K-nearest Neighbor Regression Research Articles

Prediction model and demonstration of regional agricultural carbon emissions based on PCA-GS-KNN: a case study of Zhejiang province, China

The paper proposes a prediction algorithm that is composed with principal component analysis (PCA), grid search (GS) and K-nearest neighbours (KNN). Firstly, in order to solve the problem of multicollinearity in multiple regression, principal component analysis is used to select the principal components of the regression variables; then, the K-nearest neighbour regression prediction model is used to train the data and the grid search is used to obtain better prediction model parameters in order to solve the problem of difficult parameter selection in the traditional K-nearest neighbour regression prediction model; finally, taking Zhejiang Province, China, as an example, the optimised prediction model is used to conduct regional agricultural carbon emission. The results show that the algorithm outperforms other prediction models in terms of prediction accuracy and it can accurately predict regional agricultural carbon emissions.

Inland Flooding and Rainfall from Hurricane Irene and Tropical Storm Lee (2011): Coupled Atmosphere–Wave–Ocean Model Simulations and Remote Sensing and In Situ Observations with a Machine Learning Tool

Abstract Inland flooding from landfalling tropical cyclones (TCs) is a major cause of death and damage to property and infrastructure worldwide. The mid-Atlantic region of the United States was devastated by Hurricane Irene and Tropical Storm Lee during late August–early September 2011, when the two storms produced sequential heavy rainfall and record flooding. Many rivers and streams reached their all-time record discharge to date. This study aims at 1) better understanding and predicting TC rainfall using various observed rainfall products and a high-resolution coupled atmosphere–wave–ocean model, namely, the Unified Wave Interface-Coupled Model (UWIN-CM), 2) characterizing inland flooding using streamflow data, and 3) improving prediction of TC-induced inland flooding using UWIN-CM and a machine learning K-nearest-neighbor (KNN) model. The results show that there is a wide range of uncertainty in satellite and radar–gauge-observed rainfall products in terms of rain-rate distribution and cumulative rainfall over the mid-Atlantic region. UWIN-CM rainfall is closer to the radar–gauge data than satellite data over land. Streamflow in most large rivers (>500 cfs) peaked after Lee, which reflects the sequential rainfall contributions of the two storms. The rainfall–streamflow–discharge response times were dependent on the size of the stream and the peak rain rates. To better predict rainfall and flooding, UWIN-CM and observed rainfall are used with the machine learning KNN regression model for prediction of severity of TC-induced inland flooding hazard. These results demonstrate the value of a stepped approach for rainfall and flood prediction toward a fully coupled atmosphere–ocean–land/hydrology model in the future.

A comparative study of machine learning-based load balancing in high-speed train system

With the rapid developments of fifth generation (5G) mobile communication networks in recent years, different use cases can now significantly benefit from 5G networks. One such example is high-speed trains found in several countries across the world. Due to the dense deployment of 5G millimetre wave (mmWave) base stations (BSs) and the high speed of moving trains, frequent handovers (HOs) occur which adversely affect the Quality-of-Service (QoS) of mobile users. User association for load balancing is also a key issue in 5G networks. Therefore, HO optimisation and resource allocation are major challenges in the mobility management of high-speed train systems. Handover Margin (HOM) and Time-to-Trigger (TTT) parameters are crucial for the HO process since they affect the key performance indicators (KPIs) of high-speed train systems in 5G networks. To manage system performance from the aspect of predictive analytics, we have modelled system performance of mobility management through machine learning (ML). First, the HO management process of a high-speed train scenario is framed as a supervised ML problem. The inputs for the problem are regression task, HOM and TTT and the outputs are key performance indicators (KPIs). Second, data processing is accomplished after generating a simulation dataset. Several methods are employed for the dataset, such as Adaptive Boosting (AdaBoost), Gradient Boosting Regression (GBR), CatBoost Regression (CBR), Support Vector Regression (SVR), Multi-layer Perceptron (MLP), Kernel Ridge Regression (KRR) and K-Nearest Neighbour Regression (KNNR). Tenfold cross validation is then applied for choosing the best hyperparameters. Finally, the deployed methods are compared in terms of the Mean Absolute Error (MAE), Mean Square Error (MSE), Maximum Error (Max E), and R2 score metrics. From the MAE results, CBR achieves the best outcomes for load level and throughput KPIs with 0.003 and 0.0144, respectively. On the other hand, GBR achieves the best results for call dropping ratio (CDR), radio link failure (RLF) and spectral efficiency KPIs with 0.354, 0.082 and 0.354, respectively. CBR also follows GBR for the three KPIs with 0.356, 0.082 and 0.357, respectively. Only a slight difference in estimations is present. MLP achieves the best results for HO ping-pong (HOPP) and HO probability (HOP) KPIs with 0.0045 and 0.011, respectively. This is followed by GBR and CBR. From the MSE outcomes, CBR and GBR exhibit the best results for load level and throughput KPIs with 2e-5 and 3e-5, respectively. GBR attains the best results for CDR, RLF and spectral efficiency KPIs with 0.25, 0.011 and 0.025, respectively. Accordingly, CBR follows GBR with slightly different errors for the three KPI estimations. MLP achieves the best results for HOPP and HOP KPIs with 5e-5 and 3.6e-5, respectively. Again, this is followed by GBR and CBR for the estimation of these results. This indicates that CBR and GBR can capture relationships between inputs and KPIs for the dataset used in this study, outperforming all other methods generally used for solving this problem.

