检索结果-内蒙古大学图书馆

A Multiagent Reinforcement Learning-Assisted Cache Cleaning Scheme for DM-SMR

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2023年第8期42卷 2500-2513页

作者： Shen, Zhaoyan Yang, Yuhan Pan, Yungang Zhang, Yuhao Jia, Zhiping Cai, Xiaojun Li, Bingzhe Shao, Zili Shandong Univ Sch Comp Sci & Technol Qingdao 266200 Peoples R China Linkoping Univ Dept Comp & Informat Sci S-58183 Linkoping Sweden Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74074 USA Chinese Univ Hong Kong Dept Comp Sci & Engn Kowloon Tong Hong Kong Peoples R China

To support nonsequential writes, persistent cache (PC) is constructed in drive managed SMR (DM-SMR) drive. However, PC cleaning introduces drastic performance degradation and enlarges tail latencies. In this article, we propose to utilize reinforcement learning (RL) to mitigate the longtail latency of PC cleaning. Our scheme uses the lightweight Q-learning method to monitor and learn the idle time of I/O workloads, based on which PC cleaning is intelligently guided, thus maximally exploit idle time between requests and hiding tail latency from normal requests. In addition, a multiagent RL scheme with clustering algorithm is adopted to further mitigate the tail latencies and adapt to variable workloads. We emulate a DM-SMR drive inside a Linux device driver to implement our proposed scheme. According to the experimental results, our scheme can effectively reduce the tail latency by 59.45% at the 99.9th percentile and the average latency by 48.75% compared with a typical shingled magnetic recording (SMR) design.

关键词： Cleaning process clustering algorithm reinforcement learning (RL) shingled magnetic recording (SMR) tail latency

来源：评论

学校读者我要写书评

暂无评论

Application of cloud accounting in enterprise financial forecasting and decision making in the era of big data

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2023年第1期8卷 3095-3110页

作者： Xu, Haiyan Ge, Jingru Tong, Li Yangzhou Polytech Inst Business Coll Yangzhou 225127 Jiangsu Peoples R China

In order to accurately understand the economic development of enterprises and increase the company's economic benefits, a study on financial forecasting and decision-making in big data cloud accounting enterprises is proposed. Enterprises improve the efficiency of data utilization by acquiring information processing and analysis, establishing a diversified control mechanism, and improving the effectiveness of financial and tax management. The objective function is optimized using a structured sparse induced parametric number to calculate the data block centers to describe the data objects more comprehensively and make the obtained clustered financial results more accurate. Adding classifiers to the set of labeled samples and constraining the joined samples belonging to the wrong class combine multiple kernels from different perspectives to obtain a comprehensive measure of similarity. Selecting sub-kernel functions and parameters to construct multiple kernel functions, the learning and generalization capabilities of kernel functions, and using high-dimensional data feature vectors to construct a shared hidden subspace to maximize the similarity between prediction samples and assign greater weights in the multi-perspective clustering process for corporate financial forecasting and decision making. The analysis results show that using data clustering cloud finance, financial data can be collected and corrected promptly, and the budget accuracy is up to 90%, which provides important help to enterprise financial decision-making.

关键词： Big data era Cloud accounting computing Financial forecasting and decision making clustering algorithm Objective function

来源：评论

学校读者我要写书评

暂无评论

YOLO-Banana:An Effective Grading Method for Banana Appearance Quality

引用

Journal of Beijing Institute of Technology 2023年第3期32卷 363-373页

作者： Dianhui Mao Xuesen Wang Yiming Liu Denghui Zhang Jianwei Wu Junhua Chen School of Computer Beijing Technology and Business UniversityBeijing 100048China Research Center of Information Technology Beijing Academy of Agriculture and Forestry SciencesBeijing 100097China Beijing PAIDE Science and Technology Development Co.Ltd. Beijing 100097China Institute of Standardization Theory and Strategy China National Institute of StandardizationBeijing 100088China

The increasing trend towards independent fruit packaging demands a high appearance quality of individually packed *** this paper,we propose an improved YOLOv5-based model,YOLO-Banana,to effectively grade banana appearance quality based on the number of banana defect *** to the minor and dense defects on the surface of bananas,existing detection algorithms have poor detection results and high missing *** address this,we propose a densitybased spatial clustering of applications with noise(DBSCAN)and K-means fusion clustering method that utilizes refined anchor points to obtain better initial anchor values,thereby enhancing the network’s recognition ***,the optimized progressive aggregated network(PANet)enables better multi-level feature ***,the non-maximum suppression function is replaced with a weighted non-maximum suppression(weighted NMS)function based on distance intersection over union(DIoU).Experimental results show that the model’s accuracy is improved by 2.3%compared to the original YOLOv5 network model,thereby effectively grading the banana appearance quality.

