Digital Library[ Search Result ]
Detecting CCTV Traffic Accidents and Automating Emergency Rescue Based on Deep Learning
Changhoon Park, Jihyeon Kim, Inhee Cho, Sunho Jang, Kihag Kwon
http://doi.org/10.5626/JOK.2024.51.12.1061
This paper presents a novel approach to real-time detection of traffic accidents using CCTV footage and provision of immediate information about nearby hospitals. By ensemble Densenet121 and YOLOv8 models, the proposed system effectively identified the occurrence and type of traffic accidents. Based on accident location, the system searched for the nearest available emergency rooms and confirmed their capacity in real time. This enabled a prompt delivery of accident details and hospital information to the user, addressing issues of delayed reporting and inefficient allocation of emergency room resources. This approach aims to reduce initial response time during traffic accidents, thereby maximizing the efficiency of emergency medical services and ultimately minimizing accident-related harm. Specifically, Densenet121's deep neural network architecture effectively classified accident scenes in the footage, while YOLOv8's object detection algorithm identified accident types in real-time.
Semi-Supervised Object Detection for Small Imbalanced Drama Dataset
http://doi.org/10.5626/JOK.2024.51.11.978
Images of the theme of a drama are typically zoomed-in mainly to people. As a result, people-oriented images are predominant in drama data, and class imbalance naturally occurs. This paper addresses the issue of class imbalance in drama data for object detection tasks and proposes various sampling methods to tackle this challenge within the framework of semi-supervised learning. Experimental evaluations demonstrated that the suggested semi-supervised learning approach with specialized sampling methods outperformed traditional supervised and semi-supervised methods. This study underscores the significance of selecting appropriate training data and sampling methods to optimize object detection performance in specialized datasets with unique characteristics.
Analysis of Vulnerabilities in Autonomous Driving Environments through Physical Adversarial Attacks Incorporating Natural Elements
Kyuchan Cho, Woosang Im, Sooyong Jeong, Hyunil Kim, Changho Seo
http://doi.org/10.5626/JOK.2024.51.10.935
Advancements in artificial intelligence technology have significantly impacted the field of computer vision. Concurrently, numerous vulnerabilities related to adversarial attacks, which are techniques designed to force models into misclassification, have been discovered. In particular, adversarial attacks such as physical adversarial attacks in the real world, pose a serious threat to autonomous vehicle systems. These attacks include artificially created attacks such as adversarial patches and attacks that exploit natural elements to cause misclassification. A common scenario in autonomous driving environments involves obstruction of traffic signs by natural elements such as fallen leaves or snow. These elements do not remain stationary. They can cause misclassification even in fleeting moments, highlighting a critical vulnerability. Therefore, this study investigated adversarial patch attacks based on natural elements, proposing fallen leaves as a natural adversarial element. Specifically, it reviewed current trends in adversarial attack research, presented an experimental environment based on natural elements, and analyzed experimental results to assess vulnerabilities posed by fallen leaves in physical environments to autonomous vehicles.
A Study on Sales Prediction Model Based on BiLSTM-GAT Using Credit Card Transaction Data
Wonseok Jung, Dohyung Kim, Young Ik Eom
http://doi.org/10.5626/JOK.2024.51.9.807
Sales prediction using credit card transaction data is essential for understanding consumer buying patterns and market trends. However, traditional statistical and machine learning models have limitations when it comes to analyzing temporal features and the relationships between different variables, such as geographical data and sales information by service types, population, and transaction times. This paper proposes two models that can simultaneously analyze the relationships based on commercial district features and sales time-series features. To evaluate the performance of these models, we constructed graphs based on the distances and sales similarity of features between commercial districts. We then compared the performance of the proposed models with traditional time-series models, namely LSTM and BiLSTM. The results of the experiment showed that the GAT-BiLSTM model improved prediction accuracy by approximately 15% compared to the BiLSTM model, while the BiLSTM-GAT model improved it by about 29% over the BiLSTM model, as measured by RMSE.
Drug-Drug Interaction Prediction Model Based on Deep Learning Using Drug Information Document Embedding
http://doi.org/10.5626/JOK.2024.51.6.503
The use of polypharmacy has emerged as a promising approach for various diseases, including cancer, hypertension, and asthma. However, the use of polypharmacy can result in unexpected interactions, which may lead to adverse drug effects. Therefore, predicting drug-drug interactions (DDI) is essential for safe medication practices. In this study, we propose a drug-drug interaction prediction model based on deep learning using document embedding to represent the drug. We generate documents about drug information by combining DrugBank data, which includes drug descriptions, indications, mechanisms of action, pharmacodynamics, and toxicity. Then we use Doc2Vec and BioSentVec language models to generate drug representation vectors from the drug information documents. The two drug vectors are paired and input into the deep learning-based prediction model, which outputs the likelihood of interaction between the two drugs. Our goal is to construct the optimal model for predicting drug-drug interactions by comparing the performance under various conditions, including language embedding model performance and adjustments for data imbalance. We expect the proposed model to be utilized for the advanced prediction of drug interactions during the drug prescription process and the clinical stages of new drug development.
