López Gonzales, Javier Linkolk

Nombre preferido

Afiliación principal

Facultad de Ingeniería y Arquitectura

ORCID

0000-0003-0847-0552

ID de autor de Scopus

57216856857

ID de investigador

JHU-7967-2023

Mostrando 1 - 10 de 67

Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
¿Qué tan válidas y confiables son las interpretaciones derivadas del Florida Patient Acceptance Survey en español?
(2019-03-27)
Carranza Esteban, Renzo Felipe
;
López Gonzales, Javier Linkolk
;
Caycho‐Rodríguez, Tomás
que define la validez como el grado en que, tanto la evidencia como la teora, apoyan las interpretaciones
Citas (OpenAlex): 0metric-badges.view 4
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
A new class of median estimators using auxiliary information under PPS sampling: theoretical properties and empirical evaluation
(2026-03-19)
Shah, Salman
;
Mahmoudi, Eisa
;
Qureshi, Moiz
;
Iftikhar, Hasnain
;
Rodrigues, Paulo Canas
The use of auxiliary or supplementary information plays a crucial role in enhancing the efficiency of estimators in survey sampling. Among various measures of central tendency, the median has attracted considerable attention due to its robustness against outliers and skewed distributions. This study introduces a novel estimator for the finite population median that incorporates supplementary information under a probability proportional to size (PPS) sampling design. Analytical expressions for the bias and mean squared error (MSE) of the proposed estimator are derived up to the first order of approximation. The efficiency of the proposed estimator is evaluated through theoretical comparisons and empirical analyses against existing median estimators, using MSE and percent relative efficiency (PRE) as performance criteria. Furthermore, graphical representations are employed to illustrate the comparative performance. The proposed estimator is examined using three real-world datasets, and its precision is further validated through a comprehensive simulation study. The findings consistently demonstrate that the proposed estimator outperforms its existing counterparts in terms of efficiency and robustness.
Citas (OpenAlex): 2metric-badges.view 3
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
A Flat-Hierarchical Approach Based on Machine Learning Model for e-Commerce Product Classification
(2024-01-01)
Cotacallapa, Harold
;
Saboya Rios, Nemias
;
Canas Rodrigues, Paulo
;
Salas, Rodrigo
;
López Gonzales, Javier Linkolk
Within the e-commerce sphere, optimizing the product classification process assumes pivotal importance, owing to its direct influence on operational efficiency and profitability. In this context, employing machine learning algorithms stands out as a premier solution for effectively automating this process. The design of these models commonly adopts either a flat or local (hierarchical) approach. However, each of them exhibits significant limitations. The regional approach introduces taxonomic inconsistencies in predictions, whereas the flat approach becomes inefficient when dealing with extensive datasets featuring high granularity. Therefore, our research introduces a solution for hierarchical product classification based on a Machine Learning model that integrates flat and local (hierarchical) classification approaches using a 4-level electronic product dataset obtained from a renowned e-commerce platform in Latin America. In pursuit of this goal, a comparative analysis of seven machine learning algorithms, including Multinomial Naive Bayes, Linear Support Vector Classifier, Multinomial Logistic Regression, Random Forest, XGBoost, FastText, and Voting Ensemble, was conducted. This hybrid approach model performs better than models using a single approach. It surpassed the top-performing flat approach model by 0.15% and outperformed the leading local approach (Local Classifier per Level) model by 4.88%, as measured by the weighted F1-score. Additionally, this paper contributes to the academic community by presenting a significant Spanish-language dataset comprising over one million products and discussing the preprocessing techniques tailored for the dataset. It also addresses the study’s inherent limitations and potential avenues for future exploration in this field.
Citas (OpenAlex): 7metric-badges.view 10
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Multiple Novel Decomposition Techniques for Time Series Forecasting: Application to Monthly Forecasting of Electricity Consumption in Pakistan
(2023-03-09)
Iftikhar, Hasnain
;
Bibi, Nadeela
;
Canas Rodrigues, Paulo
;
López Gonzales, Javier Linkolk
In today’s modern world, monthly forecasts of electricity consumption are vital in planning the generation and distribution of energy utilities. However, the properties of these time series are so complex that they are difficult to model directly. Thus, this study provides a comprehensive analysis of forecasting monthly electricity consumption by comparing several decomposition techniques followed by various time series models. To this end, first, we decompose the electricity consumption time series into three new subseries: the long-term trend series, the seasonal series, and the stochastic series, using the three different proposed decomposition methods. Second, to forecast each subseries with various popular time series models, all their possible combinations are considered. Finally, the forecast results of each subseries are summed up to obtain the final forecast results. The proposed modeling and forecasting framework is applied to data on Pakistan’s monthly electricity consumption from January 1990 to June 2020. The one-month-ahead out-of-sample forecast results (descriptive, statistical test, and graphical analysis) for the considered data suggest that the proposed methodology gives a highly accurate and efficient gain. It is also shown that the proposed decomposition methods outperform the benchmark ones and increase the performance of final model forecasts. In addition, the final forecasting models produce the lowest mean error, performing significantly better than those reported in the literature. Finally, we believe that the framework proposed for modeling and forecasting can also be used to solve other forecasting problems in the real world that have similar features.
