José Lara Arce

Mr. José Lara Arce

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
1 August 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
Broderick CrawfordBroderick Crawford
Broderick Crawford
FCFelipe Cisternas-Caneo
Felipe Cisternas-Caneo
Ricardo SotoRicardo Soto
Ricardo Soto
CMClaudio Patricio Toledo Mac-lean
Claudio Patricio Toledo Mac-lean
JAJosé Lara Arce
José Lara Arce
GGGiovanni Giachetti
Giovanni Giachetti
The Set Coverage Problem (SCP) is an important combinatorial optimization problem known to be NP-complete. The use of metaheuristics to solve the SCP includes different algorithms. In particular, binarization techniques have been explored to adapt metaheuristics designed for continuous optimization problems to the binary domain of the SCP. In this work, we present a new approach to solve the SCP based on the Secretary Bird Optimization Algorithm (SBOA). This algorithm is inspired by the natural behavior of the secretary bird, known for its ability to hunt prey and evade predators in its environment. Since the SBOA was originally designed for optimization problems in continuous space and the SCP is a binary problem, this paper proposes the implementation of several binarization techniques to adapt the algorithm to the discrete domain. These techniques include eight transfer functions and five different discretization methods. Taken together, these combinations create multiple SBOA adaptations that effectively balance exploration and exploitation, promoting an adequate distribution in the search space. Experimental results applied to the SCP together with its variant Unicost SCP and compared to Grey Wolf Optimizer and Particle Swarm Optimization suggest that the binary version of SBOA is a robust algorithm capable of producing high quality solutions with low computational cost. Given the promising results obtained, it is proposed as future work to focus on complex and large-scale problems as well as to optimize their performance in terms of time and accuracy.

25 December 2025 in Biomimetics
Verified
Journal Article
Open access
PDF file
Broderick CrawfordBroderick Crawford
Broderick Crawford
Alex Patricio Paz BecerraAlex Patricio Paz Becerra
Alex Patricio Paz Becerra
Ricardo SotoRicardo Soto
Ricardo Soto
AFAlvaro Peña Fritz
Alvaro Peña Fritz
GAGino Astorga
Gino Astorga
GGGiovanni Giachetti
Giovanni Giachetti
Metaheuristics are a fundament pillar of Industry 4.0, as they allow for complex optimization problems to be solved by finding good solutions in a reasonable amount of computational time. One category of important problems in modern industry is that of binary problems, where decision variables can take values of zero or one. In this work, we propose a binary version of the Pufferfish optimization algorithm (BPOA), which was originally created to solve continuous problems. The binary mapping follows a two-step technique, first transforming using transfer functions and then discretizing using binarization rules. We study representative pairings of transfer functions and binarization rules, comparing our algorithm with Particle Swarm Optimization, Secretary Bird Optimization Algorithm, and Arithmetic Optimization Algorithm with identical computational budgets. To validate its correct functioning, we solved binary problems present in industry, such as the Set Covering Problem together with its Unicost variant, as well as the Knapsack Problem. The results we achieved with regard to these problems were promising and statistically validated. The tests performed on the executions indicate that many pair differences are not statistically significant when both methods are already close to the optimal level, and significance arises precisely where the descriptive gaps widen, underscoring that transfer–rule pairing is the main performance factor. BPOA is a competitive and flexible framework whose effectiveness is mainly governed by the discretization design.

3 March 2026 in Biomimetics
Verified
Journal Article
Open access
PDF file
MRMarcelo Orlando Becerra Rozas
Marcelo Orlando Becerra Rozas
BGBady Gana
Bady Gana
JAJosé Lara Arce
José Lara Arce
ALAndrés Leiva-Araos
Andrés Leiva-Araos
Broderick CrawfordBroderick Crawford
Broderick Crawford
MGMiguel García-Remesal
Miguel García-Remesal
Optimal surgical scheduling necessitates a strategic balance between elective efficiency and responsiveness to stochastic emergency arrivals. This study evaluates a Genetic Algorithm alongside discretized variants of Particle Swarm Optimization, the Secretary Bird Optimization Algorithm, and the Mantis Shrimp Optimization Algorithm. These algorithms are assessed within a dynamic three-stage flexible flow shop model under no-buffer blocking constraints. Findings from 300 Monte Carlo replications demonstrate that while the Genetic Algorithm achieves peak global efficiency, discretized bio-inspired algorithms reach a comparable statistical efficiency frontier. Notably, the discretized Secretary Bird Optimization Algorithm facilitates superior emergency integration by maintaining natural capacity buffers, whereas the aggressive local optimization characteristic of alternative methods often triggers resource saturation in recovery units. These results indicate a potential recovery of 90 annual operating hours per theater.These results indicate a potential recovery of 90 annual operating hours per theater, representing a 6.7% increase in resource utilization efficiency. This improvement provides a critical data-driven capacity margin to mitigate the non-prioritized (Non-GES) surgical backlog in Chilean public hospitals.

