CRIS

Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1

Browse

Search Results

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Addressing Class Imbalance in Healthcare Data: Machine Learning Solutions for Age-Related Macular Degeneration and Preeclampsia
(IEEE, 2024)
;
;
Miralles-Pechuán, Luis
The use of machine learning in healthcare has transformed the way diseases are diagnosed and treatments are optimized. However, medical databases often lack balanced data due to challenges in data collection caused by privacy regulations. Certain health conditions are underrepresented, which hampers machine learning performance. To address this problem, a hybrid approach has been proposed that combines the Synthetic Minority Oversampling Technique (SMOTE) with undersampling and uses two specific techniques tailored for imbalanced datasets. Comparative evaluations were conducted using various thresholds to reduce one class and employing Balanced Accuracy to mitigate bias toward the majority class, with popular machine learning methods. The results showed that Balanced Bagging and Balanced Random Forest consistently outperformed other methods, performing the best with an average ranking of 1.42 and 3.58 out of 32 configurations in the two datasets, respectively. Tree-based approaches such as Random Forest and Gradient Boosting demonstrated similar effectiveness, emphasizing the power of aggregating predictions from multiple trees to reduce bias. Notably, undersampling and SMOTE proved advantageous for non-tree-based models like KNN, SVM, and Logistic Regression showcasing their usefulness across different algorithms. This study provides a robust solution for handling imbalanced datasets in healthcare, which could potentially optimize healthcare interventions and improve patient outcomes and care©IEEE Latin America Transactions, The authors
Scopus© Citations 1 11
Some of the metrics are blocked by your
consent settings
Comparative Analysis of Artificial Hydrocarbon Networks and Data-Driven Approaches for Human Activity Recognition
(2015)
;
;
Miralles-Pechuán, Luis
In recent years computing and sensing technologies advances contribute to develop effective human activity recognition systems. In context-aware and ambient assistive living applications, classification of body postures and movements, aids in the development of health systems that improve the quality of life of the disabled and the elderly. In this paper we describe a comparative analysis of data-driven activity recognition techniques against a novel supervised learning technique called artificial hydrocarbon networks (AHN). We prove that artificial hydrocarbon networks are suitable for efficient body postures and movements classification, providing a comparison between its performance and other well-known supervised learning methods.
Scopus© Citations 5 14 1
Some of the metrics are blocked by your
consent settings
Artificial Hydrocarbon Networks for Online Sales Prediction
(2015)
;
Miralles-Pechuán, Luis
;
Online retail sales have been growing worldwide in the last decade. In order to cope with this high dynamicity and market share competition, online retail sales prediction and online advertising have become very important to answer questions of pricing decisions, advertising responsiveness, and product demand. To make adequate investment in products and channels it is necessary to have a model that relates certain features of the product with the number of sales that will occur in the future. In this paper we describe a comparative analysis of machine learning techniques against a novel supervised learning technique called artificial hydrocarbon networks (AHN). This method is a new type of machine learning that have proved to adapt very well to a wide spectrum of problems of regression and classification. Thus, we use artificial hydrocarbon networks for predicting the number of online sales, and then we compare their performance with other ten well-known methods of machine learning regression, obtaining promising results.
Scopus© Citations 9 14 1
Some of the metrics are blocked by your
consent settings
Interoperability in Electronic Health Records Through the Mediation of Ubiquitous User Model
(2016)
;
Miralles-Pechuán, Luis
;
González-Mendoza, Miguel
Martínez Villaseñor, M. de L., Miralles Pechuan, L. J. y González Mendoza, M. (2016). Interoperability in electronic health records through the mediation of ubiquitous user model. En: En: García, C, Caballero Gil, P., Burmester, M. y Quesada Arencibia, A. (editores), Ubiquitous Computing and Ambient Intelligence : 10th International Conference, UCAmI 2016, San Bartolomé de Tirajana, Gran Canaria, Spain, November 29 - December 2, 2016 (vol. 1), (pp. 190-200). Cham : Springer International Publishing. DOI: 10.1007/978-3-319-48746-5_19
Scopus© Citations 6 16 2
Some of the metrics are blocked by your
consent settings
Feature Selection Methods Evaluation for CTR Estimation
(2016)
Miralles-Pechuán, Luis
;
;
The most widespread payment model in online advertising is Cost-per-click (CPC). In this model the advertisers pay each time that a user generates a click. In order to enhance the income of CPC Advertising Networks, it is necessary to give priority to the most profitable adverts. The most important factor in the profitability of an advert is Click-through-rate (CTR), which is the probability that a user generates a click in a given advert. In this paper we find which feature selection method between PCA, RFE, Gain ratio and NSGA-II is better suited, or if otherwise, the machine learning classification methods work best without any feature selection method. ©2016 IEE
Scopus© Citations 1 19 6
Some of the metrics are blocked by your
consent settings
A Novel Wearable Sensor-Based Human Activity Recognition Approach Using Artificial Hydrocarbon Networks
(2016)
;
;
Miralles-Pechuán, Luis
