检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Lun Hu Bo-Wei Zhao Shicheng Yang Xin Luo MengChu Zhou Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi China School of Computer Science and Technology Wuhan University of Technology Wuhan China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Hengrui (Chongqing) Artificial Intelligence Research Center Cloudwalk China New Jersey Institute of Technology Newark NJ USA

ISBN: (纸本)9781665442084

Protein-protein interactions are of great significance for us to understand the functional mechanisms of proteins. With the rapid development of high-throughput genomic technology, the amount of protein-protein interaction data has become so big that most of existing prediction algorithms are no longer applicable. To address this problem, we develop a distributed framework by reimplementing one of state-of-the-art algorithms, i.e., CoFex, by using MapReduce. In particular, we adopt a novel tree-based data structure to reduce the heavy memory consumption cased by the huge sequence information of proteins. After that, the procedure of CoFex is modified by following the paradigm of MapReduce such that the prediction task can be completed in a distributed manner, thus fulfilling the demanding requirements of large-scale protein-protein interaction prediction. A series of experiments have been conducted to evaluate the performance of the proposed distributed framework in terms of both efficiency and effectiveness. Experimental results demonstrate that the proposed framework can considerably improve the efficiency of CoFex by achieving more than two-orders-of-magnitude improvement in computational efficiency while retaining a comparable level of accuracy.

关键词： Proteins Memory management Genomics Predictive models Prediction algorithms data structures Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Moment Estimation-Incorporated Particle Swarm Optimization

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Mom...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jiufang Chen Ye Yuan Chunlin He School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chinese Academy of Sciences Chongqing Institute of Green and Intelligent Technology Chongqing China Chongqing School University of Chinese Academy of Sciences Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing China School of Computer Science China West Normal University Nanchong Sichuan China

ISBN: (纸本)9781665426220

A latent factor analysis (LFA) model can efficiently address a high-dimensional and sparse (HiDS) matrix with a stochastic gradient descent (SGD) algorithm. However, an SGD-based LFA model's performance depends heavily on its hyper-parameters. The popular method is based on grid-search, which fails because of expensive computation and time-consuming. Aiming at implementing a hyper-parameter-free LFA model, this study proposes an adaptive moment estimation-incorporated particle swarm optimization (Adam-PSO) algorithm that efficiently addresses the premature issues in a PSO algorithm. With achieved the hyper-parameter adaptation in an SGD-based LFA model, an Adam-PSO-based LFA (APL) model possessing hyper-parameter-free training is further implemented. Empirical studies on four HiDS matrices indicate that compared with state-of-the-art models with hyper-parameter adaptation settings, an APL model achieves the most efficient hyper-parameter-free training and highly competitive prediction accuracy for missing data of an HiDS matrix. Hence, it fits the need of real applications with high scalability and efficiency.

关键词： Training Adaptation models Computational modeling Stochastic processes Predictive models Prediction algorithms data models

来源：评论

学校读者我要写书评

暂无评论

On-edge multi-task transfer learning: Model and practice with data-driven task allocation

arXiv

引用

arXiv 2021年

作者： Zheng, Zimu Chen, Qiong Hu, Chuang Wang, Dan Liu, Fangming The National Engineering Research Center for Big Data Technology and System Key Laboratory of Services Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China The Edge Cloud Innovation Lab. Technical Innovation Department Cloud BU Huawei Technologies Co. Ltd. Shenzhen China The Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Hong Kong

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes heavy computation burden to the resource-constrained edge devices. Existing task allocation works usually assume all submitted tasks are equally important, leading to inefficient resource allocation at a task level when directly applied in Multi-task Transfer Learning (MTL). To address these issues, we first reveal that it is crucial to measure the impact of tasks on overall decision performance improvement and quantify task importance. We then show that task allocation with task importance for MTL (TATIM) is a variant of NP-complete Knapsack problem, where the complicated computation to solve this problem needs to be conducted repeatedly under varying contexts. To solve TATIM with high computational efficiency, we propose a data-driven Cooperative Task Allocation (DCTA) approach. Finally, we evaluate the performance of DCTA by not only a trace-driven simulation, but also a new comprehensive real-world AIOps case study which bridges model and practice via a new architecture and main components design within AIOps system. Extensive experiments show that our DCTA reduces 3.24 times of processing time, and saves 48.4% energy consumption compared with the state-of-the-art when solving TATIM. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Multi-cloud DRaaS using OpenStack Keystone Federation

Multi-cloud DRaaS using OpenStack Keystone Federation

引用

International Conference on Advances in computing and Communication Engineering (ICACCE)

作者： Sudheendra Harwalkar Dinkar Sitaram Shivangi Jadon Center for Cloud Computing and Big Data PES University Bangalore India

ISBN: (数字)9781728132501

ISBN: (纸本)9781728132518

Disaster recovery (DR) for the distributed workload and data in multi-cloud environments is very complex and challenging. There exist point tools for failover from one cloud to another cloud with active/passive data replications or with simple backup of private cloud data to public cloud(s). However, these point solutions are not integrated with the cloud environment. In this paper, we demonstrate how cost-effective DR process/solution can be accomplished with our Federated cloud Services Framework (middleware), which is built upon OpenStack [16], by leveraging existing OpenStack functionalities. As our solution leverages the functionality of the federated cloud environment, it generalizes easily to multi-cloud scenarios, and is better integrated with the cloud infrastructure. We also compare our solution to current DR process/solutions available in the market.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multicloud- auto scale with prediction and delta correction algorithm

Multicloud- auto scale with prediction and delta correction ...

