检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Pacheco, Andre G.C. Krohling, Renato R. Graduate Program in Computer Science PPGI Federal University of Espírito Santo UFES Av. Fernando Ferrari 514 Vitória-ES Brazil Production Engineering Department Graduate Program in Computer Science PPGI Federal University of Espírito Santo UFES Av. Fernando Ferrari 514 Vitória-ES Brazil

Skin cancer is one of the most common types of cancer around the world. For this reason, over the past years, different approaches have been proposed to assist detect it. Nonetheless, most of them are based only on dermoscopy images and do not take into account the patient clinical information. In this work, first, we present a new dataset that contains clinical images, acquired from smartphones, and patient clinical information of the skin lesions. Next, we introduce a straightforward approach to combine the clinical data and the images using different well-known deep learning models. These models are applied to the presented dataset using only the images and combining them with the patient clinical information. We present a comprehensive study to show the impact of the clinical data on the final predictions. The results obtained by combining both sets of information show a general improvement of around 7% in the balanced accuracy for all models. In addition, the statistical test indicates significant differences between the models with and without considering both data. The improvement achieved shows the potential of using patient clinical information in skin cancer detection and indicates that this piece of information is important to leverage skin cancer detection systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

MATLAB-based analysis of labor dispatch and work distribution: An example involving caseworkers in central Taiwan

MATLAB-based analysis of labor dispatch and work distributio...

引用

2017 IEEE International Conference on Applied System Innovation, ICASI 2017

作者： Oh, Chin-Yu Hsu, Meng-Chueh Tsai, Chang-Ming Jhang, Jyun-Yao Chen, Yu-Ren Chen, Bo-Xiang Chen, Yi-Chung Teng, Chun-Wen Chen, Shu-Hui Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan Ph. D. Program of Business Feng Chia University Taichung40724 Taiwan Graduate Institute of Public Policy and social innovation Feng Chia University Taichung40724 Taiwan General Education Center Feng Chia University Taichung40724 Taiwan

ISBN: (纸本)9781509048977

The dispatching of labor and distribution of tasks among workers are important aspects of corporate operations. Labor dispatch refers to the dispatching of employees to meet with clients;however, dispatches commonly vary with time. This means that any analysis pertaining to labor dispatch and work distribution should also vary with time. In this study, MATLAB was used to analyze data from anonymous caseworkers in central Taiwan in order to identify relationships between the location of their offices and the homes of their clients. Our aim was to determine the rationality behind labor dispatch and work distribution. This led us to develop a novel method by which to dispatch labor in order to achieve a more equitable distribution of work. Simulations demonstrate the efficacy of the proposed scheme in improving labor dispatch and work distribution. © 2017 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Advancing Precision Aquaculture Through Big Data Analytics and Machine Learning in Canadian Fish Farming

Advancing Precision Aquaculture Through Big Data Analytics a...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Bravo, Francisco Amorim, Joana Amirkandeh, Melika Besharati Bodorik, Peter Cerqueira, Vitor Gomes, Nuno R.C. Korus, Jennie Oliveira, Mariana Parent, Marianne Pimentel, João Reilly, Derek Sclodnick, Tyler Grant, Jon Filgueira, Ramón Whidden, Christopher Universidad Adolfo Ibañez Facultad de Ingenieria y Ciencias Santiago Chile Dalhousie University Faculty of Computer Science Halifax Canada University of Porto Faculty of Engineering Portugal Barcelona Spain Innovasea Marine Systems Bedford Canada Charlottetown Canada Dalhousie University Department of Oceanography Halifax Canada Marine Affairs Program Dalhousie University Halifax Canada

ISBN: (纸本)9798331540081

The aquaculture industry faces significant challenges related to sustainability, productivity, and fish welfare. Key issues include managing environmental conditions, disease, pests, and data integration from various sensors and monitoring systems. The BigFish project aims to address these challenges through advanced analytics and machine learning, focusing on three case studies in Atlantic salmon farms: predicting oxygen levels, reducing sea lice infestations, and improving data interaction and visualization. Predictive models for oxygen levels and sea lice infestation, as well as natural language interfaces for data visualization, demonstrate the potential for improved decision-making and management practices in aquaculture. Early results indicate the effectiveness of these approaches, highlighting the importance of data-driven solutions in enhancing industry sustainability and productivity. © 2024 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE TESTING OF SHIPBOARD ELECTRONIC SYSTEMS

引用

NAVAL ENGINEERS JOURNAL 1993年第3期105卷 118-124页

作者： HARDER, G MARTIN, RA PE George Harder:is an electronics engineer for Naval Undersea Warfare Center Detachment Norfolk's Electromagnetic Engineering Branch located at the Norfolk Shipboard Electronic Systems Evaluation Facility (SESEF) site. He is responsible for fleet electromagnetic readiness (FEMR) inspections on board Navy ships and provides computer programming support to SESEF. Mr. Harder has a bachelor of science degree in electrical engineering from the University of Florida and has qualified for his professional engineering license in the state of Virginia. Robert A. Martin:is a supervisor electronics engineer employed by the Naval Undersea Warfare Center Detachment Norfolk. He functions as the branch head for the Electromagnetic Engineering Office which is responsible for the operation of the Norfolk Shipboard Electronic Systems Evaluation Facility (SESEF) and the Fleet Electromagnetic Readiness (FEMR) Program. Mr. Martin received a bachelor of science degree in electrical engineering from the University of Akron.

