은닉시설 파악을 위한 PDR(Pedestrian Dead Reckoning) 기반 실내 구조 도면 생성 알고리즘 연구
Research on Pedestrian Dead Reckoning (PDR)-based indoor structural drawing generation algorithm for hiding place identification
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근, 국내에서 특정 목적을 달성하거나 금전적인 이익을 위해 사람을 강제로건물에 감금하는 납치 사건이 증가하고 있다. 납치의 대상은 어린아이부터건장한 성인 남성까지, 다양한 연령대와 배경을 갖는 사람들이 범죄의 대상으로지목되고 있다. 감금된 사람의 건물 구조 파악이 어려울 경우 피해자를 찾거나구조하는 것이 어려워지며, 구조 작업이나 구출 시도 시 피해자의 안전과 생명이위협을 받을 수 있다. 따라서, 본 논문에서는 PDR(Pedestrian Dead Reckoning)을 활용하여 건물의 구조를 파악하고 도면을 생성하는 프로세스를제안할 것이다. 또한, 부족한 센서 데이터를 보완하기 위해 GAN(Generative Adversarial Networks)을 활용하여 데이터를 생성하였으며, 도면 생성알고리즘을 사용하여 실제 건물과 86.7% 유사한 도면을 획득하였다.
Abstract
Recently, the crime of kidnapping, in which a person is forcibly confined in a building to fulfill a specific purpose or gain financial gain, has been increasing. Due to the difficulty in identifying the structure of the building in which they are confined, it is difficult to locate and rescue the victims. Therefore, in this paper, we propose a process to collect location information using pedestrian death counting (PDR) to generate drawings. A generative adversarial neural network (GAN) was used to generate data for drawing the drawings, and drawings that are 82% similar to the actual building were obtained using the proposed process
참고문헌 (25)
- A. R. Jimenez, "A comparison of pedestrian dead-reckoni ng algorithms using a low-cost MEMS IMU", Proc. IEEE Int. Symp. Intell. Signal Process, pp.37~42 (2009)
- W. Kang, "SmartPDR : Smartphone-based pedestrian dead reckoning for indoor localization", IEEE Sensors J, 15, pp.2906~2916 (2015)
- J. Kuang, "Robust pedestrian dead reckoning based on MEMS-IMU for smartphones", Sensors, 18(5), pp.1391~ (2018)
- N. -H. Ho, "Step-detection and adaptive step-length estimation for pedestrian dead-reckoning at various walking speeds using a smartphone", Sensors, 16(9), pp.1423~ (2016)
- Fourier Transform, "Fast Fourier transforms : A tutorial review and a state of the art", Signal Process, 19(4), pp.259~299 (1990)
- H. Zhao, "Pedestrian dead reckoning using pocket-worn smartphone", IEEE Access, 7, pp.91063~91073 (2019)
- R. Mohammed, "Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results", 2020 11th Internation al Conference on Information and Communication Systems (ICICS), pp.243~248 (2020)
- A. Estabrooks, "A multiple resampling method for learning from imbalanced data sets", Comput. Intell, 20(1), pp.18~36 (2004)
- N. V. Chawla, "Smote : Synthetic minority over-sampling technique", J. Artif. Intell. Res, 16, pp.321~357 (2002)
- H. He, "ADASYN: Adaptive synthetic sampling approach for imbalanced learning", Proc. IEEE Int. Joint Conf. Neural Netw. (IEEE World Congr. Comput. Intelligence), pp.1322~1328 (2008)
- A. Yadav, "Stabilizing adversarial nets with prediction methods", Proc. Int. Conf. Learn. Representations, pp.1~21 (2018)
- "Do CIFAR-10 classifiers generalize to CIFAR-10?" (2018)[URL]
- F. Pedregosa, "Scikit-learn : Machine learning in python", J. Mach. Learn. Res, 12, pp.2825~2830 (2011)
- X. Yi, "Sharpness-aware low-dose CT denoising using conditional generative adversarial network", J. Digit. Imag, 31(5), pp.655~669 (2018)
- W. Xu, "Improved bidirectional GAN-based approach for network intrusion detection using one-class classifier", Computers, 11(6), pp.85~ (2022)
- NSL-KDD, "A study on NSL-KDD dataset for intrusion detection system based on classification algorithms", Int. J. Adv. Res. Comput. Commun. Eng, 4(6), pp.446~452 (2015)
- CIC-DDos2019, "Investigation on Efficient Machine Learning Algorithm for DDoS Attack Detection", 2023 International Conference on Computer, Electrical & Communication Engineering (ICCECE), pp.1~5 (2023), IEEE
- Y. Zhang, "Generating text via adversarial training", Proc. Conf. Neural Inf. Process. Syst. Workshop Adv. Training, pp.1~6 (2016)
- BookCorpus dataset, "Aligning books and movies: Towards story-like visual explanations by watching movies and reading books", Proc. IEEE Int. Conf. Comput. Vis, pp.19~27 (2015)
- L. Yu, "SeqGAN: Sequence generative adversarial nets with policy gradient", Proc. AAAI Conf. Artifi. Intell, pp.2852~2858 (2017)
- Nottingham Dataset, "Releasing a cleaned version of the Nottingha m Dataset", Web blog post, ~ (2018)
- C. Willmott, "Advantages of the mean absolute error(MAE)over the root mean square error(RMSE)in assessing average model performance", Climate Res, 30(1), pp.79~82 (2005)
- Sparse autoencoder, "A. Ng", Standford Univ, ~, pp.Lecture Notes CS294A (2011)