Study on the Queue-Length Distribution in Geo/G(MWV)/1/N Queue with Working Vacations by Chuanyi Luo, Jiangyi Li, Yinghui Tang

“…Using supplementary variable technique and embedded Markov chain method, the queue-length distribution solution in the form of formula at arbitrary epoch is obtained. …”
Get full text

Neural Network Compensation Control for Output Power Optimization of Wind Energy Conversion System Based on Data-Driven Control by T. Li, A. J. Feng, L. Zhao

“…To solve this problem, data-driven control technology is selected and data-driven controller for the WECS is designed based on the Markov model. The neural networks are designed to optimize the output of the system based on the data-driven control system model. …”
Get full text

Evaluation of the Cyber-Physical System State Under Destructive Impact Conditions Based on a Comprehensive Analysis of Parameters by Anton Mogilny, Elena Basan, Alexey Nekrasov

“…The method was formalized in terms of the Markov decision-making process. Proposed metrics for assessing CPS behavior based on changes in its parameters were defined. …”
Get full text

A stochastic goal-based economic order quantity model for multi-item inventory by Kizito Mubiru

“…This paper proposes a multiobjective goal programming model to optimize the EOQ of multiple items under stochastic demand. Adopting Markov chain methodologies, the model initially defines the demand transition matrix, inventory cost matrix, objective function, priorities, and goal constraints. …”
Get full text

Trajectory differential privacy protection mechanism based on prediction and sliding window by Ayong YE, Lingyu MENG, Ziwen ZHAO, Yiqing DIAO, Jiaomei ZHANG

“…To address the issues of privacy budget and quality of service in trajectory differential privacy protection,a trajectory differential privacy mechanism integrating prediction disturbance was proposed.Firstly,Markov chain and exponential perturbation method were used to predict the location which satisfies the differential privacy and temporal and spatial security,and service similarity map was introduced to detect the availability of the location.If the prediction was successful,the prediction location was directly used to replace the location of differential disturbance,to reduce the privacy cost of continuous query and improve the quality of service.Based on this,the trajectory privacy budget allocation mechanism based on w sliding window was designed to ensure that any continuous w queries in the trajectory meet the ε-differential privacy and solve the trajectory privacy problem of continuous queries.In addition,a privacy customization strategy was designed based on the sensitivity map.By customizing the privacy sensitivity of semantic location,the privacy budget could be customized to improve its utilization.Finally,the validity of the scheme was verified by real data set experiment.The results illustrate that it offers the better privacy and quality of service.…”
Get full text

Spectrum prediction algorithm in ISM band based on two-dimensional LMBP neural network by Xiaoyu WAN, Pan HU, Zhengqiang WANG

“…With the rapid development and application of short-range wireless communications technology，the electromagnetic interference of ISM（2.4 GHz）band has become more apparent.Using the spectral prediction algorithm to predict the information of spectrum occupancy has become an effective way to solve the problem of compatible coexistence between devices.On the basis of verifying the time-domain and frequency-domain correlation of ISM band，an LMBP neural network of time and frequency domain was proposed and applied in the spectral prediction of ISM band.Through simulations and theoretical analysis，the best training combination of time-frequency point （△t=5，△f=2）was obtained.This point improves 95% of the spectrum prediction accuracy under the conditions of the input vector N=9 of the neural network.It increased 9% and 4% prediction accuracy compared with Markov algorithm and time-domain LMBP neural network and it had a better convergence time of training.…”
Get full text

Intelligent anti-jamming decision algorithm of bivariate frequency hopping pattern based on ET-PPO by Yibo CHEN, Zhijin ZHAO

“…In order to further improve its anti-interference ability in complex electromagnetic environment, a PPO algorithm based on weighted importance sampling and eligibility traces (ET-PPO) was proposed.On the basis of the traditional frequency hopping pattern, time-varying parameters were introduced, and the bivariate frequency hopping pattern decision problem was modeled as a Markov decision problem through the construction of the state-action-reward triple.Aiming at the high variance problem of the sample update method of an actor network of the PPO algorithm, weighted importance sampling was introduced to reduce the variance, and the action selection strategy of Beta distribution was used to enhance the stability of the learning stage.Aiming at the problem of slow convergence speed of the evaluator network, the eligibility trace method was introduced, which better balanced the convergence speed and the global optimal solution.The algorithm comparison simulation results in different electromagnetic interference environments show that ET-PPO has better adaptability and stability, and has better performance against obstruction interference and sweep frequency interference.…”
Get full text

