A convergent Deep Learning algorithm for approximation of polynomials by Després, Bruno

“…We start from the contractive functional equation proposed in [4], where it was shown that the polynomial solution of functional equation can be used to initialize a Neural Network structure, with a controlled accuracy. We propose a novel algorithm, where the functional equation is solved with a converging iterative algorithm which can be realized as a Machine Learning training method iteratively with respect to the number of layers. …”
Get full text

Stepwise fuzzy correction of the algorithm filters of random signals by A. A. Lobaty, A. S. Radkevich

“…It is assumed that the gauges are discrete and are described, like the original process assessed, by a discrete mathematical model in the form of difference equations. As an estimation algorithm, we consider a discrete Kalman filter, which, in the general case, when mathematical models are inadequate to real processes, can give distorted information. …”
Get full text

An Algorithm to Develop Lumped Model for Gunn-Diode Dynamics by Umesh Kumar

Subjects: “…Algorithm…”
Get full text

A Scene-Adaptive Phase Gradient Autofocus Algorithm by Caizhen Luo, Yi Liang, Jian Gao, Gang Lei, Chaolei Han

Subjects: “…phase gradient autofocus (PGA) algorithm…”
Get full text

Genetic Algorithm-Enhanced Direct Method in Protein Crystallography by Ruijiang Fu, Wu-Pei Su, Hongxing He

Subjects: Get full text

Hybrid tabu search algorithm for excellent Boolean function by Weiqiong WANG, Haojie XU, Meng CUI, Qiong XIE

Subjects: Get full text

Anomaly domains detection algorithm based on historical data by Fu-xiang YUAN, Fen-lin LIU, Bin LU, Dao-fu GONG

“…An anomaly domains detection algorithm was proposed based on domains’ historical data.Based on statistical differences in historical data of legitimate domains and malicious domains,the proposed algorithm used domains’ lifetime,changes of whois information,whois information integrity,IP changes,domains that share same IP,TTL value,etc,as main parameters and concrete representations of features for classification were given.And on this basis the proposed algorithm constructed SVM classifier for detecting anomaly domains.Features analysis and experimental results show that the algorithm obtains high detection accuracy to unknown domains,especially suitable for detecting long lived malicious domains.…”
Get full text

Novel image registration algorithm for scene-matching navigation by Hongrui YANG, Qiju ZHU, Peixian CAO, Hao GU, Dongdong ZHAO

“…Moreover, unlike deep learning algorithms that require extensive data training for generalization, our algorithm achieves the necessary level of generalization without such extensive training. …”
Get full text

A Heuristic Algorithm for Resource Allocation/Reallocation Problem by S. Raja Balachandar, K. Kannan

“…The performance of our heuristic is compared with the best state-of-art heuristic algorithms with respect to the quality of the solutions found. …”
Get full text

User similarity-based collaborative filtering recommendation algorithm by Hui-gui RONG, Sheng-xu HUO, Chun-hua HU, Jin-xia MO

“…Collaborative filtering recommendation algorithms widely used in e-commerce, recommend interesting content for users from massive data resources by studying their preferences and interests. …”
Get full text

Fast surface reconstruction algorithm with adaptive step size. by Jingguo Dai, Yeqing Yi, Chengzhi Liu

“…This algorithm employs a fixed step size during iterations to enhance convergence. …”
Get full text

Phishing detection algorithm based on attention and feature fusion by ZHANG Sirui, YAN Zhiwei, DONG Kejun, YUCHI Xuebiao

“…For instance, current phishing attacks often employ images in place of text and apply small-scale shifts or rotations to high-weight website logo images to evade traditional detection algorithms that rely on text or image features. To address the problem of escalating adversarial phishing technologies, a phishing detection algorithm based on the attention mechanism and feature fusion was proposed, and a hierarchical classification model was established. …”
Get full text

Real time interpolation algorithm based on Lanczos kernel by Ying GUO, Lun LI, Peng WANG

