检索结果-内蒙古大学图书馆

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Kodipalli, Ashwini Prajwal, N. Vignesh, Vamshi B. Rao, Trupthi Gargi, N. Devamane, Shridhar B. Global Academy of Technology Dept. Artificial Intelligence & Data Science Karnataka Bangalore India School of Computing Amrita Vishwavidyapeetam Department of Computer Science Mysuru India

ISBN: (纸本)9798331518943

Through early intervention and individualized treatment plans, timely disease detection and personalized healthcare can advance patient results and reduce healthcare costs. With the aim to categorize medical conditions, we present a dataset in this study that includes blood sample parameters like haemoglobin, cholesterol, and glucose. To analyse these parameters, we created a three-layered artificial neural network (ANN). Achieving an accuracy of 93.42% on the test set, the ANN was trained and validated on the dataset. With the aim of reducing overfitting and enhance model generalization, dropout layers were added. Furthermore, a comparative analysis with various optimizers was carried out. The results highlight the ANN's potential as a means for timly diagnosis, personalized healthcare, improving patient outcomes and lowering long-term healthcare costs. They also demonstrate the ANN's ability to accurately classify diseases. © 2024 IEEE.

关键词： Anaemia ANN Artificial Neural Networks Blood Test Classification Deep learning

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

Design and Optimization of Loss Functions in Fine-grained Sentiment and Emotion Analysis 5

Design and Optimization of Loss Functions in Fine-grained Se...

引用

5th International Conference on Natural Language Processing, ICNLP 2023

作者： Shiren, Ye Li, Ding Rinku, Ali Md Changzhou University School of Computer Science and Artificial Intelligence Aliyun School of Big Data School of Software Changzhou China

ISBN: (纸本)9798350302219

The unbalanced distribution of category labels and the correlation between these labels tend to cause over-learning issues in deep learning models. In fine-grained sentiment analysis datasets, the correlation between category labels and the heterogeneity of tag distribution are prominent. In the deep learning model, we use the adjusted circle-loss to introduce margin and gradient attenuation in the loss function to handle the challenges caused by unbalanced label distribution and non-independence between labels. This method can be well combined with pre-trained models and adapt to various learning models and algorithms. Compared with the state-of-the-art typical models, our loss function mechanism achieves significant improvement using SemEval18 and GoeEmotions by measure of Jaccard coefficient, micro-F1, and macro-F1. It implies that our solution could work efficiently for sentiment analysis and sentiment analysis tasks. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Membership Inference Attacks Against Sequential Recommender Systems 23

Membership Inference Attacks Against Sequential Recommender ...

引用

2023 World Wide Web Conference, WWW 2023

作者： Zhu, Zhihao Wu, Chenwang Fan, Rui Lian, Defu Chen, Enhong School of Data Science University of Science and Technology of China Hefei China School of Computer Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9781450394161

Recent studies have demonstrated the vulnerability of recommender systems to membership inference attacks, which determine whether a user's historical data was utilized for model training, posing serious privacy leakage issues. Existing works assumed that member and non-member users follow different recommendation modes, and then infer membership based on the difference vector between the user's historical behaviors and the recommendation list. The previous frameworks are invalid against inductive recommendations, such as sequential recommendations, since the disparities of difference vectors constructed by the recommendations between members and non-members become imperceptible. This motivates us to dig deeper into the target model. In addition, most MIA frameworks assume that they can obtain some in-distribution data from the same distribution of the target data, which is hard to gain in recommender system. To address these difficulties, we propose a Membership Inference Attack framework against sequential recommenders based on Model Extraction(ME-MIA). Specifically, we train a surrogate model to simulate the target model based on two universal loss functions. For a given behavior sequence, the loss functions ensure the recommended items and corresponding rank of the surrogate model are consistent with the target model's recommendation. Due to the special training mode of the surrogate model, it is hard to judge which user is its member(non-member). Therefore, we establish a shadow model and use shadow model's members(non-members) to train the attack model later. Next, we build a user feature generator to construct representative feature vectors from the shadow(surrogate) model. The crafting feature vectors are finally input into the attack model to identify users' membership. Furthermore, to tackle the high cost of obtaining in-distribution data, we develop two variants of ME-MIA, realizing data-efficient and even data-free MIA by fabricating authentic in-distrib

