Predication Model Research Articles

Predication of Dry Rubber Content in Hevea Latex based on SPSS Multiple Regression Model

The Dry Rubber content (DRC) in hevea latex is affected by a great many of factors, including producing area, strains, tree age, cutting system, origins and so on. Each factor was discussed and evaluated to confirm the influence degree. A predication model based on SPSS multiple regression models was constructed to analyse the factors influencing the DRC, and the regression equation was used to forecast the DRC in natural rubber latex. The results show that the predication model has a good achievement and the average relative error was 7.4%

Analyses of representative elementary volume for coal using X-ray μ-CT and FIB-SEM and its application in permeability predication model

The representative elemental volume (REV) study provides a bridge between macro and micro properties’ research, which is critical for understanding and predicting the heterogeneous properties of a porous media. Permeability, one of the essential properties, dominates the capability of fluid flow in porous media, which is scale dependent and thus one of the most rationale way to predict macro scale permeability is to calculate the permeability at REV. Porosity is the most common parameter to determine REV, however, the porosity based REV works less satisfactory for complex pore system. In this work, we determined the REV based on fractal dimension, which is a fundamental parameter to characterize the complex pore network, and then the relation between fractal dimension and sample size was investigated extensively. We then determined and compared the REV from the porosity and fractal dimension that calculated from various sample sizes. Our results reveal that the relationship between fractal dimension-based REV and porosity-based REV can be classified as four cases, and the most common case is porosity declines if the domain is larger than fractal dimension-based REV size. The relation discussed above can be applied to existing fractal permeability models to predict the permeability at different scales.

A Novel Wearable Device for Digital Health Based on Cardiac Force Index of Running Performance

Backgrounds: Marathons and road running have become popular in recent years, sudden cardiac death may occur even in young populations. Early detection the cardiac function changes during running is imperative. Methods: This study used the American Zephyr™ product BioHarness 3.0. It can measure basic physiological parameters, including heart-rate, respiratory rate, temperature, maximum oxygen consumption and activity. Interpretation: We investigated the correlations among the 2 new physiological parameters, including cardiac force index (CFI) = weight * activity / heart rate, cardiac force ratio (CFR) = CFI of running / CFI of walking, and finish times for 3000 meters of running. After analysis of multi-variates logistic regression model, accumulation of heart activities during running was statistically significant with the qualification of the 3000-meter running test (p = 0.04). Finally, we compared the correlations of CFR(s) between runners with stronger and weaker cardiac force during 3000-meter running. In conclusion, this study results suggested that real-time CFR changes could be a predication model for the 3000-meter running performance. Funding Statement: This study was supported from the grants of AFTYGH-10752 and AFTYGH-10812, Taoyuan Armed Forces General Hospital, Taiwan, ROC. Declaration of Interests: The authors state: None declared. Ethics Approval Statement: This was a cross-sectional study which was approved by the human trial committee of the Tri-Service General Hospital, Taiwan. Approval for this study was provided by the Institutional Review Board (IRB) of the Tri-Service General Hospital, Taiwan (Approval No: TSGH- IRB-1-104-05-147).

Clinical and Genetic Aspects of Refractory Forms of Multiple Myeloma Development

Treatment of multiple myeloma has progressed significantly over the past years after the introduction of immunomodulation drugs and proteasome inhibitors. The median of patients survival has improved. All patients with multiple myeloma have relapses during a different time interval. The duration of the achieved remission in patients with a relapse of multiple myeloma becomes shorter with each subsequent case. The choice of regimen for relapse of multiple myeloma is very complex. It depends on a number of factors, including the previous induction regimen, the number of lines of the previous therapy, and the degree of aggression of relapse. The article is devoted to peculiarities of drug resistance formation in the first line therapy in patients with multiple myeloma by assessing of genetic markers (deletion variants of GSTT1, GSTM1 genes, GSTP1 (А313G), MDR1 (C3435T)) and clinical-hematological, laboratory characteristics.The objective: to determine the peculiarities of drug resistance establishement in patients with multiple myeloma by assessing of genetic markers (deletion variants of GSTT1, GSTM1 genes, GSTP1 (А313G), MDR1 (C3435T)) and clinical signes (hematological, laboratory characteristics) for predicting the effectiveness of treatment.Materials and methods. We conducted analysis of 68 clinically-laboratory indexes of 130 patients with multiple myeloma and their results of molecular-genetic research of deletion polymorphism of genes GSTT1, GSTM1, polymorphism А313G, C3435T genes GSTP1, MDR1.Results. It was determined that important predictors of development of refractory forms of multiple myeloma is allelic polymorphism of gene GSTM1 of patients, higher level α2-globulin and calcium in blood serum till the beginning of disease.Conclusions. Implementation of predicative model taking into account polymorphism GSTM1, of level α2-globulin and calcium in blood serum till the beginning of treatment raises efficiency of evaluation of individual prognosis of response on treatment.

