scholarly journals A Novel Machine Learning Approach Combined with Optimization Models for Eco-efficiency Evaluation

2020 ◽  
Vol 10 (15) ◽  
pp. 5210 ◽  
Author(s):  
Mirpouya Mirmozaffari ◽  
Maziar Yazdani ◽  
Azam Boskabadi ◽  
Hamidreza Ahady Dolatsara ◽  
Kamyar Kabirifar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Developing Countries ◽  
Clustering Algorithms ◽  
Efficiency Score ◽  
Performance Model ◽  
Small Samples ◽  
Learning Approaches ◽  
Third Places ◽  
Free Disposal Hull ◽  
Decision Making Unit

Machine learning approaches have been developed rapidly and also they have been involved in many academic findings and discoveries. Additionally, they are widely assessed in numerous industries such as cement companies. Cement companies in developing countries, despite many profits such as valuable mines, face many challenges. Optimization, as a key part of machine learning, has attracted more attention. The main purpose of this paper is to combine a novel Data Envelopment Analysis (DEA) approach in optimization at the first step to find the Decision-Making Unit (DMU) with innovative clustering algorithms in machine learning at the second step introduce the model and algorithm with higher accuracy. At the optimization section with converting two-stage to a simple standard single-stage model, 24 cement companies from five developing countries over 2014–2019 are compared. Window-DEA analysis is used since it leads to increase judgment on the consequences, mainly when applied to small samples followed by allowing year-by-year comparisons of the results. Applying window analysis can be beneficial for managers to expand their comparison and evaluation. To find the most accurate model CCR (Charnes, Cooper and Rhodes model), BBC (Banker, Charnes and Cooper model) and Free Disposal Hull (FDH) DEA model for measuring the efficiency of decision processes are used. FDH model allows the free disposability to construct the production possibility set. At the machine learning section, a novel three-layers data mining filtering pre-processes proposed by expert judgment for clustering algorithms to increase the accuracy and to eliminate unrelated attributes and data. Finally, the most efficient company, best performance model and the most accurate algorithm are introduced. The results indicate that the 22nd company has the highest efficiency score with an efficiency score of 1 for all years. FDH model has the highest efficiency scores during all periods compared with other suggested models. K-means algorithm receives the highest accuracy in all three suggested filtering layers. The BCC and CCR models have the second and third places, respectively. The hierarchical clustering and density-based clustering algorithms have the second and third places, correspondingly.

scholarly journals Machine learning Clustering Algorithms Based on the DEA Optimization Approach for Banking System in Developing Countries

2020 ◽  
Vol 5 (6) ◽  
pp. 651-658 ◽  
Author(s):  
Mirpouya Mirmozaffari ◽  
Azam Boskabadi ◽  
Gohar Azeem ◽  
Reza Massah ◽  
Elahe Boskabadi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Developing Countries ◽  
Data Envelopment Analysis ◽  
Clustering Algorithms ◽  
Banking System ◽  
Additive Models ◽  
Malmquist Productivity Index ◽  
Productivity Index ◽  
Optimization Approach ◽  
Data Envelopment

Machine learning grows quickly, which has made numerous academic discoveries and is extensively evaluated in several areas. Optimization, as a vital part of machine learning, has fascinated much consideration of practitioners. The primary purpose of this paper is to combine optimization and machine learning to extract hidden rules, remove unrelated data, introduce the most productive Decision-Making Units (DMUs) in the optimization part, and to introduce the algorithm with the highest accuracy in Machine learning part. In the optimization part, we evaluate the productivity of 30 banks from eight developing countries over the period 2015-2019 by utilizing Data Envelopment Analysis (DEA). An additive Data Envelopment Analysis (DEA) model for measuring the efficiency of decision processes is used. The additive models are often named Slack Based Measure (SBM). This group of models measures efficiency via slack variables. After applying the proposed model, the Malmquist Productivity Index (MPI) is computed to evaluate the productivity of companies. In the machine learning part, we use a specific two-layer data mining filtering pre-processes for clustering algorithms to increase the efficiency and to find the superior algorithm. This study tackles data and methodology-related issues in measuring the productivity of the banks in developing countries and highlights the significance of DMUs productivity and algorithms accuracy in the banking industry by comparing suggested models.

scholarly journals Forecasting Mobility Trends in Southeast Asia during the Coronavirus (Covid-19) Pandemic by Machine Learning Approaches

2021 ◽  
pp. 45-53
Keyword(s):  
Machine Learning ◽  
Southeast Asia ◽  
Spatial Data ◽  
Performance Model ◽  
World Health ◽  
Learning Approaches ◽  
Health Authorities ◽  
Short Period ◽  
Novel Coronavirus ◽  
Health Organization