17 February 2026
Verified
Book Chapter
Closed access
JAJosé Lara Arce
José Lara Arce
JSJavier Sepúlveda
Javier Sepúlveda
RSRicardo Santana
Ricardo Santana
MRMarcelo Orlando Becerra Rozas
Marcelo Orlando Becerra Rozas
BGBady Gana
Bady Gana
DVDaniel Villalobos
Daniel Villalobos

3 November 2026 in Biomimetics
Verified
Journal Article
Open access
PDF file
JAJosé Lara Arce
José Lara Arce
MRMarcelo Orlando Becerra Rozas
Marcelo Orlando Becerra Rozas
BGBady Gana
Bady Gana
Broderick CrawfordBroderick Crawford
Broderick Crawford
PAPablo Aguilera
Pablo Aguilera
JGJosé Gómez-Pulido
José Gómez-Pulido
Elective surgical scheduling allocates operating rooms and specialized personnel under operational constraints, yet most metaheuristic evaluations rely on synthetic benchmarks. We study a two-stage flexible flow shop with independently assigned rooms for anesthesia preparation and surgery, calibrated with 23,865 valid records from a Chilean public hospital, and compare four population-based, bio-inspired methods: a Genetic Algorithm, discrete Particle Swarm Optimization, the Secretary Bird Optimization Algorithm, and a discrete Mantis Shrimp Optimization Algorithm. Across four 15–30-surgery instances and 400 replications, the particle swarm method achieves the lowest mean makespan among the metaheuristics for 20–30 surgeries, whereas the Secretary Bird Optimization Algorithm roughly halves the number of patients incurring inter-stage waiting relative to that method (p<0.001) and produces zero-wait schedules in some replications. Deterministic dispatching rules remain competitive or better for expected benchmark throughput, although the particle swarm method finds the shortest best-case schedule for 30 surgeries. A retrospective replay of 120 historical elective operating days reproduces the throughput–waiting trade-off. Relative to the realized manual calendar span, the particle swarm method yields a median simulated makespan difference of 15.2% (median absolute difference: 86.3 min per day). The replay evaluates scheduling with realized procedure durations, daily room counts, and the fixed configured staff pool, providing a retrospective comparison across historical workloads.

11 April 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
JPJosé Arcángel Villamayor Peralta
José Arcángel Villamayor Peralta
JAJosé Lara Arce
José Lara Arce
CPCarlos Parra
Carlos Parra
EVEmanuel Vega
Emanuel Vega
PRPablo Duque Ramirez
Pablo Duque Ramirez
MRMarcelo Orlando Becerra Rozas
Marcelo Orlando Becerra Rozas
The inspection of welded joints is a critical process in industrial environments where structural integrity and safety must be ensured. Traditional liquid penetrant testing is effective but can be limited by subjective visual assessment, variability across inspectors, and human error. This work presents an automated inspection pipeline that integrates liquid penetrant testing with artificial intelligence and computer vision. The proposed approach employs convolutional neural networks to analyze weld images and classify five surface conditions/discontinuity types, aligned with standards such as American Society for Testing and Materials E165/E165M and International Organization for Standardization 3452. Model selection is performed on a development set via stratified 10-fold cross-validation with fixed, reproducible folds, and the final evaluation is reported on a held-out test set. Performance is quantified using accuracy, precision, recall, and F1-score, and interpretability is supported via Grad-CAM++ visual explanations. Under this protocol, the proposed convolutional network achieves the best overall cross-validation performance among the evaluated deep and shallow baselines.