检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Ferreira, Mafalda Falcão Camacho, Rui Teixeira, Luís F. Doctoral Program in Informatics Engineering Faculty of Engineering University of Porto INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Department of Informatics Engineering Faculty of Engineering University of Porto Porto - Portugal

Cancer is still one of the most devastating diseases of our time. One way of automatically classifying tumor samples is by analyzing its derived molecular information (i.e., its genes expression signatures). In this work, we aim to distinguish three different types of cancer: thyroid, skin, and stomach. For that, we compare the performance of a Denoising Autoencoder (DAE) used as weight initialization of a deep neural network. Although we address a different domain problem in this work, we have adopted the same methodology of Ferreira et al.. In our experiments, we assess two different approaches when training the classification model: (a) fixing the weights, after pre-training the DAE, and (b) allowing fine-tuning of the entire classification network. Additionally, we apply two different strategies for embedding the DAE into the classification network: (1) by only importing the encoding layers, and (2) by inserting the complete autoencoder. Our best result was the combination of unsupervised feature learning through a DAE, followed by its full import into the classification network, and subsequent fine-tuning through supervised training, achieving an F1 score of 98.04% ± 1.09 when identifying cancerous thyroid samples. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Risk profile for E-Rapor services for public high school

引用

AIP Conference Proceedings 2024年第1期3165卷

作者： Dinar Mutiara Kusumo Nugraheni Tamara Tamara Andi Kurniawan Nugroho Doctoral Program in Information Systems School of Postgraduate Studies Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia Department of Electrical Engineering Universitas Semarang Jl. Soekarno-Hatta Tlogosari Semarang Jawa Tengah Indonesia

The Indonesian government has implemented E-Rapor to be employed in Indonesia since 2016. During 2016 until 2022 the usage of E-Rapor has identified some risk issues from the school perspective. Therefore, this research aims to identify the risk of the usage of E-Rapor. The research method for this study is to use a case in one of the public high schools in Jakarta, Indonesia. The usage of E-Rapor started in 2016. The E-Rapor system’s objective is to give easy access to students’ result data (evaluation card) to the central government (DAPODIK), school principals, teachers, and student’s parents. However, the implementation of the E-Rapor system has created some risk However, implementing E-Rapor in Schools has created issues among teachers. Therefore, this research proposes a study to identify the risk of the E-Raport system adopting COBIT 2019. The risk profiles are identified only on the governing E-Rapor in School. The case study research was conducted in SMAN 61 Jakarta. The result shows that types of risks that occur in High School are lack of IT Expertise, lack of Standard Operating Procedures, and issues with E-Rapor usage. After recognizing the risk, this study also proposes a strategy for overcoming the risk. The High School needs to be concerned on the area of Managing Human Resources (APO7), Domain DSS03 (Managing Issues), and Domain DSS05 (Managing Security Services)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influences of key factors on river water quality in urban and rural areas: A review

引用

Case Studies in Chemical and Environmental engineering 2023年 8卷

作者： Anh, Nguyen Tuan Can, Le Duy Nhan, Nguyen Thi Schmalz, Britta Luu, Tran Le Doctoral Training Program in Sustainable Urban Development Vietnamese German University Viet Nam Nong Lam University of Ho Chi Minh City Gia Lai Campus Viet Nam Department of Mechatronics and Sensor Systems Technology Vietnamese German University Vanh Dai 4 Quarter 4 Thoi Hoa Ward Ben Cat Binh Duong Province Viet Nam Master Program in Water Technology Reuse and Management Vietnamese German University Vanh Dai 4 Quarter 4 Thoi Hoa Ward Ben Cat Binh Duong Province Viet Nam Chair of Engineering Hydrology and Water Management Technical University of Darmstadt Germany

Water quality in rivers is deteriorating in urban and rural areas due to natural and anthropogenic factors. Understanding how changes and factors affect river water quality is crucial for managing water quality in river basins. This review focuses on analyzing key factors affecting water quality, and the temporal and spatial variations of water quality in rivers flowing in rural and urban areas. Natural processes such as weathering of rocks, evapotranspiration, atmospheric deposition, climate change, and natural disasters cause changes in the quality of river water. Anthropogenic factors could stem from industrial effluents, domestic activities, and agricultural activities such as the application of fertilizers, manures, pesticides, animal husbandry activities, irrigation practices, deforestation, and aquaculture. The seasonal variations in river water quality are discussed, and land use or cover could affect water quality parameters in a negative or positive way. In addition to traditional contaminants such as biodegradable organic matter, heavy metals, and pathogens, emerging and persistent pollutants such as organochlorine pesticides (OCPs), polycyclic aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), perfluoroalkyl and polyfluoroalkyl substances (PFASs), and phamaceutic active compounds (PhACs) has been found in many rivers, which could pose a threat to human and animal health. The comparison of key factors and parameters in urban and rural areas is also clarified, which provides authorities and policymakers with a deep understanding and supports decision-making in sustainable water management. © 2023 The Authors

