检索结果-内蒙古大学图书馆

Dynamic prompting class distribution optimization for semi-supervised sound event detection

Frontiers of Information Technology and Electronic Engineering 2025年第4期26卷 556-567页

作者： Gao, Lijian Zhu, Qing Shen, Yaxin Mao, Qirong Zhan, Yongzhao School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212016 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications Zhenjiang212016 China

Semi-supervised sound event detection (SSED) tasks typically leverage a large amount of unlabeled and synthetic data to facilitate model generalization during training, reducing overfitting on a limited set of labeled data. However, the generalization training process often encounters challenges from noisy interference introduced by pseudo-labels or domain knowledge gaps. To alleviate noisy interference in class distribution learning, we propose an efficient semi-supervised class distribution learning method through dynamic prompt tuning, named prompting class distribution optimization (PADO). Specifically, when modeling real labeled data, PADO dynamically incorporates independent learnable prompt tokens to explore prior knowledge about the true distribution. Then, the prior knowledge serves as prompt information, dynamically interacting with the posterior noisy-class distribution information. In this case, PADO achieves class distribution optimization while maintaining model generalization, leading to a significant improvement in the efficiency of class distribution learning. Compared with state-of-the-art methods on the SSED datasets from DCASE 2019, 2020, and 2021 challenges, PADO achieves significant performance improvements. Furthermore, it is readily extendable to other benchmark models. © Zhejiang University Press 2025.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

big data-Intelligence Analytics for Energy Optimization in IoT-Enabled Smart Home Devices

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Yihong Song, Qiang Zhaoqing University Big Data Engineering Technology Center China Zhaoqing University School of Computer Science and Software China

This article explores the integration of Artificial Intelligence (AI) and big data Analytics to optimize energy consumption in IoT-enabled smart home devices. It presents a robust analytical framework that leverages Variational Autoencoders (VAEs) for feature extraction and Differential Evolution (DE) for optimizing energy management parameters. data was gathered from various IoT devices, including energy usage patterns, occupancy data, and environmental conditions. The results show a notable 40% reduction in energy consumption, leading to annual cost savings of up to $300 per household. Moreover, user satisfaction increased by 25%, with participants reporting heightened awareness and engagement in energy conservation. The study highlights how the proposed framework efficiently identifies common usage patterns and optimizes energy distribution while preserving user comfort. These findings reinforce the potential of AI-driven analytics in improving energy efficiency in smart homes, demonstrating that advanced algorithms not only support energy conservation but also promote active user participation in sustainability efforts. © 2025 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Evolving Effective Drug Therapies with Multi-objective Genetic Algorithm 16th

Evolving Effective Drug Therapies with Multi-objective Genet...

引用

16th International Conference on Genetic and Evolutionary Computing, ICGEC 2024

作者： Zhang, Tiancong Weng, Shaowei Chu, Shu-Chuan Nguyen, Trong-The Dao, Thi-Kien School of Computing and Information Science Fuzhou Institute of Technology Fuzhou350506 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qing-dao266590 China University of Information Technology Ho Chi Minh City700000 Viet Nam

ISBN: (纸本)9789819615346

The development of effective drug therapies is a complex and multifaceted problem involving various biological, chemical, and computational challenges. Traditional drug development methods are often time-consuming and costly, necessitating innovative approaches. Multi-objective genetic algorithms (MOGAs) have emerged as a powerful tool for optimizing drug design by simultaneously considering multiple conflicting objectives, such as efficacy, safety, and cost. This paper reviews the application of MOGAs in drug discovery, highlighting their principles, advantages, and case studies, and discussing future directions in the field. Enhancing MOGAs in drug discovery are also outlined, emphasizing the integration with machine learning, advancements in computational infrastructure, and the potential for personalized medicine. The paper concludes by affirming the significant promise of MOGAs in accelerating the development of safe and effective drug therapies, thereby addressing critical needs in modern pharmacology. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Analysis of Schema Formation in Genetic Algorithms: A Review 16th

Analysis of Schema Formation in Genetic Algorithms: A Review

引用

16th International Conference on Genetic and Evolutionary Computing, ICGEC 2024

作者： Zhang, Tiancong Chu, Shu-Chuan Weng, Shaowei Dao, Thi-Kien Nguyen, Trong-The School of Computing and Information Science Fuzhou Institute of Technology Fuzhou350506 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qing-Dao266590 China University of Information Technology Ho Chi Minh City700000 Viet Nam

