检索结果-内蒙古大学图书馆

IFAC-PapersOnLine 2019年第11期52卷 85-90页

作者： Ricardo Massao Kagami Gilberto Reynoso-Meza Eduardo A.P. Santos Roberto Zanetti Freire Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR) Brazil

The Proportional-Integral-Derivative (PID) controller is widely used in industrial applications. In order to evaluate the performance of distinct types of controllers, several benchmark systems are available in the specialized literature. In this work, an alternative approach to tune PID controllers based on the Competition Over Resources (COR) metaheuristic optimization algorithm and TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) method is proposed to solve a vapor compression refrigeration system problem, which is a benchmark control challenge. The proposed technique considered the normalization of multiple cost functions to simplify the selection of two PIDs’ parameters, reducing the need of understanding the influences of cost functions variations in complex problems. The proposed controllers outperformed the base line controllers, providing a performance index 68.39% better than the original approach. Finally, the proposed method was compared with other tuning methods.

关键词： Competition over resources algorithm controller tuning multi-objective problem multivariable control

A dual-mode deep transfer learning (D2TL) system for breast cancer detection using contrast enhanced digital mammograms

学校读者我要写书评

暂无评论

IISE Transactions on Healthcare systems engineering 2019年第4期9卷 357-370页

作者： Wang, Kun Patel, Bhavika K. Wang, Lujia Wu, Teresa Zheng, Bin Li, Jing Industrial Engineering Program at School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe United States Department of Radiology Mayo Clinic in Arizona Scottsdale United States School of Electrical and Computer Engineering College of Engineering University of Oklahoma Norman United States

Full-field digital mammography (FFDM) and magnetic resonance imaging (MRI) are gold-standard techniques for breast cancer detection. The newly contrast-enhanced digital mammography (CEDM) integrates the complementary strengths of FFDM and MRI, and is being incorporated into the practice of leading institutions. The current clinical practice using CEDM is sub-optimal because it is primarily based on clinicians' trained eyes. Automated diagnostic systems under the conventional machine learning paradigm suffer from drawbacks, such as the requirement for precise segmentation, extraction of shallow features that do not suffice for diagnostic images, and adoption of a sequential design without a global objective. We propose a deep learning (DL)-empowered diagnostic system using CEDM, the core of which is a novel dual-mode deep transfer learning (D2TL) model. The proposed system is innovative in several aspects, including (1) a dual-mode deep architecture design;(2) use of transfer learning to facilitate robust model estimation under small sample-size;(3) development of visualization techniques to help interpret the model results and facilitate inter- and intra-tumor malignancy quantification;and (4) minimization of human bias. We apply D2TL to classify benign vs. malignant tumors using the CEDM data collected from the Mayo Clinic in Arizona. D2TL outperforms competing models and approaches. © 2019, © 2019 “IISE”.

关键词： breast cancer Deep learning imaging-based diagnosis transfer learning

A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kung, Pou-Chun Wang, Chieh-Chih Lin, Wen-Chieh Graduate Degree Program of Robotics National Chiao Tung University Hsinchu Taiwan Department of Electrical and Computer Engineering National Chiao Tung University The Mechanical and Mechatronics Systems Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan Department of Computer Science National Chiao Tung University Hsinchu Taiwan

Existing radar sensors can be classified into automotive and scanning radars. While most radar odometry (RO) methods are only designed for a specific type of radar, our RO method adapts to both scanning and automotive radars. Our RO is simple yet effective, where the pipeline consists of thresholding, probabilistic submap building, and an NDT-based radar scan matching. The proposed RO has been tested on two public radar datasets: the Oxford Radar RobotCar dataset and the nuScenes dataset, which provide scanning and automotive radar data respectively. The results show that our approach surpasses state-of-the-art RO using either automotive or scanning radar by reducing translational error by 51% and 30%, respectively, and rotational error by 17% and 29%, respectively. Besides, we show that our RO achieves centimeter-level accuracy as lidar odometry, and automotive and scanning RO have similar accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical radar

Corrigendum to “Behavioral aspects of safety culture: Identification of critical safety-related behaviors of motorcyclists in Indonesia's urban areas via the application of behavioral-based safety programs” [IATSS Research journal 46 (October 2022) 353–369]

学校读者我要写书评

暂无评论

IATSS Research 2022年第4期46卷 623-623页

作者： Andrijanto Makoto Itoh Felix Sandro Sianipar Risk Engineering Department Graduate School of Systems and Information Engineering University of Tsukuba Ibaraki 305-8573 Japan Industrial Engineering Program Study Faculty of Engineering Universitas Kristen Maranatha Bandung 40164 Indonesia Faculty of Engineering Information and Systems University of Tsukuba Ibaraki 305-8573 Japan

Consumer behavior in clothing industry and its relationship with open innovation dynamics during the covid-19 pandemic

