The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Rain rate statistics is an essential part of rain attenuation prediction models. Mostly, the 1-min integration time is required for the rain rate statistics and, if it is not available, the methods in the Rec. ITU-R P.837 are commonly used to convert the available statistics to the statistics with 1-minute integration time. In this work, a novel integration-time conversion method is proposed based...
In this study, a deep denoising recurrent temporal restricted Boltzmann machine network is proposed for long-term prediction of time series. The network is a deep dynamic network model which is stacked by multiple denoising recurrent temporal restricted Boltzmann machines with strong modeling ability for complex high noise time series data. To better deal with high noise data, a random noise is added...
Aiming at the problem of mine fault prediction, a fault prediction model based on KPCA and Pearson correlation coefficient is proposed. The model obtains the abnormal sampling data by the kernel principal component method, extracts the abnormal sampling data and draws the contribution plots, then the Pearson correlation coefficient is compared with the existing fault contribution plots. Finally, according...
Despite remarkable progress of face analysis techniques, detecting landmarks on large-pose faces is still difficult due to self-occlusion, subtle landmark difference and incomplete information. To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement...
Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space. The key idea is to impose the structural constraint that semantic representations...
According to the insufficient research on the complex electromagnetic environment adaptability for the electronic equipment, two kinds of prediction model for dual-frequency in-band electromagnetic radiation effects is established. The decision method of choosing prediction model for electronic equipment is put forward. The ultra-short wave communication stations are selected as equipment under test...
Model selection is a crucial step in choosing a best model from a series of candidate models for data based modelling problems. The commonly used Akaike information criterion (AIC) and Bayesian information criteria (BIC) may not be effective for many real-world modelling problems when the true system model structure is unknown and therefore not included in the candidate model set. This study investigates...
Evaluating workpiece quality of electrical discharge machining (EDM) process is challenging users when trying to extract features from the stochastic and time-consuming process. This study proposes an intelligent sensing unit for EDM (ISU-EDM) to extract key machining features for predicting the roughness of workpieces. In machining, the ISU-EDM can synchronously sample the waveforms of discharge...
Election forecasting has attracted many research efforts. Election forecasting helps the government to optimize the rules of election and candidates to adjust their campaign strategy according to forecasting results, and it contributes to election campaigns. Based on the poll model, this paper proposes poll model improved by delegating and weighting operations applicable to the election of Hongkong...
Aiming at the issues of random delay and delay uncertainty in both the before channel and feedback channel for network control system, the root causes of random delay influence closed-loop control system by case is analysis, and the predictive control method based on neural network to solve the feasibility of existence network random delay in control system closed-loop control has provided. Simulation...
An optimal predictive voltage control based on the deadbeat control scheme is proposed in this paper, which can eliminate the error caused the control delay and can be implemented without transforming to dq rotating coordinate system. So this method can simplify the design process of the control system. Additionally, it simplifies the implementation of switching states based on the principle of space...
Sulfur dioxide is an important source of atmospheric pollution. It is harmful to ecosystems, buildings and humans. Many countries are developing policies to reduce sulfur dioxide emissions. In this paper, prediction of China's sulfur dioxide emissions is studied by discrete grey model with fractional operators. The forecast result shows that the amount of sulfur dioxide emissions is steadily decreasing...
High dropout rate of MOOC is criticized while a dramatically increasing number of learners are appealed to these online learning platforms. Various works have been done on analysis and prediction of dropout. Machine learning techniques are widely applied to this field. However, a single classifier may not always perform reliable for predictions. In this work, we study dropout prediction for MOOC....
This paper presents a machine learning method for event-driven stock prediction, using L1 regularized Logistic regression model. It studies the stock price movement after listed companies make announcements. The model uses specific events extracted from these announcements and combine with financial indicators of listed companies, macro indicators, and technical indicators as dependent variables....
This paper has proposed a design for networked control systems with random time delays and packet dropout in the forward communication channel by using fuzzy theories. First, a simple predictive model was built by means of fuzzy cluster modeling technology and neural network approximation. Then, a prediction oriented fuzzy sliding mode controller was presented to obtain the future control actions'...
In general, predicting hydrocarbon uses seismic data which can be displayed by extracting different seismic physical parameters. Study on the temporal and spatial relationship of the seismic data volume by gray model represents that the seismic data structure and hydrocarbon are closely related. Through research of the study on space-time relation of seismic amplitude, Experts can identify hydrocarbon...
Accurate prediction of system reliability is of plenty of importance to engineering systems for accomplishing the designate function and system safety management. As the concerned system is getting complicated and more sufficient health monitoring measurement is available, the traditional reliability prediction schemes resorting to only one kind of prediction approaches, model-based or data-driven,...
We develop predictive models of pedestrian dynamics by encoding the coupled nature of multi-pedestrian interaction using game theory and deep learning-based visual analysis to estimate person-specific behavior parameters. We focus on predictive models since they are important for developing interactive autonomous systems (e.g., autonomous cars, home robots, smart homes) that can understand different...
We established an experimental region located at Wang Ye Dian forest farm in Chifeng City, Inner Mongolia, China. Within this region, the catastrophe theory model applied for 6 common species single wood volume measurement and calculation to establish a growth model for trees. The experiment was carried out through the actual measurement of the tree height (H), DBH (D), volume (V), diameter (D0) as...
Sudden Oak Death (SOD) is one of the most serious diseases in the west coast of the United States. In the USA, SOD is mainly found in California and Oregon. It is necessary to predict the outbreak risk area of SOD in the future. In this paper, based on current global vegetation cover data, past climate data and future climate data (two emission scenarios RCP26 and RCP85), the Maxent model was used...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.