Predicting highly dynamic traffic noise using rotating mobile monitoring and machine learning method

Traffic noise, characterized by its highly fluctuating nature, is the second biggest environmental problem in the world. Highly dynamic noise maps are indispensable for managing traffic noise pollution, but two key difficulties exist in generating these maps: the lack of large amounts of fine-scale noise monitoring data and the ability to predict noise levels in the absence of noise monitoring data. This study proposed a new noise monitoring method, the Rotating Mobile Monitoring method, that combines the advantages of stationary and mobile monitoring methods and expands the spatial extent and temporal resolution of noise data. A monitoring campaign was conducted in the Haidian District of Beijing, covering 54.79 km of roads and a total area of 22.15 km2, and gathered 18,213 A-weighted equivalent noise (LAeq) measurements at 1-s intervals from 152 stationary sampling sites. Additionally, street view images, meteorological data and built environment data were collected from all roads and stationary sites. Using computer vision and GIS analysis tools, 49 predictor variables were measured in four categories, including microscopic traffic composition, street form, land use and meteorology. Six machine learning models and linear regression models were trained to predict LAeq, with random forest performing the best (R2 = 0.72, RMSE = 3.28 dB), followed by K-nearest neighbors regression (R2 = 0.66, RMSE = 3.43 dB). The optimal random forest model identified distance to the major road, tree view index, and the maximum field of view index of cars in the last 3 s as the top three contributors. Finally, the model was applied to generate a 9-day traffic noise map of the study area at both the point and street levels. The study is easily replicable and can be extended to a larger spatial scale to obtain highly dynamic noise maps.

Predicting the negative conversion time of nonsevere COVID-19 patients using machine learning methods.

Based on the patient's clinical characteristics and laboratory indicators, different machine-learning methods were used to develop models for predicting the negative conversion time of nonsevere coronavirus disease 2019 (COVID-19) patients. A retrospective analysis was performed on 376 nonsevere COVID-19 patients admitted to Wuxi Fifth People's Hospital from May 2, 2022, to May 14, 2022. The patients were divided into training set (n = 309) and test set (n = 67). The clinical features and laboratory parameters of the patients were collected. In the training set, the least absolute shrinkage and selection operator (LASSO) was used to select predictive features and train six machine learning models: multiple linear regression (MLR), K-Nearest Neighbors Regression (KNNR), random forest regression (RFR), support vector machine regression (SVR), XGBoost regression (XGBR), and multilayer perceptron regression (MLPR). Seven best predictive features selected by LASSO included: age, gender, vaccination status, IgG, lymphocyte ratio, monocyte ratio, and lymphocyte count. The predictive performance of the models in the test set was MLPR > SVR > MLR > KNNR > XGBR > RFR, and MLPR had the strongest generalization performance, which is significantly better than SVR and MLR. In the MLPR model, vaccination status, IgG, lymphocyte count, and lymphocyte ratio were protective factors for negative conversion time; male gender, age, and monocyte ratio were risk factors. The top three features with the highest weights were vaccination status, gender, and IgG. Machine learning methods (especially MLPR) can effectively predict the negative conversion time of non-severe COVID-19 patients. It can help to rationally allocate limited medical resources and prevent disease transmission, especially during the Omicron pandemic.

