检索结果-内蒙古大学图书馆

10th International Conference on Social Networks Analysis, Management and Security, SNAMS 2023

作者： Al-Alshaqi, Mohammed Rawat, Danda B. Howard University Dept. of Electrical Engineering and Computer Science WashingtonDC United States WashingtonDC United States

ISBN: (纸本)9798350318906

Fake news involves disseminating deceptive, offensive, and inaccurate information, masquerading as credible news. Its primary objective is to tarnish individuals' public reputations while profiting from advertisements built on false content. We introduce an efficient fake news detection system using binary classification, employing attention-based Recurrent Neural Network (RNN) models. Our unified model, characterized by superior accuracy and comprehension, undergoes rigorous evaluation with an internet-sourced dataset, consistently yielding top-tier performance metrics. Despite relying on a single model for the entire detection process, it maintains end-to-end optimization flexibility, minimizes errors, and effectively balances bias-variance trade-offs. Our study explores fake news articles, their creators, and detection challenges, identifying heterogeneous social network patterns, both overt and covert, frequently exploited by fake news creators. We introduce a Deep Diffusive Network Model incorporating network structural data into learning. Our straightforward, linear, low-latency system achieves 98% accuracy in fake news detection. In addition to modeling and detection, advanced data analysis techniques yield deeper dataset insights. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of Irregular Bangladesh-EU Migration Trends Using Machine Learning Techniques 3

Prediction of Irregular Bangladesh-EU Migration Trends Using...

引用

3rd International Conference on Advancement in Electrical and Electronic Engineering, ICAEEE 2024

作者： Islam, Md. Shariful Rahim, Md Abdur Podder, Nitun Kumar Hossain, Md. Najmul Hossain, Md Imran Pabna University of Scence and Technology Dept. of Computer Science and Engineering Pabna Bangladesh Pabna University of Scence and Technology Dept. of Electrical Electronic and Communication Engineering Pabna Bangladesh Pabna University of Scence and Technology Dept. of Inormation and Communication Engineering Pabna Bangladesh

ISBN: (纸本)9798350388282

Remittances are important economic contributors to a countrya's economy. It has increased national savings, lowered foreign exchange limits, and helped balance payments and development budgets. Migrant workers are the main source of these remittance revenues. Many workers worldwide leave their homes and move to different parts of the world for overseas employment. These workers are authorized and have documentation of their country of origin and final destination. Besides, many workers have migrated illegally globally, particularly to European Union (EU) countries via marine routes. However, illegal immigration leads to a loss of national revenue due to non-payment of taxes and social security contributions and problems with living circumstances and legal issues. Therefore, this paper aims to present a time series forecast of irregular migrants in EU countries from Bangladesh over the next five years. We used five methods to analyze this forecasting: ARIMA (an autoregressive integrated moving average), XGBoost Series, Decision Tree, Feed Forward Neural Network, and CatBoost Regressor. In addition, we used data from the European Border and Coast Guard Agency to perform the time series forecast. A field intervention is carried out to assess the gender, age, education, socioeconomic level, and skill profile of migrant workers. Moreover, a few case studies of migrant workers and a survey were conducted to investigate the underlying causes of irregular migration. Finally, this study explains the underlying cause of irregular migration and its repercussions. It can provide some ideas for decreasing the loss of human life and property by reducing irregular migration to help take essential actions in the home and destination countries. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Service Selection and Load Balancing in Multi-Cluster Microservice Systems with MCOSS

Optimizing Service Selection and Load Balancing in Multi-Clu...