Performance evaluation of shipboard electronic systems entails debugging the systems in a laboratory environment, placing them in service and relving on svstem operators to provide feedback. General testing can be performed at selected sites by system designers, but each site where equipment is to be installed can offer unique problems. It is impossible to predict all the scenarios. Unique problems are more the rule than the exception when equipment is destined for Navy ships. Ship deployments make for difficult logistics when sending test teams to evaluate system failures. So, out of necessity, if newly installed equipment receives the proper inputs and generates the proper outputs, it is accepted and becomes the sailor's responsibilitv to maintain. In cases where documentation is ambiguous or incomplete, it is left to the sailor's ingenuity to continue testing and training on equipment. This is generallv obtained through computer simulations and back-to-back testing which can provide results for ideal conditions, but does not take the dynamics of interference into account. Remote site testing is the only way to get a true representation of equipment performance and training problems. Electronic system operators on board Navy vessels are fortunate, thev have help. There exists an organization available near major naval ports worldwide whose existence is to test electronic systems performance. The testing utilizes electronic systems as they would normally be configured for operations. This organization is the Shipboard Electronic Svstem Evaluation Facility (SESEF).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discovering Flow Anomalies: A SWEET Approach

Discovering Flow Anomalies: A SWEET Approach

引用

IEEE International Conference on Data Mining (ICDM)

作者： James M. Kang Shashi Shekhar Christine Wennen Paige Novak Department of Computer Science University of Minnesota MN USA Graduate Program in Water Resources Science University of Minnesota MN USA Department of Civil Engineering University of Minnesota MN USA

Given a percentage-threshold and readings from a pair of consecutive upstream and downstream sensors, flow anomaly discovery identifies dominant time intervals where the fraction of time instants of significantly mis-matched sensor readings exceed the given percentage-threshold. Discovering flow anomalies (FA) is an important problem in environmental flow monitoring networks and early warning detection systems for water quality problems. However, mining FAs is computationally expensive because of the large (potentially infinite) number of time instants of measurement and potentially long delays due to stagnant (e.g. lakes) or slow moving (e.g. wetland) water bodies between consecutive sensors. Traditional outlier detection methods (e.g. t-test) are suited for detecting transient FAs (i.e., time instants of significant mis-matches across consecutive sensors) and cannot detect persistent FAs (i.e., long variable time-windows with a high fraction of time instant transient FAs) due to a lack of a pre-defined window size. In contrast, we propose a Smart Window Enumeration and Evaluation of persistence-Thresholds (SWEET) method to efficiently explore the search space of all possible window lengths. Computation overhead is brought down significantly by restricting the start and end points of a window to coincide with transient FAs, using a smart counter and efficient pruning techniques. Experimental evaluation using a real dataset shows our proposed approach outperforms Nainodotve alternatives.

关键词： Birth disorders Pollution measurement Water pollution Sensor phenomena and characterization Rivers Water resources Lakes Condition monitoring Contamination Petroleum

来源：评论

学校读者我要写书评

暂无评论

Prediction of the risk types of human papillomaviruses by Support Vector Machines

Prediction of the risk types of human papillomaviruses by Su...

引用

8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence

作者： Joung, Je-Gun Sok June, O. Zhang, Byoung-Tak Biointelligence Laboratory Graduate Program in Bioinformatics Seoul National University Seoul 151-742 Korea Republic of Seoul National University Seoul 151-742 Korea Republic of School of Computer Science and Engineering Seoul National University Seoul 151-742 Korea Republic of Department of Pharmacology College of Medicine Inje University Busan 614-735 Korea Republic of

ISBN: (纸本)3540228179

Infection by high-risk human papillomaviruses (HPVs) is associated with the development of cervical cancers. Classification of risk types is important to understand the mechanisms in infection and to develop novel instruments for medical examination such as DNA microarrays. In this paper, we classify the risk type of HPVs by using the protein sequences. Our approach is based on the hidden Markov model and the Support Vector Machines. The former searches informative subsequence positions and the latter computes efficiently to classify protein sequences. In the experiments, the proposed classifier was compared with previous methods in accuracy and F-cost, also the prediction result of four unknown types is presented. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

BLISS: Using Robot in Learning Intervention to Promote Social Skills for Autism Therapy 2016

BLISS: Using Robot in Learning Intervention to Promote Socia...