Quantification and monitoring the heat-induced formation of trans fatty acids in edible oils by Raman Spectroscopy

Trans fatty acids (TFAs), a type of unsaturated fatty acids, has been linked to increased risks of coronary heart disease and other health problems. Thus, efficient and reliable detection methods for TFAs are of great importance for both industrial applications and research purposes. In this study, a rapid and pretreatment-free quantification approach was developed for TFAs in 13 edible oils (including 2 soybean oils, 2 peanut oils, 2 rapeseed oils, blend oil, oleum camelliae, sunflower oil, rice oil, sesame oil, olive oil and corn oil) with Raman spectroscopy and chemometric methods. The commercial oils contained 0–0.397% (w/w) of trielaidin and each of the oils were further added with 0.1–5% of trielaidin, resulting in a total of 130 samples. Results show that the concentration of TFAs in various oils can be well-predicted based on the Raman spectral features in the region of 1640–1680 cm−1 (characteristic to C=C stretching modes), yielding a residual predictive deviation (RPD) of 4.639. This approach exhibits high sensitivity in quantification, and TFAs added in different kinds of edible oils combined with their initial levels can be successfully quantified with good descriptive statistics (Rc = 0.9657, Rcv = 0.9598, Rp = 0.9634, RMSEC = 0.351, RMSECV = 0.391 and RMSEP = 0.302). Furthermore, in order to understand the heat-induced formation of TFAs during food preparation, the TFA concentrations of the oil heated under different temperatures was investigated based on the above predication model. The results indicate that the concentration of TFAs increased sharply when the oils were heated at 169–250 °C for 10 min.

Fatigue Stress-Life Model of RC Beams Based on an Accelerated Fatigue Method

Several standard fatigue testing methods are used to determine the fatigue stress-life prediction model (S-N curve) and the endurance limit of Reinforced Concrete (RC) beams, including the application of constant cyclic tension-tension loads at different stress or strain ranges. The standard fatigue testing methods are time-consuming and expensive to perform, as a large number of specimens is needed to obtain valid results. The purpose of this paper is to examine a fatigue stress-life predication model of RC beams that are developed with an accelerated fatigue approach. This approach is based on the hypothesis of linear accumulative damage of the Palmgren–Miner rule, whereby the applied cyclic load range is linearly increased with respect to the number of cycles until the specimen fails. A three-dimensional RC beam was modeled and validated using ANSYS software. Numerical simulations were performed for the RC beam under linearly increased cyclic loading with different initial loading conditions. A fatigue stress-life model was developed that was based on the analyzed data of three specimens. The accelerated fatigue approach has a higher rate of damage accumulations than the standard testing approach. All of the analyzed specimens failed due to an unstable cracking of concrete. The developed fatigue stress-life model fits the upper 95% prediction band of RC beams that were tested under constant amplitude cyclic loading.

Humid-thermal index for a new management approach of Ommatissus lybicus.

The Dubas bug, Ommatissus lybicus, is a serious insect pest for the date palm Phoenix dactylifera in Oman and other date palm growing countries throughout the Middle East and North Africa. Climate is a key factor affecting the insect population dynamics, including O. lybicus. There are limited studies of O. lybicus relating to microclimate. The aim of this study was to investigate the efficiency of the various humid thermal indices (HTIs) and daily accumulation of temperature and humidity to model the relationship with O. lybicus. The highly infested locations showed a strong relationship with cumulative daily mean relative humidity (RhCm ), followed by daily minimum temperature (Tmin ) for pooled data over two seasons. The next best regression models for the relationship between the infestation and climate was with the absolute factors, daily maximum humidity (Rhmx ) and daily minimum humidity (Rhmin ), compared with HTIm/m (ratio of mean humidity to mean temperature) for the autumn season. The best regression model for the spring season was daily mean humidity (Rhm ) and daily maximum temperature (Tmax ). Daily cumulative temperature was the best predictive model for O. lybicus infestation on date palms, considering the microclimate data at each location separately. The predication model points to the areas that are prone to infestation and need focus for monitoring and allocation of management resources. © 2019 Society of Chemical Industry.

