检索结果-内蒙古大学图书馆

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Okechukwu Clement Agomuo Agomuo Kingsley Uzoma Zohaib Khan Agomuo Ijeoma Otuomasirichi Junaid Hussain Muzamal Department of Operations and Information Systems University of Utah Salt Lake City USA Center for Environmental Management and Green Energy University of Nigeria Enugu Nigeria dept. of Software Engineering FAST - NUCES Lahore Pakistan Department of Agricultural Economics University of Nigeria Enugu Nigeria Fast School of computing Fast - NUCES Lahore Pakistan

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

The rapid evolution of digital financial services has significantly increased the vulnerability of financial systems to fraudulent activities. Traditional machine learning models have offered substantial progress in detecting fraudulent transactions; however, they often lack adaptability and transparency, critical for dynamic financial environments and regulatory compliance. This paper introduces a novel approach that integrates Deep Reinforcement Learning (DRL) with Explainable Artificial Intelligence (XAI) to enhance fraud detection capabilities in cloud-based financial platforms. Our model, tested on the synthetic PaySim mobile money transaction dataset, leverages the adaptive nature of DRL to continuously learn and update its fraud detection strategies based on evolving transaction patterns. Concurrently, the integration of XAI provides clear, interpretable insights into the decision-making process, thus ensuring transparency and building trust. The proposed model demonstrates superior performance with an achieved accuracy of 99.5% and an Fl-score of 99.0%, significantly outperforming traditional fraud detection systems. These results not only underscore the efficacy of our model in improving the accuracy of fraud detection but also highlight its capability in offering significant improvements in understanding the underlying reasons for each decision, thereby aiding compliance with financial regulations. The practical implications of this research highlight its potential to provide a robust, scalable, and transparent solution for realtime fraud detection, which is essential for safeguarding the integrity of modern financial systems.

关键词： Adaptation models Accuracy Explainable AI Scalability Decision making Predictive models Regulation Fraud Security Standards

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Decision Management: Multi-Modal Analytics in a Health Case Study

Data-Driven Decision Management: Multi-Modal Analytics in a ...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Okechukwu Clement Agomuo Zohaib Khan Agomuo Ijeoma Otuomasirichi Agomuo Kingsley Uzoma Junaid Hussain Muzamal Department of Operations and Information Systems University of Utah Salt Lake City USA dept. of Software Engineering FAST - NUCES Lahore Pakistan Department of Agricultural Economics University of Nigeria Enugu Nigeria Center for Environmental Management and Green Energy University of Nigeria Enugu Nigeria Fast - NUCES Fast School of computing Lahore Pakistan

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

In an era where data is abundant yet underutilized, organizations across various sectors face challenges in extracting actionable insights from complex, multi-modal datasets. To address these challenges, this study proposes a versatile data analytics framework designed to enhance predictive accuracy and support informed decision-making. The framework integrates structured and unstructured data, leveraging advanced Transformer architectures to capture temporal dynamics and complex interactions within the data. In a healthcare use case, the framework demonstrated its effectiveness by achieving an Accuracy of 0.854, an F1-Score of 0.895, and an AUC-ROC of 0.930, significantly outperforming traditional models. By incorporating SHAP for interpretability, the framework ensures that its predictions are both accurate and transparent, making it a valuable tool for decision-makers. While healthcare is one application, the framework's flexibility allows it to be adapted to a wide range of industries. Future work will focus on validating the framework across different sectors and integrating it into operational workflows to optimize decision-making and outcomes.

关键词： Accuracy Decision making Mortality Medical services Organizations Predictive models Transformers Data models Information management X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Empirical Analysis of Termination Criteria in the Genetic Algorithms for Wind Farm Micrositing

A Preliminary Empirical Analysis of Termination Criteria in ...

