检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2022年第6期3卷 924-943页

作者： Cheng, Lu Guo, Ruocheng Moraffah, Raha Sheth, Paras Candan, K. Selcuk Liu, Huan Arizona State University School Of Computing Informatics And Decision Systems Engineering TempeAZ85287 United States City University Of Hong Kong School Of Data Science Hong Kong

The convenient access to copious multifaceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine learning (causal learning). Recent years have, therefore, witnessed great effort in developing causal learning algorithms aiming to help artificial intelligence (AI) achieve human-level intelligence. Due to the lack of ground-truth data, one of the biggest challenges in current causal learning research is algorithm evaluations. This largely impedes the cross-pollination of AI and causal inference and hinders the two fields to benefit from the advances of the other. To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with Big data (i.e., the intersection of causal inference and machine learning), in this survey, we review commonly used datasets, evaluation methods, and measures for causal learning using an evaluation pipeline similar to conventional machine learning. We focus on the two fundamental causal inference tasks and causality-aware machine learning tasks. Limitations of current evaluation procedures are also discussed. We, then, examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of Big data. The survey seeks to bring to the forefront the urgency of developing publicly available benchmarks and consensus-building standards for causal learning evaluation with observational data. In doing so, we hope to broaden the discussions and facilitate collaboration to advance the innovation and application of causal learning. © 2020 IEEE.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Fast, GPU-based Computation of Large Point-Spread Function Sets for the Human Eye using the Extended Nijboer-Zernike Approach 2

Fast, GPU-based Computation of Large Point-Spread Function S...

引用

2nd IEEE Conference on Information Technology and data science, CITDS 2022

作者： Csoba, Istvan Kunkli, Roland University of Debrecen Faculty of Informatics Doctoral School of Informatics Debrecen Hungary University of Debrecen Faculty of Informatics Department of Data Science and Visualization Debrecen Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

The point-spread function (PSF) is the diffraction pattern of an infinitesimal light source and plays an important role in the study and simulation of human vision. It forms the backbone of a multitude of vision-rendering algorithms, as it can be used to obtain the necessary kernels for convolution. Its computation is often performed via ray-tracing or the fast Fourier transform (FFT), but recently we also demonstrated that the Extended Nijboer-Zernike (ENZ) approach can be a more efficient alternative, which reduces the computation time of large PSF sets to just a few minutes. In this paper, we present a significantly faster, GPU-based computation scheme of the ENZ approach to further improve the computation process for such large PSF sets. Our algorithm works by reformulating the core V-{n}-{m} function to reusable subterms that are efficient to accumulate in parallel. We demonstrate that our proposed method leads to substantial performance improvements and facilitates the interactive exploration of visual aberrations when paired with our existing vision simulation algorithm. © 2022 IEEE.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Comfort Shoulder (Rhomboid Major) Muscles Chair Identifier System 6

Comfort Shoulder (Rhomboid Major) Muscles Chair Identifier S...

引用

6th International Conference on Communications, Information System and Computer Engineering, CISCE 2024

作者： Moshayedi, Ata Jahangir Yu, Yuexin Savoji, Kimia Andani, Mehran Emadi School of Information Engineering Jiangxi University of Science and Technology Jiangxi Ganzhou China School of Computing Clemson University Biomedical Data Science and Informatics ClemsonSC United States University of Verona Department of Neurosciences Biomedicine and Movement Sciences Verona Italy

ISBN: (纸本)9798350353174

Nowadays, Sitting is one of the frequent activities of humans. particularly with the rise of office work, which is leading to an increase in the sitting periods for many individuals. Research highlights the importance of studying sitting posture to enhance seat quality, correct sitting methods, and prevent various health issues like neck and shoulder strains, etc. This article focuses on designing an IoT-based system that enables web-based data visualization without specialized software that can enable distance sampling. Through temperature sensors (DS18b20 and SHT11) and an FSR sensor, the system can identify distinct patterns in the main rhomboid muscles (the most important muscles of humans). The results show a significant relationship between individuals' body mass (BMI) and the observed muscle patterns, highlighting the importance of this correlation for researchers and industry designers alike. © 2024 IEEE.

关键词： Seats

来源：评论

学校读者我要写书评

暂无评论

Short-Term Effects of Ambient Air Pollutants on Outpatient Visits for Childhood Allergic Diseases in Shanghai,China

引用

Journal of Shanghai Jiaotong university(science) 2024年第6期29卷 979-994页

作者： HU Yi GU Jianlei WU Dan WANG Xiaolei LU Hui YU Guangjun Center for Biomedical Informatics Shanghai Children’s HospitalShanghai Jiao Tong University School of MedicineShanghai 200040China SJTU-Yale Joint Center for Biostatistics and Data Science Department of Bioinformatics and BiostatisticsShanghai Jiao Tong UniversityShanghai 200240China Shanghai Engineering Research Center for Big Data in Pediatric Precision Medicine Shanghai 200040China

