检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Haoran Zhang, Zhibo Kang, Jiarong Jiang, Xun Gong, Xiaoli Zhang, Jin Sun, Zhe Cichocki, Andrzej College of Computer Science Nankai University Tianjin China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Medicine Faculty of Health Data Science Juntendo University Japan Systems Research Institute Polish Academy of Science Warsaw Poland

ISBN: (纸本)9798350368741

data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://***/NKU-EmbeddedSystem/FreqSYN. © 2025 IEEE.

关键词： data argumentation frequency domain augmentation Gaussian kernel prediction time series

来源：评论

学校读者我要写书评

暂无评论

Class-Incremental Few-Shot Event Detection 30

Class-Incremental Few-Shot Event Detection

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhao, Kailin Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9782493814104

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, this task faces two problems, i.e., old knowledge forgetting and new class overfitting. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to handle the forgetting problem about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the superior performance of Prompt-KD. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Cancer Diseases Diagnosis Using Deep Transfer Learning Architectures 1st

Cancer Diseases Diagnosis Using Deep Transfer Learning Archi...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Promy, Tania Ferdousey Joya, Nadia Islam Turna, Tasfia Haque Sukhi, Zinia Nawrin Ashraf, Faisal Bin Uddin, Jia Department of Computer Science and Engineering School of Data Science Brac University Dhaka Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon Korea Republic of

ISBN: (纸本)9783031346187

Cancer is a lethal disease among the diseases in the world. It is clinically known as ‘Malignant Neoplasm’ which is a vast group of diseases that encompasses unmonitored cell expansion. It can begin anywhere in the body such as the breast, skin, liver, lungs, brain, and so on. As reported by the National Institutes of Health (NIH), the projected growth of new cancer cases is forecast at 29.5 million and cancer-related deaths at 16.4 million through 2040. There are many medical procedures to identify the cancer cell, such as mammography, MRI, CT scan, which are common methods for cancer diagnosis. The methods used above have been found to be ineffective and necessitate the development of new and smarter cancer diagnostic technologies. Persuaded by the phenomena of medical image classification using deep learning, our recommended initiative targets to analyze the performance of different deep transfer learning models for cancer cell diagnosis. In this paper, we have used VGG16, Inception V3 and MobileNet V2 deep architectures to diagnosis the breast cancer (KAU-BCMD dataset), lung cancer (IQ-OTH/NCCD dataset) and skin cancerHam10000). Experimental results demonstrate that VGG16 architecture shows comparatively higher accuracy by exhibiting 98.5% of accuracy for breast cancer, 99.90% for lung cancer and 93% for skin cancer dataset. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Special Issue on Evolutionary Computation for Games

引用

IEEE Transactions on Games 2023年第1期15卷 1-4页

作者： Schrum, Jacob Liu, Jialin Browne, Cameron Ekart, Aniko Gallagher, Marcus Southwestern University Department of Mathematics and Computer Science GeorgetownTX United States Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China Maastricht University Department of Data Science and Knowledge Engineering Maastricht Netherlands Aston University Department of Computer Science United Kingdom The University of Queensland School of Information Technology and Electrical Engineering Australia

The eight papers in this special section focus on applications of evolutionary computation to games to demonstrate several ways in which evolution can push boundaries and explore new areas of what is possible in the realm of games research, with a focus on game-playing, automatic agent parameter tuning, automatic game testing, and procedural content generation.

关键词： Special issues and sections Evolutionary computation Games

来源：评论

学校读者我要写书评

暂无评论

data-Driven Design for Anomaly Detection in Network Access Control Systems 2

Data-Driven Design for Anomaly Detection in Network Access C...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Muhammad, Musa Abubakar Caraffini, Fabio Fasanmade, Adebamigbe Ishola, Olabayo Mohammed, Kabiru Morden, Jarrad Coventry University School of Computing Mathematics and Data Science Coventry United Kingdom Swansea University Department of Computer Science Swansea United Kingdom De Montfort University School of Computer Science and Informatics Leicester United Kingdom

ISBN: (纸本)9798350335644

Current network access control systems can contain unpredictable interactions between multiple device models, multiple network protocol layers (e.g. TCP, UDP and ICMP), hardware, and clock-skew-specific influences, and cannot detect or identify abnormal behaviours based on the type of device. To complicate things further, the 'bring your own device' policy is increasing security threats, vulnerabilities, and risks to enterprise network environments, making intrusion detection and prevention systems unable to detect illegal and unauthorised access to devices in the enterprise network. The consequences can be disastrous. In this light, this work propose a simple but effective clustering approach capable of separating normal and abnormal network traffic patterns to detect such challenges (anomalies). The work in this paper applies this approach to single devices and aggregations of data per device type. Additionally, this work propose plotting the notched box for each cluster to acquire a better understanding of their data distributions and measuring the clusters' performance using the Adjusted Rand Index. The results show that the proposed method is valid, can be used in several contexts, and features a 95% confidence that most single device and device type distributions overlap, which makes them equivalently usable for anomaly detection purposes. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Emergency Vehicle Detection Using Deep ConvNet2D and computer Vision 2

Emergency Vehicle Detection Using Deep ConvNet2D and Compute...

