检索结果-内蒙古大学图书馆

作者： Zhang, Jie Feng, Junhong Yang, Xiani Liu, Jianming School of Computer Science and Engineering Guangxi Colleges Universities Key Lab of Complex System Optimization and Big Data Processing Yulin Normal University Guangxi Yulin537000 China Business School Yulin Normal University Guangxi Yulin537000 China

There are a wide range of genes in single-cell data, but some are not beneficial to classification. In order to eliminate these redundant genes and select beneficial genes, this study first utilises the information gain (IG) to select some genes coarsely, then uses the modified fruit fly optimisation algorithm (FOA) to choose the relevant genes refinedly from the subsets after performing IG. The proposed algorithm makes full use of respective advantages of the IG and FOA, and is abbreviated as IGFOA. The proposed algorithm is implemented on multiple scRNA-seq datasets with various numbers of cells and genes, and the obtained results validate that the IGFOA can select effectively some superior genes and acquire good classification performance. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Efact: An External Function Auto-Completion Tool to Strengthen the Static Binary Lifting

SSRN

引用

SSRN 2023年

作者： Zhang, Yilei Liao, Haoyu Wang, Zekun Huang, Bo Guo, Jianmei School of Data Science and Engineering East China Normal University Shanghai200062 China

Static binary lifting is essential in binary rewriting frameworks. Existing tools overlook the impact of External Function Completion (EXFC) in static binary lifting. EXFC recovers the prototypes of External Functions (EXFs, functions defined in standard shared libraries) using only the function symbols available. Incorrect EXFC can misinterpret the source binary, or cause memory overflows in static binary translation, which eventually results in program crashes. Notably, existing tools struggle to recover the prototypes of mangled EXFs originating from binaries compiled from C++. Moreover, they require time-consuming manual processing to support new libraries. This paper presents EFACT, an External Function Auto-Completion Tool for static binary lifting. Our EXF recovery algorithm better recovers the prototypes of mangled EXFs, particularly addressing the template specialization mechanism in C++. EFACT is designed as a lightweight plugin to strengthen other static binary rewriting frameworks in EXFC. Our evaluation shows that EFACT outperforms RetDec and McSema in mangled EXF recovery by 96.4% and 97.3% on SPEC CPU® 2017. Furthermore, we delve deeper into static binary translation and address several cross-ISA EXFC problems. When integrated with McSema, EFACT correctly translates 36.7% more benchmarks from x86-64 to x86-64 and 93.6% more from x86-64 to AArch64 than McSema alone on EEMBC. © 2023, The Authors. All rights reserved.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Apara: Workload-aware data partition and replication for parallel databases 3rd

Apara: Workload-aware data partition and replication for par...

引用

3rd APWeb and WAIM Joint Conference on Web and Big data, APWeb-WAIM 2019

作者： Zhang, Xiaolei Zhang, Chunxi Li, Yuming Zhang, Rong Zhou, Aoying International Research Center of Trustworthy Software Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China School of Data Science and Engineering East China Normal University Shanghai China

ISBN: (纸本)9783030260743

data partition and replication mechanisms directly determine query execution patterns in parallel database systems, which have a great impact on system performance. Recently, there have been some workload-aware data storage techniques, but they suffer from problems of narrow support to complex workloads or large requirements for storage. In order to enable the support for complex analytical workloads over massive distributed database systems, we design and implement a workload-aware data partition and replication tool, called Apara. We design two heuristic algorithms and define two cost models for effective data partition calculation and efficient replication usages. We run a set of experiments to compare and demonstrate the performance between Apara and the other representative work. The results show that Apara consistently outperforms the primary solutions on TPC-H workloads. © 2019, Springer Nature Switzerland AG.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Application of Image Recognition for On-board Sailor Behavior Based on Broad Learning System 4

Application of Image Recognition for On-board Sailor Behavio...

引用

4th International Conference on data-Driven Optimization of Complex Systems, DOCS 2022

作者： Liu, Wenting Zuo, Yi Li, Tieshan Philip Chen, C.L. Dalian Maritime University Collaborative Innovation Center of Maritime Big Data & Artificial General Intelligence Navigation College Dalian China University of Electronic Science and Technology of China School of Automatic Engineering Chengdu China

ISBN: (数字)9781665459822

ISBN: (纸本)9781665459822

Based on broad learning system (BLS), this paper monitors and identifies the behavior of crew members on ships. The main recognition scenarios include both of on deck and in the cabin, and the main recognition tasks include crew tracking and identification. In this paper, the video data is divided into frames and images are segmented. In the preprocessing of images, the filter is used to enhance the information and reduce the noise of the images. Finally, the recognition model is established by the BLS. In the experiment, we use BP neural network (BPNN) and support vector machine (SVM) as comparisons. The proposed method in this paper has achieved the best results in terms of recognition accuracy and training time. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

