检索结果-内蒙古大学图书馆

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Yeboah, Foster Yeboah, Jones Yeboah, George Bampoh, Kofi Nyarko-Boateng, Owusu University of Cincinnati College of Engineering and Applied Science Cincinnati United States University of Cincinnati Maths Physics and Computer Science Department Cincinnati United States EProcess International S.A Information Technology Department Accra Ghana Ipmc School of It Accra Ghana University of Cincinnati School of Information Tevhnology Cincinnati United States

ISBN: (纸本)9798331529529

Loan disbursement is crucial and remains the core to every bank. With the advancement of technology and the proliferation of mobile devices financial institutions are working to bring the banking hall to the doorsteps of their clients. There are systems that allow applicants to apply for loans online. This inadvertently has enormous benefits and risks, but applicants may not be honest providing such data. To minimize risks and maximize benefits, a system for predicting fraud is necessary. This research, through experiments and comparative analysis, confirmed that data mining can effectively assess applicants' creditworthiness. The findings revealed that the Random Forest classifier produced the most robust model, offering the highest classification accuracy among the selected classifiers, with an accuracy rate of 0.7773. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Problem based Learning for Training in Statistics and Artificial Intelligence to Biomedical Engineers 23

Problem based Learning for Training in Statistics and Artifi...

引用

Proceedings of the 15th International Conference on Education Technology and computers

作者： Beatriz Lopez Gloria Mateu Yenny Leal Electrical Electronics and Automation Engineering Department University of Girona Spain Computer Science Applied Maths and Statistics Department University of Girona Spain Medical Science Department University of Girona Spain

ISBN: (纸本)9798400709111

Problem-based learning is a teaching methodology that's is gaining attention for university students. In this work, we present a three years’ experience on the Biomedical Engineering studies, related to learning Statistics and Artificial Intelligence applied to Medicine. Up to five problems have been designed in several areas of Medicine, regarding the use of data for supporting decision making. The results are evaluated in terms of the academic outcomes and the students’ satisfactions. Challenges addressed include the progressively adaptation of the evaluation methodology, balancing team and individual assessment.

关键词： Artificial Intelligence Biomedical Engineering Medicine Statistics

来源：评论

学校读者我要写书评

暂无评论

On the Decentralization of Mobile Crowdsensing in Distributed Ledgers: An Architectural Vision

On the Decentralization of Mobile Crowdsensing in Distribute...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Lorenzo Gigli Federico Montori Mirko Zichichi Luca Bedogni Stefano Ferretti Marco Di Felice Department of Computer Science and Engineering University of Bologna Italy IOTA Foundation Berlin Germany Faculty of Maths and Physics University of Modena and Reggio Emilia Italy Department of Pure and Applied Sciences University of Urbino Italy

Mobile Crowdsensing (MCS) is a paradigm where a crowdsourcer recruits a set of workers through a campaign to collect data using sensors in their mobile device. This process greatly reduces the costs of data collection processes; however, most of the historically proposed systems are centralized. Since this makes the MCS platform a single point of failure, there is an increasing interest in decentralized blockchain-based solutions; regardless, most of the current proposals have a vertical focus and do not account for the heterogeneity of MCS. We propose a decentralized high-level architecture for MCS, based on Distributed Ledger Technology (DLT), that is adaptable to most MCS deployments. We then implement our architecture using the IOTA protocols and evaluate its performance over a real deployment in terms of scalability, showing its advantages over classic blockchains for MCS data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards a CIA compliant RSA hybrid built on an Artificial Neural Network 3

Towards a CIA compliant RSA hybrid built on an Artificial Ne...

引用

3rd International Multidisciplinary Information Technology and Engineering Conference, IMITEC 2021

作者： Magoma, Promise Chibaya, Colin University of Venda Dept of Mathematics and Applied Maths Thohoyandou South Africa Sol Plaatje University Dept of Computer Science and Info Tech. Kimberley South Africa

ISBN: (纸本)9781665417495

This study investigates the improvement of the RSA algorithm by incorporating a neural network to learn data integrity and data authenticity towards creating a CIA-compliant hybrid RSA model. This is the first time a neural network has been proposed for improving the RSA model towards CIA compliance. Experimental results indicate that a neural network can learn data integrity and data authenticity in RSA encrypted messages. Data analysis affirmed that the neural network learning can be generalized. A conclusion that the RSA algorithm can be upgraded towards CIA compliance when a neural network is incorporated was arrived at. These findings have implications for the commercial standing of the RSA algorithm as well as for the body of knowledge in the cryptography domain. © 2021 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