引用

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Poongavanam, Elumalaivasan Prathik, A. Munirathinam, T. Kayalvizhi, V. Rajesh, R. Mahavishnu, C. Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai Kattankulathur India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Sona College of Technology Department of Information Technology Salem India School of Computer Science and Engineering and Information Science Presidency University Bangalore India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Shreenivasa Engineering College Department of Computer Science and Engineering Dharmapuri India

ISBN: (纸本)9798350328202

A surveillance system detects emergency vehicles stuck in traffic. This system helps manage traffic because the number of vehicles on the road has been increasing daily for years, causing congestion. This project implements Deep ConvNet2D (Convolutional Network 2D) and computer Vision emergency vehicle recognition. We propose a CNN-based real-time image processing model for emergency vehicle detection. The signal control unit can be set to terminate the round robin sequence when an emergency vehicle is detected. A CNN trained on Indian ambulance images solves the problem. Tensor Flow, a Python library, was used for training. Our method detects and classifies emergency cars well. Existing systems use ANN algorithm, which is inaccurate and inefficient. The system uses Deep ConvNet2D Algorithm. The proposed real-time system is accurate. The proposed system loads and executes faster than the existing system. The system is efficient, scalable, and enhanced for complex use cases. © 2024 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Language-agnostic Zero-shot Entity Linking via Entity Prototype Network 15

Language-agnostic Zero-shot Entity Linking via Entity Protot...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Yang, Haihong Qin, Ming Zhang, Qiang Xu, Renjun Zhejiang University College of Computer Science and Technology Hangzhou China Zhejiang University School of Software Technology Hangzhou China Zhejiang University Center for Data Science Hangzhou China

ISBN: (纸本)9798331508821

Following the recent trend of language understanding, we introduce a novel approach for constructing a general-purpose entity linking system by learning entity prototypes. Our model, the Entity Prototype Network (EPN), generates language-agnostic entity prototypes by reading entity descriptions and aligning diverse surface forms in different languages to the corresponding entity prototype in a unified vector space. To validate our core assumption of learnable language-agnostic entity prototypes, we define a new Zero-shot Cross-lingual Entity Linking (ZXEL) task. Additionally, we propose a simple yet effective auxiliary task termed Entity Identification, which enhances our model's ability to capture both intra-entity similarity and inter-entity dissimilarity. We evaluate our model on the new task in both classic and generalized settings. Experimental results demonstrate consistent improvements (exceeding 30% on average) over competitive baselines. An ablation study confirms the necessity of our model design and highlights the impact of the proposed auxiliary task. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Representation learning: serial-autoencoder for personalized recommendation

引用

Frontiers of computer science 2024年第4期18卷 61-72页

作者： Yi ZHU Yishuai GENG Yun LI Jipeng QIANG Xindong WU School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of the People’s Republic of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China

Nowadays,the personalized recommendation has become a research hotspot for addressing information *** this,generating effective recommendations from sparse data remains a ***,auxiliary information has been widely used to address data sparsity,but most models using auxiliary information are linear and have limited *** to the advantages of feature extraction and no-label requirements,autoencoder-based methods have become quite ***,most existing autoencoder-based methods discard the reconstruction of auxiliary information,which poses huge challenges for better representation learning and model *** address these problems,we propose Serial-Autoencoder for Personalized Recommendation(SAPR),which aims to reduce the loss of critical information and enhance the learning of feature ***,we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the ***,we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating *** output rating information is used for recommendation *** experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.

关键词： personalized recommendation autoencoder representation learning collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Provenance model for Lattice QCD 40

Provenance model for Lattice QCD

引用

40th International Symposium on Lattice Field Theory, LATTICE 2023

作者： Auge, Tanja Bali, Gunnar Klettke, Meike Ludäscher, Bertram Söldner, Wolfgang Weishäupl, Simon Wettig, Tilo University of Regensburg Faculty of Computer Science and Data Science Germany University of Regensburg Department of Physics Germany University of Illinois at Urbana-Champaign School of Information Sciences United States

Workflow management has become an important topic in many research communities. Here, we focus on the particular aspect of provenance tracking. We follow the W3C PROV standard and formulate a provenance model for Lattice QCD that includes the ensemble-generation and measurement parts of the Lattice QCD workflow. Since many important provenance questions in our community require extensions of this model, we propose a multi-layered provenance approach that combines prospective and retrospective elements. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Lattice theory

来源：评论

学校读者我要写书评

暂无评论

Dual Attention and Question Categorization-Based Visual Question Answering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 81-91页

作者： Mishra, Aakansha Anand, Ashish Guha, Prithwijit Department of Computer Science & Engineering Guwahati781039 India Department of Electronics and Electrical Engineering Guwahati781039 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Guwahati Guwahati781039 India

Visual question answering (VQA) aims at predicting an answer to a natural language question associated with an image. This work focuses on two important issues pertaining to VQA, which is a complex multimodal AI task: First, the task of answer prediction in a large output answer space, and second, to obtain enriched representation through cross-modality interactions. This work aims to address these two issues by proposing a dual attention (DA) and question categorization (QC)-based visual question answering model (DAQC-VQA). DAQC-VQA has three main network modules: First, a novel dual attention mechanism that helps toward the objective of obtaining an enriched cross-domain representation of the two modalities;second, a question classifier subsystem for identifying input (natural language) question category. The second module of question categorizer helps in reducing the answer search space;and third, a subsystem for predicting answer depending on the question category. All component networks of DAQC-VQA are trained in an end-to-end manner with a joint loss function. The performance of DAQC-VQA is evaluated on two widely used VQA datasets, viz., TDIUC and VQA2.0. Experimental results demonstrate competitive performance of DAQC-VQA against the recent state-of-the-art VQA models. An ablation analysis indicates that the enriched representation obtained using the proposed dual-attention mechanism helps improve performance. © 2022 IEEE.

关键词： Forecasting

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：