An HMM-Based PoS Tagger for Old Church Slavonic

We present a hybrid HMM-based PoS tagger for Old Church Slavonic. The training corpus is a portion of one text, Codex Marianus (40k) annotated with the Universal Dependencies UPOS tags in the UD-PROIEL treebank. We perform a number of experiments in within-domain and out-of-domain settings, in which the remaining part of Codex Marianus serves as a within-domain test set, and Kiev Folia is used as an out-of-domain test set. Analysing by-PoS-class precision and sensitivity in each run, we combine a simple context-free n-gram-based approach and Hidden Markov method (HMM), and added linguistic rules for specific cases such as punctuation and digits. While the model achieves a rather non-impressive accuracy of 81% in in-domain settings, we observe an accuracy of 51% in out-of-domain evaluation, which is comparable to the results of large neural architectures based on pre-trained contextual embeddings.

The prediction and analysis of COVID-19 epidemic trend by combining LSTM and Markov method

Corona Virus Disease 2019 (COVID-19) has spread rapidly to countries all around the world from the end of 2019, which caused a great impact on global health and has had a huge impact on many countries. Since there is still no effective treatment, it is essential to making effective predictions for relevant departments to make responses and arrangements in advance. Under the limited data, the prediction error of LSTM model will increase over time, and its prone to big bias for medium- and long-term prediction. To overcome this problem, our study proposed a LSTM-Markov model, which uses Markov model to reduce the prediction error of LSTM model. Based on confirmed case data in the US, Britain, Brazil and Russia, we calculated the training errors of LSTM and constructed the probability transfer matrix of the Markov model by the errors. And finally, the prediction results were obtained by combining the output data of LSTM model with the prediction errors of Markov Model. The results show that: compared with the prediction results of the classical LSTM model, the average prediction error of LSTM-Markov is reduced by more than 75%, and the RMSE is reduced by more than 60%, the mean $${R}^{2}$$ R 2 of LSTM-Markov is over 0.96. All those indicators demonstrate that the prediction accuracy of proposed LSTM-Markov model is higher than that of the LSTM model to reach more accurate prediction of COVID-19.

Predicting business processes of the social insurance using recurrent neural network and Markov chain

Purpose Predicting the final status of an ongoing process or a subsequent activity in a process is an important aspect of process management. Semi-structured business processes cannot be predicted by precise and mathematical methods. Therefore, artificial intelligence is one of the successful methods. This study aims to propose a method that is a combination of deep learning methods, in particular, the recurrent neural network and Markov chain. Design/methodology/approach The proposed method applies the BestFirst algorithm for the search section and the Cfssubseteval algorithm for the feature comparison section. This study focuses on the prediction systems of social insurance and tries to present a method that is less costly in providing real-world results based on the past history of an event. Findings The proposed method is simulated with real data obtained from Iranian Social Security Organization, and the results demonstrate that using the proposed method increases the memory utilization slightly more than the Markov method; however, the CPU usage time has dramatically decreased in comparison with the Markov method and the recurrent neural network and has, therefore, significantly increased the accuracy and efficiency. Originality/value This research tries to provide an approach capable of producing the findings closer to the real world with fewer time and processing overheads, given the previous records of an event and the prediction systems of social insurance.

Freeze-Thaw Splitting Strength Analysis of PAC Based on the Gray-Markov Model

In this study, a freeze-thaw split test was carried out to simulate the frost-heaving behavior of permeable asphalt concrete (PAC). Furthermore, the water stability problems caused by spalling and loosening were studied. Through a comparative analysis of the freeze-thaw split ratio of porosities of 19%, 21%, and 24%, the PAC porosity with excellent water stability was determined to be 19–21%. Scanning electron microscopy (SEM) images of PAC with the three porosity values after repeated freezing and thawing verified that the porosities were greater than 24% and the asphalt film peeling area was the largest, resulting in the rapid decline of the PAC freeze-thaw split ratio. The Gray-Markov model was used to predict the water stability of the mixture with a porosity of 21%. Based on the results, a Gray-Markov method for evaluating the PAC water stability in seasonally frozen areas was introduced.

