检索结果-内蒙古大学图书馆

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

作者： R Archana Reddy Ghazi Mohamad Ramadan Bhookya Ramesh S. Meenakshi Sundaram Hassan M. Al-Jawahry School of Computer Science and Artificial Intelligence SR University Warangal Telangana India College of MLT Ahl Al Bayt University Karbala Iraq Department of CSE (Data Science) CMR Technical Campus Hyderabad India Department of AI and DS Nitte Meenakshi Institute of Technology Bengaluru India The Islamic university Najaf Iraq

The growing use of the internet, especially in the automotive industry, has resulted in the development of several online services. Globally, the exponential expansion of financial fraud has resulted in huge financial losses for organisations in a variety of industries. This research develops an innovative approach that utilizes a capability of the Multi-Verse Optimization Algorithm (MVOA) to improve the performance in fraud detection through fuzzy clustering method. The contributions of MVOA are in the enhancement of model adaptability to ever-changing fraud patterns, the adept handling of imbalanced data through diverse exploration, and the resolution of feature interdependencies. The suggested fuzzy clustering technique improves the majority sample dataset within the Advanced Integrated Fraud Detection System (AIFDS) framework by removing outliers. The dataset utilization is thoroughly evaluated using modern classifiers such as XGBoost, CATBoost, Decision Tree and Random Forest. The AIFDS, enhanced by the MVOA-with fuzzy clustering model achieved better performance in accuracy of 94.32%, Sensitivity of 96.37 and precision of 93.49%, and enhancing fraud detection and lowering the financial risks associated with fraudulent operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Cutting-Edge Machine Learning and data Mining Techniques for Enhancing Big data Management with Advanced Algorithmic Strategies for Optimal data Processing and Analysis

Exploring Cutting-Edge Machine Learning and Data Mining Tech...

引用

International Conference on Advances in Information Technology (ICAIT)

作者： M. Anitha V Sheeja Kumari N. Muthuvairavan Pillai P. Jesu Jayarin D. Beulah David Department of Artificial Intelligence & Data Science CARE College of Engineering Trichy Tamil Nadu India Department of Computational Intelligence Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Thandalam Chennai Tamil Nadu India Department of Computer Science and O. Business Systems R.M.D Engineering College Thiruvallur Tamil Nadu India Department of Information Technology Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Thandalam Chennai Tamil Nadu India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

This work focuses on diverse machine learning methods for big data analytics, which works to leverage predictive performance. The techniques like data preprocessing, dimensionality reduction, feature selection, model selection, hyperparameter tuning, and model evaluation are a focus. A number of algorithms including Random Forests, SVM (Support Vector Machines) Gradient Boosting Machines (GBM), Neural networks, and ensemble methods (Bagging and Boosting) have their performance evaluated. Hyperparameter tuning applies the Grid Search and Random Search algorithms while model evaluation is done by the K-fold Cross-validation. Fleiss' kappa provide differing levels of accuracy, precision, recall, and F1-score for different models and techniques. Ensemble methods actually show how they have all the necessary qualities to win and perform better than individual models. repeatedly testing improve the models' reliability and effectiveness for practical use. The study highlights the crucial significance of choices on the methods and algorithms that suit the peculiarities of the dataset and problem domain. Capitalizing on the machine learning techniques and in-depth evaluation methods, organizations can get the actionable insights from the big data that will ensure the headquarters' decision-making process and accomplish the meaningful outcomes. Future research could instead be exploring new algorithms and techniques to improve the prediction and scalability in big data analytics setting.

关键词： Support vector machines Machine learning algorithms Computational modeling Scalability Software algorithms Big data Prediction algorithms Boosting data models Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Zero-Added-Loss Entangled-Photon Multiplexing for Ground- and Space-Based Quantum networks

引用

Physical Review Applied 2023年第5期19卷 054029-054029页

作者： Kevin C. Chen Prajit Dhara Mikkel Heuck Yuan Lee Wenhan Dai Saikat Guha Dirk Englund Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Wyant College of Optical Sciences The University of Arizona Tucson Arizona 85721 USA NSF-ERC Center for Quantum Networks The University of Arizona Tucson Arizona 85721 USA Department of Electrical and Photonics Engineering Technical University of Denmark Kgs. Lyngby 2800 Denmark College of Information and Computer Science University of Massachusetts Amherst Massachusetts 01003 USA Brookhaven National Laboratory Upton New York 11973 USA

