检索结果-内蒙古大学图书馆

Implementation Graph Database Framework for Credit Card Fraud Detection

Procedia computer science 2023年 227卷 326-335页

作者： Nurrahmi Mauliddiah Suharjito Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia 11480 Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia 11480

Credit card use is becoming more and more commonplace every day. Financial organizations and credit card customers lose a lot of money because of complicated illegal transactions. Fraudsters constantly stay on top of new technology to quickly perpetrate fraud against customer transaction patterns. We analyze credit card transaction networks and identify suspicious patterns, such as transactions connected to multiple accounts or unusual transaction patterns, transactions made at unusual times, and to monitor credit card transactions in real-time and quickly identify suspicious transactions. TigerGraph is used to analyze data, display results on a dashboard, and send notifications via email. One meth’\ Vc 1``13-od commonly used in anomaly detection is to compare data values against the standard deviation. In this research, we explain the use of TigerGraph as a platform for anomaly detection above the standard deviation, as well as the use of the Louvain algorithm in finding merchant communities used by fraudsters. The data used in this study comes from Sparkov simulation data obtained from Kaggle. Our results show that by using TigerGraph, we managed to achieve a very high accuracy rate of 99.77%, precision 82.84%, recall 72.38%, and f1-score 77,26% in predicting transaction fraud on Sparkov simulation data. This is much better than the results reported in a paper that uses the supervised machine learning method with the AdaBoost algorithm which achieves the highest accuracy of 77%.

关键词： Credit card fraud detection TigerGraph Dashboard Alert

来源：评论

学校读者我要写书评

暂无评论

Multimodal Sentimental Classification using Long-Short Term Memory

Multimodal Sentimental Classification using Long-Short Term ...

引用

Integrated Intelligence and Communication systems (ICIICS), International Conference on

作者： Busani Sravani Pushpa Mohan A. H. A. Hussein Gotte Ranjith Kumar P. Umaeswari CSE Malla Reddy Engineering College for Women Hyderabad India Department of computer science and engineering HKBK College of Engineering Bangalore India College of Pharmacy Ahl Al Bayt University Karbala Iraq School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computer Science and Business Systems R.M.K. Engineering College Kavaraipettai India

The increasing popularity of mobile devices and social networks has leads people to share images and text to express their emotions and opinions. This paper proposed a deep learning-based technique for multimodal sentimental analysis. For this work, the CMU-MOSI and CMU-MOSEI dataset is utilized which contains video, audio and text clips. The inputs are in the form of video, audio and text, so individual preprocessing and feature extraction techniques are performed with separate techniques. Then, the extracted features from separate techniques are concatenated and given as input for the classification of sentimental analysis. The Long-Short Term Memory (LSTM) is utilized in this research for classification. The performance metrics like 7-class accuracy (Acc-7), binary accuracy (Acc-2), F1-score, Mean Absolute Error (MAE) and Correlation Coefficient (CORR) are utilized to evaluate the LSTM model. The attained result shows that the LSTM model obtains better Acc-2 of 91.57% on CMU-MOSI dataset and 91.28% of CMU-MOSEI dataset when compared to existing techniques like Multi-Tensor Fusion Network with Cross-Modal Modeling (MTFN-CMM), Sparse and Cross-Attention Network (SCANET) and Sparse and Cross-Attention Network (SCANET).

关键词：

来源：评论

学校读者我要写书评

暂无评论

CoLRIO: LiDAR-Ranging-Inertial Centralized State Estimation for Robotic Swarms

arXiv

引用

arXiv 2024年

作者： Zhong, Shipeng Chen, Hongbo Qi, Yuhua Feng, Dapeng Chen, Zhiqiang Wu, Jin Wen, Weisong Liu, Ming The School of Systems Science and Engineering Sun Yatsen University Guangzhou510006 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Aeronautical and Aviation Engineering Hong Kong Polytechnic University Hong Kong

Collaborative state estimation using different heterogeneous sensors is a fundamental prerequisite for robotic swarms operating in GPS-denied environments, posing a significant research challenge. In this paper, we introduce a centralized system to facilitate collaborative LiDAR-ranging-inertial state estimation, enabling robotic swarms to operate without the need for anchor deployment. The system efficiently distributes computationally intensive tasks to a central server, thereby reducing the computational burden on individual robots for local odometry calculations. The server back-end establishes a global reference by leveraging shared data and refining joint pose graph optimization through place recognition, global optimization techniques, and removal of outlier data to ensure precise and robust collaborative state estimation. Extensive evaluations of our system, utilizing both publicly available datasets and our custom datasets, demonstrate significant enhancements in the accuracy of collaborative SLAM estimates. Moreover, our system exhibits remarkable proficiency in large-scale missions, seamlessly enabling ten robots to collaborate effectively in performing SLAM tasks. In order to contribute to the research community, we will make our code open-source and accessible at https://***/PengYu-team/Co-LRIO. Copyright © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

