检索结果-内蒙古大学图书馆

Applying Hybrid Clustering in Pulsar Candidate Sifting with Multi-modality for FAST Survey

Research in Astronomy and Astrophysics 2024年第3期24卷 283-296页

作者： Zi-Yi You Yun-Rong Pan Zhi Ma Li Zhang Shuo Xiao Dan-Dan Zhang Shi-Jun Dang Ru-Shuang Zhao Pei Wang Ai-Jun Dong Jia-Tao Jiang Ji-Bing Leng Wei-An Li Si-Yao Li School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550025China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China CAS Key Laboratory of FAST National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China Key Laboratory of Information and Computing Guizhou Province Guizhou Normal UniversityGuiyang 550001China School of Big data and Computer Science Guizhou Normal UniversityGuiyang 550025China Guizhou Software Engineering Research Center Guiyang 550000China

Pulsar search is always the basis of pulsar navigation,gravitational wave detection and other research ***,the volume of pulsar candidates collected by the Five-hundred-meter Aperture Spherical radio Telescope(FAST)shows an explosive growth rate that has brought challenges for its pulsar candidate filtering ***,the multi-view heterogeneous data and class imbalance between true pulsars and non-pulsar candidates have negative effects on traditional single-modal supervised classification *** this study,a multi-modal and semi-supervised learning based on a pulsar candidate sifting algorithm is presented,which adopts a hybrid ensemble clustering scheme of density-based and partition-based methods combined with a feature-level fusion strategy for input data and a data partition strategy for *** on both High Time Resolution Universe SurveyⅡ(HTRU2)and actual FAST observation data demonstrate that the proposed algorithm could excellently identify pulsars:On HTRU2,the precision and recall rates of its parallel mode reach0.981 and 0.988 *** FAST data,those of its parallel mode reach 0.891 and 0.961,meanwhile,the running time also significantly decreases with the increment of parallel nodes within ***,we can conclude that our algorithm could be a feasible idea for large scale pulsar candidate sifting for FAST drift scan observation.

关键词： methods data analysis-surveys-methods numerical

来源：评论

学校读者我要写书评

暂无评论

λGrapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing 24

λGrapher: A Resource-Efficient Serverless System for GNN Se...

引用

33rd ACM Web Conference, WWW 2024

作者： Hu, Haichuan Liu, Fangming Pei, Qiangyu Yuan, Yongjie Xu, Zichen Wang, Lin National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab in the School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan China Peng Cheng Laboratory Huazhong University of Science and Technology China School of Mathematics and Computer Science Nanchang University China Paderborn University Paderborn Germany

ISBN: (纸本)9798400701719

Graph Neural Networks (GNNs) have been increasingly adopted for graph analysis in web applications such as social networks. Yet, efficient GNN serving remains a critical challenge due to high workload fluctuations and intricate GNN operations. Serverless computing, thanks to its flexibility and agility, offers on-demand serving of GNN inference requests. Alas, the request-centric serverless model is still too coarse-grained to avoid resource waste. Observing the significant data locality in computation graphs of requests, we propose λGrapher, a serverless system for GNN serving that achieves resource efficiency through graph sharing and fine-grained resource allocation. "Grapher features the following designs: (1) adaptive timeout for request buffering to balance resource efficiency and inference latency, (2) graph-centric scheduling to minimize computation and memory redundancy, and (3) resource-centric function management with fine-grained resource allocation catered to the resource sensitivities of GNN operations and function orchestration optimized to hide communication latency. We implement a prototype of λGrapher based on the representative open-source serverless platform Knative and evaluate it with real-world traces from various web applications. Our results show that λGrapher can achieve an average savings of 61.5% in memory resource and 47.2% in computing resource compared with the state of the arts while ensuring GNN inference latency. © 2024 ACM.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Current Control for Asymmetric Six-phase Permanent Magnet Motors with Less Computation and Optimized Voltage Vector Magnitude

Model Predictive Current Control for Asymmetric Six-phase Pe...

