Atkinson, J., & Escudero, A. (2022). Evolutionary natural-language coreference resolution for sentiment analysis. Int. J. Inf. Manage. Data Insights, 2(2), 100115.
Abstract: Communicating messages on social media usually conveys much implicit linguistic knowledge, which makes it difficult to process texts for further analysis. One of the major problems, the linguistic coreference resolution task involves detecting coreference chains of entities and pronouns that coreference them. It has mostly been addressed for formal and full-sized text in which a relatively clear discourse structure can be discovered, using Natural-Language Processing techniques. However, texts in social media are short, informal and lack a lot of underlying linguistic information to make decisions so traditional methods can not be applied. Furthermore, this may significantly impact the performance of several tasks on social media applications such as opinion mining, network analysis, sentiment analysis, text categorization. In order to deal with these issues, this research address the task of linguistic co-referencing using an evolutionary computation approach. It combines discourse coreference analysis techniques, domain-based heuristics (i.e., syntactic, semantic and world knowledge), graph representation methods, and evolutionary computation algorithms to resolving implicit co-referencing within informal opinion texts. Experiments were conducted to assess the ability of the model to find implicit referents on informal messages, showing the promise of our approach when compared to related methods.
|
Christie, D. A., E.K.H., Innes, H., Noti, P. A., Charnay, B., Fauchez, T. J., et al. (2022). CAMEMBERT: A Mini-Neptunes General Circulation Model Intercomparison, Protocol Version 1.0.A CUISINES Model Intercomparison Project. Planet. Sci., 3(11), 261.
Abstract: With an increased focus on the observing and modeling of mini-Neptunes, there comes a need to better understand the tools we use to model their atmospheres. In this Paper, we present the protocol for the Comparing Atmospheric Models of Extrasolar Mini-Neptunes Building and Envisioning Retrievals and Transits, CAMEMBERT, project, an intercomparison of general circulation models (GCMs) used by the exoplanetary science community to simulate the atmospheres of mini-Neptunes. We focus on two targets well studied both observationally and theoretically with planned JWST cycle 1 observations: the warm GJ 1214b and the cooler K2-18b. For each target, we consider a temperature-forced case, a clear sky dual-gray radiative transfer case, and a clear sky multiband radiative transfer case, covering a range of complexities and configurations where we know differences exist between GCMs in the literature. This Paper presents all the details necessary to participate in the intercomparison, with the intention of presenting the results in future papers. Currently, there are eight GCMs participating (ExoCAM, Exo-FMS, FMS PCM, Generic PCM, MITgcm, RM-GCM, THOR, and the Unified Model), and membership in the project remains open. Those interested in participating are invited to contact the authors.
|
Fernandez, C., Valle, C., Saravia, F., & Allende, H. (2012). Behavior analysis of neural network ensemble algorithm on a virtual machine cluster. Neural Comput. Appl., 21(3), 535–542.
Abstract: Ensemble learning has gained considerable attention in different learning tasks including regression, classification, and clustering problems. One of the drawbacks of the ensemble is the high computational cost of training stages. Resampling local negative correlation (RLNC) is a technique that combines two well-known methods to generate ensemble diversity-resampling and error negative correlation-and a fine-grain parallel approach that allows us to achieve a satisfactory balance between accuracy and efficiency. In this paper, we introduce a structure of the virtual machine aimed to test diverse selection strategies of parameters in neural ensemble designs, such as RLNC. We assess the parallel performance of this approach on a virtual machine cluster based on the full virtualization paradigm, using speedup and efficiency as performance metrics, for different numbers of processors and training data sizes.
|
Lardone, M. C., Busch, A. S., Santos, J. L., Miranda, P., Eyheramendy, S., Pereira, A., et al. (2020). A Polygenic Risk Score Suggests Shared Genetic Architecture of Voice Break With Early Markers of Pubertal Onset in Boys. J. Clin. Endocrinol. Metab., 105(3), E349–E357.