DT4I4-Secure: Digital Twin Framework for Industry 4.0 systems Security

DT4I4-Secure: Digital Twin Framework for Industry 4.0 System...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Yu-Zheng Lin Sicong Shao Md Habibor Rahman Mohammed Shafae Pratik Satam Department of Electrical and Computer Engineering University of Arizona Tucson AZ USA School of Electrical Engineering and Computer Science University of North Dakota Grand Forks ND USA Department of Systems and Industrial Engineering University of Arizona Tucson AZ USA

The rapid adoption of automation in the Cyber-Physical systems (CPS) is triggering Industry 4.0 (I4.0), integrating cloud computing, machine learning (ML), artificial intelligence (AI), and universal network connectivity into traditionally isolated systems. These I4.0 changes are optimizing the performance of Smart Manufacturing (SM) systems at the cost of increased complexity, exposing I4.0 systems to more cyberattacks than ever before. To address these challenges, this work presents DT4I4-Secure: A Digital Twin Framework for Industry 4.0 Security. The DT4I4-Secure presents a framework to create Digital Twins (DT) for I4.0 systems using a combination of models (including physics and data-based models). This paper showcases the use of the DT framework to detect attacks on I4.0 systems by comparing observations with future predictions from the DT. This paper evaluates the performance of the DT4I4-Secure for a computer Numerical Control (CNC) turning process manufacturing a metallic spool, wherein the experimental results show the model can predict normal operations with a mean absolute error (MAE) of 0.005081. This work also explores using an Exponentially Weighted Moving Average (EWMA) based dynamic threshold instead of a traditional static threshold for attack detection when the CNC turning process is under three separate attack scenarios. The DT4I4-Secure combined with the dynamic threshold shows a 3.46 times improvement in F 1 -Scores over all three attack scenarios for instantaneous attack detection while having 100% accuracy during the manufacturing cycle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring ERP User Behaviour in Developing Countries: Integrating Self-efficacy and UTAUT Perspectives 5

Exploring ERP User Behaviour in Developing Countries: Integr...

引用

5th International Conference on Advancement in Data science, E-Learning and Information systems, ICADEIS 2023

作者： Syamsuar, Dedy Oktaharisetia, Muhammad Angga Witarsyah, Deden Luthfi, Ahmad Dell, Peter Permana, Yudistira Sira Antoni, Darius Bina Nusantara University School of Information Systems Information Systems Department Indonesia Universitas Bina Darma Program Pasca Sarjana Palembang Indonesia Telkom University School of Industrial Engineering Bandung Indonesia Islamic University of Indonesia Faculty of Industrial Technology Department of Informatics Indonesia Curtin University School of Management and Marketing Faculty of Business and Law Australia Politeknik Sekayu Teknik Informatika Sekayu Indonesia Universitas Indo Global Mandiri Faculty of Computer Science Palembang Indonesia

ISBN: (纸本)9798350303414

ERP stands for enterprise resource planning. It is an information system that is all rolled into one, is very flexible and adaptable, and optimizes business operations while also centralizing all of the company's data. This study aims to empirically investigate the elements that affect users' intention and usage of enterprise resource planning (ERP). This research incorporates self-efficacy into the unified theory of acceptance and use of technology (UTAUT2). A quantitative technique was taken, and as a result, 143 replies that might be used were effectively collected. After that, the information was put through a structural equation modelling partial least square (SEM-PLS) analysis. According to the findings of this research, self-efficacy appears to have a significant influence on all endogenous variables (EE, BI, and UB), as indicated by t-values of 3.951, 7.573, and 5.492, respectively. In addition, the analysis also indicated that PE (4.317), EE (2.397), and HM (3.084) are likewise statistically and substantively significant to BI. The result shows that the R2 for BI and UB indicate a moderate impact of 0.603 and 0.521, respectively. It is suggested that the model has valuable applications in academic and real-world contexts. © 2023 IEEE.