EXTREMAL AND CONTINUA SOLUTIONS FOR STOCHASTIC FRACTIONAL DIFFERENTIAL EQUATIONS

引用

Journal of Mathematical sciences (United States) 2025年 1-15页

作者： Benhamida, Ouafaa Dahmani, Zoubir Ibrahim, Rabha W. Laboratory of Pure and Applied Maths Faculty of Sciences UMAB Mostaganem Algeria Near East University Mathematics Research Center Department of Mathematics Near East Boulevard Nicosia /Mersin 10 99138 Türkiye Department of Computer Science and Mathematics Lebanese American University Beirut 13-5053 Lebanon Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq Laboratory of LAMDA-RO Faculty of Sciences University of Blida 1 Blida 09000 Algeria

The aim of this work is to study two classes of stochastic fractional differential equations via the application of the method of upper and lower solutions combined with the Arzela-Ascoli theorem. We begin by proving an auxiliary result for the integral representation of an Airy-type stochastic problem. The specific symmetry features of an Airy-type stochastic problem depend on the form of the stochastic differential equations (SDE) and the relevant coefficients, it is vital to note. To comprehend each issue’s unique symmetries and their effects, a thorough investigation is necessary. Then, we prove an existence result for extremal solutions for the same problem. Another class of stochastic equations of higher-order type is also studied. We also present some examples to show the validity of the obtained results. At the end, a conclusion follows. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Airy equation Extremal solutions Fractional calculus Fractional differential operator Stochastic fractional differential equation Upper and lower method

来源：评论

学校读者我要写书评

暂无评论

The efficient frontiers of mean-variance portfolio rules under distribution misspecification

The efficient frontiers of mean-variance portfolio rules und...

引用

International Conference on Information Fusion

作者： Andrew Paskaramoorthy Tim Gebbie Terence L. Van Zyl School of Computer Science and Applied Maths University of the Witwatersrand Johannesburg South Africa

ISBN: (纸本)9781665414272

Mean-variance portfolio decisions that combine pre-diction and optimisation have been shown to have poor empirical performance. Here, we consider the performance of various shrinkage predictors by their efficient frontiers under different distributional assumptions to study the impact of reasonable departures from Gaussianity. Namely, we investigate the im-pact of first-order autocorrelation, second-order autocorrelation, skewness, and excess kurtosis. We show that the shrinkage predictors tend to rescale the sample efficient frontier, which can change based on the nature of local perturbations from Gaussianity. This rescaling implies that the standard approach of evaluating decision rules for a fixed level of risk aversion can give a misleading impression of comparative performance, and more so in a dynamic market setting. Our results suggest that comparing efficient frontiers has serious implications which oppose the prevailing thinking in the literature. Namely, that sample estimators out-perform Stein type estimators of the mean, and that improving the prediction of the covariance has greater importance than improving that of the means.

关键词： Measurement Analytical models Perturbation methods Conferences Autocorrelation Covariance matrices Portfolios

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Tree Classifiers to Mitigate Fraud in Electronic Loan Application

Comparative Analysis of Tree Classifiers to Mitigate Fraud i...

引用

Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), IEEE International Conference on

作者： Foster Yeboah Jones Yeboah George Yeboah Kofi Bampoh Owusu Nyarko-Boateng College of Engineering and Applied Science University Of Cincinnati Cincinnati USA Maths Physics and Computer Science Department University Of Cincinnati Cincinnati USA Information Technology Department EProcess International S.A Accra Ghana School of IT IPMC Accra Ghana School of Information Tevhnology University of Cincinnati Cincinnati USA

ISBN: (数字)9798331529529

ISBN: (纸本)9798331529536

Loan disbursement is crucial and remains the core to every bank. With the advancement of technology and the proliferation of mobile devices financial institutions are working to bring the banking hall to the doorsteps of their clients. There are systems that allow applicants to apply for loans online. This inadvertently has enormous benefits and risks, but applicants may not be honest providing such data. To minimize risks and maximize benefits, a system for predicting fraud is necessary. This research, through experiments and comparative analysis, confirmed that data mining can effectively assess applicants’ creditworthiness. The findings revealed that the Random Forest classifier produced the most robust model, offering the highest classification accuracy among the selected classifiers, with an accuracy rate of 0.7773.

