检索结果-内蒙古大学图书馆

IEEE OPEN JOURNAL OF SIGNAL PROCESSING 2025年 6卷 247-255页

作者： Rey, Samuel Das, Bishwadeep Isufi, Elvin King Juan Carlos Univ Dept Signal Theory & Commun Madrid 28933 Spain Delft Univ Technol Intelligent Syst Dept NL-2628 CD Delft Netherlands

This paper addresses the problem of online network topology inference for expanding graphs from a stream of spatiotemporal signals. Online algorithms for dynamic graph learning are crucial in delay-sensitive applications or when changes in topology occur rapidly. While existing works focus on inferring the connectivity within a fixed set of nodes, in practice, the graph can grow as new nodes join the network. This poses additional challenges like modeling temporal dynamics involving signals and graphs of different sizes. This growth also increases the computational complexity of the learning process, which may become prohibitive. To the best of our knowledge, this is the first work to tackle this setting. We propose a general online algorithm based on projected proximal gradient descent that accounts for the increasing graph size at each iteration. Recursively updating the sample covariance matrix is a key aspect of our approach. We introduce a strategy that enables different types of updates for nodes that just joined the network and for previously existing nodes. To provide further insights into the proposed method, we specialize it in Gaussian Markov random field settings, where we analyze the computational complexity and characterize the dynamic cumulative regret. Finally, we demonstrate the effectiveness of the proposed approach using both controlled experiments and real-world datasets from epidemic and financial networks.

关键词： Topology Network topology Heuristic algorithms Signal processing algorithms Signal processing Covariance matrices Mathematical models inference algorithms Computational complexity Vectors Topology inference dynamic graph learning online graph learning expanding graphs graph signal processing

来源：评论

学校读者我要写书评

暂无评论

A Rapid Concrete Crack Detection Method Based on Improved YOLOv8

引用

IEEE ACCESS 2025年 13卷 59227-59243页

作者： Wang, Yongzhen He, Jiacong China Univ Min & Technol Sch Mech & Elect Engn Xuzhou 221116 Peoples R China

An improved YOLOv8 (You Only Look Once version 8) model is proposed to tackle the challenges of low detection accuracy and slow speed resulting from the complex background and shape diversity of concrete cracks. Firstly, a lightweight feature fusion module, GE_Conv, is designed by integrating the Ghost Module and Efficient Channel Attention in series. This module is embedded into the neck network to preserve more feature information during downsampling and accelerate the model's inference speed. Secondly, the DBB_Bottleneck is introduced into the C2f module, combining the lightweight GE_Conv with the structurally re-parameterized Diverse Branch Block, enhancing the model's multi-scale feature extraction capability. Furthermore, the introduction of the GF_Detect detection head significantly reduces the number of model parameters while improving detection performance. Finally, the WIoUv3 loss function is employed to dynamically assign anchor boxes of varying qualities, thereby enhancing the accuracy of anchor box positioning. Experimental results demonstrate that the proposed model achieves a detection precision of 92.9% and a mAP@50 (mean average precision at an Intersection over Union threshold of 0.5) of 77.8%. Compared to state-of-the-art algorithms such as Faster R-CNN, SSD, RetinaNet, YOLOv5s, YOLOv7-tiny, and the original YOLOv8s, the proposed model exhibits superior performance in both detection accuracy and generalization capability. Additionally, the model achieves an average detection time of 10.20 ms per image, demonstrating its practical feasibility. This study not only improves the accuracy and speed of crack detection but also significantly reduces the computational complexity of the model, advancing the development of lightweight and practical crack detection algorithms. The proposed model can be widely applied to crack inspection tasks for roads, bridges, coal mine shafts, and other scenarios, providing efficient and reliable technical support for cra

关键词： Accuracy Feature extraction YOLO Image edge detection Computational modeling Neck inference algorithms Image segmentation Convolution Standards Concrete cracks object detection lightweight module wise intersection over union you only look once version 8

来源：评论

学校读者我要写书评

暂无评论

Offloading algorithms for Maximizing inference Accuracy on Edge Device in an Edge Intelligence System

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2023年第7期34卷 2025-2039页

作者： Fresa, Andrea Champati, Jaya Prakash IMDEA Networks Inst Edge Networks Grp Madrid 28918 Spain