We propose a scheme for optical entanglement distribution in quantum networks based on a quasideterministic entangled photon-pair source. By combining heralded photonic Bell-pair generation with spectral mode conversion to interface with quantum memories, the scheme eliminates switching losses due to multiplexing in the source. We analyze this “zero-added-loss multiplexing” (ZALM) Bell-pair source for the particularly challenging problem of long-baseline entanglement distribution via satellites and ground-based memories, where it unlocks additional advantages: (i) the substantially higher channel efficiency η of downlinks versus uplinks with realistic adaptive optics, and (ii) photon loss occurring before interaction with the quantum memory—i.e., Alice and Bob receiving rather than transmitting—improve entanglement generation rate scaling by O(η). Based on numerical analyses, we estimate our protocol to achieve >10ebit/s at memory multiplexing of 102 spin qubits for ground distance >102km, with the spin-spin Bell-state fidelity exceeding 99%. Our architecture presents a blueprint for realizing global-scale quantum networks in the near term.

关键词： Light-matter interaction Nonlinear optics Optical quantum information processing Photon pairs & parametric down-conversion Quantum communication Quantum networks Quantum optics Multiplexers Optical sources & detectors

来源：评论

学校读者我要写书评

暂无评论

Chaotic Particle Swarm Optimization Based Shortest Path Routing in VANET

Chaotic Particle Swarm Optimization Based Shortest Path Rout...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： R. Ramya A. Yazhini T. Geetha R. Sahila Devi Kavin K. S. S. Dhanalakshmi Department of Nano Electronics Materials and Sensors ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India Department of Computer Science & Engineering College of Engineering Anna University Chennai India Department of Artificial Intelligence and Data Science Agni College of Engineering and Technology Chennai India Department of Computer Science and Engineering Rohini College of Engineering and Technology Palkulam India Department of Electrical and Electronics Engineering Government College of Engineering Tirunelveli Tamilnadu India Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam Erode India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

The present study examines the Vehicle Ad hoc networks (VANETs) exhibit unexpected behavior due to their high mobility and random network structure. Including ad hoc networks, a variety of problems, including repeated connected breakdowns, flexibility, multi-hop transmission of information, and information loss, impact Transmission Control Protocols (TCP). To overcome this problem, this paper suggests employing zone-based routing in VANETs while taking mobility into account. The routing technique is implemented with a hybrid optimization strategy. The most significant swarm intelligence (SI) algorithm for solving optimization issues is the chaotic particle swarm optimization (CPSO) algorithm. Due to its simplicity, which involves just a few parameters, CPSO has grown to be considered one of the most frequently used optimization techniques. When resolving challenging optimization problems, the routing algorithms experience high overhead or incompatibilities. A CPSO based shortest path routing method is presented for VANET that offers a high-quality path for connection among nodes, improving the distribution of packets percentage and preventing end-to-end delay, in order to enhanced routing effectiveness and throughput in prevailing approaches. These achievements show that CPSO performs adequately and is experiencing significant progress.

关键词： TCP Protocols Vehicular ad hoc networks Spread spectrum communication Routing Throughput Search problems

来源：评论

学校读者我要写书评

暂无评论

Exam Cheating Classification Using a Deep Learning Approach

Exam Cheating Classification Using a Deep Learning Approach

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Bishaw, Molla Ejigu Salau, Ayodeji Olalekan Vats, Satvik Kaushik, Keshav Alemu, Wubie Belay Tin, Ting Tin Debre Tabor University Department of Information Technology Debre Tabor Ethiopia Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Graphic Era Hill University Department of Cse Uttarakhand Dehradun India Graphic Era Deemed to be University Uttarakhand Dehradun248007 India Amity School of Engineering and Technology Amity University Mohali Punjab India Debark University Department of Information Technology Debark Ethiopia Inti International University Faculty of Data Science and Information Technology Negeri Sembilan Malaysia

ISBN: (纸本)9798350379716

Exam cheating has become a significant concern in educational institutions due to its potential negative impact on academic integrity. Researchers have attempted to overcome the issue. However, the previous research did not use multiple cheating activities in their datasets and the attributes of the studies used were not strong enough to represent exam cheating, particularly about paper positions. The study utilizes the dataset containing cheating and non-cheating images to develop a model using deep learning approaches. The dataset consists of images collected from network colleges, confirming the presence of cheating and non-cheating instances. Preprocessing techniques, including image resizing, noise removal, histogram equalization, augmentation and feature extraction are applied to the dataset, and both original and augmented versions of the datasets are used in experimental studies. Different input image sizes are employed for the deep CNN, AlexNet, GoogLeNet, and ResNet architectures and evaluated for their performance in classification in a paper based exam cheating. As the experimental results demonstrate from the models used in this study the customized CNN model achieves the highest accuracy of 93% and exhibits excellent performance in terms of loss function and accuracy. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Aerial Videos with Transformers

arXiv

引用

arXiv 2022年

作者： Jin, Pu Mou, Lichao Xia, Gui-Song Zhu, Xiao Xiang The Remote Sensing Technology Institute German Aerospace Center Weßling82234 Germany The Data Science in Earth Observation Technical University of Munich Munich80333 Germany China The School of Computer Science Wuhan University Wuhan430072 China

