检索结果-内蒙古大学图书馆

4th International Conference on Electrical, Communication and computer Engineering, ICECCE 2023

作者： Girther, T. Krishnan, Yashwanth A. Ceralaathan, G. Sailesh, Sai S. Raj, Rakshith V.S. Rajalakshmi, V. Artificial Intelligence and Data Science Sri Venkateswara College of Engineering Sriperumbudur India Computer Science and Engineering Sri Venkateswara College of Engineering Sriperumbudur India

ISBN: (纸本)9798350369694

The speaker authentication is important for many domains such as safe keying systems, voice aids, or even criminal investigations and others. The shortcomings of conventional approaches for speaker extraction derive from subjectively determined parameters and empirical models employed. This paper responds to these constraints by constructing the proposed deep learning-speaker recognition system using CNN model. A dataset of speech recordings in 16 KHz sample rate PCM format will be used for training that system. To make the system more robust, we will mimic real-life scenarios by adding noise backgrounds. This study intends to design a deep learning model able to identify various voice features and discriminate voices from noise for speaker recognition. By tuning the CNN model, it will be possible to identify specific traits in each speaker’s voice and differentiate among individuals using their unique voices. The emphasis would be placed on building a practical lightweight model suitable for mobile based implementations in real-time speaker ID scenarios. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Federated Model Heterogeneous Matryoshka Representation Learning 38

Federated Model Heterogeneous Matryoshka Representation Lear...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yi, Liping Yu, Han Ren, Chao Wang, Gang Liu, Xiaoguang Li, Xiaoxiao College of Computer Science TMCC SysNet DISSec GTIISC Nankai University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHeteroFL methods rely on training loss to transfer knowledge between the client model and the server model, resulting in limited knowledge exchange. To address this limitation, we propose the Federated model heterogeneous Matryoshka Representation Learning (FedMRL) approach for supervised learning tasks. It adds an auxiliary small homogeneous model shared by clients with heterogeneous local models. (1) The generalized and personalized representations extracted by the two models' feature extractors are fused by a personalized lightweight representation projector. This step enables representation fusion to adapt to local data distribution. (2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header. This step facilitates multi-perspective representation learning and improves model learning capability. Theoretical analysis shows that FedMRL achieves a O(1/T) non-convex convergence rate. Extensive experiments on benchmark datasets demonstrate its superior model accuracy with low communication and computational costs compared to seven state-of-the-art baselines. It achieves up to 8.48% and 24.94% accuracy improvement compared with the state-of-the-art and the best same-category baseline, respectively. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CouRGe: Counterfactual Reviews Generator for Sentiment Analysis 30th

CouRGe: Counterfactual Reviews Generator for Sentiment Anal...

引用

30th Irish Conference on Artificial Intelligence and Cognitive science, AICS 2022

作者： Carraro, Diego Brown, Kenneth N. Insight Centre for Data Analytics School of Computer Science and IT University College Cork Cork Ireland

ISBN: (纸本)9783031264375

Past literature in Natural Language Processing (NLP) has demonstrated that counterfactual data points are useful, for example, for increasing model generalisation, enhancing model interpretability, and as a data augmentation approach. However, obtaining counterfactual examples often requires human annotation effort, which is an expensive and highly skilled process. For these reasons, solutions that resort to transformer-based language models have been recently proposed to generate counterfactuals automatically, but such solutions show limitations. In this paper, we present CouRGe, a language model that, given a movie review (i.e. a seed review) and its sentiment label, generates a counterfactual review that is close (similar) to the seed review but of the opposite sentiment. CouRGe is trained by supervised fine-tuning of GPT-2 on a task-specific dataset of paired movie reviews, and its generation is prompt-based. The model does not require any modification to the network’s architecture or the design of a specific new task for fine-tuning. Experiments show that CouRGe’s generation is effective at flipping the seed sentiment and produces counterfactuals reasonably close to the seed review. This proves once again the great flexibility of language models towards downstream tasks as hard as counterfactual reasoning and opens up the use of CouRGe’s generated counterfactuals for the applications mentioned above. © 2023, The Author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Elevating Cystic Fibrosis Detection in Lungs using HRCT Images with a Cutting-Edge CNN-Based Approach 2

Elevating Cystic Fibrosis Detection in Lungs using HRCT Imag...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Ganjam, Amrutha Sriya Reddy C, Kishor Kumar Radhika, D. Ganjam, Karthik Singh.t, Monika Akuthota, Keerthi Sai Stanley College of Engineering and Technology for Women abids Department of Computer Science Hyderabad India University of Edinburgh Department School of Informatics MSc Data Science Edinburgh United Kingdom Stanley College of Engineering and Technology for Women Deptartment. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331519056

