检索结果-内蒙古大学图书馆

ELXGB: An Efficient and Privacy-Preserving XGBoost for Vertical Federated Learning

IEEE TRANSACTIONS ON SERVICES COMPUTING 2024年第3期17卷 878-892页

作者： Xu, Wei Zhu, Hui Zheng, Yandong Wang, Fengwei Zhao, Jiaqi Liu, Zhe Li, Hui Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 210016 Jiangsu Peoples R China Zhejiang Lab Hangzhou 311100 Zhejiang Peoples R China

With the rapid growth of Internet data volumes, Big Data analysis technologies have gradually permeated all aspects of life. However, the existence of data silos and the promulgation of relevant regulations make it challenging to apply these technologies. In this context, federated learning provides a feasible solution. Especially, XGBoost schemes for vertical federated learning have attracted much attention due to the widespread use of XGBoost. However, these schemes have limitations in terms of security or efficiency. To address these issues, we propose an efficient and privacy-preserving vertical federated learning framework based on the XGBoost algorithm, namely ELXGB, which achieves secure data alignment, XGboost training, and inference services. First, we design two node split algorithms based on homomorphic encryption and differential privacy, which securely and efficiently achieve tree node generation to construct the global model. Then, we utilize attribute obfuscation and direction obfuscation to achieve a secure inference algorithm, which avoids sensitive information leakage and protects the global model. Additionally, the global model of ELXGB is designed to be centralized, which does not require all participants to stay online for inference. Detailed security analysis demonstrates that ELXGB is privacy-preserving. Moreover, extensive experiments on real-world datasets indicate that ELXGB achieves high efficiency without sacrificing model accuracy.

关键词： Data models Training Federated learning Security inference algorithms Computational modeling Differential privacy homomorphic encryption privacy-preserving vertical federated learning XGBoost

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第9期25卷 10777-10789页

作者： Tan, Jing Khalili, Ramin Karl, Holger Huawei Technol Munich Res Ctr D-80992 Munich Germany Univ Potsdam Hasso Plattner Inst D-14482 Potsdam Germany

The Intelligent Transportation System (ITS) environment is known to be dynamic and distributed, where participants (vehicle users, operators, etc.) have multiple, changing and possibly conflicting objectives. Although Reinforcement Learning (RL) algorithms are commonly applied to optimize ITS applications such as resource management and offloading, most RL algorithms focus on single objectives. In many situations, converting a multi-objective problem into a single-objective one is impossible, intractable or insufficient, making such RL algorithms inapplicable. We propose a multi-objective, multi-agent reinforcement learning (MARL) algorithm with high learning efficiency and low computational requirements, which automatically triggers adaptive few-shot learning in a dynamic, distributed and noisy environment with sparse and delayed reward. We test our algorithm in an ITS environment with edge cloud computing. Empirical results show that the algorithm is quick to adapt to new environments and performs better in all individual and system metrics compared to the state-of-the-art benchmark. Our algorithm also addresses various practical concerns with its modularized and asynchronous online training method. In addition to the cloud simulation, we test our algorithm on a single-board computer and show that it can make inference in 6 milliseconds.

关键词： Heuristic algorithms Computational modeling Vehicle dynamics Resource management Optimization inference algorithms Complexity theory V2X distributed systems reinforcement learning multi-objective

来源：评论

学校读者我要写书评

暂无评论

CiGNN: A Causality-Informed and Graph Neural Network Based Framework for Cuffless Continuous Blood Pressure Estimation

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 2674-2686页

作者： Liu, Lei Lu, Huiqi Whelan, Maxine Chen, Yifan Ding, Xiaorong Univ Elect Sci & Technol China Sch Life Sci & Technol Chengdu 611731 Peoples R China Univ Oxford Inst Biomed Engn Oxford OX1 2JD England Coventry Univ Ctr Healthcare & Communities Coventry CV1 5FB England