引用

2022 International Conference on Smart Energy and Electrical Engineering, SEEE 2022

作者： Sun, Jinyu Chen, Fubing Huai'An Key Laboratory of Big Data Intelligent Computing and Analysis China The School of Computer Science and Technology Huaiyin Normal University Huaian223001 China

For the sake of the fixed magnitude of candidate control sets, the conventional model predictive current control (MPCC) for asymmetric six-phase permanent magnet motors suffers from huge harmonic currents. This article designs a novel MPCC that aims to improve operational performance. First, virtual-voltage vector (VV) sets are synthesized as the new candidate vectors to restrain harmonic currents. Then, a simplified method for evaluating voltage vectors is used to alleviate the computation in the enumeration process. Moreover, the duty cycle modulation with the deadbeat solution is introduced to optimize the magnitude of the VV. The modulation range can be expanded by utilizing null vectors, which will significantly reduce the torque fluctuations and flux ripples. The experiments are conducted to verify the designed control strategy. © Published under licence by IOP Publishing Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition with DToF Sensing

Facial Expression Recognition with DToF Sensing

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chengxiao Li Xie Zhang Chenshu Wu Department of Computer Science School of Computing and Data Science The University of Hong Kong HK SAR China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Facial Expression Recognition (FER) is crucial for understanding human emotions, with applications spanning from mental health assessment to marketing recommendation systems. However, existing camera-based methods raise privacy concerns, while RF-based approaches suffer from limited environmental generalizability and high cost. In this work, we propose ToFace, a FER system leveraging a low-cost (4.8$) Direct Time-of-Flight (DToF) sensor that has been available on commodity smartphones. This sensor provides an extremely low-resolution 8 × 8 depth map and a clear Field of View (FoV), significantly mitigating privacy concerns while avoiding the impact of ambient objects. Despite the benefits, the low-resolution depth map introduces significant challenges for precise expression recognition due to limited facial structure information. We first develop a physical model to extract additional spatial information from the intermediate sensor output, i.e., the transient histograms. We then propose a physics-integrated neural network to reconstruct a facial structure map comprising both depth and orientation for accurate expression recognition. We conduct real-world experiments with 12 users and compare our model with several baselines. The results demonstrate that ToFace achieves the highest recognition accuracy of 75%.

关键词： Privacy Accuracy Face recognition Speech recognition Signal processing Robustness Sensors Transient analysis Speech processing Smart phones

来源：评论

学校读者我要写书评

暂无评论

Automated Counting System Based on Watershed Algorithm for Tilapia Fish Egg 1

Automated Counting System Based on Watershed Algorithm for T...

引用

1st IEEE International Conference on Smart Technology, ICE-SMARTec 2023

作者： Hassan, Mohamad Ghozali Harun, Nor Hazlyna Md Azhar, Amiera Syazlin Md Pauzi, Siti Naquiah Ja'afar, Noor Ashri Mansor, Nur Suhaili School of Technology Management and Logistics Universiti Utara Malaysia Malaysia School of Computing Universiti Utara Malaysia Data Science Research Lab Malaysia Institute for Advanced and Smart Digital Opportunities School of Computing Sintok Malaysia

ISBN: (纸本)9798350306156

Aquaculture is a significant component of Malaysia's fishery sector and makes a substantial contribution to the country's economy. It is the source of income and employment for the nation. Tilapia fish is one of the main species cultured in the aquaculture industry, as eggs produced by this fish are considered very valuable both in terms of quantity and quality. A standard egg selection procedure to calculate the fish egg properly has not yet been implemented. The process of fish egg selection plays a vital role in determining the accurate count of fish eggs. This study focuses on developing an automated counting system for tilapia fish eggs using an image processing technique concentrating on the watershed algorithm. This algorithm enables the image of the fish eggs to be clustered in shaded colors, thus enabling the total number of fish eggs to be automatically counted. The results show that the automated counting system for tilapia fish eggs works successfully as the accuracy obtained was above 90%. It is believed that an automated counting system can help fish breeders to perform fish egg counting automatically and more effectively and efficiently. © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

