检索结果-内蒙古大学图书馆

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

ACM Computing Surveys 2025年第8期57卷 1-37页

作者： Xu, Huali Zhi, Shuaifeng Sun, Shuzhou Patel, Vishal Liu, Li College of Computer Science Nankai University Tianjin China College of Electronic Science and Technology National University of Defense Technology Changsha China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Johns Hopkins University Baltimore United States

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks. However, traditional FSL assumes that both the related and target tasks come from the same domain, which is a restrictive assumption in many real-world scenarios where domain differences are common. To overcome this limitation, Cross-domain few-shot learning (CDFSL) has gained attention, as it allows source and target data to come from different domains and label spaces. This article presents the first comprehensive review of Cross-domain Few-shot Learning (CDFSL), a field that has received less attention compared to traditional FSL due to its unique challenges. We aim at providing both a position article and a tutorial for researchers, covering key problems, existing methods, and future research directions. The review begins with a formal definition of CDFSL, outlining its core challenges, followed by a systematic analysis of current approaches, organized under a clear taxonomy. Finally, we discuss promising future directions in terms of problem setups, applications, and theoretical advancements. © 2025 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Medical Named Entity Recognition in Arabic Text using SVM 3

Medical Named Entity Recognition in Arabic Text using SVM

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2023

作者： Hamad, Rema Muftah Abushaala, Ahmed Mohamed Misurata University Faculty of Information Technology Computer Science Department Libya

ISBN: (纸本)9798350319897

There is a huge amount of digitalized medical documents which are valuable for many applications. The text in a medical document is needed to collect knowledges and information about diseases and are used to make medical decisions. An automatic processing to extract information and recognizing named entities in these texts is very useful to facilitate many medical tasks. However, the text is not structured and is written in natural language, which makes this task a challenge. In fact, recognizing entities in Arabic language is not well studied in this field. In our work, we propose a Named Entity Recognition (NER) model to recognize entities such as: of disease, diagnosis, treatment, and symptom. For that, we perform a classification task using a dataset of 27 real medical documents based on a Support Vector Machine (SVM). We have pre-processed the text and selected candidate words to be classified. Then, we have represented each word by multiple features such as: FastText embedding, Part of Speech (PoS), Term Frequency-Inverse Document Frequency TF-IDF embedding, and non medical word matching. To classify the word, we take into account the surrounding words to capture its context. We have used PCA to reduce the size of TF-IDF vectors and we don't use a hand-crafted supplemental resource. Thus, we have classified each word into its entity class by the SVM model. Evaluation results show that our model is stable and provides high and balanced results. In addition, we outperform a state-of-the-art model by an F1-score of +6.56% although the model requires a big manual effort for preparation. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Robust Device-Free Mmwave Sensing with Specular Reflection Interference Mitigation

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5749-5764页

作者： Liu, Yulin Wang, Jie Gao, Qinghua Pan, Miao Fang, Yuguang Dalian Maritime University School of Information Science and Technology Dalian116026 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

Device-Free mmWave Sensing (DFWS) could sense target state by analyzing how target activities influence the surrounding mmWave signals. It has emerged as a promising sensing technology. However, when employing DFWS indoors, specular reflection interference arises due to the specular reflectors. This interference often induces ghost targets, impacting the accurate estimation of the number and position of targets, resulting in degradation in sensing performance. To tackle this issue, we delve into the generation mechanism of specular reflection interference and analyze its multi-domain characteristics. Through exploration, we discern its temporal sparsity, spatial symmetry or collinearity, and frequency correlation characteristics, and propose four metrics to measure them, accordingly. Specifically, we propose a temporal characteristic quantitative evaluation metric based on identity matching, spatial symmetry and collinearity quantitative evaluation metrics based on geometric analysis, and a frequency correlation quantitative evaluation metric based on Doppler velocity correction, respectively. Based on these metrics, we design a novel Specular Reflection Interference Mitigation (SRIM) method and develop a robust SRIM-DFWS prototype system based on a 60 GHz mmWave radar to validate our proposed method. Experimental results demonstrate that our proposed method could achieve accurate and effective mitigation of specular reflection interference in device-free target tracking. © 2002-2012 IEEE.

关键词： Radar interference

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Satellite Image Segmentation Analyzes for Coastal Flood Disaster 8

Deep Learning Based Satellite Image Segmentation Analyzes fo...