Causalityholds profound potentials to dissipate confusion and improve accuracy in cuffless continuous blood pressure (BP) estimation, an area often neglected in current research. In this study, we propose a two-stage framework, CiGNN, that seamlessly integrates causality and graph neural network (GNN) for cuffless continuous BP estimation. The first stage concentrates on the generation of a causal graph between BP and wearable features from the the perspective of causal inference, so as to identify features that are causally related to BP variations. This stage is pivotal for the identification of novel causal features from the causal graph beyond pulse transit time (PTT). We found these causal features empower better tracking in BP changes compared to PTT. For the second stage, a spatio-temporal GNN (STGNN) is utilized to learn from the causal graph obtained from the first stage. The STGNN can exploit both the spatial information within the causal graph and temporal information from beat-by-beat cardiac signals for refined cuffless continuous BP estimation. We evaluated the proposed method with three datasets that include 305 subjects (102 hypertensive patients) with age ranging from 20-90 and BP at different levels, with the continuous Finapres BP as references. The mean absolute difference (MAD) for estimated systolic blood pressure (SBP) and diastolic blood pressure (DBP) were 3.77 mmHg and 2.52 mmHg, respectively, which outperformed comparison methods. In all cases including subjects with different age groups, while doing various maneuvers that induces BP changes at different levels and with or without hypertension, the proposed CiGNN method demonstrates superior performance for cuffless continuous BP estimation. These findings suggest that the proposed CiGNN is a promising approach in elucidating the causal mechanisms of cuffless BP estimation and can substantially enhance the precision of BP measurement.

关键词： Estimation Feature extraction inference algorithms Graph neural networks Electrocardiography Biomedical monitoring Physiology Amplitude alteration Causality cuffless continuous blood pressure pulse transit time spatio-temporal graph neural network

来源：评论

学校读者我要写书评

暂无评论

HIPPL: Hierarchical Intent-Inferring Pointer Network With Pseudo Labeling for Consistent Persona-Driven Dialogue Generation

引用

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 2024年第4期19卷 63-78页

作者： Zhu, Luyao Li, Wei Mao, Rui Cambria, Erik Nanyang Technol Univ Singapore Singapore

Despite the recent advancements in dialogue systems, persona-driven chatbots are still in their infancy. Previous studies on persona-driven dialogue generation demonstrated its ability in generating responses that contain more detailed persona information. However, the challenge of maintaining persona consistency and contextual coherence still persists in persona-driven dialogue generation. Moreover, current methods have limitations in processing multi-source inputs and identifying interlocutor intents due to the absence of trustworthy labels and effective modeling. Additionally, numerous approaches rely on pre-trained large-scale language models that require costly computational resources. To address these challenges, a lightweight hierarchical intent-inferring pointer network is proposed for multi-source persona-driven dialogue generation. The proposed method involves detecting interlocutor intents in chitchat and utilizing pseudo labeling and natural language inference techniques to generate intent labels. Our model is evaluated on a benchmark dataset PersonaChat. The experimental results show that our model outperforms the strongest baseline by 13.47% and 4.28% in terms of persona consistency and contextual coherence, respectively.

关键词： Training data Resistance Measurement Computational modeling Noise measurement Natural language processing Coherence Chatbots Labeling Context modeling Decoding Multitasking Vocabulary Information integrity Large language models inference algorithms Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

KFA: Keyword Feature Augmentation for Open Set Keyword Spotting

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 2985-2989页

作者： Ko, Kyungdeuk Lee, Bokyeung Hong, Jonghwan Ko, Hanseok Korea Univ Seoul 02841 South Korea

In recent years, with the advancement of deep learning technology and the emergence of smart devices, there has been a growing interest in keyword spotting (KWS), which is used to activate AI systems with automatic speech recognition and text-to-speech. However, smart devices with KWS often encounter false alarm errors when inputting unexpected words. To address this issue, existing KWS methods typically train non-target words as an unknown class. Despite these efforts, there is still a possibility that unseen words not trained as part of the unknown class could be misclassified as one of the target words. To overcome this limitation, we propose a new method named Keyword Feature Augmentation (KFA) for open-set KWS. KFA performs feature augmentation through adversarial learning to increase the loss. The augmented features are constrained within a limited space using label smoothing. Unlike other generative model-based open set recognition (OSR) methods, KFA does not require any additional training parameters or repeated operation for inference. As a result, KFA has achieved a 0.955 AUROC score and 97.34% target class accuracy for Google Speech Commands V1, and a 0.959 AUROC score and 98.17% target class accuracy for Google Speech Commands V2, which is the highest performance when compared to various OSR methods.

