检索结果-内蒙古大学图书馆

Advanced Applied Informatics Winter (IIAI-AAI-Winter), International Congress on

作者： Tomoya Kubo Tomoyuki Yokogawa Kazutami Arimoto Masaki Hokari Isao Kayano Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Health Science and Technology Kawasaki University of Medical Welfare Kurashiki Okayama Japan

We developed an AI for Facial Expression Estimation to predict driver drowsiness levels, mimicking human evaluation. Traditional Image-based AIs struggle with limited data generalization in drowsiness prediction. Our proposed AI framework overcomes this by extracting Facial Action Units (FAU) from facial images, using these dynamic expression elements as primary features, making evaluation more humanlike. In our study involving 19 participants, we validated the generalization performance using a Gated Recurrent Unit (GRU) with FAU values and compared it with a Convolutional Neural Network (CNN) model based on VGGFACE (ResNet50). The proposed method demonstrated enhanced performance, showcasing potential improvements in drowsiness estimation with limited data, expecting to significantly reduce the data required for accurate drowsiness level estimation. Furthermore, the results obtained through the process of improving generalization performance imply that there exists a trade-off relationship between performance specialized to specific individuals and generalized performance in learning models utilizing features such as FAUs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Strong Stabilization of the Acrobot at the Down–Up Equilibrium Point ⋆

引用

IFAC-PapersOnLine 2023年第2期56卷 9167-9172页

作者： Ziyu Wang Xin Xin Yannian Liu School of Automation Southeast University and Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 China Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama 719-1197 Japan

In this paper, the strong stabilization of the Acrobot at the Down-Up equilibrium point is addressed, with the first link being downward and the second link being upright. By converting the strong stabilization of the Acrobot at the Down–Up equilibrium point equivalently to the existence and design of a stable stabilizing controller for a fourth-order single-input single-output linear plant with adjustable zeros, a pair of poles on the imaginary axis, and a pair of real poles located symmetrically with respect to the origin, this paper has three main contributions. Firstly, the existence of a stable stabilizing controller for any Acrobot which is linearly controllable at the Down–Up equilibrium point is proved by showing the range of the adjustable zero via adjusting a parameter of the output signal. Secondly, a necessary and sufficient condition on the mechanical parameters of the Acrobot is provided to guarantee the existence of a second-order stable stabilizing controller for the Acrobot around its Down– Up equilibrium point. Thirdly, a direct method is presented to design a second-order stable controller, whose transfer function is preset with three parameters. By utilizing the Liénard– Chipart criterion for a fourth-order polynomial, the necessary and sufficient conditions on these parameters for achieving the strong stabilization are obtained, which are expressed in a cascade form for obtaining these parameters conveniently. A numerical example is presented to validate the effectiveness of the proposed method.

关键词： Robust control strong stabilization underactuated mechanical systems reduced-order controller linear systems

来源：评论

学校读者我要写书评

暂无评论

A Trend Analysis of Test Smells in Python Test Code Over Commit History

A Trend Analysis of Test Smells in Python Test Code Over Com...

引用

Euromicro Conference on Software engineering and Advanced Applications (SEAA)

作者： Yuki Fushihara Hirohisa Aman Sousuke Amasaki Tomoyuki Yokogawa Minoru Kawahara Department of Computer Science Faculty of Engineering Ehime University Ehime Japan Center for Information Technology Ehime University Ehime Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Japan

Software testing is an essential activity for developing and maintaining high-quality software. Unit testing with test code (test cases) is a fundamental testing activity, and developers can test their production code whenever they create or modify the code. However, such quality assurance relies on the correctness of the test code. If a test code had a flaw, it would mislead the developers about the hidden faults and prevent early detection of the faults. This paper focuses on "test smells," which may cause test code flaws in Python programs, and analyzes their changing trends over commit history (code changes) toward better Python test code management. Through an empirical data analysis of 100 open-source projects, the paper reports the following findings: (1) a few kinds of test smells constitute the majority of smells detected in the studied projects, and (2) most kinds of smells tend to increase over commits, i.e., many test smells are likely to have remained in test code as technical debt.

关键词：

来源：评论

学校读者我要写书评

暂无评论

1.40/2.42/4.21-GHz Triple-Band Concurrent LNA Using Inductor Coupling

1.40/2.42/4.21-GHz Triple-Band Concurrent LNA Using Inductor...

