Search

In the quest to streamline Korean text and speech annotation, this research introduces innovative automatic annotation methods that promise to revolutionize efficiency and technical prowess in constructing Korean annotation datasets. By leveraging the sophisticated Seq2Seq architecture with BERT and bidirectional GRU models, we significantly enhance the model’s ability to grasp contextual nuances, ensuring precise text annotations. The speech annotation frontier benefits from a novel amalgamation of the Hidden Markov Model’s forced alignment and semi-supervised learning, perfected with Seneff auditory features for meticulous phonological consonant boundary detection. Empirical validation across diverse datasets showcases our methodology’s superiority, achieving a remarkable 96.01% accuracy in text annotation and setting a new benchmark for phonological boundary detection at a 14.5ms minimum distance threshold. Our approach outperforms traditional algorithms, marking a pivotal step forward in Korean automatic annotation.

In recent years, the increase in the number of vehicles on the road has impacted the service life of bridges, and thus, their performance. In China, bridge inspections must be performed and documented at least once per year using labor-intensive and subjective approaches. In this study, a computationally efficient damage identification methodology for bridges was developed based on a deep convolutional generative adversarial network (DCGAN). To predict the damage to bridges, the vibration data of the structural damage are extracted from sensor measurements on the bridges and applied to the DCGAN model. The proposed damage identification method was validated on a simple supported beam bridge and a continuous girder bridge. The effects of sample size and noise on the identification accuracy were also evaluated. The performance of the DCGAN in the damage identification process is robust and reliable. This method for structural health monitoring offers a more objective evaluation of the overall performance and condition of a bridge, thus enabling bridge owners to efficiently allocate finite maintenance resources. [ABSTRACT FROM AUTHOR]

Forest stand mean height is a critical indicator in forestry, playing a pivotal role in various aspects such as forest inventory estimation, sustainable forest management practices, climate change mitigation strategies, monitoring of forest structure changes, and wildlife habitat assessment. However, there is currently a lack of large-scale, spatially continuous forest stand mean height maps. This is primarily due to the requirement of accurate measurement of individual tree height in each forest plot, a task that cannot be effectively achieved by existing globally covered, discrete footprint-based satellite platforms. To address this gap, this study was conducted using over 1117 km2 of close-range Light Detection and Ranging (LiDAR) data, which enables the measurement of individual tree height in forest plots with high precision. Besides, this study incorporated spatially continuous climatic, edaphic, topographic, vegetative, and Synthetic Aperture Radar data as explanatory variables to map the tree-based arithmetic mean height (ha) and weighted mean height (hw) at 30 m resolution across China. Due to limitations in obtaining basal area of individual tree within plots using UAV LiDAR data, this study calculated weighted mean height through weighting an individual tree height by the square of its height. In addition, to overcome the potential influence of different vegetation divisions at large spatial scale, we also developed a machine learning-based mixed-effects model to map forest stand mean height across China. The results showed that the average ha and hw across China were 11.3 m and 13.3 m with standard deviations of 2.9 m and 3.3 m, respectively. The accuracy of mapped products was validated utilizing LiDAR and field measurement data. The correlation coefficient (푟) for ha and hw ranged from 0.603 to 0.906 and 0.634 to 0.889, while RMSE ranged from 2.6 to 4.1 m and 2.9 to 4.3 m, respectively. Comparing with existing forest canopy height maps derived using the area-based approach, it was found that our products of ha and hw performed better and aligned more closely with the natural definition of tree height. The methods and maps presented in this study provide a solid foundation for estimating carbon storage, monitoring changes in forest structure, managing forest inventory, and assessing wildlife habitat availability. The dataset constructed for this study is publicly available at https://doi.org/10.5281/zenodo.12697784 (Chen et al., 2024). [ABSTRACT FROM AUTHOR]

With the rise of artificial magnetism and metamaterials, toroidal resonance has gained much attention for its special properties. In this paper, we propose a novel hybrid graphene-metal metamolecule consisting of a square bracket-like resonator and two asymmetric U-shaped resonators. By applying various Fermi energies to graphene, the amplitude of electromagnetically induced transparency (EIT) can be efficiently manipulated, and the maximum amplitude modulation depth can attain 81% in the microwave region. Numerical simulations and theoretical analysis demonstrate that the dynamic manipulation is mainly induced by the active tuning toroidal resonance through the recombination effect of the conductive graphene. Also, the maximum group delay of 85 ps can be attained and controlled with the increasing Fermi energy. The proposed hybrid graphene-metal metamolecule and dynamically manipulating mode presents a novel modulating strategy of EIT-like analog based on the toroidal response, which has great application for the design of efficient tunable resonators, filters, and sensors. [ABSTRACT FROM AUTHOR]

