检索结果-内蒙古大学图书馆

IEEE ACCESS 2025年 13卷 62462-62475页

作者： Zahid, Anam Kamiran, Faisal Abbas, Samar Qureshi, Bilal Karim, Asim Informat Technol Univ ITU Dept Comp Sci Lahore 54000 Pakistan Lahore Univ Management Sci Syed Babar Ali Sch Sci & Engn SBASSE Dept Comp Sci Lahore 54792 Pakistan Addo Ai Lahore Pakistan

Uplift modeling studies the impact of different treatments on an outcome and has several applications, such as targeted marketing and medical therapy assessment. Usually, such studies are retrospective in nature rather than controlled experiments;hence, pre-existing bias in the observed data can distort the true effect of treatment. Previous studies on uplift modeling has largely overlooked this bias, focusing instead on model-based solutions for specific applications. In this paper, we introduce a new data-driven framework for uplift modeling based on matching. We represent individuals in treatment and control groups using weighted bipartite graphs, and bipartite graph matching is then employed to retain similar individuals, thereby reducing bias. Subsequently, appropriate datasets are generated from the matched pairs for learning predictive models for individuals. Our proposed model-independent framework facilitates robust inferences, making it adaptable to a wide range of applications and settings. In particular, we demonstrate how uplift modeling can be applied to discrimination discovery and prevention in discrimination-aware data mining. We evaluate our framework on three datasets representing three different applications. The results reveal that our framework produces better prediction performances in comparison to others and is easy to apply in practice.

关键词： Predictive models Data models Bipartite graph Decision trees inference algorithms Random forests Prevention and mitigation Churn Robustness Interference Causal inference bipartite graph matching observational studies uplift modeling

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Differential Protection of Transmission Lines Based on Bayesian inference

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2022年第3期37卷 1569-1577页

作者： Tiferes, Rodrigo Rozenblit Manassero Jr, Giovanni Univ Sao Paulo PEA Dept Engn Energia & Automacao Eletr BR-05508010 Sao Paulo Brazil

This paper presents a time-domain differential protection method based on the Bayes' Theorem and on the current samples to determine the fault occurrence probability as a function of time. It also describes the theory involved in developing the proposed protection method when considering the differential protection of transmission lines. The authors performed fault simulations using an existing electrical system modeled in EMTP varying the fault type, phases involved, fault resistance, inception angle, and fault location, and carried out a sensitivity analysis regarding high impedance faults, current transformer saturation, noisy data, misalignments between terminal samples and power swings. The authors also tested the proposed method against actual fault events from four existing transmission lines of the Brazilian interconnected power system. All results indicate that the proposed solution is fast, accurate, secure, and dependable.

关键词： Circuit faults Probability Power transmission lines Bayes methods Time-domain analysis Fault currents inference algorithms Time-domain analysis differential protection Bayes methods probability

来源：评论

学校读者我要写书评

暂无评论

Chasing Common Knowledge: Joint Large Model Selection and Pulling in MEC With Parameter Sharing

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2025年第3期36卷 437-454页

作者： Zhou, Lizhen Xu, Zichuan Xia, Qiufen Xu, Zhou Ren, Wenhao Qi, Wenbo Ma, Jinjing Yan, Song Yang, Yuan DUT Sch Software Technol Dalian 116024 Liaoning Peoples R China DUT RU Int Sch Informat Sci & Engn Dalian 116024 Liaoning Peoples R China Ant Grp Hangzhou 310000 Zhejiang Peoples R China Alibaba Cloud Hangzhou 310030 Zhejiang Peoples R China

Pretrained Foundation Models (PFMs) are regarded as a promising accelerator for the development of various Artificial Intelligence (AI) applications, and have recently been widely fine-tuned to satisfy users' personalized inference demands. As many users are attracted to PFM-based AI applications, remote data centers are increasingly unable to solely bear the enormous computational demands and meet the delay requirements of inference requests. Mobile edge computing (MEC) offers a viable solution for delivering low-latency inference services by pulling fine-tuned PFMs from the remote data center to cloudlets in the proximity of users. However, a fine-tuned PFM typically comprises billions of model parameters, which are highly resource-intensive, time-consuming, and cost-prohibitive to execute at the edge. To address this, we investigate a novel joint large model selection and pulling problem in MEC networks. The novelty of our study lies in exploring parameter sharing among fine-tuned PFMs based on their common knowledge. Specifically, we first formulate a Non-Linear Integer Programming (NLIP) for the problem to minimize the total delay of implementing all inference requests. We then transform the NLIP into an equivalent Integer Linear Program (ILP) that is much simpler to solve. We further propose a randomized algorithm with a provable approximation ratio for the problem. We also consider the online version of the problem with uncertain request demand, and develop an online learning algorithm with a bounded regret. The crux of the online algorithm is the adoption of the multi-armed bandit technique with restricted context for dynamic admissions of inference requests. We finally conduct extensive experiments based on real datasets. Experimental results demonstrate that our algorithms reduce at least 38% in total delays and average costs, while achieving a 5% improvement in average accuracies.

