检索结果-内蒙古大学图书馆

Corrigendum to “GraphRec-based Korean expert recommendation using author contribution index and the paper abstracts in marine” [Eng. Appl. Artif. Intellig. 133 (2024) 108219]

引用

engineering Applications of Artificial Intelligence 2024年 137卷

作者： Jeong-Wook Lee Jae-Hoon Kim Department of Computer Engineering and Interdisciplinary Major of Maritime AI Convergence Korea Maritime & Ocean University South Korea

来源：评论

学校读者我要写书评

暂无评论

Defensive Adversarial Training for Enhancing Robustness of ECG based User Identification∗

Defensive Adversarial Training for Enhancing Robustness of E...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Jeong, Hongbi Son, Junggab Kim, Hyunbum Kang, Kyungtae Hanyang University Dept. Applied Artificial Intelligence Major in Bio Artificial Intelligence Ansan Korea Republic of University of Nevada Las Vegas Dept. Computer Science Las VegasNV89154 United States Incheon National University Dept. Embedded Systems Engineering Incheon Korea Republic of Hanyang University Dept. Applied Artificial Intelligence Ansan Korea Republic of

ISBN: (纸本)9781665468190

Electrocardiogram (ECG) based user identification has received considerable attention with the advent of wearable devices. It provides emerging applications including personal healthcare a convenient way to authenticate users as the process can be performed at the moment the user makes contact with the device. However, a recent study discovered that injecting noise into the signal transmitted from the user to an application can effectively hinder the classification process. Many efforts have been made to deal with this noise injection attack, but most approaches have focused on noise removal. In contrast, this paper proposes Defensive Adversarial Training (DAT), which involves training a model with various noisy data to enhance the robustness of deep learning-based identification algorithms. We used two types of noise, Gaussian and Laplacian, to create noisy data. In addition, a sliding-window technique was used to effectively extract useful features and to achieve better accuracy. Our simulation results demonstrate that the proposed approach is highly robust to noise injection attacks and even against random noise. A comparative analysis with noise removal schemes also shows that the proposed DAT significantly enhances the robustness of ECG-based user identification. © 2022 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Role-Playing Video Game: It’S Effectiveness in Ideal Gas Law Learning of Junior High School Students

SSRN

引用

SSRN 2023年

作者： Dolipas, Bretel B. Dolipas, Thrysha Fabrigas, Christian Romero, Sebastien Duke Garcia, Marius Mactal, Aeron Silvio, Junel Benguet State University Philippines Environmental and Sanitary Engineer Graduate University of Cordilleras Philippines Business Administration Major in Digital Marketing Student University of the Cordilleras Philippines Computer Engineering Student University of Cordilleras Philippines Electronics and Communications Engineering Student Saint Louis University United States Electrical Engineering Student Saint Louis University United States Nursing Student Manila Central University Philippines

The study aimed to assess the effectiveness of role playing video game in the learning of Ideal Gas Laws of junior high school students. Specifically, the study determined the academic performance in Ideal Gas Laws of junior high school students when Ideal Gas Laws were taught through the conventional method and through role playing video game method of learning. The result indicated that academic performance in Ideal Gas Laws of students taught with the use of role playing video game was significantly higher compared to those taught using the conventional method of learning. In addition, the performance level of students taught using the role playing video game was fairly satisfactory or better regardless of sex. It is recommended that role playing video game technique could be an alternative and effective method in the teaching and learning of science concept. More research on role playing video game effectiveness to academic performance in other field is likewise recommended. © 2023, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Establishing Wireless Intranet Network Using UAVs and Web Application for Emergency Communications

Establishing Wireless Intranet Network Using UAVs and Web Ap...

