检索结果-内蒙古大学图书馆

1st ieee international conference on Advances in computing, Communication and Networking, ICAC2N 2024

作者： Rathore, Rachna Sharma, Yash Ambika, P. Upadhyay, Amit Kumar Mahajan, Samriti Kumar, Rupendra Jiwaji University Dept. of Mathematics Gwalior India CSE-APEX Chandigarh India Meenakshi A.H.E.R Dept. of Commerce Chennai India Mangalayatan University Dept. of Computer Engineering & Applications Aligarh India Lingayas Vidyapeeth University Dept. of Commerce & Management Faridabad India JS University Dept. Computer Science Shikohabad India

ISBN: (纸本)9798350356816

In today's world, financial fraud poses a real threat to global economies, necessitating robust detection systems. Utilizing data mining methods in fraud detection has emerged as a new approach, offering powerful tools, especially with large financial transaction datasets. This paper explores various Data Mining techniques applied in Financial Fraud Detection, including decision trees, neural networks, and clustering methods, highlighting their effectiveness in identifying fraud. As decision trees can easily classify & predict transactions based on this historical data, it helps to recognize fraudulent activities. Neural networks can improve the accuracy of predicting fraudulent transactions by detecting intricate patterns, they are capable & adaptable for learning even odd more. Data points that are close together with each other end up in the same cluster - revealing outliers such as fraud;which would appear to be a point very distant from its neighbours. The adoption of these methodologies within financial systems prevents fraud before a crime has been committed, allowing for the resources & time spent on manual investigation to be reallocated. In addition, the development of machine-learning solutions & further enhancements in artificial intelligence allows for specialized fraud prevention methods to evolve. This abstract emphasises the importance of data mining for financial security which also points at some on-going research in this area. © 2024 ieee.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

real-time Camera-to-Lidar Calibration for Autonomous Robotic systems at the Edge

Real-Time Camera-to-Lidar Calibration for Autonomous Robotic...

引用

2023 ieee international conference on Big Data, BigData 2023

作者： Wang, Ju Dasari, Venkat R. Geerhart, Billy Rapp, Brian Wang, Peng Virginia State University PetersburgVA United States DEVCOM ARL Army Research Office Aberdeen Proving GroundMD United States DEVCOM Army Research Laboratory Aberdeen Proving GroundMD United States

ISBN: (纸本)9798350324457

The research in this paper proposes a novel method for online camera-to-lidar calibration, which aligns the parameters of both lidar and camera sensors during run-time without requiring manual annotations or specialized equipment. The proposed method leverages the robot's motion and observability constraints to optimize the parameters, resulting in improved accuracy and robustness compared to traditional methods. The approach consists of two main components: a motion-based module that estimates the parameters using the robot's motion, and an observation-based module that refines the estimated parameters using observability constraints. The method is implemented on popular edge computing platforms and evaluated through experiments in various environments. The results demonstrate the superiority of the proposed method over baseline approaches, showcasing its potential for practical applications. The design of our algorithm and results of its testing on edge computing platforms will be discussed in this paper. © 2023 ieee.

关键词： 3D object detection calibration edge computing LIDAR Robotics

来源：评论

学校读者我要写书评

暂无评论

TaPaSCo-AIE: An Open-Source Framework for Streaming-based Heterogeneous Acceleration using AMD AI Engines

TaPaSCo-AIE: An Open-Source Framework for Streaming-based He...

引用

1st international conference on Smart Energy systems and Artificial Intelligence (SESAI)

作者： Heinz, Carsten Kalkhof, Torben Lavan, Yannick Koch, Andreas Tech Univ Darmstadt Embedded Syst & Applicat Grp Darmstadt Germany

ISBN: (纸本)9798350364613;9798350364606

AMD AI Engines (AIEs) extend the design space and open up new options for coarse -grained processing in re-configurable accelerators. Pure FPGA designs for machine learning often struggle to compete with the high clock frequencies of GPUs for data -intensive workloads with only limited control flow. Having AIEs available on-chip with an FPGA fabric allows for low -latency co -processing and permits parts of an application to be placed on the most suitable kind of processing unit. Many data -heavy workloads, particularly in the AI domain, benefit from data streaming. With TaPaSCo-AIE, we present a framework for heterogeneous systems centered around data streams. Our framework focuses on AMD Versal devices and incorporates AI Engines and 100G network. We demonstrate the efficient use of TaPaSCo-AIE in a real -world evaluation based on a neural network, and achieve significant performance improvements over CPUs, and even exceed the performance of an AIM GPU.