引用

Asia-Pacific Conference on Microwave

作者： Shinichiro Seguchi Kiyotaka Komoku Nobuyuki Itoh Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan

ISBN: (数字)9784902339567

ISBN: (纸本)9781665451086

This paper presents a triple-band concurrent LNA using inductor coupling. The proposed triple-band matching circuit which is implemented for both input and output consists of the dual-band notch filter with the mutual induction circuit. This type of triple-band matching circuit realizes a small occupied area. The measured $\boldsymbol{s}_{11}, \boldsymbol{s}_{22}, \boldsymbol{s}_{21}$ , and $\it NF$ were -3.88, -19.72, 14.44, and 2.50 dB at 1.40 GHz, -9.21, -27.97, 14.17, and 2.97 dB at 2.42 GHz, and -8.85, -4.63, 9.96, and 3.02 dB at 4.21 GHz, with 22.8 mW under 1.8 V supply voltage, designed by using the 180 nm CMOS process.

关键词： Couplings Semiconductor device measurement Noise figure Voltage measurement Power demand Dual band Microwave circuits

来源：评论

学校读者我要写书评

暂无评论

28-m W Fully Embedded AI Techniques with On-site Learning for Low-Power Handy Tactile Sensing System

28-m W Fully Embedded AI Techniques with On-site Learning fo...

引用

2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022

作者： Yano, Yuji Iwamoto, Hisashi Yoshimura, Takuma Nishida, Yoshihiro Mori, Tatsuya Komoku, Kiyotaka Takao, Hidekuni Arimoto, Kazutami Poco-apoco Networks Development Department Osaka Japan Kagawa University Faculty of Engineering and Design Takamatsu Japan FaMT Himeji Development Department Japan Okayama Prefectural University Faculty of Computer Science and Systems Engineering Sojya Japan

ISBN: (纸本)9781665409216

We have been studying an edge-AI learning-and-inference techniques for low-power handy battery operating tactile sensing system. It works in an event-driven of normally off power supply mechanism. The power consumption during classify operation at 10 inference per second is approximately 28m W. The proposed system adopts on-site embedded learning for the low power consumption and the high recognition accuracy, which is effective to operate in variety of environments. On-site learning function improves the recognition accuracy to classify the six kinds of paper from 50% to 91 % though humans can hardly identify them. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A NOTE ON THE ASSMUS-MATTSON THEOREM FOR SOME TERNARY CODES (A RESUME)

arXiv

引用

arXiv 2023年

作者： Bannai, Eiichi Miezaki, Tsuyoshi Nakasora, Hiroyuki Fukuoka819-0395 Japan Faculty of Science and Engineering Waseda University Tokyo169-8555 Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama719-1197 Japan

Let C be a two and three-weight ternary code. Furthermore, we assume that C are t-designs for all by the Assmus-Mattson theorem. We show that t ≤ 5. As a corollary, we provide a new characterization of the (extended)... 详细信息

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Food Volume Prediction and Classification using Multi-Task Learning

Food Volume Prediction and Classification using Multi-Task L...

引用

Artificial Intelligence (WSAI), World Symposium on

作者： Yuita Arum Sari Atsushi Nakazawa Akio Gofuku Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama University Okayama Japan Faculty of Computer Science Brawijaya University Malang Indonesia

ISBN: (数字)9798350374162

ISBN: (纸本)9798350374179

Food volume prediction is critical for calculating calories in food analysis and nutritional evaluation. However, obtaining data and measuring volume from the 3D sensor camera concurrently is time-consuming. Additionally, high computing power is necessary to compute the volume. Therefore, machine learning techniques are employed to extract specific data collected from the data collection process for learning purposes to save time. In this study, we employ Multi-Task Learning to predict volume and categorize food due to their interdependence simultaneously. We evaluate several backbones and find that ResNet50 attains the best performance with an MAE of 4.87 for volume prediction and 100% food classification accuracy. Our proposed method showcases outstanding results, aided by an efficient volume measurement methodology,

关键词： Three-dimensional displays Accuracy Volume measurement Learning (artificial intelligence) Machine learning Data collection Multitasking Cameras Data mining Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Dual Stream Deep Neural Network for Joint Sperm Morphology and Motility Estimation

Dual Stream Deep Neural Network for Joint Sperm Morphology a...