The novel coronavirus (COVID-19) was declared as the 2019-20 coronavirus pandemic by the World Health Organization (WHO) in March 2020. The COVID-19 virus has rapidly spread nationwide and internationally and caused 188 countries to report more than ten million cases of individuals contracting COVID-19. Typically, the virus is conveyed from person to person via respiratory droplets produced by coughing and sneezing. The time period between exposure and onset of symptoms is typically between two and fourteen days, and on average five days. The COVID-19 pandemic has affected many businesses relating to transportation including tourism, import-export commerce, the aviation business, and so forth. Governmental intervention in each country has had an impact on mobility trends depending on the degree of restriction such as social distancing, sharing mobility, and public transport. A COVID-19 surveillance system is one of the principal methods used for detecting COVID-19 epidemics, using short-period monitoring. However, while these networks present information on the activities of COVID-19, acquiring completed surveillance data from every medical station is profusely difficult due to many factors. This research aims to propose a performance model of machine learning approaches for COVID-19 pandemic forecasting of mobility trends in each country in Southeast Asia. Spatial data and non-spatial data are used to build the machine learning models. The experiments conducted showed that the model gave a forecasting accuracy in walking and driving mobility of 94.40% and 92.00%, respectively. The proposed forecasting model was developed to be of benefits to health authorities in the planning and administration of a suitable strategy to make decisions concerning transportation planning in each country.

scholarly journals Analysis of Cattle Social Transitional Behaviour: Attraction and Repulsion

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5340
Author(s):  
Haocheng Xu ◽  
Shenghong Li ◽  
Caroline Lee ◽  
Wei Ni ◽  
David Abbott ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Interactions ◽  
Management Practices ◽  
Clustering Algorithms ◽  
Physical Distance ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
Video Recordings ◽  
Learning Techniques ◽  
The Social

Understanding social interactions in livestock groups could improve management practices, but this can be difficult and time-consuming using traditional methods of live observations and video recordings. Sensor technologies and machine learning techniques could provide insight not previously possible. In this study, based on the animals’ location information acquired by a new cooperative wireless localisation system, unsupervised machine learning approaches were performed to identify the social structure of a small group of cattle yearlings (n=10) and the social behaviour of an individual. The paper first defined the affinity between an animal pair based on the ranks of their distance. Unsupervised clustering algorithms were then performed, including K-means clustering and agglomerative hierarchical clustering. In particular, K-means clustering was applied based on logical and physical distance. By comparing the clustering result based on logical distance and physical distance, the leader animals and the influence of an individual in a herd of cattle were identified, which provides valuable information for studying the behaviour of animal herds. Improvements in device robustness and replication of this work would confirm the practical application of this technology and analysis methodologies.

scholarly journals The Comparative Efficiency Analysis of EU Members Agriculture Sectors

2017 ◽  
Vol 37 (332) ◽  
pp. 10-19 ◽  
Author(s):  
Eligijus Laurinavičius ◽  
Daiva Rimkuvienė
Keyword(s):  
Stochastic Frontier ◽  
Efficiency Score ◽  
Data Envelopment ◽  
Multifunctional Agriculture ◽  
Stochastic Frontier Approach ◽  
Free Disposal Hull ◽  
Comparative Efficiency ◽  
Free Disposal ◽  
Decision Making Unit ◽  
Dea Method

Abstract Production economics forms a very important part of an enormous range of economic theory. Agricultural production is no exception. When evaluating the competitiveness of the multifunctional agriculture, it is necessary to use the measure of efficiency instead of productivity. The conception of the efficiency is explained and the methods for measurement are provided. The authors discuss the methods of Stochastic Frontier Approach (SFA), Free Disposal Hull (FDH) and Data Envelopment Analysis (DEA) that are particularly useful for multi-criterial evaluation of multifunctional processes. Those methods assign an efficiency score to each Decision Making Unit (DMU) based on how well it transforms a given set of inputs into outputs. Most studies have only focused on application of DEA method for assesment of the efficiency of agriculture farms. There is still a need on applications for sectors. This paper provides an examination of the applicability of DEA method to agriculture sectors efficiency measurement. By applying mathematical models, which are based on the DEA, the efficiency of agriculture in each EU country was evaluated.

scholarly journals Benchmark and application of unsupervised classification approaches for univariate data

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Maria El Abbassi ◽  
Jan Overbeck ◽  
Oliver Braun ◽  
Michel Calame ◽  
Herre S. J. van der Zant ◽  
...  
Keyword(s):  
Machine Learning ◽  
A Priori ◽  
Clustering Algorithms ◽  
Feature Space ◽  
Unsupervised Classification ◽  
Optimum Number ◽  
Data Sets ◽  
Learning Approaches ◽  
Wide Range ◽  
Characteristic Features