The creation of an algorithm for recognizing pathological abnormalities in cystic fibrosis is investigated in this paper using the CNN model with a modified psp-net. Currently, Decision Trees, Random Forests, PSP Nets, and Neural Networks are utilized in the diagnosis of cystic fibrosis. Since convolutional neural networks (CNNs) can process complicated picture data rapidly and efficiently, the goal of this study is to use CNNs for the detection of anomalies associated with cystic fibrosis. The method groups distinct annotated images into a simple and efficient structure, runs the set of images through a multiscale CNN procedure, and precisely locates the lung region affected by cystic fibrosis. The result of this paper demonstrated that differences in the training dataset can impact performance, but annotating CT images and categorizing them in terms of similar pathologies can improve the accuracy of the model. The proposed CNN model achieved an Accuracy of 84 %, Precision of 74%, Recall of 79%, F1-Score of 72%, error rate of 16% Which is better when compared with existing approaches. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Earthquake Prediction Through Machine Learning Approach 4

Earthquake Prediction Through Machine Learning Approach

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Shrote, Pratik Dasarwar, Priya Dongre, Snehlata Khobragade, Prashant Intern Center of Excellence Data Science Gh Raisoni College of Engineering Nagpur India Nagpur Campus Pune India Gh Raisoni College of Engineering Dept. of Computer Science and Engineering Nagpur India H Raisoni College of Engineering Dept. of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350387490

The population of earthquake-prone areas is growing, as is the number of people killed and injured by earthquakes. The problem of the increasing number of populated regions that are vulnerable to earthquakes is being addressed by a shortage of experts in earthquake engineering. This implies the requirement for automated intelligence-monitored mitigation and warning systems. Predicting earthquakes is still a major problem for disaster management around the globe. The objective of this work is to build a machine learning (ML) approach that uses geographic coordinates (latitude, longitude) and elevation (height) as inputs to forecast earthquake magnitude. The estimated magnitude is used to classify the seismic risk level for a given site into high, low, or no risk categories using Richter's scale. The study offers a thorough analysis of the methodology, covering feature engineering, data collecting, preprocessing, and model construction. A variety of machine learning methods are investigated, and relevant measures are used to assess their effectiveness. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Analysis Model of Learners’ Online Learning Status Based on Deep Neural Network and Multi-Dimensional Information Fusion

引用

computer Modeling in Engineering & sciences 2023年第6期135卷 2349-2371页

作者： Mingyong Li Lirong Tang Longfei Ma Honggang Zhao Jinyu Hu Yan Wei College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application Chongqing401331China

The learning status of learners directly affects the quality of *** with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile ***,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information ***,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,*** integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is *** to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple ***,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.

关键词： Deep learning fatigue detection facial expression recognition sentiment analysis information fusion

来源：评论

学校读者我要写书评

暂无评论

Multi‐task framework of precipitation nowcasting

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1350-1363页

作者： Zheng Zhang Chuyao Luo Baoquan Zhang Hao Jiang Bowen Zhang Department of Computer Science Shenzhen Key Laboratory of Internet Information CollaborationHarbin Institute of TechnologyShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina

Precipitation forecasting plays an important role in disaster warning,agricultural production,and other *** solve this issue,some deep learning methods are proposed to forecast future radar echo images and convert them into rainfall *** spatiotemporal sequence prediction methods are usually based on a ConvRNN structure that combines a Convolutional Neural Network and Recurrent Neural ***,these existing methods ignore the image change prediction,which causes the coherence of the predicted image has ***,these approaches mainly focus on complicating model structure to exploit more historical spatiotemporal ***,they ignore introducing other valuable information to improve *** tackle these two issues,we propose GCMT‐ConvRNN,a multi‐ask framework of *** for precipitation nowcasting as the main task,it combines the motion field estimation and sub‐regression as auxiliary *** this framework,the motion field estimation task can provide motion information,and the sub‐regression task offers future ***,to reduce the negative transfer between the auxiliary tasks and the main task,we propose a new loss function based on the correlation of gradients in different *** experiments show that all models applied in our framework achieve stable and effective improvement.

