Privacy-Oriented Successive Approximation Image Position Follower Processing by Ying Miao, Danyang Shao, Zhimin Yan

“…To solve the detection problem of moving the human body in the dynamic background, the motion target detection module integrates the two ideas of feature information detection and human body model segmentation detection and combines the deep learning framework to complete the detection of the human body by detecting the feature points of key parts of the human body. …”
Get full text

Default Risk Prediction of Enterprises Based on Convolutional Neural Network in the Age of Big Data: Analysis from the Viewpoint of Different Balance Ratios by Zhe Li, Zhenhao Jiang, Xianyou Pan

“…Imbalanced datasets and redundant features are two main problems that can reduce the performance of machine learning models. …”
Get full text

An approach to forecasting damage due to unfavorable circumstances associated with indistinguishability of source data by V. F. Zolotukhin, A. V. Matershev, L. A. Podkolzina

“…The resulting range, which is an elemental group of indistinguishability, characterizes the smaller and larger possible values of the size of the group of a potentially dangerous factor with a composite rather dangerous feature. It is shown that the formulated combinatorial problems without significant changes are applicable to problems in a generalized form, when composite rather dangerous features are determined using not only the operation of intersection, but also uniting and difference; thereby, the initial groups are not necessarily the objects with simple features.Discussion and Conclusions. …”
Get full text

CIDNet: A Maritime Ship Detection Model Based on ISAR Remote Sensing by Fei Liu, Boyang Liu, Hang Zhou, Song Han, Kunlin Zou, Wenjie Lv, Chang Liu

“…To solve these problems, this study proposes a new ISAR target detection model for ships based on deep learning—Complex ISAR Detection Net (CIDNet). …”
Get full text

HRNet Encoder and Dual-Branch Decoder Framework-Based Scene Text Recognition Model by Meiling Li, Xiumei Li, Junmei Sun, Yujin Dong

“…In the encoder module, the HRNet is adopted to realize the cross-parallel aggregation representation with multiple resolutions during feature extraction and then outputs four kinds of feature maps with different resolutions. …”
Get full text

A Composite Method of Marine Shafting’s Fault Diagnosis by Ship Hull Vibrations Based on EEMD by Xiaofei Wen, Wenjie Meng, Xiaoxiao Sun, Ruiping Zhou

“…The fault diagnosis is always a key issue in the security field of marine propulsion system. There are obvious problems like the unsteady working of sensors, distortion of original data, and ambivalent feature information from marine shafting’s vibration or motion. …”
Get full text

Forensic of video object removal tamper based on 3D dual-stream network by Lizhi XIONG, Mengqi CAO, Zhangjie FU

“…In order to solve the problems of inaccurate temporal detection and location of the object removal tampered video， a video tamper forensics method based on 3D dual-stream network was proposed.Firstly， the spatial rich model （SRM） layer was used to extract the high-frequency information from video frames.Secondly， the improved 3D convolution （C3D） network was used as the feature extractor of the dual-stream network to extract the high-frequency information and low-frequency information from the high-frequency frame and the original video frame respectively.Finally， through compact bilinear pooling （CBP） layer， two sets of different feature vectors were fused into one set of feature vectors for classification prediction.The experimental results demonstrate that the classification accuracy of the proposed method in all video frames has an advantage in SYSU-OBJFORG dataset， which makes the temporal detection and location of object removal tampered video more accurate.…”
Get full text

Wielkomiejskie życie Drugiej Rzeczpospolitej w polskim filmie fabularnym okresu międzywojennego. Wstęp do tematu by Wojciech Otto

“… Big city life in the Second Commonwealth of Poland in Polish interwar feature films. An Introduction Polish feature films from the interwar period are to a great extent a reflection of the reality of that time. …”
Get full text

Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification by Yongmin Liu, Fengjiao Xiao, Xinying Zheng, Weihao Deng, Haizhi Ma, Xinyao Su, Lei Wu

“…Abstract Graph neural networks have excellent performance and powerful representation capabilities, and have been widely used to handle Few-shot image classification problems. The feature extraction module of graph neural networks has always been designed as a fixed convolutional neural network (CNN), but due to the intrinsic properties of convolution operations, its receiving domain is limited. …”
Get full text

Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall by XIAO Yu, LI Zehao, WANG Chao

“…Traditional methods for panoramic unfolded image stitching of rock mass borehole walls suffer from insufficient robustness in establishing feature correspondences between adjacent images, as well as poor quality, limited quantity of extracted image feature points and otherc problems. …”
Get full text

LI-YOLO: An Object Detection Algorithm for UAV Aerial Images in Low-Illumination Scenes by Songwen Liu, Hao He, Zhichao Zhang, Yatong Zhou