Analyzing Coating Conditions of Steel Bridges at Florida: A Data-Driven Approach

Even with the continuous development of coating technologies, coating systems are susceptible to corrosion-induced premature failures and unable to meet the anticipated service life. Coating premature failures will negatively impact the safety, integrity, and longevity of steel bridge structural elements. The advancement of the data analytics approach (e.g., machine learning) offers an opportunity to leverage the wealth of historical bridge inspection and maintenance data collected by Departments of Transportation to evaluate coating conditions of steel bridges effectively and efficiently. This paper focuses on presenting a data-driven study that analyzes the conditions of coating systems of steel bridges in the state of Florida. Three machine learning algorithms were used in developing models that can be used to analyze steel bridge coating conditions based on data collected from the Bridge Management System of the Florida Department of Transportation. The result showed that the machine learning–based models were able to effectively predict steel bridge coating conditions. The k-nearest neighbor (KNN) regression algorithm offered the best performance. Although the approach was currently applied to the steel bridges of Florida, it can be easily replicable for similar data sets from other states. The research contributes to the body of knowledge by offering a data-driven understanding of coating performance of steel bridge elements. The research has the potential to offer a valuable decision-making tool for transportation agencies to effectively and easily analyze or predict steel bridge coating conditions.

Development of advanced machine learning models for optimization of methyl ester biofuel production from papaya oil: Gaussian process regression (GPR), multilayer perceptron (MLP), and K-nearest neighbor (KNN) regression models

Data-driven machine learning (ML) methods are extensively employed for modeling and simulation of highly complicated processes. ML techniques confirmed their great predictive capability compared to conventional techniques for modeling and management of non-linear relationships between input and output parameters. Biofuels as renewable sources of energy are a significant potential alternative to fossil fuels. Due to the non-linearity and complexity of biofuels production processes and increasing energy conversion, accurate and fast modeling tools are necessary for design and optimization of these processes. Hence, in this research, ML modeling techniques were developed for simulation of biofuel production from energy conversion of Papaya oil through transesterification process. In order to simulate and optimize the content Papaya oil methyl ester (POME) production, Gaussian Process Regression (GPR), Multilayer perceptron (MLP), and K-nearest neighbor (KNN) regression models, as well as adaptive boosting for amplification, were employed. The temperature of reaction, catalyst quantity, time of process, and methanol to oil molar ratio were considered as the inputs of models while the POME yield was the model output. The obtained results showed that the R2-score of 0.988, 0.993, and 0.994 were obtained for Boosted MLP, Boosted GPR, and Boosted KNN, respectively, which demonstrate the high predictive ability of these models. Also, the RMSE metric error rates of 9.8071, 4.8150, and 6.5180 corresponded to Boosted MLP, Boosted GPR, and Boosted KNN, respectively. We examined performance using another metric, MAE: 8.38008, 2.3184, and 5.21954 errors were observed for Boosted MLP, Boosted GPR, and Boosted KNN, respectively. The optimized POME production yield of 99.89% was observed at temperature of 62.5 °C, 6.47 min of reaction, catalyst quantity of 0.8125 wt% and methanol to oil molar ratio of 10.33. The obtained results of this study show that the ML techniques are highly recommended for prediction of biofuels production as cost and time saving methods.

A quantitative lower limb function assessment method based on fusion of surface EMG and inertial data in stroke patients during cycling task

ObjectiveQuantitative methods provide an accurate way to determine lower-limb motor function level that is essential for post-stroke rehabilitation protocol setup. Due to less requirement of postural stability and balance control, cycling task is more suitable for stroke patients in acute period compared to gait tasks. However, the feasibility of motor function assessment under cycling task has been rarely studied. In this study, we investigated the locomotor performance under cycling task with comparing to a lower-limb movement sequence task and developed a motor assessment framework based on fusion of surface electromyography (sEMG) and inertial features. MethodsTen post-stroke hemiparetic patients were enrolled where sEMG signals and inertial data were measured and derived in both tasks. The task effect was investigated using one-way analysis of variance and feature difference between the affected and unaffected limbs was furtherly statistically analyzed. Ratios of feature were calculated based on which a motor function assessment model was built using a K-nearest neighbor regression algorithm. ResultsResults showed that patients had more significant differences in bilateral muscle activations and ratios of features in the cycling task had higher correlation with Fugl-Meyer assessment scores. The proposed model obtained a high accuracy prediction with a significant correlation (R2 = 0.99, MAE = 0.15, p < 0.001) in lower-limb motor score prediction. ConclusionThe study provides a novel motor assessment framework that validates the usability and feasibility of cycling task and has great potential in practical clinical assessment.

