检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Kong, Lingping Velasquez, Juan D. Perfilieva, Irina Pant, Millie Pan, Jeng-Shyang Snášel, Václav Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Industrial Engineering University of Chile Santiago Chile Santiago Chile Institute for Research and Applications of Fuzzy Modeling Centre of Excellence IT4Innovations division of The University of Ostrava Ostrava Czech Republic Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India School of Artificial Intelligence Nanjing University of Information Science and Technology China Instituto Sistemas Complejos de Ingeniería Santiago Chile Santiago Chile Faculty of Computer Science and Telecommunications Cracow University of Technology Kraków Poland Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India College of Computer Science and Engineering Shandong University of Science and Technology China

Within the realm of data mining and machine learning, feature selection stands out as an essential technique for dimensionality reduction, presenting both popularity and complexity. Feature selection involves a nuanced trade-off that results in information loss. This distinction underscores the necessity for the development of lightweight, efficient, and practical methods capable of minimizing information loss while executing dimensional reduction. In this paper, we introduce a rankability-based feature selection method. The concept of rankability, proposed in 2019 and similar to the entropy concept, remains relatively unexplored. Our proposed method distinguishes itself by its lightweight complexity, eliminating the need for iterative *** evaluate the effectiveness of our approach, we conducted experiments on forty-one datasets and compared the results with four other algorithms using refined data with 10\%, 30\%, and 50\% feature dimension reduction. The findings reveal that our rankability-based feature selection method consistently outperforms the other four methods across a majority of datasets in terms of accuracy, precision, recall, and F1-macro performance. Specifically, the classification score exceeds 0.9 on accuracy for 50\% feature dimension reduction in twelve datasets, with nine datasets achieving scores over 0.9 in recall, F1-macro, and precision. Overall, our proposed feature selection method demonstrates promising performance. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

SMTrust: Proposing Trust-Based Secure Routing Protocol for RPL Attacks for IoT Applications

SMTrust: Proposing Trust-Based Secure Routing Protocol for R...

引用

2020 International Conference on Computational Intelligence, ICCI 2020

作者： Muzammal, Syeda Mariam Murugesan, Raja Kumar Jhanjhi, Noor Zaman Jung, Low Tang Taylor's University School of Computer Science and Engineering Subang Jaya Malaysia Universiti Teknologi PETRONAS High Performance Computing Cloud Centre Perak Malaysia

ISBN: (纸本)9781728154473

With large scale generation and exchange of data between IoT devices and constrained IoT security to protect data communication, it becomes easy for attackers to compromise data routes. In IoT networks, IPv6 Routing Protocol is the de facto routing protocol for Low Power and Lossy Networks (RPL). RPL offers limited security against several RPL-specific and WSN-inherited attacks in IoT applications. Additionally, IoT devices are limited in memory, processing, and power to operate properly using the traditional Internet and routing security solutions. Several mitigation schemes for the security of IoT networks and routing, have been proposed including Machine Learning-based, IDS-based, and Trust-based approaches. In existing trust-based methods, mobility of nodes is not considered at all or its insufficient for mobile sink nodes, specifically for security against RPL attacks. This research work proposes a conceptual design, named SMTrust, for security of routing protocol in IoT, considering the mobility-based trust metrics. The proposed solution intends to provide defense against popular RPL attacks, for example, Blackhole, Greyhole, Rank, Version Number attacks, etc. We believe that SMTrust shall provide better network performance for attacks detection accuracy, mobility and scalability as compared to existing trust models, such as, DCTM-RPL and SecTrust-RPL. The novelty of our solution is that it considers the mobility metrics of the sensor nodes as well as the sink nodes, which has not been addressed by the existing models. This consideration makes it suitable for mobile IoT environment. The proposed design of SMTrust, as secure routing protocol, when embedded in RPL, shall ensure confidentiality, integrity, and availability among the sensor nodes during routing process in IoT communication and networks. © 2020 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Cartpole Problem with PDL and GP Using Multi-objective Fitness Functions Differing in a Priori Knowledge 1

引用

14th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2021

作者： Shannon, Peter David Nehaniv, Chrystopher L. Phon-Amnuaisuk, Somnuk Adaptive Systems Research Group Centre for Computer Science & Informatics Research University of Hertfordshire Hatfield United Kingdom Laksmana College of Business Bandar Seri Begawan Brunei Department of Systems Design Engineering University of Waterloo WaterlooON Canada Department of Electrical & Computer Engineering University of Waterloo WaterlooON Canada School of Computing and Informatics Universiti of Teknologi Brunei Bandar Seri Begawan Brunei