“…Specifically, in the feature extraction section, this paper proposes a feature enhancement block (FEB) to realize global receptive field and context information learning through lightweight operations and embeds it into the C2f module at the end of the backbone network to alleviate the problems of high noise and detail blur caused by low illumination with very few parameter costs. …”
Get full text

Exploration and comparison of the effectiveness of swarm intelligence algorithm in early identification of cardiovascular disease by Tiantian Bai, Mengru Xu, Taotao Zhang, Xianjie Jia, Fuzhi Wang, Xiuling Jiang, Xing Wei

“…This study systematically evaluated the performance of each feature selection algorithm under different population sizes, specifically by comparing their average running time and objective function values to identify the optimal feature subset. …”
Get full text

A Hybrid Mechanism to Detect DDoS Attacks in Software Defined Networks by ÙAfsaneh Banitalebi Dehkordi, MohammadReza Soltanaghaei, Farsad Zamani Boroujeni

“…Given the importance of this issue,the purpose of this paper is to increase the accuracy of DDoS attack detection using the second order correlation coefficient technique based on â…-entropy according to source IP and selection of optimal features.To select the best features, by examining the types of feature selection algorithms and search methods, the WrapperSubsetEval feature selection algorithm, the BestFirst search method, and the best effective features were selected. …”
Get full text

Machine Learning-Augmented Triage for Sepsis: Real-Time ICU Mortality Prediction Using SHAP-Explained Meta-Ensemble Models by Hülya Yilmaz Başer, Turan Evran, Mehmet Akif Cifci

“…Metaheuristic optimization algorithms, on the other hand, are inspired by natural phenomena, providing significant benefits related to the applicable solutions for complex optimization problems. Considering that complex optimization problems emerge across various disciplines, their successful applications are possible to be observed in tasks of classification and feature selection tasks, including diagnostic processes of certain health problems based on bio-inspiration. …”
Get full text

TS-Resformer: a model based on multimodal fusion for the classification of music signals by Yilin Zhang

“…Deep learning has had a large number of scientific research results in the field of music classification, but the existing deep learning methods still have the problems of insufficient extraction of music feature information, low accuracy rate of music genres, loss of time series information, and slow training. …”
Get full text

A systematic review of machine learning and deep learning approaches in plant species detection by Deepti Barhate, Sunil Pathak, Bhupesh Kumar Singh, Amit Jain, Ashutosh Kumar Dubey

“…Many researchers have expressed their interest in developing automated plant species recognition techniques by analyzing various issues, such as expertise, complex venation structure, interclass and intraclass similarity, occluded leaves, problems with feature extraction of premature and dried leaves, etc. …”
Get full text

ERNIE-TextCNN: research on classification methods of Chinese news headlines in different situations by Yumin Yan

“…Facing the public’s demand for “quick browsing,” Chinese news headlines, characterized by their extremely short text, suffer from limited information, sparse features, and high ambiguity. To rapidly extract deep features from news headlines and enhance the classification performance of extremely short Chinese news headlines, we delve into the inherent characteristics of news headline data, focusing on multi-domain news classification problems and studying datasets of different scales. …”
Get full text

Аlgorithm of fast computation of local image histograms on video card1 by Ph. S. Trotski, B. A. Zalesky

Get full text

Optimal azimuth positioning algorithm for base station antenna based on Gaussian distribution by Songbai LIANG, Feng CHEN, Haiping SONG, Wensheng LI

“…In order to improve the accuracy and efficiency of the discovery of the antenna-feeder problem,an optimal direction angle solution based on Gaussian distribution was proposed to diagnose the antenna-feeder coverage problems of operators.First of all,the location direction information between each MR sampling point reported by the UE and the base station was calculated,and then the proportion of MR sampling points in each interval was calculated,Based on the Gaussian distribution feature,the angle range with the largest proportion of MR sampling points was the appropriate azimuth,which was based on the user hotspot distribution of the sector.Finally,the date of optimal azimuth was compared with the base station azimuth in the background antenna database to detect antenna feeder problems,such as cross feeder,improper antenna coverage direction and incorrect background antenna database,and so on.The field verification shows that,the cost,accuracy and efficiency of the antenna-feeder problems are obviously improved compared with the existing methods.…”
Get full text

DMSU-Net++: A dual multiscale retinal vessel segmentation method based on improved U-Net+. by Liu Ming, Li Qi

“…The method innovatively introduces a multiscale feature extraction module WTSAFM, which realises multiscale feature extraction via wavelet transform, and can capture image information of different frequencies more effectively while enhancing global context understanding. …”
Get full text