关键词： deep neural networks motion estimation

来源：评论

学校读者我要写书评

暂无评论

Orchestrating Plasticity and Stability: A Continual Knowledge Graph Embedding Framework with Bio-Inspired Dual-Mask Mechanism 16

Orchestrating Plasticity and Stability: A Continual Knowledg...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Song, Ailin Chen, Yuhong Wang, Yusong Zhong, Shuai Xu, Mingkun Guangdong Institute of Intelligence Science and Technology Hengqin Zhuhai China College of Computer and Data Science Fuzhou University Fuzhou China Tokyo Institute of Technology Tokyo Japan

Learning in biological systems involves the intricate modeling of diverse entities and their interrelations, leading to the evolution of logical knowledge networks with accumulating experience. Analogously, knowledge graphs serve as semantic representations of entity relationships, playing a vital role in natural language processing and graph representation learning. However, contemporary knowledge graph embedding models often neglect real-world event updates, while existing continual knowledge graph research predominantly relies on conventional learning methods that inadequately leverage graph structure, thereby compromising their continual learning capabilities. This study introduces a novel Continual mask Knowledge Graph Embedding framework (CMKGE), designed to address these limitations. CMKGE integrates semantic attributes, network structure, and continual learning mechanisms to capture the dynamic evolution of knowledge. Inspired by biological signal propagation and Dale’s principle, we introduce a dual-mask mechanism for neuronal inhibition and activation. This mechanism automatically filters critical old knowledge, enhancing model plasticity and stability. Through comprehensive evaluations on four datasets, we demonstrate CMKGE’s superiority over state-of-the-art continual embedding models. © 2024 A. Song1, Y. Chen1, Y. Wang, S. Zhong∗ & M. Xu∗.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Genetic Programming with Multi-Task Feature Selection for Alzheimer's Disease Diagnosis 13

Genetic Programming with Multi-Task Feature Selection for Al...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Tang, Shanshan Chen, Qi Xue, Bing Huang, Min Zhang, Mengjie College of Information Science and Engineering Northeastern University Liaoning Shenyang110819 China Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington New Zealand

ISBN: (纸本)9798350308365

Alzheimer's disease (AD) has been the most common cause of dementia making cognitive score prediction and important feature identification crucial for its diagnosis. Although sparse linear regression has been used for this purpose due to its simplicity, it often selects an excessive number of features to track the disease and assumes a linear relationship between input and output, which might not always hold. To address these limitations, genetic programming-based symbolic regression (GPSR) algorithms have been proposed. GPSR can select the important features by exploring the feature space and learning a regression model without any assumption of model structure. However, the generalization ability of existing GPSR methods still needs to be improved. Considering the multiple related prediction tasks in AD studies, this work proposes a new method called linear scaled GPSR with multi-task feature selection (LSGPMTFS), to promote the prediction performance of each task by knowledge-sharing among multiple tasks. LSGPMTFS has two stages. The first stage learns a specific feature subset for each task. In the second stage, the model for each task is searched on the union of feature subsets selected from the first stage. The experimental results on authentic AD datasets demonstrate that the proposed algorithm can select a small set of important features with better learning and generalization performance compared with other GPSR methods. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Models for Machine-Generated Text Detection Using Transformer-Based Models

Leveraging Deep Learning Models for Machine-Generated Text D...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Suthanthiradevi, P. Revathy, G. Rejini, K. Muthu Lakshmi, V. School of Computing Srm institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering Chennai117 India Amrita college of Engineering and Technology Department of Computer Science Engineering Nagercoil India St. Joseph's College of Engineering Department of Computer Science and Engineering OMR Chennai India

ISBN: (纸本)9798331543617

GPT is a large language model (LLM) derived from natural language processing that can generate a human-like text using machine learning. However, these models raise questions about authenticity and reliability of material, particularly in fields such as journalism, social media, and academia, despite their usefulness for automating text-based tasks. Detecting machine-generated text is thus an important difficulty in ensuring content integrity. This study investigates the use of huge language models as a technique for recognizing machine-generated material. The author proposes a comprehensive detection model by evaluating the language patterns, syntactic structures, and stylistic traits that separate AI-generated literature from human writing. In addition, this research investigate the possibilities of fine-tuning models designed expressly for text identification tasks and evaluate their performance using LLM - Detect AI Generated Text datasets. In digital ecosystems, LLMs are effective at detecting AI-generated text, providing a novel approach for content moderation, academic integrity checks, and synthetic media detection. An increasingly AI-powered future will require a model that can discriminate between human and machine-generated writing in real-time. According to experimental findings, the CNN architecture's design combined with the use of DistilBERT embeddings allows for the effective and efficient classification of AI generated text data, achieving an exceptional 98% accuracy rate. © 2024 IEEE.

关键词： Adversarial machine learning

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：