Linear Learning Algorithm Research Articles

Application of fuzzy DEA and machine learning algorithms in efficiency estimation of paddy producers of rural Eastern India

PurposeData envelopment analysis (DEA) has wide applications in the agricultural sector to evaluate the efficiency with crisp input and output data. However, in agricultural production, impreciseness and uncertainty in data are common. As a result, the data obtained from farmers vary. This impreciseness in crisp data can be represented in fuzzy sets. This paper aims to employ a combination of fuzzy data envelopment analysis (FDEA) approach to yield crisp DEA efficiency values by converting the fuzzy DEA model into a linear programming problem and machine learning algorithms for better evaluation and prediction of the variables affecting the farm efficiency.Design/methodology/approachDEA applications are focused on the use of a common two-step approach to find crucial factors that affect efficiency. It is important to identify impactful variables for minimizing production adversities. In this study, first, FDEA was applied for efficiency estimation and ranking of the paddy growers. Second, the support vector machine (SVM) and random forest (RF) were used for identifying the key leading factors in efficiency prediction.FindingsThe proposed research was conducted with 450 paddy growers. In comparison to the general DEA approach, the FDEA model evaluates fuzzy DEA efficiency giving the user the flexibility to measure the performance at different possibility levels.Originality/valueThe use of machine learning applications introduces advanced strategies and important factors influencing agricultural production, which may help future research in farms' performance.

A New Separable Piecewise Linear Learning Algorithm for the Stochastic Empty Container Repositioning Problem

A common challenge faced by liner operators in practice is to effectively allocate empty containers now in a way that minimizes the expectation of costs and reduces inefficiencies in the future with uncertainty. To incorporate uncertainties in the operational model, we formulate a two-stage stochastic programming model for the stochastic empty container repositioning (ECR) problem. This paper proposes a separable piecewise linear learning algorithm (SPELL) to approximate the expected cost function. The core of SPELL involves learning steps that provide information for updating the expected cost function adaptively through a sequence of piecewise linear separable approximations. Moreover, SPELL can utilize the network structure of the ECR problem and does not require any information about the distribution of the uncertain parameters. For the two-stage stochastic programs, we prove the convergence of SPELL. Computational results show that SPELL performs well in terms of operating costs. When the scale of the problem is very large and the dimensionality of the problem is increased, SPELL continues to provide consistent performance very efficiently and exhibits excellent convergence performance.

A machine learning approach to predict intravenous immunoglobulin resistance in Kawasaki disease patients: A study based on a Southeast China population.

Kawasaki disease is the leading cause of pediatric acquired heart disease. Coronary artery abnormalities are the main complication of Kawasaki disease. Kawasaki disease patients with intravenous immunoglobulin resistance are at a greater risk of developing coronary artery abnormalities. Several scoring models have been established to predict resistance to intravenous immunoglobulin, but clinicians usually do not apply those models in patients because of their poor performance. To find a better model, we retrospectively collected data including 753 observations and 82 variables. A total of 644 observations were included in the analysis, and 124 of the patients observed were intravenous immunoglobulin resistant (19.25%). We considered 7 different linear and nonlinear machine learning algorithms, including logistic regression (L1 and L1 regularized), decision tree, random forest, AdaBoost, gradient boosting machine (GBM), and lightGBM, to predict the class of intravenous immunoglobulin resistance (binary classification). Data from patients who were discharged before Sep 2018 were included in the training set (n = 497), while all the data collected after 9/1/2018 were included in the test set (n = 147). We used the area under the ROC curve, accuracy, sensitivity, and specificity to evaluate the performances of each model. The gradient GBM had the best performance (area under the ROC curve 0.7423, accuracy 0.8844, sensitivity 0.3043, specificity 0.9919). Additionally, the feature importance was evaluated with SHapley Additive exPlanation (SHAP) values, and the clinical utility was assessed with decision curve analysis. We also compared our model with the Kobayashi score, Egami score, Formosa score and Kawamura score. Our machine learning model outperformed all of the aforementioned four scoring models. Our study demonstrates a novel and robust machine learning method to predict intravenous immunoglobulin resistance in Kawasaki disease patients. We believe this approach could be implemented in an electronic health record system as a form of clinical decision support in the near future.

Reconfigurable Hardware Design for Automatic Epilepsy Seizure Detection using EEG Signals

Reconfigurable circuit designs for automatic seizure detection devices are essential to prevent epilepsy affected people from severe injuries and other health-related problems. In this proposed design, an automatic seizure detection algorithm based on the Linear binary Support Vector Machine learning algorithm (LSVM) is developed and implemented in a Field-Programmable Gate Array (FPGA). The experimental results showed that the mean detection accuracy is 86% and sensitivity is 97%. The resource utilization of the implemented design is less when compared to existing hardware implementations. The power consumption of the proposed design is 76mW at 100MHz. The experimental results assure that a physician can make use of this proposed design in detecting seizure events.

