Minimizing Delay in UAV-Aided Federated Learning for IoT Applications With Straggling Devices by Mudassar Liaq, Waleed Ejaz

“…We then use the concurrent deterministic simplex with root relaxation algorithm. We also propose a deep reinforcement learning (DRL)-based solution to improve runtime complexity. …”
Get full text

Prediction model of middle school student performance based on MBSO and MDBO-BP-Adaboost method by Rencheng Fang, Tao Zhou, Baohua Yu, Zhigang Li, Long Ma, Tao Luo, Yongcai Zhang, Xinqi Liu

“…Firstly, the model incorporates the good point set initialization, triangle wandering strategy and adaptive t-distribution strategy to obtain the Modified Dung Beetle Optimization Algorithm (MDBO), secondly, it uses MDBO to optimize the weights and thresholds of the BP neural network, and lastly, the optimized BP neural network is used as a weak learner for Adaboost. …”
Get full text

What Strategy Central Nervous System Uses to Perform a Movement Balanced? Biomechatronical Simulation of Human Lifting by Ali Leylavi Shoushtari

“…To solve the kinematic redundancy in previous studies it is hypothesize that CNS functions as an optimizer, such of that are the task-based algorithms which search to find optimal solution for each specific task. …”
Get full text

Energy Efficiency Maximization for Device-to-Device Communication Underlaying Cellular Networks on Multiple Bands by Yuan Zhang, Yang Yang, Linglong Dai

“…Finally, simulation results demonstrate that the proposed algorithm can achieve the near-optimal EE with much better performance than the conventional algorithm.…”
Get full text

Energy-Balanced Routing for Maximizing Network Lifetime in WirelessHART by Sheng Zhang, Ao Yan, Tianming Ma

“…Then node communication load, the residual energy, and the link transmission power are integrated as a link cost function that is accurately measured in this algorithm. A node chooses the optimal next hop by comparing the link cost function of all its neighbor nodes, which guarantees the energy balancing of the whole network. …”
Get full text

Automation and control of the vacuum block by Melikov Elchin, Maharramova Tamella, Safarova Aygun

“…In a wide range of changing conditions in input disturbing factors in quantity and quality, as well as insufficient operational quality information on the selected petroleum products, the proposed method and principles of development algorithm for controlling the process under study allows for prompt preliminary local regulation modes correction and the selection of new optimal modes for adaptive control as a whole. …”
Get full text

铰链四杆刚体导引机构综合的区间逃逸粒子群算法 by 易建, 何兵, 车林仙

“…The length of the bars is regarded as the restrict condition to obtain the unconstrained optimization model for rigid-body guidance approximate kinematc synthesis of hinged 4-bar linkages and this optimal problem is solved by means of the particle swarm optimization （PSO） algorithm. …”
Get full text

A Multiple Collision Channel Assignment Based on Imperfect Game Theory by Haofeng Dai, Shibiao He, Mian Tan, Pengyu Zheng, Hui Zhang

“…The channel allocation in wireless network will greatly affect the whole performance of the network. In order to solve this optimization problem, a kind of non cooperation channel allocation algorithm based on imperfect information was put forward. …”
Get full text

A Multiple Collision Channel Assignment Based on Imperfect Game Theory by Haofeng Dai, Shibiao He, Mian Tan, Pengyu Zheng, Hui Zhang

“…The channel allocation in wireless network will greatly affect the whole performance of the network. In order to solve this optimization problem, a kind of non cooperation channel allocation algorithm based on imperfect information was put forward. …”
Get full text

Enhancement of underwater acoustic signal based on denoising automatic-encoder by Jingwei YIN, Wuxiong LUO, Li LI, Xiao HAN, Longxiang GUO, Jianfeng WANG

“…Aiming at the difficulty of feature extraction of echo signal in active sonar,a self-encoder algorithm based on the combination of denoising self-encoder and convolution denoising self-encoder was proposed.Firstly,the preprocessing of noisy signal was carried out by using the advantage of denoising self-encoder in signal as a whole,and then the local feature of signal was optimized by combining convolutional denoising self-encoder to denoise the signal locally,so as to enhance the signal.The time domain waveform of the received signal is used as the feature input by the algorithm,and retains the signal’s amplitude and phase characteristics.The experimental results show that the algorithm not only effectively reduces the noise component in the signal,but also achieves better recovery effect in both time and frequency domains.…”
Get full text

Piecewise Model and Parameter Obtainment of Governor Actuator in Turbine by Jie Zhao, Li Wang, Dichen Liu, Jun Wang

“…Several testing functions are selected to compare genetic algorithm and particle swarm optimization algorithm (GA-PSO) with other basic intelligence algorithms. …”
Get full text

