• Geomechanics and Engineering
• /
• v.38 no.3
• /
• pp.285-305
• /
• 2024

This study investigates the behaviour of hunchback retaining walls supporting unsaturated sandy backfill under active earth pressure conditions. Utilizing a horizontal slice method and a unified effective stress methodology, the influence of various factors on lateral earth pressure, including the position of the hunch along the wall, friction angles, and wall heights, is explored. The results suggest that relocating the hunch position from close to the wall's top to near its base leads to a significant decrease (ranging from 54% to 81%) in lateral earth pressure. However, as the hunch position transitions from near the top to mid-height, the point of application of active thrust shifts upward initially, then slightly downward as the hunch position approaches the toe. Notably, the reduction in lateral earth pressure is more pronounced for shorter wall heights and higher friction angles. Building upon these findings, an Artificial Neural Network (ANN)-based model is developed to accurately predict the lateral earth pressure coefficient and point of application, achieving R² values of 0.94 and 0.93, respectively. In addition, an analytical model based on Coulomb's earth pressure theory is presented and compared with ANN models. These models are anticipated to assist designers and practitioners in optimizing hunchback retaining walls for unsaturated backfill.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2564-2588
• /
• 2024

Due to COVID19 pandemic, most of educational institutions and schools changed the traditional way of teaching to online teaching and learning using well-known Learning Management Systems (LMS) such as Moodle, Canvas, Blackboard, etc. Accordingly, LMS started to generate a large data related to students' characteristics and achievements and other course-related information. This makes it difficult to teachers to monitor students' behaviour and performance. Therefore, a need to support teachers with a tool alerting student who might be in risk based on their recorded activities and achievements in adopted LMS in the school. This paper focuses on the benefits of using recorded data in LMS platforms, specifically Moodle, to predict students' performance by analysing their behavioural data and engagement activities using data mining techniques. As part of the overall process, this study encountered the task of extracting and selecting relevant data features for predicting performance, along with designing the framework and choosing appropriate machine learning techniques. The collected data underwent pre-processing operations to remove random partitions, empty values, duplicates, and code the data. Different machine learning techniques, including k-NN, TREE, Ensembled Tree, SVM, and MLPNNs were applied to the processed data. The results showed that the MLPNNs technique outperformed other classification techniques, achieving a classification accuracy of 93%, while SVM and k-NN achieved 90% and 87% respectively. This indicates the possibility for future research to investigate incorporating other neural network methods for categorizing students using data from LMS.

• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.203-208
• /
• 2024

The identification and classification of victims in the county border area is one of the important issues. The personnel that can appear in the military border area are comprised of North Korean soldiers, U.S. soldiers, South Korean soldiers, and the general public, and are currently being confirmed through CCTV. They were classified into true categories and learned through transfer learning. The PyTorch machine learning library was used, and the dataset was utilized by crawling images corresponding to each item shared on Google. The experimental results show that each item is classified with an accuracy of 98.7500%. Future research will explore ways to distinguish more systematically and specifically by going beyond images and adding video or voice recognition.

• Journal of Astronomy and Space Sciences
• /
• v.41 no.3
• /
• pp.149-158
• /
• 2024

This study developed a machine learning-based methodology to classify gravitational wave (GW) signals from black hol-eneutron star (BH-NS) mergers by combining convolutional neural network (CNN) with conditional information for feature extraction. The model was trained and validated on a dataset of simulated GW signals injected to Gaussian noise to mimic real world signals. We considered all three types of merger: binary black hole (BBH), binary neutron star (BNS) and neutron starblack hole (NSBH). We achieved up to 96% correct classification of GW signals sources. Incorporating our novel conditional information approach improved classification accuracy by 10% compared to standard time series training. Additionally, to show the effectiveness of our method, we tested the model with real GW data from the Gravitational Wave Transient Catalog (GWTC-3) and successfully classified ~90% of signals. These results are an important step towards low-latency real-time GW detection.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.57 no.4
• /
• pp.479-488
• /
• 2024

In recent years, changes in the fishing ground environment have led to reduced catches by fishermen at traditional fishing spots and increased operational costs related to vessel exploration, fuel, and labor. In this study, we developed a deep learning model to classify the fishing activities of drift gillnet fishing boats using AIS (automatic identification system) trajectory data. The proposed model integrates long short-term memory and 1-dimensional convolutional neural network layers to effectively distinguish between fishing (throwing and hauling) and non-fishing operations. Training on a dataset derived from AIS and validation against a subset of CCTV footage, the model achieved high accuracy, with a classification accuracy of 90% for fishing events. These results show that the model can be used effectively to monitor and manage fishing activities in coastal waters in real time.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.148-158
• /
• 2024