关键词： Accuracy Banking Mobile handsets Fraud Blockchains Internet of Things Data mining Artificial intelligence Random forests

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency Trading Agent Using Deep Reinforcement Learning

Cryptocurrency Trading Agent Using Deep Reinforcement Learni...

引用

International Conference on Soft Computing and Machine Intelligence (ISCMI)

作者： Uwais Suliman Terence L. van Zyl Andrew Paskaramoorthy Computer Science and Applied Maths University of the Witwatersrand Johannesburg South Africa Institute for Intelligent Systems University of Johannesburg Johannesburg South Africa Department of Statistical Sciences University of Cape Town Johannesburg South Africa

Cryptocurrencies are peer-to-peer digital assets monitored and organised by a blockchain network. Price prediction has been a significant focus point with various machine learning algorithms, especially concerning cryptocurrency. This work addresses the challenge faced by traders of short-term profit maximisation. The study presents a deep reinforcement learning algorithm to trade in cryptocurrency markets, Duelling DQN. The environment has been designed to simulate actual trading behaviour, observing historical price movements and taking action on real-time prices. The proposed algorithm was tested with Bitcoin, Ethereum, and Litecoin. The respective portfolio returns are used as a metric to measure the algorithm's performance against the buy-and-hold benchmark, with the buy-and-hold outperforming the results produced by the Duelling DQN agent.

关键词： Deep learning Sentiment analysis Machine learning algorithms Reinforcement learning Prediction algorithms Real-time systems Cryptocurrency

来源：评论

学校读者我要写书评

暂无评论

Feature-weighted Stacking for Nonseasonal Time Series Forecasts: A Case Study of the COVID-19 Epidemic Curves

arXiv

引用

arXiv 2021年

作者： Cawood, Pieter van Zyl, Terence L. Computer Science and Applied Maths University of the Witwatersrand Johannesburg South Africa Institute for Intelligent Systems University of Johannesburg Johannesburg South Africa

We investigate ensembling techniques in forecasting and examine their potential for use in nonseasonal time-series similar to those in the early days of the COVID-19 pandemic. Developing improved forecast methods is essential as they provide data-driven decisions to organisations and decision-makers during critical phases. We propose using late data fusion, using a stacked ensemble of two forecasting models and two meta-features that prove their predictive power during a preliminary forecasting stage. The final ensembles include a Prophet and long short term memory (LSTM) neural network as base models. The base models are combined by a multilayer perceptron (MLP), taking into account meta-features that indicate the highest correlation with each base model’s forecast accuracy. We further show that the inclusion of meta-features generally improves the ensemble’s forecast accuracy across two forecast horizons of seven and fourteen days. This research reinforces previous work and demonstrates the value of combining traditional statistical models with deep learning models to produce more accurate forecast models for time-series from different domains and seasonality. © 2021, CC0.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detection of Uncertain Diabetes Mellitus Using Whale Optimization Algorithm in Convolutional Neural Network

Journal of Uncertain Systems

引用

Journal of Uncertain Systems 2022年第3期15卷

作者： Niwariya, Manoj Rajput, Anil Jaloree, Shailesh Department of Computer Applications Makhanlal Chaturvedi National University of Journalism and Communication Madhya Pradesh Bhopal 462011 India Department of Computer Science and Maths Science Government C.S.A Pg College Madhya Pradesh Sehore 466001 India Department of Applied Mathematics Sati Madhya Pradesh Vidisha 464001 India

The purpose of this study is to construct a convolutional neural network (CNN) model based on the Softmax layer to diagnose diabetes. The suggested identification algorithm is developed using data from diabetic and nondiabetic patients in the Indian database PIMA. The training data on dilation of the blood vessels, body mass index (BMI), triceps skin thickness, pregnancy count, heredity, and age are highly accurate. Additionally, the whale optimization algorithm (WOA) is utilized to determine the most pertinent functions in a given context. The suggested system, which is based on CNN capabilities at various resolutions, eliminates the need for a simple manual feature extraction phase by simultaneously capturing and categorizing features in a data neuron network. The proposed solution outperforms standard classification methods and enables a more accurate diabetes diagnosis. © World Scientific Publishing Company.

关键词： CNN diabetes mellitus PIMA database WOA

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：