With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference from the data samples collected at the EDs, we study the problem of offloading inference jobs by considering the following novel aspects: 1) in contrast to a typical computational job, the processing time of an inference job depends on the size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs) for resource-constrained devices provide the choice of scaling down the model size by trading off the inference accuracy. Considering that multiple ML models are available at the ED, and a powerful ML model is available at the ES, we formulate an Integer Linear Programming (ILP) problem with the objective of maximizing the total inference accuracy of n data samples at the ED subject to a time constraint T on the makespan. Noting that the problem is NP-hard, we propose an approximation algorithm Accuracy Maximization using LP-Relaxation and Rounding (AMR(2)) and prove that it results in a makespan at most 2T and achieves a total accuracy that is lower by a small constant from the optimal total accuracy implying that AMR(2) is asymptotically optimal. Further, if the data samples are identical we propose Accuracy Maximization using Dynamic Programming (AMDP), an optimal pseudo-polynomial time algorithm. Furthermore, we extend AMR(2) for the case of multiple ESs, where each ES is equipped with a powerful ML model. As proof of concept, we implemented AMR(2) on a Raspberry Pi, equipped with MobileNets, that is connected to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR(2) for image classification.

关键词： Data models Computational modeling inference algorithms Costs Servers Approximation algorithms Scheduling deep learning edge computing linear programming machine learning

来源：评论

学校读者我要写书评

暂无评论

A Substation Safety Measure Ticket Generation Algorithm based on Neural Network and inference Engine

A Substation Safety Measure Ticket Generation Algorithm base...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Yin Wu Huicai Zhao Xingfu Huang Liqiong Huang Yuyang Hu Guangxi Power Grid Power Dispatching and Control Center Nanning China Guangxi Power Grid Limited Liability Company Nanning Power Supply Bureau Nanning China Guangxi Power Grid Limited Liability Company Guilin Power Supply Bureau Guilin China

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Intelligent substations use fiber optic as the information transmission medium, transforming the interconnection relationship between secondary devices into fiber optic connections. The corresponding secondary circuits and hardware platforms are replaced with virtual circuits and software templates, resulting in a significant change in maintenance work methods and higher requirements for operators' maintenance work. This article proposes an intelligent substation safety measure ticket generation algorithm based on multi-scale feature convolutional neural network (MSF-CNN) and inference machine. Firstly, a neural network model suitable for safety ticket generation was designed and trained. Combining the structural characteristics of DenseNet, multi-scale feature extraction and logical relationship modeling were achieved through multi-layer convolution, concatenation, and pooling processing. The model uses hyperbolic tangent function as the activation function to improve the accuracy of regression prediction. Secondly, a custom word vector and equipment association modeling method based on SCD file parsing are proposed for the electricity proprietary terms and multi item logical relationships involved in the safety measures ticket text, in order to improve data expression accuracy and model understanding ability. In addition, based on the functional correlation and input-output interaction characteristics of substation equipment, a three-layer neural network-based inference engine was constructed to generate maintenance safety measures for primary and secondary equipment. The experimental results showed that the MSF-CNN model performed the best in accuracy, recall, and F1 score, with an accuracy of 92.5%, recall of 90.8%, and F1 score of 91.6%.

关键词： Optical fibers Substations Accuracy Neural networks Training data Data models inference algorithms Safety Maintenance Engines

来源：评论

学校读者我要写书评

暂无评论

Hybrid Offline Passive Grammatical inference and Online Planning for Non-Markovian Tasks

Hybrid Offline Passive Grammatical Inference and Online Plan...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mahyar Alinejad Alvaro Velasquez Yue Wang George Atia Dept. of Electrical and Computer Engineering University of Central Florida Orlando Florida Dept. of Computer Science University of Colorado Boulder Colorado Dept. of Electrical and Computer Engineering Dept. of Computer Science University of Central Florida Orlando Florida

