检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Ahmad, Hussain Treude, Christoph Wagner, Markus Szabo, Claudia School of Computer and Mathematical Sciences University of Adelaide Australia School of Computing and Information Systems Singapore Management University Singapore Department of Data Science and AI Faculty of IT The Monash University Australia

Microservice architectures have become increasingly popular in both academia and industry, providing enhanced agility, elasticity, and maintainability in software development and deployment. To simplify scaling operations in microservice architectures, container orchestration platforms such as Kubernetes feature Horizontal Pod Auto-scalers (HPAs) designed to adjust microservice resources to accommodate fluctuating workloads. However, existing HPAs are not suitable for resource-constrained environments, as they make scaling decisions based on the individual resource capacities of microservices, leading to service unavailability, resource mismanagement, and financial losses. Furthermore, the inherent delay in initializing and terminating microservice pods hinders HPAs from timely responding to workload fluctuations, further exacerbating these issues. In addition, the architectures of existing HPAs exhibit several challenges, including single point of failure and the absence of coordinated scaling operations. To address these concerns, we propose Smart HPA and ProSmart HPA, reactive and proactive horizontal pod auto-scalers. These auto-scalers integrate centralized and decentralized styles. Smart HPA optimizes resource exchange in constrained environments, while ProSmart HPA uses machine learning to manage resource demands proactively, reducing delays and enabling preemptive resource sharing. Our experiments show Smart HPA outperforms Kubernetes HPA, and ProSmart HPA surpasses both by reducing resource overutilization, overprovisioning, underprovisioning, and increasing resource allocation to microservice applications. © 2024, The Authors. All rights reserved.

关键词： Losses

来源：评论

学校读者我要写书评

暂无评论

Rapid Maize Seedling Detection Based on Receptive-Field and Cross-Dimensional Information Interaction

Rapid Maize Seedling Detection Based on Receptive-Field and ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Hao, Fengqi Zhu, Shulei Ma, Dexin Dong, Xiangjun Kong, Hoiio Liu, Xia Mu, Chunhua Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China City University of Macau Faculty of Data Science 999078 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China Communication College Qingdao Agricultural University Qingdao266109 China Maize Research Institute Shandong Academy of Agricultural Sciences National Engineering Laboratory of Wheat and Maize Key Laboratory of Biology and Genetic Improvement of Maize in Northern Yellow-huai River Plain Ministry of Agriculture Jinan250100 China

ISBN: (纸本)9781665410205

The seedling stage is important in the growth and development of maize, and it is also a critical period that affects maize yield and quality. Accurately recognizing this stage of maize is challenging, as current maize seedling detection methods struggle with small sizes and complex environments. This paper proposes a rapid maize seedling detection method that emphasizes spatial feature extraction in the receptive field and cross-dimensional interaction - receptive field triplet attention YOLO (RFT-YOLO). First, we design a convolutional module for cross-dimensional information interaction within the receptive field. Second, we introduce an advanced selective fusion network, which boosts the multi-scale fusion capability of small object features while reducing the GFLOPs of the model. Additionally, we employ Inner-IoU to diminish sensitivity to positional biases of small objects and expedite the convergence of the loss function. Finally, we create a dataset of maize seedlings to conduct our experiments. Experimental results demonstrate that the RFT-YOLO significantly enhances performance, reducing the number of parameters by 35.3% and GFLOPs by 14.24%, compared to the baseline model. Moreover, the mean average precision (mAP) improves from 89.6% to 91.5%. These improvements confirm the model's effectiveness in detecting maize seedlings. © 2024 IEEE.

关键词： Deep learning Maize seedling detection Object detection UAV

来源：评论

学校读者我要写书评

暂无评论

Seat Occupancy Detection in Electric Vehicles: Unveiling Passenger Presence through Overlap Area Analysis

Seat Occupancy Detection in Electric Vehicles: Unveiling Pas...

引用

International Electronics Symposium (IES)

作者： Alivia Haris Alfan Rizaldy Pratama Bima Sena Bayu Dewantara Dadet Pramadihanto Center for Research and Innovation on Advanced Transportation Electrification Politeknik Elektronika Negeri Surabaya Surabaya Indonesia Data Science Department Faculty of Computer Science Universitas Pembangunan Nasional Veteran Jawa Timur Surabaya Indonesia Department of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia

ISBN: (数字)9798350391992

ISBN: (纸本)9798350392005

The high number of bus passengers often leads to situations where some passengers are unable to secure a seat, resulting in the inconvenience of standing for the whole ride or wasting time waiting at the bus stop. To address this issue, this paper aims to develop a system capable of detecting bus seat occupancy, differentiating between occupied and unoccupied seats by passengers to inform potential passengers if seats are available before they take the next bus and help the government monitor its citizen and improve its public transportation services. The system uses a YOLO algorithm to perform object detection, enabling it to detect passengers, and an overlap percentage formula between passenger and seat bounding box to determine if the detected passenger is occupying the seat. The system provides real-time video output with texts indicating the total number of current passengers, total boarded passengers, also occupied and unoccupied seats. The system achieves accuracy of 95% for the front seat section and 92% for the back seat section.