引用

International Conference on intelligent computing, Instrumentation and Control Technologies (ICICICT)

作者： Sudheendra Harwalkar Dinkar Sitaram Dhanaraj V Kidiyoor Milan M L Ornella D'souza Radhika Agarwal Yamini Agarwal Center for Cloud Computing and Big Data PES University Bangalore India

IT enabled enterprise organizations are embracing multi-cloud to handle their peak loads in addition to their private cloud (own data centers) and the market prediction indicates that by year 2020, about 80% of enterprise will have or working towards multi-cloud enablement for their IT needs. There are multiple products from third-party supporting multi-cloud and also some of the cloud service providers have already enabled the service using proprietary cloud management tools with custom built plug-ins. One of the major challenges in multi-cloud is efficient resource utilization and cost savings without vendor/broker lock-in. At present, multi-cloud interface standardization is still in draft. In this paper we propose handling of cloud burst at peak load with our OpenStack [9] Middleware Framework, which uses default OpenStack services. It also has built-in support for prediction, resource allocation and proactive workload migration techniques which can be integrated easily with cloud provider solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fast Geometric Modeling Method for Cold Blades 1

引用

Asia-Pacific International Symposium on Aerospace Technology, APISAT 2018

作者： Liu, Kaicheng Wang, Jianjun Ni, Bowen School of Energy and Power Engineering Beihang University Beijing100191 China Cloud Computing and Big Data Center China Mobile Group Xinjiang Company Limited Xinjiang830018 China

ISBN: (数字)9789811333057

ISBN: (纸本)9789811333040

A geometric modeling method for cold blade is proposed based on hot-to-cold finite element (FE) transformation calculation. The main idea is to interpolate the deformation result calculated from hot-to-cold transformation to the control points of the hot blade profile. Subtract the interpolated displacement values from the coordinates of the hot control points then the coordinates of the cold control points are obtained. The resulting coordinates could be directly used for solid modeling in commercial CAD programs. Both the hot-to-cold FE transformation calculation part and the output part of the cold blade profile’s control point coordinates could be accomplished in a whole process automatically in the commercial FE program ANSYS15.0. The flow chart of the entire process is given attached with ANSYS APDL commands. Finally, a numerical example based on a blisk sector model is provided. The hot-to-cold FE transformation calculation is performed, the finite element model (FEM) is obtained and solid model is built. Additionally, the effect of mesh density on the modeling accuracy is investigated. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

Predicting Virtual Machine Resource Consumption Based on Optimized Grey Model

Predicting Virtual Machine Resource Consumption Based on Opt...

引用

第二届先进电子材料、计算机与材料工程国际学术会议（AEMCME 2019）

作者： Shi Aiwu Gao Di He Kai Cloud Computing and Big Data Research Center Wuhan Textile University

In order to relatively change the computing specifications of virtual machines(VMs for short) for the changing resource consumption of VMs, and reduce the impact of the changes, this paper proposes the optimized grey GM(1, 1) model to predict the resource consumption of VMs. Because VM resources may fluctuate greatly in a short time, the initial data are smoothed first, and then modeled, the model edge value is optimized according to the characteristics of cloud environment. Experiments show that the accuracy and stability of the prediction model can be improved by sorting out the initial data and optimizing the model. The prediction value is helpful to design the allocation scheme of VM resources, improve the utilization rate of physical resources in cloud environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DCSim: Cooling Energy Aware VM Allocation Framework for a cloud data center

DCSim: Cooling Energy Aware VM Allocation Framework for a Cl...

引用

International Conference on Advances in computing and Communication Engineering (ICACCE)

作者： Priyank Bhandia Ravi S. Anupindi Pavan Yekbote Nikhil Singh H.L. Phalachandra Dinkar Sitaram Center for Cloud Computing and Big Data PES University Bangalore India