ISBN: (数字)9783030802530

ISBN: (纸本)9783030802523

We present a study looking at the effect of a priori domain knowledge on an EA fitness function. Our experiment has two aims: (1) applying an existing NSGA-II framework for GP with PDL to the cartpole problem—applying GP & PDL to cartpole and a purely behavioral problem for the first time—and (2) contrasting two multi-objective fitness functions: one with high and the other with low a priori domain knowledge. In our experiment we created two populations with an EA, varying in the number of objectives use for the fitness function, 2 objective criteria to represent low a priori knowledge and 3 to represent high. With fitness functions tailored to find specifically prescribed solutions we expect greater discriminating power and more feedback to an evolutionary process. This comes at the cost of excluding some unexpected solutions from the evolutionary process and placing a greater burden on the designer. We address the question: how large is the disadvantage for the low a priori fitness function in a worst-case scenario, where innovative solutions will not enhance performance. This question is interesting because we would prefer to guide EA with simple, easy to create and understand, objective criteria rather than complex and highly specific criteria. Understanding any associated penalty for using simple, easy to create fitness functions, is crucial in assessing how much effort and should be put into designing objective criteria. © 2021, Springer Nature Switzerland AG.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Beyond Images: An Integrative Multi-modal Approach to Chest X-Ray Report Generation

arXiv

引用

arXiv 2023年

作者： Aksoy, Nurbanu Sharoff, Serge Baser, Selcuk Ravikumar, Nishant Frangi, Alejandro F. CISTIB Centre for Computational Imaging and Simulation Technologies in Biomedicine United Kingdom School of Computing University of Leeds Leeds United Kingdom School of Languages Cultures and Societies University of Leeds Leeds United Kingdom School of Health Sciences Faculty of Biology Medicine and Health The University of Manchester United Kingdom School of Computer Science Faculty of Science and Engineering The University of Manchester United Kingdom Department of Radiology Kastamonu Training and Research Hospital Kastamonu Turkey

Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images. Most existing methods focus solely on the image data, disregarding the other patient information accessible to radiologists. In this paper, we present a novel multi-modal deep neural network framework for generating chest X-rays reports by integrating structured patient data, such as vital signs and symptoms, alongside unstructured clinical *** introduce a conditioned cross-multi-head attention module to fuse these heterogeneous data modalities, bridging the semantic gap between visual and textual data. Experiments demonstrate substantial improvements from using additional modalities compared to relying on images alone. Notably, our model achieves the highest reported performance on the ROUGE-L metric compared to relevant state-of-the-art models in the literature. Furthermore, we employed both human evaluation and clinical semantic similarity measurement (Bio-ClinicalBERT Score1) alongside word-overlap metrics to improve the depth of quantitative analysis. A human evaluation, conducted by a board-certified radiologist, confirms the model’s accuracy in identifying high-level findings, however, it also highlights that more improvement is needed to capture nuanced details and clinical context. © 2023, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Continuous Human Activity Recognition using Radar Imagery and Dynamic Time Warping

Continuous Human Activity Recognition using Radar Imagery an...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Ruchita Mehta Vasile Palade Sara Sharifzadeh Bo Tan Yordanka Karayaneva Centre for Computational Science and Mathematical Modelling Coventry University Coventry UK Department of Computer Science Swansea University Swansea UK Faculty of Technology and Communication Sciences Tampere University Finland School of Computing Engineering & Digital Technologies Teesside University Middlesbrough UK

Remote Human Activity Recognition (HAR) in a private residential area has a beneficial influence on the elderly population's life, since this group of people require regular monitoring of health conditions. This paper addresses the problem of continuous detection of daily human activities using mm-wave Doppler radar. Unlike most previous research, this work records the data in terms of continuous series of activities rather than individual activities. These series of activities are similar to real-life activity patterns. The Dynamic Time Warping (DTW) algorithm is used for the detection of human activities in the recorded time series of data and compared to other time-series classification methods. DTW requires less amount of labelled data. The input for DTW was provided using three strategies, and the obtained results were compared against each other. The first approach uses the pixel-level data of frames (named UnSup-PLevel). In the other two strategies, a Convolutional Variational Autoencoder (CVAE) is used to extract Un-Supervised Encoded features (UnSup-EnLevel) and Supervised Encoded features (Sup-EnLevel) from the series of Doppler frames. Results demonstrates the superiority of the Sup-EnLevel features over UnSup-EnLevel and UnSup-PLevel strategies. However, the performance of the UnSup-PLevel strategy worked surprisingly well without using annotations.

