- 著者
- Yuhei Umeda
- 出版者
- The Japanese Society for Artificial Intelligence
- 雑誌
- 人工知能学会論文誌 (ISSN:13460714)
- 巻号頁・発行日
- vol.32, no.3, pp.D-G72_1-12, 2017-05-01 (Released:2017-05-01)
- 参考文献数
- 33
- 被引用文献数
- 55
This paper focuses on a classification problem for volatile time series. One of the most popular approaches for time series classification is dynamic time warping and feature-based machine learning architectures. In many previous studies, these algorithms have performed satisfactorily on various datasets. However, most of these methods are not suitable for chaotic time series because the superficial changes in measured values are not essential for chaotic time series. In general, most time series datasets include both chaotic and non-chaotic time series; thus, it is necessary to extract the more essential features of a time series. In this paper, we propose a new approach for volatile time series classification. Our approach generates a novel feature by extracting the structure of the attractor using topological data analysis to represent the transition rules of the time series. As this feature represents the essential property of systems of the time series, our approach is effective for both chaotic and non-chaotic types. We applied a learning architecture inspired by a convolutional neural network to this feature and found that the proposed approach improves performance in a human activity recognition problem by 18.5% compared with conventional approaches.
- 著者
- Koyo Kido Reiko Yamada Yuri Maegawa Takamitsu Tanaka Yuhei Umeda Yohei Ikenoyama Hiroki Yukimoto Akina Shigehuku Junya Tsuboi Misaki Nakamura Masaki Katsurahara Yasuhiko Hamada Kyosuke Tanaka Noriyuki Horiki Hayato Nakagawa
- 出版者
- The Japanese Society of Internal Medicine
- 雑誌
- Internal Medicine (ISSN:09182918)
- 巻号頁・発行日
- pp.0003-22, (Released:2022-10-05)
- 参考文献数
- 9
A 64-year-old man with a history of diabetes and gallstones was admitted to our institution with suspected pancreatic malignancy. Computed tomography (CT) revealed multiple pancreatic cysts and massive ascites, and endoscopic ultrasonography (EUS) revealed a 28×27-mm hypoechoic mass in the pancreatic head. An EUS-guided fine-needle aspiration biopsy was performed, and there were no malignant findings. Based on the test results and imaging findings, type 1 autoimmune pancreatitis was suspected. The patient was administered 30 mg of prednisolone daily. After 11 days, CT revealed that the pancreatic cysts and ascites had reduced in size.
- 著者
- Yasuhiko Hamada Yuhei Umeda Yohei Ikenoyama Akina Shigefuku Hiroki Yukimoto Misaki Nakamura Masaki Katsurahara Kyosuke Tanaka Noriyuki Horiki Yuka Sugimoto Hayato Nakagawa
- 出版者
- The Japanese Society of Internal Medicine
- 雑誌
- Internal Medicine (ISSN:09182918)
- 巻号頁・発行日
- pp.9733-22, (Released:2022-06-21)
- 参考文献数
- 22
A 44-year-old woman presented with severe anemia. We strongly suspected gastrointestinal bleeding; however, esophagogastroduodenoscopy, colonoscopy, and computed tomography showed no bleeding sources. Video capsule endoscopy revealed an actively bleeding submucosal lesion within the jejunum. Double-balloon enteroscopy revealed a 20-mm continuously bleeding submucosal lesion in the distal jejunum. We suspected small intestinal vascular malformation and performed surgical resection. The resected specimen pathologically comprised dilated, thin-walled lymphatic channels and blood vessels involving the small intestinal submucosa. Therefore, the patient was diagnosed with small intestinal lymphatic-venous malformation. Postoperatively, the patient recovered well, and recurrence was not observed.