Integrating Landsat-8 and Sentinel-2 Time Series Data for Yield Prediction of Sugarcane Crops at the Block Level

Early prediction of sugarcane crop yield at the commercial block level (unit area of a single crop of the same variety, ratoon or planting date) offers significant benefit to growers, consultants, millers, policy makers, crop insurance companies and researchers. This current study explored a remote sensing based approach for predicting sugarcane yield at the block level by further developing a regionally specific Landsat time series model and including individual crop sowing (or previous seasons’ harvest) date. For the Bundaberg growing region of Australia this extends over a five months period, from July to November. For this analysis, the sugarcane blocks were clustered into 10 groups based on their specific planting or ratoon commencement date within the specified five months period. These clustered or groups of blocks were named ‘bins’. Cloud free (<20%) satellite data from the polar-orbiting Landsat-8 (launched 2013), Sentinel-2A (launched 2015) and Sentinel-2B (launched 2017) sensors were acquired over the cane growing region in Bundaberg (area of 32,983 ha), from the growing season starting in July 2014, with the average green normalised difference vegetation index (GNDVI) derived for each block. The number of images acquired for each season was defined by the number of cloud free acquisitions. Using the Simple Linear Machine Learning (ML) algorithm, the extracted Landsat derived GNDVI values for each of the blocks were converted to Sentinel GNDVI. The average GNDVI of each ‘bin’ was plotted and a quadratic model was fitted through the time series to identify the peak growth stage defined as the maximum GNDVI value. The model derived maximum GNDVI values for each of the bins were then regressed against the average actual yield (t·ha-1) achieved for the respective bin over the five growing years, producing strong correlations (R2 = 0.92 to 0.99). The quadratic curves developed for the different bins were shifted according to the specific planting or ratoon date of an individual block allowing for the peak GNDVI value of the block to be calculated, regressed against the actual block yield (t·ha-1) and the prediction of yield to be made. To validate the accuracies of the 10 time series algorithms representing each of the 10 bins, 592 individual blocks were selected from the Bundaberg region during the 2019 harvest season. The crops were clustered into the appropriate bins with the respective algorithm applied. From a Sentinel image acquired on the 5 May 2019, the prediction accuracies were encouraging (R2 = 0.87 and RMSE = 11.33 (t·ha-1)) when compared to actual harvested yield, as reported by the mill. The results presented in this paper demonstrate significant progress in the accurate prediction of sugarcane yield at the individual sugarcane block level using a remote sensing, time-series based approach.

Forecasting severe grape downy mildew attacks using machine learning.

Grape downy mildew (GDM) is a major disease of grapevine that has an impact on both the yields of the vines and the quality of the harvested fruits. The disease is currently controlled by repetitive fungicide treatments throughout the season, especially in the Bordeaux vineyards where the average number of fungicide treatments against GDM was equal to 10.1 in 2013. Reducing the number of treatments is a major issue from both an environmental and a public health point of view. One solution would be to identify vineyards that are likely to be heavily attacked in spring and then apply fungicidal treatments only to these situations. In this perspective, we use here a dataset including 9 years of GDM observations to develop and compare several generalized linear models and machine learning algorithms predicting the probability of high incidence and severity in the Bordeaux region. The algorithms tested use the date of disease onset and/or average monthly temperatures and precipitation as input variables. The accuracy of the tested models and algorithms is assessed by year-by-year cross validation. LASSO, random forest and gradient boosting algorithms show better performance than generalized linear models. The date of onset of the disease has a greater influence on the accuracy of forecasts than weather inputs and, among weather inputs, precipitation has a greater influence than temperature. The best performing algorithm was selected to evaluate the impact of contrasted climate scenarios on GDM risk levels. Results show that risk of GDM at bunch closure decreases with reduced rainfall and increased temperatures in April-May. Our results also show that the use of fungicide treatment decision rules that take into account local characteristics would reduce the number of treatments against GDM in the Bordeaux vineyards compared to current practices by at least 50%.

Stock Prediction Analysis by using Linear Regression Machine Learning Algorithm

Stock market is varying day to day. Many factors such as government policies, industry performance, market sentiment etc are the main cause of up and downs in stock market. To invest money in stock market, study and analysis of stock market is essential. This type of analysis can be done by using Machine learning algorithms. The main objective of this paper is to predict the stock market future values by using linear regression machine learn algorithms based on past values. The methodology is developed and implemented in python on APPLE and TSLA stock.