Assessment and quantification of ovarian reserve on the basis of machine learning models.

Early detection of ovarian aging is of huge importance, although no ideal marker or acknowledged evaluation system exists. The purpose of this study was to develop a better prediction model to assess and quantify ovarian reserve using machine learning methods. This is a multicenter, nationwide population-based study including a total of 1,020 healthy women. For these healthy women, their ovarian reserve was quantified in the form of ovarian age, which was assumed equal to their chronological age, and least absolute shrinkage and selection operator (LASSO) regression was used to select features to construct models. Seven machine learning methods, namely artificial neural network (ANN), support vector machine (SVM), generalized linear model (GLM), K-nearest neighbors regression (KNN), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were applied to construct prediction models separately. Pearson's correlation coefficient (PCC), mean absolute error (MAE), and mean squared error (MSE) were used to compare the efficiency and stability of these models. Anti-Müllerian hormone (AMH) and antral follicle count (AFC) were detected to have the highest absolute PCC values of 0.45 and 0.43 with age and held similar age distribution curves. The LightGBM model was thought to be the most suitable model for ovarian age after ranking analysis, combining PCC, MAE, and MSE values. The LightGBM model obtained PCC values of 0.82, 0.56, and 0.70 for the training set, the test set, and the entire dataset, respectively. The LightGBM method still held the lowest MAE and cross-validated MSE values. Further, in two different age groups (20-35 and >35 years), the LightGBM model also obtained the lowest MAE value of 2.88 for women between the ages of 20 and 35 years and the second lowest MAE value of 5.12 for women over the age of 35 years. Machine learning methods combining multi-features were reliable in assessing and quantifying ovarian reserve, and the LightGBM method turned out to be the approach with the best result, especially in the child-bearing age group of 20 to 35 years.

Quantitative Estimation of Rainfall from Remote Sensing Data Using Machine Learning Regression Models

To estimate rainfall from remote sensing data, three machine learning-based regression models, K-Nearest Neighbors Regression (K-NNR), Support Vector Regression (SVR), and Random Forest Regression (RFR), were implemented using MSG (Meteosat Second Generation) satellite data. Daytime and nighttime data from a rain gauge are used for model training and validation. To optimize the results, the outputs of the three models are combined using the weighted average. The combination of the three models (hereafter called Com-RSK) markedly improved the predictions. Indeed, the MAE, MBE, RMSE and correlation coefficient went from 23.6 mm, 10.0 mm, 40.6 mm and 89% for the SVR to 20.7 mm, 5.5 mm, 37.4 mm, and 94% when the models were combined, respectively. The Com-RSK is also compared to a few methods using the classification in the estimation, such as the ECST Enhanced Convective Stratiform Technique (ECST), the MMultic technique, and the Convective/Stratiform Rain Area Delineation Technique (CS-RADT). The Com-RSK show superior performance compared to ECST, MMultic and CS-RADT methods.The Com-RSK is also compared to the two products of satellite estimates, namely CMORPH and CHIRPS. The results indicate that Com-RSK performs better than CMORPH and CHIRPS according to MBE, RMSE and CC (coefficient correlation). A comparison with three types of satellite precipitation estimation products, such as global product, regional product, and near real-time product, is performed. Overall, the methodology developed here shows almost the same results as regional product methods and exhibits better results than near real-time and global product methods.

A machine learning q-RASPR approach for efficient predictions of the specific surface area of perovskites.

In this study, the specific surface area of various perovskites was modeled using a novel quantitative read-across structure-property relationship (q-RASPR) approach, which clubs both Read-Across (RA) and quantitative structure-property relationship (QSPR) together. After optimization of the hyper-parameters, certain similarity-based error measures for each query compound were obtained. Clubbing some of these error-based measures with the previously selected features along with the Read-Across prediction function, a number of machine learning models were developed using Partial Least Squares (PLS), Ridge Regression (RR), Linear Support Vector Regression (LSVR), Random Forest (RF) regression, Gradient Boost (GBoost), Adaptive Boosting (Adaboost), Multiple Layer Perceptron (MLP) regression and k-Nearest Neighbor (kNN) regression. Based on the repeated cross-validation as well as external prediction quality and interpretability, the PLS model (nTraining = 38, nTest = 12, =0.737, was selected as the best predictor which underscored the previously reported results. The finally selected model should efficiently predict specific surface areas of other perovskites for their use in photocatalysis. The new q-RASPR method also appears promising for the prediction of several other property endpoints of interest in materials science.

