Multivariate Nonlinear Analysis and Prediction of Shanghai Stock Market by Junhai Ma, Lixia Liu

“…The results indicate that multivariate nonlinear prediction model outperforms univariate nonlinear prediction model, local linear prediction method of multivariate time series outperforms local polynomial prediction method, and BP neural network method. Multivariate nonlinear prediction model is a useful tool for stock price prediction in emerging markets.…”
Get full text

Resistance Spot Welding Defect Detection Based on Visual Inspection: Improved Faster R-CNN Model by Weijie Liu, Jie Hu, Jin Qi

“…Additionally, a new pruning model is introduced, reducing unnecessary layers and parameters in the neural network, leading to faster processing times without sacrificing accuracy. …”
Get full text

Intelligent Prediction of Sieving Efficiency in Vibrating Screens by Bin Zhang, Jinke Gong, Wenhua Yuan, Jun Fu, Yi Huang

“…By the examination of testing points, the prediction performance of least square support vector machine is better than that of the existing formula and neural network, and its average relative error is only 4.2%.…”
Get full text

An Intelligent System for Load Forecasting on a Distribution Network by Saheed Gbadamosi, Ojo Olukayode Adedayo

“…This technique is an integrated system consisting of fuzzy logic systems and Artificial Neural network (ANN). The inputs to the system include days of the week, temperature, time, current and previous hourly load on the distribution network. …”
Get full text

Frequency-Division Combination Forecasting of Stock Market Based on Wavelet Multiresolution Analysis by Shihua Luo, Jiangyou Huo, Zian Dai

“…Using the daily closing price data of SSE (Shanghai Stock Exchange) Composite Index and Shenzhen Component Index as samples, compared with conventional wavelet prediction model, ARIMA model, and BP neural network model, the empirical results show that the new algorithm M-ARIMA-BP can improve the accuracy of volatility forecasting and perform better in predicting prices rising and falling.…”
Get full text

Channel modeling of molecular communication via free diffusion with multiple receiver by Zhuo SUN, Xu BAO, Jie LIN, Wence ZHANG

“…A coexistence scenario with a point source, a pair of absorbing and transparent receiver was considered, an interference factor was introduced in the proposed channel model based on the receiving molecular probability in the transparent receiver considering the influences of the absorbing receiver on the transparent one.Furthermore, the channel model of point source and transparent receiver had been proposed by using Levenberg-Marquardt algorithm combined with artificial neural network to study and predict channel model parameters.The simulation results not only verify the effectiveness of the proposed channel model, but also show that the peak time of any point in the environment is directly proportional to the square of the distance from the point source to the receiver, and inversely proportional to the molecular diffusion coefficient, and the peak time is not affected by the absorbing receiver in the environment.…”
Get full text

Forecasting-Aided Monitoring for the Distribution System State Estimation by S. Carcangiu, A. Fanni, P. A. Pegoraro, G. Sias, S. Sulis

“…In this paper, an innovative approach based on an artificial neural network (ANN) load forecasting model to improve the distribution system state estimation accuracy is proposed. …”
Get full text

Semantic Recognition and Location of Cracks by Fusing Cracks Segmentation and Deep Learning by Qing An, Xijiang Chen, Xiaoyan Du, Jiewen Yang, Shusen Wu, Ya Ban

“…Therefore, a recognition method based on the combination of convolutional neural network and cluster segmentation is proposed. The proposed method realizes the accurate identification of concrete surface crack image under complex background and improves the efficiency of concrete surface crack identification. …”
Get full text

Research on manufacturing energy consumption optimization platform technology based on knowledge-base by Weiwei YANG, Sining WANG, Guide ZHENG, Yaqiong SONG

“…China’s manufacturing industry accounts for the largest proportion of the economy and involves a huge scale.It is of practical significance for enterprises to gradually realize energy consumption optimization through digital technology.Taking automobile manufacturing as an example, a scheme of energy consumption optimization based on knowledge-base was proposed, including the analysis of the characteristics of energy consumption in manufacturing industry, the key technologies of energy consumption optimization and the presentation of application practice.Starting with the production equipment of the enterprise, the law affecting energy consumption was found and a knowledge-base was build through the information of manufacturing execution system and equipment operation status of the enterprise, and the optimization of energy consumption was realized through machine learning algorithms such as neural network and correlation analysis.…”
Get full text

Predicting the Hall-Petch slope of magnesium alloys by machine learning by Bo Guan, Chao Chen, Yunchang Xin, Jing Xu, Bo Feng, Xiaoxu Huang, Qing Liu

“…Two machine learning models, artificial neural network (ANN) and random forest (RF), were built and validated using 138 data. …”
Get full text

Neuro-dynamic Programming to Optimal Control of a Biotechnological Process by Tatiana Ilkova, Mitko Petrov

“…For this purpose, a neural network is used in NDP, which ignores the poor results of the utility criterion. …”
Get full text

Intelligent vulnerability detection system based on graph structured source code slice by Deqing ZOU, Xiang LI, Minhuan HUANG, Xiang SONG, Hao LI, Weiming LI