Разработка предикатной модели выбора лексических значений при переводе на русский жестовый язык на основе семантического словаря В.А. Тузова и системы автоматической обработки текста «Диалинг»

Разработка предикатной модели выбора лексических значений при переводе на русский жестовый язык на основе семантического словаря В.А. Тузова и системы автоматической обработки текста «Диалинг»

Establishment of a Model to Assess Soil Cadmium Uptake by Brassica Chinensis

Core Ideas Cadmium uptake by Brassica chinensis was positively related with soil Cd content. Soil pH and OC acted as dominant factors regulating Cd uptake in Brassica chinensis. The log‐transformed data was more appropriate in establishing the regress equations. The predication model was best established combining with soil pH and OC. Estimating cadmium (Cd) bioavailability and transfer to plants are important for food safety. We aimed to determine the dominant soil factors regulating the transfer of Cd from a wide variety of Chinese soils to Pak Choi (Brassica chinensis) and to establish a model for prediction of Cd uptake in B. chinensis. A greenhouse experiment was conducted in which B. chinensis plants were grown under 14‐h 20°C light/10‐h 16°C dark photoperiod for 60 d. The total Cd content in the plant and soil samples was measured. The Cd concentration in B. chinensis was positively correlated to the soil Cd concentration, and negatively correlated to the soil pH and soil organic carbon (SOC) content. The bio‐concentration factors (BCF) measured in acidic soils (the maximum value being 0.551) were higher than those in alkaline soils (the maximum value being 0.366). Multivariable (pH, SOC, and total soil Cd) regression analysis could estimate the Cd bioavailability more accurately compared with the single‐factor (total soil Cd) analysis. The most accurate Freundlich‐type equation (Log[Cplant] = 2.34Log[Csoil] – 0.27pH – 0.23Log[SOC] + 0.92) was developed to estimate the Cd bioavailability using combined data from all treatments. The model described by us would be useful for estimating the bioavailability of Cd to B. chinensis in a variety of soils and would be helpful in assessing the risk of Cd contamination in soils.

Research and Implement of Course Early Warning System Based on Teaching Behaviour Data

Digital early warning research based on the course performance of students, is constantly advancing. However, there are a few scholars combing one of specific course, taking the early predication by digging and analysing the data of teaching behaviour and provide real-time intervention. This research, making Java program design as entry point design an overall framework for early warning system based on the data of teaching behaviour, and combines the certain algorithm to implementing the early course predication model with relatively higher accuracy by gathering and analysing students’ past learning data as well as real-time teaching behaviour’s data. Practice indicates that, according to the grade and GPA (grade point average) of pre-course as well as study behaviour during week 4 and week 6, there can be predicted course pass rate of students accurately, especially from week5, which has high accuracy of predicting. Moreover, the model is able to provide early intervention and automatically sending learning materials for some students who get unsatisfied performance basing on the predicating data, to improve the pass rate for students.

Effect of irrigation amount and fertilization on agriculture non-point source pollution in the paddy field

It is the key point to reveal the effect of irrigation water and fertilization conditions on the agriculture non-point pollution in the paddy field. In this study, the estimation model of agricultural non-point source pollution loads at field scale was established on the basis of agricultural drainage irrigation model and combined with pollutant concentration predication model. Based on the estimation model of agricultural non-point source pollution in the field and experimental data, the load of agricultural non-point source pollution in different irrigate amount and fertilization schedule in paddy field was calculated. The results showed that the variation of field drainage varies greatly under different irrigation conditions, and there is an "inflection point" between the irrigation water amount and field drainage amount. The non-point pollution load increased with the increase of irrigation water and showed a significant power correlation. Under the different irrigation condition, the increase amplitude of non-point pollution load with the increase of irrigation water was different. When the irrigation water is smaller, the non-point pollution load increase relatively less, and when the irrigation water increased to inflection point, the non-point pollution load will increase considerably. In addition, there was a positive correlation between the fertilization and non-point pollution load. The non-point pollution load had obvious difference in different fertilization schedule even with same fertilization level, in which the fertilizer pollution load increased the most in the period of turning green to tillering. The results provide some basis for the field control and management of agricultural non-point source pollution.

Biotechnical monitoring system for determining person's health state in polluted environment using hybrid decisive rules

Setting exposure criteria to environmental pollutants is dependent on a range of interrelated variables, therefore it is complicated to understand and model exposure levels. Fuzzy logic is a convenient approach to integrate expert judgment and mathematical modelling in one predication model. Monitoring health state of population is useful tool to develop and calibrate parameters of fuzzy logic model. Analysis of the indistinct decisive rules making a basis of creation of knowledge bases of expert systems, solving problems of monitoring of a state of environment and health of humans on the basis of collectives of the hybrid mathematical models working with diverse structure of data in the absence of their exact analytical description are considered. Disease risk was analysed for populations living in two environmental conditions, one a polluted mining community (Zheleznogorsk city) and the other a cleaner environment community (Kursk city). Diseases screening for polluted area was conducted and analysed.