关键词： Training Internet Convolution Artificial intelligence Signal processing algorithms Pattern classification inference algorithms Generative adversarial networks Classification algorithms Accuracy Deep learning keyword spotting open set recognition

来源：评论

学校读者我要写书评

暂无评论

Recognition of Emotional Categories Using Mined Fuzzy Rules From Electroencephalogram Signals With Gated Eye Track Data Approach

引用

IEEE ACCESS 2024年 12卷 118122-118140页

作者： Farhadi Sedehi, Javid Jafarnia Dabanloo, Nader Maghooli, Keivan Sheikhani, Ali Islamic Azad Univ Dept Biomed Engn Sci & Res Branch Tehran *** Iran

Researchers suggest that a short video clip, when tagged with a single label, is sufficient for classification into an emotional category. However, when subjects view an emotional film tagged similarly, there is no guarantee that the designated emotion persists throughout the duration, or when exactly the emotion is elicited. This inconsistency adversely affects the performance of emotion recognition (ER) systems. In this study, we propose a multimodal ER system employing an eye-tracking gated strategy to identify the most effective timing for emotional categorization. Initially, common eye-tracking features are extracted and selected using the minimum-redundancy-maximum-relevance (mRMR) method. Subsequently, the most discriminative feature is employed as a threshold to pinpoint the most relevant timing. EEG signals from these moments are then decomposed into five standard frequency bands using the Daubechies wavelet function (order 4). Furthermore, four types of entropy features are extracted from four-second segments of 62 and 32 channels for the SEED-IV and MAHNOB-HCI databases, respectively. The best features, as determined by the mRMR method, are fed into a Sugeno-fuzzy inference system (S-FIS) designed to derive rules for discriminating between the four emotional categories of happiness, fear, sadness, and neutrality. The S-FIS rules were refined using a genetic algorithm (GA), leading to most discriminative rules achieving average accuracies of 94.42% and 85.20% for the alpha frequency bands of the SEED-IV and MAHNOB-HCI databases, respectively. The results of this study demonstrate the effectiveness of fuzzy rule extraction in enhancing the performance of multimodal ER systems

关键词： Electroencephalography Feature extraction Accuracy Emotion recognition Databases Gaze tracking Support vector machines Fuzzy systems inference algorithms Electroencephalogram (EEG) emotion recognition Sugeno-fuzzy inference system (S-FIS) entropy mine fuzzy rule

来源：评论

学校读者我要写书评

暂无评论

Online inference for Mixture Model of Streaming Graph Signals With Sparse Excitation

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 6419-6433页

作者： He, Yiran Wai, Hoi-To Chinese Univ Hong Kong Dept SEEM Shatin Hong Kong Peoples R China

This paper considers a joint multi-graph inference and clustering problem for simultaneous inference of node centrality and association of graph signals with their graphs. We study a mixture model of filtered low pass graph signals with excitation driven by a sparse matrix. While the mixture model is motivated from practical scenarios, it presents significant challenges to prior graph learning methods. As a remedy, we consider an inference problem focusing on the node centrality of graphs. We design an expectation-maximization (EM) algorithm with a unique low-rank plus sparse prior derived from low pass signal property. We propose a novel online EM algorithm for inference from streaming data. As an example, we extend the online algorithm to detect if the signals are generated from an abnormal graph. We show that the proposed algorithms converge to a stationary point of the maximum-a-posterior (MAP) problem. Numerical experiments support our analysis.

关键词： Signal processing algorithms inference algorithms Clustering algorithms Topology Mixture models Data models Approximation algorithms Blind centrality inference clustering of graph signals expectation maximization online graph learning

来源：评论

学校读者我要写书评

暂无评论

IoTInfer: Automated Blackbox Fuzz Testing of IoT Network Protocols Guided by Finite State Machine inference

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第22期9卷 22737-22751页

作者： Shu, Zhan Yan, Guanhua SUNY Binghamton Dept Comp Sci Binghamton NY 13902 USA

The popularity of Internet of Things (IoT) devices calls for effective yet efficient methods to assess the security and resilience of IoT devices. In this work, we explore a new heuristic based on finite state machine (FSM) inference to guide generation of test cases for blackbox fuzzing tests of IoT network protocol implementations. Our method, which is called IoTInfer, balances exploration and exploitation by continuously monitoring how likely mutation of an input message leads to counterexamples conflicting with the prediction by the current FSM. IoTInfer also applies clustering techniques to coarsen the FSM inferred when there are limited computational resources provisioned for fuzzing tests. We implement IoTInfer for both Bluetooth and Telnet protocols, which are widely used by existing IoT devices. Our experimental results with a variety of IoT devices reveal that IoTInfer is efficient at generating meaningful test cases, some of which can expose previously unknown vulnerabilities or implementation deviations from protocol specifications. We also compare IoTInfer with two other state-of-the-art blackbox IoT device fuzzing tools and find that IoTInfer is better at eliciting different types of responses from the fuzzing targets.

