检索结果-内蒙古大学图书馆

Service Benefit Aware Multi-Task Assignment Strategy for Mobile Crowd Sensing

SENSORS 2019年第21期19卷 4666-4666页

作者： Li, Zhidu Liu, Hailiang Wang, Ruyan Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Key Lab Opt Commun & Networks Chongqing 400065 Peoples R China Key Lab Ubiquitous Sensing & Networking Chongqing 400065 Peoples R China

Mobile crowd sensing (MCS) systems usually attract numerous participants with widely varying sensing costs and interest preferences to perform tasks, where accurate task assignment plays an indispensable role and also faces many challenges (e.g., how to simplify the complicated task assignment process and improve matching accuracy between tasks and participants, while guaranteeing submitted data credibility). To overcome these challenges, we propose a service benefit aware multi-task assignment (SBAMA) strategy in this paper. Firstly, service benefits of participants are modeled based on their task difficulty, task history, sensing capacity, and sensing positivity to meet differentiated requirements of various task types. Subsequently, users are then clustered by enhanced fuzzy clustering method. Finally, a gradient descent algorithm is designed to match task types to participants achieving the maximum service benefit. Simulation results verify that the proposed task assignment strategy not only effectively reduces matching complexity but also improves task completion rate.

关键词： Mobile Crowd Sensing task assignment service benefit users clustering gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning

引用

algorithmS 2023年第2期16卷 99-99页

作者： Tzougas, George Kutzkov, Konstantin Heriot Watt Univ Sch Math & Comp Sci Dept Actuarial Math & Stat Edinburgh EH14 4AS Scotland Teva Pharmaceut Sofia 1407 Bulgaria

We developed a methodology for the neural network boosting of logistic regression aimed at learning an additional model structure from the data. In particular, we constructed two classes of neural network-based models: shallow-dense neural networks with one hidden layer and deep neural networks with multiple hidden layers. Furthermore, several advanced approaches were explored, including the combined actuarial neural network approach, embeddings and transfer learning. The model training was achieved by minimizing either the deviance or the cross-entropy loss functions, leading to fourteen neural network-based models in total. For illustrative purposes, logistic regression and the alternative neural network-based models we propose are employed for a binary classification exercise concerning the occurrence of at least one claim in a French motor third-party insurance portfolio. Finally, the model interpretability issue was addressed via the local interpretable model-agnostic explanations approach.

关键词： predictive insurance analytics logistic regression neural networks deviance loss function cross-entropy loss function regularization procedures CANN approach embedding layers transfer learning Newton-Raphson algorithm gradient descent algorithm LIME model agnostic approach

来源：评论

学校读者我要写书评

暂无评论

A Novel Interactively Recurrent Self-Evolving Fuzzy CMAC and Its Classification Applications

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS 2015年第3期14卷 1550019-1550019页

作者： Wang, Jyun-Guo Tai, Shen-Chuan Lin, Cheng-Jian Natl Cheng Kung Univ Inst Comp & Commun Engn Tainan 701 Taiwan Natl Chin Yi Univ Technol Dept Comp Sci & Informat Engn 57Sec 2Zhongshan Rd Taichung 41170 Taiwan

In this paper, an Interactively Recurrent Self-evolving Fuzzy Cerebellar Model Articulation Controller (IRSFCMAC) model is developed for solving classification problems. The proposed IRSFCMAC classifier consists of internal feedback and external loops, which are generated by the hypercube cell firing strength to itself and other hypercube cells. The learning process of the IRSFCMAC gets started with an empty hypercube base, and then all of hypercube cells are generated and learned online via structure and parameter learning, respectively. The structure learning algorithm is based on the degree measure to determine the number of hypercube cells. The parameter learning algorithm, based on the gradient descent method, adjusts the shapes of the membership functions and the corresponding fuzzy weights of the IRSFCMAC. Finally, the proposed IRSFCMAC model is tested by four benchmark classification problems. Experimental results show that the proposed IRSFCMAC model has superior performance than traditional FCMAC and other models.