Research on Discrete Dynamic System Modeling of Vocal Performance Teaching Platform Based on Big Data Environment by Xiaohui Gong

“…The results show that the optimization model based on the deep recurrent neural network algorithm has the advantages of high feasibility, high intelligence, and wide range of applications. …”
Get full text

Trail-Using Ant Behavior Based Energy-Efficient Routing Protocol in Wireless Sensor Networks by Soon-gyo Jung, Byungseok Kang, Sanggil Yeoum, Hyunseung Choo

“…Swarm Intelligence (SI) observes the collective behavior of social insects and other animal societies. Ant Colony Optimization (ACO) algorithm is one of the popular algorithms in SI. …”
Get full text

Next generation network resource allocation method based on cooperative game and decision-making in advance by RAO Xiang, ZHANG Shun-yi, SUN Yan-fei, DING Wen-tao

“…It’s an important way to guarantee QoS for the next generation network（NGN） with diverse services by allo-cating resources reasonably and optimizing the efficiency of whole network according to diverse service styles.A net-work resource allocating method based on co-operative game theory for NGN was proposed and analyzed,and it had a weakness which brought about overgreat system costing.In order to overcome this weakness,an idea about deci-sion-making in advance was added,and an improved resource allocation algorithm was proposed,which could guarantee the efficiency of whole network best and reduce the system costing.Simulation results of this method show its validity.…”
Get full text

Energy Management Strategy Based on the Driving Cycle Model for Plugin Hybrid Electric Vehicles by Xiaoling Fu, Huixuan Wang, Naxin Cui, Chenghui Zhang

“…The state of charge (SOC) profile can be obtained by the DP algorithm for the whole driving cycle. In order to optimize the energy management strategy in the hybrid power system, the optimal motor torque control sequence can be calculated using the DP algorithm for the segments between the traffic intersections. …”
Get full text

Next generation network resource allocation method based on cooperative game and decision-making in advance by RAO Xiang, ZHANG Shun-yi, SUN Yan-fei, DING Wen-tao

“…It’s an important way to guarantee QoS for the next generation network（NGN） with diverse services by allo-cating resources reasonably and optimizing the efficiency of whole network according to diverse service styles.A net-work resource allocating method based on co-operative game theory for NGN was proposed and analyzed,and it had a weakness which brought about overgreat system costing.In order to overcome this weakness,an idea about deci-sion-making in advance was added,and an improved resource allocation algorithm was proposed,which could guarantee the efficiency of whole network best and reduce the system costing.Simulation results of this method show its validity.…”
Get full text

参数方程曲线的最优逼近算法及实现 by 丁克会, 席平原, 周红斌

“…The features of single and double arc approximating,and combines the merits of two kinds of fitting are discussed. By the algorithm of approximating curve in optimizing three-point arc and mixing single and double arc in permission tolerance,smooth link of whole approximating arc with inflexion points and extreme value points is attained. …”
Get full text

UAV-Enabled Inspection System With No-Fly Zones: DRL-Based Joint Mobile Nest Scheduling and UAV Trajectory Design by Jin Dai, Yunfei Gao, Chao Cai, Wei Xiong, Manjia Liu

“…Then we propose an efficient two-step optimization method that involves optimizing the UAV trajectory with a modified multi-step dueling DDQN (MSD-DDQN) algorithm and planning the mobile nest’s path using the A* algorithm. …”
Get full text

Research on deep reinforcement learning based intelligent shop scheduling method by Zihui LUO, Chengling JIANG, Liang LIU, Xiaolong ZHENG, Huadong MA

“…The unprecedented prosperity of the industrial internet of things (IIoT) has opened up a new path for the traditional industrial manufacturing model.Intelligent shop scheduling is one of the key technologies to achieve the overall control and flexible production of the whole production process.It requires an effective plan with a minimum makespan to allocate multiple processes and multiple machines for production scheduling.Firstly, the shop scheduling problem was defined as a Markov decision process (MDP), and a shop scheduling model based on the pointer network was established.Secondly, the job scheduling process was regarded as a mapping from one sequence to another, and a new shop scheduling algorithm based on deep reinforcement learning (DRL) was proposed.By analyzing the convergence of the model under different parameter settings, the optimal parameters were determined.Experimental results on different scales of public data sets and actual production data sets show that the proposed DRL algorithm can obtain better performances.…”
Get full text

Designing pathways for bioproducing complex chemicals by combining tools for pathway extraction and ranking by Anastasia Sveshnikova, Omid Oftadeh, Vassily Hatzimanikatis

“…Abstract The synthesis of many important biochemicals involves complex molecules and numerous reactions. The design and optimization of whole-cell biocatalysts for the production of these molecules requires metabolic modeling to extract production pathways from biochemical databases and integrate them into genome-scale models of the host. …”
Get full text