Markov Modeling and Behavior Analysis of Steam Generation (SG) System in a Thermal Power Plant (TPP)

Steam generation (SG) system having five subsystems, namely Economizer, Reheater, Superheater, Furnace, Turbines, and Generator. The differential equations are acquired from the state transition diagram (STD) made pertaining to the real environment of the plant using Markov Method (MM). To get the performance of the system these equations are being worked out using normalizing conditions. The Performance values are attained by providing the apt values of failure and repair rates (FRRs) in the Markov model. Optimal Availability of the system is achieved with the Genetic algorithm (GA) technique.

Mathematical Model Construction of the Production Workshop Based on the Complex Network and Markov Theory

Because of the advantages of the complex network in describing the interaction between nodes, the complex network theory is introduced into the production process of the modern workshop in this paper. According to the characteristics of the workshop, based on extracted key nodes, the complex network model of the workshop is constructed to realize the mathematical description of the production process of the workshop. Aiming at the multidisturbance factors in the production process of the workshop, the key disturbance factors are predicted based on the Markov method, and the propagation dynamics model close to the actual production of the workshop is established. Finally, the bottleneck prediction model of the workshop under the disturbance environment is established. The simulation results show that the proposed prediction model is in good agreement with the actual data, and the coincidence rate is as high as 93.7%.

Methodological Foundations of Mathematical Modeling of the Basic System of Indicators of Information Integrated Logistic Support of Exported Knowledge-Intensive Products

the article describes a general approach for the formation of a basic system of integrated logistics support indicators based on the example of the export of high-tech products. A review of domestic standards for the calculation of various indicators is carried out. The applied calculation methods are described, the choice of the Markov method of calculation is justified, and the search for independent variables and constants is carried out. In conclusion, the conclusions about the need to develop a set of measures to support exports are presented. It is proved that the use of integrated logistics support provides an increase in the competitiveness of domestic knowledge-intensive products on the international market.

Multi-scale flood prediction based on GM (1,2)-fuzzy weighted Markov and wavelet analysis

In order to forecast flood accurately and reveal the relationship between rainstorm and flood at the micro level, a model which combines wavelet analysis, GM (1,2) and fuzzy weighted Markov is built. Taking the Jialu River of Zhengzhou City in China as study area, the GM (1,2) model is constructed between the components of rainfall and flood volume by wavelet decomposition to connect the two variables, then a fuzzy weighted Markov method is introduced to correct the predicted component of flood volume. The corrected results are superimposed to obtain the predicted value of flood. To verify the reliability of the model, the maximum daily, 3-, 5- and 7-day flood volume of the next five floods in Zhongmu and Jiangang hydrological stations are predicted in turn. The results show that the multi-scale flood forecasting model has high overall forecasting accuracy, with the average relative errors all less than 10%. The forecasting accuracy of maximum five-day flood volume is higher than other periods. On the micro level, the results indicate that the fluctuation trend and period of rainfall-flood volume in d1, d2 and d3 are basically the same. Among the components of forecasted flood, the impact of rainfall on flood volume is most significant in the d3 component.

Reliability Analysis of Boost Converters Connected to a Solar Panel Using a Markov Approach

In the past few decades, the energy shortage and global warming problems became a serious concern for humanity. To solve these problems, many countries have evolved renewable energy sources (RESs) such as solar, wind, hydro, tidal, geothermal, and biomass energy sources. Solar energy is usually harvested via a solar panel that is connected to a boost converter to supply the loads. The converter has a key role in the system, since it controls the voltage at the DC bus. If any accidental fault occurs in the converter, the solar panel cannot supply electricity to the loads. Therefore, reliability evaluation of the converter is usually warranted. In this study, reliability evaluation of boost converters connected to a solar panel is carried out using the Markov technique. This technique is widely employed to evaluate the reliability and availability of a system with fixed failure and repair rates. Using the Markov method, we found that the reliability of the typical specific converter considered is 0.9986 for and that its life expectancy or Mean-Time-To-Failure (MTTF) is .