关键词： YOLOv5 banana appearance grading clustering algorithm weighted non-maximum suppression(weighted NMS) progressive aggregated network(PANet)

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Routing algorithm using Chaotic Grey Wolf with Mobile Sink-based Path Optimization for Wireless Sensor Networks

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第12期14卷 161-171页

作者： AL Harthi, Latifah Ahmed, Alaa E. S. Ibrahim, Mostafa E. A. Imam Muhamad Ibn Saud Islamic Univ IMSIU Coll Comp & Informat Sci Riyadh Saudi Arabia Benha Univ Shoubra Fac Engn Cairo Egypt Benha Univ Benha Fac Engn Dept Elect Engn Banha Egypt

The task of deploying an energy -conscious wireless sensor networks (WSNs) is challenging. One of the most effective methods for conserving WSNs energy is clustering. The deployed sensors are divided into groups by the clustering algorithm, and each group's cluster head (CH) is chosen to gather and combine data from other sensors in the group. Mobile Wireless Sensor Networks, which enable moving the sink node, aid in reducing energy consumption. Thus, this paper introduces an energy efficient clustering algorithm and optimized path for a mobile sink using a swarm intelligence algorithms. The Chaotic Grey Wolf Optimization (CGWO) approach is used to form clusters and identify CHs. While utilizing the Slime Mould algorithm (SMA) for determining the shortest path between a mobile sink and CHs. The effectiveness of the suggested routing strategy is evaluated against that of other current, cutting -edge protocols. The findings demonstrate that in terms of overall energy consumption and network lifetime, the suggested algorithm performs better than others. While for stability period the proposed algorithm outperforms three of compared algorithms and was close to the fourth.

关键词： Wireless sensor network clustering algorithm grey wolf optimizer slime mould algorithm mobile sink

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Robust Communication for Internet of Vehicles

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2023年第4期57卷 364-370页

作者： Gasmi, Rim Illizi Univ Ctr Illizi 33000 Algeria

The high number of connected nodes in Internet of Vehicles (IoVs) drives to high data exchange between nodes, which increases the network overhead. Moreover, the recurrent change in vehicle mobility in Internet of Vehicles (IoVs) drives to frequent changes in network topology which in turn causes frequent link disconnections. Therefore, the most addressed issues in IoVs are to manage the high quantity of packets sent by the huge number of vehicles connected with IoT devices, to reduce communication delays and guarantee the longest communication stability. clustering techniques have been utilized to reduce network overhead in IoVs networks. Classical clustering algorithms have been proposed to enhance network performances. However, IoVs environment is characterized by the high dynamicity of nodes, therefore, the optimization methods already proposed cannot perfectly deal with the characteristics of IoVs. Reinforcement learning (RL) is a machine learning algorithm, where the agent learns from its environment and tries to enhance its policies to obtain the best reward. In this paper, we propose to use deep reinforcement learning (DRL) to select the best cluster heads based on node's degree, node's buffer size, and signal strength. In the proposed work, the vehicle can perfectly select the cluster heads by choosing the best state-action values taking in consideration the high dynamicity of the network.

关键词： reinforcement learning clustering algorithm IoVs reliable communication

来源：评论

学校读者我要写书评

暂无评论

Digital Divide in the European Union: A Typology of EU Citizens

引用

SOCIAL INDICATORS RESEARCH 2025年第1期176卷 149-172页

作者： Gomes, Ana Dias, Jose G. Inst Univ Lisboa ISCTE IUL Business Res Unit BRU IUL Lisbon Portugal Inst Univ Mil Portuguese Air Force Acad Ctr Invest Acad Forca Aerea Sintra Portugal

