检索结果-内蒙古大学图书馆

Method for Brillouin gain spectrum recovery based on compressed sensing with convex optimization

APPLIED OPTICS 2024年第21期63卷 5713-5720页

作者： Zhu, Borong Azad, Abul kalam Yu, Kuanglu Ma, Xiaole Beijing Key Lab Adv Informat Sci & Network Technol Beijing 100044 Peoples R China Beijing Jiaotong Univ Inst Informat Sci Sch Comp & Informat Technol Beijing 100044 Peoples R China Univ Dhaka Dept Elect & Elect Engn Dhaka 1000 Bangladesh

The traditional Brillouin optical fiber distributed sensors obtain the Brillouin gain spectrum (BGS) through frequency-by-frequency sweeping acquisition, which can be time-consuming and data intensive. These characteristics put a lot of pressure on data storage, especially on signal processing. Compressed sensing is a method represented by random sampling to reduce the number of acquisition frequencies, but the results obtained may be unstable. In this paper, we have proposed a reconstruction algorithm based on compressed sensing with convex optimization (COP), which can recover the whole BGS by collecting only 10% of the acquisition frequencies. The recovered BGS can attain a RMSE similar to the fully collected BGS. The proposed algorithm also provides more accurate and stable performances for different random sampling points compared to existing reconstruction methods. For example, for a 10% sampling percentage, with a reduction in error of 2.24 and 0.40 MHz, values are lower than those employing the orthogonal matching pursuit (OMP) and the regularized orthogonal matching pursuit (ROMP), respectively. Moreover, the reconstruction results of the proposed method are more stable for different random sampling points, with a reduction in standard deviation of 2.58 and 0.07 MHz. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Erbium-doped fiber amplifiers Fiber optic sensors Fourier transforms neural networks Optical fibers Signal processing

来源：评论

学校读者我要写书评

暂无评论

Towards the distributed Wound Treatment Optimization Method for Training CNN Models: Analysis on the MNIST Dataset 15

Towards the Distributed Wound Treatment Optimization Method ...

引用

IEEE 15th International Symposium on Autonomous Decentralized Systems (ISADS)

作者： Ponce, Hiram Moya-Albor, Ernesto Brieva, Jorge Univ Panamer Fac Ingn Augusto Rodin 498 Mexico City 03920 DF Mexico

ISBN: (纸本)9781665464512

Convolutional neural network (CNN) is a prominent algorithm in Deep Learning methods. CNN architectures have been used successfully to solve various problems in image processing, for example, segmentation, classification, and enhancement task. However, automatic search for suitable architectures and training parameters remain an open area of research, where metaheuristic algorithms have been used to fine-tuning the hyper-parameters and learning parameters. This work presents a bio-inspired distributed strategy based on Wound Treatment Optimization (WTO) for training the learning parameters of a LenNet CNN model fast and accurate. The proposed method was evaluated over the popular benchmark dataset MNIST for handwritten digit recognition. Experimental results showed an improvement of 36.87% in training time using the distributed WTO method compared to the baseline with a single learning agent, and the accuracy increases 4.69% more using the proposed method in contrast with the baseline. As this is a preliminary study towards the distributed WTO method for training CNN models, we anticipate this approach can be used in robotics, multi-agent systems, federated learning, complex optimization problems, and many others, where an optimization task is required to be solved fast and accurate.

关键词： Convolution neural network Wound Treatment Optimization distributed Metaheuristic Optimization MNIST Image Classification distributed Systems

来源：评论

学校读者我要写书评

暂无评论

PL-Transformer: a POS-aware and layer ensemble transformer for text classification

引用

neural COMPUTING & APPLICATIONS 2023年第2期35卷 1971-1982页

作者： Shi, Yu Zhang, Xi Yu, Ning Beijing Univ Posts & Telecommun Key Lab Trustworthy Distributed Comp & Serv BUPT Minist Educ Beijing Peoples R China

The transformer-based models have become the de-facto standard for natural language processing (NLP) tasks. However, most of these models are only designed to capture the implicit semantics among tokens without considering the extra off-the-shelf knowledge (e.g., parts-of-speech) to facilitate the NLP tasks. Additionally, despite using multiple attention-based encoders, they only utilize the embeddings from the last layer, ignoring that from other layers. To address these issues, in this paper, we propose a novel POS-aware and layer ensemble transformer neural network (named as PL-Transformer). PL-Transformer utilizes the parts-of-speech information explicitly and leverages the outputs from different encoder layers with correlation coefficient attention (C-Encoder) jointly. Moreover, we use correlation coefficient attention to bound dot product in C-Encoder, which improves the overall model performance. Extensive experiments on four datasets demonstrate that PL-Transformer can improve the text classification performance. For example, the accuracy on the MPQA dataset is improved by 3.95% over the vanilla transformer.