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Planning in non-Markovian environments often requires inferring task structures, such as reward machines, through interactions with the environment. Traditional active grammatical inference methods, like Angluin’s L * algorithm, depend on continuous querying to learn task structures for the underlying planning objectives. In contrast, we propose a hybrid approach that combines passive grammatical inference, using the Regular Positive and Negative inference (RPNI) algorithm, with online planning. By leveraging pre-collected positive and negative trajectories, RPNI learns a deterministic finite automaton (DFA) that captures the task structure, significantly reducing the need for real-time interactions. Subsequently, online planning is conducted over the product MDP, which integrates the environment with the learned DFA. This hybrid methodology minimizes the cost of online interactions and improves learning efficiency in complex environments. Our approach outperforms baseline algorithms in terms of runtime and sample complexity, and is well-suited for real-world scenarios where task structures are implicit, and interactions with the environment are expensive.

关键词： Runtime Learning automata Signal processing algorithms Signal processing inference algorithms Real-time systems Planning Complexity theory Trajectory Speech processing

来源：评论

学校读者我要写书评

暂无评论

Anda: Unlocking Efficient LLM inference with a Variable-Length Grouped Activation Data Format

Anda: Unlocking Efficient LLM Inference with a Variable-Leng...

引用

IEEE Symposium on High-Performance Computer Architecture

作者： Chao Fang Man Shi Robin Geens Arne Symons Zhongfeng Wang Marian Verhelst School of Electronic Science and Engineering Nanjing University China ESAT-MICAS KU Leuven Belgium

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

The widely-used, weight-only quantized large language models (LLMs), which leverage low-bit integer (INT) weights and retain floating-point (FP) activations, reduce storage requirements while maintaining accuracy. However, this shifts the energy and latency bottlenecks towards the FP activations that are associated with costly memory accesses and computations. Existing LLM accelerators focus primarily on computation optimizations, overlooking the potential of jointly optimizing FP computations and data movement, particularly for the dominant FP-INT GeMM operations in LLM inference. To address these challenges, we investigate the sensitivity of activation precision across various LLM modules and its impact on overall model accuracy. Based on our findings, we first propose the Anda data type: an adaptive data format with group-shared exponent bits and dynamic mantissa bit allocation. Secondly, we develop an iterative post-training adaptive precision search algorithm that optimizes the bit-width for different LLM modules to balance model accuracy, energy efficiency, and inference speed. Lastly, a suite of hardware optimization techniques is proposed to maximally exploit the benefits of the Anda format. These include a bit-plane-based data organization scheme, Anda-enhanced processing units with bit-serial computation, and a runtime bit-plane Anda compressor to simultaneously optimize storage, computation, and memory footprints. Our evaluations on FP-INT GeMM operations show that Anda achieves a $2.4 \times$ speedup, $4.0 \times$ area efficiency, and $3.1 \times$ energy efficiency improvement on average for popular LLMs including OPT, LLaMA, and LLaMA-2 series over the GPU-like FP-FP baseline. Anda demonstrates strong adaptability across various application scenarios, accuracy requirements, and system performance, enabling efficient LLM inference across a wide range of deployment scenarios.

关键词： Accuracy Runtime Large language models Computational modeling Organizations Energy efficiency Iterative algorithms inference algorithms Hardware Optimization

来源：评论

学校读者我要写书评

暂无评论

A radar behavior mode recognition method with Bayesian inference

A radar behavior mode recognition method with Bayesian infer...

引用

IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Xingyu Wang China State Shipbuilding Corporation Limited No.723 Research Institute China

ISBN: (数字)9798331529482

ISBN: (纸本)9798331529499

With the increasingly complex electromagnetic signal environment, the traditional radar signal behavior mode recognition method for phased array and radar seeker of this kind of special multi-mode radar mode recognition is more difficult, this paper proposes a based on Bayesian inference, combined with the radar signal pulse stream sliding window processing mechanism, can effectively make up for the traditional radar signal behavior pattern recognition on the shortcomings of the mechanism for phased array and guide head of this kind of special body multi-mode radar pattern recognition method is proposed accordingly. Under this mechanism, a corresponding radar behavior mode recognition method is proposed for the special multi-mode radar of phased array and radar seeker.