关键词： FPGA Versal AI Engine Heterogeneous computing Network

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Weather Monitoring System with Intelligent Design and XGBoost Regression

Low-Cost Weather Monitoring System with Intelligent Design a...

引用

2023 international conference on Evolutionary Algorithms and Soft computing Techniques, EASCT 2023

作者： Vishnu Vilashini, S. Kishore, S. Nair, Rekha. R. Babu, Tina Bhadani, Anant Thanushree, G.R. Dixit, Anuj Kumar Dayananda Sagar University School of Engineering Department of Computer Applications Bengaluru India Nitte Institute of Professional Education Department of Computer Applications Karnataka India Allaince University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350313413

Weather monitoring is a critical aspect of weather forecasting and analysis, providing essential data for decision-making in various sectors. However, traditional weather monitoring systems face limitations such as high costs, limited accuracy, and inadequate coverage. The proposed system addresses these challenges by utilizing the Internet of Things (IoT) technology and NodeMCU, a low-cost microcontroller. The novelty of this work lies in the implementation of a cost-effective weather monitoring system that accurately forecasts upcoming weather conditions. Notably, the XGBoost Regression model emerges as the top performer, exhibiting exceptional accuracy with a mean absolute error (MAE) of 0.0213 indicating high accuracy in weather prediction. This innovative approach not only provides an affordable solution but also demonstrates the system's advanced capability to predict future weather patterns. Utilizing a NodeMCU board, real-time sensor data is gathered and transmitted to ThingSpeak's cloud server for analysis. This methodology has the potential for future applications in industries such as agriculture, transportation, and disaster management. © 2023 ieee.

关键词： NodeMCU real-time monitoring Recursive feature elimination ThingSpeak Weather prediction XGBoost Regression

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of embedded High-Temperature Doubly Salient Electro-Magnetic Starter/Generator for Aviation

引用

ieee TRANSACTIONS ON INDUSTRY applications 2023年第6期59卷 7126-7136页

作者： Jiang, Siyuan Zhou, Bo Xiong, Lei Yu, Xiaodong Shi, Hongjun Ren, Chengbo Henan Polytech Univ Sch Elect Engn & Automat Jiaozuo 454003 Peoples R China Henan Int Joint Lab Direct Drive & Control Intelli Jiaozuo 454003 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 210016 Peoples R China Ningbo Jingcheng Car Ind Co Ltd Ningbo 315105 Peoples R China

In view of the high temperature operation characteristics of the embedded starter/generator for the more electric engine (MEE), the influence of material property change on motor performance at high temperature is studied. Furthermore, considering the influence of high temperature, the electromagnetic calculation of doubly salient electro-magnetic machine (DSEM) is carried out, and the excitation design principle of DSEM under high temperature is pointed out. The performance of DSEMs using DW310 silicon steel and 1J22 iron-cobalt alloy material was compared. Based on the silicon steel material, the structural parameters of DSEM are analyzed. According to the key parameters obtained from structural parameter analysis, Box-Behnken method and genetic algorithm were used to carry out the multi-parameter and multi-objective optimization design. The optimization objectives include excitation current, voltage ripple and cogging torque, to meet the torque and power quality requirements of MEE. Then the performance of DSEM at room temperature and high temperature is analyzed by the finite element method, which verifies the effectiveness of the design. Finally, a high-temperature and high-speed DSEM prototype was processed. At the same time, in order to cooperate with the test, a DSEM ground simulation test system platform for MEE was built to test the prototype. Its design experience lays a foundation for the embedded DSEM design of more electric aircraft.

关键词： Doubly salient electro-magnetic machine high temperature more electric engine multi-objective optimization structural parameters

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Feature Fusion with Fuzziness based Semi-Supervised Learning for Alzheimer's Disease Diagnosis

Multi-Modal Feature Fusion with Fuzziness based Semi-Supervi...

