检索结果-内蒙古大学图书馆

8th International Conference on Electronic Information Technology and computer engineering, EITCE 2024

作者： Qu, Zhiyu Wu, Xu Geng, Zhenya College of Information Science and Engineering Hohai University Jiangsu Nanjing China College of Computer Science and Software Engineering Hohai University Jiangsu Nanjing China The 49th Research Institute of China Electronics Technology Group Corporation Heilongjiang Harbin China

ISBN: (纸本)9798400710094

Traditional Direction of Arrival (DOA) estimation algorithms for coherent signals in uniform circular array (UCA), such as mode space transformation, allow for the adaptation of advanced algorithms initially developed for uniform linear arrays to be applied effectively in UCA. However, after mode space transformation, the array will encounter aperture loss and will also be unable to perform two-dimensional DOA estimation effectively. In this paper, we propose a new method that that integrates covariance matrix element transformation with the Multiple Signal Classification (MUSIC) to estimate the DOA of coherent signals in various symmetric antenna arrays, including UCA. The algorithm leverages the phase difference symmetry of the antenna array to decorrelate the incoming signals, effectively restoring the full rank of the covariance matrix. Subsequently, it employs two-dimensional MUSIC for DOA estimation. Simulation results demonstrate the effectiveness of the proposed algorithm. © 2024 Copyright held by the owner/author(s).

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

DDA: Distillation-Driven Acceleration of the Reverse Diffusion Process for Stochastic Multi-Ship Trajectory Prediction

DDA: Distillation-Driven Acceleration of the Reverse Diffusi...

引用

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

作者： Ma, Kun Han, Qilong Yao, Jingzheng Wu, Changmao Zhang, Yuntao College of Computer Science and Technology Harbin Engineering University Harbin China Yantai Research Institute Harbin Engineering University Yantai China Institute of Software Chinese Academy of Sciences Beijing China College of Shipbuilding Engineering Harbin Engineering University Harbin China

ISBN: (纸本)9798350368741

Modeling stochastic multi-ship trajectories is vital for maritime safety and interaction efficiency. Recent researches show that diffusion models excel in trajectory prediction, surpassing GANs and VAEs in generation quality, diversity and stability. However, their slow sampling speed remains a major limitation, as producing high-quality trajectories typically requires hundreds of denoising steps. We introduce DDA, a novel method that accelerates multi-ship trajectory generation by distilling the reverse diffusion process, progressively reducing sampling steps by half while minimizing quality loss. We use CVAE-based encoder to map multimodal inputs into state embeddings in the latent space, and use distillation diffusion in the latent space to more quickly and better represent multi-ship trajectories. The diffusion model uses Transformer-based core, and we incorporate SO(2) invariance and equivariance to enhance model representation. Validation on real-world AIS datasets shows that the student model retains high-quality trajectory generation while sampling speed is approximately 30 times faster. © 2025 IEEE.

关键词： Accelerating Sampling AIS Diffusion Model Progressive Distillation VAE

来源：评论

学校读者我要写书评

暂无评论

Sample Compression for Continual Learning

arXiv

引用

arXiv 2025年

作者： Comeau, Jacob Bazinet, Mathieu Germain, Pascal Subakan, Cem Computer Science and Software Engineering Department Laval University Canada Mila - Quebec Artificial Intelligence Institute Canada Computer Science and Software Engineering Department Concordia University Canada

Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees for the continual learning setup. In this paper, we present a new method called ‘Continual Pick-to-Learn’ (CoP2L), which is able to retain the most representative samples for each task in an efficient way. The algorithm is adapted from the Pick-to-Learn algorithm, rooted in the sample compression theory. This allows us to provide high-confidence upper bounds on the generalization loss of the learned predictors, numerically computable after every update of the learned model. We also empirically show on several standard continual learning benchmarks that our algorithm is able to outperform standard experience replay, significantly mitigating catastrophic forgetting. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach for investigating liquid fuel injection in combustion system

引用

Discover Artificial Intelligence 2025年第1期5卷 1-14页

作者： Inam, Syed Azeem Khan, Abdullah Ayub Ahmed, Noor Mazhar, Tehseen Shahzad, Tariq Khan, Sunawar Saeed, Mamoon M. Hamam, Habib Department of Artificial Intelligence and Mathematical Science Sindh Madressatul Islam University Sindh Karachi Pakistan Department of Computer Science and Information Technology Shaheed Benazir Bhutto University Lyari Karachi Pakistan Department of Computer Science Shaheed Zulfiqar Ali Bhutto Institute of Science and Technology Karachi Pakistan Department of Computer Science School Education Department Government of Punjab Layyah31200 Pakistan School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan Department of Software Engineering Islamia University of Bahawalpur Bahawalnagar62300 Pakistan Sana’a00967 Yemen Faculty of Engineering Uni de Moncton MonctonNBE1A3E9 Canada Department of Electrical and Electronic Engineering Sciences University of Johannesburg Johannesburg South Africa Av. Grandes Ecoles BP 1989 Libreville Gabon Bridges for Academic Excellence Spectrum Center-ville Tunis Tunisia