This work has been accepted by IEEE TGRS for publication. Unmanned aerial vehicles (UAVs) are widely applied for purposes of inspection, search, and rescue operations by the virtue of low-cost, large-coverage, real-time, and high-resolution data acquisition capacities. Massive volumes of aerial videos are produced in these processes, in which normal events often account for an overwhelming proportion. It is extremely difficult to localize and extract abnormal events containing potentially valuable information from long video streams manually. Therefore, we are dedicated to developing anomaly detection methods to solve this issue. In this paper, we create a new dataset, named Drone-Anomaly, for anomaly detection in aerial videos. This dataset provides 37 training video sequences and 22 testing video sequences from 7 different realistic scenes with various anomalous events. There are 87,488 color video frames (51,635 for training and 35,853 for testing) with the size of 640 × 640 at 30 frames per second. Based on this dataset, we evaluate existing methods and offer a benchmark for this task. Furthermore, we present a new baseline model, ANomaly Detection with Transformers (ANDT), which treats consecutive video frames as a sequence of tubelets, utilizes a Transformer encoder to learn feature representations from the sequence, and leverages a decoder to predict the next frame. Our network models normality in the training phase and identifies an event with unpredictable temporal dynamics as an anomaly in the test phase. Moreover, To comprehensively evaluate the performance of our proposed method, we use not only our Drone-Anomaly dataset but also another dataset. We will make our dataset and code publicly available © 2022, CC BY-NC-ND.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Adaptive Loose Optimization for Robust Question Answering

arXiv

引用

arXiv 2023年

作者： Ma, Jie Wang, Pinghui Wang, Zewei Kong, Dechen Hu, Min Han, Ting Liu, Jun The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Automation Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The China Mobile Research Institute China The Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China

Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering). Current debiasing methods often come at the cost of significant in-distribution performance to achieve favorable out-of-distribution generalization ability, while non-debiasing methods sacrifice a considerable amount of out-of-distribution performance in order to obtain high in-distribution performance. Therefore, it is challenging for them to deal with the complicated changing real-world situations. In this paper, we propose a simple yet effective novel loss function with adaptive loose optimization, which seeks to make the best of both worlds for question answering. Our main technical contribution is to reduce the loss adaptively according to the ratio between the previous and the current optimization state on mini-batch training data. This loose optimization can be used to prevent non-debiasing methods from overlearning data bias while enabling debiasing methods to maintain slight bias learning. Experiments on the visual question answering datasets, including VQA v2, VQA-CP v1, VQA-CP v2, GQA-OOD, and the extractive question answering dataset SQuAD demonstrate that our approach enables QA methods to obtain state-of-the-art in- and out-of-distribution performance in most cases. The source code has been released publicly in https://***/reml-group/ALO. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based EEG Signal Classification of Epileptic Patients

Deep Learning-Based EEG Signal Classification of Epileptic P...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： V. Senthil Kumar C. Karpagavalli S. Pradeep S. Divya Syed Noeman Taqui Nadanakumar Vinayagam Department of Computer Science and Engineering SRM Institute of Science and Technology Tiruchirapalli Tamil Nadu India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam Tamil Nadu India Department of Electronics and Communication Engineering S.A. Engineering College Chennai Tamil Nadu India Department of Biomedical Engineering Dr. N. G.P. Institute of Technology Coimbatore Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Automobile Engineering Hindustan Institute of Technology and Science Padur Chennai Tamil Nadu India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Epilepsy is a neurological disorder characterized by repeated seizures throughout the day. Epilepsy affects around 65 million people worldwide. For people with focal epilepsy, surgery is a possibility but medicine is the standard treatment for generalized epilepsy. Unfortunately, these medications fail to control epileptic seizures in more than 30% of patients. Yet, this ends up in accidents and significantly shortens the patient's life expectancy. An electroencephalogram (EEG) is a critical diagnostic tool for epilepsy. The conventional method for detecting epileptic activity is expert human interpretation of multi-channel EEG readings. This is a complex and time-consuming procedure, thus many researchers have tried to automate it using Machine Learning (ML) and Deep Learning (DL) methods. Unfortunately, the investigation did not produce satisfactory results. This study aims to fill this research gap by proposing a new CNN-BLSTM (Convolutional Neural Network-Bidirectional Long Short-Term Memory) based hybrid DL model for epileptic detection. The EEG data from Kaggle was collected and processed. This study uses the same amount of data and epochs for training, validation, and testing all four DL models such as AlexNet, VGG-16, InceptionV3, and the proposed model. According to the experiment findings, the proposed model has a better level of accuracy (98.37 % ) than the other three models.