引用

2024 ieee international conference on computing, applications and systems, COMPAS 2024

作者： Bushra, Umme Habiba Chowdhury Priya, Fahmida Patwary, M. Jamshed Alam International Islamic University Chittagong Department of Computer Science and Engineering Chattogram Bangladesh Chittagong University of Engineering and Technology Institute of Information and Communication Technology Chattogram Bangladesh

ISBN: (纸本)9798331529765

Alzheimer's disease is a prominent kind of dementia that is caused by a slow decline of cognitive abilities, including memory loss, impaired speech and diminished reactivity. The condition primarily affects brain regions responsible for cognition, memory and language and typically becomes apparent after the age of 60, with a greater risk among older individuals. To meet the requirement for early identification, researchers have explored various machine-learning techniques. To enhance the accuracy of diagnosing Alzheimer's disease, researchers have employed supervised and unsupervised learning approaches derived from machine learning. While supervised learning relies on labelled data, obtaining sufficient labelled samples can be time-consuming and requires specialized assistance. The focus is on multiclass classification, harnessing MRI and PET data. SGLDM and SIFT feature extraction algorithms are utilized to enable the fusion of features from diverse perspectives, resulting in a robust classification model. This research introduces a novel strategy for AD diagnosis, combining multimodal feature fusion with a fuzziness-based-semi-supervised learning method. The method leverages both labeled and mislabeled data to enhance the model's reliability. The proposed method demonstrated notable enhancements in the classifier's performance compared to existing approaches on the dataset. © 2024 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Privacy-Preserving Model for IoMT Medical systems 6

A Blockchain-Based Privacy-Preserving Model for IoMT Medical...

引用

6th international conference on Blockchain computing and applications, BCCA 2024

作者： Alsadhan, Afnan Alsalamah, Hessah Alhogail, Areej Information Systems Department King Saud University Riyadh Saudi Arabia

ISBN: (纸本)9798350351538

The Internet of Medical Things (IoMT) is a rapidly growing field involving the use of interconnected medical devices, sensors and systems for healthcare applications. The use of IoMT has the potential to revolutionize the healthcare industry by improving patient medication outcomes, increasing efficiency and reducing costs. However, the widespread adoption of IoMT also raises concerns about privacy and security, as it involves collecting, processing and sharing sensitive medical data. One of the main challenges in IoMT lies in ensuring the privacy and security of medical data while enabling the necessary data sharing and analysis to support healthcare applications. To address the limitations and ongoing challenges in this field, this paper presents a state-of-the-art system that utilizes permissioned blockchain and fully homomorphic encryption optimization to preserve medical data privacy in IoMT systems. The application of hybrid data classification before encryption is proposed, as this would enhance privacy and reduce processing time. For the Saudi healthcare sector, this hybrid classification model will involve a combination of the Health Insurance Portability and Accountability Act (HIPPA) identifiers and the Saudi Authority for Data and Artificial Intelligence (SDAIA) personal data protection standards. The latest technologies will be utilized in this research to achieve the highest level of performance and enhance data privacy. © 2024 ieee.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

REMOTE: Re-thinking Task Mapping on Wireless 2.5D systems-on-Package for Hotspot Removal 31

REMOTE: Re-thinking Task Mapping on Wireless 2.5D Systems-on...

引用

31st IFIP/ieee international conference on Very Large Scale Integration (VLSI-SoC)

作者： Medina, Rafael Huang, Darong Ansaloni, Giovanni Zapater, Marina Atienza, David Ecole Polytech Fed Lausanne Embedded Syst Lab ESL Lausanne Switzerland HES SO REDS Inst Delemont Switzerland

ISBN: (纸本)9798350325997

2.5D systems-on-Package (SoPs) are composed by several chiplets placed on an interposer. They are becoming increasingly popular as they enable easy integration of electronic components in the same package and high fabrication yields. Nevertheless, they introduce a new bottleneck in inter-chiplet communication, which must be routed through the interposer. Such a constraint favors mapping related tasks on computing cores within the same chiplet, leading to thermal hotspots. Inpackage wireless technology holds promise to reconsider such a position because integrated wireless antennas provide low-latency and high-bandwidth communication paths, thus bypassing the interposer bottleneck. Furthermore, in this work, we propose a new task mapping heuristic that leverages in-package wireless technology to improve the thermal behavior of 2.5D SoPs executing complex applications. Combining system simulation and thermal modeling, our results show that we can distribute computation in wireless 2.5D SoPs to reduce peak temperatures by up to 24% through task mapping with a negligible performance impact.

