检索结果-内蒙古大学图书馆

Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch

Journal of Shanghai Jiaotong University (science) 2025年 1-8页

作者： Huang, Shun Zhang, Yunxiang Fang, Zhihua Tang, Minrui Xu, Ruifeng He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The sound emitted by machines under abnormal working conditions exhibits various frequency patterns. Currently, the most advanced anomalous sound detection (ASD) approach is to apply a multi-head self-attention mechanism to the Log-Mel spectrogram for automatic frequency pattern analysis. However, the Log-Mel spectrogram may filter out high-frequency components of abnormal sounds;thus the use of self-attention mechanisms on Log-Mel spectrogram seems to have certain limitations. In this paper, we construct a simple convolutional neural network to extract comprehensive frequency features from raw audio to complement spectral-temporal information fusion. The parameters of this neural network are continuously updated during the training process to extract better frequency features for downstream classification neural networks in ASD. Additionally, a method for data augmentation in the batch dimension was developed to help the classification model learn both types of comprehensive features simultaneously. The proposed method achieved an AUC of 94.13% and a pAUC of 89.09% on the DCASE 2020 Challenge Task 2 dataset. Even when using only the features proposed in this paper, an AUC of 84.62% was achieved. (Figure presented.). © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Spectrogram Refinement Network for Robust Speaker Verification

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The accuracy and reliability of automatic speaker verification (ASV) face significant challenges in noisy environments. In recent years, joint training of speech enhancement front-end and ASV back-end has been widely applied to improve the robustness of ASV systems. Traditional joint training directly uses the enhanced speech features as the input of the back-end. However, the diversity of noise types and noise intensities will excessively suppress the enhanced features, resulting in speech distortion or residual noise. To alleviate this problem, we propose a dual-path spectrogram refinement network that enables the enhanced features to learn supplementary information from the separated noise features. In addition, we incorporate coordinate attention into the overall joint architecture to capture more comprehensive frequency and temporal information of the speaker from different spatial positions. We conduct extensive experiments on the VoxCeleb1 test set, the out-of-domain noise test set, and the VOiCES corpus. The experimental results demonstrate that our proposed method significantly improves the accuracy and robustness of speaker verification systems in both clean and noisy environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

MultiJSQ:Direct joint segmentation and quantification of left ventricle with deep multitask-derived regression network

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 175-192页

作者： Xiuquan Du Zheng Pei Ying Liu Xinzhi Cao Lei Li Shuo Li Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui UniversityHefeiChina School of Computer Science and Technology Anhui UniversityHefeiChina Department of Neurology Shuyang Affiliated Hospital of Nanjing University of Traditional Chinese MedicineSuqianChina Department of Biomedical Engineering Case Western Reserve UniversityClevelandOhioUSA

Quantitative analysis of clinical function parameters from MRI images is crucial for diagnosing and assessing cardiovascular ***,the manual calculation of these parameters is challenging due to the high variability among patients and the time-consuming nature of the *** this study,the authors introduce a framework named MultiJSQ,comprising the feature presentation network(FRN)and the indicator prediction network(IEN),which is designed for simultaneous joint segmentation and *** FRN is tailored for representing global image features,facilitating the direct acquisition of left ventricle(LV)contour images through pixel ***,the IEN incorporates specifically designed modules to extract relevant clinical *** authors’method considers the interdependence of different tasks,demonstrating the validity of these relationships and yielding favourable *** extensive experiments on cardiac MR images from 145 patients,MultiJSQ achieves impressive outcomes,with low mean absolute errors of 124 mm^(2),1.72 mm,and 1.21 mm for areas,dimensions,and regional wall thicknesses,respectively,along with a Dice metric score of *** experimental findings underscore the excellent performance of our framework in LV segmentation and quantification,highlighting its promising clinical application prospects.

