Enhancing stock index prediction: A hybrid LSTM-PSO model for improved forecasting accuracy. by Xiaohua Zeng, Changzhou Liang, Qian Yang, Fei Wang, Jieping Cai

“…Moreover, increasing PSO iterations lead to gradual loss reduction, which indicates PSO-LSTM's good convergence. …”
Get full text

Indoor RFID localization algorithm based on adaptive bat algorithm by Liangbo XIE, Yuyang LI, Yong WANG, Mu ZHOU, Wei NIE

“…Aiming at the problem that long time-consuming and poor positioning accuracy using geometric method in the traditional UHF RFID indoor localization algorithm, an RFID indoor positioning algorithm based on adaptive bat algorithm (ABA) was proposed.Firstly, the phase of multiple frequency points was obtained by frequency hopping technology, and the location evaluation function of bat algorithm was established based on the angle information of multiple signal classification (MUSIC) algorithm and the distance information of clustering.Secondly, the bat location was initialized by tent reverse learning to increase the diversity of the population, and the adaptive weight factor was introduced to update the bat location.Finally, the target position was searched iteratively based on the position evaluation function to achieve fast centimeter level positioning.Experimental results show that the median localization error of the proposed algorithm is 7.74 cm, and the real-time performance is improved by 12 times compared with the traditional positioning algorithm based on the Chinese remainder theorem (CRT).…”
Get full text

TOPOLOGY OPTIMIZATION DESIGN OF RELIABILITY STRATEGY FOR TENT FRAME BASED ON UNCERTAINTY THEORY by LI KongWei, XU BaoLiang, LUO Yi, LV GuiFang

“…The results of the mechanical simulations show that the scheme not only obtains the ideal results, but also avoids repeated iterative scheme trial calculations, thus significantly reducing the time costs and workload of the R＆D process, thus promising optimal promotion value and applicability in the engineering fields.…”
Get full text

2RPS/2SPS Parallel Mechanism and Kinematics Analysis by Zhou Yijun, Chen Yefu, Su Ronghai

“…The inverse positional solution equation is established by the space coordinate transformation equation and the closed vector method，and the forward position problem is performed by Newton iteration method in numerical analysis based on inverse solution. …”
Get full text

The Promotion Effect of Computer-Aided Technology Combined with RBF Neural Network Algorithm on Art Design by Chunliang Pan, Yuning Pan

“…Because noise is ubiquitous in reality, the evolution of system dynamics often cannot be carried out strictly according to the iterative rules. In addition, this study shows the changing rules of the competition relationship and the distribution of competitors under the interference of noise. …”
Get full text

Polynomial estimation method for PN sequence based on reliability accumulation by Song CHEN, Kai-zhi HUANG, Hua ZHAO

“…The issues of insufficient efficiency and poor error-tolerance of current high-order polynomial estimation me-thods under error conditions were studied.By combining the iterative berlekamp-massey(BM)algorithm in GF(2)and the improved Chase algorithm,a novel algorithm based on reliability accumulation was proposed.The sequence soft infor-mation was mapped to sequence reliability as the input information of BM algorithm,and the corresponding output relia-bility of estimated polynomial was accumulated as the rule of correct polynomial.In order to improve the estimation pre-cision,the candidate reliability-accumulated polynomial set were reduced by the characteristics of primitive polynomial in GF(2).The simulation results show that the proposed method is irrelevant with the tapped number of ator poly-nomial,and has a good estimation performance to estimate 17-order polynomials when the sequence BER is 18%.…”
Get full text

Research on Management Model Based on Deep Learning by Yuting Zhao

“…The error of prediction is updated according to variable hidden layers and nodes within iteration. Improved DNN is used and modify weights that have an effect on the features extracted in advance to increase the accuracy and precisions are used. …”
Get full text

Deep and robust resource allocation for random access network based with imperfect CSI by Weihua WU, Guanhua CHAI, Qinghai YANG, Runzi LIU

“…A deep and robust resource allocation framework was proposed for the random access based wireless networks,where both the communication channel state information (C-CSI) and the interference channel state information (I-CSI) were uncertain.The proposed resource allocation framework considered the optimization objective of wireless networks as a learning problem and employs deep neural network (DNN) to approximate optimal resource allocation policy through unsupervised manner.By modeling the uncertainties of CSI as ellipsoid sets,two concatenated DNN units were proposed,where the first was uncertain CSI processing unit and the second was the power control unit.Then,an alternating iterative training algorithm was developed to jointly train the two concatenated DNN units.Finally,the simulations verify the effectiveness of the proposed robust leaning approach over the nonrobust one.…”
Get full text