“…In order to improve the timeliness and reliability of color image scaling algorithms,a high effective real-time color image scaling algorithm was proposed,which first generated the kernel look up table that could be used for whole target image based on Lanczos kernel,and interpolation of all target image pixels had only fixed point operation which had low computational complexity.Meanwhile,an optimized method for rasterizing pixels of target image was proposed,which needed little memory space but embraced high efficiency of memory utilization.The experiment results show that the proposed algorithm achieves good image quality,and the computational complexity is far more less than classic image scaling algorithms.So the proposed algorithm can effectively implement real-time resizing of color images and color videos in any scaling factors.…”
Get full text

Adaptive integration algorithm for stiff ordinary differential equations by Raimondas Čiegis, Olga Suboč

“… The accuracy of one adaptive integration algorithm is investigated. The accuracy of the discretization is estimated by comparing the discrete and exact stability factors. …”
Get full text

Least square-based vehicle position estimation algorithm by PENG Xin, LI Ren-fa, YANG Liu, LIU Liang-jiao

“…A vehicle position estimation algorithm base on least square optimization was prposed.Firstly,the algorithm deduced the convex constraint condition which the distance matrix had to conform within a short time interval.Then,the least square method was employed to estimate the vehicles’ relative position.Finally,the local maps were merged into the global map.Simulation results demonstrate that the algorithm can achieve preferable estimation accuracy,and meet the real time constraint in vehicular networks.…”
Get full text

Algorithm for optimization of cold‑rolled pipe rolling routes by S. V. Pilipenko

Subjects: Get full text

The Optimization Algorithm for Large-Scale In Situ Stress Field by Fei Li, Ningdong Chang

“…In order to reduce the computing cost without losing the accuracy of the calculation, an optimization algorithm combined with a reduced order model, which is realized by the proper orthogonal decomposition algorithm (POD) for large-scale in situ stress field, is put forward in this paper. …”
Get full text

Retracted Article: Using bibliometrics to understand algorithmic finance by Hanan Qudah, Bassam Khalil Atallah Baqila, Jomana Mustafa Odah Albadienah, Mohammad Zakaria AlQudah, Shatha Al Qudah, Samer Alrahamneh, Ahmad Ababne, Ishraq Qudah

Get full text

Region inpainting algorithm of mouth-muffles for facial recognition by Yue LI, Yaguan QIAN, Xiaohui GUAN, Wei LI, Bin WANG, Zhaoquan GU

“…Facial recognition under occlusion is a well-known difficult problem in real scenes.Especially after the outbreak of COVID-19, in airports, stations and other places that need to verify the identity of visitors, the mouth-muffle occlusion greatly reduces the facial features that can be important for identification, and the accuracy of face recognition algorithm decreases.Face de-occlusion was studied, and a novel framework was proposed to restore face, which used the edge generation network to generate edge maps.On this basis, the occluded region was restored by the region completion network while preserving identity information.In order to improve the performance, the spatial weighted adversarial loss and identity-preserving loss were introduced to train the above two networks.Then two face datasets with mouth-muffles were constructed by face landmarks.The experimental results show that the accuracy of facial recognition algorithm ArcFace on the face dataset restored by the proposed model was 98.39%, which was 4.13% higher than that of directly using ArcFace.…”
Get full text

Pruning automatic sphere decoding algorithm and performance analysis by LI Ying, WEI Ji-bo

“…A pruning automatic sphere decoding（PASD） algorithm was presented to reduce the complexity and keep the efficiency of ASD simultaneously.The proposed algorithm efficiently reduced the size of the border node list in ASD by statistical pruning,and obtained the tradeoff between the performance of symbol error ratio（SER） and complexity by setting reasonable parameter’s values.Analysis and simulation show that for a higher level（more than 4） modulation,PASD is able to reduce the number of comparisons by at least 30% as compared to ASD without much penalty of the performance in the same SNR region.…”
Get full text