Computationally Efficient and Effective Machine Learning Model Using Time Series Data in Different Prediction Problems

2021 ◽  
pp. 218-233
Author(s):  
Dwiti Krishna Bebarta ◽  
Birendra Biswal
Keyword(s):  
Machine Learning ◽  
Predictive Models ◽  
Time Series Data ◽  
Predictive Analytics ◽  
Learning Model ◽  
Series Data ◽  
Computationally Efficient ◽  
Machine Learning Model ◽  
High Degree ◽  
Prediction Problems

Automated feature engineering is to build predictive models that are capable of transforming raw data into features, that is, creation of new features from existing ones on various datasets to create meaningful features and examining their effect on planned model performances on various parameters like accuracy, efficiency, and prevent data leakage. So the challenges for experts are to plan computationally efficient and effective machine, learning-based predictive models. This chapter will provide an imminent to the important intelligent techniques that could be utilized to enhance predictive analytics by using an advanced form of the predictive model. A computationally efficient and effective machine learning model using functional link artificial neural network (FLANN) is discussed to design for predicting the business needs with a high degree of accuracy for the traders or investors. The performance of the models using FLANN is encouraging when scientifically analyzed the experimental results of the model using different statistical analyses.

scholarly journals Forecasting Amazon Rain-Forest Deforestation Using a Hybrid Machine Learning Model

2022 ◽  
Vol 14 (2) ◽  
pp. 691
Author(s):  
David Dominguez ◽  
Luis de Juan del Villar ◽  
Odette Pantoja ◽  
Mario González-Rodríguez
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Rain Forest ◽  
Time Series Data ◽  
Learning Model ◽  
Series Data ◽  
Amazon Rain Forest ◽  
Machine Learning Model ◽  
Hybrid Machine ◽  
The Impact

The present work aims to carry out an analysis of the Amazon rain-forest deforestation, which can be analyzed from actual data and predicted by means of artificial intelligence algorithms. A hybrid machine learning model was implemented, using a dataset consisting of 760 Brazilian Amazon municipalities, with static data, namely geographical, forest, and watershed, among others, together with a time series data of annual deforestation area for the last 20 years (1999–2019). The designed learning model combines dense neural networks for the static variables and a recurrent Long Short Term Memory neural network for the temporal data. Many iterations were performed on augmented data, testing different configurations of the regression model, for adjusting the model hyper-parameters, and generating a battery of tests to obtain the optimal model, achieving a R-squared score of 87.82%. The final regression model predicts the increase in annual deforestation area (square kilometers), for a decade, from 2020 to 2030, predicting that deforestation will reach 1 million square kilometers by 2030, accounting for around 15% compared with the present 1%, of the between 5.5 and 6.7 millions of square kilometers of the rain-forest. The obtained results will help to understand the impact of man’s footprint on the Amazon rain-forest.

Predictive Analytics for OSA Detection Using Non-Conventional Metrics

2020 ◽  
Vol 10 (4) ◽  
pp. 13-23
Author(s):  
Vinit Kumar Gunjan ◽  
Madapuri Rudra Kumar
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Sleep Apnea ◽  
Early Diagnosis ◽  
Predictive Analytics ◽  
Learning Model ◽  
Model Tests ◽  
Svm Classifier ◽  
Machine Learning Model ◽  
Effective Performance

Early diagnosis in the case of the sleep apnea has its own set of benefits for treating the cases. However, there are many challenges and limitations that impact the current conditions for testing. In this manuscript, a model is proposed for early diagnosis of OSA, using the non-conventional metrics. Profoundly, the metrics used are combination of symptoms, causes, and effects of the problem. Using a machine learning model and two sets of classifiers, the inputs collected as part of the training datasets are used for analysis. The data classifiers used for the model tests are NB and SVM. In a comparative analysis of the results, it is imperative that SVM classifier-based training of the proposed algorithm is giving more effective performance.

scholarly journals An Advanced Machine Learning Model for Disease Prediction

2020 ◽  
Vol 9 (2) ◽  
pp. 1220-1225
Keyword(s):  
Machine Learning ◽  
Predictive Analytics ◽  
Learning Model ◽  
Control Measures ◽  
Disease Prediction ◽  
Common People ◽  
Machine Learning Model ◽  
The World ◽  
Conventional Models ◽  
Precision Rate

To settle on right choices and pass on about vital control measures, numerous flare-up expectation models for anticipating COVID-19 are getting utilized all round the world. Straightforward conventional models have indicated extremely less precision rate for future forecast use, because of more significant levels of vulnerability and absence of proper information. Among the different machine learning model algorithms contemplated, an ensembled model was seen as giving the best outcomes. Because of the multifaceted nature of the virus's temperament, this research paper recommends machine learning to be an extremely helpful gadget to consider in case of the ongoing pandemic. This paper gives a colossal benchmark to call attention to the probability of machine learning to be utilized as an instrument for future exploration on pandemic control and its timely prediction. Moreover, this paper delineates that the best prompts for pandemic prediction are frequently comprehended by combining machine learning, predictive analytics and visualisation tools like Tableau. The main purpose of this research is to build a perfect ML model prototype which can be later used when access to appropriate dataset (which is both large and consists of many different features) is available. Also, the secondary aim is to automate the process of reporting so as to facilitate quicker action by the concerned authorities, and help common people reach out to the correct destination for treatment or help. Furthermore, the Tableau analysis performed on the dataset is to provide more analytical depths for people with expertise in the medical domain.

