检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Suthanthiradevi, P. Revathy, G. Sathish Kumar, P. Karthikeyan, B. Muthu, Lakshmi.V SRM institute of Science and Technology Data Science and Business Systems School of Computing India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering India Rajalakshmi institute of technology Computer and Communication Engineering India SASTRA Deemed University School of Computing India St. Joseph's Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350372120

With the recent advent of technology, social networks are accessible 24/7 using mobile devices. During covid-19 pandemic the propagation of misinformation are mostly related to the disease, its cures and prevention. With Twitter as the medium this information was spreaded to millions of people who lack domain specific knowledge. This can lead to bloster fear and direct damage to the people. This research focuses on identifying the veracity of the Twitter posts behind pandemic situation. The authors have proposed a Transformer Model using Bat Algorithm for identifying the fake news. This model is trained and evaluated using infodemic metadata. Our experimental results shows by which proposed model accurately detected the fake news and achieved 96.5% of f1-score. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations 41

Imitation Learning from Purified Demonstrations

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ProgMate: An Intelligent Programming Assistant Based on LLM 54

ProgMate: An Intelligent Programming Assistant Based on LLM

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Li, Ying Yang, Runze Zhang, Xiantao Shi, Peng Yang, Da Huang, Xuefei 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 study addresses the challenges faced in personalized tutoring within large-scale programming courses, such as significant ability gaps among students, limited available resources, among others. For these reasons, we proposed an intelligent programming assistant, ProgMate, based on large language models (LLMs). Benefitting from the robust understanding and learning capabilities of LLM, ProgMate not only comprehensively monitors the learning process, but can also surpass human teaching in aspects such as intelligent assignment grading, identification of knowledge gaps, and assessment of learning abilities. ProgMate embodies a new 4-A digital teaching paradigm, characterized by its ability to provide precise guidance with anything, to anyone, anywhere, at any time, with features like 'omnipresence', 'adaptive guidance' and 'customization'. It facilitates the organic integration of collective teaching and individualized guidance, continuous learning, and long-term development, as well as resource efficiency and precision nurturing, offering a viable path and empirical support for the digital transformation of future education. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Early Diagnosis of Schizophrenia in Patients Using Deep Learning Techniques 10

Early Diagnosis of Schizophrenia in Patients Using Deep Lear...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Priyanka, G. Nivaashini, M. Pavithra, S. Srimaha, T.S. Kanishgaa, P.R. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

While Brain, emotion, and behaviours abnormalities are hallmarks of schizophrenia, a complex and long-lasting mental illness. Its symptoms are divided into three categories: positive, negative, and cognitive. Positive symptoms include delusions, disordered thinking, abnormal gait, and hallucinations. Diminished ability to express emotions, alogia, anhedonia, avolition, and social disengagement are detrimental symptoms. Deficiencies in working memory, problems paying attention, and trouble making decisions are examples of cognitive symptoms. Environmental variables, genetic predisposition, and neurochemical imbalances interact intricately in an etiology of schizophrenia. Typically, antipsychotic drugs, psychotherapy, and social support are used in conjunction for treatment. The management of symptoms and enhancement of the general health of persons diagnosed with schizophrenia need early intervention and customized treatment strategies. The CNN, BiLSTM, GRU, and Transformer deep learning models are implemented in this study, and their respective performances are assessed. The transformer and GRU models outperform the other models when hyperparameter adjustment is carried out to increase the models' efficacy. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment 38

DFA-GNN: Forward Learning of Graph Neural Networks by Direct...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Gongpei Wang, Tao Lang, Congyan Jin, Yi Li, Yidong Ling, Haibin Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University United States

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks. © 2024 Neura

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using Focal Network and Resnet

Emotion Recognition Using Focal Network and Resnet

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Meena, T. Balasai, Sigireddy Anandh Duggireddy Kumar, P. Phaneendhra Velagapudi Ramakrishna Siddartha Engineering College Department of Computer Science and Engineering India Velagapudi Ramakrishna Siddartha Engineering College Department of Artificial Intelligence and Data Science India

ISBN: (纸本)9798350382693

Image emotion recognition involves finding the emotions from visual data, usually done through convolutional neural networks (CNN) or deep neural networks (DNN). The existing methodologies are often high complex or time complex and it is not giving the good considerable results and computationally expensive due to high number of parameters. In this paper we try to accomplish a better output by using focal network which stood among other transformers architecture due to the unique property of the dynamic attention Recent studies have shown the efficacy of transformer architectures in various deep learning tasks and challenged the convolution neural networks on various tasks. but, It has a tradeoff between reduced parameter complexity and the need for extensive training data. Drawing inspiration from recent publications, the study adopts a focal network for training, demonstrating its effectiveness in enhancing the model's attention and optimizing emotional feature extraction. The proposed methodology aims to do the process of image emotion recognition by using the advantages of transformers while mitigating the computational problem associated with the deep neural networks. The incorporation of a focal network addresses attention-related challenges, and it contributes to the development of more efficient emotion recognition systems. This research offers insights into the evolving landscape of image emotion recognition methodologies and underscores the potential of transformer architectures in advancing this field. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Deep Learning-Based Model for Detecting Spoofed Faces in Images 2nd

Computer Vision and Deep Learning-Based Model for Detectin...