Estimating stomatal conductance of citrus under water stress based on multispectral imagery and machine learning methods.

Canopy stomatal conductance (Sc) indicates the strength of photosynthesis and transpiration of plants. In addition, Sc is a physiological indicator that is widely employed to detect crop water stress. Unfortunately, existing methods for measuring canopy Sc are time-consuming, laborious, and poorly representative. To solve these problems, in this study, we combined multispectral vegetation index (VI) and texture features to predict the Sc values and used citrus trees in the fruit growth period as the research object. To achieve this, VI and texture feature data of the experimental area were obtained using a multispectral camera. The H (Hue), S (Saturation) and V (Value) segmentation algorithm and the determined threshold of VI were used to obtain the canopy area images, and the accuracy of the extraction results was evaluated. Subsequently, the gray level co-occurrence matrix (GLCM) was used to calculate the eight texture features of the image, and then the full subset filter was used to obtain the sensitive image texture features and VI. Support vector regression, random forest regression, and k-nearest neighbor regression (KNR) Sc prediction models were constructed, which were based on single and combined variables. The analysis revealed the following: 1) the accuracy of the HSV segmentation algorithm was the highest, achieving more than 80%. The accuracy of the VI threshold algorithm using excess green was approximately 80%, which achieved accurate segmentation. 2) The citrus tree photosynthetic parameters were all affected by different water supply treatments. The greater the degree of water stress, the lower the net photosynthetic rate (Pn), transpiration rate (Tr), and Sc of the leaves. 3) In the three Sc prediction models, The KNR model, which was constructed by combining image texture features and VI had the optimum prediction effect (training set: R2 = 0.91076, RMSE = 0.00070; validation set; R2 = 0.77937, RMSE = 0.00165). Compared with the KNR model, which was only based on VI or image texture features, the R2 of the validation set of the KNR model based on combined variables was improved respectively by 6.97% and 28.42%. This study provides a reference for large-scale remote sensing monitoring of citrus Sc by multispectral technology. Moreover, it can be used to monitor the dynamic changes of Sc and provide a new technique for gaining a better understanding of the growth status and water stress of citrus crops.

A Comparative Analysis of Multidimensional COVID-19 Poverty Determinants: An Observational Machine Learning Approach.

Poverty is a glaring issue in the twenty-first century, even after concerted efforts of organizations to eliminate the same. Predicting poverty using machine learning can offer practical models for facilitating the process of elimination of poverty. This paper uses Multidimensional Poverty Index Data from the Oxford Poverty and Human Development Initiative across the years 2019 and 2021 to make predictions of multidimensional poverty before and during the pandemic. Several poverty indicators under health, education and living standards are taken into consideration. The work implements several data analysis techniques like feature correlation and selection, and graphical visualizations to answer research questions about poverty. Various machine learning, such as Multiple Linear Regression, Decision Tree Regressor, Random Forest Regressor, XGBoost, AdaBoost, Gradient Boosting, Linear Support Vector Regressor (SVR), Ridge Regression, Lasso Regression, ElasticNet Regression, and K-Nearest Neighbor Regression algorithm, have been implemented to predict poverty across four datasets on a national and a subnational level. Regularization is used to increase the performance of the models, and cross-validation is used for estimation. Through a rigorous analysis and comparison of different models, this work identifies important poverty determinants and concludes that overall, Ridge Regression model performs the best with the highest R 2 score.