scholarly journals A versatile computational algorithm for time-series data analysis and machine-learning models

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Taylor Chomiak ◽  
Neilen P. Rasiah ◽  
Leonardo A. Molina ◽  
Bin Hu ◽  
Jaideep S. Bains ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Computational Algorithm ◽  
Time Series Data ◽  
Simulated Data ◽  
Series Data ◽  
Learning Models ◽  
Machine Learning Model ◽  
Time Series Data Analysis

AbstractHere we introduce Local Topological Recurrence Analysis (LoTRA), a simple computational approach for analyzing time-series data. Its versatility is elucidated using simulated data, Parkinsonian gait, and in vivo brain dynamics. We also show that this algorithm can be used to build a remarkably simple machine-learning model capable of outperforming deep-learning models in detecting Parkinson’s disease from a single digital handwriting test.

scholarly journals Improving Current Glycated Hemoglobin Prediction in Adults: Consistency and Robustness of Machine Learning Algorithms with Electronic Health Records (Preprint)

2020 ◽  
Author(s):  
Zakhriya Alhassan ◽  
MATTHEW WATSON ◽  
David Budgen ◽  
Riyad Alshammari ◽  
Ali Alessan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Time Series Data ◽  
Learning Model ◽  
Series Data ◽  
Learning Models ◽  
Health Records ◽  
Conventional Machine ◽  
Deep Learning Model ◽  
Machine Learning Models

BACKGROUND Predicting the risk of glycated hemoglobin (HbA1c) elevation can help identify patients with the potential for developing serious chronic health problems such as diabetes and cardiovascular diseases. Early preventive interventions based upon advanced predictive models using electronic health records (EHR) data for such patients can ultimately help provide better health outcomes. OBJECTIVE Our study investigates the performance of predictive models to forecast HbA1c elevation levels by employing machine learning approaches using data from current and previous visits in the EHR systems for patients who had not been previously diagnosed with any type of diabetes. METHODS This study employed one statistical model and three commonly used conventional machine learning models, as well as a deep learning model, to predict patients’ current levels of HbA1c. For the deep learning model, we also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and have an understanding of the reasons behind the models' decisions. All models were trained and tested using a large and naturally balanced dataset from Saudi Arabia with 18,844 unique patient records. RESULTS The machine learning models achieved the best results for predicting current HbA1c elevation risk. The deep learning model outperformed the statistical and conventional machine learning models with respect to all reported measures when employing time-series data. The best performing model was the multi-layer perceptron (MLP) which achieved an accuracy of 74.52% when used with historical data. CONCLUSIONS This study shows that machine learning models can provide promising results for the task of predicting current HbA1c levels. For deep learning in particular, utilizing the patient's longitudinal time-series data improved the performance and affected the relative importance for the predictors used. The models showed robust results that were consistent with comparable studies.

scholarly journals Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization

2019 ◽  
Vol 33 ◽  
pp. 1658-1665 ◽  
Author(s):  
Bryan Wilder ◽  
Bistra Dilkina ◽  
Milind Tambe
Keyword(s):  
Machine Learning ◽  
Combinatorial Optimization ◽  
Loss Function ◽  
Optimization Algorithm ◽  
Predictive Models ◽  
Optimization Problems ◽  
Learning Model ◽  
Discrete Problem ◽  
Combinatorial Optimization Problems ◽  
Machine Learning Model

Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is first trained via a measure of predictive accuracy, and then its predictions are used as input into an optimization algorithm which produces a decision. However, the loss function used to train the model may easily be misaligned with the end goal, which is to make the best decisions possible. Hand-tuning the loss function to align with optimization is a difficult and error-prone process (which is often skipped entirely).We focus on combinatorial optimization problems and introduce a general framework for decision-focused learning, where the machine learning model is directly trained in conjunction with the optimization algorithm to produce highquality decisions. Technically, our contribution is a means of integrating common classes of discrete optimization problems into deep learning or other predictive models, which are typically trained via gradient descent. The main idea is to use a continuous relaxation of the discrete problem to propagate gradients through the optimization procedure. We instantiate this framework for two broad classes of combinatorial problems: linear programs and submodular maximization. Experimental results across a variety of domains show that decisionfocused learning often leads to improved optimization performance compared to traditional methods. We find that standard measures of accuracy are not a reliable proxy for a predictive model’s utility in optimization, and our method’s ability to specify the true goal as the model’s training objective yields substantial dividends across a range of decision problems.

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

Sign in / Sign up

Export Citation Format

Share Document