwei Wu Xidong Xi Guitao Cao Wenming Cao MOE Research Center for Software/Hardware Co-Design Engineering East China Normal University College of Information Engineering Shenzhen University

ISBN: (纸本)9781665429825

While Deep Neural Networks (DNNs) are achieving state-of-the-art performance on medical domains across a variety of tasks, the need for explainability of model predictions in these high-stakes tasks is still lacking. Current for the explainability in model predictions potentially relies on the supervised counterfactual generation that is time-consuming and direction uncontrollable. Yet, the counterfactual generation needs to be easy to implement and have a controllable direction. In light of this trend, we propose an approach for the unsupervised latent direction search of black-box models that are steerable to the user by enabling the user to effectively explore counterfactual generation in a directional way, without relying on domain- or data-specific assumptions. To identify these explainable directions, we use Principal component Analysis (PCA), a general manifold learning framework to extract low-dimensional subspaces based on a local noise injection of the pre-trained generative model, so that a small perturbation in the subspaces would provide enough change in the resulting data. With experiments on three real-world CXR datasets involving 6 tasks, we find that our approach is capable of learning explainable predictions that discard unrelated confounding factors. Moreover, our method enables practitioners to edit directions to better understand which features are used for predictions.

关键词： Biological system modeling Perturbation methods Neural networks Predictive models Sampling methods Market research Task analysis

来源：评论

学校读者我要写书评

暂无评论

MGC: Multiple-Gray-code for 3D NAND Flash based High-Density SSDs

MGC: Multiple-Gray-Code for 3D NAND Flash based High-Density...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Yina Lv Liang Shi Qiao Li congming Gao Yunpeng Song Longfei Luo Youtao Zhang School of Computer Science and Technology East China Normal University Shanghai China Ministry of Education Software/Hardware Co-Design Engineering Research Center School of Informatics Xiamen University Xiamen China Computer Science Department University of Pittsburgh Pittsburgh USA

QLC (4-bit-per-cell) and more-bit-per-cell 3D NAND flash memories are increasingly adopted in large storage systems. While achieving significant cost reduction, these memories face degraded performance and reliability issues. The industry has adopted two-step programming (TSP), rather than one-step programming, to perform fine-granularity program control and choose gray-code encoding, as well as LDPC (Low-Density Parity-Check code) for error correction. Different flash manufacturers often integrate different gray-codes in their products, which exhibit different performance and reliability characteristics. Unfortunately, a fixed gray-code encoding design lacks the ability to meet the dynamic read and program performance requirements at both application and device *** this paper, we propose MGC, a multiple-gray-code encoding strategy, that adaptively chooses the best gray-code to meet the optimization goals at runtime. In particular, MGC first extracts the performance and reliability requirements based on application-level access patterns and detects the reliability degree of SSD. It then determines the appropriate gray-code to encode the data, either from host/user application or due to garbage collection, before writing the pages to the flash memory. MGC is integrated in FTL (flash translation layer) and enhances the flash controller to enable runtime gray-code arbitration. We evaluate the proposed MGC scheme. The results show that MGC achieves better performance and lifetime guarantee compared with state-of-the-arts and introduces little overhead.

关键词： Performance evaluation Three-dimensional displays Runtime Programming Writing Encoding Parity check codes

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of H.265 Intra-Frame coding Based on FPGA Heterogeneous Platform 22

Parallel Implementation of H.265 Intra-Frame Coding Based on...

引用

22nd IEEE International conference on High Performance computing and communications, 18th IEEE International conference on Smart City and 6th IEEE International conference on Data Science and Systems, HPCC-SmartCity-DSS 2020

作者： Chen, Wenjie He, Qunfang Li, Shen Xiao, Bo Chen, Mingsong Chai, Zhilei East China Normal University National Trusted Embedded Software Engineering Technology Research Center Shanghai China East China Normal University MoE Engineering Research Center for Software/Hardware Co-design Technology Shanghai China Jiangnan University School of IoT Engineering Wuxi China

ISBN: (纸本)9781728176499

The new video coding algorithm H.265 achieved twice compression rate than the prevailing H.264, but the encoding speed is reduced several times, making it difficult for the real-Time applications such as video surveillance and remote meeting. In this paper, we design a parallel intra-frame mode decision architecture based on FPGA to accelerate the coding. We prove that the mode decision problem of multi-level large coding unit of H.265 can be transformed into the accumulation of multiple single-level small coding unit mode decision. Furthermore, we design how mode decision is accelerated by fine-grained parallelism within coding unit, and pipelining among coding units, then implement them on FPGA. The experimental results show that the proposed architecture achieves maximum 93.6\times acceleration compare with the ARM A53 platform, with an insignificant loss of video quality. © 2020 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

CHECKING coNTINUOUS STOCHASTIC LOGIC AGAINST QUANTUM coNTINUOUS-TIME MARKOV CHAINS

arXiv

引用

arXiv 2022年

作者： Mei, Jingyi Xu, Ming Guan, Ji Deng, Yuxin Yu, Nengkun Shanghai Key Lab of Trustworthy Computing East China Normal University China Shanghai Key Lab of Trustworthy Computing & MoE Engineering Research Center of Software/Hardware Co-design Technology and Application East China Normal University China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences China Department of Computer Science Stony Brook University United States

Verifying quantum systems has attracted a lot of interest in the last decades. In this paper, we study the quantitative model-checking of quantum continuous-time Markov chains (quantum CTMCs). The branching-time properties of quantum CTMCs are specified by continuous stochastic logic (CSL), which is famous for verifying real-time systems, including classical CTMCs. The core of checking the CSL formulas lies in tackling multiphase until formulas. We develop an algebraic method using proper projection, matrix exponentiation, and definite integration to symbolically calculate the probability measures of path formulas. Thus the decidability of CSL is established. To be efficient, numerical methods are incorporated to guarantee that the time complexity is polynomial in the encoding size of the input model and linear in the size of the input formula. A running example of Apollonian networks is further provided to demonstrate our method. © 2022, CC BY.

关键词： Stochastic systems

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：