A high-resolution, spatially explicit forest age map is essential for quantifying forest carbon stocks and carbon sequestration potential. Prior attempts to estimate forest age on a national scale in China have been limited by sparse resolution and incomplete coverage of forest ecosystems, attributed to complex species composition, extensive forest areas, insufficient field measurements, and inadequate methods. To address these challenges, we developed a framework that combines machine learning algorithms (MLAs) and remote sensing time series analysis for estimating the age of China's forests. Initially, we identify and develop the optimal MLAs for forest age estimation across various vegetation divisions based on forest height, climate, terrain, soil, and forest-age field measurements, utilizing these MLAs to ascertain forest age information. Subsequently, we apply the LandTrendr time series analysis to detect forest disturbances from 1985 to 2020, with the time since the last disturbance serving as a proxy for forest age. Ultimately, the forest age data derived from LandTrendr are integrated with the result of MLAs to produce the 2020 forest age map of China. Validation against independent field plots yielded an R2 ranging from 0.51 to 0.63. On a national scale, the average forest age is 56.1 years (standard deviation of 32.7 years). The Qinghai–Tibet Plateau alpine vegetation zone possesses the oldest forest with an average of 138.0 years, whereas the forest in the warm temperate deciduous-broadleaf forest vegetation zone averages only 28.5 years. This 30 m-resolution forest age map offers crucial insights for comprehensively understanding the ecological benefits of China's forests and to sustainably manage China's forest resources. The map is available at 10.5281/zenodo.8354262 (Cheng et al., 2023a). [ABSTRACT FROM AUTHOR]

Summary: Aiming to the problems of high circulating current and low efficiency caused by the traditional strategy of dual active bridge (DAB) converter under light load, in this paper, simple graphical optimization method (GSO) is proposed to improve the efficiency of dual active bridge converter. Through the contour plot of transmission power and current stress, optimal efficiency point can be obtained by tangent of contour map under condition of constant power, and heavily calculation or complex iterations of existing conventional control strategies are avoided. Moreover, analysis of proposed graphical current stress optimization is addressed, and controller design of proposed method is given and described. Efficiency comparison between traditional modulation strategy and GSO is given to show the advantage of proposed mothed. An experimental prototype is built to verify the analysis. [ABSTRACT FROM AUTHOR]

In order to address the issue of keeping the converter operating at a high efficiency level under different conditions, this paper suggests an adaptive step frequency adjustment online optimization search algorithm, which achieves the goal of fast adjustment and real‐time response to parameter changes. The converter is quickly adjusted to operate at a high efficiency by sampling the input and output current values and modulating the switching frequency utilizing the algorithm. Additionally, the algorithm shifts between two working models to finish the search for the best switching frequency while the converter's characteristics do not change. Moreover, it accomplishes the objective of instantly resynchronizing the algorithm after a change in the converter's parameters and starting a search for the best switching frequency in the new converter state. For various input voltages and output loads, the operating principle, optimal frequency, and efficiency are given. In addition, the principle analysis when the converter parameters are changed is provided, and the choice of two algorithm models is compared. Finally, a prototype buck converter with adjustable input voltage and load is constructed to test the algorithm's efficiency. [ABSTRACT FROM AUTHOR]

Tissue biopsy can be wildly used in cancer diagnosis. However, manually classifying the cancerous status of biopsies and tissue origin of tumors for cancerous ones requires skilled specialists and sophisticated equipment. As a result, a data-based model is urgently needed. In this paper, we propose a data-based ensemble model for tumor type identification and cancer origins classification. Our model is an ensemble model that combines different models based on mRNA groups which serve distinct functions. The experiment on the TCGA dataset exhibits a promising result on both tasks - 98% on tumor type identification and 96.1% on cancer origin classification. We also test our model on external validation datasets, which prove the robustness of our model.