An Efficient Automated Technique for Classification of Breast Cancer Using Deep Ensemble Model

引用

Computer Systems science & Engineering 2023年第7期46卷 897-911页

作者： Muhammad Zia Ur Rehman Jawad Ahmad Emad Sami Jaha Abdullah Marish Ali Mohammed A.Alzain Faisal Saeed Department of Electrical Engineering HITEC UniversityTaxila47080Pakistan School of Computing Edinburgh Napier UniversityEdinburghEH105DTUK Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia DAAI Research Group Department of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City University15 Bartholomew RowBirminghamB55JUUK

Breast cancer is one of the leading cancers among *** has the second-highest mortality rate in women after lung *** detection,especially in the early stages,can help increase survival ***,manual diagnosis of breast cancer is a tedious and time-consuming process,and the accuracy of detection is reliant on the quality of the images and the radiologist’s ***,computer-aided medical diagnosis has recently shown promising results,leading to the need to develop an efficient system that can aid radiologists in diagnosing breast cancer in its early *** research presented in this paper is focused on the multi-class classification of breast *** deep transfer learning approach has been utilized to train the deep learning models,and a pre-processing technique has been used to improve the quality of the ultrasound *** proposed technique utilizes two deep learning models,Mobile-NetV2 and DenseNet201,for the composition of the deep ensemble *** learning models are fine-tuned along with hyperparameter tuning to achieve better ***,entropy-based feature selection is *** cancer identification using the proposed classification approach was found to attain an accuracy of 97.04%,while the sensitivity and F1 score were 96.87%and 96.76%,*** performance of the proposed model is very effective and outperforms other state-of-the-art techniques presented in the literature.

关键词： Breast cancer image enhancement ensemble model transfer learning feature selection

来源：评论

学校读者我要写书评

暂无评论

TikTok Video Cluster Analysis Based on Trending Topic 9th

TikTok Video Cluster Analysis Based on Trending Topic

引用

9th International Conference on computing and Informatics, ICOCI 2023

作者： Bakar, Juhaida Abu Sharimi, Nur Azmielia Muhammad Shahril, Mohd Azrul Edzwan Azmi, Nur Syafiqah Harun, Nor Hazlyna Awang, Hapini Bakar, Nur Syafiqah Abu Data Management and Software Solution Research Lab School of Computing Universiti Utara Malaysia Kedah Sintok06010 Malaysia Data Science Research Lab School of Computing Universiti Utara Malaysia Kedah Sintok06010 Malaysia Institute for Advanced and Smart Digital Opportunities School of Computing Universiti Utara Malaysia Kedah Sintok06010 Malaysia Faculty of Medicine and Health Sciences Universiti Sains Islam Malaysia Negeri Sembilan Nilai71800 Malaysia

ISBN: (纸本)9789819995882

TikTok is a popular social networking application that offers trend research and is a valuable source for users. However, this is often misconstrued for content, which may not be suitable for children due to misappropriate content. This study aims to improve user perception of TikTok by using topic modelling and clustering techniques to identify trending topics in TikTok videos. The research uses Latent Dirichlet Allocation (LDA) and K-means clustering techniques to enhance the recognition of local and global topics across text documents. The methodology includes data collection, data pre-processing, clustering, topic modelling, and results. Ten subjects associated with trending TikTok videos are displayed using the LDA algorithm, and the generated topics are used to produce an Inter-topic Distance Map. The method’s effectiveness is evaluated using log-likelihood score and perplexity measurements. It has a log-likelihood score of 5579 and a perplexity score of 287. A good model is one with a higher log-likelihood and lower perplexity. The study ex-tracts popular TikTok topics using both the LDA topic modelling technique and the K-means clustering algorithm. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Towards Techniques for Updating Virtual Knowledge Graphs 17

