检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Burgert, Tom Demir, Begüm BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany

The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervised image classification. In particular, channel transformations (e.g., solarize, grayscale, brightness adjustments) are integrated into data augmentation pipelines for remote sensing (RS) image classification tasks. However, contradicting beliefs exist about their proper applications to RS images. A common point of critique is that the application of channel augmentation techniques may lead to physically inconsistent spectral data (i.e., pixel signatures). To shed light on the open debate, we propose an approach to estimate whether a channel augmentation technique affects the physical information of RS images. To this end, the proposed approach estimates a score that measures the alignment of a pixel signature within a time series that can be naturally subject to deviations caused by factors such as acquisition conditions or phenological states of vegetation. We compare the scores associated with original and augmented pixel signatures to evaluate the physical consistency. Experimental results on a multi-label image classification task show that channel augmentations yielding a score that exceeds the expected deviation of original pixel signatures can not improve the performance of a baseline model trained without augmentation. © 2024, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

English Offensive Text Detection Using CNN Based Bi-GRU Model

English Offensive Text Detection Using CNN Based Bi-GRU Mode...

引用

Information and Communication Technology (ICICT), International Conference on

作者： Tonmoy Roy Md Robiul Islam Asif Ahammad Miazee Anika Antara Al Amin Sunjim Hossain Data Analytics & Information Systems Utah State University Utah United States Computer Science William & Mary Virginia United States Computer Science Maharishi International University Iowa United States Electrical and Electronics Engineering Brac University Dhaka Bangladesh Computer Science Uttara University Dhaka Bangladesh Computer Science Northern University Dhaka Bangladesh

ISBN: (数字)9798331508227

ISBN: (纸本)9798331508234

Over the years, the number of users of social media has increased drastically. People frequently share their thoughts through social platforms, and this leads to an increase in hate content. In this virtual community, individuals share their views, express their feelings, and post photos, videos, blogs, and more. Social networking sites like Facebook and Twitter provide platforms to share vast amounts of content with a single click. However, these platforms do not impose restrictions on the uploaded content, which may include abusive language and explicit images unsuitable for social media. To resolve this issue, a new idea must be implemented to divide the inappropriate content. Numerous studies have been done to automate the process. In this paper, we propose a new Bi-GRU-CNN model to classify whether the text is offensive or not. The combination of the Bi-GRU and CNN models outperforms the existing models.

关键词： Image resolution Social networking (online) Blogs Text detection Information and communication technology Videos

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

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Xi’an710072 China The University of Adelaide Australian Institute for Machine Learning AdelaideSA5000 Australia Monash University Faculty of Information Technology Department of Data Science and AI Australia

The scarcity of annotations has become a significant obstacle in training powerful deep-learning models for medical image segmentation, limiting their clinical application. To overcome this, semi-supervised learning that leverages abundant unlabeled data is highly desirable to enhance model training. However, most existing works still focus on specific medical tasks and underestimate the potential of learning across diverse tasks and datasets. In this paper, we propose a Versatile Semi-supervised framework (VerSemi) to present a new perspective that integrates various SSL tasks into a unified model with an extensive label space, exploiting 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, capturing 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 that aligns aggregated predictions from various tasks with those from the synthetic task, further guiding the model to accurately segment foreground regions during training. We evaluated our VerSemi framework against seven established SSL methods on four public benchmarking datasets. Our results suggest that VerSemi consistently outperforms all competing methods, beating the second-best method with a 2.69% average Dice gain on four datasets and setting a new state of the art for semi-supervised medical image segmentation. Code is available at https://***/maxwell0027/VerSemi. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

THEF: A Privacy-Preserving Framework for Transformer Inference leveraging HE and TEE

THEF: A Privacy-Preserving Framework for Transformer Inferen...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Zehao Li Jiachun Liao Jinhao Yu Lei Zhang Department of Computer Science and Engineering Shanghai Jiao Tong University China Big Data Research Center Nanhu Laboratory Jiaxing China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

The transformer has profoundly driven the development of natural language processing and computer vision tasks. However, their widespread deployment has raised concerns about the potential leakage of data privacy. To address the issue, homomorphic encryption (HE) is employed as a secure technique to process user private inputs over ciphertexts. As HE only supports linear operations, non-linear functions are required to be approximated into polynomials, which leads to heavy communication and computation overhead. In this paper, we propose THEF (Tee-And-HE-based Framework), an efficient and secure inference framework for transformer inference, which uses HE to ensure data security and leverages Trusted Execution Environment (TEE) to reduce communication and computation cost. We also design a number of optimization methods, including expanding encoding matrix multiplication scheme, batch acceleration and adaptive scheme, to improve performances of the THEF. Finally, we compare the performances of THEF and the state-of-the-art methods. The experimental results demonstrate that THEF maintains a level of accuracy close to that of plaintext model, reduces end-to-end communication cost by 80% and achieves significant improvement in end-to-end run-time.

