检索结果-内蒙古大学图书馆

8th World Conference on Smart Trends in Systems Security and Sustainability, WorldS4 2024

作者： Olaifa, Moses Malele, Vusumuzi Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria South Africa Unit of Data Science and Computing Vaal Campus North-West University Vanderbijlpark South Africa

ISBN: (纸本)9789819786947

Over the past few decades, mortality rates associated with air quality pollution have risen in numerous countries around the globe. This pollution stems from different factors such as meteorological conditions, human activities from urban industrialization, vehicular emission, and so on. Air pollution constituents such as NO2, CO, SO, and coarse and fine particulate matter for different locations have been analyzed to learn both correlation and inter-dependency for long and short terms. However, many of these studies overlook datasets collected using low-cost tools and equipment. Most of the time, datasets of this nature are marred with inconsistencies and gaps at irregular intervals. This may render the air pollutant data unsuitable. In order to test the suitability of machine learning algorithms on such dataset, this study conducts a time-series forecast analysis using the prophet algorithm. Two additional models including linear regressor and random forest regressor are trained and tested on the same dataset and a comparative analysis of the three models is performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Online Incremental Learning with Abstract Argumentation Frameworks 1

Online Incremental Learning with Abstract Argumentation Fram...

引用

1st Workshop on Argumentation and Machine Learning, ArgML 2022

作者： Ayoobi, H. Cao, M. Verbrugge, R. Verheij, B. Department of Artificial Intelligence Bernoulli Institute Faculty of Science and Engineering University of Groningen Netherlands Faculty of Science and Engineering University of Groningen Netherlands Department of Computing Faculty of Engineering Imperial College London United Kingdom

The environment around general-purpose service robots has a dynamic nature. Accordingly, even the robot's programmer cannot predict all the possible external failures which the robot may confront. This research proposes an online incremental learning method that can be further used to autonomously handle external failures originating from a change in the environment. Existing research typically offers special-purpose solutions. Furthermore, the current incremental online learning algorithms can not generalize well with just a few observations. In contrast, our method extracts a set of hypotheses, which can then be used for finding the best recovery behavior at each failure state. The proposed argumentation-based online incremental learning approach uses an abstract and bipolar argumentation framework to extract the most relevant hypotheses and model the defeasibility relation between them. This leads to a novel online incremental learning approach that overcomes the addressed problems and can be used in different domains including robotic applications. We have compared our proposed approach with state-of-the-art online incremental learning approaches and an approximation-based reinforcement learning method. The experimental results show that our approach learns more quickly with a lower number of observations and also has higher final precision than the other methods. © 2022 Copyright for this paper by its authors.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness 38

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qian, Yang Wang, Xinbiao Du, Yuxuan Luo, Yong Tao, Dacheng School of Computer Science Faculty of Engineering University of Sydney NSW2008 Australia Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Quantum Approximate Optimization Algorithm (QAOA) and its variants exhibit immense potential in tackling combinatorial optimization challenges. However, their practical realization confronts a dilemma: the requisite circuit depth for satisfactory performance is problem-specific and often exceeds the maximum capability of current quantum devices. To address this dilemma, here we first analyze the convergence behavior of QAOA, uncovering the origins of this dilemma and elucidating the intricate relationship between the employed mixer Hamiltonian, the specific problem at hand, and the permissible maximum circuit depth. Harnessing this understanding, we introduce the Mixer Generator Network (MG-Net), a unified deep learning framework adept at dynamically formulating optimal mixer Hamiltonians tailored to distinct tasks and circuit depths. Systematic simulations, encompassing Ising models and weighted Max-Cut instances with up to 64 qubits, substantiate our theoretical findings, highlighting MG-Net's superior performance in terms of both approximation ratio and efficiency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Carbon Cold Emitter Data Interpretation: Should We Go for Millikan–Lauritsen Plot over Fowler–Nordheim Approach for Developing Display Device

