The Fitting Optimization Path Analysis on Scale Missing Data: Based on the 507 Patients of Poststroke Depression Measured by SDS

Objective. To explore the optimal fitting path of missing data of the Scale to make the fitting data close to the real situation of patients’ data. Methods. Based on the complete data set of the SDS of 507 patients with stroke, the data simulation sets of Missing Completely at Random (MCAR), Missing at Random (MAR), and Missing Not at Random (MNAR) were constructed by R software, respectively, with missing rates of 5%, 10%, 15%, 20%, 25%, 30%, 35%, and 40% under three missing mechanisms. Mean substitution (MS), random forest regression (RFR), and predictive mean matching (PMM) were used to fit the data. Root mean square error (RMSE), the width of 95% confidence intervals (95% CI), and Spearman correlation coefficient (SCC) were used to evaluate the fitting effect and determine the optimal fitting path. Results. when dealing with the problem of missing data in scales, the optimal fitting path is ① under the MCAR deletion mechanism, when the deletion proportion is less than 20%, the MS method is the most convenient; when the missing ratio is greater than 20%, RFR algorithm is the best fitting method. ② Under the Mar mechanism, when the deletion ratio is less than 35%, the MS method is the most convenient. When the deletion ratio is greater than 35%, RFR has a better correlation. ③ Under the mechanism of MNAR, RFR is the best data fitting method, especially when the missing proportion is greater than 30%. In reality, when the deletion ratio is small, the complete case deletion method is the most commonly used, but the RFR algorithm can greatly expand the application scope of samples and save the cost of clinical research when the deletion ratio is less than 30%. The best way to deal with data missing should be based on the missing mechanism and proportion of actual data, and choose the best method between the statistical analysis ability of the research team, the effectiveness of the method, and the understanding of readers.

Toward the Next Generation of Digitalization in Agriculture Based on Digital Twin Paradigm

Digitalization has impacted agricultural and food production systems, and makes application of technologies and advanced data processing techniques in agricultural field possible. Digital farming aims to use available information from agricultural assets to solve several existing challenges for addressing food security, climate protection, and resource management. However, the agricultural sector is complex, dynamic, and requires sophisticated management systems. The digital approaches are expected to provide more optimization and further decision-making supports. Digital twin in agriculture is a virtual representation of a farm with great potential for enhancing productivity and efficiency while declining energy usage and losses. This review describes the state-of-the-art of digital twin concepts along with different digital technologies and techniques in agricultural contexts. It presents a general framework of digital twins in soil, irrigation, robotics, farm machineries, and food post-harvest processing in agricultural field. Data recording, modeling including artificial intelligence, big data, simulation, analysis, prediction, and communication aspects (e.g., Internet of Things, wireless technologies) of digital twin in agriculture are discussed. Digital twin systems can support farmers as a next generation of digitalization paradigm by continuous and real-time monitoring of physical world (farm) and updating the state of virtual world.

Research on Artificial Intelligence Classification and Statistical Methods of Financial Data in Smart Cities

In order to improve the effect of financial data classification and extract effective information from financial data, this paper improves the data mining algorithm, uses linear combination of principal components to represent missing variables, and performs dimensionality reduction processing on multidimensional data. In order to achieve the standardization of sample data, this paper standardizes the data and combines statistical methods to build an intelligent financial data processing model. In addition, starting from the actual situation, this paper proposes the artificial intelligence classification and statistical methods of financial data in smart cities and designs data simulation experiments to conduct experimental analysis on the methods proposed in this paper. From the experimental results, the artificial intelligence classification and statistical method of financial data in smart cities proposed in this paper can play an important role in the statistical analysis of financial data.

Partial Discharge Pulse Segmentation Approach of Converter Transformers Based on Higher Order Cumulant

As one of the most effective methods to detect the partial discharge (PD) of transformers, high frequency PD detection has been widely used. However, this method also has a bottleneck problem; the biggest problem is the mixed pulse interference under the fixed length sampling. Therefore, this paper focuses on the study of a new pulse segmentation technology, which can separate the partial discharge pulse from the sampling signal containing impulse noise so as to suppress the interference of pulse noise. Based on the characteristics of the high-order-cumulant variation at the rising edge of the pulse signal, a method for judging the starting and ending time of the pulse based on the high-order-cumulant is designed, which can accurately extract the partial discharge pulse from the original data. Simulation results show that the location accuracy of the proposed method can reach 94.67% without stationary noise. The field test shows that the extraction rate of the PD analog signal can reach 79% after applying the segmentation method, which has a great improvement compared with a very low location accuracy rate of 1.65% before using the proposed method.