Prognostic Value and Predication Model of Microvascular Invasion in Patients with Intrahepatic Cholangiocarcinoma.

Background: Whether microvascular invasion (MVI) adversely influences oncological outcomes for intrahepatic cholangiocarcinoma (ICC) patients remains unclear. The purpose of this study was to determine the impact of MVI on postoperative survival and establish a new predictive model for MVI before surgical intervention in patients with ICC.Methods: In this two-center retrospective study, 556 and 31 consecutive patients who underwent curative liver resection for ICC at ZSH and XJFH were analyzed, respectively. Propensity score matching (PSM) and Cox regression analyses were used to explore the prognostic role of MVI on the OS and DFS. Multivariate logistic regression was used to identify the relative risk factors of MVI, which were incorporated into the nomogram.Results: After PSM, 50 MVI cases matched with 172 non-MVI cases, and no bias was observed between the two groups (propensity score, 0.118 (0.099, 0.203) vs. 0.115 (0.059, 0.174), p=0.251). The multivariate Cox analysis showed that MVI was negatively associated with OS (HR 1.635, 95% CI 1.405-1.993, p=0.04) and DFS (HR 1.596, 95% CI 1.077-2.366, p=0.02). The independent factors associated with MVI were ALT, AFP, tumor maximal diameter, and tumor capsule. The nomogram that incorporated these variables achieved good concordance indexes for predicting MVI. Patients with a cutoff score of 168 were considered to have different risks of the presence of MVI preoperatively.Conclusions: The presence of MVI was an adverse prognostic factor for ICC patients. Using the nomogram model, the risk of an individual patient harboring MVI was determined, which led to a rational therapeutic choice.

A Gaussian-Gaussian-Restricted-Boltzmann-Machine-based Deep Neural Network Technique for Photovoltaic System Generation Forecasting

Abstract This paper proposes a new Gaussian-Gaussian-Restricted-Boltzmann-Machine-based method for forecasting photovoltaic (PV) system generation forecasting. Although renewable energy such as PV system and wind power generation has been used to suppress greenhouse gases in the world, it has a drawback that weather conditions influence the generation output significantly. Thus, it is not easy to perform Economic Load Dispatch (ELD) and Unit Commitment in power systems smoothly. From a standpoint of power system operation, more accurate predication models are required to deal with predicted values of PV system generation. In this paper, an efficient Deep Neural Network (DNN) model with Gaussian Gaussian Restricted Boltzmann Machine is presented to predict one-step-ahead PV system generation output. The model is based on Restricted Boltzmann Machine as a feature extractor and MultiLayer Perceptron (MLP) as ANN. The effectiveness of the proposed method is demonstrated for real data of a PV system.

Eye movements and visual discomfort when viewing stereoscopic 3D content

The visual brain fuses the left and right images projected onto the two eyes from a stereoscopic 3D (S3D) display, perceives parallax, and rebuilds a sense of depth. In this process, the eyes adjust vergence and accommodation to adapt to the depths and parallax of the points they gazed at. Conflicts between accommodation and vergence when viewing S3D content potentially lead to visual discomfort. A variety of approaches have been taken towards understanding the perceptual bases of discomfort felt when viewing S3D, including extreme disparities or disparity gradients, negative disparities, dichoptic presentations, and so on. However less effort has been applied towards understanding the role of eye movements as they relate to visual discomfort when viewing S3D. To study eye movements in the context of S3D viewing discomfort, a Shifted-S3D-Image-Database (SSID) is constructed using 11 original nature scene S3D images and their 6 shifted versions. We conducted eye-tracking experiments on humans viewing S3D images in SSID while simultaneously collecting their judgments of experienced visual discomfort. From the collected eye-tracking data, regions of interest (ROIs) were extracted by kernel density estimation using the fixation data, and an empirical formula fitted between the disparities of salient objects marked by the ROIs and the mean opinion scores (MOS). Finally, eye-tracking data was used to analyze the eye movement characteristics related to S3D image quality. Fifteen eye movement features were extracted, and a visual discomfort predication model learned using a support vector regressor (SVR). By analyzing the correlations between features and MOS, we conclude that angular disparity features have a strong correlation with human judgments of discomfort.