关键词： Task mapping In-package wireless communication Thermal management Multi-chiplet systems

来源：评论

学校读者我要写书评

暂无评论

Improved Memory Contention Analysis for the 3-Phase Task Model

Improved Memory Contention Analysis for the 3-Phase Task Mod...

引用

ieee international conference on embedded and real-time computing systems and applications (RTCSA)

作者： Jatin Arora Syed Aftab Rashid Geoffrey Nelissen Claudio Maia Eduardo Tovar CISTER ISEP Porto Portugal VORTEX CoLab Portugal Hitachi Energy Research Baden-Dattwil Switzerland Eindhoven University of Technology Eindhoven the Netherlands

ISBN: (数字)9798350387957

ISBN: (纸本)9798350387964

In multiprocessor-based real-time systems, main memory is identified as a major bottleneck in the worst-case timing analysis of tasks. Phased execution models such as the 3-phase task model, i.e., that divides the execution of tasks into distinct computation and memory phases, have shown to be a good candidate to tackle the memory contention problem. The 3-phase execution model in particular has gained much attention from both academia and industry as it limits when tasks can access main memory to pre-defined phases. Information on when those phases may happen and their length can then be leveraged to build a fine-grained memory contention analysis. However, the existing work that focus on the memory contention analysis for 3-phase tasks may overestimate the memory contention caused by interfering write requests. This yields pessimistic bounds on the total memory contention suffered by tasks which in turn leads to pessimistic worst-case execution time (WCET) and worst-case response time (WCRT) bounds. In this work, we improve the state-of-the-art memory contention analysis for 3-phase tasks by (i) tightly bounding the memory contention that can be suffered due to write requests; and (ii) providing a new memory contention-aware WCET analysis.

关键词： Industries Analytical models Computational modeling real-time systems Timing time factors

来源：评论

学校读者我要写书评

暂无评论

Extension of Single Particle Model with electrolyte and Temperature (SPMeT) for real-time Performance and Safety Monitoring of Battery Energy Storage systems (BESS) in Grid Service 17

Extension of Single Particle Model with electrolyte and Temp...

引用

17th Annual ieee international systems conference (SysCon)

作者： Chundru, Venkata Rajesh Downing, Walter D., Jr. Sarlashkar, Jayant Surampudi, Bapi Southwest Res Inst San Antonio TX 78237 USA

ISBN: (纸本)9781665439947

In modern smart grid systems stability and reliability are important criteria due to the inclusion of multiple distributed energy sources such as photovoltaic (PV) and wind power generation. Battery energy storage systems (BESS) are key in enabling this objective of stable grid operation through ancillary grid services such as frequency regulation and energy arbitrage [1] [2]. However, these systems are subject to frequent transient operation under varying environmental conditions leading to significant performance degradation. Accurate prediction and control of battery charge and discharge processes is essential to ensure the safe and reliable operation of these systems. This work focuses on developing a controls-oriented model for Nickel-Manganese-Cobalt oxide (NMC) chemistry lithium-ion batteries based on the existing single-particle model with electrolyte and temperature (SPMeT) from the literature. This work extends the SPMeT model by adding aging mechanisms due to lithium plating on the cell anode during the charging process along with SEI growth. The SEI growth rate was attributed to both capacity and power fade. The lithium plating state tracks the loss in the inventory of cyclable lithium leading to a nonlinear drop in the capacity of the cells. Concurrent with these mechanisms the model tracks the growth of dendrites on the anode as a function of lithium plating. These aging mechanisms enable mitigation of aging for grid-connected cells by active management of charge profile in a model-based controls scheme. The dendrite growth estimate can be used for prognostics and schedule replacement of the cells to prevent battery fires. This model was calibrated using the data from LG M50T cells from automotive applications and later modified to work for grid duty applications. The resultant model is real-time compatible and battery management system (BMS)-friendly and can be used to study the impact of different grid duty cycles on battery life.

关键词： battery energy storage degradation safety grid duty cycles physics-based model battery model controls BMS

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：