Human activity recognition has gained more interest in several research communities given that understanding user activities and behavior helps to deliver proactive and personalized services. There are many examples of health systems improved by human activity recognition. Nevertheless, the human activity recognition classification process is not an easy task. Different types of noise in wearable sensors data frequently hamper the human activity recognition classification process. In order to develop a successful activity recognition system, it is necessary to use stable and robust machine learning techniques capable of dealing with noisy data. In this paper, we presented the artificial hydrocarbon networks (AHN) technique to the human activity recognition community. Our artificial hydrocarbon networks novel approach is suitable for physical activity recognition, noise tolerance of corrupted data sensors and robust in terms of different issues on data sensors. We proved that the AHN classifier is very competitive for physical activity recognition and is very robust in comparison with other well-known machine learning methods.
Scopus© Citations 56 7 1
Some of the metrics are blocked by your
consent settings
A Flexible Approach for Human Activity Recognition Using Artificial Hydrocarbon Networks
(2016)
;
Miralles-Pechuán, Luis
;
Physical activity recognition based on sensors is a growing area of interest given the great advances in wearable sensors. Applications in various domains are taking advantage of the ease of obtaining data to monitor personal activities and behavior in order to deliver proactive and personalized services. Although many activity recognition systems have been developed for more than two decades, there are still open issues to be tackled with new techniques. We address in this paper one of the main challenges of human activity recognition: Flexibility. Our goal in this work is to present artificial hydrocarbon networks as a novel flexible approach in a human activity recognition system. In order to evaluate the performance of artificial hydrocarbon networks based classifier, experimentation was designed for user-independent, and also for user-dependent case scenarios. Our results demonstrate that artificial hydrocarbon networks classifier is flexible enough to be used when building a human activity recognition system with either user-dependent or user-independent approaches.
Scopus© Citations 35 9 1
Some of the metrics are blocked by your
consent settings
A methodology based on Deep Learning for advert value calculation in CPM, CPC and CPA networks
(2016)
Miralles-Pechuán, Luis
;
Rosso, Dafne
;
Jiménez, Fernando
;
García, Jose M.
In this research, we propose a methodology for advert value calculation in CPM, CPC and CPA networks. Accurately estimating this value increases the three previous networks’ incomes by selecting the most profitable advert. By increasing income, publishers are better paid and improved services are afforded to advertisers. To develop this methodology, we propose a system based on traditional Machine Learning methods and Deep Learning methods. The system has two inputs and one output. The inputs are the user visit and the data about the advertiser. The output is the advert value expressed in dollars. Deep Learning predicts model behavior more precisely for many supervised problems. The three experiments carried out allow us to conclude that DL is a supervised method that is very efficient in the classification of spam adverts and in the estimation of the CTR. In the prediction of online sales, DLNN have shown, on average, worse performance than cubist and random forest methods, although better performance than model tree, model rules and linear regression methods.
Scopus© Citations 21 6 1
Some of the metrics are blocked by your
consent settings
Multi-objective evolutionary feature selection for online sales forecasting
(2017)
Jiménez, Fernando
;
Sánchez, Gracia
;
García, José M.
;
Sciavicco, Guido
;
Miralles-Pechuán, Luis
Sales forecasting uses historical sales figures, in association with products characteristics and peculiarities, to predict short-term or long-term future performance in a business, and it can be used to derive sound financial and business plans. By using publicly available data, we build an accurate regression model for online sales forecasting obtained via a novel feature selection methodology composed by the application of the multi-objective evolutionary algorithm ENORA (Evolutionary NOn-dominated Radial slots based Algorithm) as search strategy in a wrapper method driven by the well-known regression model learner Random Forest. Our proposal integrates feature selection for regression, model evaluation, and decision making, in order to choose the most satisfactory model according to an a posteriori process in a multi-objective context. We test and compare the performances of ENORA as multi-objective evolutionary search strategy against a standard multi-objective evolutionary search strategy such as NSGA-II (Non-dominated Sorted Genetic Algorithm), against a classical backward search strategy such as RFE (Recursive Feature Elimination), and against the original data set.
Scopus© Citations 98 47 2
Some of the metrics are blocked by your
consent settings
Human Activity Recognition on Mobile Devices Using Artificial Hydrocarbon Networks
(2018)
;
Miralles-Pechuán, Luis
;
González Mora, José Guillermo
;
Human activity recognition (HAR) aims to classify and identify activities based on data-driven from different devices, such as sensors or cameras. Particularly, mobile devices have been used for this recognition task. However, versatility of users, location of smartphones, battery, processing and storage limitations, among other issues have been identified. In that sense, this paper presents a human activity recognition system based on artificial hydrocarbon networks. This technique have been proved to be very effective on HAR systems using wearable sensors, so the present work proposes to use this learning method with the information provided by the in-sensors of mobile devices. Preliminary results proved that artificial hydrocarbon networks might be used as an alternative for human activity recognition on mobile devices. In addition, a real dataset created for this work has been published. © Springer Nature Switzerland AG 2018.
7 2

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results