Research and Design on Cognitive Computing Framework for Predicting Judicial Decisions

This paper aims to provide a cognitive computing framework to meet the challenges of semantic understanding, knowledge learning and judicial reasoning in the Chinese legal domain. In our framework, legal factors are first represented in a formal way; secondly, legal factors are extracted, and concepts and their relations are augmented with a combination of rule-based and deep learning methods; thirdly, a predication model is generated and trained to make judicial decisions. When a fact description is brought into the model, the probability of judicial decisions will be given automatically. Two elementary results are obtained: I. Our method can effectively predict the decisions for divorce cases with different expression styles, and offers better performance than traditional methods like Support Vector Machine (SVM); II. Our machine learning predicting results can be easily understood by general public as applied induction rules are given.

PreMOn: LODifing linguistic predicate models

PreMOn is a freely available linguistic resource for exposing predicate models (PropBank, NomBank, VerbNet, and FrameNet) and mappings between them (e.g., SemLink and the predicate matrix) as linguistic linked open data (LOD). It consists of two components: (1) the PreMOn Ontology, that builds on the OntoLex-Lemon model by the W3C ontology-Lexica community group to enable an homogeneous representation of data from various predicate models and their linking to ontological resources; and, (2) the PreMOn Dataset, a LOD dataset integrating various versions of the aforementioned predicate models and mappings, linked to other LOD ontologies and resources (e.g., FrameBase, ESO, WordNet RDF). PreMOn is accessible online in different ways (e.g., SPARQL endpoint), and extensively documented.

Theory-based approaches and microstructural analysis to evaluate the service life-retention of stressed carbon fiber composite strands for concrete bridge applications

Prestressed concrete girders and piles with steel strands are used in construction of bridges in North America, due to their economy of design, fabrication, and installation. However, they are often exposed to harsh environments, which results in rapid degradation. Therefore, carbon fiber reinforced polymer (CFRP) tendons have successfully been introduced as prestressing reinforcement for pile applications. This paper presents a study on the physical characterization, microstructural analysis, and durability performance of unstressed and stressed carbon-fiber composite cables (CFCCs) for prestressing applications. This is achieved through testing 120 CFCC specimens, subjected to stress levels of about 40% and 65% of their guaranteed strength, and 51 specimens without sustained load under tension. Moreover, prediction models were introduced to assess the long-term performance and retentions of CFCC strands. The models included Arrhenius model, Fick's law, Fib Bulletin (40) model, and a developed approach that incorporates the effects of temperature, design life, and relative humidity of exposure into the environmental reduction factor. Based on the predication model, the tensile strength retention (CE) for CFCC strands, is predicted to retain over 0.95 and 0.84 of ultimate tensile strength for a relative humidity (RH) < 90% and a moisture saturated environment (RH = 100%), respectively, after 100 years of service life with elevated temperature and sustained load.

Feedback Rate Based User Order Predication (FR-UOP) Model for Sentiment Analysis in Data Mining

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Geographically Derived Socioeconomic Factors to Improve Risk Prediction in Patients Having Aortic Valve Replacement

Socioeconomic status (SES) has been associated with adverse outcomes after cardiac surgery, but is not included in commonly applied risk adjustment models. This study evaluates whether inclusion of SES improves aortic valve replacement (AVR) risk prediction models, as this is the most common elective operation performed at our institution during the study period. All patients who underwent AVR at a single institution from 2005 to 2015 were evaluated. SES measures included unemployment, poverty, household income, home value, educational attainment, housing density, and a validated SES index score. The risk scores for mortality, complications, and increased length of stay were generated using models published by the Society for Thoracic Surgeons. Univariate models were fitted for each SES covariate and multivariable models for mortality, any complication, and prolonged length of stay (PLOS). A total of 1,386 patients underwent AVR with a 2.7% mortality, 15.1% complication rate, and 9.7% PLOS. In univariate models, higher education was associated with decreased mortality (odds ratio [OR] 0.96, p = 0.04) and complications (OR 0.97, p <0.01). Poverty was associated with increased length of stay (OR 1.02, p = 0.02). In the multivariable models, the inclusion of SES covariates increased the area under the curve for mortality (0.735 to 0.750, p = 0.14), for any complications (0.663 to 0.680, p <0.01), and for PLOS (0.749 to 0.751, p = 0.12). The inclusion of census-tract-level socioeconomic factors into the the Society of Thoracic Surgeons risk predication models is new and shows potential to improve risk prediction for outcomes after cardiac surgery. With the possibility of reimbursement and institutional ranking based on these outcomes, this study represents an improvement in risk prediction model.