Fusion of auto encoders and multi-modal data based video recommendation method by Qiuyang GU, Chunhua JU, Gongxing WU

“…Nowadays, the commonly used linear structure video recommendation methods have the problems of non-personalized recommendation results and low accuracy, so it is extremely urgent to develop high-precision personalized video recommendation method.A video recommendation method based on the fusion of autoencoders and multi-modal data was presented.This method fused two data including text and vision for video recommendation.To be specific, the method proposed firstly used bag of words and TF-IDF methods to describe text data, and then fused the obtained features with deep convolutional descriptors extracted from visual data, so that each video document could get a multi-modal descriptors, and constructed low-dimensional sparse representation by autoencoders.Experiments were performed on the proposed model by using three real data sets.The result shows that compared with the single-modal recommendation method, the recommendation results of the proposed method are significantly improved, and the performance is better than the reference method.…”
Get full text

DEVELOPMENT AND VALIDATION OF NUMERICAL METHOD FOR STRENGTH ANALYSIS OF LATTICE COMPOSITE FUSELAGE STRUCTURES by I. O. Kondakov

“…Parameters of flanges and webs are calculated automatically from the condition of stiffness characteristics equality of real rib and the model. This method allows to perform local strength analysis of high-loaded ribs of lattice structure without use of here-dimensional finite elements, that allows to shorten time of calculations and sufficiently simplify the procedure of analysis of results of calculations.For validation of the suggested method, the results of experimental investigations of full-scale prototype of shell of lattice composite fuselage section have been used. …”
Get full text

Prognosis method to predict small-sized breast cancer affected by fibrocystic disease by S. A. Velichko, E. M. Slonimskaya, I. G. Frolova, D. G. Bukharin, A. V. Doroshenko

“…The purpose of the study is to develop an effective radiological symptom-complex of small-sized breast cancer affected by fibrocystic breast disease by using multivariate statistical methods.Materials and methods. Radiological findings of small-sized breast cancer affected by fibrocystic mastopathy were analyzed in 100 patients with histologically verified diagnosis.Results. …”
Get full text

A simple spot test quantification method to determine formaldehyde in aqueous samples by Amara Dar, Umer Shafique, Jamil Anwar, Waheed-uz-Zaman, Arooj Naseer

“…Spots have been quantified by scanning the spotted TLC and analyzing the image in computer with Visual Basic 6.0 based graphic application. The study consisted of developing an appropriate calibration line, analyzing artificial and real samples, and comparing the new method with a standard spectrophotometric method (NIOSH Method-3500, 1994). …”
Get full text

A Detection Method of Lentinus Edodes Based on Improved YOLOv4 Algorithm by HUANG Ying-lai, LI Da-ming, LU Xin, YANG Liu-song

“…In order to explore the picking of Lentinus edodes which are cultivated in bags, a recognition algorithm based on improved YOLOv4 is proposed.The main improvement measures are: in the structure of PANet (Path Aggregation Network), we add a feature map path with residual attention mechanism to improve the recognition accuracy of small targets, and replace the convolution layer in PANet network with deep separable convolution structure to reduce the amount of parameters.Focal loss is selected to improve the original confidence loss function.In the aspect of data preprocessing, gamma transform method is used to enhance and expand the data.In the training process, the idea of transfer learning is used to load the pre training weight of VOC data set on the backbone network.Compared with the original YOLOv4 algorithm, the mAP value is increased by 4.82 percentage points to 94.39%, and the amount of algorithm parameters is reduced by 58.13%.The algorithm is more efficient and lightweight, providing visual algorithm support for mechanical picking.…”
Get full text

RESEARCH ON PERFORMANCE OPTIMIZATION METHOD OF MECHANICAL PARTS BASED ON CAD/CAE INTEGRATION by WU Qiang, LIU FuYun, HU RuKai, YU HanHong

“…This method took Visual Studio as the platform, used APDL and C⁺⁺ language for redeveloped ANSYS and Solid Works respectively, and developed a digital design system of mechanical parts based on CAD/CAE integration. …”
Get full text

Formation Consensus Control Method With Time-Varying Parameters Based on Virtual Leader by Hongyun Wang, Xiwei Guo, Wenzhao Li, YaQin Li, Weiwei Gao

“…A method of formation pattern alternation and consistent flight control in complex battlefield environment is put forward, considering the single formation pattern during formation flight and failing to deal with the changeable battlefield environment. …”
Get full text

A Method for Automatically Locating Defects in CCTV Inspection Data of Sewer Pipes by Jun Tang, Jisheng Xia, Zhiqiang Xie, Zhaoyong Li, Yuting Zhang

“…Currently, spatial localization of sewer defects in closed circuit television (CCTV) inspection data is primarily performed through manual visual inspections by professional technicians, which is time-consuming and costly. …”
Get full text

Nonplanar Crack Growth Simulation of Multiple Cracks Using Finite Element Method by Yahya Ali Fageehi, Abdulnaser M. Alshoaibi