ISBN: (数字)9781728132501

ISBN: (纸本)9781728132518

Explosion of digital content has resulted in large amounts of resources being provisioned and managed for various applications in cloud data centers. Energy consumption in these large cloud data centers is a rising concern, accounting for 1.3% of the worlds electricity consumption [1]. data center cooling accounts for 40% of this energy consumption [2]. Of the various mechanisms available for studying the energy consumption in data centers, a simulation based approach is quite popular. In this paper, we propose DCSim, a configurable extension to cloudSim, a popularly used cloud infrastructure and simulation framework. cloudSim provides coarse power models to calculate total energy consumption in a data center for a given workload, but has no provision to factor in the data center topology and current cooled area into this power model. This makes building intelligent cooling energy aware allocation policies in cloudSim difficult. In DCSim, we introduce a novel data center model that addresses the shortcomings of cloudSim by encapsulating concepts of Racks, Aisles, Sectors and Zones (collectively referred to as DCObjects). We also provide the capability to model the cooling of these DCObjects. This makes the study of cooling aware resource provisioning for workloads easier. The DCObjects and the data center model presented are designed to be fully extensible to support future developments in this area. In this work we also implement a Cooling aware VM allocation policy, and demonstrate using multiple algorithms, that this VM allocation policy will effectively reduce the total data center power consumption by 18.18% over an algorithm which does not factor in the cooled DCObjects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ketogenic Diets Potentially Reverse Type 2 Diabetes Via Continuous Remote Care Intervention: A Case Study in Central China

引用

Current Developments in Nutrition 2021年 5卷 5140437-5140437页

作者： Nie, Linfeng Zhai, Qianqian Wei, Yi Wang, Tao Li, Pan Xinxiang Medical University Center for Health Big Data and Intelligent Computing Xinxiang Medical University

AbstractObjectivesType 2 diabetes (T2D) remains a major public health challenge worldwide. Ketogenic diets (KD) have been reported to be effective in managing T2D, yet it is unclear if KD-based T2D management is suitable for patients in the central region of China where high-carbohydrate diets prevail. Here, an overweight T2D patient from Zhengzhou (Henan province), were enrolled in a 12-week KD-based continuous remote care intervention program. MethodsOur 12-week intervention program is consisted of remote nutritional education, online personal coaching, and continuous monitoring of major biomarkers, e.g., body weight, blood pressure, continuous flash glucose monitoring, beta-hydroxybutyrate (BHB). The participant was advised to achieve and sustain nutritional ketosis through carbohydrate restriction since the onset of the study, and was instructed to reduce or stop diabetes medications within targeted continuous glucose levels, and to adjust carbohydrate intake in case of hypoglycemia. ResultsIn 12 weeks, the participant (male; 52 years old) achieved a weight loss of 7.4 kg (from 90.1 kg to 82.7 kg), with waist circumference reduced from 103 cm to 97 cm and body mass index (BMI) reduced from 29.42 kg/m 2 to 26.50 kg/m 2; his HbA1c level and fasting glucose was reduced from 6.2% and 6.78 mmol/L at baseline to 5.8% and 5.48 mM/L repectively, with his fasting insulin decreased from 13.41 mM/L at baseline to 8.40 μIU/mL, HOMA-IR from 4.04 to 2.03, and an ideal ambulatory glucose profile (AGP) (Time in Range (TIR) ≧ 99%). The participant was advised to discontinue all diabetes medications after 1 week. During the 4 th week, hypoglycemic events were detected, and the participant was advised to adjust carbohydrate intake; no hypoglycemic events were observed afterwards. Biomarkers related to blood lipids, lipoproteins, liver, kidney, thyroid and inflammation remained normal after the intervention. ConclusionsOur results suggest that a 12-week KD-based continuous remote c

关键词：

来源：评论

学校读者我要写书评

暂无评论

Progressive Dual Priori Network for Generalized Breast Tumor Segmentation

arXiv

引用

arXiv 2023年

作者： Wang, Li Wang, Lihui Kuai, Zixiang Tang, Lei Ou, Yingfeng Ye, Chen Zhu, Yuemin Wu, Min Shi, Tianliang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Imaging Center Harbin Medical University Cancer Hospital Harbin150081 China Radiology Department Guizhou Provincial People’s Hospital Guiyang550002 China Radiology Department Tongren People’s Hospital Tongren554300 China Univ Lyon INSA Lyon CNRS Inserm CREATIS UMR 5220 U1206 LyonF-69621 France

To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori network (PDPNet) to segment breast tumors from dynamic enhanced magnetic resonance images (DCE-MRI) acquired at different centers. The PDPNet first cropped tumor regions with a coarse-segmentation based localization module, then the breast tumor mask was progressively refined by using the weak semantic priori and cross-scale correlation prior knowledge. To validate the effectiveness of PDPNet, we compared it with several state-of-the-art methods on multi-center datasets. The results showed that, comparing against the suboptimal method, the DSC and HD95 of PDPNet were improved at least by 5.13% and 7.58% respectively on multi-center test sets. In addition, through ablations, we demonstrated that the proposed localization module can decrease the influence of normal tissues and therefore improve the generalization ability of the model. The weak semantic priors allow focusing on tumor regions to avoid missing small tumors and low-contrast tumors. The cross-scale correlation priors are beneficial for promoting the shape-aware ability for irregular tumors. Thus integrating them in a unified framework improved the multicenter breast tumor segmentation performance. The source code and open data can be accessed at https://github. com/wangli100209/PDPNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

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：