An Improved Gradient Boosted Algorithms Based Solutions Predictive Model (Trade)

As a subsystem of an Intelligent Transportation System (ITS), an Advanced Traveller Information System (ATIS) disseminates real-time traffic information to travellers. To help travellers better make their route choice decisions, there is a strong need to predict traffic congestion and disseminate the predicted congestion information to travellers. This paper offers some insights and predictions on how ATIS information provision is becoming more pervasive due to recent advances in telecommunication systems. The paper also discusses how ATIS systems will likely evolve based on the experiences of Information Service Providers (ISP) and ATIS modelling specialists. Then, it reviews four types of prediction models: 1) simulation models; 2) dynamic traffic assignment (DTA) models; 3) statistical models; and 4) heuristic models. The functional requirements and capabilities of the four types of prediction models are discussed and summarised. Furthermore, a comprehensive prediction procedure is presented, which combines the four types of prediction models.

Reduction of fouling and contamination by predictive kinetic models

Discrete-time state-space models have been extensively used in simulation-based design of dynamical systems. These prediction models may not accurately represent the true physics of a dynamical system due to potentially flawed understanding of the system, missing physics, and/or numerical approximations. To improve the validity of these models at new design locations, this paper proposes a novel dynamic model discrepancy quantification (DMDQ) framework. Time-instantaneous prediction models are constructed for the model discrepancies of “hidden” state variables, and are used to correct the discrete-time prediction models at each time-step. For discrete-time models, the hidden state variables and their discrepancies are coupled over two adjacent time steps. Also, the state variables cannot be directly measured. These factors complicate the construction of the model discrepancy prediction models. The proposed DMDQ framework overcomes these challenges by proposing two discrepancy modeling approaches: an estimation-modeling approach and a modeling-estimation approach. The former first estimates the model discrepancy and then builds a nonparametric prediction model of the model discrepancy; the latter builds a parametric prediction model of the model discrepancy first and then estimates the parameters of the prediction model. A subsampling method is developed to reduce the computational effort in building the two types of prediction models. A mathematical example and an electrical circuit dynamical system demonstrate the effectiveness of the proposed DMDQ framework and highlight the advantages and disadvantages of the proposed approaches.

This article contains description how to create prediction models for more efficient utilization of running IT resources. Prediction model creation is presented as one of the most important steps within the process of the knowledge discovery. Presented models were created based on real data from a local IT company by means of the programming language R. This article also marginally covers the steps, which are to be carried out before the actual modelling. The steps to mention are the following: available data understanding and their subsequent preprocessing for further work, individual attributes analysis using data visualization by means of graphs and tracking certain behavior and correlations in data. First of all, designing models using linear and multiple regression will be followed in detail. Then, the methods of new values prediction will be described using the R language. Finally, the different types of prediction models will be considered using appropriate indicators. The results obtained should assist and simplify the methods of the knowledge discovery in certain enterprises based on the available databases, and also help to choose the most suitable prediction models learning method.

Potatoes are an important crop in the world; they are the main source of food for a large number of people globally and also provide an income for many people. The true forecasting of potato yields is a determining factor for the rational use and maximization of agricultural practices, responsible management of the resources, and wider regions’ food security. The latest discoveries in machine learning and deep learning provide new directions to yield prediction models more accurately and sparingly. From the study, we evaluated different types of predictive models, including K-nearest neighbors (KNN), gradient boosting, XGBoost, and multilayer perceptron that use machine learning, as well as graph neural networks (GNNs), gated recurrent units (GRUs), and long short-term memory networks (LSTM), which are popular in deep learning models. These models are evaluated on the basis of some performance measures like mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) to know how much they accurately predict the potato yields. The terminal results show that although gradient boosting and XGBoost algorithms are good at potato yield prediction, GNNs and LSTMs not only have the advantage of high accuracy but also capture the complex spatial and temporal patterns in the data. Gradient boosting resulted in an MSE of 0.03438 and an R2 of 0.49168, while XGBoost had an MSE of 0.03583 and an R2 of 0.35106. Out of all deep learning models, GNNs displayed an MSE of 0.02363 and an R2 of 0.51719, excelling in the overall performance. LSTMs and GRUs were reported to be very promising as well, with LSTMs comprehending an MSE of 0.03177 and GRUs grabbing an MSE of 0.03150. These findings underscore the potential of advanced predictive models to support sustainable agricultural practices and informed decision-making in the context of potato farming.

RATIONALE. Sex differences have been observed in the incidence, severity, mortality, and outcomes of acute respiratory distress syndrome (ARDS) and COVID-19. However, the molecular basis for the differences between males and females remains unclear. METHODS. Bronchoalveolar lavage (BAL) samples collected from NIH-supported ARDSNet trials were provided by BioLINCC. To generate proteomics datasets, we purified extracellular vesicles (EVs) and then EV proteins, which were subsequently analyzed them using mass spectrometry. The proteomics datasets were precleaned and differentially expressed proteins were clustered to identify sex-specific endotypes. The prediction models for the identified endotypes were developed by training a univariate logistic regression model, and model performance was evaluated based on three-class accuracy.RESULTS. There were 57 ARDS patients and 49 healthy controls. We identified 6,616 proteins in BAL-EVs. Among these, the expression of 861 proteins was significantly upregulated or downregulated in patients compared to controls. K-means clustering of the demographics-correlated proteins revealed two distinct endotypes. These endotypes could be clearly differentiated based on gender, demographics, p/f ratio, smoking status, and various functional annotations. The prediction model developed based on proteomic datasets achieved an area under the curve (AUC) of 0.993 (sensitivity 94.59%, specificity 95.00%). When transformed into clinical settings, the new model derived from clinical variables showed an AUC value above 0.750. The prediction performance was improved if we combined omics data with clinical settings to develop the model (AUC 0.797), demonstrating the excellent performance of these three types of prediction models. CONCLUSION. Our study provides molecular mechanisms and prediction models for the sex differences in ARDS. Sex may serve as an independent predictor of the development, responses to treatments, mortality, and long-term outcomes associated with ARDS.