关键词： Heuristic algorithms Time series analysis Pipelines Radar detection Streaming media Radar imaging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

IF-City: Intelligible Fair City Planning to Measure, Explain and Mitigate Inequality

arXiv

引用

arXiv 2022年

作者： Lyu, Yan Lu, Hangxin Lee, Min Kyung Schmitt, Gerhard Lim, Brian Y. School of Computer Science and Engineering Southeast University Nanjing China Future Cities Laboratory Singapore-ETH Centre Singapore Department of Architecture ETH Zurich Switzerland School of Information The University of Texas at Austin United States School of Computing National University of Singapore Singapore Singapore

With the increasing pervasiveness of Artificial Intelligence (AI), many visual analytics tools have been proposed to examine fairness, but they mostly focus on data scientist users. Instead, tackling fairness must be inclusive and involve domain experts with specialized tools and workflows. Thus, domain-specific visualizations are needed for algorithmic fairness. Furthermore, while much work on AI fairness has focused on predictive decisions, less has been done for fair allocation and planning, which require human expertise and iterative design to integrate myriad constraints. We propose the Intelligible Fair Allocation (IF-Alloc) Framework that leverages explanations of causal attribution (Why), contrastive (Why Not) and counterfactual reasoning (What If, How To) to aid domain experts to assess and alleviate unfairness in allocation problems. We apply the framework to fair urban planning for designing cities that provide equal access to amenities and benefits for diverse resident types. Specifically, we propose an interactive visual tool, Intelligible Fair City Planner (IF-City), to help urban planners to perceive inequality across groups, identify and attribute sources of inequality, and mitigate inequality with automatic allocation simulations and constraint-satisfying recommendations. We demonstrate and evaluate the usage and usefulness of IF-City on a real neighborhood in New York City, US, with practicing urban planners from multiple countries, and discuss generalizing our findings, application, and framework to other use cases and applications of fair allocation. Copyright © 2022, The Authors. All rights reserved.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Optimal Geospatial Query Placement in Cloud 1st

Optimal Geospatial Query Placement in Cloud

引用

1st International Conference on Intelligent and Cloud computing, ICICC 2019

作者： Das, Jaydeep Addya, Sourav Kanti Ghosh, Soumya K. Buyya, Rajkumar Advanced Technology Development Centre Indian Institute of Technology Kharagpur KharagpurWest Bengal721302 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur KharagpurWest Bengal721302 India School of Computing and Information Systems University of Melbourne MelbourneVIC3010 Australia

ISBN: (纸本)9789811559709

computing resources requirements are increasing with the massive generation of geospatial queries. These queries extract information from a large volume of spatial data. Placement of geospatial queries in virtual machines with minimum resource and energy wastage is a big challenge. Getting query results from mobile locations within a specific time duration is also a major concern. In this work, a bi-objective optimization problem has been formulated to minimize the energy consumption of cloud servers and service processing time. To solve the problem, a crow search based bio-inspired heuristic has been proposed. The proposed algorithm has been compared with traditional First Fit and Best Fit algorithms through simulation, and the obtained results are significantly better than the traditional techniques. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

H-SynEx: Using synthetic images and ultra-high resolution ex vivo MRI for hypothalamus subregion segmentation

arXiv

引用

arXiv 2024年

作者： Rodrigues, Livia Bocchetta, Martina Puonti, Oula Greve, Douglas Londe, Ana Carolina França, Marcondes Appenzeller, Simone Iglesias, Juan Eugenio Rittner, Leticia Universidade Estadual de Campinas School of Electrical and Computer Engineering Brazil Massachusetts General Hospital Harvard Medical School United States Dementia Research Centre Department of Neurodegenerative Disease UCL Queen Square Institute of Neurology University College London London United Kingdom Centre for Cognitive and Clinical Neuroscience Division of Psychology Department of Life Sciences College of Health Medicine Life Sciences Brunel University London United Kingdom Universidade Estadual de Campinas School of Medical Sciences Brazil Centre for Medical Image Computing University College London United Kingdom Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology United States