Received-Signal-Strength (RSS) Based 3D Visible-Light-Positioning (VLP) System Using Kernel Ridge Regression Machine Learning Algorithm With Sigmoid Function Data Preprocessing Method

In this work, we propose and demonstrate a received-signal-strength (RSS) based visible-light-positioning (VLP) system using sigmoid function data preprocessing (SFDP) method; and apply it to two types of regression based machine learning algorithms; including the second-order linear regression machine learning (LRML) algorithm, and the kernel ridge regression machine learning (KRRML) algorithm. Experimental results indicate that the use of SFDP method can significantly improve the positioning accuracies in both the LRML and KRRML algorithms. Besides, the SFDP with KRRML scheme outperforms the other three schemes in terms of position accuracy, with the experimental average positioning error of about 2 cm in both horizontal and vertical directions.

An Improved Potential Game Theory Based Method for Multi-UAV Cooperative Search

Unmanned Aerial Vehicle (UAV) has been widely used in a variety of application, and the target search is one of the hot issues in the UAV research fields. Compared with the single UAV, the multi-UAV system can be competent for more complex tasks, with higher execution efficiency and stronger robustness. However, there exist some new challenges in the multi-UAV cooperative search, such as collaborative control and search area covering problems. To complete these tasks efficiently, the cooperative search problem is modeled as a potential game, and a modified binary log linear learning (BLLL) algorithm is proposed in this paper, to solve the covering problem using multiple UAVs. Furthermore, to improve the cooperative control performance based on potential game theory, a novel action selection strategy for UAVs is proposed. This strategy can avoid a UAV wandering around at the zero utility area by exchanging the information with neighbors. Finally, various simulations are carried out. The experimental results show that the proposed method can effectively complete cooperative search tasks and has better performance than the original BLLL algorithm.

Interactive intelligent teaching and automatic composition scoring system based on linear regression machine learning algorithm

Intelligent education is an intelligent education platform that integrates correct education concept and Internet of things, big data, cloud computing and other technologies. This paper hopes to use the construction of the composition scoring model to further construct a computer scoring system for college English translation, which can give students a translation score and give feedback evaluation based on the quality of the translation. In this paper, according to the knowledge of the existing automatic scoring system at home and abroad, the feature selection method (TF-IDF, IG, CHI) is discussed and analyzed. Moreover, this paper studies the impact of our composition automatic scoring from the perspective of linguistics. In addition, this paper uses the multiple regression method to evaluate the final score. The features considered in this paper mainly include simple linguistic features and complex linguistic features. Finally, performance analysis of the algorithm model is performed by setting up a control experiment. The research results show that the proposed algorithm model has certain effects. The future trend is to form adult auxiliary machines through various human-computer interaction technologies, which will reshape future learning and education and form a new teaching form.

Multichannel DNA Sensor Array Fingerprints Cell States and Identifies Pharmacological Effectors of Catabolic Processes.

Cells at disease onset are often associated with subtle changes in the expression level of a single or few molecular components, making traditionally used biomarker-driven clinical diagnosis a challenging task. We demonstrate here the design of a DNA nanosensor array with multichannel output that identifies the normal or pathological state of a cell based on the alteration of its global proteomic signature. Fluorophore-encoded single-stranded DNA (ssDNA) strands were coupled via supramolecular interaction with a surface-functionalized gold nanoparticle quencher to generate this integrated sensor array. In this design, ssDNA sequences exhibit dual roles, where they provide differential affinities with the receptor gold nanoparticle as well as act as transducer elements. The unique interaction mode of the analyte molecules disrupts the noncovalent supramolecular complexation, generating simultaneous multichannel fluorescence output to enable signature-based analyte identification via a linear discriminant analysis-based machine learning algorithm. Different cell types, particularly normal and cancerous cells, were effectively distinguished using their fluorescent fingerprints. Additionally, this DNA sensor array displayed excellent sensitivity to identify cellular alterations associated with chemical modulation of catabolic processes. Importantly, pharmacological effectors, which could modulate autophagic flux, have been effectively distinguished by generating responses from their global protein signatures. Taken together, these studies demonstrate that our multichannel DNA nanosensor is well suited for rapid identification of subtle changes in a complex mixture and thus can be readily expanded for point-of-care clinical diagnosis, high-throughput drug screening, or predicting the therapeutic outcome from a limited sample volume.