Citas (OpenAlex): 47metric-badges.view 6
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Teaching vocation as a key dimension of teacher education in Peru: evidence from the CVOC-D scale
(2026-03-26)
Vera-Mendoza, Edwin Michel
;
Gonzales Medina, Ronny Ivan
;
Orrego Granados, David Leandro
;
Tocto Cano, Esteban
;
López Gonzales, Javier Linkolk
This study aimed to examine the psychometric properties of the Teaching Vocation Scale (CVOC-D), designed to assess teaching vocation within the Peruvian educational context, where no specific instruments currently exist. Using an instrumental design and quantitative approach, data were collected from 319 teachers. Reliability and validity analyses indicated satisfactory results, with an overall reliability of ω = 0.869 and acceptable coefficients for the three identified dimensions: vocational awareness (0.805), satisfaction with teaching (0.807), and commitment to education (0.642). An exploratory factor analysis explained 42.6% of the variance, while confirmatory factor analysis demonstrated a moderately adequate model fit (χ 2 = 5123.53, p < 0.001; CFI = 0.824; TLI = 0.796; RMSEA = 0.097). Although three items were eliminated, the final version of the scale retained strong psychometric properties. The findings confirmed that the CVOC-D is a valid and reliable instrument for measuring teaching vocation, aligned with the cultural and professional characteristics of Peruvian teachers. This tool represents a significant contribution to psychological assessment in education, providing a robust basis for future research and practical applications in teacher training and professional development.
Citas (OpenAlex): 0metric-badges.view 5
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
A hybrid AI approach for predicting academic performance in RBE students
(2025-10-21)
Gonzales, Willy
;
Cordero, Zindel
;
Abanto Ramirez, Carlos Daniel
;
Susanibar Ramírez, Edgar Tito
;
Iftikhar, Hasnain
Machine learning has advanced significantly in recent years and is being used in higher education to perform various types of data analysis. While the literature demonstrates the application of machine learning algorithms to predict performance in university education, no such applications are found in EBR, let alone in private institutions of a denominational nature, which presents an opportunity to study prediction in these institutions. To address this gap, this research aims to propose a predictive approach as a decision-support tool for regular basic education, using machine learning techniques. Among the techniques utilized, three machine learning models (Logistic Regression, Support Vector Machine, and Random Forest), along with deep learning models (AlexNet, Gated Recurrent Unit, and Bidirectional Gated Recurrent Unit), were analyzed, as well as ensemble models. Nonetheless, the Ensemble model, which combines deep learning and machine learning techniques, is preferred due to its superior accuracy, precision, and sensitivity performance metrics.
Citas (OpenAlex): 7metric-badges.view 3
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Global Shocks and Local Fragilities: A Financial Stress Index Approach to Pakistan’s Monetary and Asset Market Dynamics
(2025-08-19)
Yousfani, Kinza
;
Iftikhar, Hasnain
;
Rodrigues, Paulo Canas
;
Torres Armas, Elías A.
;
López Gonzales, Javier Linkolk
Economic stability in emerging market economies is increasingly shaped by the interplay between global financial integration, domestic monetary dynamics, and asset price fluctuations. Yet, early detection of financial market disruptions remains a persistent challenge. This study constructs a Financial Stress Index (FSI) for Pakistan, utilizing monthly data from 2005 to 2024, to capture systemic stress in a globalized context. Using Principal Component Analysis (PCA), the FSI consolidates diverse indicators, including banking sector fragility, exchange market pressure, stock market volatility, money market spread, external debt exposure, and trade finance conditions, into a single, interpretable measure of financial instability. The index is externally validated through comparisons with the U.S. STLFSI4, the Global Economic Policy Uncertainty (EPU) Index, the Geopolitical Risk (GPR) Index, and the OECD Composite Leading Indicator (CLI). The results confirm that Pakistan’s FSI responds meaningfully to both global and domestic shocks. It successfully captures major stress episodes, including the 2008 global financial crisis, the COVID-19 pandemic, and politically driven local disruptions. A key understanding is the index’s ability to distinguish between sudden global contagion and gradually emerging domestic vulnerabilities. Empirical results show that banking sector risk, followed by trade finance constraints and exchange rate volatility, are the leading contributors to systemic stress. Granger causality analysis reveals that financial stress has a significant impact on macroeconomic performance, particularly in terms of GDP growth and trade flows. These findings emphasize the importance of monitoring sector-specific vulnerabilities in an open economy like Pakistan. The FSI offers strong potential as an early warning system to support policy design and strengthen economic resilience. Future modifications may include incorporating real-time market-based metrics indicators to better align the index with global stress patterns.
Citas (OpenAlex): 3metric-badges.view 2