Towards Techniques for Updating Virtual Knowledge Graphs

引用

17th International Rule Challenge and 7th Doctoral Consortium @ RuleM+RR, RuleML+RR-Companion 2023

作者： Wandji, Romuald Esdras Šimkus, Mantas Calvanese, Diego Department of Computing Science Umeå Universitet Umeå Sweden Research Centre for Knowledge and Data Faculty of Engineering Free University of Bozen-Bolzano Bolzano Italy

The field of Virtual Knowledge Graphs (VKGs) continues to grow in both academic and applied contexts. Yet, the issue of updates in VKG systems has not yet received adequate attention, although it is crucial to manage data modifications at the data source level through the lens of an ontology. In this paper, we focus on VKGs whose ontology is specified in the lightweight ontology language DL-LiteA, and we propose diverse settings and research directions we intend to explore to address the challenge of translating ontology-based updates into updates at the level of data sources. We also pay attention to the important problem of automated analysis of mappings, which plays a major role when it comes to reformulating ontology-based update requests into update requests over the data sources. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Hybrid genetic model with ANOVA for predicting breast neoplasm using METABRIC gene data

引用

Materials Today: Proceedings 2022年 56卷 1847-1852页

作者： Thakur, Bharti Gupta, Gaurav Kumar, Nagesh Yogananda School of AI Computing and Data Science Shoolini University Himachal Pradesh Solan India Chitkara School of Engineering & Technology Chitkara University Himachal Pradesh India

In 2020, 2.3 million females identified with breast cancer, and it is the second most frequent cancer among females. As a result, there is severe requirement of an accurate procedure to recognize breast cancer. In accordance with breast cancer organization the breast cancer is divided into two types one is invasive and another one is non-invasive. In Indian cities like Delhi, Kolkata and Mumbai have the highest death rate for female due to breast cancer. Unusual alteration in genes is the prime reason for breast cancer. Our paper contains metabric dataset related to 1905 patients along with 31 clinical characteristics and 331 genes. The novelty of this paper is to find out genes which are highly responsible for death from breast cancer with foremost clinical features and implementation of a hybrid method which is a combination of genetic algorithm and artificial neural network to get the best accuracy with the help of machine learning as this can preserve life of females. For attribute scaling standard scaler is used which range data in between 0 and 1. Attribute selection is performed with the help of ANOVA which is a statistical appliance. With this tool 6 leading clinical attributes are examined. In our research 12 genes gsk3b, kmt2c, map4, tsc2, tnk2, pdgfb, ncoa3, akt1, afdn, sdc4,map2k2 and tubb4b which are extremely responsible for death in our dataset are recognized and our hybrid method implementation gives the perfection of 90.57%. © 2021

关键词： Analysis of variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving data Publishing Models, Challenges, Applications, and Issues 1st

Privacy-Preserving Data Publishing Models, Challenges, Appli...

引用

1st International Conference on Expert Clouds and Applications, ICOECA 2023

作者： Jayapradha, J. Prakash, M. Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India Department of Data Science and Business Systems SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India

ISBN: (纸本)9789819917440

The distribution of Electronic Health Records is highly needed for various analysis purposes and medical studies. However, the data should be disclosed to the data recipient in such a way that the privacy of the individual is ensured. Privacy-preserving data publishing is a challenging task because the distributed data should be protected against multiple privacy threats. Several privacy models, methods, techniques have been proposed and studied in earlier works, however, the study concerning privacy models considering adversary background knowledge is very limited. In this study, various privacy models and their attack models have been analyzed and depicted, the main focus of the study is the adversary’s background knowledge privacy-preserving data publishing model. Various research challenges in security and privacy have been identified and summarized. Furthermore, the various applications of privacy-preserving data publishing such as Cloud, E-health, Social Network, Agriculture, and Smart City have been studied and the need for privacy is briefed. Finally, the paper highlighted the study's intuitions regarding present unresolved challenges as well as probable future approaches in privacy-preserving data publishing. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Records management

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：