关键词： Text classification Transformer Part-of-speech Layer ensemble

来源：评论

学校读者我要写书评

暂无评论

OfpCNN: On-Demand Fine-Grained Partitioning for CNN Inference Acceleration in Heterogeneous Devices

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第12期34卷 3090-3103页

作者： Yang, Lei Zheng, Can Shen, Xiaoyuan Xie, Guoqi Hunan Univ Coll Comp Sci & Elect Engn Key Lab Embedded & Network Comp Hunan Prov Changsha 410082 Hunan Peoples R China Hunan Univ Res Inst Chongqing 401151 Peoples R China

Collaborative inference is a promising method for balancing the limited computational power of Internet of Things (IoT) devices with the huge computational demands of convolutional neural networks (CNNs). In this approach, a CNN is divided into multiple partitions and placed on multiple devices to run simultaneously. However, two major challenges are raised. (1) Computational latencies vary when the central processing unit (CPU) loads of devices are different. However, no suitable methods are available for accurately determining computation latencies on the basis of CPU utilization. (2) Existing methods partition a CNN model either vertically or horizontally. The granularity of these methods is extremely coarse and their accuracy is low. To address the aforementioned issues, this study proposes a distributed collaborative inference framework that supports a fine-grained partitioning scheme for CNN in heterogeneous devices (hereafter referred to as OfpCNN). First, the framework uses the layer latency prediction model based on floating-point operations and CPU load (FCPM) to accurately predict the computation latency of each layer of CNN in different devices. Subsequently, OfpCNN uses horizontal and vertical partitioning methods (HVPM) to partition the input feature maps and the structure of CNN respectively in accordance with network conditions and computing capacity, then assigns them to multiple devices for execution. The HVPM solution overall considers the execution position of the layer, parallelism, and location of devices responsible for data aggregation and distribution, which can consequently obtain more fine-grained partition schemes. Experimental results show that FCPM can achieve a minimum accuracy of 88% and HVPM can improve the inference speed by 1-2.54 times compared with other state-of-the-art methods.

关键词： Edge computing deep neural networks edge intelligence collaborative inference model partitioning

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-Based Classifier With Custom Feature-Extraction Layers for Digitally Modulated Signals

引用

IEEE TRANSACTIONS ON BROADCASTING 2024年第3期70卷 763-773页

作者： Snoap, John A. Popescu, Dimitrie C. Spooner, Chad M. Old Dominion Univ Dept Elect & Comp Engn Norfolk VA 23529 USA Distributed Spectrum New York NY USA NorthWest Res Associates Monterey CA 93940 USA

The paper presents a novel deep-learning (DL) based classifier for digitally modulated signals that uses a capsule network (CAP) with custom-designed feature extraction layers. The classifier takes the in-phase/quadrature (I/Q) components of the digitally modulated signal as input, and the feature extraction layers are inspired by cyclostationary signal processing (CSP) techniques, which extract the cyclic cumulant (CC) features that are employed by conventional CSP-based approaches to blind modulation classification and signal identification. Specifically, the feature extraction layers implement a proxy of the mathematical functions used in the calculation of the CC features and include a squaring layer, a raise-to-the-power-of-three layer, and a fast-Fourier-transform (FFT) layer, along with additional normalization and warping layers to ensure that the relative signal powers are retained and to prevent the trainable neural network (NN) layers from diverging in the training process. The classification performance and the generalization abilities of the proposed CAP are tested using two distinct datasets that contain similar classes of digitally modulated signals but that have been generated independently, and numerical results obtained reveal that the proposed CAP with novel feature extraction layers achieves high classification accuracy while also outperforming alternative DL-based approaches for signal classification in terms of both classification accuracy and generalization abilities.

关键词： Capsule networks cyclic cumulants digital communications deep learning signal classification

来源：评论

学校读者我要写书评

暂无评论

STUDY OF SPEECH EMOTION RECOGNITION USING BLSTM WITH ATTENTION 31

STUDY OF SPEECH EMOTION RECOGNITION USING BLSTM WITH ATTENTI...