引用

International Symposium on Advanced Electrical and Communication Technologies (ISAECT)

作者： Mohamed Mohandes Salman A. Khan Shafiqur Rehman Ali Al-Shaikhi Bo Liu Kashif Iqbal Electrical Engineering Dept. King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia College of Computing and Information Sciences Karachi Institute of Economics and Technology Karachi Pakistan Interdisciplinary Research Center for Sustainable Energy Systems (IRC-RES) King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

ISBN: (数字)9798331529987

ISBN: (纸本)9798331529994

Wind energy has evolved as a leading source of renewable energy. The harnessing of maximum wind energy from a wind farm is governed by many factors. One key factor is the optimal layout design of the wind farm. This layout defines the optimal placement of wind turbines within the farm. The sheer complexity of identifying this optimal layout in presence of various technical constraints makes the wind farm micrositing (WFM) an NP-hard optimization problem. The problem is generally solved with nature-inspired algorithms (NIAs) whose performance depends on several parameters. Among these, the algorithm termination condition plays a crucial role since it determines the right amount of time required by the algorithm to converge. In the context of WFM problem, this study proposes several termination criteria while using the genetic algorithm as the test bench. Performance of six termination criteria is empirically evaluated with respect to the quality of solutions produced and the execution time involved. Results indicate that among the various criteria tested, the Running mean and Phi were the best in terms of quality of solution and runtime, respectively.

关键词： Renewable energy sources Runtime Wind energy Layout Simulated annealing Wind farms Wind turbines Complexity theory Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Analysis of Different Grid Sizes for Wind Farm Micrositing Using an Evolutionary Algorithm for Turaif, Saudi Arabia

A Preliminary Analysis of Different Grid Sizes for Wind Farm...

引用

International Symposium on Advanced Electrical and Communication Technologies (ISAECT)

ISBN: (数字)9798331529987

ISBN: (纸本)9798331529994

Wind energy has brought a revolution in the domain of renewable energy, and is gradually replacing the traditional fossil fuels. A major challenge in harnessing maximum wind energy from a wind farm is the efficient placement of turbines within the farm, known as wind farm micrositing (WFM). The problem is classified as an NP-hard problem and therefore optimization algorithms from the domain of evolutionary computation and swarm intelligence have been traditionally employed. The optimal micrositing depends on several key factors, such as land topography, wind speed, wind direction, and grid size. While significant research has been carried out on many of these factors, the study on the impact of grid size on wind power generation has received little attention. This study provides a preliminary analysis on the impact of various unconventional grid sizes such as 11×11, 12×12, up to 15×15 through the use of a genetic algorithm. The performance is measured both in terms of the quality of solution produced as well as the execution time. Results indicate that increase in the grid size has a positive impact on the quality of solution, measured through conversion efficiency. However, the correlation between algorithmic execution time and grid size is almost negligible, as a change in grid size does not affect the execution time of the algorithm.

关键词： Correlation Wind energy Wind speed Wind farms Wind power generation Size measurement Time measurement Particle swarm optimization Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Repairing with Zero Skip Cost

arXiv

引用

arXiv 2024年

作者： Zhang, Wenqin Chee, Yeow Meng Dau, Son Hoang Etzion, Tuvi Kiah, Han Mao Luo, Yuan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Dept. of Industrial Systems Engineering and Management National University of Singapore Singapore School of Computing Technologies RMIT University MelbourneVIC Australia Computer Science Faculty Technion Israel Institute of Technology School of Physical and Mathematical Sciences Nanyang Technological University Singapore

To measure repair latency at helper nodes, we introduce a new metric called skip cost that quantifies the number of contiguous sections accessed on a disk. We provide explicit constructions of zigzag codes and fractio...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Pose Estimation Using Media-Pipe an Artificial Intelligence Applications in Health and Fitness

Real-Time Human Pose Estimation Using Media-Pipe an Artifici...

引用

Artificial Intelligence and Signal Processing (AISP), INDIA, International Conference on

作者： Ketan Totlani Shiva S. Dhavala S Sandeep Kumar Vijayarao Yagnesh Challagundla B Roy Eugenia R. Zhuo School of Computer and Systems Sciences Jaipur National University Rajasthan India School of Information Science and Engg. Rashtreeya Vidyalaya College of Engineering Bengaluru India Dept. of Computer Science and Engineering RM.K Engineering College Kavaraipettai Tamil Nadu India School of Electronics Engineering VIT-AP University Amaravati Andhra Pradesh India College of Information and Computing Sciences University of Santo Tomas Manila Philippines