Alternating minimum mean square error hybrid beamforming algorithm in mmWave MIMO system by Min SHEN, Hao XU, Yun HE, Pengguang ZHOU

“…The two-stage hybrid beamforming architecture can solve the problem of limited number of RF chains effectively.However,it is still difficult to design a hybrid beamforming algorithm with better performance.In order to achieve higher spectral efficiency,an alternating minimum mean square error (Alt-MMSE) hybrid beamforming algorithm was proposed.Firstly,the initial digital matrix by using the orthogonal properties of the digital matrix was designed,and then the digital matrix by minimizing the square error of the transmitted signal and the received signal was updated.During each iteration,the phase of the analog matrix could be obtained from the updated digital matrix and the optimal fully digital matrix.The simulation results show that the proposed algorithm has better performance and is closer to fully digital beamforming than OMP hybrid beamforming algorithm and hybrid processing scheme based on matrix decomposition .…”
Get full text

Energy-efficient cooperative sensing and transmission in relay-assisted cognitive radio network by Li FENG, Yu-jun KUANG, Bin-wei WU, Xin-chuan FU

“…An innovative EE-oriented cooperative sensing and transmission scheme in relay-assisted cognitive radio networks,called energy-efficient best-relay cooperative transmission (BCT) was proposed.Based on the BCT scheme,mean energy efficiency (MEE) maximization problem with sensing duration and transmitting power as optimization variables was modeled for fading channels under constraint of minimal secondary outage probability.By virtue of Jensen’s inequality,the original optimization problem was decomposed into two relatively independent subproblems which solved sensing duration and power allocation respectively.And for the two subproblems,an efficient cross iteration based algorithm was proposed to obtain the suboptimal solutions.Both analytical and simulation results demonstrate that the proposals can achieve significantly higher EE while enhancing reliability of secondary transmission remarkably compared to non-cooperation single cognitive transmission schemesin high QoS requirement.…”
Get full text

Multi-scale guided filtering integrated with superpixel and patch shift by Jianwu LONG, Jiangzhou ZHU

“…In order to avoid the phenomenon that edges were easily blurred during filtering, a multi-scale guided filtering integrated with superpixel and patch shift was proposed.Firstly, the bilateral filtering was applied to an input image to get more accurate superpixel regions.Then, the overlapping was used as the final filtering region, which was formed by the local window and the superpixel.The local window was selected by a metric function so that it did not contain edge information as much as possible.Finally, a small-scale window was used to preserve the edges, and then the window scale was increased for iterative guided filtering.The final filtering output was calculated by fusing the results of different window scales to smooth details while preserving the structural edges.Additionally, the evaluation index of filtering results quality was proposed and compared in different algorithms.The proposed algorithm has stronger edge preservation ability and can obtain better filtering effectiveness than other algorithms.…”
Get full text

Edge computing offloading policies and resource allocation considering system fairness in trusted environments by Shouyi YANG, Fukang LI, Ruimin REN

“…Considering the fairness problem in edge computing in an unreliable trust environment, the offloading decision and resource allocation problem of edge computing was studied for a multi-user multi-server scenario.Based on the proposed real-time trust model, system fairness was defined from the perspective of user satisfaction, a joint optimization model considering trust and fairness was established, and a trust-based task offloading and resource allocation (TOA) algorithm was proposed on this basis.The original NP-hard problem was converted into multiple deterministic optimization subproblems, the offloading strategy was determined based on the backtracking algorithm, and the optimization of resource allocation was accomplished by using the Lagrange multiplier method, the convex optimization toolbox, and the bifurcated iterative search method, so as to achieve system fairness and enhance user satisfaction.Simulation experimental results show that the proposed algorithm outperforms other benchmark algorithms.…”
Get full text

Neural network decoding of the block Markov superposition transmission by Qianfan WANG, Sheng BI, Zengzhe CHEN, Li CHEN, Xiao MA