引用

Journal of The Institution of Engineers (India): Series D 2022年第2期103卷 629-638页

作者： Goley, M. Chaudhary, S. Pandey, A. Mandal, V. Chattopadhyay, K.K. Banerjee, D. Faculty of Engineering and Computing Sciences Teerthanker Mahaveer University Uttar Pradesh Moradabad244001 India School of Materials Science and Nanotechnology Jadavpur University Kolkata India

Cold cathode emission or cold field emission (CFE) is a purely quantum mechanical phenomenon. Here the exact mechanism behind the observed current–voltage relationship is yet to be pinpointed. For instance, a good cold emitter is very reasonably supposed to have low work function and good conductivity whereas carbon allotropes like diamond have just the reverse in both the cases, i.e., it is insulating in nature having a very wide band gap as well as high work function yet it is considered to be an efficient field emitter. Since the early twentieth century, different groups have suggested different equations or relations that can describe the experimental CFE current–voltage characteristics adequately. Although they all fundamentally follow an exponential law, so far the theory suggested by Fowler and Nordheim (F–N) is the most accepted one. However, there is another kind of voltage dependence of current, suggested by Millikan and Lauritsen (M–L) which is despite being reasonable not so common now a day to use. This article revisits both the F–N and M–L plots and has shown that one rather uses the M–L plot than the most widely used F–N plots due to its simplicity. To establish this, few cold field emission data of different carbon nanostructures have been analyzed by both F–N and M–L plot. It has been shown that the M–L plots may even be more useful sometimes along with their inherent simplicity. The detailed theoretical discussion has been incorporated along with the experimental verification. © 2022, The Institution of Engineers (India).

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Optimizing Treatment Outcomes in Rheumatoid Arthritis Patients: A Data science Approach to Analysing Multimorbidity 5

Optimizing Treatment Outcomes in Rheumatoid Arthritis Patien...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Moovendran, Manikandan Nitheesh, S. Sri Sharvesh, S.S. Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai603203 India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389609

This study aims to explore the data science strategies for new insights into multimorbidity understanding and identifying potential therapy targeting in rheumatoid arthritis patients. Rheumatoid Arthritis (RA) is a chronic inflammatory (auto immune) disease that has the potential to result in co-morbid illnesses, meaning it affects both sides of the equation by making treating patients even tougher than had been previously determined. Although the controversial method of drug-drug interactions remains central to this phenomenon, an even lesser acknowledged mechanism that may exert significant control over disease status and remission rates with RA is the interaction between comorbidities themselves. The presence and types of comorbidities, how they accumulate over time, and their interplay with therapies across the life span remain unknown. To identify comorbidity patterns and predict patient outcomes, we leverage a dataset of patient registries, wearable technology or Electronic Health Records (EHR) using advanced machine learning techniques like clustering and predictive analytics. Image analysis of these data is done by Convolutional Neural Network (CNN). Clinical notes can be particularly informative using random forest, Gradient Boosting Machine (GBM), Support Vector Machine (SVM), by combining these to get an Ensemble Model which improves overall performances of the model and network analysis which enables creating a comprehensive understanding of the relationships between different chronic conditions alongside their treatments. These findings imply that in some cases there may be relationships between specific comorbidity profiles and treatment outcomes, providing a practical basis for investigating individual-level factored medicine. This study analyses these data with different models and highlights the power of data science both in clinical decision-making and uncovering previously unknown patterns of illness to improve patient care. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Data Fusion Architecture Empowered with Deep Learning for Breast Cancer Classification

引用

Computers, Materials & Continua 2023年第12期77卷 2813-2831页

作者： Sahar Arooj Muhammad Farhan Khan Tariq Shahzad Muhammad Adnan Khan Muhammad Umar Nasir Muhammad Zubair Atta-ur-Rahman Khmaies Ouahada Faculty of Computing Riphah International UniversityIslamabad45000Pakistan Department of Forensic Sciences University of Health SciencesLahore54000Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O.Box 524Johannesburg2006South Africa School of Computing Skyline University CollegeUniversity City SharjahSharjah1797United Arab Emirates Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Software Faculty of Artificial Intelligence&SoftwareGachon UniversitySeongnamGyeonggido13120Korea Department of Computer Science Bahria UniversityLahore CampusLahore54000Pakistan Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia

Breast cancer(BC)is the most widespread tumor in females worldwide and is a severe public health *** is the leading reason of death affecting females between the ages of 20 to 59 around the *** detection and therapy can help women receive effective treatment and,as a result,decrease the rate of breast cancer *** cancer tumor develops when cells grow improperly and attack the healthy tissue in the human *** are classified as benign or malignant,and the absence of cancer in the breast is considered *** learning,machine learning,and transfer learning models are applied to detect and identify cancerous tissue like *** research assists in the identification and classification of *** implemented the pre-trained model AlexNet and proposed model Breast cancer identification and classification(BCIC),which are machine learning-based models,by evaluating them in the form of comparative *** used 3 datasets,A,B,and *** fuzzed these datasets and got 2 datasets,A2C and *** A2C is the fusion of A,B,and C with 2 classes categorized as benign and *** B3C is the fusion of datasets A,B,and C with 3 classes classified as benign,malignant,and *** used customized AlexNet according to our datasets and BCIC in our proposed *** achieved an accuracy of 86.5%on Dataset B3C and 76.8%on Dataset A2C by using AlexNet,and we achieved the optimum accuracy of 94.5%on Dataset B3C and 94.9%on Dataset A2C by using proposed model BCIC at 40 epochs with 0.00008 learning *** proposed fuzzed dataset model using transfer *** fuzzed three datasets to get more accurate results and the proposed model achieved the highest prediction accuracy using fuzzed dataset transfer learning technique.

关键词： Breast cancer classification deep learning machine learning transfer learning learning rate

来源：评论

学校读者我要写书评

暂无评论

Applications of geoforensic trace evidence

引用

Geology Today 2024年第4期40卷 139-145页

作者： Jeffery, Adam J. Pirrie, Duncan Pringle, Jamie K. Ruffell, Alastair Stimpson, Ian G. School of Chemical and Physical Sciences Keele University School of Geography Geology and the Environment Keele University Faculty of Computing Engineering and Science University of South Wales School of the Natural Built Environment Queen's University

Geoforensic trace evidence studies can be crucial for law enforcement and civil/criminal prosecution and defence, to test potential links between suspect(s), crime scenes or forensic object(s). In addition, trace geological evidence can be used to identify forensic sites of interest such as clandestine graves of murder victims. However, geoforensic trace evidence also has applications in a range of other investigations. This article briefly details the current geoscientific methods used to assist in such investigations and uses recent case studies to illustrate their use. © 2024 The Author(s). Geology Today published by The Geological Society of London and The Geologists’ Association and John Wiley & Sons Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A parametric study on chemical activator selection and soaking procedure development for barium incorporation in concurrent activated and surface modified palm kernel shell derived activated carbon

引用

Discover Chemical engineering 2024年第1期4卷 1-17页

作者： Lai, Jia Yen Ngu, Lock Hei Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Kuching Malaysia

The concurrent activation and surface modification (CAM) process is an integrated process used to synthesise palm kernel shell derived activated carbon (PKSdAC) in this study. CAM involves chemical activation and surface modification via metal impregnation in one process. This study investigated the usage of different acids as chemical activators and different soaking procedures for impregnating barium (Ba) in CAM-PKSdAC. It shows that chemical impregnation of PKS using 10% sulphuric acid (H2SO4) mass loading via two soaking steps can impregnate a high Ba amount of 0.86–2.98 wt. % in CAM-PKSdAC, compared to one soaking step. The two soaking steps procedure reduced the overage formation of BaSO4 from sealing the pores of PKS. Comparing HCl and H2SO4, at 30% acid mass loading, the impregnation of PKS with H2SO4 produced a higher impregnated Ba amount in CAM-PKSdAC. BaSO4 generated from the reaction between H2SO4 on the PKS surface with BaCl2 solution causes a reduction reaction at high temperatures. BaSO4 reacted with a carbon-reducing agent and is reduced to barium sulphide (BaS), impregnating Ba on CAM-PKSdAC. In conclusion, H2SO4 was found to be the suitable chemical activator with two soaking steps for the CAM process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid UNet and Vision Transformer Architecture with Multi-scale Fusion for Brain Tumor Segmentation 5th

A Hybrid UNet and Vision Transformer Architecture with Multi...