引用

8th International Conference on Electrical, Telecommunication and computer Engineering, ELTICOM 2024

作者： Hayatunnufus Candra, Ade Slamet, Bejo Jaya, Ivan Wilson Syadzwana, Hajarani Universitas Sumatera Utara Computer Science Faculty of Computer Science and Information Technology Medan Indonesia Universitas Sumatera Utara Faculty Forestry Departement Forestry Medan Indonesia

ISBN: (纸本)9798331531249

Rob floods have become a crucial and complex problem that occurs in many coastal areas throughout the world. This disaster occurs due to many factors, including when sea water rises above normal height and enters coastal areas, causing waterlogging in the area, the impact can damage the environment, infrastructure and disrupt the lives of local communities. Medan Belawan District is one of the sub-districts located in the north of the city of Medan, which borders the Malacca Strait to the north, being a location that is very close to the water so it is predicted that it will be affected by the Rob flood disaster. Deep Learning is a technological innovation whose application can be used to improve flood disaster mitigation. This research uses the Computational Neural Network (CNN) algorithm by implementing the U-Net architecture. U-Net is a type of CNN algorithm architecture which is built with an Encoder-Decoder architecture. Semantic segmentation, which is widely used in classifying satellite images, is one of the methods applied in this research. The segmentation process that applies pixel wise classification aims to make the differences in image details visible and the extraction process can be carried out. The steps taken in this research include Data Gathering, Spatial Filtering, Visual Filtering, Annotation, Pre-Processing, Modeling, Post-Processing and Deployment. In a comparative analysis of image segmentation, researchers compared the results of the U-Net and K-means models used, for semantic segmentation with k- means having two pixel quantization techniques: k-Means with k=2 and multi-otsu with k=5. The U-Net model performs segmentation by utilizing an artificial neural network that has been previously trained to identify and map pixel labels in images. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Framework for Democratizing Open-Source Decision-Making using Decentralized Autonomous Organization 6

A Framework for Democratizing Open-Source Decision-Making us...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Afifi, Khalifa H. Fouad, Khaled M. Asian, Heba K. Faculty of Information Technology and Computer Science Nile University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computers and Engineering New Mansoura University Egypt Cairo Egypt Center of Informatics Science Faculty of Information Technology and Computer Science Nile University Cairo Egypt

ISBN: (纸本)9798350373875

The open Source Software (OSS) became the backbone of the most heavily used technologies, including operating systems, cloud computing, AI, Blockchain, Bigdata Systems, IoT, and many more. Although the OSS individual contributors are the primary power for developing the OSS projects, they do not contribute to the OSS project's decisionmaking as much as their contributions in the OSS Projects development. This paper proposes a framework to democratize the OSS Project's decision-making using a blockchain-related technology called Decentralized Autonomous Organization (DAO). Using DAO, contributors get incentive tokens as a reward in return for contributions. The earned tokens can be used in the process of decision-making governance. This governance model tends to allow OSS individual contributors to have a public voice in the OSS project's development roadmap in particular, and the OSS decision making governance in general. © 2024 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

YOLOv8n-CGW: A novel approach to multi-oriented vehicle detection in intelligent transportation systems

引用

Multimedia Tools and Applications 2025年第7期84卷 3809-3840页

作者： Berwo, Michael Abebe Fang, Yong Sarwar, Nadeem Mahmood, Jabar Aljohani, Mansourah Elhosseini, Mostafa School of Information and Engineering Chang’an University Shaanxi Xi’an710064 China Department of Computer Science Bahria University Lahore Campus Punjab Lahore54600 Pakistan Department of Information Technology Faculty of Computing and Information Technology University of Sialkot Punjab Sialkot51040 Pakistan College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

In the context of Intelligent Transportation Systems (ITS), the role of vehicle detection and classification is indispensable for streamlining transportation management, refining traffic control, and conducting in-depth accident analyses. However, the intricate task of accurately detecting multi-oriented vehicles in diverse scenarios remains a challenge, even with the advancements in ITS. Factors such as vehicle morphology, design, road conditions, structural details, and climatic variables provide a significant part in the detection. To address this, our study introduces an advanced YOLOv8n model, specifically the YOLOv8n-CGW, which is built upon pre-trained deep learning frameworks. This model is meticulously tailored to enhance the detection capabilities for multi-oriented vehicles. Comprehensive evaluations on esteemed datasets like MtV, MERGED, Custom dataset, DAWN, WEDGE, and UA-DETRAC underscore the superiority of our approach over existing models. Notably, our YOLOv8n-CGW model achieves a remarkable mAP of 83.3% and boasts a swift inference time of 0.0019s, setting a new benchmark in the domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing Standardized Inverse Time-Current Curve Types of Overcurrent Relays for Efficient Overcurrent Protection in Distribution Networks 47

Analyzing Standardized Inverse Time-Current Curve Types of O...