学校读者我要写书评

暂无评论

Journal of Open Innovation: Technology, Market, and Complexity 2021年第4期7卷 211页

作者： Ong, Ardvin Kester S. Cleofas, Maria Arielle Prasetyo, Yogi Tri Chuenyindee, Thanatorn Young, Michael Nayat Diaz, John Francis T. Nadlifatin, Reny Redi, Anak Agung Ngurah Perwira School of Industrial Engineering and Engineering Management Mapúa University 658 Muralla St. Manila 1002 Philippines School of Graduate Studies Mapúa University 658 Muralla St. Intramuros Manila 1002 Philippines Department of Industrial Engineering Faculty of Engineering University of Santo Tomas Manila 1015 Philippines Navaminda Kasatriyadhiraj Royal Thai Air Force Academy Bangkok 10220 Thailand Department of Finance and Accounting Asian Institute of Management Manila 1229 Philippines Department of Information Systems Institut Teknologi Sepuluh Nopember Kampus ITS Sukolilo Surabaya 60111 Indonesia Industrial Engineering Department BINUS Graduate Program—Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia

The fashion industry has been continuously growing over the years, yet it is an industry that was greatly affected by the COVID-19 pandemic. The purpose of the study was to determine the factors affecting buying behavior of Filipinos towards clothing apparel during the COVID-19 pandemic. There were 457 respondents who voluntarily participated and answered an online questionnaire. Structural equation modeling (SEM) indicated that marketing mix was found to have significant effects on attitude, subjective norm, and perceived behavioral control, which subsequently led to purchase intention. In addition, the COVID-19 latent variable was found to have significant effects on self-perceived severity and self-efficacy, which subsequently led to attitude and purchase intention. Interestingly, marketing mix was found to have the highest effect on actual purchase, which indicated that innovation dynamics are the keys for the buying behavior. The SEM construct can be applied to determine the clothing apparel buying behaviors of consumers in other countries, particularly during the COVID-19 pandemic. Finally, advertisements, promotions, sales, and health safety should be considered as innovation dynamics during the COVID-19 pandemic. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

关键词： Consumer behavior COVID-19 pandemic Fashion industry Innovation dynamic Open innovation Protection motivation theory Theory of planned behavior

Ontology and Rules for Characterization of Sensors and Actuators Devices in AADL Models

学校读者我要写书评

暂无评论

Ontology and Rules for Characterization of Sensors and Actua...

Brazilian Symposium on computing System engineering (SBESC)

作者： Diego Camara Sales Cristian Koliver Leandro Buss Becker UFSC Florianopolis SC Brazil Federal Institute of Amazon - IFAM Campus Manaus Distrito Industrial AM Brazil Graduate Program on Automation Systems Engineering (PGEAS) UFSC Florianopolis SC Brazil

ISBN: (数字)9781728182865

ISBN: (纸本)9781728182872

This paper presents a set of ontologies to organize concepts, categories, properties, and relationships that are typically used by designers for characterizing sensing and actuation devices that compose a given system architecture (SA). From the characterization of such devices, modeling can be done using the Architecture Analysis and Design Language (AADL). AADL supports modeling and analysis of functional and nonfunctional properties to evaluate quality attributes from ontology models. The paper also proposes an AADL property set that can be applied to sensors and actuators (S&A), based on previous researches with ontologies applied to sensor networks. Specific characteristics are provided to describe systems' quality attributes. This aims to be used for analyzing the designed architecture, and also its probable future evolution.

关键词： Ontologies Actuators Software Sensor phenomena and characterization Computer architecture Standards ISO Standards

Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis: A review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mao, Lingchao Wang, Hairong Hu, Leland S. Tran, Nhan L. Canoll, Peter D. Swanson, Kristin R. Li, Jing H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA30332 United States Mathematical NeuroOncology Lab Precision Neurotherapeutics Innovation Program Mayo Clinic Arizona 5777 East Mayo Blvd Support Services Building Suite 2-700 PhoenixAZ85054 United States Department of Radiology Mayo Clinic Arizona 5777 E. Mayo Blvd PhoenixAZ85054 United States School of Computing Informatics and Decision Systems Engineering Arizona State University 699 S Mill Ave TempeAZ85281 United States Department of Neurosurgery Mayo Clinic Arizona 5777 E. Mayo Blvd PhoenixAZ85054 United States Department of Cancer Biology Mayo Clinic Arizona 5777 E. Mayo Blvd PhoenixAZ85054 United States Department of Pathology and Cell Biology Columbia University Medical Center 630 West 168th Street New YorkNY10032 United States

Cancer remains one of the most challenging diseases to treat in the medical field. Machine learning has enabled in-depth analysis of rich multi-omics profiles and medical imaging for cancer diagnosis and prognosis. Despite these advancements, machine learning models face challenges stemming from limited labeled sample sizes, the intricate interplay of high-dimensionality data types, the inherent heterogeneity observed among patients and within tumors, and concerns about interpretability and consistency with existing biomedical knowledge. One approach to surmount these challenges is to integrate biomedical knowledge into data-driven models, which has proven potential to improve the accuracy, robustness, and interpretability of model results. Here, we review the state-of-the-art machine learning studies that adopted the fusion of biomedical knowledge and data, termed knowledge-informed machine learning, for cancer diagnosis and prognosis. Emphasizing the properties inherent in four primary data types including clinical, imaging, molecular, and treatment data, we highlight modeling considerations relevant to these contexts. We provide an overview of diverse forms of knowledge representation and current strategies of knowledge integration into machine learning pipelines with concrete examples. We conclude the review article by discussing future directions to advance cancer research through knowledge-informed machine *** Codes 92B99 Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge representation

Mine-to-client planning with Markov Decision Process

学校读者我要写书评

暂无评论

Mine-to-client planning with Markov Decision Process

European Control Conference (ECC)

作者： João Marcelo Leal Gomes Leite Edilson F. Arruda Laura Bahiense Lino G. Marujo Industrial Engineering Program Alberto Luiz Coimbra Institute – Graduate School and Research in Engineering Federal University of Rio de Janeiro Rio de Janeiro Brazil Systems Engineer and Computer Science Program Alberto Luiz Coimbra Institute – Graduate School and Research in Engineering Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (数字)9783907144022

ISBN: (纸本)9781728188133

This works presents an innovative application of Markov Decision Process (MDP) to a medium-term mining logistics planning problem considering the mine-to-client supply chain. We implemented three distinct algorithms based on state-of-the-art approaches to solve large-scale problems, and compared their results. Furthermore, we combined all three variants in a single novel algorithm that attained fast convergence and may be an alternative to circumvent the curse of dimensionality underlying large scale problems.

关键词： Supply chains Planning Uncertainty Markov processes Computational modeling

Short-term forecasting of Amazon rainforest fires based on ensemble decomposition model

学校读者我要写书评

暂无评论

arXiv 2020年

作者： da Silva, Ramon Gomes Ribeiro, Matheus Henrique Dal Molin Mariani, Viviana Cocco dos Santos Coelho, Leandro Pontifical Catholic University of Parana Industrial & Systems Engineering Graduate Program Curitiba Brazil Federal Technological University of Parana Department of Mathematics Pato Branco Brazil Federal University of Parana Dept. of Electrical Eng. Curitiba Brazil Pontifical Catholic University of Parana Mechanical Engineering Graduate Program Curitiba Brazil

Accurate forecasting is important for decision-makers. Recently, the Amazon rainforest is reaching record levels of the number of fires, a situation that concerns both climate and public health problems. Obtaining the desired forecasting accuracy becomes difficult and challenging. In this paper were developed a novel heterogeneous decomposition-ensemble model by using Seasonal and Trend decomposition based on Loess in combination with algorithms for short-term load forecasting multimonth-ahead, to explore temporal patterns of Amazon rainforest fires in Brazil. The results demonstrate the proposed decomposition-ensemble models can provide more accurate forecasting evaluated by performance measures. Diebold-Mariano statistical test showed the proposed models are better than other compared models, but it is statistically equal to one of them. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision making

Radar Occupancy Prediction with Lidar Supervision while Preserving Long-Range Sensing and Penetrating Capabilities

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kung, Pou-Chun Wang, Chieh-Chih Lin, Wen-Chieh The Graduate Degree Program of Robotics National Yang Ming Chiao Tung University Hsinchu Taiwan The Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Taiwan The Mechanical and Mechatronics Systems Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan The Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan

Radar shows great potential for autonomous driving by accomplishing long-range sensing under diverse weather conditions. But radar is also a particularly challenging sensing modality due to the radar noises. Recent works have made enormous progress in classifying free and occupied spaces in radar images by leveraging lidar label supervision. However, there are still several unsolved issues. Firstly, the sensing distance of the results is limited by the sensing range of lidar. Secondly, the performance of the results is degenerated by lidar due to the physical sensing discrepancies between the two sensors. For example, some objects visible to lidar are invisible to radar, and some objects occluded in lidar scans are visible in radar images because of the radar's penetrating capability. These sensing differences cause false positive and penetrating capability degeneration, respectively. In this paper, we propose training data preprocessing and polar sliding window inference to solve the issues. The data preprocessing aims to reduce the effect caused by radar-invisible measurements in lidar scans. The polar sliding window inference aims to solve the limited sensing range issue by applying a near-range trained network to the long-range region. Instead of using common Cartesian representation, we propose to use polar representation to reduce the shape dissimilarity between long-range and near-range data. We find that extending a near-range trained network to long-range region inference in the polar space has 4.2 times better IoU than in Cartesian space. Besides, the polar sliding window inference can preserve the radar penetrating capability by changing the viewpoint of the inference region, which makes some occluded measurements seem non-occluded for a pretrained network. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical radar