Abstract: Context: Voice break, as a landmark of advanced male puberty in genome-wide association studies (GWAS), has revealed that pubertal timing is a highly polygenic trait. Although voice break is easily recorded in large cohorts, it holds quite low precision as a marker of puberty. In contrast, gonadarche and pubarche are early and clinically well-defined measures of puberty onset. Objective: To determine whether a polygenic risk score (PRS) of alleles that confer risk for voice break associates with age at gonadarche (AAG) and age at pubarche (AAP) in Chilean boys. Experimental Design: Longitudinal study. Subjects and Methods: 401 boys from the Growth and Obesity Chilean Cohort Study (n = 1194; 49.2% boys). Main Outcome Measures: Biannual clinical pubertal staging including orchidometry. AAG and AAP were estimated by censoring methods. Genotyping was performed using the Multi-Ethnic Global Array (Illumina). Using GWAS summary statistics from the UK-Biobank, 29 significant and independent single nucleotide polymorphisms associated with age at voice break were extracted. Individual PRS were computed as the sum of risk alleles weighted by the effect size. Results: The PRS was associated with AAG (beta=0.01, P = 0.04) and AAP (beta=0.185, P = 0.0004). In addition, boys within the 20% highest PRS experienced gonadarche and pubarche 0.55 and 0.67 years later than those in the lowest 20%, respectively (P = 0.013 and P = 0.007). Conclusions: Genetic variants identified in large GWAS on age at VB significantly associate with age at testicular growth and pubic hair development, suggesting that these events share a genetic architecture across ethnically distinct populations.
|
Pinto, J., Aylwin, R., Silva-Oelker, G., & Jerez-Hanckes, C. (2021). Diffraction efficiency optimization for multilayered parametric holographic gratings. Opt. Lett., 46(16), 3929–3932.
Abstract: Multilayered diffraction gratings are an essential component in many optical devices due to their ability to engineer light. We propose a first-order optimization strategy to maximize diffraction efficiencies of such structures by a fast approximation of the underlying boundary integral equations for polarized electromagnetic fields. A parametric representation of the structure interfaces via trigonometric functions enables the problem to be set as a parametric optimization one while efficiently representing complex structures. Derivatives of the efficiencies with respect to geometrical parameters are computed using shape calculus, allowing a straightforward implementation of gradient descent methods. Examples of the proposed strategy in chirped pulse amplification show its efficacy in designing multilayered gratings to maximize their diffraction efficiency.
|
Pinto-Rios, J., Calderon, F., Leiva, A., Hermosilla, G., Beghelli, A., Borquez-Paredes, D., et al. (2023). Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach. Complexity, 2023, 4140594.
Abstract: A deep reinforcement learning (DRL) approach is applied, for the first time, to solve the routing, modulation, spectrum, and core allocation (RMSCA) problem in dynamic multicore fiber elastic optical networks (MCF-EONs). To do so, a new environment was designed and implemented to emulate the operation of MCF-EONs – taking into account the modulation format-dependent reach and intercore crosstalk (XT) – and four DRL agents were trained to solve the RMSCA problem. The blocking performance of the trained agents was compared through simulation to 3 baselines RMSCA heuristics. Results obtained for the NSFNet and COST239 network topologies under different traffic loads show that the best-performing agent achieves, on average, up to a four-times decrease in blocking probability with respect to the best-performing baseline heuristic method.
|
Sahlevani, S. F., Pandiyarajan, T., Arulraj, A., Valdes, H., Sanhueza, F., Contreras, D., et al. (2024). Tailored engineering of rod-shaped core@shell ZnO@CeO2 nanostructures as an optical stimuli-responsive in sunscreen cream. Mater. Today Commun., 38, 107959.
Abstract: The catalytic efficiency of the materials can be boosted with the selective designing (nanostructures) including the core@shell which aids in attaining the separation of photoinduced charge carriers. However, to effectively separate the carriers and reduce the rate of recombination, tuning the thickness of the shell wall is a vital one. The one-dimensional (1D) rod-like shell wall-controlled ZnO@CeO2 core@shell structures were successfully prepared via co-precipitation and hydrothermal methods using the hexamethylenetetramine (HMTA) as a reagent. The CeO2 shell wall thickness was fine-tuned between 15 and 70 nm with a variation in the concentration of HMTA reagent. The results revealed that the concentration of HMTA played a significant role in the formation of ZnO@CeO2 core@shell structures and in tuning their thickness. The FE-SEM images evidenced the core-shell structures formation with the specific thickness and uniformity. The HR-TEM images confirmed the homogeneity and regular form of the shell thickness. The unit cell and crystallite size were identified from the XRD analysis. The constructed core-shell structures were further employed in the formula of the prototypes of sunscreen and their photoprotective performance was analyzed in the view to cut the solar light irradiation in a new sunscreen formulation. The developed core-shell ZnO@CeO2 structures showed the excellent optical absorption in both the UV as well as visible regions.
|