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model 31

Enhancing Rumor Detection Methods with Propagation Structure...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cui, Chaoqun Li, Siyuan Ma, Kunkun Jia, Caiyan School of Computer Science and Technology & Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9798891761964

Pretrained Language Models (PLMs) have excelled in various Natural Language Processing tasks, benefiting from large-scale pretraining and self-attention mechanism's ability to capture long-range dependencies. However, their performance on social media application tasks like rumor detection remains suboptimal. We attribute this to mismatches between pretraining corpora and social texts, inadequate handling of unique social symbols, and pretraining tasks ill-suited for modeling user engagements implicit in propagation structures. To address these issues, we propose a continue pretraining strategy called Post Engagement Prediction (PEP) to infuse information from propagation structures into PLMs. PEP makes models to predict root, branch, and parent relations between posts, capturing interactions of stance and sentiment crucial for rumor detection. We also curate and release large-scale Twitter corpus: TwitterCorpus (269GB text), and two unlabeled claim conversation datasets with propagation structures (UTwitter and UWeibo). Utilizing these resources and PEP strategy, we train a Twitter-tailored PLM called SoLM. Extensive experiments demonstrate PEP significantly boosts rumor detection performance across universal and social media PLMs, even in few-shot scenarios. On benchmark datasets, PEP enhances baseline models by 1.0-3.7% accuracy, even enabling it to outperform current state-of-the-art methods on multiple datasets. SoLM alone, without high-level modules, also achieves competitive results, highlighting the strategy's effectiveness in learning discriminative post interaction features. © 2025 Association for Computational Linguistics.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Differentiable Optimized Product Quantization and Beyond 23

Differentiable Optimized Product Quantization and Beyond

引用

2023 World Wide Web Conference, WWW 2023

作者： Lu, Zepu Lian, Defu Zhang, Jin Zhang, Zaixi Feng, Chao Wang, Hao Chen, Enhong School of Computer Science University of Science and Technology of China Hefei China School of Data Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9781450394161

Vector quantization techniques, such as Product Quantization (PQ), play a vital role in approximate nearest neighbor search (ANNs) and maximum inner product search (MIPS) owing to their remarkable search and storage efficiency. However, the indexes in vector quantization cannot be trained together with the inference models since data indexing is not differentiable. To this end, differentiable vector quantization approaches, such as DiffPQ and DeepPQ, have been recently proposed, but existing methods have two drawbacks. First, they do not impose any constraints on codebooks, such that the resultant codebooks lack diversity, leading to limited retrieval performance. Second, since data indexing resorts to operator, differentiability is usually achieved by either relaxation or Straight-Through Estimation (STE), which leads to biased gradient and slow convergence. To address these problems, we propose a Differentiable Optimized Product Quantization method (DOPQ) and beyond in this paper. Particularly, each data is projected into multiple orthogonal spaces, to generate multiple views of data. Thus, each codebook is learned with one view of data, guaranteeing the diversity of codebooks. Moreover, instead of simple differentiable relaxation, DOPQ optimizes the loss based on direct loss minimization, significantly reducing the gradient bias problem. Finally, DOPQ is evaluated with seven datasets of both recommendation and image search tasks. Extensive experimental results show that DOPQ outperforms state-of-the-art baselines by a large margin. © 2023 ACM.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Threshold Huffman-Based Covert Timing Channel Detection

引用

International Journal of Network Security 2025年第1期27卷 61-71页

作者： Lin, Yuwei Chen, Yonghong Zhuang, Xiaolong Huang, Xuwen School of Computer Science and Technology Huaqiao University Fujian Xiamen361000 China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Fujian Xiamen361000 China