引用

31st European Signal processing Conference, EUSIPCO 2023

作者： Sherman, Dalia Hazan, Gershon Gannot, Sharon Faculty of Engineering Bar-Ilan University Ramat Gan Israel

ISBN: (纸本)9789464593600

We present a study of a neural network-based method for speech emotion recognition that uses audio-only features. In the studied scheme, the acoustic features are extracted from the audio utterances and fed to a neural network that consists of convolutional neural networks (CNN) layers, bidirectional long short-term memory (BLSTM) combined with an attention mechanism layer, and a fully-connected layer. To illustrate and analyze the classification capabilities of the network, we used the t-distributed stochastic neighbor embedding (t-SNE) method. We evaluate our model using Ryerson audio-visual dataset of emotional speech and song (RAVDESS) and interactive emotional dyadic motion capture (IEMOCAP) datasets achieving weighted accuracy (WA) of 80% and 66%, respectively. © 2023 European Signal processing Conference, EUSIPCO. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Decentralized DNN Task Partitioning and Offloading Control in MEC Systems With Energy Harvesting Devices

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL processing 2023年第1期17卷 173-188页

作者： Wang, Feng Cai, Songfu Lau, Vincent K. N. Guangdong Univ Technol Sch Informat Engn Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China

In this paper, we study a decentralized deep neural network (DNN) task partitioning and offloading control problem for a multi-access edge computing (MEC) system with multiple wireless devices (WDs) powered by renewable energy sources. Instead of generic computational tasks, we focus on the case when the WDs and the MEC systems are computing DNN inferencing tasks. For each WD, we build a virtual local-computing CPU workload queue and an energy queue to model the DNN computation dynamics and the battery energy dynamics, respectively. We first introduce a new Lyapunov function based on the DNN tasks' cumulative execution latency and the total energy consumptions of the entire MEC system. Using a Lyapunov optimization approach, the DNN task partitioning and offloading control at the WDs are formulated as a Lyapunov drift minimization problem. To facilitate a distributed implementation, we exploit the linear structure of the cumulative latency and the independency of each WD's local-computing CPU rate, and we decompose the centralized Lyapunov drift minimization problem into multiple distributed subproblems, each of which is associated with a single WD. Next, we develop a parametric online learning algorithm such that each sub-Lyapunov drift minimization problem is solved locally at its associated WD. The proposed solution is completely decentralized in the sense that the sequential offloading and DNN task segmentation control at each WD is determined by its local battery energy queue state information (EQSI), the channel state information (CSI), and the DNN inferencing task workload queue state information (TQSI). Numerical results reveal that the proposed online learning algorithm can achieve significant performance gain over various state-of-the-art baselines.

关键词： Computation offloading deep neural network (DNN) inferencing energy harvesting Lyapunov optimization multi-access edge computing (MEC) parametric online learning

来源：评论

学校读者我要写书评

暂无评论

A 22-nm Delta-Sigma Computing-In-Memory SRAM Macro With Near-Zero-Mean Outputs and LSB-First ADCs for Edge AI processing

引用

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2025年

作者： Chen, Peiyu Zhao, Wentao Wu, Meng Shen, Linxiao Jia, Tianyu Huang, Ru Ye, Le Ma, Yufei Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou 311215 Peoples R China Peking Univ Inst Artificial Intelligence Beijing 100871 Peoples R China Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China

This work proposes a static random access memory (SRAM)-based delta-sigma computing-in-memory (Delta Sigma CIM) processor for edge intelligence applications in 22-nm CMOS technology. This Delta Sigma CIM processor effectively mitigates redundant operations associated with unchanged input features and adaptively adjusts computing-in-memory (CIM) outputs to achieve a near-zero-mean (NZM) distribution, thereby benefiting the energy-intensive analog-to-digital converters (ADCs). The proposed Delta Sigma CIM macro involves three main innovations at the architecture and circuit levels: first, it replaces absolute inputs with deltas computed from consecutive input values, resulting in a notable 35.8% reduction in energy consumption for the CIM array;second, the delta matrix-vector multiplications (MVMs) implemented by Delta Sigma CIM array can self-adaptively shift the analog CIM outputs to be NZM distributed, facilitating streamlined centralized data processing;and third, the introduction of a least significant bit first (LSB-first) ADC, whose number of conversions adjust dynamically based on instantaneous input values, allows for efficient analog output conversion of highly concentrated NZM analog data without compromising full-scale range or precision. Compared with state-of-the-art (SOTA) analog SRAM-based CIM macros, this work achieves superior area-energy efficiency product by 1.25x with up to 21.38 TOPS/W and 1.44 TOPS/mm(2) at full precision of 8b input, 8b weight, and 24b output, through bit-serial inputs and shifter-and-adder.