“…For the intelligent vulnerability detection, the system extracts the graph structured source code slices according to the vulnerability characteristics from the program dependency graph of source code, and then presents the graph structured slice information to carry out vulnerability detection by using the graph neural network model.Slice level vulnerability detection was realized and the vulnerability line was located at the code line level.In order to verify the effectiveness of the system, compared with the static vulnerability detection systems, the vulnerability detection system based on serialized text information, and the vulnerability detection system based on graph structured information, the experimental results show that the proposed system has a high accuracy in the vulnerability detection capability and a good performance in the vulnerability code line prediction.…”
Get full text

Comparison of Machine Learning Techniques for the Prediction of Compressive Strength of Concrete by Palika Chopra, Rajendra Kumar Sharma, Maneek Kumar, Tanuj Chopra

“…Using R miner, the most widely used data mining techniques decision tree (DT) model, random forest (RF) model, and neural network (NN) model have been used and compared with the help of coefficient of determination (R2) and root-mean-square error (RMSE), and it is inferred that the NN model predicts with high accuracy for compressive strength of concrete.…”
Get full text

Daily Precipitation Prediction Based on SVM-CEEMDAN-BiLSTM Model by LING Ming, XIAO Liying, ZHAO Jia, WANG Pinggen, WANG Yin, XIANG Kai, CAI Gaotang

“…In order to solve the problem of low prediction accuracy of the maximum value and rain-free days in daily precipitation series,a coupled model of precipitation prediction based on a support vector machine (SVM),complete ensemble empirical modal decomposition (CEEMDAN),and bi-directional long and short-term memory neural network (BiLSTM) was proposed. This paper applied the coupled model to predict the daily precipitation at Jingdezhen Station and Ganxian Station in the Poyang Lake Basin, and the results were compared with those of traditional model combinations. …”
Get full text

Research on the Prediction Model of the Friction Coefficient of Asphalt Pavement Based on Tire-Pavement Coupling by Miao Yu, Xinquan Xu, Chuanhai Wu, Shanqiang Li, Mingxia Li, Haifeng Chen

“…By integrating the above influence factors, the BP neural network method was applied to the regression of the prediction model for the asphalt pavement friction coefficient. …”
Get full text

Speaker verification method based on deep information divergence maximization by Chen CHEN, Yafeng RONG, Chaoqun JI, Deyun CHEN, Yongjun HE

“…To solve the problem that the nonlinear relationship between speaker representations cannot be accurately captured in speaker verification, an objective function based on depth information divergence maximization was proposed.It could implicitly represent the nonlinear relationship between speaker representations by calculating the similarity between their distributions.Under the supervision of the optimization goal of maximizing the statistical correlation, the deep neural network was optimized towards the direction that the within-class data was more compact and the between-class data were far away from each other, and finally the discrimination of deep speaker representation space could be effectively improved.Experimental results show that compared with other deep learning methods, the relative EER of the proposed method is reduced by 15.80% at most, which significantly improves the system performance.…”
Get full text

New Models for Solving Time-Varying LU Decomposition by Using ZNN Method and ZeaD Formulas by Liangjie Ming, Yunong Zhang, Jinjin Guo, Xiao Liu, Zhonghua Li

“…In this paper, by employing the Zhang neural network (ZNN) method, an effective continuous-time LU decomposition (CTLUD) model is firstly proposed, analyzed, and investigated for solving the time-varying LU decomposition problem. …”
Get full text

Method to generate cyber deception traffic based on adversarial sample by Yongjin HU, Yuanbo GUO, Jun MA, Han ZHANG, Xiuqing MAO

“…In order to prevent attacker traffic classification attacks,a method for generating deception traffic based on adversarial samples from the perspective of the defender was proposed.By adding perturbation to the normal network traffic,an adversarial sample of deception traffic was formed,so that an attacker could make a misclassification when implementing a traffic analysis attack based on a deep learning model,achieving deception effect by causing the attacker to consume time and energy.Several different methods for crafting perturbation were used to generate adversarial samples of deception traffic,and the LeNet-5 deep convolutional neural network was selected as a traffic classification model for attackers to deceive.The effectiveness of the proposed method is verified by experiments,which provides a new method for network traffic obfuscation and deception.…”
Get full text

Flexural Strength Prediction of Welded Flange Plate Connections Based on Slenderness Ratios of Beam Elements Using ANN by Amir A. Hedayat, Ehsan Jazebi, Saman AsadAbadi, Amin Iranpour

“…Proposed theoretical formulas and artificial neural network- (ANN-) based models developed in this study were able to adequately predict the connection strength.…”
Get full text

Deepfake swapped face detection based on double attention by Xiaojuan GONG, Tianqiang HUANG, Bin WENG, Feng YE, Chao XU, Lijun YOU

“…In view of the existing Deepfake detection algorithms, such problems as low accuracy and poor interpretability are common.A neural network model combining the double attention was proposed, which used channel attention to capture the abnormal features of false faces and combined the location of spatial attention to focus the abnormal features.To fully learn the contextual semantic information of the abnormal part of the false face, so as to improve the effectiveness and accuracy of face changing detection.In addition, the decision-making area of real and fake faces was shown effectively in the form of thermal diagram, which provided a certain degree of explanation for the face exchange detection model.Experiments on FaceForensics ++ open source data set show that the detection accuracy of proposed method is superior to MesoInception, Capsule-Forensics and XceptionNet.…”
Get full text