This study aims to investigate the short-term effects of ambient air pollutants on outpatient visits for childhood allergic *** data on ambient air pollutants(NO2,SO2,CO and PM2.5)and outpatient visits for childhood allergic diseases(asthma,atopic dermatitis and allergic rhinitis)were obtained in Shanghai,China from 2013 to *** effects of ambient air pollutants were estimated for total outpatient visits for childhood allergic diseases,gender and age stratification and disease classification by using distributed lag non-linear model(DLNM).We found positive associations between short-term exposure to air pollutants and childhood allergic *** and children aged 7 years old were more likely to be sensitive to ambient air ***2 and SO2 showed stronger effects on asthma and atopic dermatitis,*** study provides evidence that short-term exposure to ambient air pollutants can increase the risk of childhood allergic diseases.

关键词： childhood allergic diseases ambient air pollutant nitrogen dioxide(NO2) sulfur dioxide(SO2) particulate matter<2.5μm in diameter(PM2.5)

来源：评论

学校读者我要写书评

暂无评论

data-Driven Design for Anomaly Detection in Network Access Control Systems 2

Data-Driven Design for Anomaly Detection in Network Access C...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Muhammad, Musa Abubakar Caraffini, Fabio Fasanmade, Adebamigbe Ishola, Olabayo Mohammed, Kabiru Morden, Jarrad Coventry University School of Computing Mathematics and Data Science Coventry United Kingdom Swansea University Department of Computer Science Swansea United Kingdom De Montfort University School of Computer Science and Informatics Leicester United Kingdom

ISBN: (纸本)9798350335644

Current network access control systems can contain unpredictable interactions between multiple device models, multiple network protocol layers (e.g. TCP, UDP and ICMP), hardware, and clock-skew-specific influences, and cannot detect or identify abnormal behaviours based on the type of device. To complicate things further, the 'bring your own device' policy is increasing security threats, vulnerabilities, and risks to enterprise network environments, making intrusion detection and prevention systems unable to detect illegal and unauthorised access to devices in the enterprise network. The consequences can be disastrous. In this light, this work propose a simple but effective clustering approach capable of separating normal and abnormal network traffic patterns to detect such challenges (anomalies). The work in this paper applies this approach to single devices and aggregations of data per device type. Additionally, this work propose plotting the notched box for each cluster to acquire a better understanding of their data distributions and measuring the clusters' performance using the Adjusted Rand Index. The results show that the proposed method is valid, can be used in several contexts, and features a 95% confidence that most single device and device type distributions overlap, which makes them equivalently usable for anomaly detection purposes. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Development of a Natural Language Processing Tool to Extract Acupuncture Point Location Terms 11

Development of a Natural Language Processing Tool to Extract...

引用

11th IEEE International Conference on Healthcare informatics, ICHI 2023

作者： Li, Yiming Peng, Xueqing Li, Jianfu Peng, Suyuan Pei, Donghong Tao, Cui Xu, Hua Hong, Na The University of Texas Health Science Center at Houston School of Biomedical Informatics HoustonTX United States Yale University Section of Biomedical Informatics and Data Science School of Medicine New HavenCT United States Peking University National Institute of Health Data Science Beijing China The University of Texas Md Anderson Cancer Center HoustonTX United States

ISBN: (纸本)9798350302639

Acupuncture point location information is significant to the effect of acupuncture therapy. A wealth of knowledge related to acupuncture point locations is typically dispersed across books or reports in free-text format, which can pose challenges for machines to understand and facilitate. In this study, our purpose is to develop a natural language processing (NLP) tool to extract acupuncture point location information. We adopted the World Health Organization (WHO) Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our reference standard and corpus. Our proposed approach to develop and validate the NLP tool involves three key steps: 1) We leveraged pre-existing terminologies from the anatomy domain, specifically the International Anatomical Terminology (IAT) and Uber-anatomy Ontology (UBERON), to construct a baseline dictionary of acupoint locations. This dictionary was then used in conjunction with a dictionary lookup method to match terms in the acupuncture location descriptions outlined by the WHO Standard;2) We employed NLP models based on machine learning and deep learning techniques, specifically utilizing Conditional Random Fields (CRFs) and Recurrent Neural Network (RNN) for training. The CRFs and RNN models achieved overall F1 scores of 0.955 and 0.945, respectively;3) We encoded the extracted entities into standardized concepts and enriched the baseline dictionary using these entities. In this study, a customized NLP tool was developed and validated for extracting acupuncture point location terms. This tool can be used in various informatics applications to support acupuncture research, education, and practices. © 2023 IEEE.

关键词： Acupuncture

来源：评论

学校读者我要写书评

暂无评论

A Variational Autoencoder-Feed Forward Networks (VAE-FNN) Model for Classifying DNA Barcodes 1

A Variational Autoencoder-Feed Forward Networks (VAE-FNN) Mo...