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Air Quality Prediction Based on Singular Spectrum Analysis and Artificial Neural Networks
(2024-12-06)
López Gonzales, Javier Linkolk
;
Salas, Rodrigo
;
Velandia, Daira
;
Canas Rodrigues, Paulo
Singular spectrum analysis is a powerful nonparametric technique used to decompose the original time series into a set of components that can be interpreted as trend, seasonal, and noise. For their part, neural networks are a family of information-processing techniques capable of approximating highly nonlinear functions. This study proposes to improve the precision in the prediction of air quality. For this purpose, a hybrid adaptation is considered. It is based on an integration of the singular spectrum analysis and the recurrent neural network long short-term memory; the SSA is applied to the original time series to split signal and noise, which are then predicted separately and added together to obtain the final forecasts. This hybrid method provided better performance when compared with other methods.
Citas (OpenAlex): 6metric-badges.view 3
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Sex differences in social network addiction and emotional eating among adolescents in a Peruvian region: a cross-sectional analysis
(2024-10-25)
Saintila, Jacksaint
;
Soriano Moreno, Anderson Nelver Elías
;
Basauri-Delgado, Miguel
;
Carranza-Cubas, Sandra P.
;
López Gonzales, Javier Linkolk
Maladaptive eating behaviors are becoming increasingly prevalent among adolescents, and their relationship to exposure to media messages has been extensively examined. However, more specifically, the influence of social networks on emotional eating (EmE) has received relatively less attention in the Peruvian context. To determine the association between social network addiction (SNA) and EmE among Peruvian adolescents, considering sex differences. A cross-sectional study was conducted. A total of 878 adolescents were considered. The Social Network Addiction Questionnaire and the Emotional Eating Questionnaire were administered. Similarly, sociodemographic data were collected. To explore the association between SNA and EmE, we performed Poisson regression analyses with robust variance. We considered a p-value of equal to or less than 0.05 as statistically significant. Adolescents with an EmE score greater than 5 had significantly higher SNA scores, averaging 24.7 (± 12.3), compared to 15.5 (± 10.3) in those with an EmE score between 0 and 5 (p < 0.001). In multiple regression analyses, men with moderate/severe SNA were 1.77 times more likely to have EmE compared to those without SNA (95% CI 1.45–2.15; p < 0.001), while in women, moderate/severe SNA was associated with a 1.98 times higher likelihood of EmE (95% CI 1.61–2.45; p < 0.001). These findings highlight the need for public health interventions to educate adolescents about the use of social networks to minimize the negative effects of prolonged exposure on eating habits. Many teenagers are developing unhealthy eating habits, and researchers have studied how media influences this. However, the effect of social media on emotional eating (eating in response to emotions) in Peru has received less attention. This study explored the link between social media addiction and emotional eating among Peruvian teenagers, focusing on differences between boys and girls. We studied 878 teenagers using two questionnaires: one about social media addiction and one about emotional eating. We also collected basic background information. A statistical analysis called Poisson regression was used to see how likely emotional eating is in teenagers with high social media use. Results showed that teenagers with higher emotional eating scores also had higher social media addiction scores. Boys with moderate or severe social media addiction were 1.77 times more likely to have emotional eating behaviors, while girls were 1.98 times more likely. These results highlight the need for programs to teach teenagers about the healthy use of social media to reduce its negative impact on eating habits.
Citas (OpenAlex): 4metric-badges.view 10
Publicacion
Algunas métricas están bloqueadas por su
configuración de consentimiento
Modeling and Analysis of Monkeypox Outbreak Using a New Time Series Ensemble Technique
(2024-08-14)
Meza Cuba, Wilfredo
;
Huaman Alfaro, Juan Carlos
;
Iftikhar, Hasnain
;
López Gonzales, Javier Linkolk
The coronavirus pandemic has raised concerns about the emergence of other viral infections, such as monkeypox, which has become a significant hazard to public health. Thus, this work proposes a novel time series ensemble technique for analyzing and forecasting the spread of monkeypox in the four highly infected countries with the monkeypox virus. This approach involved processing the first cumulative confirmed case time series to address variance stabilization, normalization, stationarity, and a nonlinear secular trend component. After that, five single time series models and three proposed ensemble models are used to estimate the filtered confirmed case time series. The accuracy of the models is evaluated using typical accuracy mean errors, graphical evaluation, and an equal forecasting accuracy statistical test. Based on the results, it is found that the proposed time series ensemble forecasting approach is an efficient and accurate way to forecast the cumulative confirmed cases for the top four countries in the world and the entire world. Using the best ensemble model, a forecast is made for the next 28 days (four weeks), which will help understand the spread of the disease and the associated risks. This information can prevent further spread and enable timely and effective treatment. Furthermore, the developed novel time series ensemble approach can be used to forecast other diseases in the future.
Citas (OpenAlex): 38metric-badges.view 6

López Gonzales, Javier Linkolk

Filtros

Ajustes

Ordenar por

resultados por página