引用

2nd International Conference on data science and Network Engineering, ICDSNE 2024

作者： Salian, Gayathri P Rao, Manasa K Rashmi, M. Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

ISBN: (纸本)9789819783359

In the modern era of smart applications, video data is critically important in various contexts. In most of these applications, cameras are frequently incorporated to facilitate authentication. As a result, face recognition is the biometric method most frequently employed to authenticate users in these applications. The vulnerability of face recognition systems to spoofing attacks grows in tandem with their increased usage. As a result, robust countermeasures are required. This paper presents an approach to face anti-spoofing through transfer learning and YOLOv8 optimization. Additionally, a custom dataset was constructed using images obtained from web cameras and an existing dataset to assess the proposed work’s real-time effectiveness. The proposed approach also adds a blurriness threshold during image capture to improve performance. With a mean Average Precision (mAP50) of 0.975, the experimental outcomes highlight the model’s effectiveness in detecting face spoofing. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Unified Graph and Hypergraph Neural Network for Next-item Recommendation

Unified Graph and Hypergraph Neural Network for Next-item Re...

引用

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

作者： Zhang, Xinyu Jiang, Qize Zhang, Hanyuan Sun, Weiwei School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China

ISBN: (纸本)9798350368741

The task of next-item recommendation is a crucial component in recommendation systems. The challenge of this task lies in extracting complex interaction information from users' historical interactions with items. While prior research has transformed users' interaction histories into graphs and hypergraphs to mine high-order interactions, the integration of both remains uncharted. Existing methods treat graphs and hypergraphs separately in representation learning, missing out on their shared attributes. Addressing this gap, we introduce a novel unified framework that integrates graphs and hypergraphs into one unified message passing paradigm. Our method employs graph neural networks and hypergraph neural networks to continuously conduct representation learning, achieving end-to-end next item recommendation. Specifically, our framework consists of the following components: 1) a unique method for graph and hypergraph construction from interaction histories, with items as nodes and users as hyperedges;2) a novel message passing framework compatible with both graph and hypergraph neural networks;and 3) an innovative hypergraph neural network aggregation module enhanced with time and position encoders. The test results on multiple public benchmarks verify that our method outperforms current best practices in performance. © 2025 IEEE.

关键词： Graph Neural Network Hypergraph Neural Network Next-item Recommendation User Modeling

来源：评论

学校读者我要写书评

暂无评论

Document-level Clinical Entity and Relation Extraction via Knowledge Base-Guided Generation 23

Document-level Clinical Entity and Relation Extraction via K...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Bhattarai, Kriti Oh, Inez Y. Abrams, Zachary B. Lai, Albert M. Institute for Informatics Data Science & Biostatistics Washington University School of Medicine United States Department of Computer Science Washington University in St. Louis United States

ISBN: (纸本)9798891761308

Generative pre-trained transformer (GPT) models have shown promise in clinical entity and relation extraction tasks because of their precise extraction and contextual understanding capability. In this work, we further leverage the Unified Medical Language System (UMLS) knowledge base to accurately identify medical concepts and improve clinical entity and relation extraction at the document level. Our framework selects UMLS concepts relevant to the text and combines them with prompts to guide language models in extracting entities. Our experiments demonstrate that this initial concept mapping and the inclusion of these mapped concepts in the prompts improves extraction results compared to few-shot extraction tasks on generic language models that do not leverage UMLS. Further, our results show that this approach is more effective than the standard Retrieval Augmented Generation (RAG) technique, where retrieved data is compared with prompt embeddings to generate results. Overall, we find that integrating UMLS concepts with GPT models significantly improves entity and relation identification, outperforming the baseline and RAG models. By combining the precise concept mapping capability of knowledge-based approaches like UMLS with the contextual understanding capability of GPT, our method highlights the potential of these approaches in specialized domains like healthcare.. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient Boosted Decision Tables

引用

IEEE Transactions on Services Computing 2023年第5期16卷 3604-3620页

作者： Zheng, Yifeng Xu, Shuangqing Wang, Songlei Gao, Yansong Hua, Zhongyun Harbin Institute of Technology School of Computer Science and Technology Guangdong Shenzhen518055 China Csiro Data61 SydneyNSW2720 Australia

Vertical federated learning (VFL) has recently emerged as an appealing distributed paradigm empowering multi-party collaboration for training high-quality models over vertically partitioned datasets. Gradient boosting has been popularly adopted in VFL, which builds an ensemble of weak learners (typically decision trees) to achieve promising prediction performance. Recently there have been growing interests in using decision table as an intriguing alternative weak learner in gradient boosting, due to its simpler structure, good interpretability, and promising performance. In the literature, there have been works on privacy-preserving VFL for gradient boosted decision trees, but no prior work has been devoted to the emerging case of decision tables. Training and inference on decision tables are different from that in the case of generic decision trees, not to mention gradient boosting with decision tables in VFL. In light of this, we design, implement, and evaluate Privet, the first system framework enabling privacy-preserving VFL service for gradient boosted decision tables. Privet delicately builds on lightweight cryptography and allows an arbitrary number of participants holding vertically partitioned datasets to securely train gradient boosted decision tables. Extensive experiments over several real-world datasets and synthetic datasets demonstrate that Privet achieves promising performance, with utility comparable to plaintext centralized learning. © 2008-2012 IEEE.

关键词： Decision trees

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：