引用

IFIP Networking Conference

作者： Daniel Bachar Anat Bremler-Barr David Hay Dept. of Computer Science Reichman University Israel Dept. of Computer Science Tel-Aviv University Israel Dept. of Computer Science The Hebrew University Israel

With the advent of cloud and container technologies, enterprises develop applications using a microservices architecture, managed by orchestration systems (e.g. Kubernetes), that group the microservices into clusters. As the number of application setups across multiple clusters and different clouds is increasing, technologies that enable communication and service discovery between the clusters are emerging (mainly as part of the Cloud Native ecosystem). In such a multi-cluster setting, copies of the same microservice may be deployed in different geo-locations, each with different cost and latency penalties. Yet, current service selection and load balancing mechanisms do not take into account these locations and corresponding penalties. We present MCOSS, a novel solution for optimizing the service selection, given a certain microservice deployment among clouds and clusters in the system. Our solution is agnostic to the different multi-cluster networking layers, cloud vendors, and discovery mechanisms used by the operators. Our simulations show a reduction in outbound traffic cost by up to 72% and response time by up to 64%, compared to the currently-deployed service selection mechanisms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Facial Feature Extraction with AI: An Innovative Approach 5

Revolutionizing Facial Feature Extraction with AI: An Innova...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Lakshmi, B. Alekhya, Jandhyam Lakshmi Parish Venkata Kumar, K. Kishore, B. Kamala Nyni, K. Likhita, K. V.R. Siddhartha Engineering Dept. of Computer Applications KanuruVijayawada 7 India V.R. Siddhartha Engineering College Dept of Computer Science and Engineering KanuruVijayawada 7 India Department of Computer Applications India

ISBN: (纸本)9798350385649

This paper provides a technique for detecting human faces & extracting their features based on segmentation of skin tone & facial structure. The system goes through several stages. The method first searches for regions where faces might be present by segmenting skin tone. After performing various morphological operations on skin, it uses aspect ratio of a face to find viable face blocks. face blocks are then used to extract additional features. Therefore, one may identify and validate a person's image using their face features by using this biometric attribute. To enhance facial recognition, numerous researchers have employed Support Vector Machine (SVM), Principal Component Analysis (PCA), a combination of SVM and PCA, PCA with an Artificial Neural Network, and even the conventional PCA-SVM. Due to PCA-ANN's limited dataset limitation, PCA-SVM is superior to PCA-ANN. To extract features, relative location & size are used. If algorithm is unable to identify even one feature in a prospective face block, it rejects face block. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of TRUTH: Fixing a Protocol to Make it 5G-Compliant

Cryptanalysis of TRUTH: Fixing a Protocol to Make it 5G-Comp...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Munilla, J. Burmester, M. Caballero-Gil, P. University of Málaga Dpt. of Telecommunication Engineering Málaga29071 Spain Florida State Unviersity Department of Computer Science TallahasseeFL32304 United States University of La Laguna Dept. of Computer Science and Ai Tenerife La Laguna Spain

ISBN: (纸本)9798350364910

Trust and security are critical deployment require-ments for Industrial Internet of Things (IIoT) networks. A recent protocol, called TRUTH, integrates security mechanisms for authentication and privacy alongside a Dempster-Shafer based trust model, to assess the trustworthiness of collected data. We analyze this protocol and show that it does not comply with the implementation requirements of the 5G standard, and that flaws in the identification of involved parties hinder its adoption by 5G devices. We show how to fix this protocol and tailor it for the specific 5G implementation constraints, by enhancing its computational and communication performance. Finally, we show how to prove the security of this fixed protocol (TRUTH +) using the Tamarin automated verification tool. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Predicting Lung Cancer with Artificial Neural Network: Analyzing Performance and Feature Importance

Predicting Lung Cancer with Artificial Neural Network: Analy...

引用

Cognitive Computing in Engineering, Communications, sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Vatsal Mehta Varun M Ashwini Kodipalli Roshan Joy Martis Shridhar B. Devamane Ushasree. A Dept. of AI & Data Science Global Academy of Technology Bangalore Karnataka India Dept. of Electronics & Communication Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science School of Computing Mysuru Dept. of Computer Science & Engineering Gokaraju Lailavathi Engineering College Hyderabad India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Lung cancer is the primary cause of cancer-related deaths globally. This cancer is majorly observed in smokers, increasing air pollution has also begun to affect non-smokers. Research indicates that exposure to polluted air significantly raises the risk of developing lung cancer, posing a major threat to public health. Despite advancements in medical technology, the mortality rate from lung cancer remains high, highlighting the importance of early diagnosis. Machine learning and deep learning offer promising solutions for early and accurate prediction through advanced data analysis. In our study, we utilized a dataset with 26 attributes for discern lung cancer, categorizing cases into three risk levels: high, medium, and low. We applied various algorithms and develop an Artificial Neural Network (ANN), comparing the overall performance with various machine-learning and deep-learning models. Our results show that the ANN achieved a high accuracy of 94.9% using the Adam optimizer, making it an effective model for lung cancer prediction.