EDSL: An encoder-decoder architecture with symbol-level features for printed mathematical expression recognition

arXiv

引用

arXiv 2020年

作者： Fu, Yingnan Gao, Ming Liu, Tingting Zhou, Aoying School of Data Science and Engineering East China Normal University Shanghai200062 China

Printed Mathematical expression recognition (PMER) aims to transcribe a printed mathematical expression image into a structural expression, such as LaTeX expression. It is a crucial task for many applications, including automatic question recommendation, automatic problem solving and analysis of the students, etc. Currently, the mainstream solutions rely on solving image captioning tasks, all addressing image summarization. As such, these methods can be suboptimal for solving MER problem. In this paper, we propose a new method named EDSL, shorted for encoder-decoder with symbol-level features, to identify the printed mathematical expressions from images. The symbol-level image encoder of EDSL consists of segmentation module and reconstruction module. By performing segmentation module, we identify all the symbols and their spatial information from images in an unsupervised manner. We then design a novel reconstruction module to recover the symbol dependencies after symbol segmentation. Especially, we employ a position correction attention mechanism to capture the spatial relationships between symbols. To alleviate the negative impact from long output, we apply the transformer model for transcribing the encoded image into the sequential and structural output. We conduct extensive experiments on two real datasets to verify the effectiveness and rationality of our proposed EDSL method. The experimental results have illustrated that EDSL has achieved 92.7% and 89.0% in evaluation metric Match, which are 3.47% and 4.04% higher than the state-of-the-art method. Our code and datasets are available at https://***/abcAnonymous/EDSL. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Approximated orthonormal normalisation in training neural networks

arXiv

引用

arXiv 2019年

作者： Zhang, Guoqiang Niwa, Kenta Kleijn, W.B. School of Electrical and Data Engineering University of Technology Sydney Australia Corporation School of Engineering and Computer Science Victoria University of Wellington

Generalisation of a deep neural network (DNN) is one major concern when employing the deep learning approach for solving practical problems. In this paper we propose a new technique, named approximated orthonormal normalisation (AON), to improve the generalisation capacity of a DNN model. Considering a weight matrix W from a particular neural layer in the model, our objective is to design a function h(W) such that its row vectors are approximately orthogonal to each other while allowing the DNN model to fit the training data sufficiently accurate. By doing so, it would avoid co-adaptation among neurons of the same layer to be able to improve network-generalisation capacity. Specifically, at each iteration, we first approximate (WW )~? using its Taylor expansion before multiplying the matrix W. After that, the matrix product is then normalised by applying the spectral normalisation (SN) technique to obtain h(W). Conceptually speaking, AON is designed to turn orthonormal regularisation into orthonormal normalisation to avoid manual balancing the original and penalty functions. Experimental results show that AON yields promising validation performance compared to orthonormal regularisation. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Representation Learning for Quantum Cross-Platform Verification

引用

Physical Review Letters 2024年第13期133卷 130601页

作者： Yang Qian Yuxuan Du Zhenliang He Min-Hsiu Hsieh Dacheng Tao School of Computer Science Faculty of Engineering College of Computing and Data Science JD Explore Academy Beijing 101111 China *** Beijing 101111 China Taipei 114699 Taiwan

Cross-platform verification, a critical undertaking in the realm of early-stage quantum computing, endeavors to characterize the similarity of two imperfect quantum devices executing identical algorithms, utilizing minimal measurements. While the random measurement approach has been instrumental in this context, the quasiexponential computational demand with increasing qubit count hurdles its feasibility in large-qubit scenarios. To bridge this knowledge gap, here we introduce an innovative multimodal learning approach, recognizing that the formalism of data in this task embodies two distinct modalities: measurement outcomes and classical description of compiled circuits on explored quantum devices, both containing unique information about the quantum devices. Building upon this insight, we devise a multimodal neural network to independently extract knowledge from these modalities, followed by a fusion operation to create a comprehensive data representation. The learned representation can effectively characterize the similarity between the explored quantum devices when executing new quantum algorithms not present in the training data. We evaluate our proposal on platforms featuring diverse noise models, encompassing system sizes up to 50 qubits. The achieved results demonstrate an improvement of 3 orders of magnitude in prediction accuracy compared to the random measurements and offer compelling evidence of the complementary roles played by each modality in cross-platform verification. These findings pave the way for harnessing the power of multimodal learning to overcome challenges in wider quantum system learning tasks.