关键词： Computational modeling Accuracy Delays inference algorithms Heuristic algorithms Costs Adaptation models Context modeling Approximation algorithms Load modeling Mobile edge computing (MEC) model selection model pulling approximation algorithm online learning

来源：评论

学校读者我要写书评

暂无评论

A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models

引用

IEEE CIRCUITS AND SYSTEMS MAGAZINE 2025年第1期25卷 35-57页

作者： Guo, Cong Cheng, Feng Du, Zhixu Kiessling, James Ku, Jonathan Li, Shiyu Li, Ziru Ma, Mingyuan Molom-Ochir, Tergel Morris, Benjamin Shan, Haoxuan Sun, Jingwei Wang, Yitu Wei, Chiyue Wu, Xueying Wu, Yuhao Yang, Hao Frank Zhang, Jingyang Zhang, Junyao Zheng, Qilin Zhou, Guanglei Li, Hai Chen, Yiran Duke Univ Dept Elect & Comp Engn Durham NC 27705 USA

The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality. These models are increasingly integrated into diverse applications, impacting both research and industry. However, their development and deployment present substantial challenges, including the need for extensive computational resources, high energy consumption, and complex software optimizations. Unlike traditional deep learning systems, LLMs require unique optimization strategies for training and inference, focusing on system-level efficiency. This paper surveys hardware and software co-design approaches specifically tailored to address the unique characteristics and constraints of large language models. This survey analyzes the challenges and impacts of LLMs on hardware and algorithm research, exploring algorithm optimization, hardware design, and system-level innovations. It aims to provide a comprehensive understanding of the trade-offs and considerations in LLM-centric computing systems, guiding future advancements in AI. Finally, we summarize the existing efforts in this space and outline future directions toward realizing production-grade co-design methodologies for the next generation of large language models and AI systems.

关键词： Large language models Artificial intelligence Natural language processing Multimodal sensors Energy consumption Deep learning Training Hardware design languages Algorithm design and analysis Software algorithms inference algorithms Next generation networking Collaborative software Large language model hardware-software co-design

来源：评论

学校读者我要写书评

暂无评论

Correlation-Aided Joint Activity Detection and Channel Estimation for Multidevice Collaborative Massive Access

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第10期11卷 18394-18409页

作者： Li, Yang Chen, Shuyi Meng, Weixiao Li, Cheng Harbin Inst Technol Commun Res Ctr Harbin 150001 Peoples R China Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada

This article investigates an uplink grant-free massive access (GF-MA) system, where a large number of Internet of Things devices collaborate to achieve complex applications. For this scenario, device activity identification is a challenging problem due to the interference from massive devices and the limitation in the number of pilot sequences. By utilizing the inherent correlation features in multidevice collaborative scenarios, in this work, we present a detection approach that aims to enhance the accuracy of both activity detection and channel estimation (CE). Specifically, we first propose a task-driven activity (TDA) model to capture the active probability in multidevice collaborative scenarios. Subsequently, considering the TDA model, we propose a message-passing-based algorithm named TDA-JDE for device activity detection and CE. The proposed algorithm jointly processes messages containing channel impulse response (CIR), device activity, and task status information to leverage device activity correlation information. Finally, to obtain the parameters in the TDA model, we propose a parameter estimation algorithm based on the expectation-maximization framework with relaxation and reconstruction strategy (EM-RR). Extensive numerical results show that the proposed algorithm can achieve higher detection accuracy when compared with three benchmark schemes in multidevice collaborative massive access (MA) scenarios.