App-DDoS detection method based on K-means multiple principal component analysis by Hong-yu YANG, Yuan CHANG

“…In this experiment, the proposed method was compared with the fuzzy synthetical evaluation (FSE) algorithm, the hidden semi-Markov model (HsMM) detection algorithm and the dempster-shafer evidence theory (D-S) algorithm. …”
Get full text

Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition by Dan QU, Wen-lin ZHANG

“…Original eigenphone speaker adaptation method performed well when the amount of adaptation data was suffi-cient.However,it suffered from server overfitting when insufficient amount of adaptation data was provided.A sparse group LASSO(SGL) constraint eigenphone speaker adaptation method was proposed.Firstly,the principle of eigenphone speaker adaptation was introduced in case of hidden Markov model-Gaussian mixture model (HMM-GMM) based speech recognition system.Then,a sparse group LASSO was applied to estimation of the eigenphone matrix.The weight of the SGL norm was adjusted to control the complexity of the adaptation model.Finally,an accelerated proximal gradient method was adopted to solve the mathematic optimization.The method was compared with up-to-date norm algorithms.Experiments on an mandarin Chinese continuous speech recognition task show that,the performance of the SGL con-straint eigenphone method can improve remarkably the performance of the system than original eigenphone method,and is also superior to l₁、l₂-norm and elastic net constraint methods.…”
Get full text

Hierarchical Bayesian Spatio-Temporal Modeling for PM10 Prediction by Esam Mahdi, Sana Alshamari, Maryam Khashabi, Alya Alkorbi

“…The disaggregating technique with a Markov chain Monte Carlo method with Gibbs sampler are used to handle the missing data. …”
Get full text

Joint admission control algorithm based on load transfer in heterogeneous networks by Weiwei XIA, Zhaoming DING, Lianfeng SHEN

“…A load-transfer-based joint admission control (LJAC) algorithm in heterogeneous networks was proposed.The access requirements of users were admitted based on load balancing,the dynamic load transfer of traffics in the overlapping coverage areas of heterogeneous networks were introduced,and the influence of such factors as the layout of heterogeneous networks and the vertical handoff was considered in the algorithm.The integrated system of heterogeneous networks was modeled as a multidimensional Markov chain,the steady-state probabilities were obtained and the quality of service (QoS) performance metrics were derived.Based on the Poisson point process theory,the upper bound of capacity of the heterogeneous networks satisfying QoS limitations was obtained.The admission control parameters of the integrated system of heterogeneous networks were optimized in order to maximize the resource utilization rate as well as guaranteeing the QoS of users.The simulation results demonstrate lower traffic blocking probability,lower failure probability of vertical handoff requirements,and larger system capacity gain can be achieved by using the proposed LJAC algorithm.…”
Get full text

Enhanced Multi-UAV Path Planning in Complex Environments With Voronoi-Based Obstacle Modelling and Q-Learning by Wenjia Su, Min Gao, Xinbao Gao, Zhaolong Xuan

“…To tackle the challenge of obstacle avoidance path planning for multiple unmanned aerial vehicles (UAVs) in intricate environments, this study introduces a Voronoi graph–based model to represent the obstacle-laden environment and employs a Markov decision process (MDP) for single UAV path planning. …”
Get full text

The Discrete-Time Bulk-Service Geo/Geo/1 Queue with Multiple Working Vacations by Jiang Cheng, Yinghui Tang, Miaomiao Yu

“…The service times both in a working vacation and in a busy period and the vacation times are assumed to be geometrically distributed. By using embedded Markov chain approach and difference operator method, queue length of the whole system at random slots and the waiting time for an arriving customer are obtained. …”
Get full text

Distributed Cognitive Radio Spectrum Access with Imperfect Sensing Using CTMC by K. Muthumeenakshi, S. Radha

“…In this paper, a primary prioritized distributed DSA algorithm using continuous-time Markov chain (CTMC) model is proposed. In a distributed scheme, each secondary user needs to be aware of the statistics—arrival and service rates—of the other secondary users to optimize the throughput while maintaining fairness. …”
Get full text