The hypothalamus is a small structure located in the center of the brain and is involved in significant functions such as sleeping, temperature, and appetite control. Various neurological disorders are also associated with hypothalamic abnormalities. Automated image analysis of this structure from brain MRI is thus highly desirable to study the hypothalamus in vivo. However, most automated segmentation tools currently available focus exclusively on T1w images. In this study, we introduce H-SynEx, a machine learning method for automated segmentation of hypothalamic subregions that generalizes across different MRI sequences and resolutions without retraining. H-synEx was trained with synthetic images built from label maps derived from ultra-high resolution ex vivo MRI scans, which enables finer-grained manual segmentation when compared with 1mm isometric in vivo images. We validated our method using Dice Coefficient (DSC) and Average Hausdorff distance (AVD) across in vivo images from six different datasets with six different MRI sequences (T1, T2, proton density, quantitative T1, fractional anisotrophy, and FLAIR). Statistical analysis compared hypothalamic subregion volumes in controls, Alzheimer’s disease (AD), and behavioral variant frontotemporal dementia (bvFTD) subjects using the Area Under the Receiving Operating Characteristic curve (AUROC) and Wilcoxon rank sum test. Our results show that H-SynEx successfully leverages information from ultra-high resolution scans to segment in vivo from different MRI sequences. Our automated segmentation was able to discriminate controls versus Alzheimer’s Disease patients on FLAIR images with 5mm spacing. H-SynEx is openly available at https://***/liviamarodrigues/hsynex. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Flow behavior in idealized & realistic upper airway geometries

引用

computers in Biology and Medicine 2025年 194卷

作者： Brenda Vara Almirall Hadrien Calmet Hua Qian Ang Kiao Inthavong Barcelona Super-Computing Centre (BSC-CNS) Department of Computer Applications in Science and Engineering Barcelona Spain School of Engineering RMIT University Bundoora Victoria 3083 Australia

This study investigated the flow characteristics in idealized and realistic upper airway models during oral inhalation, focusing on their ability to replicate airflow dynamics and turbulence that impact pharmaceutical aerosol delivery. While idealized airway models, such as the United States Pharmacopeia (USP) model, are widely used in regulatory testing, they lack anatomical fidelity, potentially underestimating critical features, including the laryngeal jet formation, which are essential for accurate particle deposition predictions. Understanding the implications of idealized and realistic models is addressed using Large Eddy Simulations (LES) at inhalation rates of 15 and 30 L/min. Four airway models were analyzed: the USP model, the Virginia Commonwealth University (VCU) model, and two realistic models reconstructed from CT scans of healthy adults. The findings revealed the limitations of the USP model, while the VCU models demonstrated laminar flow behavior with a laryngeal jet with a lower magnitude compared to the realistic models. The realistic models (R01 and R02) exhibited more complex flow features, including an earlier laryngeal jet formation, emphasizing the importance in understanding the limitations of idealized models and the variations between realistic models.

关键词： CFD LES Idealized upper airway Realistic upper airway

来源：评论

学校读者我要写书评

暂无评论

Deploying Machine Learning Inference on Diabetic Retinopathy in Binary and Multi-class Classification

Deploying Machine Learning Inference on Diabetic Retinopathy...

引用

Industrial Electronics Research and Applications (ICIERA), International Conference on

作者： Indira Bidari Satyadhyan Chickerur Akshay Kulkarni Anish Mahajan Amogh Nikkam Abhishek THM School of Computer Science and Engineering KLE Technological University Hubballi India Centre for High Performance Computing KLE Technological University Hubballi India

ISBN: (纸本)9781665435437

Diabetic Retinopathy is a condition of the person's eye that causes vision loss and blindness in diabetic people. Among adults between 20–74 years, this disease most of the time acts as the cause of blindness. Also, it is the leading reason behind cecity among working-aged adults worldwide. An efficient health care system contributes to an essential part of the country's economy, development, and industrialization. It affects one out of three persons with diabetes. The longer a person has diabetes, the higher their risk of developing some ocular problem. The mobile and web application built adds assistance to the people for endorsing their qualms and knowing about their condition's severity. Since most of the users can be from rural areas, we built applications that work both offline and online. The inference is to select a configuration based on a single input. To decrease the magnitude of the mobile application model, we implemented MobileN et architecture. It is considered a light weightedmodel as it has fewer parameters than others, making it suitable for the application objective. The accuracy of MobileNet is 76 percent. ResNet 50 architecture is used in the web application, which requires an internet facility to predict the output. Because of the increase in the parameters, it provides higher accuracy when compared to the MobileN et model. Kaggle eyepacs dataset is given as input for both models. The dataset is divided into five classes: No Diabetic Retinopathy, mild, moderate, severe, and proliferative. The models classify the images given as input and display one of these class labels as a result. An oversampling technique has been implemented to overcome the problem of data bias. NodeJS and python have been used to build web applications and android studio for mobile applications. The time taken to display the result in both applications is less than 10 seconds. The size of the mobile application has been reduced from 120MB to 25 MB. This application is hel

关键词： Retinopathy Urban areas Blindness Cameras Diabetes Mobile applications Browsers

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：