关键词： Deep learning Accuracy Computational modeling Biological system modeling Lung cancer Mortality Artificial neural networks Predictive models Prediction algorithms Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Evaluating Low-Resource Lane Following Algorithms for Compute-Constrained Automated Vehicles

arXiv

引用

arXiv 2024年

作者： Froemming-Aldanondo, Beñat Rastoskueva, Tatiana Evans, Michael Machado, Marcial Vadella, Anna Johnson, Rickey Escamilla, Luis Jostes, Milan Butani, Devson Kaddis, Ryan Chung, Chan-Jin Siegel, Josh Dept. of Computer Science & Engineering University of Minnesota Minneapolis United States Dept. of Computer Science The University of Arizona Tucson United States Dept. of Computer Science Old Dominion University Norfolk United States Dept. of Computer Science & Engineering The Ohio State University Columbus United States Dept. of Computer Science SWE Butler University Indianapolis United States Dept. of Computer Science North Carolina A&T State University Greensboro United States Dept. of Computer Science New Mexico State University Las Cruces United States Dept. of Math & Computer Science Lawrence Technological University Southfield United States DeepTech Lab Michigan State University East Lansing United States

Reliable lane-following is essential for automated and assisted driving, yet existing solutions often rely on models that require extensive computational resources, limiting their deployment in compute-constrained vehicles. We evaluate five low-resource lane-following algorithms designed for real-time operation on vehicles with limited computing resources. Performance was assessed through simulation and deployment on real drive-by-wire electric vehicles, with evaluation metrics including reliability, comfort, speed, and adaptability. The top-performing methods used unsupervised learning to detect and separate lane lines with processing time under 10 ms per frame, outperforming compute-intensive and poor generalizing deep learning approaches. These approaches demonstrated robustness across lighting conditions, road textures, and lane geometries. The findings highlight the potential for efficient lane detection approaches to enhance the accessibility and reliability of autonomous vehicle technologies. Reducing computing requirements enables lane keeping to be widely deployed in vehicles as part of lower-level automation, including active safety systems. © 2024, CC BY.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Grammatical Evolution of Synthesizable Finite State Machine-Based Behavioural Level Hardware Description Language Codes 16th

Grammatical Evolution of Synthesizable Finite State Machine-...

引用

16th International Joint Conference on Computational Intelligence, IJCCI 2024

作者： Majeed, Bilal McEllin, Jack Sarma, Rajkumar Youssef, Ayman Mota Dias, Douglas Ryan, Conor BDS Labs Dept. of CSIS University of Limerick Limerick Ireland Dept. of Computers and Systems Electronics Research Institute Cairo Egypt Department of Computer Science & Applied Physics Atlantic Technological University Galway Ireland

