检索结果-内蒙古大学图书馆

IEEE International Conference on Big data

作者： Joshua DeOliveira Walter Gerych Aruzhan Koshkarova Elke Rundensteiner Emmanuel Agu Data Science Program Worcester Polytechnic Institute Worcester MA Department of Computer Science Worcester Polytechnic Institute Worcester MA

ISBN: (纸本)9781665480468

Human activity recognition (HAR) is the process of using mobile sensor data to determine the physical activities performed by individuals. HAR is the backbone of many mobile healthcare applications, such as passive health monitoring systems, early diagnosing systems, and fall detection systems. Effective HAR models rely on deep learning architectures and big data in order to accurately classify activities. Unfortunately, HAR datasets are expensive to collect, are often mislabeled, and have large class imbalances. State-of-the-art approaches to address these challenges utilize Generative Adversarial Networks (GANs) for generating additional synthetic data along with their labels. Problematically, these HAR GANs only synthesize continuous features — features that are represented by real numbers — recorded from gyroscopes, accelerometers, and other sensors that produce continuous data. This is limiting since mobile sensor data commonly has discrete features that provide additional context such as device location and the time-of-day, which have been shown to substantially improve HAR classification. Hence, we studied Conditional Tabular Generative Adversarial Networks (CTGANs) for data generation to synthesize mobile sensor data containing both continuous and discrete features, a task never been done by state-of-the-art approaches. We show HAR-CTGANs generate data with greater realism resulting in allowing better downstream performance in HAR models, and when state-of-the-art models were modified with HAR-CTGAN characteristics, downstream performance also improves.

关键词： Training Medical services Big data Generative adversarial networks data models Stability analysis Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure 10

Who Responded to Whom: The Joint Effects of Latent Topics an...

引用

10th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2024

作者： Ji, Lu Chen, Lei Li, Jing Wei, Zhongyu Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China School of Data Science Fudan University China Department of Computing The Hong Kong Polytechnic University Hong Kong Research Institute of Intelligent and Complex Systems Fudan University China

ISBN: (纸本)9798891761551

Vast amount of online conversations are produced on a daily basis, resulting in a pressing need to automatic conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a neural model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts. © 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

Architecture of Modern E-Learning Management System

Architecture of Modern E-Learning Management System

引用

2023 IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2023

作者： Scerbakov, Nikolai Schukin, Alexander Rezedinova, Eugenia Graz University of Technology Institute of Interactive Systems and Data Science Graz Austria Peter the Great St. Petersburg Polytechnic University Institute of Computer Science and Cybersecurity St. Petersburg Russia

ISBN: (纸本)9798350336917

Abstract-In contemporary educational institutions, a robust Learning Management System (LMS) plays an important role within the E-Learning infrastructure. An LMS serves as an organized repository for course materials while also incorporating vital communication features like discussion forums, annotations, and chats. The LMS encompasses tools designed to monitor students' advancement through course materials and assess the knowledge they acquire during their learning journey. Since the LMS is a complex software application, which operates for extended periods of time, it needs a careful consideration of its design in terms of functionality, dependability, and lifecycle management. In this paper, we present the architecture of a modern LMS called WBT-Master. This architectural framework is referred to as CDAT, representing Controller, data, Activity, and Template. The 'Activity' assumes a central role within the application. It processes the incoming data according to its designated purpose, and visualizes the data on the user's screen. The 'Template' element comprises HTML fragments containing placeholders The placeholders are bound to the activity variables. 'Controllers' act as event handlers and load the different activities depending on user actions. 'data Provider' offer a unified data representation on diverse data sources. We also explore the system's data organization principles and its seamless integration with popular cloud services. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

arXiv

引用

arXiv 2024年

作者： Tan, Xue Luan, Hao Luo, Mingyu Sun, Xiaoyan Chen, Ping Dai, Jun School of Computer Science Fudan University Shanghai China Department of Computer Science Worcester Polytechnic Institute MA United States Institute of Big Data Fudan University Shanghai China

Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database, enabling them to produce responses that are more accurate and contextually appropriate. It is worth noting that the knowledge database, being sourced from publicly available channels such as Wikipedia, inevitably introduces a new attack surface. RAG poisoning attack involves injecting malicious texts into the knowledge database, ultimately leading to the generation of the attacker’s target response (also called poisoned response). However, there are currently limited methods available for detecting such poisoning attacks. We aim to bridge the gap in this work by introducing RevPRAG, a flexible and automated detection pipeline that leverages the activations of LLMs for poisoned response detection. Our investigation uncovers distinct patterns in LLMs’ activations when generating poisoned responses versus correct responses. Our results on multiple benchmarks and RAG architectures show our approach can achieve a 98% true positive rate, while maintaining a false positive rate close to 1%. © 2024, CC BY-SA.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach 39

Personalized Federated Collaborative Filtering: A Variationa...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Zhiwei Long, Guodong Zhou, Tianyi Jiang, Jing Zhang, Chengqi Australian Artificial Intelligence Institute Faculty of Engineering and IT University of Technology Sydney Australia Department of Computer Science University of Maryland College Park United States Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)157735897X

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Using Facial Features for Mental Health Screening

Multi-Task Learning Using Facial Features for Mental Health ...

引用

IEEE International Conference on Big data

作者： Ricardo Flores Avantika Shrestha Ml Tlachac Elke A. Rundensteiner Data Science Department Worcester Polytechnic Institute Worcester MA USA Department of Information Systems and Analytics Center for Health and Behavioral Sciences Bryant University Smithfield RI USA Data Science Department Computer Science Department Worcester Polytechnic Institute Worcester MA USA

Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are prevalent mental health conditions with severe physical and social impacts. They are expensive and detection is difficult, requiring substantial time from trained mental professionals. To alleviate this issue, recent studies explore the diagnostic potential of deep learning models trained on modalities extracted from clinical interview videos, conducted by a virtual agent. However, deep learning models are challenging to train because of the long sequences and small number of participants common in the mental health community. To combat these challenges, we leverage multi-task learning, using temporal facial features as input, to screen for MDD and PTSD. The multi-task architecture is based on a bidirectional GRU model with self-attention. We evaluate our multi-task model on temporal facial features extracted from responses to 15 clinical interview questions conducted by a virtual agent. The results suggest that multi-task learning increases the generalization performance compared to single-task learning. For MDD screening, multi-task learning improved the balanced accuracy over single-task learning for 11 of the 15 datasets. In fact, our multi-learning model increased the MDD screening ability by 25 percent to a balanced accuracy of 0.87 in some scenarios. This work provides valuable findings for the future of mental screening applications leveraging temporal facial features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation

Zero-shot LLM-guided Counterfactual Generation: A Case Study...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Bhattacharjee, Amrita Moraffah, Raha Garland, Joshua Liu, Huan Arizona State University School of Computing and Ai TempeAZ United States Worcester Polytechnic Institute Department of Computer Science WorcesterMA United States Arizona State University Global Security Initiative TempeAZ United States

ISBN: (纸本)9798350362480

With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of methods to stress-test these models and provide some degree of interpretability or explainability. While counterfactual examples are useful in this regard, automated generation of counterfactuals is a data and resource intensive process, that may be infeasible in practice, especially for new tasks and data domains. Therefore, in this work we explore the possibility of leveraging large language models (LLMs) for zero-shot counterfactual generation in order to stress-test NLP models. We propose a structured pipeline to facilitate this generation, and we hypothesize that the instruction-following and textual understanding capabilities of recent LLMs can be effectively leveraged for generating high quality counterfactuals in a zero-shot manner, without requiring any training or fine-tuning. Through comprehensive experiments on a variety of propreitary and open-source LLMs, along with various downstream tasks in NLP, we explore the efficacy of LLMs as zero-shot counterfactual generators in evaluating and explaining black-box NLP models. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Vision-based FDM Printing for Fabricating Airtight Soft Actuators