ISBN: (数字)9798350350654

ISBN: (纸本)9798350350661

Significant progress has been achieved in the fields of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in recent years. Nevertheless, a significant gap continues to exist in the effective surveillance of human actions, activities, and the recognition of human movements or poses. Machines and computers are fundamentally incapable of comprehending human activities without user intervention. Consequently, we now depend on technology to record and archive human actions through live broadcast data, videos, or images. The field of pose estimation, which is a critical area of research with applications in fields such as Augmented Reality, Animation, Gaming, Healthcare, and Sports, is expanding due to the rapid advancement of computer vision technology. This project implements innovative methods to train models and deter- mine poses, utilizing random inputs from internet images, videos, and live streaming. In particular, models that have been trained with artificial intelligence have been created for daily physical activities that necessitate intricate pose estimation. The initial step in the project is to utilize MediaPipe to estimate the poses of the human body. Subsequently, the angles between the body joints are calculated to create the desired models. Additionally, a web-based user interface (WEB-UI) was developed to enable access from any location. The methodology involves the extraction of data from critical body locations, the framing of models, and the utilization of the MediaPipe model due to its superior performance and features in comparison to other models. The objective of this method is to develop a web application for end-users, train AI models for daily physical activities, and establish an efficient system for single human pose estimation. This approach provides a cost-effective alternative to physical trainers and enables the monitoring of health and sports activities to be enhanced.

关键词： Deep learning Computational modeling Pose estimation Data visualization Feature extraction Data models Artificial intelligence Recommender systems Videos Sports

来源：评论

学校读者我要写书评

暂无评论

Pairs in Nested Steiner Quadruple systems

arXiv

引用

arXiv 2024年

作者： Chee, Yeow Meng Dau, Son Hoang Etzion, Tuvi Kiah, Han Mao Zhang, Wenqin Dept. of Industrial Systems Engineering and Management National University of Singapore Singapore School of Computing Technologies RMIT University MelbourneVIC3000 Australia Computer Science Faculty TechnionIsrael Institute of Technology Haifa3200003 Israel School of Physical and Mathematical Sciences Nanyang Technological University Singapore School of Electronic Information and Engineering Shanghai Jiao tong University China

Motivated by a repair problem for fractional repetition codes in distributed storage, each block of any Steiner quadruple system (SQS) of order v is partitioned into two pairs. Each pair in such a partition is called a nested design pair and its multiplicity is the number of times it is a pair in this partition. Such a partition of each block is considered as a new block design called a nested Steiner quadruple system. Several related questions on this type of design are considered in this paper: What is the maximum multiplicity of the nested design pair with minimum multiplicity? What is the minimum multiplicity of the nested design pair with maximum multiplicity? Are there nested quadruple systems in which all the nested design pairs have the same multiplicity? Of special interest are nested quadruple systems in which all the (v2) pairs are nested design pairs with the same multiplicity. Several constructions of nested quadruple systems are considered and in particular classic constructions of SQS are examined. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Eco-Sustainability and Green Analytics Model to Measure the Performance of Big Data systems

Towards Eco-Sustainability and Green Analytics Model to Meas...

引用

International Conference on Information Management (ICIM)

作者： Yusmadi Yah Jusoh Rusli Abdullah Rozi Nor Haizan Nor Jamaiah Hj. Yahaya Shireen Muhammad Aishwharya Raani Arunachalam Dept. of Software Engineering and Information Systems Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang Malaysia Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Faculty of Communication Visual Art and Computing Universiti Selangor (UNISEL) Selangor Malaysia

Many BDS is doomed to failure because of the missing knowledge on measuring the performance of BDS. The failure to identify the performance measurement and correct will make the problems worsen. This will complicate the efforts of fixing such problems and more importantly, will affect the quality of knowledge, insights, and results expected by the users in the future. In achieving durable performance, the organization needsto understand the factors that contribute to the performance of the eco-sustainability and green analytics metrics for BDS. Although the existence of its importance and awareness was largely neglected. Therefore, the eco-sustainability and green analytic measurement of the BDS is examined in this research. Measuring the BDS performance has the benefit of identifying problems and launching corrective actions before these problems happen and become worsen. The research will investigate the eco-sustainability and green analytic measures which will be proposed and used to capture performance for each process of BDS. Then, based on such measures and metrics, as well as existing performance concepts, frameworks, and models, a measurement model for BDS will be created. The model will be validated through expert evaluations and confirmatory studies with users and practitioners of BDS users. The research has a greater significance in leveraging existing performance concepts in BDS settings and the research proposes users' participation in the sustainability and continuous performance evaluation of theirBDS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Certain Investigation on IoT Based Cotton Dust Pollution Monitoring in Textile Plants