Network covert timing channels in computer networks evade effective detection by traditional security mechanisms such as firewalls, posing a significant threat to network security. However, most existing methods struggle to detect such channels when the window size is small. Additionally, the emergence of the new ϵ-κlibur channel has resulted in a decline in performance for detection methods such as GAS, SnapCatch, and DNN when detecting this particular channel. In this paper, we investigate a Huffman tree-based approach for detecting anomalous nodes in traffic and achieving the classification of channels through the design of weight intervals. Our method achieves an average detection rate of over 95% for each channel. Additionally, compared to GAS, SnapCatch, and DNN, our method improves the detection rates for the ϵ-κlibur channel by 11.75%, 8.46%, and 4.81%, respectively. The experimental results demonstrate that our proposed approach successfully detects ϵ-κlibur and achieves detection in a small window. © (2025), (Femto Technique Co., Ltd.). All rights reserved.

关键词： computer system firewalls

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visualizing Program Behavior: A Study of Enhanced Program Diagrams Using LLM 54

Visualizing Program Behavior: A Study of Enhanced Program Di...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Li, Ying Yang, Runze Gui, ShiJie Shi, Peng Huang, Xuefei Yang, Da Zhang, Xiaozhou Gai, Yiming School of Computer Science and Engineering Beihang University Beijing China International Innovation Institute Beihang University Key Laboratory of Data Science and Intelligent Computing Hangzhou China

ISBN: (纸本)9798350351507

This paper aims to address the difficulties faced by novice programmers in grasping code structure and execution flow, improving programming thinking, and pinpointing code errors with accuracy. It proposes providing students with program behavior diagrams based on large language models (LLMs) and visualization techniques to achieve personalized guidance. Specifically, these program behavior diagrams include programming thinking visualization diagrams and code vulnerability visualization diagrams. A programming thinking visualization diagram employs static code analysis to gather code structure information, combined with the structured chain-of-thought method to collectively optimize the LLM. This enables the LLM to explain each interpretable part of the code from top to bottom, detailing the programming concepts, and displaying them on a modularized code structure diagram. The code vulnerability visualization diagram primarily utilizes the fine-tuned LLM, optimizing it based on program analysis and clustering analysis methods to accurately identify vulnerabilities in student code and display them on a code flow diagram. Its feature is to visually display to students the error location, error information, and the impact of errors on program flow, rather than providing the programming answers. Lastly, through experiments and statistical analysis of actual teaching data, this paper serves a demonstration that the enhanced models used in the visualization diagram generation process have a noticeable effect on mainstream LLMs, and that visualization diagrams hold significant value for students at different stages of learning. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

MART(Splitting-Merging Assisted Reliable)Independent Component Analysis for Extracting Accurate Brain Functional Networks

引用

Neuroscience Bulletin 2024年第7期40卷 905-920页

作者： Xingyu He Vince D.Calhoun Yuhui Du School of Computer and Information Technology Shanxi UniversityTaiyuan 030006China Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Georgia State UniversityGeorgia Institute of TechnologyEmory UniversityAtlanta 30303USA

Functional networks(FNs)hold significant promise in understanding brain *** component analysis(ICA)has been applied in estimating FNs from functional magnetic resonance imaging(fMRI).However,determining an optimal model order for ICA remains challenging,leading to criticism about the reliability of FN ***,we propose a SMART(splitting-merging assisted reliable)ICA method that automatically extracts reliable FNs by clustering independent components(ICs)obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model *** extend SMART ICA to multi-subject fMRI analysis,validating its effectiveness using simulated and real fMRI *** on simulated data,the method accurately estimates both group-common and group-unique components and demonstrates robustness to *** two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects,the resulting reliable group-level FNs are greatly similar between the two cohorts,and interestingly the subject-specific FNs show progressive changes while age ***,both small-scale and large-scale brain FN templates are provided as benchmarks for future *** together,SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data,while also providing linkages between different FNs.

关键词： Independent component analysis Functional magnetic resonance imaging-Brain functional networks Clustering Multi-model-order

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：