Assessing the Impact of Spatial Proximity Data on the Solar Insolation Prediction

Improving the prediction of the availability of solar energy resources became a necessary component in the operation of utilities with a high penetration level of renewable energy resources. In this article, the solar insolation data in spatial proximity is leveraged to investigate the error in the prediction of solar insolation using multiple learning algorithms. Different error measures are utilized to evaluate the accuracy of the presented linear and nonlinear learning algorithms. Essential data preprocessing steps are conducted on the solar insolation data available from multiple meteorological stations in spatial proximity. The impact of utilizing the spatiotemporal data compared with the temporal data is analyzed. A comprehensive analysis based on multiple error measures is presented to compare the prediction error while employing multiple learning algorithms. It is shown that it is possible to identify the particular station and the particular learning algorithm that contribute the most in improving the solar insolation prediction of a specific location.

Collaborative linear manifold learning for link prediction in heterogeneous networks

Link prediction in heterogeneous networks aims at predicting missing interactions between pairs of nodes with the help of the topology of the target network and interconnected auxiliary networks. It has attracted considerable attentions from both computer science and bioinformatics communities in the recent years. In this paper, we introduce a novel Collaborative Linear Manifold Learning (CLML) algorithm. It can optimize the consistency of nodes similarities by collaboratively using the manifolds embedded between the target network and the auxiliary network. The experiments on four benchmark datasets have demonstrated the outstanding advantages of CLML, not only in the high prediction performance compared to baseline methods, but also in the capability to predict the unknown interactions in the target networks accurately and effectively.

Neuro-Fuzzy Modeling of Data Singular Spectrum Decomposition and Traffic Flow Prediction

Dynamic traffic flow prediction is one of the important topics in traffic engineering and intelligent transportation systems. The traffic flow has stochastic nature and nonlinear dynamics which make accurate prediction of traffic flow a challenging process. In most existing methods, the nonlinear and stochastic qualities of traffic flow have not been taken into consideration simultaneously and these methods do not possess satisfactory accuracy either. In this paper, in order to reduce the prediction error based on traffic flow characteristics, we applied two different methods. At first, we applied a locally linear neuro-fuzzy method using local linear model tree learning algorithm for nonlinear identification of traffic flow. Then, to eliminate the noisy components and also to increase the prediction accuracy, we proposed a method, which is the combination of singular spectrum analysis (SSA) and locally linear neuro-fuzzy model (LLNF). In this method, firstly, the principal components of the traffic flow time series were extracted, several noisy and unimportant components were thrown out and then every remained important component was modeled by using a LLNF network, the trained networks were utilized for one-step-ahead prediction, and finally the predicted patterns were combined to construct the general prediction. Moreover, we compared the results of these two methods with each other and also with those of several other intelligent methods such as multi-layer perceptron, radial-basis function, network and adaptive network fuzzy inference system. The simulation results revealed that the proposed SSA + LLNF approach for traffic flow prediction had promising and superior performance.

Multiple Machine Learning Classifiers for Student’s Admission to University Prediction

Data is the most important asset for any organization which is further processed to produce useful information. Machine Learning and Big Data techniques are widely used for industrial sectors to generate useful patterns helpful for earning more profits and expand businesses. From the past few years, a lot of research works have been done by using Big Data techniques on educational data for improvement in Education System. Machine Learning and Big Data can be useful for predicting the students’ admission, performance of teaching, performance of a student, identifying the group of students of similar behavior. However, the manual process of record checking is time consuming, tedious, and error prone; due to the inherent volume and complexity of data. In this study, the combination of linear and non-linear machine learning algorithms; Logistic Regression, Decision Tree, k-NN, and Naïve Bayes have been chosen to perform prediction of the target class for an unseen observation by polling. As the models built in this work are predicting the likelihood of a student taking up the admission into any university based on the student data collected by any marketing agency, the combined models are collectively called as the Admission Predictor. The administrative officials of any academic institution can use this kind of an application to explore and analyze the patterns that are affecting the student admission and come up with enhanced strategies to improve admission. Such an application not only plays a vital role in administration, but also help the management in reformulating the marketing criteria for overall development of academic institution.