关键词： Phased arrays Mechatronics Array signal processing Radar Radar signal processing inference algorithms Bayes methods Pattern recognition Information technology Sorting

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Semantic Segmentation Tasks in Autonomous Driving: A Likelihood Active inference Approach

Resource Allocation for Semantic Segmentation Tasks in Auton...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xinxin Zhu F. Richard Yu Ying He Biao He College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Research Institute for Smart Cities School of Architecture and Urban Planning Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The latest Segment Anything Model enables realtime scene annotation and understanding for autonomous driving systems, enhancing driving safety. However, effectively allocating resources for real-time performance and accuracy remains challenging in edge-cloud architectures. Traditional reinforcement learning struggles with poor generalization and the explorationexploitation dilemma, making it difficult to define clear reward functions. To address this, we propose a likelihood active inference approach to optimize resource allocation and improve system resource utilization. We use "intelligence" as a high-level indicator to quantify the efficiency of cognition in active inference, evaluating the difference between predicted and actual states during policy exploration. Experimental results show our algorithm outperforms mainstream deep reinforcement learning algorithms, improving sample efficiency and suitability for dynamically changing task workloads.

关键词： Accuracy Heuristic algorithms Signal processing algorithms Signal processing Prediction algorithms inference algorithms Real-time systems Resource management Speech processing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Partial inference in Structured Prediction

Partial Inference in Structured Prediction

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chuyang Ke Deepak Maurya Jean Honorio Purdue University CS West Lafayette USA CIS and OPTIMA ARC Training Centre The University of Melbourne Melbourne Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this work, we examine the partial inference problem in the context of structured prediction. Using a generative model approach, we consider the task of maximizing a score function with unary and pairwise potentials in the space of labels on graphs. Employing a two-stage convex optimization algorithm for label recovery, we analyze the conditions under which a majority of the labels can be recovered. We introduce a novel perspective on the Karush-Kuhn-Tucker (KKT) conditions and primal and dual construction, and provide statistical and topological requirements for partial recovery with provable guarantees. The full-length paper with detailed proofs of our novel theoretical claims can be accessed from https://***/abs/2306.03949.

关键词： Signal processing algorithms Signal processing Prediction algorithms inference algorithms Convex functions Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

LAD: Efficient Accelerator for Generative inference of LLM with Locality Aware Decoding

LAD: Efficient Accelerator for Generative Inference of LLM w...

引用

IEEE Symposium on High-Performance Computer Architecture

作者： Haoran Wang Yuming Li Haobo Xu Ying Wang Liqi Liu Jun Yang Yinhe Han Chinese Academy of Sciences Institute of Computing Technology University of Chinese Academy of Sciences

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Large Language Models (LLMs) have emerged as the cornerstone of content generation applications due to their ability to capture relations between newly generated token and the full preceding context. However, this ability stems from the attention mechanism for decoding that retains the entire generation history as key value cache (KV cache). As the generated sequence lengthens, the KV cache expands, causing a substantial memory access bottleneck. In advanced LLM generation systems running on GPUs, the attention mechanism for decoding accounts for more than 50% of the total inference time when the KV cache length reaches 4096. To address this issue, this paper introduces LAD (Locality Aware Decoding), an LLM generation accelerator with algorithm-hardware enhancements that significantly decrease KV cache access, resulting in considerable speedups and energy savings. A key insight underlying LAD is that when the attention score for a specific position remains fixed over the next several decoding steps, it is unnecessary to repeatedly retrieve the associated key and value at each step to reproduce the computation. Our analysis reveals that numerous positions exhibit notable numerical locality in attention scores through multiple decoding steps. Leveraging these insights, we have designed an innovative attention decoding computation method that decreases the frequency of accessing the key and value for positions demonstrating good locality, all while maintaining decoding accuracy. Extensive experiments show that LAD generates sequences with an average ROUGE-1 similarity of 97% compared to those generated by the original model. When the length of KV cache exceeds 2048, the high configuration of LAD accelerator achieves on average (geomean) $10.7 \times$ speedup and $52.4 \times$ energy efficiency for the attention mechanism compared to the A100 GPU. For end-to-end model inference, it also achieves on average $2.3 \times$ speedup and $13.4 \times$ energy efficiency.

关键词： Attention mechanisms Accuracy Large language models Memory management Graphics processing units Energy efficiency inference algorithms Decoding History Optimization

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：