引用

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Yadav, Abhivyakti Divya, S. Oviya, I.R. Raja, Kalpana Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Medicine Yale University Section for Biomedical Informatics and Data Science New HavenCT United States

ISBN: (纸本)9798350342796

DNA Barcodes, which are particular fragments derived from brief sections of DNA (such as mitochondrial, nuclear, and plastid sequences), can be used to identify organisms from the major life kingdoms. In addition to supporting conventional taxonomic techniques, DNA barcoding is a potent tool that advances our knowledge of species diversity and their ecological functions. On a variety of organisms, the use of this approach for species categorization has been successful. In this paper, we examine how DNA barcoding has been used to classify species based on DNA barcodes as well as other related research that has been done over the years on the subject. After experimenting with a number of deep learning models, we have propose a Variational Auto Encoder + Feed Forward Neural Network workflow for classifiying species using DNA barcodes. The models have been assessed on the basis of performance factors including accuracy, recall, and precision. COI, rbcL, matK, and ITS are the specific gene sections that have been identified as barcodes. For both simulated and real datasets, the model can attain an average accuracy of greater than 95 percent. This DNA barcoding approach has the ability to simplify DNA barcode-based species identification and serve as a tool for species categorization. © 2023 IEEE.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Findings of WASSA 2023 Shared Task: Multi-Label and Multi-Class Emotion Classification on Code-Mixed Text Messages 13

Findings of WASSA 2023 Shared Task: Multi-Label and Multi-Cl...

引用

13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023

作者： Bölücü, Necva Ameer, Iqra Al Bataineh, Ali Xu, Hua Data61 CSIRO Sydney Australia Division of Science and Engineering Penn State University AbingtonPA United States Norwich University United States Section of Biomedical Informatics and Data Science Yale School of Medicine United States

ISBN: (纸本)9781959429876

We present the results of the WASSA 2023 Shared-Task 2: Emotion Classification on codemixed text messages (Roman Urdu + English), which included two tracks for emotion classification: multi-label and multi-class. The participants were provided with a dataset of codemixed SMS messages in English and Roman Urdu labeled with 12 emotions for both tracks. A total of 5 teams (19 team members) participated in the shared task. We summarized the methods, resources, and tools used by the participating teams. We also made the data freely available for further improvements to the task. © 2023 Association for Computational Linguistics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Access control for data Spaces 28

Access control for Data Spaces

引用

28th Conference on Innovation in Clouds, Internet and Networks, ICIN 2025

作者： Fotiou, Nikos Siris, Vasilios A. Polyzos, George C. ExcID P.C. Athens11362 Greece Department of Informatics School of Information Sciences and Technology Athens University of Economics and Business Athens10434 Greece School of Data Science The Chinese University of HongKong Guangdong Shenzhen518172 China

ISBN: (纸本)9798331542399

data spaces represent an emerging paradigm that facilitates secure and trusted data exchange through foundational elements of data interoperability, sovereignty, and trust. Within a data space, data items, potentially owned by different entities, can be interconnected. Concurrently, data consumers can execute advanced data lookup operations and subscribe to data-driven events. Achieving fine-grained access control without compromising functionality presents a significant challenge. In this paper, we design and implement an access control mechanism that ensures continuous evaluation of access control policies, is data semantics aware, and supports subscriptions to data events. We present a construction where access control policies are stored in a centralized location, which we extend to allow data owners to maintain their own Policy Administration Points. This extension builds upon W3C Verifiable Credentials. © 2025 IEEE.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Tomato Disease Classification Using CNN 4th

Tomato Disease Classification Using CNN

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Archanaa, N. Daniel, V. Vifert Jenuben Divya, S. Raja, Kalpana Oviya, I.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Sciences Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States

ISBN: (纸本)9789819736898

Plant disease detection using various machine learning techniques is a very popular research area. Many promising results have been obtained, but only a few specific applications can still make farmers’ lives easier. This research focuses on the important task of identifying tomato diseases at an early stage to prevent their spread and protect crop yields more broadly, emphasizing the idea that disease prevention will more important than treatment. Leveraging the capabilities of convolutional neural networks (CNN), we developed a model that diagnoses eight distinct tomato diseases using only their images. Diseases listed include bacterial spot, early blight, late blight, leaf mold, septoria leaf spot, two-spotted spider mite, target spot, and tomato yellow leaf curl virus. An integral part of our approach involves sophisticated image prepossessing and enhancement techniques, ensuring data quality and model robustness. Feature extraction plays a key role in transforming raw image data into recognizable patterns. The architecture of the CNN has been meticulously designed, consisting of multiple layers with a notable focus on the ReLU activation function and other relevant hyper-parameters. Our main dataset comes from PlantVillage, known for synthesizing rich and diverse plant images. After rigorous training and validation, the CNN model showed exceptional accuracy of 96.88% in tomato disease identification. However, challenges such as overfitting, image quality variability, and class imbalances were encountered but were resolved through strategic data augmentation, careful CNN overlay. In summary, our research presents a practical solution for farmers and agricultural entities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fruits

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：