关键词： Recurrent network cerebellar model articulation controller fuzzy theory gradient descent algorithm classification

来源：评论

学校读者我要写书评

暂无评论

Event-triggered PID control for wastewater treatment plants

引用

JOURNAL OF WATER PROCESS ENGINEERING 2020年 38卷

作者： Du, Shengli Yan, Qiushuo Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing 100124 Peoples R China

This paper is concerned with the dissolved oxygen control problem in the wastewater treatment plants (WWTPs) based on a dynamic event-triggered PID control strategy (D-EPID). The aim of the paper is to develop a simple event-triggered PID strategy for practical application. The developed strategy differs from existing PID controllers in that, it updates the control input only when certain triggering conditions are satisfied, while existing controllers update the control input at each sampling instant. The latter controller may consume extra energy even there is no need to update the control input. The triggering condition is designed based on the deviation of tracking error and an auxiliary variable. The stability analysis is conducted theoretically via designing an appropriate Lyapunov function, which cannot be provided by existing PID control methods. The controller is designed for improving the control performance of WWTPs by regulating one significant variable, i.e., oxygen concentration at some set points. Simulations based on the BSM1 platform are conducted to verify the effectiveness of the proposed control strategy. Simulation results show that for our proposed control method, the updating number of the control input can be decreased greatly while maintaining the desired tracking performance.

关键词： Event-triggered control gradient descent algorithm PID control WWTPs

来源：评论

学校读者我要写书评

暂无评论

Riemannian optimization for phase retrieval from masked Fourier measurements

引用

ADVANCES IN COMPUTATIONAL MATHEMATICS 2021年第6期47卷 88-88页

作者： Li Huiping Li Song Zhejiang Univ Sch Math Sci 38 Zheda Rd Hangzhou 310027 Peoples R China Hangzhou Normal Univ Dept Math 2318 Yuhangtang Rd Hangzhou 311121 Peoples R China

In this paper, we consider the noisy phase retrieval problem under the measurements of Fourier transforms with complex random masks. Here two kinds of Riemannian optimization algorithms, namely, Riemannian gradient descent algorithm (RGrad) and Riemannian conjugate gradient descent algorithm (RCG), are presented to solve such problem from these special but widely used measurements in practical applications. Since the masked Fourier measurements are less random, we establish stable guarantees for signals by the truncated variants of RGrad and RCG, respectively. First of all, a good initialization is constructed by means of a truncated spectral method. Then we prove that a signal x is an element of C-n can be recovered robustly to bounded noise through these two algorithms, provided that L = O(log n) complex random masks are performed in the measurement process. This implies that the sample complexity is optimal up to a log factor, namely, O(n log n). Particularly, each sequence generated by the truncated RGrad and RCG provably converges to the true solution at a geometric rate in the noiseless case. Finally, several empirical experiments are provided to show the effectiveness and stability of such two kinds of algorithms compared with Wirtinger Flow(WF) algorithm, for which provable guarantee has been set up for signals under masked Fourier measurements, provided that L = O(log(4) n).

关键词： Phase retrieval Riemannian optimization gradient descent algorithm Conjugate gradient descent algorithm Masked Fourier measurements

来源：评论

学校读者我要写书评

暂无评论

TSK Interval Type-2 Fuzzy Neural Networks for Chaotic Time Series Prediction

TSK Interval Type-2 Fuzzy Neural Networks for Chaotic Time S...

引用

8th World Congress on Intelligent Control and Automation (WCICA)

作者： Zhao, Liang Henan Univ Technol Inst Elect Engn Zhengzhou 450000 Peoples R China

ISBN: (纸本)9781424467129

This paper presents TSK interval type-2 fuzzy neural network (TSK IT2FNN) and its learning algorithm for chaotic time series prediction. First, The structure of TSK IT2FNN is decided using the hierarchical fuzzy clustering algorithm. Then its parameters of the precondition membership function and consequence weight are optimized using the gradient descent algorithm. Finally the effectiveness of IT2FNN and its learning algorithm are evaluated by using the Mackey-Glass chaotic time series. The simulation result shows that this proposed method is effective in the paper.

关键词： chaotic time series TSK interval type-2 fuzzy neural network hierarchical fuzzy clustering algorithm gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Temporal community detection based on symmetric nonnegative matrix factorization

引用

INTERNATIONAL JOURNAL OF MODERN PHYSICS B 2017年第13期31卷 1750102-1750102页

作者： Jiao, Pengfei Lyu, Haodong Li, Xiaoming Yu, Wei Wang, Wenjun Tianjin Univ Sch Comp Sci & Technol Tianjin 300072 Peoples R China

To understand time-evolving networks, researchers should not only concentrate on the community structures, an essential property of complex networks, in each snapshot, but also study the internal evolution of the entire networks. Temporal communities provide insights into such mechanism, i.e., how the communities emerge, expand, shrink, merge, split and decay over time. Based on the symmetric nonnegative matrix factorization (SNMF), we present a dynamic model to detect temporal communities, which not only could find a well community structure in a given snapshot but also demands the results bear some similarity to the partition obtained from the previous snapshot. Moreover, our method can handle the situation that of the number of community changes in the networks. Also, a gradient descent algorithm is proposed to optimize the objective function of the model. Experimental results on both the synthetic and real-world networks indicate that our method outperforms the state-of-art methods for temporal community detection.