关键词： Training Accuracy Epilepsy Surgery Brain modeling Electroencephalography data models

来源：评论

学校读者我要写书评

暂无评论

Smart Retail Store Surveillance and Security with Cloud-Powered Video Analytics and Transfer Learning Algorithms

Smart Retail Store Surveillance and Security with Cloud-Powe...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： P. Sivalakshmi U. Kavitha R. Usha Ojasvi Pattanaik S.P. Maniraj C. Srinivasan Department of Electronics and Communication Engineering R.M.K. College of Engineering and Technology Chennai Tamil Nadu India School of Commerce Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Mathematics S. A. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Vignan Institute of Management and Technology for Women Ghatkesar JNTU Hyderabad India Department of Data Science and Business Systems Faculty of Engineering & Technology SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Retail security and surveillance systems have transformed into data-driven smart solutions thanks to the fast development of technology. This paper presents a new method for improving retail shop security and surveillance by combining transfer learning (TL) algorithms with cloud-powered video analytics. It is now possible to remotely interpret, analyze, and store massive amounts of video data produced by security cameras using cloud computing capabilities. In addition, TL methods are used to customize pre-trained deep learning models for retail settings, allowing for precise event and anomaly identification. This method drastically reduces the computing load on local devices and makes surveillance systems more accurate and responsive. One of the main advantages of the proposed system is that it can monitor the store premises in real time. It can also automatically identify suspicious actions like stealing or damage and inform staff or security about possible risks. By using cloud infrastructure, the system can also adapt to changing security needs and expand dynamically to handle increasing data volumes. Retailers may find useful information for refining shop layouts, product placements, and marketing tactics by integrating cloud-powered video analytics, which allows advanced functions like crowd analysis, heat mapping, and customer behavior analysis. A thorough plan for smart retail store security and surveillance, using cloud computing, video analytics, and TL algorithms to build a strong and effective system for protecting digital retail spaces.

关键词： Cloud computing Machine learning algorithms Accuracy Surveillance Visual analytics Scalability Transfer learning Real-time systems Safety Security

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Feature Selection Method Based on Rankability

SSRN

引用

SSRN 2024年

作者： Kong, Lingping Velasquez, Juan D. Perfilieva, Irina Pant, Millie Pan, Jeng-Shyang Snášel, Václav Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Industrial Engineering University of Chile Santiago Chile Santiago Chile Institute for Research and Applications of Fuzzy Modeling Centre of Excellence IT4Innovations division of The University of Ostrava Ostrava Czech Republic Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India School of Artificial Intelligence Nanjing University of Information Science and Technology China Instituto Sistemas Complejos de Ingeniería Santiago Chile Santiago Chile Faculty of Computer Science and Telecommunications Cracow University of Technology Kraków Poland Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India College of Computer Science and Engineering Shandong University of Science and Technology China

Within the realm of data mining and machine learning, feature selection stands out as an essential technique for dimensionality reduction, presenting both popularity and complexity. Feature selection involves a nuanced trade-off that results in information loss. This distinction underscores the necessity for the development of lightweight, efficient, and practical methods capable of minimizing information loss while executing dimensional reduction. In this paper, we introduce a rankability-based feature selection method. The concept of rankability, proposed in 2019 and similar to the entropy concept, remains relatively unexplored. Our proposed method distinguishes itself by its lightweight complexity, eliminating the need for iterative *** evaluate the effectiveness of our approach, we conducted experiments on forty-one datasets and compared the results with four other algorithms using refined data with 10\%, 30\%, and 50\% feature dimension reduction. The findings reveal that our rankability-based feature selection method consistently outperforms the other four methods across a majority of datasets in terms of accuracy, precision, recall, and F1-macro performance. Specifically, the classification score exceeds 0.9 on accuracy for 50\% feature dimension reduction in twelve datasets, with nine datasets achieving scores over 0.9 in recall, F1-macro, and precision. Overall, our proposed feature selection method demonstrates promising performance. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

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：