A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide

Empirical spatial air pollution models have been applied extensively to assess exposure in epidemiological studies with increasingly sophisticated and complex statistical algorithms beyond ordinary linear regression. However, different algorithms have rarely been compared in terms of their predictive ability.This study compared 16 algorithms to predict annual average fine particle (PM2.5) and nitrogen dioxide (NO2) concentrations across Europe. The evaluated algorithms included linear stepwise regression, regularization techniques and machine learning methods. Air pollution models were developed based on the 2010 routine monitoring data from the AIRBASE dataset maintained by the European Environmental Agency (543 sites for PM2.5 and 2399 sites for NO2), using satellite observations, dispersion model estimates and land use variables as predictors. We compared the models by performing five-fold cross-validation (CV) and by external validation (EV) using annual average concentrations measured at 416 (PM2.5) and 1396 sites (NO2) from the ESCAPE study. We further assessed the correlations between predictions by each pair of algorithms at the ESCAPE sites.For PM2.5, the models performed similarly across algorithms with a mean CV R2 of 0.59 and a mean EV R2 of 0.53. Generalized boosted machine, random forest and bagging performed best (CV R2~0.63; EV R2 0.58–0.61), while backward stepwise linear regression, support vector regression and artificial neural network performed less well (CV R2 0.48–0.57; EV R2 0.39–0.46). Most of the PM2.5 model predictions at ESCAPE sites were highly correlated (R2 > 0.85, with the exception of predictions from the artificial neural network). For NO2, the models performed even more similarly across different algorithms, with CV R2s ranging from 0.57 to 0.62, and EV R2s ranging from 0.49 to 0.51. The predicted concentrations from all algorithms at ESCAPE sites were highly correlated (R2 > 0.9). For both pollutants, biases were low for all models except the artificial neural network. Dispersion model estimates and satellite observations were two of the most important predictors for PM2.5 models whilst dispersion model estimates and traffic variables were most important for NO2 models in all algorithms that allow assessment of the importance of variables.Different statistical algorithms performed similarly when modelling spatial variation in annual average air pollution concentrations using a large number of training sites.

Cross domain association using transfer subspace learning

Transfer learning has gained more attention recently by utilizing knowledge acquired from one domain to advance a learning performance in another domain. Existing homogeneous transfer learning methods have progressed to a point where feature spaces are common in training and testing domains. However, heterogeneous transfer learning is still in its nascent stage where features of training and testing domains are different. Taking this into account, Bregman Divergence Regularization is used to minimize the probability distribution difference between training and testing domains and to take them together to a shared subspace. To discriminate data within individual domains, a projection matrix is obtained using Fisher Linear Discriminant Analysis subspace learning algorithm. Experimentation is performed on two efficiently used biometrics: the face and fingerprint. Two types of cross-domain settings are used: (1) Face + Finger2Finger where training samples come from face (labeled samples) and fingerprint (unlabeled samples) data sets, while testing is performed on a fingerprint dataset. (2) Finger + Face2Face where training samples come from fingerprint (labeled samples) and face (unlabeled samples) data sets while testing is performed on a face dataset. This paper proposes a cross domain association between face and fingerprint that finds utility in forensic applications.

Predicting the vessel lumen area tree-ring parameter of <i>Quercus robur</i> with linear and nonlinear machine learning algorithms

Climate-growth relationships in <i>Quercus robur</i> chronologies for vessel lumen area (VLA) from two oak stands (QURO-1 and QURO-2) showed a consistent temperature signal: VLA is highly correlated with mean April temperature and the temperature at the end of the previous growing season. QURO-1 showed significant negative correlations with winter sums of precipitation. Selected climate variables were used as predictors of VLA in a comparison of various linear and nonlinear machine learning methods: Artificial Neural Networks (ANN), Multiple Linear Regression (MLR), Model Trees (MT), Bagging of Model Trees (BMT) and Random Forests of Regression Trees (RF). ANN outperformed all the other regression algorithms at both sites. Good performance also characterised RF and BMT, while MLR, and especially MT, displayed weaker performance. Based on our results, advanced machine learning algorithms should be seriously considered in future climate reconstructions.

Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan’s electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area.

Improvement of Automated Learning Methods based on Linear Learning Algorithms

In recent years, the process of learning creatures is converted to one of the new research area. These researches are divided into two general categories that one of them is based on proposing a solution and learning based methodology to any machines. Learning is defined as changes made in the performance of a system based on experiences. The most prominent features of learning-based systems are that they improve themselves over time. Therefore, learning based machines have a big role in these systems. However, they are not very productive in some application and research areas such as smart real time systems especially. In this paper is proposed a new approach based on reinforcement learning technique that has three versions in order to implementation in different areas. It behaviors based on reward and penalty model. The effectiveness of these interactions with the environment is evaluated by the maximum (minimum) of the number of rewards (penalty) taken from the environment. The main advantage of the reinforcement learning over other learning methods is the need for no information from the environment (except amplification signal). The other learning methods as supervised or unsupervised are not appropriate to these problems. In this method, each agent decides the next its actions based on current k-actions instead of one action. The three versions are simple, sequential and unstructured linear learning methods so they evaluated in different possibilities to get the appropriate responses. Depending on the needs of any system, they can be used. The mode of convergence of actions in the proposed automaton (machine) in six different scenarios is examined.