引用

IEEE Sensors Applications Symposium, SAS

作者： Jihoon Yang Juhyun Kim Sion Kang Haeeun Ok Yijun Yoo Hyewon Koh Pilkyo Kim Alexander L. Head Anthony Smith Dept. of Computer Education Jeju National University Jeju Republic of Korea Dept. of Management Information Systems Jeju National University Jeju Republic of Korea Dept. of Computer Science and Engineering Chungnam National University Daejeon Republic of Korea Dept. of Computer Engineering Jeju National University Jeju Republic of Korea Major of Housing & Family Welfare(Faculty of Human Ecology & Welfare) Jeju National University Jeju Republic of Korea Dept. of Computer Science & Statistics Jeju National University Jeju Republic of Korea Dept. of Computer and Information Technology Purdue University West Lafayette Indiana USA

Every year, natural disasters such as earthquakes, hurricanes, volcanic eruptions, and tsunamis occur around the world. Natural disasters not only cause economic damage and casualties, but also destroy entire infrastructures. When communication infrastructure is damaged, information exchange between rescuers and victims or among rescuers themselves is not smooth, which inevitably reduces the effectiveness of relief activities. The purpose of this study is to establish a communication network using unmanned aerial vehicles (UAVs) known as drones, and to provide smooth communication services to areas where communication facilities have been destroyed through web application development. A low-altitude aerial base station (ABS) is built using a drone and provides a wireless intranet communication network. The intranet-only web application is developed to provide a service that allows people to send and receive messages and location information. In future research, separating the communication network between rescuers and non-rescuers and using multiple ABSs to build the network could serve more people in a wider disaster area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Person Name Extraction from TV program Using Pre-trained Language Model and News Headline

Person Name Extraction from TV program Using Pre-trained Lan...

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Kazuki Oda Minoru Sasaki Major in Computer and Information Sciences Graduate School of Science and Engineering Ibaraki University Hitachi Ibaraki Japan Faculty of Engineering Ibaraki University Hitachi Ibaraki Japan

ISBN: (纸本)9781665424219

In this study, we focus on extracting person names from text contained in from TV programs and TV-CMs broadcast in Japan. Person name extraction from TV programs is a challenging task because person names are often recognized with other entity names such as locations and organizations. To tackle this problem, we experiment with an existing named entity extraction method using a list of names extracted from Wikipedia. However, this method results in low precision in extracting the person names, which leads to the problem that the list of person names is not effective for TV program texts. In this paper, to solve this problem, we propose a person name extraction method using Conditional Random Fields (CRF) with ELMo pre-training language model. Also, we propose to use news headlines to construct the person name extraction model for effective extraction of person names performing on the TV programs. As a result of our experiments, the proposed model trained with training data and news headlines provides the highest precision. These results show that adding the news headlines as external information to TV program data is effective for person name extraction.

关键词： TV Training data Organizations Encyclopedias Data models Internet Online services

来源：评论

学校读者我要写书评

暂无评论

Typical Defects Detection of I&C Cables in Nuclear Power Plants Based on Time-Frequency Domain Reflection Method 5

Typical Defects Detection of I&C Cables in Nuclear Power Pla...

引用

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Tu, Hua Ma, Shu Liu, LiHua Wang, ZhiWu Zhang, Xiang Li, LiXing Lin, TaoKun Deng, HongLei Suzhou Nuclear Power Research Institute Equipment Management Department Hunan China Major Equipment Management Office ChinaNuclear Power Operations Co. Ltd. Chongqing China Daya Bay Nuclear Power Operations and Management Co. Ltd. Medium and Long-term Renovation Project Department Guangdong China South China University of Technology School of Electric Power Engineering Guangdong China South China University of Technology School of Computer Science & Engineering Guangdong China

ISBN: (纸本)9781665485081

In order to enhance the safe and stable operation of instrumentation and control (I&C) cables in nuclear power plant (NPP), time-frequency reflection method (TFDR) based on SPWVD (Smooth Pseudo Wigner-Ville Distribution) is proposed to detect and locate typical defects in I&C cables. Firstly, the defect information of the cable was obtained by the reflected signal produced by a linear Frequency Modulation (FM) Gaussian signal. Secondly, the receiving signals were processed by SPWVD to obtain time-frequency domain distribution. Thirdly, time-frequency cross-correlation (TFCC) of the incident and reflected signals were analyzed and normalized from the results of time-frequency distribution. Finally, evaluation and localization of typical defects of I&C cables were discussed. In this paper, a 50 meters I&C cable was prepared to simulate several typical defects, including short circuit, open circuit, and metal shield damage. Subsequently, TFDR method was adopted to detect these defects to verify the reliability of this technology. The experiment shows that the cross term generated by WVD reduces the reliability of the detection, SPWVD can effectively eliminate cross term by windowing and convolved process. By adopting TFDR with SPWVD, artificial defects can be accurately detected. The measured positions of the defects are approach to the actual locations of the defects. The measuring errors are less than 2%. © 2022 IEEE.

关键词： Wigner-Ville distribution

来源：评论

学校读者我要写书评

暂无评论

Manipulating optical field of a microcavity by tailoring phase space

Manipulating optical field of a microcavity by tailoring pha...

引用

CLEO: Science and Innovations, S and I 2022

作者： Qian, Yan-Jun Liu, Hui Cao, Qi-Tao Kullig, Julius Rong, Kexiu Qiu, Cheng-Wei Wiersig, Jan Gong, Qihuang Chen, Jianjun Xiao, Yun-Feng State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics School of Physics Peking University Beijing100871 China Institute for Physics Otto von Guericke University Magdeburg MagdeburgD-39016 Germany Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore117583 Singapore Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan030006 China Department of Physics and Applied Optics Beijing Area Major Laboratory Beijing Normal University Beijing100875 China

We propose to manipulate the optical mode of a microcavity by tailoring its phase space, through which the photon transport can be precisely controlled, resulting in on-demand engineering of far-field emission pattern... 详细信息

ISBN: (纸本)9781557528209

关键词： Microcavities

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Mixed Integer Linear Programming for Daily Unit Commitment with Pumped Storage Hydropower, EV Charging Demand, and Solar PV Supply

Fuzzy Mixed Integer Linear Programming for Daily Unit Commit...

引用

IEEE PES Asia-Pacific Power and Energy engineering Conference (APPEEC)

作者： Dino Ny Chawalit Jeenanunta Jun-Ichi Takada Sapa Chanyachatchawan Sukita Kaewpasuk Boonyarit Intiyot Aussadavut Dumrongsiri School of Integrated Science and Innovation Sirindhorn International Institute of Technology Thammasat University Pathum Thani Thailand School of Management Technology Sirindhorn International Institute of Technology Thammasat University Pathum Thani Thailand Department of Transdisciplinary Science and Engineering Major in Global Engineering for Development Environment and Society Tokyo Institute of Technology Tokyo Japan National Electronics and Computer Technology Center National Science and Technology Development Agency Pathum Thani Thailand Department of Mathematics and Computer Science Faculty of Science Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798350318098

ISBN: (纸本)9798350318104

There is increasing penetration of renewable energy sources such as photovoltaic (PV) systems and the growing popularity of electric vehicles (EVs) in many countries. The uncertainty of PV generation and EV charging demand has become a significant challenge in unit commitment (UC) planning. Pumped Storage Hydropower (PSH) is introduced into the power system to respond to these uncertainties. This paper presents a Fuzzy Mixed-integer Linear Programming (FMILP) model for the schedule of the usage of PSHs with the uncertainties of demand and supply. The FMILP model considers uncertainties and imprecisions associated with forecasted demand, EV charging demand, and PV supply in the daily UC problem. The objective is to minimize the total production cost while ensuring the power system’s reliable and sustainable operation by determining the optimal schedule for power generators to meet the power demand over 48 periods. A small system of 33 generators, including thermal and hydro generators, and 7 PSHs are studied. Numerical simulations have demonstrated the effectiveness of the FMILP model by identifying the uncertainty range between the lower and upper bounds, including the worst-case scenario. The numerical results show that the FMILP model can provide a more reliable and robust solution than deterministic MILP unit commitment.

关键词： Schedules Uncertainty Costs Upper bound Hydroelectric power generation Electric vehicle charging Generators

来源：评论

学校读者我要写书评

暂无评论

Fundus Image Translation with Scale-Aware Registration and Gradient-Guided GAN

SSRN

引用

SSRN 2024年

作者： Kim, JuChan Le, Duc-Tai Bum, Junghyun Son, Chang-Hwan Lee, Eun Jung Han, Jong Chul Choo, Hyunseung Department of Artificial Intelligence Systems Engineering Sungkyunkwan University Korea Republic of College of Computing and Informatics Sungkyunkwan University Korea Republic of Sungkyun AI Research Institute Sungkyunkwan University Korea Republic of Software Science and Engineering Major Kunsan National University Korea Republic of Department of Ophthalmology Samsung Medical Center Korea Republic of School of Medicine Sungkyunkwan University Korea Republic of Department of Medical Device Management and Research SAIHST Sungkyunkwan University Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Two major fundus imaging types, conventional fundus (CF) imaging and ultrawidefield fundus (UF) imaging, are widely used in ophthalmology. In a typical clinical setting, both imaging methods are used simultaneously to diagnose diseases depending on the case. This study introduced an enhanced method of modality transformation to boost the diagnostic support capabilities of deep-learning models in ophthalmology. The method proposed in this study to translate UF images (UFIs) to CF images (CFIs) can replace the common clinical approach of both imaging methods, thereby reducing financial and temporal burdens on patients. This study learns and transforms the relationship between these modalities using UFI–CFI image pairs obtained from the same patient on the same day to minimize distorted information and accurately convert between different modalities. Our proposed model uses scale-aware registration and gradient-guided translation methods to align the UFI–CFI pairs, The generated CFIs not only enhance the quality of images and better represent the retinal area compared to existing methods but also effectively preserve the disease-related details in UFIs, aiding in the diagnosis. In addition, we optimize the image transformation performance, resulting in an 22% improvement in image quality assessment scales compared with previous methods. Furthermore, we acquired the observation that our results are nearly impossible to discern any differences between the real CFIs and the generated CFIs in the view of ophthalmologists. © 2024, The Authors. All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fleet Management with ESP8266-based IoT Sensors for Weight and Location Tracking

Enhancing Fleet Management with ESP8266-based IoT Sensors fo...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Sheshang Degadwala Rocky Upadhyay Shivam Upadhyay Shrinal S Dave Digvijaysinh Mahida Dhairya Vyas Department Department of Computer Engineering Sigma University Gujarat India Dept. of IT Drs. Kiran & Pallavi Patel Global University Vadodara Dept. of CSE Drs. Kiran & Pallavi Patel Global University Vadodara BS Computer Science Major Student University of Massachusetts Boston USA CSE Department KSET KPGU University Vadodara Gujarat India The Maharaja Sayajirao University of Baroda Vadodara Gujarat India

This research study explores the implementation of ESP8266-based Internet of Things (IoT) sensors to enhance fleet management systems. In the context of logistics and transportation industries, accurate and real-time tracking of vehicle weight and location plays a crucial role in optimizing operations, ensuring compliance with regulations, and improving overall efficiency. The proposed system employs ESP8266 microcontrollers equipped with load cells for weight measurement and GPS modules for location tracking. These sensors collect and transmit data to a central server, enabling the fleet managers to access the critical information required for route planning, regulatory compliance, and safety. Furthermore, this study discusses about the cost-effectiveness and scalability of ESP8266-based IoT sensors by highlighting their potential to streamline fleet management practices while reducing operational costs, fuel consumption, and carbon emissions. This research study serves as a valuable resource for industry professionals and researchers interested in leveraging IoT technology to enhance fleet management.

关键词：

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：