Interpretable Autoencoders Trained on Single Cell Sequencing Data Can Transfer Directly to Data from Unseen Tissues

Autoencoders have been used to model single-cell mRNA-sequencing data with the purpose of denoising, visualization, data simulation, and dimensionality reduction. We, and others, have shown that autoencoders can be explainable models and interpreted in terms of biology. Here, we show that such autoencoders can generalize to the extent that they can transfer directly without additional training. In practice, we can extract biological modules, denoise, and classify data correctly from an autoencoder that was trained on a different dataset and with different cells (a foreign model). We deconvoluted the biological signal encoded in the bottleneck layer of scRNA-models using saliency maps and mapped salient features to biological pathways. Biological concepts could be associated with specific nodes and interpreted in relation to biological pathways. Even in this unsupervised framework, with no prior information about cell types or labels, the specific biological pathways deduced from the model were in line with findings in previous research. It was hypothesized that autoencoders could learn and represent meaningful biology; here, we show with a systematic experiment that this is true and even transcends the training data. This means that carefully trained autoencoders can be used to assist the interpretation of new unseen data.

MOPower: an R-shiny application for the simulation and power calculation of multi-omics studies.

Background: Multi-omics studies are increasingly used to help understand the underlying mechanisms of clinical phenotypes, integrating information from the genome, transcriptome, epigenome, metabolome, proteome and microbiome. This integration of data is of particular use in rare disease studies where the sample sizes are often relatively small. Methods development for multi-omics studies is in its early stages due to the complexity of the different individual data types. There is a need for software to perform data simulation and power calculation for multi-omics studies to test these different methodologies and help calculate sample size before the initiation of a study. This software, in turn, will optimise the success of a study. Results: The interactive R shiny application MOPower described below simulates data based on three different omics using statistical distributions. It calculates the power to detect an association with the phenotype through analysis of n number of replicates using a variety of the latest multi-omics analysis models and packages. The simulation study confirms the efficiency of the software when handling thousands of simulations over ten different sample sizes. The average time elapsed for a power calculation run between integration models was approximately 500 seconds. Additionally, for the given study design model, power varied with the increase in the number of features affecting each method differently. For example, using MOFA had an increase in power to detect an association when the study sample size equally matched the number of features. Conclusions: MOPower addresses the need for flexible and user-friendly software that undertakes power calculations for multi-omics studies. MOPower offers users a wide variety of integration methods to test and full customisation of omics features to cover a range of study designs.

Computer Digital Technology-Based Educational Platform for Protection and Activation Design of Ming Furniture

Chinese Ming-style furniture is the first of the three major furnitures in the world, which has high artistic value and complete structural system. The protection of Ming-style furniture and making its design show vitality that has always been a research topic in China and even in the world. Based on 3D virtual simulation technology, this paper uses 3D scanning reverse data acquisition technology and intelligent operation of computer engine to realize big data simulation and develops the design software of Ming furniture. By means of computer information technology, we interpret and present the structural thinking and design concept of Ming furniture and transform it into design program software. This has formed a system-wide educational software operation platform for knowledge reserve, thinking training, design and application, and achievement transformation. By applying the mechanism strategy of production and teaching to the talent training plan of colleges and universities, the underlying logic of talent training, technical management, and production management that can open up the innovative industry of Ming furniture is also constructed. After experimenting with the platform software, students are able to understand the relationship between the structure and form of Ming furniture and can design new styles that fit the logic of Ming furniture shapes as they prefer.

Water table depth prediction based on Deep learning models in Electrical Power Transmission Lines area

Background: Predicting water table depth in Electrical Power Transmission Lines area presents great importance and helps the decision makers do the safety analysis during the project. The present study predicts the water table depth with observed weather data and hydrologic data. Method: The study first compared the results of LSTM, GRU, LSTM-S2S, and FFNN models in daily data simulation. Moreover, two scenarios (S1 and S2) were set to identify the effect of the water component on water table depth simulation. In addition, in order to analyze how data time scale influences the model simulation results, the monthly scale data was simulated by LSTM, GRU, and LSTM-S2S models. Result: The result indicated that LSTM-S2S was the best model for predicting daily water table depth among the four models. By contrast, FFNN performed the worst. LSTM and GRU model performed equally well both in daily data and monthly data simulation. S1 performed better than S2 in the water table depth simulation. The average daily performance of R2 and NSE was both higher than that in the monthly results with LSTM, GRU, and LSTM-S2S models. Conclusion: As a result, the method in the present study can be used to simulate the water table depth in the future in Electrical Power Transmission Lines area.