引用

Communication systems (ECCS), European Conference on

作者： Sigit Adinugroho Atsushi Nakazawa Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama University Okayama Japan Faculty of Computer Science Brawijaya University Malang Indonesia

ISBN: (数字)9798350377927

ISBN: (纸本)9798350377934

Morphology and motility are vital features to evaluate sperm quality, which is essential for estimating the success of assisted reproduction. Current standards from the World Health Organization (WHO) suggest that human operators are needed to perform sperm quality assessments. However, human assessment is proven to be subjective and leads to variability in the results. To cope with that problem, an automated approach is needed. This study aimed to perform a joint motility and morphology estimation via a single model that has never been done before. The model takes a stack of optical flow images and a grayscale image to be processed by motion and appearance stream. The outputs from each stream are combined and further processed by a regressor to estimate the morphology and motility. The proposed approach performed better than similar methods by achieving mean average errors of $\mathbf{4. 4 9 5 \%}$ and $\mathbf{7. 8 6 5 \%}$ for morphology and motility estimation, respectively.

关键词： Standards organizations Morphology Estimation Europe Organizations Streaming media Gray-scale Quality assessment Error correction codes Optical flow

来源：评论

学校读者我要写书评

暂无评论

Hook Point Estimation for System Call Detection by Virtual Machine Monitor

Hook Point Estimation for System Call Detection by Virtual M...

引用

International Symposium on Computing and Networking Workshops (CANDARW)

作者： Masaya Sato Taku Omori Toshihiro Yamauchi Hideo Taniguchi Faculty of Computer Science and Systems Engineering Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Natural Science and Technology Okayama University Okayama Japan

Virtual machine monitors (VMMs) are used to monitor the behavior of virtual machine (VM) programs. System call detection is frequently used to monitor behavior. To monitor the system calls, the VMM inserts a breakpoint, called a hook point, into the memory of the monitored VM. Researchers have determined hook points based on experimental knowledge or reading the source code of operating systems (OSes). However, reading the source codes of OS requires specialized knowledge. In addition, the appropriate hook point differs among OS versions. Therefore, analyzing the source code in each OS update is impractical. We propose a method for estimating the hook point using a memory analysis technique. The proposed method acquires the memory of the monitored VM and then searches for an appropriate instruction appropriate to hook. The search instructions depend on the processor architecture. Therefore, the proposed method does not require knowledge of OS versions or reading the source code of OSes. The experimental results showed that the proposed method precisely estimates the hook point. In addition, the overhead of the proposed method is small, considering the boot time of the monitored VM.

关键词： Performance evaluation Virtual machine monitors Codes Source coding Operating systems Linux computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Novel Assessment of Spontaneous Laughter Based on Heart Rate Variability under Daily-living Conditions: Dividing from Exercise-induced Acute Elevation of Autonomic Nerve Activity

Transactions of Japanese Society for Medical and Biological ...

引用

Transactions of Japanese Society for Medical and Biological engineering 2022年第6期60卷 175-179页

作者： Yamada, Miyu Ayabe, Makoto Mitani, Kaito Graduate Schoolof Computer Science and Systems Engineering Okayama Prefectural University Japan Human Information Engineering Okayama Prefectural University Japan

The present investigation aimed to identify the distinguishing effects of spontaneous laughter (SL) and aerobic exercise on autonomic nervous system (ANS) activity to develop a novel technique for indirect SL identification based on heart rate variability (HRV) under daily-living conditions. The subjects of the present investigation were ten healthy young men. The investigation consisted of three 15 min experimental periods, each following a resting period after 5 h of daily-living conditions. The three experimental periods included lightintensity aerobic exercise (LAE), moderate-intensity aerobic exercise (MAE), or SL and were randomly distributed across three separate days. To induce SL, the subjects were shown comedy movies. Their ANS activity was monitored throughout the investigation period using continuous heart rate (HR) responses. Total power, low frequency (LF), and high frequency (HF) components were recorded using frequency analysis. LF and HF components were normalized to total power (nHF, nLF), and LF was then divided by HF to obtain a sympathetic activity index (LFHF). Instances of SL during the daily-living periods were subjectively identified using laughter intensity scores. Our results revealed a significant correlation between the effects of time and task on HR during the experimentalperiods (p ＜0.001). HR significantly increased during LAE and MAE, but not during SL, compared with that during the resting period (p ＜ 0.05). Temporaleffects on ANS were evaluated, and no significant difference was observed between the three conditions. During daily-living conditions, ANS activity differed significantly from baseline (p ＜ 0.05) but HR did not. The present investigation revealed that SL induces similar ANS responses but different HR responses compared to aerobic exercise. These findings imply that HR responses via HRV and ANS could provide a novel means of identifying SL in daily-living conditions. © 2022, Japan Soc. of Med. Electronics and Biol. Engin

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：