The intricacies and instability of introducing cryogenic propellants into the combustion system have piqued the curiosity of scientists studying the procedure. The latest innovation is utilizing data-driven machine learning and deep learning approaches to gain deeper insights into the related difficulties. However, the current work serves as a baseline for future research because relatively few studies have used data-driven methodologies to assess the temperature of liquid fuel injections in combustion systems. The performance of Linear Regression (LR), Random Forest (RF), Extra Trees Regressor (ETR), Polynomial Regression (PR), Support Vector Regressor (SVR), Decision Tree Regressor (DTR), Gradient Boost Regressor (GBR), XGB Regressor (XGBoost), AdaBoost Regressor (ABR), K-Neighbors Regressor (KNR), Long-Short Term Memory (LSTM), Bi-LSTM (Bi-directional Long-Short Term Memory) has all been investigated in this study. The study also suggested a Fully Connected Neural Network (FCNN) to examine its performance and paired it with an Extra Tree Regressor (ETR). The coupled FCNN and Extra Tree Regressor outperform the other algorithms with a Mean Square Error (MSE) of 0.0000005062, Root Mean Square Error (RMSE) of 0.00071148, Mean Absolute Error (MAE) of 0.00020672, and R-squared (R2) value of 0.99998689. Linear Regression, Polynomial Regression, and Support Vector Regressor are found to be the least-performing algorithms. The current work uses machine learning and deep learning methods to make data-driven decisions for liquid fuel injection in the combustion system. © The Author(s) 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Lift: Exploiting Hybrid Stacked Memory for Energy-Efficient Processing of Graph Convolutional Networks 23

Lift: Exploiting Hybrid Stacked Memory for Energy-Efficient ...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jiaxian Chen Zhaoyu Zhong Kaoyi Sun Chenlin Ma Rui Mao Yi Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350323481

Graph Convolutional Networks (GCNs) are powerful learning approaches for graph-structured data. GCNs are both computing- and memory-intensive. The emerging 3D-stacked computation-in-memory (CIM) architecture provides a promising solution to process GCNs efficiently. The CIM architecture can provide near-data computing, thereby reducing data movement between computing logic and memory. However, previous works do not fully exploit the CIM architecture in both dataflow and mapping, leading to significant energy *** paper presents Lift, an energy-efficient GCN accelerator based on 3D CIM architecture using software and hardware co-design. At the hardware level, Lift introduces a hybrid architecture to process vertices with different characteristics. Lift adopts near-bank processing units with a push-based dataflow to process vertices with strong re-usability. A dedicated unit is introduced to reduce massive data movement caused by high-degree vertices. At the software level, Lift adopts a hybrid mapping to further exploit data locality and fully utilize the hybrid computing resources. The experimental results show that the proposed scheme can significantly reduce data movement and energy consumption compared with representative schemes.

关键词： 3D-stacked memory

来源：评论

学校读者我要写书评

暂无评论

Dealing with Noisy Data in Federated Learning: An Incentive Mechanism with Flexible Pricing 25

Dealing with Noisy Data in Federated Learning: An Incentive ...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Hengzhi Chen, Haoran Ma, Minghe Cui, Laizhong Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798400712746

Federated Learning (FL) has emerged as a promising training framework that enables a server to effectively train a global model by coordinating multiple devices, i.e., clients, without sharing their raw data. Keeping data locally can ensure data privacy, but also makes the server difficult to assess data quality, leading to the noisy data issue. Specifically, for any given training task, only a portion of each client’s data is relevant and beneficial, while the rest may be redundant or noisy. Training with excessive noisy data can degrade performance. Motivated by this, we investigate the limitations of existing studies and develop an incentive mechanism with flexible pricing tailored for noisy data settings. The insight lies in mitigating the impact of noisy data by selecting appropriate clients and incentivizing them to clean their data spontaneously. Further, both rigorous theoretical analysis and extensive simulations compared with state-of-the-art methods have been well-conducted to validate the effectiveness of the proposed mechanism. © 2025 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Chain of Thought for Automated Medical Coding of Lymphoma Cases 10th

Leveraging Chain of Thought for Automated Medical Coding o...

引用

10th China Health Information Processing Conference, CHIP 2024

作者： Song, Wenlong Hu, Jiaxin Li, Zixuan Yuan, Chi College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9789819642977

Objective: This study aims to explore the application of Chain of Thought (CoT) reasoning in automating ICD coding, specifically focusing on lymphoma cases. By leveraging large language models (LLMs) and CoT prompting, the research aims to improve the accuracy and interpretability of automated ICD coding in healthcare. Methods: We optimized CoT prompting for Qwen 2.5:14b to guide the model in reasoning through the diagnostic process in a step-by-step manner. There are three main components for our pipeline. This framework was then evaluated on multiple LLMs, including Qwen 2.5, Llama 3.1, and Gemma 2, using a clinical lymphoma dataset for automated ICD-10 and ICD-O coding tasks. The models were assessed on their ability to extract relevant diagnoses from clinical text and map them to appropriate ICD codes. Results: The results indicated that CoT reasoning improves the interpretability and accuracy of ICD coding. However, the generalizability of CoT-based prompt design is not guaranteed for all the LLMs. Prompts optimized for one model do not consistently transfer to others, highlighting the importance of customizing prompts for each specific model. Conclusion: Our findings suggest that CoT reasoning can enhance automated ICD coding when tailored to the characteristics of each model. Future work should focus on optimizing CoT prompting techniques for different models to enhance generalizability and improve the scalability of automated coding systems in healthcare. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Oncology

来源：评论

学校读者我要写书评

暂无评论

Random Masked Autoencoders Framework for Multi-View Multi-Label Learning with Incomplete Views and Labels 25

Random Masked Autoencoders Framework for Multi-View Multi-La...