AbstractUnsupervised machine learning, and in particular data clustering, is a powerful approach for the analysis of datasets and identification of characteristic features occurring throughout a dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the data structure. Here, we introduce an approach for unsupervised data classification of any dataset consisting of a series of univariate measurements. It is therefore ideally suited for a wide range of measurement types. We apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in data sets. We also provide guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of novel and existing machine learning approaches and observe significant performance differences. Careful selection of the feature space construction method and clustering algorithms for a specific measurement type can therefore greatly improve classification accuracies.

scholarly journals Product Sentiment Analysis for Amazon Reviews

2021 ◽  
Vol 13 (3) ◽  
pp. 15-30
Author(s):  
Arwa S. M. AlQahtani
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Binary Classification ◽  
Rapid Development ◽  
Performance Model ◽  
Machine Learning Algorithms ◽  
Sentiment Classification ◽  
Learning Approaches ◽  
Customer Reviews ◽  
Online Customer Reviews

Recently, Ecommerce has Witnessed Rapid Development. As A Result, Online Purchasing has grown, and that has led to Growth in Online Customer Reviews of Products. The Implied Opinions in Customer Reviews Have a Massive Influence on Customer's Decision Purchasing, Since the Customer's Opinion About the Product is Influenced by Other Consumers' Recommendations or Complaints. This Research Provides an Analysis of the Amazon Reviews Dataset and Studies Sentiment Classification with Different Machine Learning Approaches. First, the Reviews were Transformed into Vector Representation using different Techniques, I.E., Bag-Of-Words, Tf-Idf, and Glove. Then, we Trained Various Machine Learning Algorithms, I.E., Logistic Regression, Random Forest, Naïve Bayes, Bidirectional Long-Short Term Memory, and Bert. After That, We Evaluated the Models using Accuracy, F1-Score, Precision, Recall, and Cross-Entropy Loss Function. Then, We Analyized The Best Performance Model in Order to Investigate Its Sentiment Classification. The Experiment was Conducted on Multiclass Classifications, Then we Selected the Best Performing Model And Re-Trained It on the Binary Classification.

scholarly journals Deep learning for small and big data in psychiatry

2020 ◽  
Vol 46 (1) ◽  
pp. 176-190 ◽  
Author(s):  
Georgia Koppe ◽  
Andreas Meyer-Lindenberg ◽  
Daniel Durstewitz
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Prediction Performance ◽  
Statistical Hypothesis ◽  
Small Samples ◽  
Single Subject ◽  
Model Parameters ◽  
Learning Approaches ◽  
Comprehensive Overview ◽  
The Common

AbstractPsychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of ‘small’ experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather ‘small’ samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving a comprehensive overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.

scholarly journals Machine Learning Algorithms Based on an Optimization Model

2020 ◽  
Author(s):  
Mirpouya Mirmozaffari ◽  
Noorbakhsh Amiri Golilarz ◽  
Shahab S. Band
Keyword(s):  
Machine Learning ◽  
Optimization Model ◽  
Clustering Algorithms ◽  
Stochastic Frontier ◽  
Performance Model ◽  
Machine Learning Algorithms ◽  
Attribute Selection ◽  
Coefficient Of Determination ◽  
Scientific Assessment ◽  
Non Parametric

The main purpose of this paper is to propose a novel optimization model with a new machine learning approach in the first section to achieve the best results in financial institutions in the second section. Since the constancy of efficacy derived from parametric and non-parametric is not significant, this paper provides a scientific assessment at the optimization section and proposes a novel combined parametric and non-parametric model which will be a new experiment in literature perception. A scientific assessment of banks based on a combination of the efficiency measurement method of CCR(Charnes, Cooper and Rhodes model) or CRS(Constant Return to Scale) BCC(Banker, Charnes, and Cooper model) or VRS (Variable Return to Scale) in Data Envelopment Analysis (DEA), as well as Stochastic Frontier Approach (SFA) for 65 banks during Feb to July 2020, are introduced. For analyzing the performance of the parametric and non-parametric approaches we have considered the linear regression and Unreplicated Linear Functional Relationship (ULFR). At the machine learning section, a novel four-layers data mining filtering pre-processes for selected supervised classification as well as unsupervised clustering algorithms to increase the accuracy and to remove unrelated attributes and data are applied. For the four kinds of preprocessing approaches of unsupervised attributes, supervised attributes, supervised instances, and unsupervised instances, we have chosen discretization, attribute selection, stratified remove folds, and resample filters respectively. Based on the nature of the suggested financial institution's dataset and attributes, the most appropriate preprocessing filter in each layer to achieve the highest performance is suggested. Finally, the superior bank, best performance model, and the most accurate algorithm are introduced. The results indicate that the bank number 56 is the superior bank. Among the proposed techniques, the novel recommended CVS compared with CCR-BCC and SFA models, has a more positive correlation with profit risk, and show a higher coefficient of determination values. Sequential Minimal Optimization(SMO) algorithm receives the highest accuracy in all four suggested filtering layers.

Sign in / Sign up

Export Citation Format

Share Document