“…This analysis was performed by using the developed source code software written by Visual Fortran Language. This source code includes the adaptive mesh generation utilizing the advanced front method and also the mesh refinement process. …”
Get full text

Mining Evaluation of Sulfur Deposits in Al-Mishraq Area Using Geostatistical Method by Muzher Jar Hassan, Ghazi Atiya Zarraq

“…The validity and suitability of using the open mine method for extracting sulfur in the study area was discussed based on a decisive and important  factor, which is the stripping ratio, which determines the type of appropriate extractive method, and it was equal to 6 for the entire study area, a large value that exceeded the maximum  permissible limit of  5. …”
Get full text

Assessing the Load-Carrying Capacity of Composite Castellated Beams by Finite Element Method by Mohammad Sadeghi, Ehsan Dehghani, Mohammad Ali Fathali

“…In this study, a comparative analysis of the behaviors of composite beams with castellated and solid-web has been conducted using finite element method. Nine composite castellated beams and nine solid-web composite beams, both with equal heights and cross-sectional areas, were modeled based on castellated configurations. …”
Get full text

Non-destructive Analysis of Pamelo Citrus Fruit Maturity with Impedance Spectroscopy Method by Elfirza Rosiana, Hedy Aditya Baskara, Jan Setiawan, Donie Agus Ardianto, Abdurahman Abdurahman, Riski Maulana, Fitri Yanti

“…Generally, the quality of the fruit is evaluated by a visual judgment ratio that can be wrong. This method also only evaluates the external quality of the fruit. …”
Get full text

Identification Method of Mature Wheat Varieties Based on Improved DenseNet Model by Zihang Liu, Yuting Zhang, Guifa Teng

“…In order to achieve accurate and efficient recognition of wheat varieties planted in wheat fields, a recognition method based on an enhanced DenseNet network model is proposed in this study. …”
Get full text

An Objective Evaluation Method for Image Sharpness Under Different Illumination Imaging Conditions by Huan He, Benchi Jiang, Chenyang Shi, Yuelin Lu, Yandan Lin

“…In this method, the visual saliency, color difference, and gradient information are selected as the image features, and the relevant feature information of these three aspects is extracted from the image as the feature value for the blurred image evaluation under different illumination imaging conditions. …”
Get full text

Screening uncalibrated priority pollutants by improved AHP-CRITIC method at development land by Xinni Wei, Xiuli Dang, Peng Liu, Ge Gao, Hang Zhu, Jiayue Shi, Qiyuan Zhang, Roland Bol, Peng Zhang, Iseult Lynch, Long Zhao

“…To address this challenge and begin to quantify the currently unlisted uncalibrated pollutants present in the industrial land in northeast China, 170 candidate pollutants were screened based on the literature research method. The Analytical Hierarchy Process (AHP) and the Criteria Importance Through Intercrieria Correlation (CRITIC) were utilized equally to screen for priority control of unlisted uncalibrated pollutants. …”
Get full text

IDENTIFICATION OF SOME COMPOSITE MEDICINAL DRUGS CONTAINING PARACETAMOL, WITH IR-SPECTROMETRY METHOD by A. S. Saushkina, L. N. Zinchuk, M. A. Denisov, V. A. Shokurov, D. V. Goncharov

“…However, in order to identify sophisticated counterfeits, only a visual assessment of the drug is not enough. Purpose screening evaluation of potentiallycounterfeited or poor-quality drugs using the IR spectrometry along the total spectrum.Materials and methods. …”
Get full text

Product Image Generation Method Based on Morphological Optimization and Image Style Transfer by Aimin Zhou, Xinle Wang, Yujin Huang, Weitang Wang, Shutao Zhang, Jinyan Ouyang

“…Firstly, based on computational esthetics and principles of visual perception, an esthetic comprehensive evaluation model is constructed and used as the fitness function. …”
Get full text

ECO++: Adaptive deep feature fusion target tracking method in complex scene by Yuhan Liu, He Yan, Qilie Liu, Wei Zhang, Junbin Huang

“…Efficient Convolution Operator (ECO) algorithms have achieved impressive performances in visual tracking. However, its feature extraction network of ECO is unconducive for capturing the correlation features of occluded and blurred targets between long-range complex scene frames. …”
Get full text

Time series image coding classification theory based on Lagrange multiplier method by Wentao Jiang, Ming Zhao, Hongbo Li

“…Researchers have begun transforming one-dimensional time series (TS) into visual representations, harnessing the capabilities of image classification paradigms to improve TS classification accuracy. …”
Get full text

Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements by Yunfei Zhong, Yumei Pu, Xiaoxuan Li, Wenxuan Zhou, Hongjian He, Yuyang Chen, Lang Zhong, Danfei Liu

“…The method reduces the number of model parameters and training time by replacing the backbone network. …”
Get full text