https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/15312 2026-03-25T19:56:33Z https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/32426 Title: Critical voxel learning with vision transformer and derivation of logical AV safety assessment scenarios Authors: Kang, Minhee; Seo, Jungwook; Hwang, Keeyeon; Yoon, Young Abstract: Safety assessment is an active research subject for autonomous vehicles (AVs) that have emerged as a new mode of mobility. In particular, scenario-based safety assessments have garnered significant attention. AVs can be tested on how they safely avoid hypothetical situations leading to accidents. However, scenarios written by humans based on their expert knowledge and experience may only partially reflect real-world situations. Instead, we are keen on a different technique of extracting statistically significant and more detailed scenarios from sensor data captured during the critical moments when AVs become vulnerable to potential accidents. Specifically, we first render the three-dimensional space around an AV with fixed-sized voxels. Then, we modeled the aggregate kinetics of the objects in each voxel detected by 3D-LiDAR sensors mounted on real test AVs. The Vision Transformer we used to model the kinetics helped us quickly pinpoint critical voxels containing objects that threatened the AV's safety. We traced the trajectory of the critical voxels on a visual attention map to describe in detail how AVs become vulnerable to accidents according to the logical scenario format defined by the PEGASUS Project. We tested our novel method with 250 h of 3D-LiDAR recordings capturing critical moments. We devised an inference model that detected critical situations with an F1-score of 98.26%. For each type of scenario, our model consistently identified the critical objects and their tendency to influence AVs. Given the evaluation results, we can ensure that our data-driven approach yields an AV safety assessment scenario with high representativeness, coverage, expansion, and computational feasibility. © 2023 Elsevier Ltd 2024-02-01T00:00:00Z https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/32411 Title: ENN: Hierarchical Image Classification Ensemble Neural Network for Large-Scale Automated Detection of Potential Design Infringement Authors: Lee, Chan Jae; Jeong, Seong Ho; Yoon, Young Abstract: This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. This work proposes an ensemble neural network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. First, we performed image classification and objection detection learning per design right using acclaimed existing models with high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiplies the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was performed an order of magnitude faster than the single model. The ENN maintained a high level of accuracy as it was scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as customs at the border that deal with a swarm of products. 2023-11-01T00:00:00Z https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/32102 Title: EQuaTE: Efficient Quantum Train Engine for Run-Time Dynamic Analysis and Visual Feedback in Autonomous Driving Authors: Park, Soohyun; Feng, Hao; Park, Chanyoung; Lee, Youn Kyu; Jung, Soyi; Kim, Joongheon Abstract: This article proposes an efficient quantum train engine (EQuaTE), a novel development tool for quantum neural network (QNN) autonomous driving software which plots gradient variances to confirm whether the QNN falls into local minima situations (called <italic>barren plateaus</italic>). Based on this run-time visualization, the stability and feasibility of QNN-based software can be tested during run-time operations of autonomous driving functionalities. This software testing of QNN via dynamic analysis is essentially required due to undetermined probabilistic qubit states during run-time operations. Furthermore, the EQuaTE is capable for visual feedback because the barren plateaus can be identified at local autonomous driving platforms and the corresponding information will be visualized at remotely-connected cloud. Based on this visualized information at the cloud, the QNN which is also stored at cloud should be automatically re-organized and re-trained for eliminating barren plateaus. Then, the trained parameters can be downloaded into the QNN of autonomous driving platforms. IEEE 2023-09-01T00:00:00Z https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/25271 Title: 이종 사물인터넷 센서와 딥러닝에 기반한 독거노인 원격 모니터링 시스템의 개발 및 운영 사례 연구 Authors: 윤영; 김현민; 이시우; 사파 시아바시 푸리 Abstract: 본 논문은 독거노인의 복합적 행태를 이종 사물인터넷 센서들과 딥러닝 기법을 활용하여 인지하고 낙상, 잦은 기침, 수면의 질 감소, 발열 및 비정상적 생활 동선의 발생 등 위급하거나 건강이 저하되는 상황을 적시에 보호자 및 의료복지 담당자에게 알리고 적정한 후속 서비스를 추천 및 수행할 수 있는 시스템을 논한다. 독거노인들의 생활을 최대한 방해하지 않기 위하여 전면 비접촉식 상황 인식 기술을 선보인다. 본 논문은 센서 데이터의 수집 및 분석 체계의 설계와 구현 방법은 물론, 서울시 총 5개구 거주 독거노인들을 대상으로 실증한 경험을 통해 설치, 설정, 운영 및 유지 보수 측면에서의 다양한 문제점들을 서술하고 해당 시스템의 전국 확산에 대비한 향후 발전 방향을 제언한다. 2022-01-01T00:00:00Z