检索结果-内蒙古大学图书馆

Experimental Results of Federated Learning in Unmanned Aerial Vehicle Swarm

学校读者我要写书评

暂无评论

Experimental Results of Federated Learning in Unmanned Aeria...

2021 IEEE International Conference on Space-Air-Ground Computing, SAGC 2021

作者： Shen, Yun Dong, Chao Qu, Yuben Ren, Weiqing Zhu, Xiaojun Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space China Shanghai Jiao Tong University Department of Computer Science and Engineering China

ISBN: (纸本)9781665400114

Unmanned aerial vehicles (UAVs) need to deploy machine learning (ML) models to execute complex tasks such as target tracking. For traditional centralized ML, UAVs need to transmit the raw data to the ground central server for model training. However, the transmission of raw data not only causes a large delay but also may incur sensitive information leakage. Federated learning (FL) as a distributed machine learning enables multiple UAVs to form a swarm for distributed model training. Nevertheless, most of current researches on FL of UAV swarm are based on theoretical architecture and simulations. In this paper, we focus on verifying the feasibility of deploying FL in a UAV swarm through practical experiments. Moreover, we further explore the impact of the distance change between the training node UAVs and the parameter server UAV on the training accuracy. The experimental results show that the UAV swarm can perform 15 rounds of global training in 5 minutes, with a training accuracy of 84.28%. © 2021 IEEE.

关键词： Antennas

A Smote-Based Churn Prediction System Using Machine Learning Techniques

学校读者我要写书评

暂无评论

A Smote-Based Churn Prediction System Using Machine Learning...

science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Akinyemi Omololu Akinrotimi Roseline Oluwaseun Ogundokun Modinat Abolore Mabayoje Rafiat Ajibade Oyekunle Marion Olubunmi Adebiyi Department of Mathematics Sciences(Computer Science Program) Augustine University Ilara-Epe Epe Nigeria Department of Computer Science Landmark University Omu-Aran Nigeria Department of Multimedia Engineering Kaunas University of Technology Lithuania SDG 4. Quality Education Landmark University Omu Aran Nigeria Department of Computer Science University of Ilorin Ilorin Nigeria Department of Information and Communication University of Ilorin Ilorin Nigeria Department of Computer Science Landmark University Omu-Aran Omu Aran Nigeria

The financial backbone of every telecommunications company is strictly made up of the number of customers patronizing the organization. Due to the high level of competition amongst existing telecommunication companies, customers sometimes leave, dropping the services of a particular one for the other. Predicting which subscribers may want to leave a telecommunications company and providing solutions to keep them from doing so, are the main objectives of customer churn prediction. Churn prediction helps classify consumers who are likely to move from one business to another. The ability to foresee churners before they leave has been increasingly useful in recent years, especially in light of increased competition among communications carriers. To compute churners for telecommunications providers, the study described in this paper used oversampling techniques to balance churn data and applied the dimensionality reduction technique to discover optimal features with a strong predictive ability for detecting would-be churners and non-churners. The model used Logistic Regression and the Naïve Bayes Classification Algorithm to implement comparative classification strategies. The performance levels of these strategies were compared using a Telecommunications Customer Churn data set, as well as performance metrics such as accuracy, sensitivity, and specificity. The Naïve Bayes Algorithm proves more efficient than its counterpart giving higher positive rate detection and a lower negative rate detection.

关键词： Measurement Companies Sensitivity and specificity Prediction algorithms Data models Telecommunications Numerical models

Unbiased Estimation using Underdamped Langevin Dynamics

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ruzayqat, Hamza Chada, Neil K. Jasra, Ajay Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

In this work we consider the unbiased estimation of expectations w.r.t. probability measures that have non-negative Lebesgue density, and which are known point-wise up-to a normalizing constant. We focus upon developing an unbiased method via the underdamped Langevin dynamics, which has proven to be popular of late due to applications in statistics and machine learning. Specifically in continuous-time, the dynamics can be constructed so that as the time goes to infinity they admit the probability of interest as a stationary measure. In many cases, time-discretized versions of the underdamped Langevin dynamics are used in practice which are run only with a fixed number of iterations. We develop a novel scheme based upon doubly randomized estimation as in [17, 19], which requires access only to time-discretized versions of the dynamics. The proposed scheme aims to remove the dicretization bias and the bias resulting from running the dynamics for a finite number of iterations. We prove, under standard assumptions, that our estimator is of finite variance and either has finite expected cost, or has finite cost with a high probability. To illustrate our theoretical findings we provide numerical experiments which verify our theory, which include challenging examples from Bayesian statistics and statistical *** Codes 60J22, 65C05, 65C40, 82C31, 62G08, 35Q56 © 2022, CC BY.

关键词： Dynamics

Comparative Analysis of Real-Time Multi-Person Pose Detection in Electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Shang-Te Tsai Zong-Rong Wu Pin-Hsuan Lin Chin-Hsiung Chen Wei Chien Yu-Cheng Chang School of Art and Design Sanming University Fujian China Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Business Administration National Central University Taoyuan Taiwan Department of Electrical Engineering New Taipei Municipal Tamsui Commercial Industrial Vocational Senior High School New Taipei Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy.