引用

Proceedings of the 2025 5th International Conference on Bioinformatics and Intelligent Computing

作者： Bo Cui Qing Ai Yuting Xu Yiying Wang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9798400712203

Dual incomplete multi-view multi-label learning (DIMVMLL) aims to make accurate predictions for multiple labels by exploiting incomplete multi-view information and incomplete multi-label information from input samples. Since the view information and label information of samples are incomplete in this task, existing DIMVMLL methods classify samples based on the semantic relationships between view features and labels. However, in the DIMVMLL task, exploring the consistent and complementary information between views is important for the classification performance of model. To learn high-quality view consistency information and complementary information, we propose random masked autoencoders framework (RMAF). First, we design a triple reconstruction loss for the dual-channel autoencoders to guide the model in extracting consistent and complementary information between views and introduce contrastive learning to guide the model in learning private information for each view. Second, we propose a feature-level random masking strategy to enhance high-level feature extract ability of the autoencoders. Furthermore, to preserve the feature semantic structure, we introduce structure loss. Extensive experiments have validated the effectiveness of our model.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Federated RL with NEAT, Markov Chains, and Gaussian Processes

引用

Procedia computer science 2025年 260卷 742-751页

作者： Robert McMenemy Kallinatha H D Hamsaveni M Sachin D N Software Engineer Independent Researcher Glasgow Area Scotland UK Dept of Computer Science and Engineering Siddaganga Institute of Technology Tumakuru India Dept of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India

Reinforcement Learning (RL) is a machine learning approach in which an agent learns to make decisions in an environment to maximize a cumulative reward. When combined with NeuroEvolution of Augmenting Topologies (NEAT), RL offers several advantages. NEAT is a genetic algorithm that optimizes the development of artificial neural networks by modifying both their structure and weights. When integrated with RL, NEAT can improve the learning process by merging evolutionary optimization with RL techniques. NEAT has demonstrated significant potential in evolving neural networks for RL tasks. However, traditional centralized training methods encounter scalability and data privacy issues. This paper investigates the integration of NEAT with Federated Learning (FL) and its enhancement with Markov Chains and Gaussian Processes to address certain issues. We propose a new framework that combines NEAT for neural network evolution with TensorFlow Federated (TFF) for decentralized training across multiple clients. Our approach is assessed using the BipedalWalker-v3 environment from OpenAI Gym. The experimental results show that our federated NEAT framework, augmented with Markov Chains and Gaussian Processes, achieves competitive performance while maintaining data privacy and reducing computational overhead on central servers. Additionally, we implement parallelization techniques using concurrent futures to enhance the efficiency of NEAT generations.

关键词： Federated Learning NEAT Reinforcement Learning TensorFlow Federated NeuroEvolution Privacy Decentralized Training Parallelization Markov Chains Gaussian Processes

来源：评论

学校读者我要写书评

暂无评论

MTEE: Multiscale Temporal Entropy Evaluation Paradigm for Heterogeneous Complex Datasets 20th

MTEE: Multiscale Temporal Entropy Evaluation Paradigm for H...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2024

作者： An, Ledong Wang, Chenyang Huang, Shaoyuan Guo, Yang Zhang, Cheng Qiu, Chao Wang, Xiaofei College of Intelligent and Computing Tianjin University Tianjin China College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China Tianjin University of Finance and Economics Tianjin China Software Technology Company Limited Suzhou215163 China

ISBN: (纸本)9789819628292

The rapid advancements in time-series forecasting have led to the emergence of datasets with increasingly diverse characteristics. Researchers typically focus on designing robust algorithms to handle these datasets. However, model performance can vary across different datasets. Existing studies commonly use Mean Absolute Error (MAE) and Mean Squared Error (MSE) to evaluate model performance. These metrics often need to fully account for the impact of dataset quality on forecast accuracy and reliability, leading to insufficient explanations of model forecasts and even dataset dependence. Furthermore, the lack of dataset evaluation makes it difficult to determine whether forecast results are influenced by data characteristics or model architecture, significantly hindering model improvement. To address this problem, this study proposes a new dataset evaluation paradigm-Multiscale Temporal Entropy Evaluation Paradigm. This paradigm aims to tackle the problem of data feature ambiguity affecting model forecast interpretability. By evaluating nine time-series datasets from domains such as weather, economics, transportation, and networks and comparing these evaluations with the forecast results from six different models, this study demonstrates the effectiveness of this method in explaining the relationship between dataset features and model performance. © IFIP International Federation for Information Processing 2025.

关键词： Spatio-temporal data

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：