关键词： Temporal community nonnegative matrix factorization time-evolving networks gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Orientation Estimation Method for Magnetic and Inertial Sensors in the Presence of Magnetic Disturbances

引用

SENSORS 2017年第5期17卷 1161-1161页

作者： Fan, Bingfei Li, Qingguo Wang, Chao Liu, Tao Zhejiang Univ Sch Mech Engn State Key Lab Fluid Power & Mechatron Syst Hangzhou 310027 Zhejiang Peoples R China Queens Univ Dept Mech & Mat Engn Kingston ON K7L 3N6 Canada

Magnetic and inertial sensors have been widely used to estimate the orientation of human segments due to their low cost, compact size and light weight. However, the accuracy of the estimated orientation is easily affected by external factors, especially when the sensor is used in an environment with magnetic disturbances. In this paper, we propose an adaptive method to improve the accuracy of orientation estimations in the presence of magnetic disturbances. The method is based on existing gradient descent algorithms, and it is performed prior to sensor fusion algorithms. The proposed method includes stationary state detection and magnetic disturbance severity determination. The stationary state detection makes this method immune to magnetic disturbances in stationary state, while the magnetic disturbance severity determination helps to determine the credibility of magnetometer data under dynamic conditions, so as to mitigate the negative effect of the magnetic disturbances. The proposed method was validated through experiments performed on a customized three-axis instrumented gimbal with known orientations. The error of the proposed method and the original gradient descent algorithms were calculated and compared. Experimental results demonstrate that in stationary state, the proposed method is completely immune to magnetic disturbances, and in dynamic conditions, the error caused by magnetic disturbance is reduced by 51.2% compared with original MIMU gradient descent algorithm.

关键词： inertial and magnetic sensors orientation estimation magnetic disturbances instrumented gimbal gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A Comparative Performance of Optimizers and Tuning of Neural Networks for Spoof Detection Framework

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2022年第4期13卷 884-890页

作者： Chadha, Ankita Abdullah, Azween Angeline, Lorita Taylors Univ Sch Comp Sci Subang Jaya 47500 Selangor Malaysia

The breakthroughs in securing speaker verification systems have been challenging and yet are explored by many researchers over the past five years. The compromise in security of these systems is due to naturally sounding synthetic speech and handiness of the recording devices. For developing a spoof detection system, the back-end classifier plays an integral role in differentiating spoofed speech from genuine speech. This work conducts the experimental analysis and comparison of up-to-date optimization techniques for a modified form of Convolutional Neural Network (CNN) architecture which is Light CNN (LCNN). The network is standardized by exploring various optimizers such as Adaptive moment estimation, and other adaptive algorithms, Root Mean Square propagation and Stochastic gradient descent (SGD) algorithms for spoof detection task. Furthermore, the activation functions and learning rates are also tested to investigate the hyperparameter configuration for faster convergence and improving the training accuracy. The counter measure systems are trained and validated on ASV spoof 2019 dataset with Logical (LA) and Physical Access (PA) attack data. The experimental results show optimizers perform better for LA attack in contrast to PA attack. Additionally, the lowest Equal Error Rate (EER) of 9.07 is obtained for softmax activation with SGD with momentum wrt LA attack and 9.951 for SGD with nestrov wrt PA attack.

关键词： Spoof detection speech synthesis voice conversion convolutional neural networks optimizers gradient descent algorithm spoofed speech automatic speaker verification

来源：评论

学校读者我要写书评

暂无评论

An unsupervised neural network to solve transportation problems

引用

Journal of the Institution of Engineers (India), Part PR: Production Engineering Division 2005年第SEPT.期86卷 5-7页

作者： Mouli, K. V. V. Chandra Srinivas, J. Subbaiah, K.V. Department of Mechanical Engineering Gandhi Institute of Technology and Management Visakhapatnam 530 045 India Department of Mechanical Engineering Chaitnaya College of Engineering Visakhapatnam 530 041 India Department of Mechanical Engineering AU College of Engineering Visakhapatnam 530 003 India

This article presents a new two-layer neural network model for predicting the optimum solution to linear programming problems. An energy function that transforms linear programming problem into a non-linear function is developed from the objective and constraints. The learning rule, based on gradient descent algorithm, is employed to get the appropriate weight structure of the neural network. The network is tested with different examples including a transportation problem. The results are compared along with the available solutions.

关键词： Energy function gradient descent algorithm Linear programming problem Penalty function Two-layer neural network

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：