We investigate Autism Spectrum Disorder (ASD), which is typified by deficits in social interaction, repetitive behaviors, limited vocabulary, and cognitive delays. Traditional diagnostic methodologies, reliant on expert evaluations, frequently result in deferred detection and intervention, particularly in South Korea, where there is a dearth of qualified professionals and limited public awareness. In this study, we employ advanced deep learning algorithms to enhance early ASD screening through automated video analysis. Utilizing architectures such as Convolutional Long Short-Term Memory (ConvLSTM), Long-term Recurrent Convolutional Network (LRCN), and Convolutional Neural Networks with Gated Recurrent Units (CNN+GRU), we analyze video data from platforms like YouTube and TikTok to identify stereotypic behaviors (arm flapping, head banging, spinning). Our results indicate that the LRCN model exhibited superior performance with 79.61% accuracy on the augmented platform video dataset and 79.37% on the original SSBD dataset. The ConvLSTM and CNN+GRU models also achieved higher accuracy than the original SSBD dataset. Through this research, we underscore AI's potential in early ASD detection by automating the identification of stereotypic behaviors, thereby enabling timely intervention. We also emphasize the significance of utilizing expanded datasets from social media platform videos in augmenting model accuracy and robustness, thus paving the way for more accessible diagnostic methods.

• Wind and Structures
• /
• v.37 no.5
• /
• pp.383-397
• /
• 2023

In the Structural Health Monitoring (SHM) system of civil engineering, data missing inevitably occurs during the data acquisition and transmission process, which brings great difficulties to data analysis and poses challenges to structural health monitoring. In this paper, Convolution Neural Network (CNN) is used to recover the nonstationary wind speed data missing randomly at sampling points. Given the technical constraints and financial implications, field monitoring data samples are often insufficient to train a deep learning model for the task at hand. Thus, simulation combined transfer learning strategy is proposed to address issues of overfitting and instability of the deep learning model caused by the paucity of training samples. According to a portion of target data samples, a substantial quantity of simulated data consistent with the characteristics of target data can be obtained by nonstationary wind-field simulation and are subsequently deployed for training an auxiliary CNN model. Afterwards, parameters of the pretrained auxiliary model are transferred to the target model as initial parameters, greatly enhancing training efficiency for the target task. Simulation synergy strategy effectively promotes the accuracy and stability of the target model to a great extent. Finally, the structural dynamic response analysis verifies the efficiency of the simulation synergy strategy.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.313-323
• /
• 2024

Deterioration of buildings is one of the biggest problems in modern society, and the importance of a safety diagnosis for old buildings is increasing. Therefore, most countries have legal maintenance and safety diagnosis regulations. However, the reliability of the existing safety diagnostic processes is reduced because they involve subjective judgments in the data collection. In addition, unstructured tasks increase rework rates, which are time-consuming and not cost-effective. Therefore, This paper proposed the method that can calculate the safety grade of deterioration automatically. For this, a DNN structure is generated by using existing precision inspection data and precision safety diagnostic data, and an objective building safety grade is calculated by applying status evaluation data obtained with a UAV, a laser scanner, and reverse engineering 3D models. This automated process is applied to 20 old buildings, taking about 40% less time than needed for a safety diagnosis from the existing manual operation based on the same building area. Subsequently, this study compares the resulting value for the safety grade with the already existing value to verify the accuracy of the grade calculation process, constructing the DNN with high accuracy at about 90%. This is expected to improve the reliability of aging buildings in the future, saving money and time compared to existing technologies, improving economic efficiency.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3925-3932
• /
• 2024

During outages at nuclear power plants, much more care for radiation workers against internal exposure should be ensured given that more hot particles exist relative to the amount during normal operation. If fuel-type hot particles (FTHP) are inhaled, they can cause more severe health risks compared to activation-type hot particles (ATHP), which contain ⁶⁰Co, due to the alpha-emitting nuclides within FTHPs. The activities of difficult-to-measure nuclides within FTHPs inhaled by workers are inferred by the age-dating technique using a¹⁴¹Ce/¹⁴⁴Ce ratio as measured by whole-body counters. However, this method may be limited to outages that last for only a few months due to the short half-life (32.5 days) of ¹⁴¹Ce. We studied the feasibility of utilizing ²⁴¹Am, a nuclide with a long half-life of 432.6 years, as an alternative to ¹⁴¹Ce. Additionally, we improved the performance of a stand-type whole-body counter for low-energy gamma spectroscopy to meet the criterion (RMSE ≤0.25) specified in ANSI/HPS N13.30-2011 by employing an artificial neural network (ANN). This study can contribute to more rapid and accurate internal dose assessments for workers who have inhaled FTHPs during long-term outages at nuclear power plants.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.87-94
• /
• 2024

Children with speech sound disorders (SSDs) face various challenges in producing speech sounds, which often lead to significant social and educational barriers. Detecting and treating SSDs in children is complex due to the variability in disorder severity and diagnostic boundaries. This study aims to develop an automated SSD detection system using deep learning models, leveraging their ability to transcribe audio, efficiently capture sound patterns on a vast scale, and address the limitations of traditional methods involving speech-language pathologists. For this study, we collected audio recordings from 573 children aged two to nine using standardized prompts from the Assessment of Phonology and Articulation for Children. Speech-language pathologists analyzed the recordings and identified 92 children with SSDs. To build an automatic SSD detection system, we used a dataset to train neural network models for automatic speech recognition and audio classification. Five different methods are studied, with the best method achieving 73.9% unweighted average recall. While the results show the potential of using deep learning models for the automatic detection of SSDs in children, further research is needed to improve the reliability of the models widely used in practice.