ISBN: (纸本)9789819615346

Genetic algorithms (GAs) are a powerful class of optimization techniques inspired by the principles of natural selection and genetics. One of the theoretical cornerstones of GAs is schema theory, which provides a framework for understanding how building blocks of solutions, known as schemas, are propagated and combined through generations. This review paper aims to provide a comprehensive theoretical analysis of schema formation in genetic algorithms. It delves into the foundational principles of schema theory, including the schema theorem and its implications for the efficiency and behavior of GAs. The paper also explores advanced topics such as schema disruption mechanisms, the impact of multimodal and epistatic fitness landscapes, and the integration of schema theory with hybrid approaches. Additionally, practical implications and real-world applications of schema theory are discussed through case studies and best practices. By elucidating the mechanisms of schema formation and their influence on genetic algorithm performance, this review seeks to offer valuable insights and directions for future research. Ultimately, this theoretical exploration aims to bridge the gap between abstract concepts and practical application, contributing to the advancement of genetic algorithms as robust optimization tools. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Should Audio Front-Ends be Adaptive? Comparing Learnable and Adaptive Front-Ends

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 998-1010页

作者： Qiquan Zhang Buddhi Wickramasinghe Eliathamby Ambikairajah Vidhyasaharan Sethu Haizhou Li School of Electrical Engineering and Telecommunications The University of New South Wales Sydney NSW Australia School of Electrical and Computer Engineering Purdue University West Lafayette IN USA School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore

Hand-crafted features, such as Mel-filterbanks, have traditionally been the choice for many audio processing applications. Recently, there has been a growing interest in learnable front-ends that extract representations directly from the raw audio waveform. However, both hand-crafted filterbanks and current learnable front-ends lead to fixed computation graphs at inference time, failing to dynamically adapt to varying acoustic environments, a key feature of human auditory systems. To this end, we explore the question of whether audio front-ends should be adaptive by comparing the Ada-FE front-end (a recently developed adaptive front-end that employs a neural adaptive feedback controller to dynamically adjust the Q-factors of its spectral decomposition filters) to established learnable front-ends. Specifically, we systematically investigate learnable front-ends and Ada-FE across two commonly used back-end backbones and a wide range of audio benchmarks including speech, sound event, and music. The comprehensive results show that our Ada-FE outperforms advanced learnable front-ends, and more importantly, it exhibits impressive stability or robustness on test samples over various training epochs.

关键词： Gabor filters Filters Band-pass filters Training Feature extraction Power harmonic filters Speech recognition Adaptive filters Adaptive control Acoustics

来源：评论

学校读者我要写书评

暂无评论

Joint Multi-Scale Contextual and Noise Suppression for Group Emotion Recognition

Joint Multi-Scale Contextual and Noise Suppression for Group...

引用

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

作者： Guo, Wangdong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Group Emotion Recognition (GER) seeks to identify emotional states within multi-person groups. The complexity of the environment and the reliance on a single group emotion label often result in noisy individuals with inconsistent emotional expressions, hampering accurate emotion classification. Mainstream GER networks attempt to downweight noisy individuals, but when their numbers are high and over-relying on a single group label, the negative impact of noise on individuals remains significant, further complicating classification and diminishing accuracy. To address these limitations, we propose the Multi-Scale Contextual and Noise Suppression Model (MCon-NSM), a novel framework that enhances GER by capturing fine-grained interaction contexts and collaboratively suppressing noise at both the individual and group label levels. Extensive experiments on the GAF series datasets demonstrate that our method achieves results comparable to state-of-the-art techniques, validating its effectiveness in mitigating noise in GER. © 2025 IEEE.

关键词： Emotion analysis Group emotion recognition Multi-Scale context learning Noise suppression

来源：评论

学校读者我要写书评

暂无评论

Class-wise Adaptive Logits Distillation with Meta-Learning

Class-wise Adaptive Logits Distillation with Meta-Learning

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiao Huang Wu Chen Wei Zhou College of Computer and Information Science College of Software Southwest University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Knowledge distillation has become a crucial technique for transferring intricate knowledge from a teacher model to a smaller student model. While logit-based knowledge distillation has shown promise, existing methods often overlook the efficient distillation of logits. In this paper, we introduce a novel approach called Class-wise Adaptive Logits Distillation (CALD) based on meta-learning. Our method leverages a meta-network to generate class-adaptive weights, delivering both explicit and implicit knowledge adaptively. By training the meta-network to assign higher weights to specific classes crucial for the student model’s learning from the teacher model, our approach enhances the knowledge transfer process. Experimental results on CIFAR-100 and ImageNet datasets demonstrate that CALD surpasses state-of-the-art knowledge distillation methods, achieving enhanced accuracy and efficiency in transferring knowledge from teacher to student models.

关键词： Metalearning Training Adaptation models Accuracy Signal processing Acoustics Speech processing Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

A Novel and Efficient Multi-scale Spatio-Temporal Residual Network for Multi-class Intrusion Detection 6th

A Novel and Efficient Multi-scale Spatio-Temporal Residual ...

引用

6th International Conference on Machine Learning for Cyber Security, ML4CS 2024

作者： Li, Nan Gao, Zhaojian Ye, Jiabin Tang, Wei Che, Xun Chen, Yadang Nanjing Big Data Group Co. Ltd. Nanjing210003 China School of Computer Science and Engineering Southeast University Nanjing210096 China Nanjing Zhixun Interconnection Technology Co. Nanjing211100 China Hangzhou SecLead Information Technology Co. Ltd. Hangzhou310056 China Jiangsu Ruizhihe Information Technology Co. Wuxi214434 China School of Computer Science and Cyberspace Security Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9789819645657

With the development of network devices, the network traffic presents high-dimensional, enormous as well as complex characteristics, and the network threats and attacks continue to intensify. Existing network intrusion detection models tend to disregard the extraction and learning of the temporal features of data, which will greatly affect the accuracy of network intrusion detection models. To address the shortcomings of the single structure and the inability to comprehensively learn features, we propose a novel Transformer-based network intrusion detection method, which integrates the degree of importance of traffic features and the fact that intrusion detection data has temporal and spatial characteristics. Specifically, firstly, we adopt the Transformer to perform feature extraction and construct global correlations on the input data, after that, we utilize the improved Inception to extract multi-scale features and weight the spatial features at different scales using self-attention module, in addition to that, bigRU is employed to enhance the temporal features. Finally, the proposed model is validated on the publicly available CIC-IDS-2017 and CIC-DDoS-2019 datasets, which verifies that the proposed method outperforms the existing state-of-the-art models in terms of performance by four evaluation metrics, and also shows significant performance improvement in binary as well as multi-class classification tasks compared to other state-of-the-art methods, which proves the efficiency and effectiveness of our method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

First Token Probability Guided RAG for Telecom Question Answering

arXiv

引用

arXiv 2025年

作者： Chen, Tingwei Chen, Jiayi Zhao, Zijian Chen, Haolong Zhang, Liang Zhu, Guangxu Shenzhen Research Institute of Big Data Shenzhen China Shenzhen China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

Large Language Models (LLMs) have garnered significant attention for their impressive general-purpose capabilities. For applications requiring intricate domain knowledge, Retrieval-Augmented Generation (RAG) has shown a distinct advantage in incorporating domain-specific information into LLMs. However, existing RAG research has not fully addressed the challenges of Multiple Choice Question Answering (MCQA) in telecommunications, particularly in terms of retrieval quality and mitigating hallucinations. To tackle these challenges, we propose a novel first token probability guided RAG framework. This framework leverages confidence scores to optimize key hyperparameters, such as chunk number and chunk window size, while dynamically adjusting the context. Our method starts by retrieving the most relevant chunks and generates a single token as the potential answer. The probabilities of all options are then normalized to serve as confidence scores, which guide the dynamic adjustment of the context. By iteratively optimizing the hyperparameters based on these confidence scores, we can continuously improve RAG performance. We conducted experiments to validate the effectiveness of our framework, demonstrating its potential to enhance accuracy in domain-specific MCQA tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Efficient Modeling Attack on Multiplexer PUFs via Kronecker Matrix Multiplication

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Hongfei Wan, Caixue Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology 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 Wuhan430074 China

The Physical Unclonable Function (PUF) is valued for its lightweight nature and unique functionality, making it a common choice for securing hardware products requiring authentication and key generation mechanisms. In response to the susceptibility of individual PUFs to modeling attacks, advanced PUF variants have been developed to improve security measures. One notable type in this regard is the multiplexer-based composition of arbiter PUFs, known as MPUF, which aims to meet high reliability and security standards simultaneously. Current research on attacking MPUF encounters challenges such as substantial demands for training CRPs and low success rates. In this work, we propose a novel numerical modeling attack strategy for MPUFs. Using Kronecker products from mathematical perspective, this method precisely describe the MPUF model without using complex network architectures, boosting attack accuracy and overall efficiency. Experiment comparison with state-of-the-art works demonstrates that our method achieves better performance in terms of attack accuracy, robustness, and efficiency. Our method is able to successfully attack a (512, 8)-MPUF in 32.71 minutes with 97.14% accuracy, outperforming all existing attack methods on MPUFs. More, we validate our method through experiments with hardware implementations on FPGAs. The advantages of our method also include the adaptability to be employed to attack other MPUF variations like cMPUF and rMPUF, and the capability to be integrated with an existing attack method for launching efficient attack on MPUFs leveraging reliability information. © 2025 IEEE.

关键词： modeling attack multiplexer-based PUF Physical unclonable function

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：