“…A neural network (NN)-based decoding algorithm of block Markov superposition transmission (BMST) was researched.The decoders of the basic code with different network structures and representations of training data were implemented using NN.Integrating the NN-based decoder of the basic code in an iterative manner,a sliding window decoding algorithm was presented.To analyze the bit error rate (BER) performance,the genie-aided (GA) lower bounds were presented.The NN-based decoding algorithm of the BMST provides a possible way to apply NN to decode long codes.That means the part of the conventional decoder could be replaced by the NN.Numerical results show that the NN-based decoder of basic code can achieve the BER performance of the maximum likelihood (ML) decoder.For the BMST codes,BER performance of the NN-based decoding algorithm matches well with the GA lower bound and exhibits an extra coding gain.…”
Get full text

Gerschgorin disk theorem based spectrum sensing for wideband cognitive radio by Bin SHEN, Shu WANG, Qiong HUANG, Qian-bin CHEN

“…Gerschgorin disk theorem (GDT) based wideband spectrum sensing methods, namely Gerschgorin likelihood estimate(GLE) algorithm and Gerschgorin disk radii iteration(GDRI) algorithm, were proposed for cognitive radios. …”
Get full text

Convergence of Linear Bregman ADMM for Nonconvex and Nonsmooth Problems with Nonseparable Structure by Miantao Chao, Zhao Deng, Jinbao Jian

“…We show that any cluster point of the iterative sequence generated by the proposed algorithm is a critical point, under mild condition. …”
Get full text

RW-MC:self-adaptive random walk based matrix completion algorithm by Xin-heng WANG, Qian-yun WANG, Jia-jie WANG, Guo-feng ZHAO, Wen-qiang JIN

“…Concerning the continually perceiving performance of virtual access points (VAP) was urgent in software-defined wireless network (SDWN),with the features of VAPs’ measurement data (VMD),a self-adaptive matrix completion algorithm based on random walk was proposed,named RW-MC.Firstly,the discrete ratio and covering ratio of VMD account for a sample determination model was used to claim initial samples.Secondly,random walk model was implemented for generating sampling data points in the next iteration.Finally,a self-adaptive sampling redress model concerning the differences between the current error rates and normalize error rates of neighboring completion matrices.The experiments show that the approach can collect the real-time sensory data,meanwhile,maintain a relatively low error rate for a small sampling rate.…”
Get full text

Project Management of Information System using Scrum Framework in the Development Of Mediahome SMM Website by Ari Afriansah, Falentino Sembiring, Rieska Rahayu Ayuningsih, Sudin Saepudin

“…The Scrum framework was utilized for project development, proving effective in facilitating the iterative and structured management of tasks. During the development process, some technical issues arose, particularly related to the migration of servers from DomaiNesia to ProviderIndo. …”
Get full text

Dynamic Resource Management in 802.11 Wireless Mesh Networks by George Athanasiou

“…This index reflects the way the communication load is shared in the neighboring APs. The iterative heuristic algorithms that we propose controls the communication load of each mesh AP in a distributed manner. …”
Get full text

Electromagnetic signal fast adversarial attack method based on Jacobian saliency map by Jian ZHANG, Xia ZHOU, Yiran ZHANG, Zicong WANG

“…In order to generate high-quality electromagnetic signal countermeasure examples, a fast Jacobian saliency map attack (FJSMA) method was proposed.The Jacobian matrix of the attack target class was calculated and feature saliency maps based on the matrix were generated, then the most salient feature points were iteratively selected and perturbations in their neighborhood were continuously added while introducing a single point perturbation constraint, finally adversarial examples were generated.Experimental results show that, compared with Jacobian saliency map attack method, FJSMA improves the generation speed by about 10 times while maintaining the same high attack success rate, and improves the similarity by more than 11%, and compared with other gradient-based methods, the attack success rate is improved by more than 20%, and the similarity is improved by 20% to 30%.…”
Get full text

An Improved Sensitivity Method for the Simultaneous Identification of Unknown Parameters and External Loads of Nonlinear Structures by Chongwen Wang, Chengbin Du

“…In addition, the key issues associated with the sensitivity method are systematically studied, and suggestions for improvement are put forward, including the use of the difference method instead of the derivative method to calculate the sensitivity, the use of a fixed regularization parameter instead of the traditional regularization parameter calculation methods, and measures for guarantee of iterative convergence. The improved sensitivity method is applied to two types of nonlinear structures, and the effects of the regularization parameter, distribution of measured points, response types, noise levels, and the magnitude of the perturbation on the identified results are discussed.…”
Get full text