This paper addresses the heterogeneity of the digital divide and internet use among citizens in the 28 European Union (EU) countries (at the time of the survey). Drawing from the Eurobarometer Surveys, three indicators of the digital divide are used to define the groups: frequency of internet access, means of internet access, and online activities. The categorical clustering algorithm identifies six groups of internet users: Non-Users, Basic Users, Information Exchangers, Instrumental Users, Socializers, and Advanced Users, each with distinct socio-demographic profiles. The study reveals significant socio-economic and demographic profiling variables characterizing these patterns, including age, education, gender, occupation, type of community and geographic location. A major digital divide is detected in many countries;Notably, Romania, Greece, and Bulgaria have the largest proportion of Non-Users, emphasizing the need for targeted policy interventions. These results provide crucial insights for the European Commission's digitization strategy, suggesting that more nuanced and targeted measures are needed to ensure equitable digital access across the EU.

关键词： Internet Digital divide European Union clustering algorithm Unobserved heterogeneity Social networks

来源：评论

学校读者我要写书评

暂无评论

Neural Network algorithm for Solving Nonlinear Equation Systems 15th

Neural Network Algorithm for Solving Nonlinear Equation Syst...

引用

15th International Conference on Advances in Swarm Intelligence (ICSI)

作者： Chang, Yuxin Zhang, Xinming Harbin Inst Technol Shenzhen Sch Sci Shenzhen 518055 Peoples R China

ISBN: (纸本)9789819771837;9789819771844

In practical research, nonlinear equation systems (NESs) are common mathematical models widely applied across various fields. Solving these nonlinear equation systems is crucial for addressing many engineering challenges. However, due to the inherent complexity and diverse solutions of nonlinear equation systems, traditional optimization algorithms and intelligent optimization algorithms have certain limitations. Neural network algorithms, which have gained significant popularity in recent years, excel in fitting nonlinear relationships. This research aims to explore different neural network models to develop efficient and accurate computational models for solving various types of nonlinear equation systems, thus overcoming some of the limitations of traditional and intelligent optimization algorithms. By leveraging the adaptability and generality of neural networks, we seek to enhance their performance in solving complex nonlinear equation systems. Furthermore, by integrating iterative algorithms and clustering algorithms, we aim to improve solution accuracy and effectively address the multiple roots problem associated with nonlinear equation systems.

关键词： Nonlinear equation systems Iterative neural network clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

FCMEDriver: Identifying Cancer Driver Gene by Combining Mutual Exclusivity of Embedded Features and Optimized Mutation Frequency Score 1

引用

20th International Symposium on Bioinformatics Research and Applications (ISBRA)

作者： Yi, Sichen Xie, MinZhu Hunan Normal Univ Sch Math & Stat Minist Educ Key Lab Comp & Stochast Math LCSM Changsha 410081 Peoples R China Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China

ISBN: (数字)9789819750870

ISBN: (纸本)9789819750863;9789819750870

Efficiently identifying cancer driver genes is critical to drug design, cancer diagnosis and treatment. Current unsupervised cancer driver gene prediction approaches mainly exploit mutual exclusivity of mutated driver genes and integrate multi-omics data with gene function networks. Some of them identify driver genes based on the gene features learned by network embedding algorithms. However, these methods are limited to using the mutual exclusivity from original data without considering the mutual exclusivity implanted in the learned features. Additionally, they simply assume that all driver genes have high mutation frequencies. Thus, we propose a novel unsupervised framework FCMEDriver, which utilizes the mutual exclusivity from the learned features and mutation frequency to predict driver genes. In FCMEDriver, a feature clustering algorithm is designed to obtain modules. Based on the modules, our extensive experiments show that the Euclidean distances between learned features are highly related with the mutual exclusivity defined on the original data, and they can reveal more information compared to mutual exclusivity. Thus, we apply the Euclidean distances of learned gene features for each module to calculate a module importance score for each gene. Since the fact that most of driver genes have intermediate mutation frequencies, we design a mutation frequency scoring function for each gene to optimize the existing mutation frequency scoring strategy in which genes with intermediate mutation frequencies are more inclined to obtain similar high scores as those genes with high mutation frequencies. The weighted sum of the module importance score and the mutation frequency score is used to prioritize the genes. The experiment results show that FCMEDriver outperforms other four state-of-the-art methods for cancer driver identification.