A New Drought Monitoring Index on the Tibetan Plateau Based on Multisource Data and Machine Learning Methods

Drought is a major disaster over the Tibetan Plateau (TP) that exerts great impacts on natural ecosystems and agricultural production. Furthermore, most drought indices are only useful for assessing drought conditions on a coarse temporal scale. Drought indices that describe drought evolution at a fine temporal scale are still scarce. In this study, four machine learning methods, including random forest regression (RFR), k-nearest neighbor regression (KNNR), support vector regression (SVR), and extreme gradient boosting regression (XGBR), were used to construct daily drought indices based on multisource remote sensing and reanalysis data. Through comparison with in situ soil moisture (SM) over the TP, our results indicate that the drought index based on the XGBR model outperforms other models (R2 = 0.76, RMSE = 0.11, MAE = 0.08), followed by RFR (R2 = 0.74, RMSE = 0.11, MAE = 0.08), KNNR (R2 = 0.73, RMSE = 0.11, MAE = 0.08) and SVR (R2 = 0.66, RMSE = 0.12, MAE = 0.1). A new daily drought index, the standardized integrated drought index (SIDI), was developed by the XGBR model for monitoring agricultural drought. A comparison with ERA5-Land SM and widely used indices such as SPI-6 and SPEI-6 indicated that the SIDI depicted the dry and wet change characteristics of the plateau well. Furthermore, the SIDI was applied to analyze a typical drought event and reasonably characterize the spatiotemporal patterns of drought evolution, demonstrating its capability and superiority for drought monitoring over the TP. In addition, soil properties accounted for 59.5% of the model output, followed by meteorological conditions (35.8%) and topographic environment (4.7%).

Forecasting PM10 Concentrations in the Caribbean Area Using Machine Learning Models

In the Caribbean basin, particulate matter lower or equal to 10 μm in diameter (PM10) has a huge impact on human mortality and morbidity due to the African dust. For the first time in this geographical area, the theoretical framework of artificial intelligence is applied to forecast PM10 concentrations. The aim of this study is to forecast PM10 concentrations using six machine learning (ML) models: support vector regression (SVR), k-nearest neighbor regression (kNN), random forest regression (RFR), gradient boosting regression (GBR), Tweedie regression (TR), and Bayesian ridge regression (BRR). Overall, with MBEmax = −2.8139, the results showed that all the models tend to slightly underestimate PM10 empirical data. GBR is the model that gives the best performance (r = 0.7831, R2 = 0.6132, MAE = 6.8479, RMSE = 10.4400, and IOA = 0.7368). By comparing our results to other PM10 ML studies in megacities, we found similar performance using only three input variables, whereas previous studies use many input variables with Artificial Neural Network (ANN) models. All these results showed the features of PM10 concentrations in the Caribbean area.

Estimation Method of State of Charge of Power Battery of New Energy Vehicle Based on K Nearest Neighbor Regression

In order to improve the power battery state of charge detection ability of new energy vehicles and reduce harmonic interference, a measurement method of power battery state of new energy vehicles based on K-nearest neighbor regression analysis is proposed. Build a charging state parameter collection model of new energy vehicle power battery, consider the unbalanced power of uncertain factors, realize the oscillation and fusion processing of charging state of new energy vehicle power battery through the dynamic matching method of mobile energy storage resources of electric vehicle, extract the microgrid load fluctuation characteristic value of charging state signal of new energy vehicle power battery, and analyze the percentage of remaining electricity to rated capacity. The initial charge and capacity characteristics of the battery of the new energy vehicle power battery are matched. The K-nearest neighbor regression analysis method is used to realize the regression analysis and dynamic estimation of the battery state of charge parameters. According to the state of charge of the new energy vehicle power battery, the steady-state characteristic quantity is output, and the demand response load model parameter reconstruction and load balance matching method are used to realize the state of charge estimation and parameter adaptive evaluation of the new energy vehicle power battery. The simulation results show that the accuracy of measuring the state of charge of the power battery of new energy vehicles is high, and the harmonic suppression ability is strong, which improves the balanced configuration and load balancing scheduling ability of the power system of the power battery of new energy vehicles.

Intelligent digital twin – machine learning system for real-time wind turbine wind speed and power generation forecasting

Wind power is a key pillar in efforts to decarbonise energy production. However, variability in wind speed and resultant wind turbine power generation poses a challenge for power grid integration. Digital Twin (DT) technology provides intelligent service systems, combining real-time monitoring, predictive capabilities and communication technologies. Current DT research for wind turbine power generation has focused on providing wind speed and power generation predictions reliant on Supervisory Control and Data Acquisition (SCADA) sensors, with predictions often limited to the timeframe of datasets. This research looks to expand on this, utilising a novel framework for an intelligent DT system powered by k-Nearest Neighbour (kNN) regression models to upscale live wind speed forecasts to higher wind turbine hub-height and then forecast power generation. As there is no live link to a wind turbine, the framework is referred to as a “Simulated Digital Twin” (SimTwin). 2019-2020 SCADA and wind speed data are used to evaluate this, demonstrating that the method provides suitable predictions. Furthermore, full deployment of the SimTwin framework is demonstrated using live wind speed forecasts. This may prove useful for operators by reducing reliance on SCADA systems and provides a research and development tool where live data is limited.