关键词： Enterprise resource planning

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue Detection

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue D...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Xie, Shuaiyue Chuah, Joong Huang Chai, Grace Mei Ting Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur50603 Malaysia Smart Manufacturing Systems Research Group University of Southampton Malaysia Johor Iskandar Puteri79100 Malaysia

ISBN: (纸本)9798350341072

Driver fatigue is a significant cause of road accidents. Effective real-time fatigue detection systems are necessary to improve road safety. Utilizing a lightweight and fast model and creating an effective fatigue judgment rule is important in detecting fatigue in real-time. In this research, we propose a fatigue detection model based on You Look Only Once version 8 (YOLOv8) model to detect driver's facial features and use percentage of eyelid closure over the pupil over time (PERCLOS) and Percentage of Open Mouth (POM) indicators to identify fatigue. This research is divided into two parts. The first part involves creating, labeling, and preprocessing the dataset. We use the YawDD dataset as the original dataset and manually label a new dataset using the Roboflow platform. We then preprocessed the new dataset to train the YOLOv8 model for face features detection. In the second part, we established a multi-indicator fatigue determination rule that uses PERCLOS and POM indicators and set a threshold to determine whether the driver is fatigue. By combining the YOLOv8 model with the fatigue determination rules based on PERCLOS and POM, we successfully built a model to identify a driver's fatigue. Finally, the fatigue detection model based on YOLOv8 achieves a high accuracy rate of 96.9% and a high speed of 11.4 ms/frame in face features detection, surpassing other traditional models and previous generations of YOLO models. This model can effectively detect fatigue in both driver-driving pictures and videos. © 2023 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Apache Spark Powered: Enhancing Network Intrusion Detection System Using Random Forest

Apache Spark Powered: Enhancing Network Intrusion Detection ...

引用

Novel Intelligent and Leading Emerging sciences Conference (NILES)

作者： Hesham Mamdouh Mohamed Tarek Abdelrahman Radwan Adel Saeed Ahmed Abdeen Monier Ashraf Khaled M. Fouad Ibrahim Abdelbaky School of Engineering and Applied Science (EAS) Nile University Giza Egypt CS program School of Information Technology and Computer Science (ITCS) Nile University Giza Egypt Faculty of Computer Science and Engineering New Mansoura University Artificial Intelligence Department Faculty of Computers and Artificial Intelligence Benha University Banha Egypt

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

The increasing sophistication of cyber attacks necessitates effective intrusion detection systems. We propose a novel intrusion detection method integrating deep learning with big data management using Apache Spark. Leveraging the comprehensive CSE-CIC-IDS2018 dataset, we apply extensive data preprocessing, including handling missing and unreliable values, duplicates, and redundant columns. In addition, implementation of a Random Forest based feature importance approach is derived to prioritize the most impactful Features. Furthermore, stratified k-fold cross-validation is used for a model selection process on a class-imbalanced dataset. Our weighted Random Forest classifier achieves a remarkable weighted average F1-score of 0.999 and a test inference time of 0.673 seconds using only the top 34 features, outperforming previous studies without sampling techniques. The proposed architecture offers a scalable and accurate solution for intrusion detection in cloud architectures, demonstrating the effectiveness of combining deep learning and big data technologies for cybersecurity.

关键词： Deep learning Cloud computing Data preprocessing Network intrusion detection Cluster computing Forestry Big Data Random forests Cyberattack Testing

来源：评论

学校读者我要写书评

暂无评论

A Robust Development of an Efficient Industrial Monitoring and Fault Identification Model using Internet of Things

A Robust Development of an Efficient Industrial Monitoring a...

引用

Big Data & Machine Learning (ICBDML), IEEE International Conference on

作者： Yahya Yaqoob Obaid Al Belushi P. Jasmin Dennis S. Deepa V. Arulkumar D. Kanchana Ragini Y P Department of Systems Engineering Military Technical College Sultanate of Oman Department of Electronics and Communication Engineering Vi Institute of Technology Chengalpattu Tamil Nadu Department of Computer Science and Business Systems RMD Engineering College Kavarapettai Tamil Nadu Department of Information Technology Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Chennai Tamil Nadu Department of Computer Applications SRM Institute of Science and Technology Ramapuram Chennai Tamil Nadu Department of Biosciences Saveetha School of Engineering SIMATS Chennai Tamil Nadu