关键词： Internet of Things Fuzzing Protocols Security Performance evaluation Codes inference algorithms Device security security and privacy

来源：评论

学校读者我要写书评

暂无评论

Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2024年第8期71卷 1589-1597页

作者： Fleck Jr, Marcos A. Pereira, Elisa G. Gava, Jonas F. Silva, Henrique B. Moraes, Fernando G. Calazans, Ney L. V. Meneguzzi, Felipe Bastos, Rodrigo P. Reis, Ricardo A. L. Ost, Luciano Garibotti, Rafael Pontificia Univ Catolica Rio Grande do Sul Sch Technol BR-90619900 Porto Alegre Brazil Univ Fed Rio Grande do Sul PGMicro BR-90010150 Porto Alegre Brazil Univ Aberdeen Sch Nat & Comp Sci Aberdeen AB24 3FX Scotland Univ Grenoble Alpes CNRS Grenoble INP TIMA F-38000 Grenoble France Loughborough Univ Wolfson Sch Loughborough LE11 3TU England

The presence of unmanned surface vehicles (USVs) is increasingly frequent in lakes and water reservoirs, performing tasks such as monitoring water quality or delivering goods across the water. However, the emergence of such autonomous vessels raises concerns in terms of safety for people sharing the same environment and the risk of collisions with fixed structures and floating bodies, including other vessels. Therefore, the detection of obstacles and their reliable operation becomes primary in USVs. This work explores the effects caused by neutron radiation on an object detection algorithm tailored for USVs. Results report 77 silent data corruption (SDC)-induced failures, showing that radiation-induced soft errors contribute to missed and false detection of, respectively, existing and nonexistent objects. Furthermore, results suggest that object detection algorithms running with the multicore strategy ( $\text {FIT}_{\text {SDC}}$ rate of 34.3 at sea level and 308.6 at Lake Titicaca) exhibit a 16.4% greater resilience to SDCs compared to the single-core strategy.

关键词： Reliability YOLO Neutrons inference algorithms Autonomous vehicles Safety Feature extraction Neutron radiation object recognition algorithm uncrewed surface vessels unmanned surface vehicles (USVs)

来源：评论

学校读者我要写书评

暂无评论

QChi: A Faster Classification Algorithm Based on Wang-Mendel Algorithm

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2024年第4期32卷 2261-2271页

作者： Jara, Leonardo Gonzalez, Antonio Perez, Raul Univ Granada DaSCI Andalusian Res Inst Dept Comp Sci & Artificial Intelligence Granada 18012 Spain

To address learning problems in which many examples and variables are involved, the use of algorithms that are capable of processing the data using simple and efficient techniques is required. The Wang and Mendel algorithm applied to classification (also known as the Chi algorithm) satisfies these properties in many cases. However, in particularly complex problems, such as those provided by big data, it has become necessary to use architectures for parallel processing, such as MapReduce, whose base algorithm is just this algorithm. The use of these architectures is necessary because the bottleneck of the algorithm is the calculation of the weight of the rules. This calculation requires, for each selected rule, to consider the adaptation of all the examples with this rule. Although this calculation is polynomial-order, in problems with many examples and where many rules are generated, it is very time consuming. In this article, we propose Quick Chi (QChi), a new algorithm based on the Wang-Mendel algorithm that uses, among other changes to make it efficient, a new way of calculating the weights of the rules that is much less computationally expensive. The reduction in learning time is so significant that it allows the algorithm to tackle big data problems without parallel processing structures. In addition to the description of the algorithm, this article checks experimentally on a wide variety of problems, including those that other authors have used as big data problems that this algorithm drastically reduces the learning time while maintaining the classification performance.

关键词： Classification algorithms Proposals Complexity theory Big Data Training inference algorithms Linguistics Big data fast fuzzy inference fuzzy rule-based classification systems fuzzy rule learning Wang-Mendel method

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：