MRIS: A Multi-modal Retrieval Approach for Image Synthesis on Diverse Modalities.

Multiple imaging modalities are often used for disease diagnosis, prediction, or population-based analyses. However, not all modalities might be available due to cost, different study designs, or changes in imaging technology. If the differences between the types of imaging are small, data harmonization approaches can be used; for larger changes, direct image synthesis approaches have been explored. In this paper, we develop an approach based on multi-modal metric learning to synthesize images of diverse modalities. We use metric learning via multi-modal image retrieval, resulting in embeddings that can relate images of different modalities. Given a large image database, the learned image embeddings allow us to use k-nearest neighbor (k-NN) regression for image synthesis. Our driving medical problem is knee osteoarthritis (KOA), but our developed method is general after proper image alignment. We test our approach by synthesizing cartilage thickness maps obtained from 3D magnetic resonance (MR) images using 2D radiographs. Our experiments show that the proposed method outperforms direct image synthesis and that the synthesized thickness maps retain information relevant to downstream tasks such as progression prediction and Kellgren-Lawrence grading (KLG). Our results suggest that retrieval approaches can be used to obtain high-quality and meaningful image synthesis results given large image databases.

Analysis of Influencing Factors and Distribution Simulation of Budget Hotel Room Pricing Based on Big Data and Machine Learning from a Spatial Perspective

The goal of investors in the hotel business is to maximize profits, and the price is an important means of achieving this goal. This has attracted many scholars to study the spatiotemporal relationship between hotel room prices and their possible influencing factors from different perspectives. However, most existing studies adopt the linear assumption of the hedonic model, with limited features and a lack of feature selection procedures. Additionally, there are few forecasts of hotel pricing from a spatial perspective. To overcome these gaps, this study adopts linear and nonlinear machine learning methods based on the “big data” of Sanya City to explore the influencing factors of budget hotel pricing. Based on the spatial perspective, 81 potential factors were considered. They are further selected using a feature extraction model called recursive feature elimination. Six machine-learning algorithms were evaluated and compared: random forest, extreme gradient boosting, multi-linear regression, support vector regression, multilayer perceptron regression, and K-nearest neighbor regression. The optimal value was used to further calculate the feature importance. They disclosed 40 important impact characteristics and predicted the spatial distribution of hotel pricing.

Machine learning of plasma metabolome identifies biomarker panels for metabolic syndrome: findings from the China Suboptimal Health Cohort

BackgroundMetabolic syndrome (MetS) has been proposed as a clinically identifiable high-risk state for the prediction and prevention of cardiovascular diseases and type 2 diabetes mellitus. As a promising “omics” technology, metabolomics provides an innovative strategy to gain a deeper understanding of the pathophysiology of MetS. The study aimed to systematically investigate the metabolic alterations in MetS and identify biomarker panels for the identification of MetS using machine learning methods.MethodsNuclear magnetic resonance-based untargeted metabolomics analysis was performed on 1011 plasma samples (205 MetS patients and 806 healthy controls). Univariate and multivariate analyses were applied to identify metabolic biomarkers for MetS. Metabolic pathway enrichment analysis was performed to reveal the disturbed metabolic pathways related to MetS. Four machine learning algorithms, including support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and logistic regression were used to build diagnostic models for MetS.ResultsThirteen significantly differential metabolites were identified and pathway enrichment revealed that arginine, proline, and glutathione metabolism are disturbed metabolic pathways related to MetS. The protein-metabolite-disease interaction network identified 38 proteins and 23 diseases are associated with 10 MetS-related metabolites. The areas under the receiver operating characteristic curve of the SVM, RF, KNN, and logistic regression models based on metabolic biomarkers were 0.887, 0.993, 0.914, and 0.755, respectively.ConclusionsThe plasma metabolome provides a promising resource of biomarkers for the predictive diagnosis and targeted prevention of MetS. Alterations in amino acid metabolism play significant roles in the pathophysiology of MetS. The biomarker panels and metabolic pathways could be used as preventive targets in dealing with cardiometabolic diseases related to MetS.