General Improvements of Heuristic Algorithms for Low Complexity DOA Estimation by Haihua Chen, Haoran Li, Mingyang Yang, Changbo Xiang, Masakiyo Suzuki

“…Traditional heuristic algorithms usually need a large number of particles and iteration times. …”
Get full text

Medical Images Segmentation Based on Unsupervised Algorithms: A Review by Revella E. A. Armya, Adnan Mohsin Abdulazeez

“…The key aim of this paper is to study some literature on unsupervised algorithms (K-mean, K-medoids) and to compare the working efficiency of unsupervised algorithms with different types of medical images. …”
Get full text

An Adaptive Cauchy Differential Evolution Algorithm for Global Numerical Optimization by Tae Jong Choi, Chang Wook Ahn, Jinung An

“…In this paper, we present an adaptive parameter control DE algorithm. In the proposed algorithm, each individual has its own control parameters. …”
Get full text

Frequency Synchronization Algorithms for MIMO-OFDM Systems with Periodic Preambles by Jian Sun, Fudong Li, Cheng-Xiang Wang, Xuemin Hong, Dongfeng Yuan

Get full text

GNN-based optimization algorithm for joint user scheduling and beamforming by Shiwen HE, Jun YUAN, Zhenyu AN, Min ZHANG, Yongming HUANG, Yaoxue ZHANG

“…The coordinated multi-point (CoMP) transmission technology has the characteristics of reducing co-channel interference and improving spectral efficiency.For the CoMP technology, user scheduling (US) and beamforming (BF) design are two fundamental research problems located in the media access control layer and the physical layer, respectively.Under the consideration of user service quality requirements, the joint user US-BF optimization problem was investigated with the goal of maximizing network throughput.To overcome the problem that the traditional optimization algorithm had high computational cost and couldn’t effectively utilize the network historical data information, a joint US and power allocation (M-JEEPON) model based on graph neural network was proposed to realize joint US-BF optimization by combining the beam vector analytical solution.The simulation results show that the proposed algorithm can achieve the performance matching or even better than traditional optimization algorithms with lower computational overhead.…”
Get full text

A novel improved flooding algorithm for DSR protocol in MANET by Peili CONG, Heng ZHAO

Subjects: Get full text

On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition by Jascha Kolberg, Yannik Schäfer, Christian Rathgeb, Christoph Busch

Get full text

OPTIMIZATION AND RESEARCH OF TIDAL TURBINE BLADES BASED ON GENETIC ALGORITHM by WANG YongDing, LI NingYe

Subjects: Get full text

A Lightweight Small Target Detection Algorithm for UAV Platforms by Yanhui Lv, Bo Tian, Qichao Guo, Deyu Zhang

“…Therefore, a lightweight object detection algorithm tailored for UAV platforms, called RSG-YOLO, is proposed. …”
Get full text

Improved Kalman filter indoor positioning algorithm based on CHAN by Rui JIANG, Yue YU, Youyun XU, Xiaoming WANG, Dapeng LI

“…Due to the raising complexity of the indoor environment, the influence of the non-line-of-sight error is gradually increasing in indoor positioning.How to reduce the non-line-of-sight error in the indoor positioning environment is particularly significant.The UWB indoor positioning technology was selected, Kalman filter has been used widely in reducing the positioning error in indoor non-line-of-sight situations.However, in the process of switching between line of sight and non-line-of-sight scenes, the Kalman filter will produce a new error.To solve this problem, an improved Kalman filter indoor positioning algorithm based on CHAN was proposed.The ranging results of five or more base stations were used to construct a positioning solution equation set.Then the CHAN algorithm that was sensitive to positioning errors under non-line-of-sight conditions was selected to calculate the result.Finally, residual processing was performed with the results of each base station and different confidence regions were judged in line with the residual processing.For different confidence regions, the Kalman filter preset gain factor K was used to improve the stability of the positioning result and reduce the positioning error in the conversion process.In the simulation environment, the error can reach about 80 cm.In real scene, the algorithm can reduce the positioning error in non-line-of-sight scenes to 60 cm, which can improve accuracy 60% higher than normal complex indoor positioning.…”
Get full text

Efficient distributed traffic offloading algorithm based on SDN architecture by Wen-jie QIAN, Zhu REN, Wei-wei CHENG, Wen-tao LYU, Wei-qiang XU

Subjects: Get full text

A Global Optimization Algorithm for Sum of Linear Ratios Problem by Yuelin Gao, Siqiao Jin

“…Therefore, a branch and bound algorithm for solving sum of linear ratios programming problem is put forward, and the convergence of the algorithm is proved. …”
Get full text

Differential Evolution Algorithm for Identification of Structural Damage in Steel Beams by Brunno Emidio Sobrinho, Gilberto Gomes, Welington Vital da Silva, Ramon Silva, Erwin U. L. Palechor, Luciano M. Bezerra

Get full text

A Danger-Theory-Based Immune Network Optimization Algorithm by Ruirui Zhang, Tao Li, Xin Xiao, Yuanquan Shi

“…Existing artificial immune optimization algorithms reflect a number of shortcomings, such as premature convergence and poor local search ability. …”
Get full text

Firefly Optimization-Based Cooperative Localization Algorithm for Intelligent IoT by Cheng peng Liu, Bin Xia, Liye Zhang

“…The traditional firefly localization algorithm only considers part of the ranging information, and the positioning effect is not good. …”
Get full text

Round reduction-based fault attack on SM4 algorithm by Min WANG, Zhen WU, Jin-tao RAO, Hang LING

Subjects: “…SM4 algorithm…”
Get full text

Detection of phishing websites based on the improved TrustRank algorithm by Hao HAN, Bowen LIU, Guoyuan LIN

“…Anti-phishing methods just generally detect phishing sites based on comparing the similarity of pages features,which could be anti-detected when attackers are clear about the extraction process of features.Therefore,a method based on web pages relationship was proposed to detect phishing websites.According to this method,phishing websites were detected by an improved TrustRank algorithm which set up a collection of web pages and used the link relationship between phishing websites and other websites.Experiments show that the improved TrustRank algorithm can focus the trust values of phishing websites on some range with the lower false positive rate,the lower false negative rate and the higher speed compared to other methods.…”
Get full text

Multichannel speech enhancement algorithm based on hybrid reverberation model by XIE Yuan, ZOU Tao, SUN Weijun, XIE Shengli

“…To solve the speech enhancement problem in reverberation and noise scenarios, a new speech enhancement model was constructed integrating multichannel linear prediction model and spatial coherence model, and then a multichannel speech enhancement algorithm based on a hybrid reverberation model was designed. …”
Get full text

An Improved Harmony Search Algorithm for Proactive Routing Protocol in VANET by Ravie Chandren Muniyandi, Mohammad Kamrul Hasan, Mustafa Raad Hammoodi, Ali Maroosi

“…The harmony search (HS) is an emerging metaheuristic optimization algorithm with features of simplicity and exploration efficiency. …”
Get full text

Node selection algorithm based on channel coefficient for cognitive network by Jin-huai GUO, Ke-feng FAN, Su-bing ZHANG

“…To improve communication performance of cognitive network,according to the principle of opportunity cooperative communication,node selection algorithm based on channel coefficient for cognitive network was proposed and studied.Results show that the proposed algorithm can enhance spectrum utilize efficiency and improve network throughput effectively.…”
Get full text