Certain Investigation on IoT Based Cotton Dust Pollution Mon...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： P Sivanesan Anand J V Trilok Sai Vaddanam Shaik Mohammad Irfan Department of Information Communication Technology School of Computing SASTRA University Thanjavur Tamilnadu India Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Chennai Tamil Nadu India Dept. of Computer science and Business Systems SASTRA University Thanjavur Tamilnadu India Dept.of ECE Siddhartha Academy of Higher Education Vijayawada Andhra Pradesh India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The objective of the work is to track the level of cotton dust in the textile sector. The IoT-enabled cotton dust monitoring system deploys three sensors: Sharp GP2Y1010AU0F; Shinyei PPD42NS; and Honeywell HPMA115S0-XXX measuring the dust levels. The Optical dust sensor GP2Y1010AU0F has a threshold of 1 mg/mS, which is placed inside the mask and when that threshold is crossed, buzzer alerts the worker with the air contaminants. It measures inhaled cotton dust and sends data to IoT, real-time concentration height of dust into the mobile devices. Experimental results show that Sharp GP2Y1010AU0F sensor has achieved award for acquiring the highest mean dust concentration of 95.167 mg/mS with a standard deviation of 3.014 among the three sensors, while Honeywell HPMA115S0-XXX and Shinyei PPD42NS recorded a mean of 87.833 mg/mS and 77.500 mg/mS, respectively. The observed response times of the sensors as follows for GP2Y1010AU0F-8s, HPMA115S0-XXX-6s, and PPD42NS- 5s, recording the fastest response by Honeywell HPMA115S0-XXX. A comparative study in accuracy, precision and sensitivity, with a response time, shows the merits and demerits for each sensor. Results emphasize the effectiveness of the system proposed for monitoring in terms of airborne cotton dust exposure in improving safety in textile workplaces. A meta-analysis is performed with Bayesian framework using JASP software.

关键词： Sensor phenomena and characterization Software Real-time systems Sensors Safety Bayes methods Pollution measurement Cotton Time factors Monitoring

来源：评论

学校读者我要写书评

暂无评论

Refinement of an Epilepsy Dictionary through Human Annotation of Health-related posts on Instagram

arXiv

引用

arXiv 2024年

作者： Min, Aehong Wang, Xuan Correia, Rion Brattig Rozum, Jordan Miller, Wendy R. Rocha, Luis M. Donald Bren School of Information & Computer Sciences University of California IrvineCA United States Luddy School of Informatics Computing & Engineering Indiana University BloomingtonIN United States Instituto Gulbenkian de Ciência Oeiras Portugal Dept. of Systems Science & Industrial Engineering Binghamton University BinghamtonNY United States School of Nursing Indiana University IndianapolisIN United States

Objective — To (1) identify health-related terms used on social media posts that do not precisely match the health-related meaning of terms in a biomedical dictionary, (2) decide which terms need to be removed in order to improve the quality of the dictionary in the scope of biomedical text mining tasks, (3) evaluate the effect of removing imprecise terms on such tasks, and (4) discuss how human-centered annotation complements automated annotation in social media mining for biomedical purposes. Materials and Methods — We used a dictionary built from biomedical terminology extracted from various sources such as DrugBank, MedDRA, MedlinePlus, TCMGeneDIT, to tag more than 8 million Instagram posts by users who have mentioned an epilepsy-relevant drug at least once, between 2010 and early 2016. A random sample of 1,771 posts with 2,947 term matches was evaluated by human annotators to identify false-positives. Frequent terms with a high false-positive rate were removed from the dictionary. To study the effect of removing those terms, we constructed knowledge networks using the refined and the original dictionaries and performed an eigenvector-centrality analysis on both networks. OpenAI’s GPT series models were compared against human annotation. Results — Analysis of the estimated false-positive rates of the annotated terms revealed 8 ambiguous terms (plus synonyms) used in Instagram posts, which were removed from the original dictionary. We show that the refined dictionary thus produced leads to a significantly different rank of important terms, as measured by their eigenvector-centrality of the knowledge networks. Furthermore, the most important terms obtained after refinement are of greater medical relevance. In addition, we show that OpenAI’s GPT series models fare worse than human annotators in this task. Discussion — Dictionaries built from traditional clinical terminology are not tailored for social media language and can bias results when used in biomedical infe

关键词： Eigenvalues and eigenfunctions

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：