Research on Spatio-temporal Evolution of Land Use and Landscape Patterns along the Yangtze River in Anhui Province by YIN Jian, ZHANG Bin, QIU Yuanhong

“…To explore the law of landscape change in the Yangtze River in Anhui Province,based on the land use data of Anhui section of Yangtze River Basin in 1995,2005 and 2015,this paper analyzes the landscape pattern and its changes of 1995—2005 and 2005—2015,predicts the landscape pattern of land in 2025 by the MCE-CA-Markov constrained by land type suitability,and analyzes the impact of human activities on changes in landscape patterns.The results show that:From 1995 to 2015,the cultivated land was the dominant landscape type in the region.It is predicted that the cultivated land will still occupy the dominant position in 2025,and the construction land will increase.There is an obvious correlation between the decrease of cultivated land area and the increase of construction land area.From 1995 to 2015,the regional landscape showed balanced development,and the connectivity between the landscapes decreased.In 2025,the balance of the landscape will decrease,and the degree of irregularity and fragmentation of the landscape will increase.Through the analysis of landscape development intensity,it is found that the development intensity of landscape as a whole is increasing,that of cultivated land is decreasing,and that of construction land is increasing.Human activities are the main driving force of landscape change.…”
Get full text

Joint optimization method of intelligent service arrangement and computing-networking resource allocation for MEC by Yun LI, Qian GAO, Zhixiu YAO, Shichao XIA, Jishen LIANG

“…., computing power, storage, and bandwidth, with the objective of minimizing task processing latency, the joint optimization of service caching and computing-networking resource allocation was abstracted as a partially observable Markov decision process.Considering the temporal dependency of service request and its coupling relationship with service caching, a long short-term memory network was introduced to capture time-related network state information.Then, based on recurrent multi-agent deep reinforcement learning, a distributed service arrangement and resource allocation algorithm was proposed to autonomously decide service caching and computing-networking resource allocation strategies.Simulation results demonstrate that significant performance improvements in terms of cache hit rate and task processing latency achieved by the proposed algorithm.…”
Get full text

Node selection method in federated learning based on deep reinforcement learning by Wenchen HE, Shaoyong GUO, Xuesong QIU, Liandong CHEN, Suxiang ZHANG

“…To cope with the impact of different device computing capabilities and non-independent uniformly distributed data on federated learning performance, and to efficiently schedule terminal devices to complete model aggregation, a method of node selection based on deep reinforcement learning was proposed.It considered training quality and efficiency of heterogeneous terminal devices, and filtrate malicious nodes to guarantee higher model accuracy and shorter training delay of federated learning.Firstly, according to characteristics of model distributed training in federated learning, a node selection system model based on deep reinforcement learning was constructed.Secondly, considering such factors as device training delay, model transmission delay and accuracy, an optimization model of accuracy for node selection was proposed.Finally, the problem model was constructed as a Markov decision process and a node selection algorithm based on distributed proximal strategy optimization was designed to obtain a reasonable set of devices before each training iteration to complete model aggregation.Simulation results demonstrate that the proposed method significantly improves the accuracy and training speed of federated learning, and its convergence and robustness are also well.…”
Get full text

LED Lighting System Reliability Modeling and Inference via Random Effects Gamma Process and Copula Function by Huibing Hao, Chun Su, Chunping Li

“…Considering the model is so complicated and analytically intractable, the Markov chain Monte Carlo (MCMC) method is used to estimate the unknown parameters. …”
Get full text

Relations of Society Concepts and Religions from Wikipedia Networks by Klaus M. Frahm, Dima L. Shepelyansky

“…Using the reduced Google matrix algorithm, we determine relations and interactions of 23 society concepts and 17 religions represented by their respective articles for each of the eight editions. The effective Markov transitions are found to be more intense inside the two blocks of society concepts and religions while transitions between the blocks are significantly reduced. …”
Get full text

Using the Bayesian Model Averaging Approach for Genomic Selection by Considering Skewed Error Distributions by Azadeh Ghazanfari, Afshin Fayyaz Movaghar

“…Materials and Methods: In this study, we apply the BMA method to linear regression models with skew-normal and skew-t distributions to determine the best subset of predictors. Occam’s window and Markov-Chain Monte Carlo model composition (MC3) were used to determine the best model and its uncertainty. …”
Get full text