关键词： Privacy Costs Accuracy Noise Optimization methods Transformers Encoding Polynomials Safety Homomorphic encryption

来源：评论

学校读者我要写书评

暂无评论

Approximate Message Passing with Rigorous Guarantees for Pooled data and Quantitative Group Testing

arXiv

引用

arXiv 2023年

作者： Tan, Nelvin Cobo, Pablo Pascual Scarlett, Jonathan Venkataramanan, Ramji Department of Engineering University of Cambridge United Kingdom Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore Singapore

In the pooled data problem, the goal is to identify the categories associated with a large collection of items via a sequence of pooled tests. Each pooled test reveals the number of items of each category within the pool. We study an approximate message passing (AMP) algorithm for estimating the categories and rigorously characterize its performance, in both the noiseless and noisy settings. For the noiseless setting, we show that the AMP algorithm is equivalent to one recently proposed by El Alaoui et al. Our results provide a rigorous version of their performance guarantees, previously obtained via non-rigorous techniques. For the case of pooled data with two categories, known as quantitative group testing (QGT), we use the AMP guarantees to compute precise limiting values of the false positive rate and the false negative rate. Though the pooled data problem and QGT are both instances of estimation in a linear model, existing AMP theory cannot be directly applied since the design matrices are binary valued. The key technical ingredient in our analysis is a rigorous asymptotic characterization of AMP for generalized linear models defined via generalized white noise design matrices. This result, established using a recent universality result of Wang et al., is of independent interest. Our theoretical results are validated by numerical simulations. For comparison, we propose estimators based on convex relaxation and iterative thresholding, without providing theoretical guarantees. The simulations indicate that AMP outperforms the convex estimator for noiseless pooled data and QGT, but the convex estimator performs slightly better for noisy pooled data with three categories when the number of observations is small. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Coexistence of 802.11 WLAN and 5G Networks using a Multi-Task Learning with Convolutional Neural Network Model

Enhancing the Coexistence of 802.11 WLAN and 5G Networks usi...

引用

Information Technology and Digital Innovation (ISITDI), International Symposium on

作者： Dody Ichwana Putra Shelvi Ekariani Dept. of Computer Engineering Universitas Andalas Padang Indonesia Dept. of Mathematics and Data Science Universitas Andalas Padang Indonesia

ISBN: (数字)9798350389241

ISBN: (纸本)9798350389258

The increasing need for high-speed internet for wireless devices has driven the development of 5G New Radio (NR) technology. The 5G NR operates in various spectrums such as sub-1 GHz, sub-6 GHz, and millimeter wave (mmWave) in the 26–28 GHz range. Conversely, the new standard Wi-Fi 6E operates on the unlicensed band and currently utilizes 2.4 GHz, 5 GHz, and 6 GHz. The coexistence of 5G NR sub-6 GHz and Wi-Fi 6E networks can result in interference and reduced performance for both technologies. To address this challenge, we introduce a Multi-Task Learning (MTL) approach using Convolutional Neural Networks (CNN) to improve the coexistence of 5G and Wi-Fi 6E networks. This proposes identifying and classifying packets transmitted and its modulation over both types of networks. The MTL-CNN model is trained to classify packets based on their type (e.g., 5G or Wi-Fi) and to identify the specific protocol used within each packet. We confirm the accuracy of this method with Wi-Fi and 5G signals produced by the MATLAB waveform simulator and subsequently deploy it on a hardware testbed using SDR. Our experimental results show that this method improves the accuracy of packet identification and classification, thus enhancing the coexistence between 5G and Wi-Fi 6E networks. MTL-CNN potentially leads to more efficient use of the wireless spectrum and improves the overall performance of wireless communication systems.

关键词： Wireless communication Accuracy 5G mobile communication Modulation Multitasking Mathematical models Convolutional neural networks Millimeter wave communication Wireless fidelity IEEE 802.11 Standard

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of Reward Functions for Load Balancing in Cloud datacenters

Design and Evaluation of Reward Functions for Load Balancing...

引用

Innovative Trends in Information Technology (ICITIIT), International Conference on

作者： Samriddhee Ghosh Karthick Seshadri Chidambaran Kollengode Dept. of Computer Science and Engineering National Institute of Technology Andhra Pradesh India AI and Data Platforms LinkedIn Bangalore India

ISBN: (数字)9798350386813

ISBN: (纸本)9798350386820

Task scheduling and virtual machine (VM) consolidation techniques optimize resource utilization and distribute the load evenly across physical machines and virtual machines in a virtualized data center. Users’ requests to applications hosted on the virtual machines are dynamic. Though schedulers assign tasks to VMs based on the current state of the VMs and the expected resource requirements of the tasks, the requirements of the tasks typically tend to deviate from the expected requirements. This eventually leads to load imbalance and skewed energy consumption across virtual machines. Load imbalance and high energy consumption occur due to dynamic nature of workloads across the data center. An overloaded VM experiences degradation in performance thereby violating Quality of Service (QoS) and Service Level Agreement (SLA) requirements. In this work, a reinforcement learning (RL)-based task scheduling approach is utilized to minimize load imbalance, wherein we compare the effectiveness of using different reward functions. The RL agent learns a policy to minimize the number of overloaded VMs and to reduce deviation from a load-balanced condition by efficiently scheduling tasks using Q-learning algorithm. It takes scheduling decisions with the help of previous experiences when it encounters similar workload patterns. Experiments have been performed on the real time Google cluster traces and the proposed reward functions were assessed for their performance.

关键词： Energy consumption data centers Q-learning Quality of service Virtual machining Scheduling Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Switching Millimeter Wave Channels Using Fuzzy Controller System

Switching Millimeter Wave Channels Using Fuzzy Controller Sy...

引用

IEEE International Conference on RFID-Technology and Applications (RFID-TA)

作者： Esmail Abuhdima Abdulmajid Mrebit Naomi Rolle Jason Laing Nabeyou Tedessa Jian Liu Amirhossein Nazeri Gurcan Comert Chin-Tser Huang Pierluigi Pisu Engineering Technology ECPI University Newport news VA USA Engineering and Computer Science Benedict College Columbia USA Computer Science and Engineering University of South Carolina Columbia USA International Center for Automotive Clemson University Greenville USA Computational Data Science and Engineering North Carolina A&T State University Greensboro NC USA

ISBN: (数字)9798331540227

ISBN: (纸本)9798331540234

This paper introduces a novel approach for managing 5G millimeter-wave channel switching, addressing the critical need for high-speed, low-latency communication. While promising significantly higher transmission rates, millimeter-wave frequencies are highly susceptible to environmental conditions such as rain, snow, dust, and sand, leading to signal attenuation and connectivity disruptions. To counter these challenges, we propose a Fuzzy Controller for switching mm-wave channels, which utilizes advanced algorithms to ensure smooth and efficient channel transitions. Our model quantifies the impact of environmental conditions on 5G signal propagation, precisely simulating how rainfall influences signal strength. Unlike devices on the market that typically switch between two frequencies based on signal strength alone, our approach intelligently incorporates environmental data such as visibility and rain intensity to choose optimally from five different frequencies. Through extensive simulations and performance evaluations, we show that our approach ensures reliable connectivity while maintaining high data speeds and minimizing latency. This research sets a foundational platform for future investigations into robust millimeter-wave channel switching mechanisms for 5G networks, enhancing user experience and overall network efficiency.

关键词： Rain 5G mobile communication Snow Millimeter wave technology Switches Control systems Attenuation User experience Reliability Millimeter wave communication

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Alzheimer Disease Using MRI Scan: A Deep Learning Approach

Diagnosing Alzheimer Disease Using MRI Scan: A Deep Learning...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： S. Saravanan K. Muthumanickam N. Subha P.C.Senthil Mahesh Department of CSE-Data Science Dayananda Sagar Academy of Technology and Management Bengaluru India Department of Information Technology Kongunadu College of Engineering and Technology (Autonomous) Thottiyam Tamilnadu India Department of Computer Science and Engineering Knowledge Institute of Technology Salem Tamilnadu India Department of Computer Science and Engineering Excel Engineering College Komarapalayam Tamilnadu India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

The neurodegenerative disease known as Alzheimer's disease (AD), which affects people worldwide, is complicated to treat and expensive. Conventional approaches, including manual Support Vector Machine (SVM) based methods with separate feature extraction and preprocessing, lack automation and pose limitations. This project recognizes the pressing need for efficient and automated solutions. Building on existing work that employed SVM and manual processing for Alzheimer's diagnosis, this work proposes a novel approach. Utilizing brain MRI scans and the VGG16 architecture, our automated system achieves high accuracy in predicting both labeled and unlabeled data. The integration of VGG16 ensures a streamlined process, eliminating manual intervention in feature extraction and preprocessing. This automation enhances accessibility, reduces costs, and offers a user-friendly interface for users. In contrast to traditional methods, our proposed system allows users to input MRI scans, facilitating prompt and accurate predictions. Upon analysis, the proposed system provides doctor recommendations and suggests prescriptions. The VGG16-based approach not only ensures superior diagnostic accuracy but also streamlines the entire process, emphasizing the importance of early detection for improved outcomes in Alzheimer's disease management.

关键词： Support vector machines Accuracy Automation Magnetic resonance imaging Manuals Pressing Streaming media

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

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：