ISBN: (数字)9798350374100

ISBN: (纸本)9798350374117

Internet of Things (IoT) is rapidly developing technologies and the Internet of Things (IoT) is a network of physical items or effects embedded with computer software, detectors, and network connectivity. The Internet of Things also addresses the issue of centralizing physical bias management online. We are leveraging the Internet of Things (IoT) idea to construct a system that will automatically monitor all artificial processes and issue warnings or expert comments when necessary. nowadays, gas leakage is a serious concern in the house and as well as vigilance. If the gas sense is indeed low, it's because we've been too careless, intolerant, or both to look for it. If the gas position is raised, however, calamity may ensue. In this research, the crucial concept is introduced to prevent this catastrophe from occurring. In this study, we propose an alternate approach to this impending calamity and design a system with integrated sensors, controllers, and some IoT-assisted software. The suggested method, known as the Internet of Things based Industrial Safety System (IoTISS), is compared against the more established Industrial Safety System (ISS) to see how well it performs. In this system, we are monitoring the detection of gas leakages with various warning characteristics as well as other devices are used for monitoring various aspects like humidity and temperature using DHT22 sensor, MQ2 gas monitoring sensor, fire sensor and NodeMCU ESP8266 WiFi module. NodeMCU ESP8266, which doubles as a WiFi module, will receive data from all of these types of sensors.

关键词： Temperature sensors Fault diagnosis Industries Sensor phenomena and characterization Sensor systems Software Internet of Things

来源：评论

学校读者我要写书评

暂无评论

African Vultures Based Feature Selection with Multi-modal Deep Learning for Automatic Seizure Prediction

African Vultures Based Feature Selection with Multi-modal De...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Mounika Nallur Sandhya M Zabiha Khan Mohan B R C P Nayana S A Rajashekhar Software Engineer Masters in Computer Information Systems Murray State University USA Department of Computer Science and Engineering East West Institute of Technology Bengaluru India Department of Artificial Intelligence & Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India

The superiority of life for people with epilepsy can be greatly improved with the assistance of accurate seizure prediction and early warning. An automatic prediction model is required to procedure the EEG signals and account for the leads optimization problematic, as opposed to the majority of hand-designed prediction approaches. In this research, we put forth a fully automated model for seizure prediction using Channel and Spatial attention (CASA). The first step in the feature extraction practice is to pre-process the raw EEG signals. Large amounts of computation can be saved by adding more features to the system, but finding the right ones can be tricky. The African vulture optimization algorithm's (AVOA) strong capacity to break out of local optima is what makes this procedure possible. CASA saved the raw EEG data's temporal and geographical details. Automatic optimization of EEG full-lead data was completed with channel attention (CA), leading to an increase in the accuracy of predictions. The aforementioned adaptive learning of feature parameters was accomplished via spatial attention (SA). When all else fails, a fully associated layer is used to make the seizure forecast. The suggested algorithm is tested on the Freiburg EEG database, and the results reveal that the AVOA-based system performs admirably when it comes to predicting seizures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Communication Latency and Platoon Control Based on Uplink RSMA for Future V2X Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Gang Hu, Jiewen Ma, Zheng Fan, Pingzhi Yu, F. Richard Southwest Jiaotong University School of Information Science and Technology Chengdu611756 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

As an effective solution to address road congestion and improve traffic efficiency, vehicle platooning has received a lot of attention in recent years. However, vehicle-to-vehicle (V2V) communication latency can largely impact on the performance of vehicle platooning, which has not been well investigated. Rate-splitting multiple access (RSMA), as one of the promising technologies for 6 G, holds great potential for application in vehicle platooning to reduce the communication latency and thereby enhance platoon control performance. Motivated by the above considerations, platoon control and communication latency are jointly considered in this paper. We first introduce the communication latency into the vehicle dynamics model, and then derive a distributed model predictive control (DMPC)-based platoon control model. To reduce the communication latency, uplink RSMA is introduced for inter-platoon V2V communication. Since the latency minimization problem is non-convex and challenging to solve directly, we first employ a bisection method to give a latency upper bound and transform the initial problem into a non-convex feasibility problems in each iteration. Subsequently, through theoretical derivation, the bandwidth allocation factor is expressed in terms of transmission power, which reduces the number of optimization variables and transforms the problem into a convex problem. Then we can obtain the optimal solution by solving a convex problem in each iteration. Finally, the simulation results demonstrate that the proposed RSMA significantly outperforms traditional frequency division multiple access (FDMA) and non-orthogonal multiple access (NOMA), and can significantly reduce communication latency, enhance platoon control safety, improve driving comfort, and lower the performance requirement on vehicle maximum torque. © 2025 IEEE.

关键词： Traffic congestion

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：