关键词： Cancer driver clustering algorithm Mutual exclusivity embedded feature

来源：评论

学校读者我要写书评

暂无评论

An efficient adaptive approach to automatically identify rock discontinuity parameters using 3D point cloud model from outcrops

引用

GEOLOGICAL JOURNAL 2023年第6期58卷 2195-2210页

作者： Cai, Xue-heng Lu, Qing Zheng, Jun Liao, Ke-Wu Liu, Jian Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China Zhejiang Univ Ctr Balance Architecture Hangzhou Peoples R China Zhejiang Univ Co Ltd Inst Geotech & Underground Engn Design & Res Architectural Design & Res Inst Hangzhou Peoples R China Zhejiang Highway & Water Transportat Engn Consult Chief Engineers Off Hangzhou Peoples R China

Digital geological survey methods have become supplementary approaches for traditional geological survey in the last two decades. In this paper, the Unmanned Aerial Vehicle (UAV)-based photogrammetry technology is used to obtain the 3D point cloud model of rock outcrops. The clustering algorithm is used to automatically identify the rock discontinuity parameters. However, the obtained 3D point cloud model with high resolution often has a huge point data which usually poses a great challenge to the computational efficiency of the automatic identification. In fact, too-dense point cloud data may not be necessary for cases when the rock mass is relatively intact. The optimal point cloud resolution, which balances the accuracy and efficiency, depends on the degrees of fragmentation of the rock mass under investigation. For a model with the same resolution, large-size discontinuities may have quite a few redundant point cloud data that are of little use to improve the identification accuracy whereas small-size discontinuities may not be properly identified due to insufficient number of data points. In this paper, the influence of the degree of fragmentation of rock mass on the identified results was investigated. The uniform grid method was adopted to sparse the 3D point cloud model. The optimal point cloud resolution for different discontinuities was suggested. The applicability and feasibility of the proposed approach were verified via three illustrative examples of typical rock slopes.

关键词： 3D point cloud automatic identification clustering algorithm rock discontinuity UAV

来源：评论

学校读者我要写书评

暂无评论

Nanomechanical-based classification of prostate tumor using atomic force microscopy

引用

PROSTATE 2023年第16期83卷 1591-1601页

作者： Zeng, Jinshu Zhang, Yan Xu, Renfeng Chen, Huitin Tang, Xiaoqiong Zhang, Sheng Yang, Hongqin Fujian Med Univ Affiliated Hosp 1 Dept Ultrasound Imaging Fuzhou Peoples R China Fujian Med Univ Binhai Campus Affiliated Hosp 1 Natl Reg Med Ctr Dept Ultrasound Imaging Fuzhou Peoples R China Fujian Normal Univ Coll Photon & Elect Engn Minist Educ Key Lab Sci & Technol Med Fuzhou Peoples R China Fujian Med Univ Affiliated Hosp 1 Dept Pathol Fuzhou Peoples R China Fujian Med Univ Affiliated Hosp 1 Dept Pathol Fuzhou 350005 Peoples R China Fujian Normal Univ Coll Photon & Elect Engn Key Lab Sci & Technol Med Minist Educ Fuzhou 350007 Peoples R China

BackgroundThe loss of mechanical homeostasis between tumor cells and microenvironment is an important factor in tumor metastasis. In the process, mechanical forces affect cell proliferation, differentiation, migration and tissue *** high spatial resolution of Atomic force microscopy (AFM) technology, our study provides the direct measurement of the nanomechanical properties of prostate cancer clinical tissue *** and MethodsAFM was used to determine the biomechanical properties of prostate tissue with different grade scores. K-means clustering method and fuzzy C-means were used to distinguish the cellular component in prostate tissue from non-cellular component based on their viscoelasticity. Futhermore, AFM measurements in vitro cells, including metastatic prostate cells (PC-3) and normal human prostate cells (PZ-HPV-7) were carried *** Young's modulus was decreased in prostate cancer progression, and the elasticity of cellular component in prostate cancer tissue was smaller than that of normal prostate tissue. PC-3 cells were softer than PZ-HPV-7 cells. Further mechanism investigation showed that the difference in modulus between cancerous and normal prostate tissue may be associated with a greater actin cytoskeleton distribution inside the cancer *** results suggests that the nanomechanical properties can classify the prostate tumor, which could be used as an index for the identification and classification of cancer at cellular level.

关键词： atomic force microscopy classification clustering algorithm prostate cancer viscoelasticity

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：