关键词： In-memory computing Energy efficiency Common Information Model (computing) Energy consumption Arrays neural networks Computational efficiency Computer architecture Random access memory Hardware Analog computing computing-in-memory edge computing neural network accelerator static random access memory (SRAM)

来源：评论

学校读者我要写书评

暂无评论

An ANN-Based Output-Error-Driven Incremental Model Predictive Control for Buck Converter Against Parameter Variations

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS 2024年第2期12卷 1230-1248页

作者： Xiang, Yangxiao Chung, Henry Shu-Hung Shen, Ruihua Lo, Alan Wai-Lun City Univ Hong Kong Ctr Smart Energy Convers & Utilizat Res Dept Elect Engn Hong Kong Peoples R China Chu Hai Coll Higher Educ Dept Comp Sci Hong Kong Peoples R China

DC/DC buck converters have been widely applied in the power processing of distributed energy resources (DERs) penetrated dc microgrid. Model predictive control (MPC) provides optimal control for the buck converter, but it often requires multiple sensors or complex observers to realize zero-steady-state-error control against parameter variations. An output-error-driven incremental MPC (OEDIMPC) for buck converter is proposed in this article. Different from the traditional concept of calculating the optimal duty cycle, the proposed MPC calculates the optimal rate of change of the duty cycle by using a reduced-state output-error-driven prediction model. As a result, the OEDIMPC achieves zero-steady-state-error control against parameter variations, including load value, input voltage, output inductor, and output capacitor, with significantly improved dynamic performance and minimal sensor and observer requirements. Besides, small- and large-signal analyses are used to study the stability boundary of the OEDIMPC under parameter variations, and a shallow layer artificial neural network (ANN) is utilized to realize the OEDIMPC on the hardware. The proposed technique has been evaluated experimentally on a buck converter with resistor load and constant power load (CPL), confirming its effectiveness.

关键词： Buck converters Inductors Observers Capacitive sensors Predictive models Capacitors Voltage control Artificial neural networks (ANNs) buck converter dc microgrids explicit model predictive control (EMPC) parameter variation sensorless

来源：评论

学校读者我要写书评

暂无评论

A predicted-loss based active learning approach for robust cancer pathology image analysis in the workplace

引用

BMC MEDICAL IMAGING 2024年第1期24卷 5页

作者： Kim, Mujin Robles, Willmer Rafell Quinones Ko, Young Sin Wong, Bryan Lee, Sol Yi, Mun Yong Korea Adv Inst Sci & Technol Grad Sch Data Sci Dept Ind & Syst Engn Daejeon South Korea Seegene Med Fdn Pathol Ctr Seoul South Korea

BackgroundConvolutional neural network-based image processing research is actively being conducted for pathology image analysis. As a convolutional neural network model requires a large amount of image data for training, active learning (AL) has been developed to produce efficient learning with a small amount of training data. However, existing studies have not specifically considered the characteristics of pathological data collected from the workplace. For various reasons, noisy patches can be selected instead of clean patches during AL, thereby reducing its efficiency. This study proposes an effective AL method for cancer pathology that works robustly on noisy *** proposed method to develop a robust AL approach for noisy histopathology datasets consists of the following three steps: 1) training a loss prediction module, 2) collecting predicted loss values, and 3) sampling data for labeling. This proposed method calculates the amount of information in unlabeled data as predicted loss values and removes noisy data based on predicted loss values to reduce the rate at which noisy data are selected from the unlabeled dataset. We identified a suitable threshold for optimizing the efficiency of AL through sensitivity *** compared the results obtained with the identified threshold with those of existing representative AL methods. In the final iteration, the proposed method achieved a performance of 91.7% on the noisy dataset and 92.4% on the clean dataset, resulting in a performance reduction of less than 1%. Concomitantly, the noise selection ratio averaged only 2.93% on each *** proposed AL method showed robust performance on datasets containing noisy data by avoiding data selection in predictive loss intervals where noisy data are likely to be distributed. The proposed method contributes to medical image analysis by screening data and producing a robust and effective classification model tailored for cancer pathology

关键词： Active learning strategy Noisy data Cancer pathology images Convolutional neural networks Deep learning Histopathology image analysis Predicted loss

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：