关键词： YOLO Accuracy Government Streaming media Electric vehicles Real-time systems Distance measurement

来源：评论

学校读者我要写书评

暂无评论

FEDBN: FEDERATED LEARNING ON NON-IID FEATURES VIA LOCAL BATCH NORMALIZATION 9

FEDBN: FEDERATED LEARNING ON NON-IID FEATURES VIA LOCAL BATC...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Li, Xiaoxiao Jiang, Meirui Zhang, Xiaofei Kamp, Michael Dou, Qi Department of Computer Science Princeton University United States Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Statistics Iowa State University United States Dept of Data Science and AI Faculty of IT Monash University Australia

The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of independent and identically distributed samples across local clients does not hold for federated learning setups. Under this setting, neural network training performance may vary significantly according to the data distribution and even hurt training convergence. Most of the previous work has focused on a difference in the distribution of labels or client shifts. Unlike those settings, we address an important problem of FL, e.g., different scanners/sensors in medical imaging, different scenery distribution in autonomous driving (highway vs. city), where local clients store examples with different distributions compared to other clients, which we denote as feature shift non-iid. In this work, we propose an effective method that uses local batch normalization to alleviate the feature shift before averaging models. The resulting scheme, called FedBN, outperforms both classical FedAvg, as well as the state-of-the-art for non-iid data (FedProx) on our extensive experiments. These empirical results are supported by a convergence analysis that shows in a simplified setting that FedBN has a faster convergence rate than FedAvg. Code is available at https://***/med-air/FedBN. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

MULTI-MODAL VISION TRANSFORMERS FOR CROP MAPPING FROM SATELLITE IMAGE TIME SERIES

arXiv

引用

arXiv 2024年

作者： Follath, Theresa Mickisch, David Hemmerling, Jan Erasmi, Stefan Schwieder, Marcel Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany Thünen Institute of Farm Economics Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

Using images acquired by different satellite sensors has shown to improve classification performance in the framework of crop mapping from satellite image time series (SITS). Existing state-of-the-art architectures use self-attention mechanisms to process the temporal dimension and convolutions for the spatial dimension of SITS. Motivated by the success of purely attention-based architectures in crop mapping from single-modal SITS, we introduce several multi-modal multi-temporal transformer-based architectures. Specifically, we investigate the effectiveness of Early Fusion, Cross Attention Fusion and Synchronized Class Token Fusion within the Temporo-Spatial Vision Transformer (TSViT). Experimental results demonstrate significant improvements over state-of-the-art architectures with both convolutional and self-attention components. © 2024, CC BY.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Heart Disease Classification: An Ensemble-Based Deep Learning Approach

Enhanced Heart Disease Classification: An Ensemble-Based Dee...

引用

IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)

作者： Nivaashini M Sathish Kumar G Uma Maheshwari G Soundariya R S Arun Kumar B Vijaya G Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Coimbatore Tamil Nadu India Department of Computer Technology Bannari Amman Institute of Technology Sathyamangalam Tamil Nadu India Department of Artificial Intelligence and Data Science Faculty of Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376142

The WHO's assessment indicates a rising prevalence of heart disease, exacerbated by challenges in detection and diagnosis in India due to population growth. Machine Learning (ML) is increasingly used for precise judgments in healthcare, aiming to accurately diagnose heart-related illnesses. This study proposes a Deep Learning (DL) ensemble method, combining ML classifiers to enhance accuracy. The ensemble model outperforms AdaBoost, XGBoost, Random Forest, Decision Tree, SVM, and Logistic Regression with 98.3% accuracy on a UCI dataset. Correlation-based Feature Selection (CFS) for relevant characteristic selection improves the model's accuracy, recall, precision, and f1-score. This research contributes to improved disease prediction and categorization in cardiovascular health, vital for effective healthcare interventions and outcomes.

关键词： Heart Deep learning Support vector machines Accuracy Medical services Signal processing SPICE Regression tree analysis Random forests Diseases

来源：评论

学校读者我要写书评

暂无评论

An Efficient Model based on Machine Learning Algorithms for Virtual Machines Classification in Cloud Computing Environment

An Efficient Model based on Machine Learning Algorithms for ...

引用

Innovative Research in Applied science, Engineering and Technology (IRASET),Conference on

作者： Abdelhadi Amahrouch Mehdi Bouhamidi Youssef Saadi Said El Kafhali Faculty of Sciences and Techniques Data Science for Sustainable Earth Laboratory Sultan Moulay Slimane University Beni Mellal Morocco Laboratory of Industrial and Human Automation Mechanics and Computer Science Polytechnic University Hauts-de-France France Faculty of Sciences and Techniques Computer Networks Modeling and Mobility Laboratory Hassan First University of Settat Settat Morocco

ISBN: (数字)9798350309508

ISBN: (纸本)9798350309515

In cloud computing, virtual machines consolidation (VMC) techniques are commonly used to improve resource utilization and reduce energy consumption. Task scheduling in cloud systems is a crucial aspect of VMC as it involves mapping clients' requirements to the appropriate computing resources such as Virtual Machines (VMs) or Physical Machines (PMs). The cloud provider must ensure that tasks are executed efficiently using the available shared computing resources while maintaining the quality of service (QoS) and minimizing the carbon footprint. Therefore, a good VM migration based on the customer's needs and IT resource capacity is required to maintain the best performance of the cloud system. In this work, we introduce an approach that leverage machine learning-based algorithms for VMs classification based on their latency sensitivity to facilitate subsequent migration into a suitable PM for better VMC. These algorithms categorize VMs into two groups: potentially inter-active machines (exhibiting periodic behavior on a daily scale) and latency-insensitive machines (for example, batch workloads, development, and test workloads). Our model demonstrated robust performance, achieving an accuracy of around 83%, thus establishing itself as the most proficient classifier in this study.

关键词： Cloud computing Machine learning algorithms Sensitivity Processor scheduling Computational modeling Quality of service Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Special issue: Recent developments in causal inference and machine learning

引用

Behaviormetrika 2022年第2期49卷 275-276页

作者： Shimizu, Shohei Kawano, Shuichi Faculty of Data Science Shiga University 1-1-1 Banba Hikone Shiga 522-8522 Japan Department of Computer and Network Engineering The University of Electro-Communications 1-5-1 Chofugaoka Tokyo Chofu 182-8585 Japan

来源：评论

学校读者我要写书评

暂无评论

EQCNN: Enhanced Remote Sensing Imagery Classification with Circuit-Based Error-Corrected Quantum Convolutional Neural Networks

EQCNN: Enhanced Remote Sensing Imagery Classification with C...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Muhammad Zaman Tanzila Kehkashan Adnan Akhunzada Hashem Alaidaros Mueen Uddin Muhammad Azeem Faculty of Computer Science University of Lahore Sargodha Punjab Pakistan Faculty of Computing Universiti Teknologi Malaysia Johor Bahru Malaysia Department of Data and Cybersecurity College of Computing & IT University of Doha for Science & Technology Doha Qatar Department of Cybersecurity Dar Al-Hekma University Jeddah Saudi Arabia

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Quantum information processing is more complex than classical counterpart because of the No-Cloning theorem, decoherence, and issues detecting quantum states. Building a quantum computer without error detection and correction module is challenging. To overcome this challenge, qubit error correction codes are implemented. Inadequate error detection and correction codes have been the downfall of earlier attempts to encode quantum information, leading to disrupted qubit transmission. Qubit information is decohered by circuit noise. Unfortunately, the principal qubit error, phase flip error is not corrected by existing qubit error correction methods. In this study, we proposed Quantum Error Detection and Correction scheme (QEDC) to keep qubit in a coherent state. Used S gates, unitary gates, 10 CNOT gates, and Hadamard gates spanning on 4 physical and 1 logical qubits over the IBM Quantum Experience Machine. We found that the error probability is reduced to 7.91% owing to the efficiency of the quantum information encoding and phase flip control. Furthermore, we proposed Error Corrected Quantum Convolution Neural Network (EQCNN) for Image Classification. EQCNN combat and correct qubit errors that occur during the image processing. EQCNN outperformed over Earth Observatory (EO) dataset, EuroSAT and achieved an impressive results of 99.3% accuracy, 98.9% F1-score, 96.73% precision, and 98.4% recall.

关键词： Quantum system Accuracy Observatories Qubit Neural networks Logic gates Quantum state Convolutional neural networks Remote sensing Image classification

来源：评论

学校读者我要写书评

暂无评论

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University China Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science & AI Faculty of Information Technology Monash University Australia

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant unlabeled data is highly desirable to boost the model training. However, most existing works still focus on limited medical tasks and underestimate the potential of learning across diverse tasks and multiple datasets. Therefore, in this paper, we introduce a Versatile Semi-supervised framework (VerSemi) to point out a new perspective that integrates various tasks into a unified model with a broad label space, to exploit more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, to capture cross-dataset semantics. Particularly, we create a synthetic task with a cutmix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint. This involves aligning aggregated predictions from various tasks with those from the synthetic task, further guiding the model in accurately segmenting foreground regions during training. We evaluated our VerSemi model on four public benchmarking datasets. Extensive experiments demonstrated that VerSemi can consistently outperform the second-best method by a large margin (e.g., an average 2.69% Dice gain on four datasets), setting new SOTA performance for semi-supervised medical image segmentation. The code will be released. © 2023, CC BY.

关键词： Semantics

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：