引用

47th ICT and Electronics Convention, MIPRO 2024

作者： Rojnić, Michele Prenc, Rene Dubravac, Marina Šimić, Zvonimir University Of Rijeka Faculty Of Engineering Croatia University Of Osijek Faculty Of Electrical Engineering Computer Science And Information Technology Croatia

ISBN: (纸本)9798350382495

The selection of the appropriate curve type of overcurrent relay function is significant for achieving optimal coordination of overcurrent protection in distribution networks. In this study, we conducted a comprehensive analysis of the overcurrent relays performance regarding their different inverse time-current curve types. Additionally, different fault locations were taken into consideration. To investigate the impact of curve types on overcurrent relays coordination, we employed a uniform curve type for all overcurrent relays in two representative power systems. The results, encompassing three standardized IEC curve types, are presented, and analyzed to illustrate the efficacy of our proposed approach. Therefore, this study underscores the critical role that curve type selection has in determining the feasibility of attaining reasonably low overcurrent relay trip times. © 2024 IEEE.

关键词： Relay protection

来源：评论

学校读者我要写书评

暂无评论

Evaluation Of Time Series Forecasting Techniques For Air Quality Prediction: Case Study of NO2 Levels

Evaluation Of Time Series Forecasting Techniques For Air Qua...

引用

2024 International of Seminar on Application for technology of information and Communication, iSemantic 2024

作者： Anggraini, Lilis Noersasongko, Edi Purwanto Marjuni, Aris Dian Nuswantoro University Semarang Faculty of Computer Science Semarang Indonesia Banjarmasin Faculty of Information Technology Semarang Indonesia

ISBN: (纸本)9798350366648

Air quality is an important factor for human life, as a decrease in air quality has a major impact on human health. Nitrogen dioxide (NO2) is one of the main pollutants that has a direct effect on human health. This study assesses the performance of three models for time series forecasting, namely AutoRegressive Integrated Moving Average (ARIMA), eXtreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) in predicting NO2 concentration. The data used is air quality data from Beijing over the period 2013 to 2024. The research methodology includes data pre-processing steps to address missing values and reduce noise. Afterwards, ARIMA, XGBoost and LSTM models are applied, with the most maximized parameters selected through a cross-validation process. The XGBoost model based on the test results is the model with the best performance among other models, evidenced by the lowest prediction error values (RMSE, MAPE, MAE). The ARIMA and LSTM models, although providing good results, are still below the performance of XGBoost, XGBoost is able to capture fluctuations in NO2 concentration more accurately. This finding suggests that XGBoost is superior in modeling the complexity of air quality time series data. With the results obtained, it is expected to contribute to the development of better air quality prediction strategies and support more informed decision making for public health improvement. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing V2X QoS: dynamic scheduling scheme over 5G networks and byon

引用

International Journal of information technology (Singapore) 2024年第7期16卷 4427-4433页

作者： Mansouri, Wahida Ali Mohammed Elmourssi, Doaa Elyass, Wiam Almalih Department of Computer Science and Information Technology Faculty of Sciences and Arts Northern Border University LETI Laboratory University of Sfax

Over the years, various research teams have dedicated efforts to create scheduling algorithms that are not only effective but also efficient, with the goal of enhancing the quality of service in Vehicle-to-Everything (V2X) communication over 5G (5 Generation) networks. The proliferation of connected vehicles and the advent of 5G technologies present an unprecedented opportunity to optimize communication reliability, latency, and throughput in V2X scenarios. This paper introduces a novel scheduling that adapts to the dynamic nature of vehicular environments, ensuring seamless and efficient communication. The proposed scheduling scheme takes into consideration the traffic prioritization to effectively manage Quality of Service (QoS) for diverse traffic types. This approach considers different metrics such as channel quality, remaining payload, and delay. The results of our simulation show how well our Scheduling V2X Communications (SVC) algorithm performs, leading to minimizing latencies. For a sample of 100 users, the average latency in our suggested scheme was less than 0.001 ms. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： 5G networks Prioritization QoS Scheduling V2X

来源：评论

学校读者我要写书评

暂无评论

Economical Camera-based Measuring Scheme for Roundabout Traffic

引用

Periodica Polytechnica Transportation Engineering 2025年第2期53卷 235-241页

作者： Kovács, Tamás Kovács, Lóránt Department of Information Technology GAMF Faculty of Engineering and Computer Science John von Neumann University Izsáki út 10. KecskemétH-6000 Hungary

Counting the turning movements in a four-leg roundabout is a challenging task and often executed by vehicle recognition and tracking on traffic videos. In order to obtain accurately all the 12 flow values of the origin-destination (O-D) matrix we need to measure arbitrary chosen 12 linearly independent flow values. However, the larger the area to be observed the more cameras are needed because the good pixel resolution of the vehicles and the proper camera inclination angles are essential. Here we propose a novel measuring scheme, which observes only two roundabout legs instead of observing all the four, as a result obtaining all the 12 flow values requires a reduced number of cameras. The directly measured flow values and the mathematical method of determining the O-D matrix are given in details. © 2025 Budapest University of technology and Economics. All rights reserved.

关键词： Object recognition

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：