关键词： River basin River water quality Rural areas Urban areas Water pollution

来源：评论

学校读者我要写书评

暂无评论

Examining associations with on-time performance and identifying relevant road network, demographic, socioeconomic and land use characteristics within the bus stop vicinity for proactive and reliable public transportation system planning

引用

Multimodal Transportation 2023年第4期2卷

作者： Mishra, Raunak Pulugurtha, Srinivas S. Mathew, Sonu Former Graduate Student of Infrastructure and Environmental Systems Ph.D. Program The University of North Carolina at Charlotte 9201 University City Boulevard Charlotte 28223-0001 NC United States Professor & Research Director of Civil & Environmental Engineering Department Director of Infrastructure Design Environment and Sustainability (IDEAS) Center The University of North Carolina at Charlotte 9201 University City Boulevard Charlotte 28223-0001 NC United States Post-Doctoral Researcher of IDEAS Center The University of North Carolina at Charlotte 9201 University City Boulevard Charlotte 28223-0001 NC United States

Growing population, rapid urbanization, and increasing travel demand emphasize the need for reliable public transportation systems and sustainable transportation planning. A reliable bus service fosters a more significant, satisfied, and committed base of users. This research focuses on examining the association between on-time performance (OTP) and road network, demographic, socioeconomic, and land use characteristics to identify relevant external factors for proactive and reliable public transportation system planning. The analysis was conducted at a bus stop level. Bus arrival/departure data from the Charlotte Area Transit System (CATS) was obtained. The road network, demographic, socioeconomic, and land use characteristics were captured within 0.25-mile and 0.50-mile buffers. Pearson correlation analysis was conducted to understand the association between OTP and road network, demographic, socioeconomic, and land use characteristics by day of the week and time of the day. The results show that OTP is associated with external factors such as the number of signalized or cul-de-sac/dead-end intersections, number of lanes, network density, population, income (median and total), and land use types related to residential and commercial/employment purposes within the bus stop vicinity. The findings provide vital insights for transit agencies to enhance scheduling, service and maximize benefits, effectively utilize available resources, plan, and provide equitable services to all riders. © 2023 The Author(s)

关键词： Bus stop Demographic Land use On-time performance Pearson correlation Road network Socioeconomic Transit

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for modelling infectious disease epidemics

引用

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. © Springer Nature Limited 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of traffic congestion based on time series dataset number of vehicles using neural network algorithm

引用

AIP Conference Proceedings 2024年第1期2982卷

作者： Prasetyo Wibowo Yunanto Rahmat Gernowo Oky Dwi Nurhayati Doctoral Program of Information System Diponegoro University Jl. Imam Bardjo SH No.5 Semarang Indonesia Information Systems and Technology Universitas Negeri Jakarta Jl. Rawamangun Muka Jakarta Indonesia Department of Physics Diponegoro University Jl. Prof. H. Soedarto Semarang Indonesia Computer Engineering Department Diponegoro University Jl. Prof. H. Soedarto Semarang Indonesia

The increasing number of vehicles that was not accompanied by an adequate road infrastructure readiness causes traffic jams. Traffic jams often occur repeatedly every day, especially at certain times, such as when people are going to and from work. The same traffic jams can also occur at the beginning or the end of the week; this usually repeats every week. As a result, if the congestion dataset is known, the repeating traffic congestion for daily and weekly congestion can be anticipated. In this study, traffic congestion predictions are modeled using the Neural Network Algorithm based on traffic congestion data collected within 24 hours for one to two weeks. The parameters used in optimizing Neural Network performance are learning rate, momentum, and epochs (training cycles). Based on these experiments, the Neural Network Algorithm successfully modeled traffic density patterns which are recurring congestion patterns, with quite good results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AISI SAE 1045 steel tenacity variation evaluation subjected to corrosion process by chloride using the Charpy pendulum machine

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1154卷

作者： C G Cárdenas-Arias A D Rincón-Quintero C L Sandoval-Rodriguez B E Tarazona-Romero J S Muñoz-Gutierrez J L Jímenez-Rueda O A Acosta-Cárdenas Design and materials research group (DIMAT) Energy Systems Automation and Control Research Group (GISEAC) Electromechanical Engineering Faculty of Natural Sciences and Engineering Unidades Tecnológicas de Santander (UTS) Bucaramanga Colombia Doctoral Program in Engineering of Materials and Sustainable Processes University of the Basque Country UPV/EHU Bilbao Spain Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV / EHU) Engineer Torres Quevedo Square 1 Bilbao BI Spain Doctoral Program in Electronic and Communications Department of Communications Engineering University of the Basque Country UPV/EHU Bilbao Spain

