著者

宮原 彬

出版者

長崎大学

雑誌

長崎大学外国人留学生指導センター年報

巻号頁・発行日

vol.2, pp.55-70, 1994-03-25

著者

長山 格 宮原 彬 島袋 航一

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)

巻号頁・発行日

vol.139, no.9, pp.986-992, 2019

被引用文献数

3

---

<p>In this paper, we propose a new intelligent security camera system, that is named COMDES, for automated detection of snatching incidents on streets during the night by using LSTM network. Although over a half of all snatching incidents occur at night, this has not been considered in past studies. Thus, we have proposed an intelligent security camera system using a deep neural network and snapshot of a video frame to detect snatching incidents in the night by our previous paper. The COMDES can perform more efficient detection of snatching than our previous paper, by using sequential frames observed in the criminal scene and LSTM. It can classifies the situations into criminal or non-criminal scenes precisely. The experimental results show that the system, COMDES, can effectively detect snatching incidents with an accuracy of 98.89%.</p>

著者

長山 格 宮原 彬 島袋 航一

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌. D, 産業応用部門誌 (ISSN:09136339)

巻号頁・発行日

vol.139, no.2, pp.158-165, 2019

被引用文献数

2

---

<p>This paper proposes a new lazy learning algorithm, named balanced-kNN, for high performance robust classification of noisy patterns. K-nearest neighbor (k-NN) is a simple and powerful method with a high accuracy for various real world applications using unbiased datasets. However, noisy datasets are often gathered in real world applications. This paper presents a new robust algorithm, balanced-kNN, and compares the prediction accuracy with some conventional methods by using UCI datasets. The experimental results show that the balanced-kNN algorithm can perform more efficient classification of noisy data than the normal-kNN and weighted-kNN algorithms.</p>