Predictive analytics has gained a lot of reputation in the emerging technology Big data. Predictive analytics is an advanced form of analytics. Predictive analytics goes beyond data mining. A huge amount of medical data is available today regarding the disease, their symptoms, reasons for illness, and their effects on health. But this data is not analysed properly to predict or to study a disease. The aim of this paper is to give a detailed version of predictive models from base to state-of-art, describing various types of predictive models, steps to develop a predictive model, their applications in health care in a broader way and particularly in diabetes.

Many cities have already installed bike-sharing systems for several years now, but especially in recent years with the rise of micro-mobility, many efforts are being made worldwide to improve the operation of these systems. Technology has an essential role to play in the success of micro-mobility schemes, including bike-sharing systems. In this paper, it is examined if a state-of-the-art mobile application (app) can contribute to increasing the usage levels of such a system. It is also seeking to identify groups of travelers, who are more likely to be affected by the sophisticated app. With this aim, a questionnaire survey was designed and addressed to the users of the bike-sharing system of the city of Thessaloniki, Greece, as well as to other residents of the city. Through a descriptive analysis, the most useful services that an app can provide are identified. Most importantly, two different types of predictive models (i.e., classification tree and binary logit model) were applied in order to identify groups of users who are more likely to shift to or to use the bike-sharing system due to the sophisticated app. The results of the two predictive models confirm that people of younger ages and those who are not currently users of the system are those most likely to be attracted to the system due to such an app. Other factors, such as car usage frequency, education, and income also appeared to have slight impact on travelers’ intention to use the system more often due to the app.

Changes in environments over 20years and the assessment of individual long-term exposure to air pollution for epidemiology.

Machine learning models to predict 6-month mortality risk in home-based hospice patients with advanced cancer.

Multiple mechanical properties prediction of hydraulic concrete in the form of combined damming by experimental data mining

An integrated recommender system for improved accuracy and aggregate diversity

Several vitrified waste forms were fabricated and characterized, which contain simulated radioactive waste incineration ash, and a long-term leaching test was conducted by an ISO method for 820 days to assess the chemical durability of vitrified waste forms. Two semi-empirical mechanism models were applied to find out the dominant leaching mechanism of glass elements. For glass elements, dissolution associated with diffusion was the dominant leaching mechanism and leaching characteristics also depend upon solubilities of components. A type of prediction model was applied to observe the long-term leaching behavior of major glass elements and surrogates. Diffusion coefficients and dissolution rate constants, the main parameters in the long-term prediction model, were obtained for glass elements and surrogate nuclides using experimental data for short and long-term periods. The model could be used to predict long-term behavior of such elements to observe and assess the stability of vitrified waste forms.

Single nucleotide mutations in exonic regions can significantly affect gene function through a disruption of splicing, and various computational methods have been developed to predict the splicing-related effects of a single nucleotide mutation. We implemented a new method using ensemble learning that combines two types of predictive models: (a) base sequence-based deep neural networks (DNNs) and (b) machine learning models based on genomic attributes. This method was applied to the Massively Parallel Splicing Assay challenge of the Fifth Critical Assessment of Genome Interpretation, in which challenge participants predicted various experimentally-defined exonic splicing mutations, and achieved a promising result. We successfully revealed that combining different predictive models based upon the stacked generalization method led to significant improvement in prediction performance. In addition, whereas most of the genomic features adopted in constructing machine learning models were previously reported, feature values generated with DSSP, a DNN-based splice site prediction tool, were novel and helpful for the prediction. Learning the sequence patterns associated with normal splicing and the change in splicing site probabilities caused by a mutation was presumed to be helpful in predicting splicing disruption.

A traffic crash is becoming one of the major factors that leads to unexpected death in the world. Short window traffic crash prediction in the near future is becoming more pragmatic with the advancements in the fields of artificial intelligence and traffic sensor technology. Short window traffic prediction can monitor traffic in real time, identify unsafe traffic dynamics, and implement suitable interventions for traffic conflicts. Crash prediction being an important component of intelligent traffic systems, it plays a crucial role in the development of proactive road safety management systems. Some near future crash prediction models were put forward in recent years; further improvements need to be implemented for actual applications. This paper utilizes traffic accident data from the study Freeway in China to build a time series-based count data model for daily crash prediction. Lane traffic flow, weather information, vehicle speed, and truck to car ratio were extracted from the deployment of non-intrusive detection systems with support of the Bridge Management Administration study and were input into the model as independent variables. Different types of prediction models in machine learning and time series forecasting methods such as boosting, ARIMA, time-series count data model, etc. are compared within the paper. Results show that integrating time series with a count data model can capture traffic accident features and account for the temporal structure for variable serial correlation. A prediction error of 0.7 was achieved according to Root Mean Squared Deviation.