关键词： Artificial neural networks Deep learning Quantum benchmarking Quantum computation

来源：评论

学校读者我要写书评

暂无评论

Targeted Detection of Anomalous Merchants on Integrated Payment Platforms via Multifaceted Transaction Representation Learning

Targeted Detection of Anomalous Merchants on Integrated Paym...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Lu, Guanyu Lin, Xiang Pavlovski, Martin Zhang, Xinyu Zhou, Fang East China Normal University School of Data Science and Engineering Shanghai China Temple University PhiladelphiaPA United States Shanghai Shouqianba Internet Technology Co. Ltd. Shanghai China

ISBN: (纸本)9798350362480

Integrated payment platforms have significantly improved the convenience of daily life, yet they also present a fertile ground for fraudulent behavior. This paper focuses on the detection of anomalous merchants at the transaction level on such platforms, as locating specific anomalous patterns at such a granular level aids in taking corresponding security measures. However, in an integrated payment scenario, a limited number of imprecise labels are accessed at the merchant level rather than the transaction level, thus rendering transaction-level anomaly detection quite difficult. Meanwhile, the collected data comprises not only normal merchants and target anomalies (of interest) but also non-target anomalies (of lesser interest). To address these challenges, we adopt a two-step approach. First, we cluster merchants exhibiting similar behaviors and filter out potential non-target anomalies to better understand the transactional patterns among normal merchants. Then, we learn transaction representations encapsulated within hyperspheres, considering three key aspects: transaction context, historical information, and merchant information;and leverage such representations to determine anomaly scores for individual transactions. Real-world transactions from an integrated payment platform were used in the experiments. The results demonstrate that our model outperforms several state-of-the-art baselines, with an average AUPRC improvement of 10.5%-11.6%, 16.5%-16.7%, and 3.7%-5.4% in the three discovered merchant clusters. © 2024 IEEE.

关键词： anomaly detection integrated payment platform transaction representation learning

来源：评论

学校读者我要写书评

暂无评论

dFC: A data-density-aware Fuzzy Clustering Algorithm for Imbalanced Biomedical datasets

dFC: A Data-density-aware Fuzzy Clustering Algorithm for Imb...

引用

2017 IEEE 8th International Conference on Software engineering and Service science

作者： Jin Wang Lei You Wenjie Fan Fang Miao Tao Yang School of Information Science & Engineering Chengdu University Institute of Big Data Chengdu University

Imbalanced data are common in biomedical areas but pose a computational challenge for clustering methods. This paper investigates the effects of imbalanced datasets using fuzzy clustering, and proposes a data-density-aware fuzzy clustering method(d FC) to solve this problem. Specifically, a dataset is segmented into different areas with similar local density, and then a novel fuzzy clustering algorithm was implemented based on the initial partition. Our new method was evaluated using real and simulated imbalanced datasets. The experimental results show that our method can better classify imbalanced datasets with less iterations and computational time compared to FCM especially for large datasets.

关键词： FCM distribution-density imbalanced dataset

来源：评论

学校读者我要写书评

暂无评论

A Transformer-based Long-term Prediction Model for Charging Pile Power Consumption 6

A Transformer-based Long-term Prediction Model for Charging ...

引用

6th International Conference on Power and Energy Technology, ICPET 2024

作者： Zhu, Mingzhao Tao, Haicheng Ding, Da Li, Huijia Cao, Jie College of Information Engineering Nanjing University Of Finance & Economics Nanjing China College of Computer and Information Hohai University Nanjing China School of Statistics and Data Science Nankai University Tianjin China School of Management Hefei University of Technology Hefei China

ISBN: (纸本)9798350375855

The distribution, quantity, and charging speed of charging piles have a direct impact on the popularity of electric vehicles, which has been a topic of widespread concern in recent years. By predicting the power consumption of charging piles, the operation and energy utilisation efficiency of charging piles can be optimised, thereby aiding in the layout and management of charging infrastructure. Consequently, this paper concentrates on the long-term sequence prediction of charging pile power consumption. The field of time series prediction has witnessed considerable advancement with the advent of deep learning. However, the majority of studies have concentrated on the analysis of complete data, with intermittent time series prediction receiving comparatively limited attention. In order to enhance the prediction of the power consumption of charging piles with intermittent characteristics, a novel model is developed. This model is based on the Transformer architecture and employs separate inputs for position and value during the input process. Within the model, modules with time segmentation and fusion are selected to replace the attention mechanism of general Transformer-like models. Finally, Split-Attention with mixed values and positions is employed, and information fusion is performed at the conclusion of the model. The experiments are conducted on a real dataset, utilising common evaluation metrics for time series prediction and metrics that have been demonstrated to be more suitable for intermittent time series. The experimental results demonstrate that the model is more effective than several commonly used time series prediction baselines in predicting the power consumption of charging piles. © 2024 IEEE.

关键词： Prediction models

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：