引用

5th International Conference on Medical Imaging and Computer Aided Diagnosis, MICAD 2024

作者： Ranjbarzadeh, Ramin Anari, Shokofeh Crane, Martin Bendechache, Malika School of Computing Faculty of Engineering and Computing Dublin City University Dublin Ireland Department of Accounting Economic and Financial Sciences Islamic Azad University South Tehran Branch Tehran Iran ADAPT Research Centre School of Computer Science University of Galway Galway Ireland

ISBN: (纸本)9789819638628

This research presents an advanced neural network architecture for the segmentation of brain tumors. Our suggested model for brain tumor segmentation incorporates the Vision Transformer (ViT) as a 3D encoder alongside a modified UNet architecture to effectively capture both global and local information in MRI data. The model contains a dual-encoder architecture: a 3D ViT encoder captures global contextual information throughout the MRI volume, while a concurrent convolutional encoder emphasizes localized features. The encoder routes are enhanced by skip connections, facilitating efficient feature transmission between the ViT and UNet layers. In the bottleneck, features from both encoders are integrated via a multi-scale fusion block, augmenting the model's capacity to discern intricate spatial hierarchies and tumor changes. The decoder pathway employs a hierarchical upsampling and multi-scale fusion framework, meticulously rebuilding the final segmentation map with a focus on spatial accuracy. This hybrid model integrates the ViT's capacity to capture long-range relationships with the UNet's proficiency in fine-grained spatial localization, yielding a strong segmentation output on the BraTS 2020 dataset that is adept at addressing the complex and diverse architecture of brain tumors in MRI. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection and Segmentation Using RCNN

引用

Computers, Materials & Continua 2022年第6期71卷 5005-5020页

作者： Maham Khan Syed Adnan Shah Tenvir Ali Quratulain Aymen Khan Gyu Sang Choi Department of Computer Science University of Engineering&TechnologyTaxila47080Pakistan Faculty of Computing The Islamia University of BahawalpurBahawalpur63100Pakistan Department of Information and Communication Engineering Yeungnam UniversityGyeongbuk38541Korea

Brain tumors are considered as most fatal *** reduce the risk of death,early identification of the disease is *** of the best available methods to evaluate brain tumors is Magnetic resonance Images(MRI).Brain tumor detection and segmentation are tough as brain tumors may vary in size,shape,and *** makes manual detection of brain tumors by exploring MRI a tedious job for radiologists and doctors’.So an automated brain tumor detection and segmentation is *** work suggests a Region-based Convolution Neural Network(RCNN)approach for automated brain tumor identification and segmentation using MR images,which helps solve the difficulties of brain tumor identification efficiently and *** methodology is based on the accurate and efficient selection of tumorous *** reduces computational complexity and *** have validated the designed experimental setup on a standard dataset,BraTS *** used binary evaluation matrices based on Dice Similarity Coefficient(DSC)and Mean Average Precision(mAP).The segmentation results are compared with state-of-the-art methodologies to demonstrate the effectiveness of the proposed *** suggested approach attained an averageDSC of 0.92 andmAP 0.92 for 10 patients,while on the whole dataset,the scores are DSC 0.89 and mAP *** following results clearly show the performance efficiency of the proposed methodology.

关键词： Brain tumor MRI preprocessing image segmentation brain tumor localization medical ML RCNN BraTS 2020 LGG HGG

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：