关键词： Training Accuracy Microcontrollers Neural networks Real-time systems Safety Internet of Things

Learning Better Masking for Better Language Model Pre-training

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Dongjie Zhang, Zhuosheng Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Masked Language Modeling (MLM) has been widely used as the denoising objective in pretraining language models (PrLMs). Existing PrLMs commonly adopt a Random-Token Masking strategy where a fixed masking ratio is applied and different contents are masked by an equal probability throughout the entire training. However, the model may receive a complicated impact from pre-training status, which changes accordingly as training time goes on. In this paper, we show that such time-invariant MLM settings on masking ratio and masked content are unlikely to deliver an optimal outcome, which motivates us to explore the influence of time-variant MLM settings. We propose two scheduled masking approaches that adaptively tune the masking ratio and masked content in different training stages, which improves the pre-training efficiency and effectiveness verified on the downstream tasks. Our work is a pioneer study on time-variant masking strategy on ratio and content and gives a better understanding of how masking ratio and masked content influence the MLM pretraining1 Copyright © 2022, The Authors. All rights reserved.

关键词： Modeling languages

Improved Chest X-Ray Image Quality Using Median and Gaussian Filter Methods

学校读者我要写书评

暂无评论

Improved Chest X-Ray Image Quality Using Median and Gaussian...

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Lucky Indra Kesuma Ermatita Ermatita Erwin Erwin Purwita Sari Rudhy Ho Purabaya Doctoral Program in Engineering Faculty of Engineering Universitas Sriwijaya Palembang Indonesia Universitas Sjakhyakirti Information System Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Departement of Computer System Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Informatic Management Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Information System Faculty of Computer Science Universitas Pembangunan Nasional Veteran Jakarta Jakarta Indonesia

ISBN: (纸本)9781665473286

The lungs are one of the organs of the body that are responsible for the human respiratory process and are very susceptible to dangerous diseases. For this reason, early detection and diagnosis of lung organs is needed, one of which is through examination of Chest X-Ray (CXR) images. Examination of the results of CXR images is still done manually by doctors and radiologists, this requires time and high accuracy. To facilitate the examination, it is necessary to image quality enhancement in order to get better image quality results so as to produce an accurate diagnosis. The initial stage in this research is to apply the contour improvement technique to the image using Morphology Opening, and followed by noise reduction using Median Filter and Gaussian filter. The results of the two methods of noise reduction are compared with the results of image quality in order to find out the best method that can be applied. The implementation of image quality enhancement results was measured quantitatively using Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), and Structural Similarity Index Metrics (SSIM). In the Morphology Opening and Median Filter methods, the values obtained are 39.187, 22.252, and 0.952, respectively. Meanwhile, the Morphology Opening and Gaussian Filter methods obtained values of 38.717, 23.917 and 0.956. Based on these results, it can be concluded that both methods are able to improve image quality well.

关键词： Image quality PSNR Multimedia systems Noise reduction Morphology Lung Medical services

Fusion of Mixture of Experts and Generative Artificial Intelligence in Mobile Edge Metaverse

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Mao, Shiwen Kim, Dong In The College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The School of Electrical and Computer Engineering University of Sydney Australia The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is slowed down by the challenges of content creation, scalability, and dynamic user interaction. Our study investigates an integration of Mixture of Experts (MoE) models with Generative Artificial Intelligence (GAI) for mobile edge computing to revolutionize content creation and interaction in the Metaverse. Specifically, we harness an MoE model's ability to efficiently manage complex data and complex tasks by dynamically selecting the most relevant experts running various sub-models to enhance the capabilities of GAI. We then present a novel framework that improves video content generation quality and consistency, and demonstrate its application through case studies. Our findings underscore the efficacy of MoE and GAI integration to redefine virtual experiences by offering a scalable, efficient pathway to harvest the Metaverse's full potential. © 2024, CC BY.

关键词： Augmented reality

An autonomous robotic system for collecting garbage over small water bodies

学校读者我要写书评

暂无评论

An autonomous robotic system for collecting garbage over sma...

作者： Syed Nouman Hasany Saniya Shah Zaidi Syed Ahmad Sohail Muhammad Farhan Electrical Engineering Program Habib University Computer Science Program Habib University Electrical and Computer Engineering Program Habib University

Water pollution is a grave problem requiring utmost attention as it directly affects marine *** freshwater ecosystem,for example,lakes and ponds,a major chunk of water garbage is plastic floating on the surface of water which is labor intensive to collect *** this paper,we present a novel autonomous robotic system capable of navigating small water bodies and is equipped with computer vision that helps it to detect the *** detection is followed by focusing on an area of interest to determine whether the garbage lies in the scope of robot for ***,if WiFi communication is available,the robot has the provision of tracking the detected garbage to determine its *** design of garbage collection unit of the robot ensures the garbage does not move outward once *** robot is tested in two different pools and with plastic bottles as main type of *** results manifest the high degree of control of its locomotion as well as of detection and collection of the *** deep neural network based detector onboard the robot can be retrained after self-collection of appropriate data to detect other types of garbage as well.

关键词： An autonomous robotic system for collecting garbage over small water bodies

Adversarial Self-Attention for Language Understanding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Hongqiu Ding, Ruixue Zhao, Hai Xie, Pengjun Huang, Fei Zhang, Min Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China School of Computer Science and Technology Soochow University China Damo Academy Alibaba Group China

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a "shortcut" between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its robust variant for Transformer-based pre-trained language models (e.g. BERT). We propose Adversarial Self-Attention mechanism (ASA), which adversarially biases the attentions to effectively suppress the model reliance on features (e.g. specific keywords) and encourage its exploration of broader semantics. We conduct a comprehensive evaluation across a wide range of tasks for both pre-training and fine-tuning stages. For pre-training, ASA unfolds remarkable performance gains compared to naive training for longer steps. For fine-tuning, ASA-empowered models outweigh naive models by a large margin considering both generalization and robustness. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics