检索结果-内蒙古大学图书馆

adaptive segmentation Enhanced Asynchronous Federated Learning for Sustainable Intelligent Transportation Systems

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第7期25卷 6658-6666页

作者： Zhou, Xiaokang Liang, Wei Kawai, Akira Fueda, Kaoru She, Jinhua Wang, Kevin I-Kai Shiga Univ Fac Data Sci Hikone 5228522 Japan RIKEN RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan Hunan Univ Technol & Business Sch Adv Interdisciplinary Studies Changsha 410205 Peoples R China Hunan Univ Technol & Business Sch Management Sci & Engn Changsha 410205 Peoples R China Xiangjiang Lab Changsha 410205 Peoples R China Tokyo Univ Technol Sch Engn Tokyo 1920982 Japan Univ Auckland Dept Elect Comp & Software Engn Auckland 1010 New Zealand

The proliferation of advanced embedded and communication technologies has facilitated the possibility of modern Intelligent Transportation System (ITS). The hierarchical nature of such large-scale and distributed systems brings obvious challenges in creating a scalable and sustainable computing environment, and hence the development and application of edge intelligence become critical. Federated learning (FL), as an emerging distributed machine learning paradigm, aims to offer secure knowledge sharing and effective learning across multiple devices. However, conventional FL may fall into trouble when facing large-scale and network-agnostic systems with fast moving devices and changing network attributes. In this study, we propose an adaptive segmentation enhanced Asynchronous Federated Learning (AS-AFL) model, aiming to improve the learning efficiency and reliability in sustainable ITS via a decentralized fashion. Specifically, a meta-learning based adaptive segmentation scheme is designed to automatically separate the client nodes (e.g., vehicles) into multiple edge groups according to their homogeneous attributes. An integrated aggregation mechanism is then developed to realize the horizontal FL among a group of similar client nodes via the so-called intra-group synchronous aggregation, while allowing the vertical FL across different groups via the so-called inter-group asynchronous aggregation. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning and communication performance of our proposed model, compared with several conventional FL schemes in a distributed ITS application scenario.

关键词： Decentralized federated learning adaptive segmentation sustainable computing intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional flame temperature reconstruction through adaptive segmentation-weighted non-negative least squares and light field imaging

引用

OPTICAL ENGINEERING 2025年第5期64卷

作者： Ling, Tianxiang Hossain, Md. Moinul Chen, Guoqing Qi, Qi Zhang, Biao Xu, Chuanlong Southeast Univ Natl Engn Res Ctr Power Generat Control & Safety Sch Energy & Environm Nanjing Peoples R China Univ Kent Sch Engn Math & Phys Canterbury Kent England China Energy Sci & Technol Res Inst Co Ltd State Key Lab Low Carbon Smart Coal Fired Power Ge Nanjing Peoples R China

Existing flame temperature reconstruction algorithms experience significant performance degradation when subjected to radiation intensity noise interference, resulting in limited accuracy in low-temperature regions of flames with broad temperature distributions. We propose a three-dimensional (3D) flame temperature reconstruction algorithm by integrating adaptive segmentation-weighted non-negative least squares with light field imaging. Building on the non-negative least squares framework, the proposed algorithm introduces an adaptive strategy to improve the temperature reconstruction accuracy of low-temperature regions of flames. It also incorporates adaptive weight factors to reduce measurement errors caused by the extensive temperature range, enabling precise 3D temperature reconstruction. To validate the algorithm, numerical simulations of a bimodal asymmetric flame were performed to evaluate its noise tolerance and compare its performance with other existing algorithms. The simulation results indicated that the proposed algorithm demonstrates strong noise resistance, achieving similar to 70% higher reconstruction accuracy than the least-square QR decomposition algorithm. Experiments were carried out on bimodal flames to reconstruct the temperature under various combustion conditions. The reconstructed temperature showed good agreement with trends reported in the literature. Our results demonstrate the viability and robustness of the proposed algorithm for reconstructing broader temperature distributions of flames. (c) 2025 Society of Photo-Optical Instrumentation Engineers (SPIE) [DOI:10.1117/***.64.5.054112]

关键词： light field imaging flame temperature reconstruction algorithm adaptive segmentation

来源：评论

学校读者我要写书评

暂无评论

adaptive segmentation Network for Scene Text Detection 32nd

Adaptive Segmentation Network for Scene Text Detection

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Zhao, Guiqin Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China

ISBN: (纸本)9783031441912;9783031441929

Inspired by deep convolution segmentation algorithms, scene text detectors break the performance ceiling of datasets steadily. However, these methods often encounter threshold selection bottlenecks and have poor performance on text instances with extreme aspect ratios. In this paper, we propose to automatically learn the discriminate segmentation threshold, which distinguishes text pixels from background pixels for segmentation-based scene text detectors and then further reduces the time-consuming manual parameter adjustment. Besides, we design a Global-information Enhanced Feature Pyramid Network (GE-FPN) for capturing text instances with macro size and extreme aspect ratios. Following the GE-FPN, we introduce a cascade optimization structure to further refine the text instances. Finally, together with the proposed threshold learning strategy and text detection structure, we design an adaptive segmentation Network (ASNet) for scene text detection. Extensive experiments are carried out to demonstrate that the proposed ASNet can achieve the state-of-the-art performance on four text detection benchmarks, i.e., ICDAR 2015, MSRA-TD500, ICDAR 2017 MLT and CTW1500. The ablation experiments also verify the effectiveness of our contributions.

关键词： Text detection adaptive segmentation

来源：评论

学校读者我要写书评

暂无评论

OTSUCNV: an adaptive segmentation and OTSU-based anomaly classification method for CNV detection using NGS data

引用

BMC GENOMICS 2024年第1期25卷 1页

作者： Xie, Kun Ge, Xiaojun Alvi, Haque A. K. Liu, Kang Song, Jianfeng Yu, Qiang Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Xidian Univ Hangzhou Inst Technol Hangzhou 311200 Peoples R China

Copy-number variations (CNVs), which refer to deletions and duplications of chromosomal segments, represent a significant source of variation among individuals, contributing to human evolution and being implicated in various diseases ranging from mental illness and developmental disorders to cancer. Despite the development of several methods for detecting copy number variations based on next-generation sequencing (NGS) data, achieving robust detection performance for CNVs with arbitrary coverage and amplitude remains challenging due to the inherent complexity of sequencing samples. In this paper, we propose an alternative method called OTSUCNV for CNV detection on whole genome sequencing (WGS) data. This method utilizes a newly designed adaptive sequence segmentation algorithm and an OTSU-based CNV prediction algorithm, which does not rely on any distribution assumptions or involve complex outlier factor calculations. As a result, the effective detection of CNVs is achieved with lower computational complexity. The experimental results indicate that the proposed method demonstrates outstanding performance, and hence it may be used as an effective tool for CNV detection.

关键词： Copy number variation Next-generation sequencing adaptive segmentation OTSU Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Convolution and Multiscale Dilated EfficientNetB7-Based Plant Disease Detection and Classification with adaptive segmentation Procedures

引用

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS 2025年第0期

作者： Patil, Manesh P. Borse, Indrabhan S. P K Univ Dept Comp Sci & Engn Thanra 473665 Madhya Pradesh India

The economic success of the country is mainly dependent on crop growth. Diseases in crops are the greatest obstacle to food production. Early recognition of plant diseases is critical in the universe. In the standard diagnosis method, biologists directly assess each individual plant via onsite examinations. Nevertheless, physical crop illness examinations have some restrictions due to decreased precision and inadequate employee availability. To resolve these issues, there is a need to create automated systems that can recognize and classify the plant illnesses. New pathogens on the leaves of plants constantly appear because of plant structure and farming practices. Consequently, reliable identification and classification of leaf-related illnesses at their initial phases helps to prevent infection progression and promote plant productivity. The abundance of moderately strong data in the image environment and front, the significant color similarities in the unaffected and infected plant regions, the presence of distortion in sample images, and alterations in the location and dimension of foliage make plant leaf disease detection a challenging task. Therefore, an efficient deep model-based plant disease discovery and classification model is executed in this research work. Initially, the required image is acquired from online databases. The gathered images are then specified as input to the segmentation phase in which the adaptive and Attention-aided Mask Region-based Convolutional Neural Network (AAM-RCNN) is utilized. For enhanced segmentation performance, the parameters in the AAM-RCNN are optimized with the aid of the Boosted Random Parameter-based Golden Tortoise Beetle Optimizer (BRP-GTBO). The segmented images are taken for detection and classification process takes place with the aid of Hybrid Convolution Two-Dimension/One-Dimension (2D/1D) and Multi-scale Dilated EfficientnetB7 (HC-MDEB7). In the Hybrid Convolution (2D/1D) model, the color and morphological fea

关键词： adaptive segmentation plant disease detection and classification adaptive and attention aided mask region-based convolutional neural network boosted random parameter-based golden Tortoise Beetle Optimizer hybrid convolution (2D/1D) and multi-scale dilated EfficientNetB7

来源：评论

学校读者我要写书评

暂无评论

Non-Stationarity-Based adaptive segmentation Applied to Voice Disorder Discrimination

引用

IEEE ACCESS 2023年 11卷 54750-54759页

作者： Vieira, Vinicius J. D. Costa, Silvana C. Correia, Suzete E. N. Fed Inst Paraiba IFPB Elect Engn Grad Program BR-58015435 Joao Pessoa Paraiba Brazil

Voice disorders can affect people in all age groups. Vocal health is especially important when voice is used as a work tool, as in the fields of education (teachers), music (singers) and multimedia (journalists). Several researches based on linear and nonlinear models of speech production have attempted to identify the intrinsic characteristics in voices affected by pathologies of organic or functional origin. However, there has been no consensus thus far on the best measure to distinguish a healthy voice from a pathological voice, whether in the diagnosis or treatment phase of a disorder. A common procedure in feature extraction uses a traditional voice segmentation, based on stationary frame sizes. On the other hand, no studies have attempted to analyze how laryngeal pathologies can introduce non-stationary acoustic variations in voice. In this study, the Index of Non-Stationarity (INS) is used to identify frame sizes that can be considered truly stationary for each signal. Healthy voice signals and voice signals affected by pathologies such as paralysis, Reinke's edema and nodules are analyzed, and a comparative analysis of the traditional and INS-based adaptive segmentation is performed. Linear predictive coding (LPC) coefficients, mel-frequency cepstral coefficients (MFCC), gammatone-frequency cepstral coefficients (GFCC) and recurrence quantification measures (RQMs) are used as acoustic measures. Classification is carried out by performing a linear discriminant analysis (LDA). The results show that the proposed adaptive segmentation can increase pathology recognition (sensitivity) by up to 18%, for the linear model of speech production.

关键词： Acoustic analysis of voice adaptive segmentation feature extraction index of non-stationarity speech signal processing voice disorders

来源：评论

学校读者我要写书评

暂无评论

Simulation of Image Restoration Technology on Museum VR Platform Based on adaptive segmentation and Wireless Sensor Network

引用

MOBILE NETWORKS & APPLICATIONS 2025年第SUPPL1期30卷 27-27页

作者： Sun, Yong Wei, Wei Chen, Yi Ding, Chen Sang, Tianyi Nanjing Univ Sci Technol ZiJin Coll Sch Comp & Artificial Intelligence Nanjing 210023 Peoples R China Nanjing Vocat Univ Ind Technol Sch Arts & Design Nanjing 210007 Peoples R China

With the development of wireless sensor network (WSN) technology, image restoration technology based on WSN has gradually become a research hotspot. This paper aims to study the image restoration technology based on adaptive segmentation and wireless sensor network, and explore its application in museum VR platform to improve the accuracy and efficiency of image restoration. The image data is transmitted through wireless sensor network, and the collaborative processing ability of sensor nodes is used to restore the image. In this paper, the museum VR platform is built, and the research is simulated and tested. The experimental results show that the image restoration technology based on adaptive segmentation and wireless sensor network has a significant improvement in image quality and recovery speed. Compared with traditional methods, this technology can better maintain the details and texture of the image, and has higher stability and anti-interference ability, which can not only improve the virtual experience of users, but also provide strong support for the protection of cultural relics and digital management.

关键词： adaptive segmentation Wireless sensor network Museum VR platform Image recovery technology Simulation study

来源：评论

学校读者我要写书评

暂无评论

High-resolution bioprinting of complex bio-structures via engineering of the photopatterning approaches and adaptive segmentation

引用

BIOFABRICATION 2025年第2期17卷 025026-025026页

作者： Babayigit, Ceren Tavares-Negrete, Jorge Alfonso Esfandyarpour, Rahim Boyraz, Ozdal Univ Calif Irvine Dept Elect Engn & Comp Sci Irvine CA 92697 USA Univ Calif Irvine Dept Biomed Engn Irvine CA 92697 USA Univ Calif Irvine Dept Mech & Aerosp Engn Irvine CA 92697 USA

Digital light processing (DLP) technology has significantly advanced various applications, including 3D bioprinting, through its precision and speed in creating detailed structures. While traditional DLP systems rely on light-emitting diodes (LEDs), their limited power spectral density, high etendue, and spectral inefficiency constrain their performance in resolution, dynamic range, printing time, and cell viability. This study proposes and evaluates a dual-laser DLP system to overcome these limitations and enhance bioprinting performance. The proposed dual-laser system resulted in a twofold increase in resolution and a twelvefold reduction in printing time compared to the LED system. The system's capability was evaluated by printing three distinct designs, achieving a maximum percentage error of 1.16% and a minimum of 0.02% in accurately reproducing complex structures. Further, the impact of exposure times (10-30 s) and light intensities (0.044-0.11 mW mm-2) on the viability and morphology of 3T3 fibroblasts in GelMA and GelMA-poly(ethylene glycol) diacrylate (PEGDA) hydrogels is assessed. The findings reveal a clear relationship between longer exposure times and reduced cell viability. On day 7, samples exposed for extended periods exhibited the lowest metabolic activity and cell density, with differences of similar to 40% between treatments. However, all samples show recovery by day 7, with GelMA samples exhibiting up to a sixfold increase in metabolic activity and GelMA-PEGDA samples showing up to a twofold increase. In contrast, light intensity variations had a lesser effect, with a maximum variation of 15% in cell viability. We introduced a segmented printing method to mitigate over-crosslinking and enhance the dynamic range, utilizing an adaptive segmentation control strategy. This method, demonstrated by printing a bronchial model with a 14.43x compression ratio, improved resolution and maintained cell viability up to 90% for GelMA and 85% for GelMA-PEGDA du

关键词： adaptive segmentation 3D bioprinting Bronchial-tree bioprinting

来源：评论

学校读者我要写书评

暂无评论

Non-stationary clutter suppression method for bistatic airborne radar based on adaptive segmentation and space-time compensation

引用

IET RADAR SONAR AND NAVIGATION 2021年第9期15卷 1001-1015页

作者： Xiong, Yuanyi Xie, Wenchong Wuhan Radar Acad Key Res Lab 288 Huangpu St Wuhan 430019 Hubei Peoples R China

Bistatic airborne radar has excellent performance due to the separate transmitter and receiver, but its clutter distribution is usually non-stationary, which causes the performance of the traditional Space time adaptive processing (STAP) method to fail. Herein, firstly a bistatic airborne radar clutter signal model established, followed by an analysis of its clutter distribution characteristics in detail, and finally a bistatic airborne radar space-time compensation STAP method based on adaptive segmentation is proposed. The method first uses the distribution characteristics of the peak spectral centre in the first pulse data of the airborne radar to adaptively segment the clutter data, including extremely non-stationary, severely non-stationary, and non-stationary clutter regions. Then the clutter data are compensated based on the estimation value of the space-time peak spectrum centre. Finally, each range section is processed by using STAP, and the detected target Doppler frequency is adaptively moved. Simulation results verify the effectiveness of the proposed method.

关键词： radar signal processing space-time peak spectrum centre Radar theory airborne radar Electromagnetic compatibility and interference clutter distribution characteristics radar clutter space-time adaptive processing nonstationary clutter regions radar detection adaptive segmentation clutter data Radar equipment, systems and applications bistatic airborne radar space-time compensation STAP method traditional Space time adaptive processing method Signal processing and detection nonstationary clutter suppression method interference suppression

来源：评论

学校读者我要写书评

暂无评论

Research on adaptive segmentation and Collaborative Computing of Edge Intelligence Model in Power Edge Gateway 24

Research on Adaptive Segmentation and Collaborative Computin...

引用

Proceedings of the 7th International Conference on Information Technologies and Electrical Engineering

作者： Wei Zhang Peng Wang Zenghai Wang Jie Yang Feng Jiao Liguo Liu State Grid Information & Telecommunication Co. Ltd. Beijing Branch Beijng China

ISBN: (纸本)9798400707087

This paper proposes an edge intelligence model adaptive segmentation and collaborative computing method for power edge gateways to improve computing efficiency and resource utilization. First, an adaptive segmentation algorithm is studied and designed to effectively optimize the computational overhead and delay by adjusting the segmentation strategy of the model in real time. Next, the design of the collaborative computing framework realizes efficient data interaction between edge nodes, and uses advanced data exchange protocols to improve the reliability and speed of communication between nodes. Through empirical analysis, it has been verified that the model has significant performance improvements in application scenarios such as real-time fault detection, load forecasting, and smart meter reading analysis. Compared with traditional methods, the performance improvement rate reaches more than 20%. Experimental results show that the model proposed in this paper has high computational efficiency, resource utilization and task response capabilities, and can adapt to diverse power system application requirements. In summary, this article provides theoretical and practical support for the application of edge intelligence in power gateways and verifies its effectiveness in practical application scenarios.

关键词： adaptive segmentation

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：