关键词： Task analysis Correlation Internet of Things Collaboration Channel estimation Performance evaluation inference algorithms Grant-free massive access (GF-MA) Internet of Things (IoT) joint activity detection and channel estimation (CE) message-passing (MP) algorithm multidevice collaboration

来源：评论

学校读者我要写书评

暂无评论

Automated Ensemble for Deep Learning inference on Edge Computing Platforms

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第6期9卷 4202-4213页

作者： Bai, Yang Chen, Lixing Abdel-Mottaleb, Mohamed Xu, Jie Univ Miami Dept Elect & Comp Engn Coral Gables FL 33146 USA Shanghai Jiao Tong Univ Inst Cyber Sci & Technol Shanghai 200240 Peoples R China

Advances in deep learning (DL) have triggered an explosion of mobile intelligence, posing a soaring demand for computing resources that cannot be satisfied by mobile devices. In this article, we employ edge computing to deliver better DL inference services to end users. The key is to leverage deep neural network (DNN) ensemble techniques that provide state-of-the-art performance for many machine learning applications in terms of inference accuracy and robustness. Compared to end devices, the edge computing platform is endowed with more powerful computing resources, making it feasible to implement DNN ensembles for DL inferences. However, due to the constrained computing capacity of edge servers and the possible service response deadline, an edge server can only use a limited number of DNNs to construct DNN ensembles. This poses a unique problem, namely, DNN ensemble selection, for identifying the best-fit DNN ensembles. We propose a novel algorithm called automated DNN ensemble selection (AES) algorithm to solve this problem. Because DNNs exhibit performance variations over different distributions of input data, AES adaptively determines a DNN ensemble according to the features of admitted inference tasks. AES is an online learning algorithm that learns DNNs' in-use performance over time. An ensemble selection rule is further designed as a subroutine of AES to recruit members into the DNN ensemble based on the accuracy and diversity of DNNs. In particular, we theoretically prove that AES can achieve asymptotic optimality. We carry out experiments on real-world data sets. The results show that using the DNN ensemble technique on edge computing platforms dramatically improves the DL inference quality, and AES outperforms other benchmark schemes.

关键词： Edge computing Servers Task analysis Mobile handsets Deep learning inference algorithms Performance evaluation Deep neural network (DNN) ensemble edge computing multiarmed bandit (MAB)

来源：评论

学校读者我要写书评

暂无评论

Interactive inference Under Information Constraints

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2022年第1期68卷 502-516页

作者： Acharya, Jayadev Canonne, Clement L. Liu, Yuhan Sun, Ziteng Tyagi, Himanshu Cornell Univ Sch Elect & Comp Engn Ithaca NY 14850 USA Univ Sydney Sch Comp Sci Sydney NSW 2006 Australia Indian Inst Sci Dept Elect Commun Engn Bengaluru 560012 India

We study the role of interactivity in distributed statistical inference under information constraints, e.g., communication constraints and local differential privacy. We focus on the tasks of goodness-of-fit testing and estimation of discrete distributions. From prior work, these tasks are well understood under noninteractive protocols. Extending these approaches directly for interactive protocols is difficult due to correlations that can build due to interactivity;in fact, gaps can be found in prior claims of tight bounds of distribution estimation using interactive protocols. We propose a new approach to handle this correlation and establish a unified method to establish lower bounds for both tasks. As an application, we obtain optimal bounds for both estimation and testing under local differential privacy and communication constraints. We also provide an example of a natural testing problem where interactivity helps.

关键词： Protocols Testing Task analysis Estimation Privacy Correlation Complexity theory Distributed algorithms inference algorithms estimation statistics minimax techniques data privacy communication channels

来源：评论

学校读者我要写书评

暂无评论

EICD: Causal Structure Recovery of Bearing Failure Data Containing Latent Confounding

引用

IEEE SENSORS JOURNAL 2024年第19期24卷 30560-30574页

作者： Ding, Xu Chen, Jun Chen, Guanhua Xu, Juan Hefei Univ Technol Inst Ind & Equipment Technol Anhui Prov Key Lab Aerosp Struct Parts Forming Tec Hefei 230009 Peoples R China Hefei Univ Technol Sch Comp & Informat Hefei 230061 Peoples R China