ISBN: (纸本)9789897587214

The importance of designing efficient and accurate digital circuits has grown due to the widespread use of wearable, ready-made, and custom electronic products. These digital circuits are typically sequential and designed using synthesizable Hardware Description Languages (HDLs) that can be translated into hardware. A large part of this exercise comprises designing synthesizable HDLs for sequential circuits, which are challenging to design and test, thus requiring much time for the engineers to construct them. This paper proposes using Grammatical Evolution (GE) to evolve the synthesizable HDL codes for sequential circuits on the behavioural or algorithmic level in SystemVerilog. The codes evolved in this work are of JK-Flip Flop (JK-FF), 3-bit UpDown Counter (UDC), and 8-Floor Elevator (8FE), all from the perspective of Finite State Machines (FSMs). Circuits such as 3-bit UDC and JK-FF are the basic blocks in many circuits in the industry, while 8FE is a real-life example mimicking 3-bit UDC but with a few practical exceptions. All circuits are evolved using two types of grammars. The G1 Type Grammar evolves parts of the code, while the more powerful and generic G2 Type Grammar evolves the full HDL codes for these sequential circuits. The GE-based evolution of these synthesizable design codes using both types of grammar achieves a success rate of over 86% for all circuits. Moreover, all the solution circuits evolved with the best achieved success score under the respective hyperparameter settings for G1 and G2 Type Grammar are synthesised, and their synthesis reports are compared against the synthesis reports of Gold (human-designed) circuits. The synthesis is performed using Cadence Genus at Generic Process Design Kit (GPDK) 45, 90, and 180 nm technology libraries. The synthesis results show that machine-generated designs often perform as well as or better than human-designed circuits. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Flip flop circuits

来源：评论

学校读者我要写书评

暂无评论

Power Quality Control and Comparison of a Micro Grid System Using Fuzzy MPPT Technique 5

Power Quality Control and Comparison of a Micro Grid System ...

引用

5th International Conference on Energy, Power, and Environment, ICEPE 2023

作者： Sahoo, Satyabrata Thokchom, Surmila Puhan, Pratap Sekhar Panda, Gayadhar NallaMallaReaddy Engineering College Dept. of Electrical and Electronics Engineering Hyderabad India National Institute of Technology Meghalaya Dept. of Computer Science and Engineering Meghalaya India Sreenidhi Institute of Science and Technology Dept. of Electrical and Electronics Engineering Hyderabad India National Institute of Technology Meghalaya Dept. of Electrical Engineering Meghalaya India

ISBN: (纸本)9798350313123

This paper presents a power quality control in a microgrid system using different Maximum Power Point Tracking (MPPT) techniques. The main aim of the study is to evaluate the performance of the microgrid system in terms of power quality parameters, such as harmonic distortion and voltage stability, when different MPPT techniques are employed. The microgrid system incorporates a hybrid power generation system consisting of solar panels, wind turbines, and energy storage systems, which are integrated and controlled using different MPPT techniques, including the Perturb & Observation (P&O) method and the Fuzzy MPPT technique. A single-phase sinusoidal pulse width modulation (SPWM) inverter, based on the PQ control strategy, is used to supply power to the grid and maintain a constant DC link voltage. Additionally, a fuel cell is employed to substantially reduce power fluctuations. A comparison of the power quality performance of the micro grid system using these MPPT techniques is carried out through simulation studies using MATLAB/Simulink platform. The results are analyzed and discussed in detail, and recommendations are provided for improving the power quality control of the microgrid system. © 2023 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Precoding to Reduce Complexity of Factor Graph for MIMO-SCMA 16

Precoding to Reduce Complexity of Factor Graph for MIMO-SCMA

引用

16th International Conference on Signal Processing and Communication System, ICSPCS 2023

作者： Takada, Kazushi Saba, Takahiko Dept. of Computer Science Chiba Institute of Technology 2-17-1 Tsudanuma Narashino Chiba275-0016 Japan

ISBN: (纸本)9798350333510

Combining sparse code multiple access (SCMA) with multiple-input multiple-output (MIMO) can improve spectral efficiency of SCMA. However, in a downlink MIMO-SCMA system, each user receives signals from all transmit antennas. This increases the computational complexity of detection using the message passing algorithm (MPA) to estimate the desired symbols. To solve this problem, we propose a precoding scheme that can reduce the computational complexity of MPA without compromising the bit error rate (BER) performance. In the proposed scheme, weights are multiplied by symbols to be transmitted by the base station so that each user receives signals with a reduced number of superposed symbols. computer simulation results show that the proposed scheme can improve the BER performance while reducing the computational complexity of MPA. © 2023 IEEE.

关键词： Computational complexity

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：