Vision-based FDM Printing for Fabricating Airtight Soft Actu...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Yijia Wu Zilin Dai Haotian Liu Lehong Wang Markus P. Nemitz Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Department of Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Mechanical and Materials Engineering Worcester Polytechnic Institute Worcester MA USA Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

Pneumatic soft robots are typically fabricated by molding, a manual fabrication process that requires skilled labor. Additive manufacturing has the potential to break this limitation and speed up the fabrication process but struggles with consistently producing high-quality prints. We propose a low-cost approach to improve the print quality of desktop fused deposition modeling by adding a webcam to the printer to monitor the printing process and detect and correct defects such as holes or gaps. We demonstrate that our approach improves the air-tightness of printed pneumatic actuators while reducing the need for fine-tuning printing parameters. Our approach presents a new option for robustly fabricating airtight, soft robotic actuators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Emulation to Mathematical: A More General Traffic Obfuscation Approach To Encounter Feature based Mobile App traffic Classification

arXiv

引用

arXiv 2023年

作者： Gao, Lichun Zeng, Mingjie Huang, Zhanhong Computer Science Department Worcester Polytechnic Institute Worcester United States

The usage of the mobile app is unassailable in this digital era. While tons of data are generated daily, user privacy security concerns become an important issue. Nowadays, tons of techniques, such as machine learning and deep learning traffic classifiers, have been applied to analyze users’ app traffic. These techniques allow the monitor to get the fingerprints of using apps while the user traffic is still encrypted, which raises a severe privacy issue. In order to fight against this type of data analysis, people have been researching obfuscation algorithms to confuse feature-based machine learning classifiers with data camouflage by modification on packet length distribution. The existing works achieve this goal by remapping traffic packet length distribution from the source app to the fake camouflage app. However, this solution suffers from its lack of scalability and flexibility in practical application since the method needs to pre-sample the target fake app’s traffic before the use of traffic camouflage. In this paper, we proposed a practical solution by using a mathematical model to calculate the target distribution while maintaining at least 50% accuracy drops on the performance of the AppScanner mobile traffic classifier and roughly 20% overhead created during packet modification. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Hyper-Graph Neural Networks for Context-Aware Human Activity Recognition

Heterogeneous Hyper-Graph Neural Networks for Context-Aware ...

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Wen Ge Guanyi Mou Emmanuel O. Agu Kyumin Lee Computer Science Department Worcester Polytechnic Institute Worcester MA USA

Context-aware Human Activity Recognition (CHAR) is challenging due to the need to recognize the user's current activity from signals that vary significantly with contextual factors such as phone placements and the varied styles with which different users perform the same activity. In this paper, we argue that context-aware activity visit patterns in realistic in-the-wild data can equivocally be considered as a general graph representation learning task. We posit that exploiting underlying graphical patterns in CHAR data can improve CHAR task performance and representation learning. Building on the intuition that certain activities are frequently performed with the phone placed in certain positions, we focus on the context-aware human activity problem of recognizing the tuple. We demonstrate that CHAR data has an underlying graph structure that can be viewed as a heterogenous hypergraph that has multiple types of nodes and hyperedges (an edge connecting more than two nodes). Subsequently, learning representations becomes a graph node representation learning problem. After task transformation, we further propose a novel Heterogeneous HyperGraph Neural Network architecture for Context-aware Human Activity Recognition (HHGNN-CHAR), with three types of heterogeneous nodes (user, phone placement, and activity). Connections between all types of nodes are represented by hyperedges. Rigorous evaluation demonstrated that on an unscripted, in-the-wild CHAR dataset, our proposed framework significantly outperforms state-of-the-art (SOTA) baselines including CHAR models that do not exploit graphs, and GNN variants that do not incorporate heterogeneous nodes or hyperedges with overall improvements 14.04% on Matthews Correlation Coefficient (MCC) and 7.01% on Macro F1 scores.

关键词：

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：