Prediction of Cancer Prognosis Using Patient-Specific Cancer Driver Gene Information
http://doi.org/10.5626/JOK.2024.51.6.574
Accurate prediction of cancer prognosis is crucial for effective treatment. Consequently, numerous studies on cancer prognosis have been conducted, with recent research leveraging various machine learning techniques such as deep learning. In this paper, we first constructed patient-specific gene networks for each patient, then selected patient-specific cancer driver genes, considering the heterogeneity of cancer. We propose a deep neural architecture that can predict the prognosis more accurately using patient-specific cancer driver gene information. When our method was applied to gene expression data for 11 types of cancer, it demonstrated a significantly higher prediction accuracy compared to the existing methods.
Application of OOD Detection Using MSP in EEG-Based Emotion Classification
HyoSeon Choi, Dahoon Choi, Byung Hyung Kim
http://doi.org/10.5626/JOK.2024.51.5.438
Several deep learning approaches have recently improved the performance of emotion classification tasks. However, these successful applications cannot be directly applied to learning EEG signals because of their nonlinear and complex data structure. This limitation leads to inter- and intra-subject variability problems for understanding complex emotion dynamics. To address this limitation, we focus on studying the variability rather than extracting features from high-dimensional neural activities. In the context of deep learning, we propose a framework to detect and remove abnormal pairs of EEG data and labels for enhancing model performance by utilizing the Maximum Softmax Probability approach. Experimental results on public datasets demonstrated the superiority of our method with a maximum improvement of 4% in accuracy.
Graph Structure Learning-Based Neural Network for ETF Price Movement Prediction
Hyeonsoo Jo, Jin-gee Kim, Taehun Kim, Kijung Shin
http://doi.org/10.5626/JOK.2024.51.5.473
Exchange-Traded Funds (ETFs) are index funds that mirror particular market indices, usually associated with their low risk and expense ratio to individual investors. Various methods have emerged for accurately predicting ETF price movements, and recently, AI-based technologies have been developed. One representative method involves using time-series-based neural networks to predict the price movement of ETFs. This approach effectively incorporates past price information of ETFs, allowing the prediction of their movement. However, it has a limitation as it only utilizes historical information of individual ETFs and does not account for the relationships and interactions between different ETFs. To address this issue, we propose a model that can capture relationships between ETFs. The proposed model uses graph structure learning to infer a graph representing relationships between ETFs. Based on this, a graph neural network predicts the ETF price movement. The proposed model demonstrates superior performance compared to time-series-based deep-learning models that only use individual ETF information.
SASRec vs. BERT4Rec: Performance Analysis of Transformer-based Sequential Recommendation Models
Hye-young Kim, Mincheol Yoon, Jongwuk Lee
http://doi.org/10.5626/JOK.2024.51.4.352
Sequential recommender systems extract interests from user logs and use them to recommend items the user might like next. SASRec and BERT4Rec are widely used as representative sequential recommendation models. Existing studies have utilized these two models as baselines in various studies, but their performance is not consistent due to differences in experimental environments. This research compares and analyzes the performance of SASRec and BERT4Rec on six representative sequential recommendation datasets. The experimental result shows that the number of user-item interactions has the largest impact on BERT4Rec training, which in turn leads to the performance difference between the two models. Furthermore, this research finds that the two learning methods, which are widely utilized in sequential recommendation settings, can also have different effects depending on the popularity bias and sequence length. This shows that considering dataset characteristics is essential for improving recommendation performance.
Improved Recall of Plant Disease Detection Model using Image Super Resolution
Hyeonggyeong Kim, Chaesung Lim, Seungmin Tak
http://doi.org/10.5626/JOK.2024.51.2.125
Early identification and diagnosis of plant disease is very important because plant diseases have a great impact on yield. Currently, research on developing and advancing models for diagnosing plant diseases and pests using artificial intelligence is being actively conducted. However, even if the model showed good performance during verification, the performance deteriorates when the resolution of the input image is low during operation. If disease control is delayed because of delayed diseases diagnosis due to low resolution, the entire crop is affected by the diseases resulting in a decrease in yield. The purpose of this study was to improve the reproducibility of the model by utilizing super-resolution that increases the resolution of the image. BICUBIC, SRCNN, and SRGAN were used as super-resolution algorithms. After x4 scale super-resolution of test images with 64×64, 128×128, and 192×192 resolutions, they were directly input into the trained YOLOv5 model. As a result, the recall improved by 34% in SRGAN, 30% in SRCNN, and 19% in BICUBIC.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr