检索结果-内蒙古大学图书馆

PID control of hypnotic induction in anaesthesia employing multiobjective optimization design procedures

IFAC-PapersOnLine 2021年第15期54卷 31-36页

作者： Ricardo Massao Kagami Renan Muniz Franco Gilberto Reynoso-Meza Roberto Zanetti Freire Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifícia Universidade Católica do Paraná (PUCPR) Brazil Department of Chemistry – Apucarana’s Campus Universidade Tecnológica Federal do Paraná (UTFPR) Brazil

General anaesthesia is a clinical procedure that involves the continuous monitoring of several parameters for the correct application of anaesthetics and associated drugs. Focusing on the automatic control in anaesthesia, this work presents a multiobjective optimization design of controllers based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to solve the problem of drug delivery for induction of anaesthesia. Five Proportional-Integral-Derivative (PID) controllers in a decentralized scheme were tuned for one specific patient and tested in a total of 24 simulated patients. Acting over the infusions of Propofol, Remifentanil, Atracurium, Dobutamine, and Sodium Nitroprusside the proposed controllers could maintain the controlled variables in a safe range for surgical procedures.

关键词： Anaesthesia controller tuning multiobjective problem multivariable control PID controller

来源：评论

学校读者我要写书评

暂无评论

Investigation of manufacturing conditions of single roll rapidly solidified ribbon for anode materials of magnesium rechargeable batteries

引用

Keikinzoku/Journal of Japan Institute of Light Metals 2023年第11期73卷 537-544页

作者： Kirimoto, Yuichi Fuke, Kousuke Tsukeda, Tadayoshi Aida, Tetsuo Nemoto, Yasunori Ikeda, Minoru Tabata, Hironobu Kurihara, Hideki Suzuki, Mayumi Department of Nano and Functional Material Science Graduate School of Science and Engineering for Education University of Toyama 3190 Gofuku Toyama-shi-shiToyama Toyama930-8555 Japan Program of Materials Science and Engineering Studies in Science and Engineering Graduate School of Science and Engineering University of Toyama Toyama-shi-shiToyama Toyama Japan Faculty of Sustainable Design Academic Assembly University of Toyama Toyama-shi Toyama-shi-shiToyama Toyama Japan FLOW Science JAPAN Shizuoka Hamamatsu-shi Japan CHUETSU METAL WORKS CO. LTD Nakaniikawa-gun Toyama Japan Saitama Industrial Technology Center Saitama Kawaguchi-shi Japan Department of Mechanical Systems Engineering Faculty of Engineering Toyama Prefectural University Imizu-shi Toyama Japan

Magnesium rechargeable batteries are attracting attention as next-generation rechargeable batteries because of their resource abundance, cost, safety, and high electrical capacity per volume compared to conventional lithium-ion rechargeable batteries. Our joint research team focused not only on the electrochemically active magnesium composition of ribbon for the negative electrode materials of magnesium rechargeable batteries but also on the production process, focused on the single roll type liquid quenching and rapid solidification method, which can be produced at a lower cost. In this study, the optimal processing conditions were examined by comparing CAE analysis with ribbon actually manufactured, with the aim of further improving manufacturing conditions using the same method, such as length discontinuities, thickness, and surface properties of ribbon. We specifically various process parameters such as injection pressure and roll peripheral speed for evaluation. As a result, several linear cracks were observed on the surface of the ribbon as the peripheral speed increased and as the Gap became wider, and the surface properties tended to deteriorate. Also, It was found that the dominant factor in the length of the ribbon was the peripheral speed. As the peripheral speed increased, the length of the ribbon tended to increase. © 2023 Japan Institute of Light Metals. All rights reserved.

关键词： Surface properties

来源：评论

学校读者我要写书评

暂无评论

Machine learning techniques in bank credit analysis of companies: A case study of a Brazilian bank 49

Machine learning techniques in bank credit analysis of compa...

引用

49th International Conference on Computers and industrial engineering, CIE 2019

作者： Assef, F.M. Steiner, M.T.A. Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Paraná Curitiba Brazil

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, not always did the best accuracy represent the best technique for the assessment of this problem. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study. © 2019, Computers and industrial engineering. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Approach to Semantic Interoperability for Product Development Through Automatic Requirement Extraction and Semantic Reconciliation 16th

An Approach to Semantic Interoperability for Product Develop...

引用

16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019

作者： Canciglieri, Matheus Beltrame de Moura Leite, Athon Francisco Curi Staben Szejka, Anderson Luis Junior, Osiris Canciglieri Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)9783030422493

The strong competitiveness challenges manufacturing industry to rationalize different ways of bringing new products to the market in the shortest time with competitive prices while ensuring higher quality. Industries need to effectively share product requirements, which comes from various sources and are heterogeneous in nature, during the Product Development Process (PDP) to stay competitive. However, problems with misinterpretation of such requirements have been identified during its sharing due to semantic interoperability obstacles related to the process of automatically gathering requirements and their translation and reuse. This research proposes an approach to automatically gather product requirements, extracting its knowledge and translate it for further use and reuse along PDP. The research structure consisted of firstly studying the current issues of the topic, secondly by exploring an approach, to be validated in an experimental case. Current issues point out to gaps related to the process of semantic reconciliation and knowledge extraction perspectives, giving it a multi-dimensional panorama where semantic issues are intertwined among different perspectives. The later solution presents an approach which considers raw information being processed into product features, refining knowledge during PDP and making it reusable in different cycles. The approach brings a new view on practical methods for automatically collect product requirements, extract its knowledge and translate it into product features, based on knowledge extraction methods and by using semantic reconciliation as means for translating product’s requirements. Further research will focus on expanding the approach and including more features to increasingly complex cases, to explore the full potential of the approach. © 2019, IFIP International Federation for Information Processing.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Computer Vision with Cognitive Learning to Improve the Decision-Making During the Sales Process in Physical Stores 16th

Computer Vision with Cognitive Learning to Improve the Decis...

引用

16th IFIP WG 5.1 International Conference on Product Lifecycle Management, PLM 2019

作者： da Silva Ramalho, Vinícius Szejka, Anderson Luis Rudek, Marcelo Junior, Osiris Canciglieri Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)9783030422493

In a world where the information is obtained faster than ever seem, new methods to process that high volume of data are being developed frequently. This is more notorious in a virtual ambient where the data is generated in a manner that is faster and easier to analyze than in the real world. This is very evident in the retail field, where virtual stores have easy access to all the advertisement a user visited and simple to obtain user profile, on the other hand physical stores are limited to basically create a register in a database when there is a purchase. In an attempt to improve the retailers experience from physical stores to manage their business this document has the objective to develop a computational tool that will analyze the people flux going in the establishment, trying to inform the retailer the amount of people and their gender to help the sales process in physical stores. To this end, computational vision methods and algorithms were raised, which after selection, theoretical conception and tool’s implementation it was tested with benchmarks to operate locally and in real time by accessing the cameras installed strategically in a real scenario. Two scenarios were tested: static ambient light and dynamic light. Two tests were conducted: YOLOv2 against background subtraction-based counter;gender classification using full body features. Even though the results were not as positive as needed for commercial use, the tool demonstrated potential and space for improvements. © 2019, IFIP International Federation for Information Processing.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Forged content shared widely on social media platforms is a major social problem that requires increased regulation and poses new challenges to the research community. The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous work on detecting AI-generated fake videos only utilizes visual modality or audio modality. While there are some methods in the literature that exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multi-modal datasets of deepfake videos involving acoustic and visual manipulations. Moreover, these existing methods are mostly based on CNN and suffer from low detection accuracy. Inspired by the recent success of Transformer in various fields, to address the challenges posed by deepfake technology, in this paper, we propose an Audio-Visual Transformer-based Ensemble Network (AVTENet) framework that considers both acoustic manipulation and visual manipulation to achieve effective video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multi-modal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that our best model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. © 2023, CC BY.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

A New Damage Index for Structural Health Monitoring: A Comparison of Time and Frequency Domains

引用

Procedia Computer Science 2021年 179卷 930-935页

作者： Fergyanto E. Gunawan Tran Huu Nhan Muhammad Asrol Yasuhiro Kanto Insannul Kamil Sutikno Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia 11480 Department of Automotive Engineering Faculty of Transportation Engineering Ho Chi Minh City University of Technology Ho Chi Minh City Viet Nam Mechanical Systems Engineering College of Engineering Ibaraki University Ibaraki Japan Department of Industrial Engineering Department Faculty of Engineering Andalas University Padang Indonesia Department of Mechanical Engineering Department Faculty of Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia

With the adoption of the damage tolerance design principle, the health monitoring system has become an integral part of the operation of engineering structures. For the system to work, a damage indicator that describes the structural integrity level should be established and monitored. The damage indicator is usually derived from structural responses. Many quantities have been proposed for damage indicator including natural frequency, mode shape, curvature, strain energy, and t-, F-, and z-statistics. In this paper, we propose a new damage indicator in the time and frequency domains derived from the Euler-Bernoulli beam theory. We evaluate the method by using data obtained from a numerical simulation of a cracked beam. The beam deformation is nonlinear due to the contact between the crack faces during vibration. The proposed damage index is estimated in the domains for various observation points on the beam. Besides, the existence of the crack is also predicted by the widely used traditional method based on the change of the natural frequency and mode shape. A comparison is made between the present method and the existing ones. We conclude the present proposal is more sensitive to detect the crack.

关键词： Euler-Bernoulli Beam Structural Health Monitoring Damage Indicator Natural Frequency Finite Element Method

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Teaching Introductory programming Using Flowcharts with Real and Simulated Robots for The Brazilian Robotics Olympiad (OBR)

FluxProg 2.0 - Teaching Introductory Programming Using Flowc...

引用

IEEE Latin American Robotics Symposium, LARS

作者： João Alberto Fabro Matheus Biscaya Gutierrez Fernando Henrique Ratusznei Caetano DAINF - Academic Department of Informatica PPGCA - Graduate Program on Applied Computing LASER-Laboratory for Advanced Robotics and Embedded Systems UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Information Systems academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Computer Engineering academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

In this paper, an approach to aid in introductory programming courses is presented, focused on students that had never had any contact with computer programming. The approach, that was introduced in a previous paper [3], presents programming concepts using icons and “flowcharts”, and a 3D robotics simulator (CoppeliaSim), that has free educational use. This time, a real version of the simulated robot, built using Arduino and cheap, easily obtainable electronic components, is also presented. The programs to control the robot are developed by graphically constructing flowcharts on the visual editor, and then following the execution of programs using the simulated (or real) robot, step by step. This graphic program editor is named “FluxProg”, and its 2nd version is now available online, with new features comprising variables, arithmetic and logic expressions, thus providing a complete programming environment.

关键词： Flowcharts Visualization Three-dimensional displays Conferences Education Electronic components Robots

来源：评论

学校读者我要写书评

暂无评论

Proposal of a framework for a disaster management system

Proposal of a framework for a disaster management system

引用

2016 industrial and systems engineering Research Conference, ISERC 2016

作者： Foggiatto, Anderson Avanzi, Daniel de Freitas Rocha Loures, Eduardo Deschamps, Fernando Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil Instituto Curitiba de Informática Curitiba Brazil Federal University of Technology - Parana Curitiba Brazil Department of Mechanical Engineering Federal University of Parana Curitiba Brazil

During a disaster, the more coordinated the response, the lesser its impacts are. One of the factors that has a major influence in response coordination is the interoperability among involved actors - public and private entities that interact to exchange information through the communication of people and systems. This factor is critical because it allows an efficient and effective mobilization of available resources towards reducing the effects caused by an event. This work proposes a framework for the development of Disaster Management systems (DMS) that promote real time communication (information flow and process coordination) among different involved entities, primarily focusing on interoperability in its different levels. This framework is based both on a literature review of scientific works and a survey of worldwide initiatives related to improving disaster response. The main components of the related framework architecture are an SDK (software development kit), a common relational database, multiple communication platforms (e.g., a Web portal and a mobile app), and low-cost hardware to better collect and make needed information available quickly and accurately. © 2016 Proceedings of the 2016 industrial and systems engineering Research Conference, ISERC 2016. All rights reserved.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

AImotion Challenge Results: a Framework for AirSim Autonomous Vehicles and Motion Replication

AImotion Challenge Results: a Framework for AirSim Autonomou...

引用

Computers and Automation (CompAuto), International Conference on

作者： Bruno J. Souza Lucas C. de Assis Dominik Rößle Roberto Z. Freire Daniel Cremers Torsten Schön Munir Georges Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil Control and Automation Eng. Department Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil Technische Hochschule Ingolstadt AImotion Bavaria Institute Ingolstadt Germany Department of Informatics Technical University of Munich Munich Germany

ISBN: (纸本)9781665481953

The use of simulation environments is becoming more significant in the development of autonomous cars, as it allows for the simulation of high-risk situations while also being less expensive. In this paper, we presented a framework that allows the creation of an autonomous vehicle in the AirSim simulation environment and then transporting the simulated movements to the TurtleBot. To maintain the car in the correct direction, computer vision techniques such as object detection and lane detection were assumed. The vehicle's speed and steering are both determined by Proportional-Integral-Derivative (PID) controllers. A virtual personal assistant was developed employing natural language processing to allow the user to interact with the environment, providing movement instructions related to the vehicle's direction. Additionally, the conversion of the simulator movements for a robot was implemented to test the proposed system in a practical experiment. A comparison between the real position of the robot and the position of the vehicle in the simulated environment was considered in this study to evaluate the performance of the algorithms.

关键词： Computer vision Lane detection Robot kinematics Atmospheric modeling Computational modeling Virtual environments Natural language processing

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：