Deep learning is widely used in the field of intelligent fault diagnosis. However, data-driven deep learning models are with unsatisfying interpretability and their performance cannot be maintained when a sample distribution shift occurs. Causal discovery can enhance the interpretability of deep learning models by establishing causal graphs to uncover causal invariance in the data. Nevertheless, causal discovery suffers from the curse of dimensionality due to the large conditional sets used in conditional independence (CI) tests, and the Markov equivalence class (MEC) obtained contains many undirected edges due to some causal structures having the same CI. In response, we incorporate the causal direction criterion (CDC) into iterative causal discovery (ICD) to construct the extended ICD (EICD) algorithm. EICD can obtain a detailed causal graph with lower complexity, enhancing the interpretability of the diagnostic framework. First, EICD reduces the number of required CI tests by limiting the size of the conditioning set and its distance from the target node. Second, based on CDC, EICD uses causal asymmetry to infer the direction of causal edges between pairs of nodes, thus accelerating ICD and adding more directional causal edges compared to MEC. In the experimental section, we compare the number of CI tests and the improvement in directional accuracy with other algorithms and use the EICD algorithm to reconstruct the causal graph of the faulty system. The experiments demonstrate that the EICD algorithm can reduce the required number of CI tests and recover the underlying causal structure more accurately.

关键词： Fault diagnosis Data models Feature extraction Deep learning Signal processing algorithms inference algorithms Convolution Causal discovery casual effect inference fault diagnosis latent confounding

来源：评论

学校读者我要写书评

暂无评论

FML-Vit: A Lightweight Vision Transformer Algorithm for Human Activity Recognition Using FMCW Radar

引用

IEEE SENSORS JOURNAL 2024年第22期24卷 38518-38526页

作者： Ding, Minhao Dongye, Guangxin Lv, Ping Ding, Yipeng Cent South Univ Sch Elect Informat Changsha 410083 Peoples R China

In recent years, human activity recognition (HAR) using frequency module continuous wave (FMCW) radar is an effective tool that has been widely used in the fields of healthcare, smart driving, and smart living due to its convenience, inexpensiveness, and accuracy. Past studies have mainly investigated the improvement of the accuracy of HAR models while neglecting the deployment of the models. Therefore, we propose a model named FMCW lightweight vision transformer (FML-Vit) for HAR, primarily consisting of the FML-Vit block and FML-Vit subsample modules. The FML-Vit block, by incorporating a cascaded linear self-attention mechanism in place of the traditional multi-head attention mechanism, can transform the time complexity from O(K-2) to O(K). The FML-Vit subsampling modules perform dimension reduction and feature reallocation, while the context broadcasting (CB) module is used to reduce the density in the original attention maps, thereby increasing both the capacity and generalizability of the ViT. The proposed algorithm is compared with nine different state-of-the-art methods on self-datasets and open-source datasets. The results demonstrate that FML-Vit outperforms other current lightweight networks with the fastest inference.

关键词： Radar Transformers Accuracy Computational modeling Sensors inference algorithms Human activity recognition Attention mechanisms Spectrogram Signal processing algorithms Cascaded linear multihead attention mechanism context broadcasting (CB) frequency module continuous wave (FMCW) lightweight vison transformer (FML-Vit)

来源：评论

学校读者我要写书评

暂无评论

Implicit Posteriori Parameter Distribution Optimization in Reinforcement Learning

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第5期54卷 3051-3064页

作者： Li, Tianyi Yang, Genke Chu, Jian Shanghai Jiao Tong Univ Ningbo Artificial Intelligence Inst Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Automation Shanghai 200240 Peoples R China

Efficient and intelligent exploration remains a major challenge in the field of deep reinforcement learning (DRL). Bayesian inference with a distributional representation is usually an effective way to improve the exploration ability of the RL agent. However, when optimizing Bayesian neural networks (BNNs), most algorithms need to specify an explicit parameter distribution such as a multivariate Gaussian distribution. This may reduce the flexibility of model representation and affect the algorithm performance. Therefore, to improve sample efficiency and exploration based on Bayesian methods, we propose a novel implicit posteriori parameter distribution optimization (IPPDO) algorithm. First, we adopt a distributional perspective on the parameter and model it with an implicit distribution, which is approximated by generative models. Each model corresponds to a learned latent space, providing structured stochasticity for each layer in the network. Next, to make it possible to optimize an implicit posteriori parameter distribution, we build an energy-based model (EBM) with value function to represent the implicit distribution which is not constrained by any analytic density function. Then, we design a training algorithm based on amortized Stein variational gradient descent (SVGD) to improve the model learning efficiency. We compare IPPDO with other prevailing DRL algorithms on the OpenAI Gym, MuJoCo, and Box2D platforms. Experiments on various tasks demonstrate that the proposed algorithm can represent the parameter uncertainty implicitly for a learned policy and can consistently outperform competing approaches.

关键词： Bayes methods Uncertainty Artificial neural networks Task analysis Mathematical models inference algorithms Generators Bayesian inference exploration parameter distribution reinforcement learning (RL)

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：