The steel corrosion affecting study is important for industries and companies as well as for manufacturers of these material types. AISI SAE 1045 steel was used in this study, due to its frequent use. A specimen's series were prepared which were induced in an aggressive environment with the aim of degenerative process accelerating by increasing the material corrosion impact by altering the material mechanical properties. 15 specimens were exposed to the fog bank chamber, likewise 15 specimens in saline immersion chamber all with different exposure times 15. 30, and 45 days, subsequently the specimens are the impact test subjected to by the method of Charpy obtaining the tenacity value. To determine these values, the ASTM E23, ASTM A673 and ASTM E739 standards were used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generation and Capture of Electric Energy Using Piezoelectric Materials: A Review

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1154卷

作者： A D Rincón-Quintero C L Sandoval-Rodriguez N D Zanabria-Ortigoza C G Cárdenas-Arias J G Ascanio-Villabona M A Durán-Sarmiento Design and materials research group (DIMAT) Automation and Control Energy Systems Research Group (GISEAC) Electromechanical engineering Faculty of Natural Sciences and Engineering Unidades Tecnológicas de Santander (UTS) Calle de los estudiantes No 9-82 680005 Bucaramanga Colombia Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country UPV/EHU 48013 Bilbao Spain Doctoral Program in Electronic and Communications Department of Communications Engineering University of the Basque Country UPV/EHU 48013 Bilbao Spain Doctoral Program in Engineering of Materials and Sustainable Processes University of the Basque Country UPV/EHU 48013 Bilbao Spain

Piezoelectricity comes as a principle of transformation of mechanical energy into electrical energy, it is limited in terms of investment, time and research, due to this fact, the need arises to be able to innovate with data collection on the most used models to collect and generate electrical energy. In this research, the literature regarding the generation and collection of electrical energy using piezoelectric materials was analyzed, from this analysis, fifty innovative articles were determined in the last three years, which were reflected in a data matrix, in which It presents the generation and collection element, the applications, and shows the performance in terms of power or voltage that the prototypes supply. With the results of the table, a condensed panorama of current data is obtained, about the most used and outstanding of this form of little-used energy, but which is a competent and efficient alternative for the generation of electricity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting online item-choice behavior: A shape-restricted regression approach

arXiv

引用

arXiv 2020年

作者： Nishimura, Naoki Sukegawa, Noriyoshi Takano, Yuichi Iwanaga, Jiro Graduate School of Systems and Information Engineering University of Tsukuba Ibaraki305-8577 Japan Recruit Lifestyle Co. Ltd. Tokyo100-6640 Japan Department of Information and Computer Technology Tokyo University of Science Tokyo125-8585 Faculty of Engineering Information and Systems University of Tsukuba Ibaraki305-8577 Doctoral Program in Policy and Planning Sciences University of Tsukuba Ibaraki305-8577 Erdos Inc. Kanagawa222-0033

This paper examines the relationship between user pageview (PV) histories and their item-choice behavior on an e-commerce website. We focus on PV sequences, which represent time series of the number of PVs for each user-item pair. We propose a shape-restricted optimization model that accurately estimates item-choice probabilities for all possible PV sequences. This model imposes monotonicity constraints on item-choice probabilities by exploiting partial orders for PV sequences, according to the recency and frequency of a user's previous PVs. To improve the computational efficiency of our optimization model, we devise efficient algorithms for eliminating all redundant constraints according to the transitivity of the partial orders. Experimental results using real-world clickstream data demonstrate that our method achieves higher prediction performance than that of a state-of-the-art optimization model and common machine learning methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Text data labeling process for semi-supervised learning modeling

引用

AIP Conference Proceedings 2024年第1期3165卷

作者： Ahmad Abdul Chamid Widowati Widowati Retno Kusumaningrum Doctoral Program in Information Systems School of Postgraduate Studies Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia Department of Informatics Engineering Faculty of Engineering Muria Kudus University Jl. Lingkar Utara UMK Gondangmanis Kudus 59327 Indonesia Department of Mathematics Faculty of Science and Mathematics Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Jl. Prof Sudarto S.H. Tembalang Semarang 50275 Indonesia

To develop a semi-supervised learning model, it is necessary to have a little labeled data and a lot of unlabeled data. The data labeling process requires great effort and must involve experts. In the process of labeling text data requires a linguist to do the labeling. In this study using text data in the form of marketplace user reviews, in general the data is still dirty and data preprocessing needs to be done. The data preprocessing techniques applied are normalization, tokenization, stopword removal, and stemming. After the data goes through the preprocessing stage, labeling is carried out by involving more than one linguist. The results of the labeling that have been carried out by linguists will be carried out a consistency test process by applying the Cohen Kappa method. The data that has been labeled by 2 linguists is 820 data, after the consistency test is obtained the delivery aspect with a kappa value of 1, the service aspect with a kappa value of 0.960, the quality aspect with a kappa value of 0.981, the size aspect with a kappa 0.997, the color aspect with a kappa value of 1. Based on the results of the consistency test from the 2 experts for the 5 aspects, consistent results were obtained. So that the data that has been labeled can be used as training data to carry out the process of developing a semi-supervised learning model. A series of labeling processes up to consistency testing will be the main basis for developing a semi-supervised learning model.

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

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

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：