Search

Your search keyword '"Kotaro Usui"' showing total 4 results
Start Over Author "Kotaro Usui"
4 results on '"Kotaro Usui"'

1. Cholesterol crystal embolism-related cerebral infarction: Magnetic resonance imaging and clinical characteristics

Author

Yuko Kondo, Mami Kanzaki, Daisuke Ishima, Ryo Usui, Ayato Kimura, Kotaro Usui, Yasuyuki Amoh, Yasuo Takeuchi, Toshihiro Kumabe, Junya Ako, Kagami Miyaji, Kazutoshi Nishiyama, and Tsugio Akutsu

Subjects
Cholesterol crystal embolism, Cerebral infarction, Cholesterol crystal embolism-related cerebral infarction, Atheroembolism, Atherothrombotic cerebral infarction, Diffusion-weighted imaging, Neurology. Diseases of the nervous system, RC346-429
Abstract

Background and aims: Cholesterol crystal embolism-related cerebral infarction (CCE-CI) is frequently misdiagnosed due to the lack of specific symptoms. To aid in differential diagnosis, this study comprehensively characterized the magnetic resonance imaging (MRI) and clinical manifestations of CCE-CI and compared these features to those of atherothrombotic cerebral infarction (ACI). Methods: This single-center, retrospective, observational study was conducted at Kitasato University Hospital, Kanagawa, Japan. We identified 37 clinically or histopathologically confirmed CCE-CI cases and 110 ACI cases treated from January 2006 to May 2020. Groups were compared for mean age, sex ratio, clinical presentations, imaging manifestations, precipitating factors, comorbid conditions, medications, and smoking history. Results: Of 37 eligible patients with CCE-CI, 10 (27.0%) received brain MRI, of which 8 (21.6%) exhibited high-intensity signals indicative of brain lesions on diffusion-weighted imaging (DWI). However, two patients with DWI lesions exhibited no detectable neurological abnormalities. Patients with CCE-CI frequently demonstrated bilateral DWI lesions involving the bilateral anterior and posterior circulation, a pattern absent in ACI (50% vs. 0%, p

Published
2021
Full Text
View/download PDF

4. Detecting shoplifting from customer behavior data by extended XCS-SL: Towards feature extraction on class-imbalanced sequence data

Author

Kotaro Usui, Keiki Takadama, Masaya Nakata, and Minato Sato

Subjects
Sequence, Learning classifier system, business.industry, Computer science, Feature extraction, Pattern recognition, Machine learning, computer.software_genre, Class (biology), Sequence labeling, Data sequences, Artificial intelligence, business, computer, Consumer behaviour
Abstract

This paper explores a novel Learning Classifier System (LCS) that can detect shoplifting behavior from the class-imbalanced sequence data of customer-behaviors. The shoplifting behavior detection is related to the sequence labeling as a time-series classification. More importantly, the target problem has a difficulty of the class-imbalanced problem in addition to the time-series classification because the number of data of shoplifters might be much fewer than that of customers who do not shoplift. To tackle this difficult issue, this paper proposes a feature extraction method for the sequence labeling in the class-imbalanced problem and applies it into XCS-SL (LCS for sequence labeling). The proposed LCS (called as XCS-SLFEM (XCS-SL for Feature Extraction of Minority class data)) extracts the features of the minority class from those of the majority one by representing them as the classifiers. The intensive simulation using the customer-behavior dataset that includes the shoplifting behaviors has revealed the following implications: (1) XCS-SLFEM shows the superior performance as compared with XCS-SL in the customer-behavior dataset including the class-imbalanced sequence data; (2) the classification accuracy of XCS-SLFEM increases as the size of memory for the sequence histories increases; and (3) XCS-SLFEM has the potential of predicting shoplifting before the shoplifters do shoplift.

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results