引用

Proceedings of the international Convention on Rehabilitation engineering & Assistive Technology

作者： Settapon Santatiwongchai Boonserm Kaewkamnerdpong Wisanu Jutharee Kajornvut Ounjai Department of Computer Engineering Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand Biological Engineering Program Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand Institute of Field Robotics King Mongkut's University of Technology Thonburi Bangkok Thailand

Robots have been introduced for autism therapy. However, most robotics studies focused on providing means of practice with dyadic interaction activities. To live in the society, autistic children need social interaction skills. In this study, we developed a mobile robot with non-threatening facial expression and investigated the potential of using this robot in triadic interaction activity for autism therapy to promote social interaction in children with autism. From the experiment that subjects play a picture matching game, it can be indicated that the robot can attract children with autism. Subjects can learn and understand the rule with their parents' participation. They could learn the name of the object in the picture that they do not know before as well. Some parents found that the robot could aid them in training their children. Autism specialists discovered some capabilities that they have never observed from the subjects in their therapeutic sessions. Therefore, this robot could be useful for autism specialists in finding aptitudes of children with autism in order to provide suitable intervention for effective therapy. This robot could be helpful for parents/caregivers in conducting therapeutic activities at home (continuing after therapeutic session with specialists) for even more effective therapy.

关键词： Mobile Robot Autism Non-Humanoid Robot Social Interaction

来源：评论

学校读者我要写书评

暂无评论

Investigating the Link between User Stories and Documentation Debt on Software Projects

Investigating the Link between User Stories and Documentatio...

引用

International Conference on Information Technology: New Generations (ITNG)

作者： Henrique F. Soares Nicolli S.R. Alves Thiago S. Mendes Manoel Mendonça Rodrigo O. Spínola Graduate Program in Systems and Computer at Salvador University Salvador Brazil Fraunhofer Project Center for Software and System Engineering at UFBA Salvador Brazil Federal Institute of Bahia - IFBA Salvador Brazil

Technical debt is a metaphor that describes the effect of immature artefacts in software development. One of its types is documentation debt, which can be identified by locating missing, inadequate or incomplete artefacts in software projects. Nowadays, we can observe more organizations using agile methods to support their activities. In particular, the use of user stories reduces the focus on requirement specification tasks and, as a consequence, creates difficulties that need to be overcame by the development team. In order to investigate these difficulties and assess whether they create a favourable scenario for incurring documentation debt, this paper presents the results of a literature review and an exploratory study. The results from both studies allowed us to identify a list of causes that can lead the development team to incur documentation debt when working with agile requirements. This is an important step in order to manage the technical debt from a preventive perspective.

关键词： Software Documentation Bibliographies Protocols Libraries Software engineering Estimation

来源：评论

学校读者我要写书评

暂无评论

Predicting probability of mortality in the neonatal intensive care unit

Predicting probability of mortality in the neonatal intensiv...

引用

28th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBS'06

作者： Dajie, Zhou Frize, Monique IEEE Program of Systems Science University of Ottawa 800 King Edward Ottawa Ont. K1N 6N5 Canada Department of Systems and Computer Engineering Carleton University University of Ottawa 1125 Colonel By Drive Ottawa Ont. K1S 5B5 Canada

ISBN: (纸本)1424400325

Artificial neural networks can be trained to predict outcomes in a neonatal intensive care unit (NICU). This paper expands on past research and shows that neural networks trained by the maximum likelihood estimation criterion will approximate the 'a posteriori probability' of NICU mortality. A gradient ascent method for the weight update of three-layer feed-forward neural networks was derived. The neural networks were trained on NICU data and the results were evaluated by performance measurement techniques, such as the Receiver Operating Characteristic Curve and the Hosmer-Lemeshow test The resulting models applied as mortality prognostic screening tools are presented. © 2006 IEEE.

关键词： Neonatal monitoring

来源：评论

学校读者我要写书评

暂无评论

Broadband delay lines and nonreciprocal resonances in unidirectional waveguides

引用

Physical Review B 2019年第2期100卷 020303(R)-020303(R)页

作者： Sander A. Mann Dimitrios L. Sounas Andrea Alù Photonics Initiative Advanced Science Research Center City University of New York New York 10031 USA Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 USA Department of Electrical and Computer Engineering Wayne State University Detroit Michigan 48202 USA Physics Program Graduate Center City University of New York New York 10016 USA Department of Electrical Engineering City College of The City University of New York New York 10031 USA

Slow-light waveguides play an important role in optical pulse delay lines, but are practically limited by disorder-induced attenuation. Topological edge states, unidirectional and robust against disorder, have been proposed as a way to address this issue. Here, we study the transmission phase and pulse propagation dynamics through unidirectional systems in the presence of strong discontinuities. We first investigate a magnetically biased slow-light channel, demonstrating broadband pulse delays in small footprints. We uncover a nonreciprocal etalonlike resonance, sustained by propagating forward and evanescent backward modes, affecting pulse propagation and delay. We then show the existence of these features in topologically protected edge states, highlighting their universality. These exotic resonances provide a new degree of freedom in unidirectional waveguides to engineer their response, and they may therefore prove highly useful in various nanophotonic applications.

关键词： Plasmonics Topological effects in photonic systems Topological insulators Topological materials Waveguides Lorentz symmetry

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：