Flor de Luz Palomino Valdivia

Prof. Flor de Luz Palomino Valdivia


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Herwin HuillcenHerwin Huillcen
Herwin Huillcen
Flor de Luz Palomino ValdiviaFlor de Luz Palomino Valdivia
Flor de Luz Palomino Valdivia
JCJuan Carlos Gutiérrez Cáceres
Juan Carlos Gutiérrez Cáceres
Human violence recognition is an area of great interest in the scientific community due to its broad spectrum of applications, especially in video surveillance systems, because detecting violence in real time can prevent criminal acts and save lives. The majority of existing proposals and studies focus on result precision, neglecting efficiency and practical implementations. Thus, in this work, we propose a model that is effective and efficient in recognizing human violence in real time. The proposed model consists of three modules: the Spatial Motion Extractor (SME) module, which extracts regions of interest from a frame; the Short Temporal Extractor (STE) module, which extracts temporal characteristics of rapid movements; and the Global Temporal Extractor (GTE) module, which is responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated for its efficiency, effectiveness, and ability to operate in real time. The results obtained on the Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to various alternatives. In addition, the VioPeru dataset was created, which contains violent and non-violent videos captured by real video surveillance cameras in Peru, to validate the real-time applicability of the model. When tested on this dataset, the effectiveness of our model was superior to the best existing models.

23 August 2025 in Sensors
Verified
Journal Article
Open access
PDF file
Herwin HuillcenHerwin Huillcen
Herwin Huillcen
Flor de Luz Palomino ValdiviaFlor de Luz Palomino Valdivia
Flor de Luz Palomino Valdivia
According to the World Health Organization, cardiovascular diseases, including cardiac arrhythmias, are the leading cause of death worldwide due to their silent, asymptomatic nature. To address this problem, early and accurate diagnosis is crucial. Although this task is typically performed by a cardiologist, diagnosing arrhythmias can be imprecise due to the subjectivity of reading and interpreting electrocardiograms (ECGs), and electrocardiograms are often subject to noise and interference. Deep learning-based approaches present methods for automatically detecting arrhythmias and are positioned as an alternative to support cardiologists’ diagnoses. However, these methods are trained and tested only on open datasets of electrocardiograms from Holter devices, whose results aim to improve the accuracy of the state of the art, neglecting the efficiency of the model and its application in a practical clinical context. In this work, we propose an efficient model based on a 1D CNN architecture to detect arrhythmias from smartwatch ECGs, for subsequent deployment in a practical scenario for the monitoring and early detection of arrhythmias. Two datasets were used: UMass Medical School Simband for a binary arrhythmia detection model to evaluate its efficiency and effectiveness, and the MIT-BIH arrhythmia database to validate the multiclass model and compare it with state-of-the-art models. The results of the binary model achieved an accuracy of 64.81%, a sensitivity of 89.47%, and a specificity of 6.25%, demonstrating the model’s reliability, especially in specificity. Furthermore, the computational complexity was 1.2 million parameters and 68.48 MFlops, demonstrating the efficiency of the model. Finally, the results of the multiclass model achieved an accuracy of 99.57%, a sensitivity of 99.57%, and a specificity of 99.47%, making it one of the best state-of-the-art proposals and also reconfirming the reliability of the model.

2 March 2023
Verified
Book Chapter
Closed access
PDF file
Herwin HuillcenHerwin Huillcen
Herwin Huillcen
Flor de Luz Palomino ValdiviaFlor de Luz Palomino Valdivia
Flor de Luz Palomino Valdivia
ISIvan Soria Solis
Ivan Soria Solis
ACAquino Cruz Aquino Cruz
Aquino Cruz Aquino Cruz
JCJuan Carlos Gutiérrez Cáceres
Juan Carlos Gutiérrez Cáceres



9 September 2025 in Sensors
Verified
Journal Article
Open access
PDF file
Flor de Luz Palomino ValdiviaFlor de Luz Palomino Valdivia
Flor de Luz Palomino Valdivia
Herwin HuillcenHerwin Huillcen
Herwin Huillcen
Multivariate time series analysis presents significant challenges due to its dynamism, heterogeneity, and scalability. Given this, preprocessing is considered a crucial step to ensure analytical quality. However, this phase falls solely on the user without system support, resulting in wasted time, subjective decision-making, and cognitive overload, and is prone to errors that affect the quality of the results. This situation reflects the lack of interactive visual analysis approaches that effectively integrate preprocessing with guidance mechanisms. The main objective of this work was to design and develop a guidance system for interactive visual analysis in multivariate time series preprocessing, allowing users to understand, evaluate, and adapt their decisions in this critical phase of the analytical workflow. To this end, we propose a new guide-based approach that incorporates recommendations, explainability, and interactive visualization. This approach is embodied in the GUIAVisWeb tool, which organizes a workflow through tasks, subtasks, and preprocessing algorithms; recommends appropriate components through consensus validation and predictive evaluation; and explains the justification for each recommendation through visual representations. The proposal was evaluated in two dimensions: (i) quality of the guidance, with an average score of 6.19 on the Likert scale (1–7), and (ii) explainability of the algorithm recommendations, with an average score of 5.56 on the Likert scale (1–6). In addition, a case study was developed with air quality data that demonstrated the functionality of the tool and its ability to support more informed, transparent, and effective preprocessing decisions.