关键词： global image features joint segmentation and quantification left ventricle(LV) multitask-derived regression network

来源：评论

学校读者我要写书评

暂无评论

Time series numerical association rule mining variants in smart agriculture

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16853-16866页

作者： Fister, Iztok Fister, Dušan Fister, Iztok Podgorelec, Vili Salcedo-Sanz, Sancho Faculty of Electrical Engineering and Computer Science University of Maribor Koroška cesta 46 Maribor2000 Slovenia Department of Signal Processing and Communications Universidad de Alcalá Alcalá de Henares Madrid28805 Spain

Numerical association rule mining offers a very efficient way of mining association rules, where algorithms can operate directly with categorical and numerical attributes. These methods are suitable for mining different transaction databases, where data are entered sequentially. However, little attention has been paid to the time series numerical association rule mining, which offers a new technique for extracting association rules from time series data. This paper presents a new algorithmic method for time series numerical association rule mining and its application in smart agriculture. We offer a concept of a hardware environment for monitoring plant parameters and a novel data mining method with practical experiments. The practical experiments showed the method’s potential and opened the door for further extension. © 2023, The Author(s).

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation for Improved Lossless Screen Content Compression 48

Image Segmentation for Improved Lossless Screen Content Comp...

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Uddehal, Shabhrish Reddy Strutz, Tilo Och, Hannah Kaup, André Coburg University Department of Electrical Engineering and Computer Science Coburg Germany Friedrich-Alexander University Multimedia Communications and Signal Processing Erlangen Germany

ISBN: (纸本)9781728163277

In recent years, it has been found that screen content images (SCI) can be effectively compressed based on appropriate probability modelling and suitable entropy coding methods such as arithmetic coding. The key objective is determining the best probability distribution for each pixel position. This strategy works particularly well for images with synthetic (textual) content. However, usually screen content images not only consist of synthetic but also pictorial (natural) regions. These images require diverse models of probability distributions to be optimally compressed. One way to achieve this goal is to separate synthetic and natural regions. This paper proposes a segmentation method that identifies natural regions enabling better adaptive treatment. It supplements a compression method known as Soft Context Formation (SCF) and operates as a pre-processing step. If at least one natural segment is found within the SCI, it is split into two subimages (natural and synthetic parts) and the process of modelling and coding is performed separately for both. For SCIs with natural regions, the proposed method achieves a bit-rate reduction of up to 11.6% and 1.52% with respect to HEVC and the previous version of the SCF. © 2023 IEEE.

关键词： lossless coding probability distribution screen content images segmentation soft context formation

来源：评论

学校读者我要写书评

暂无评论

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

Segmentation of CAD models using hybrid representation

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 188-202页

作者： Claude UWIMANA Shengdi ZHOU Limei YANG Zhuqing LI Norbelt MUTAGISHA Edouard NIYONGABO Bin ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peace-Bay Academy of Virtual Reality Shenyang 110004China China Aerospace Systems Engineering Corporation Beijing 100070China Department of Signal and Information Processing Beihang UniversityBeijing 100191China Department of Computer Science University of SherbrookeSherbrooke J1C0A1Canada

In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD *** previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point ***,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological ***,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation *** combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh *** complex CAD models,model segmentation is crucial for model retrieval and *** partial retrieval,it aims to segment a complex CAD model into several simple *** first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh *** second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD *** combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object *** study uses the Fusion 360 Gallery *** results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.

关键词： B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net

来源：评论

学校读者我要写书评

暂无评论

Remarks on Gibbs Permutation Matrices for Ternary Bent Functions 53

Remarks on Gibbs Permutation Matrices for Ternary Bent Funct...

引用

53rd IEEE International Symposium on Multiple-Valued Logic, ISMVL 2023

作者： Stanković, Radomir S. Stanković, Milena Moraga, Claudio Astola, Jaakko T. Mathematical Institute of Sasa Belgrade Serbia Faculty of Electronic Engineering Department of Computer Science Niš Serbia Technical University of Dortmund Faculty of Computer Science Dortmund Germany Tampere University of Technology Department of Signal Processing Tampere Finland

ISBN: (纸本)9781665464161

As in the binary case, ternary bent functions are a very small portion of the set of all ternary functions for a given number of variables. For example, for n = 2, there are 486 ternary bent functions out of 19683 ternary functions, which is 2, 47%, and this number reduces exponentially with the increase of n. However, finding, or alternatively, constructing them is a challenging task. A possible approach is based upon the manipulation of known ternary bent functions to construct other ternary bent functions. In this paper, we define Gibbs permutation matrices derived from the Gibbs derivative with respect to the Vilenkin-Chrestenson transform and propose their usage in constructing bent functions. The method can be extended to p-valued bent functions, where p is a prime larger than 3. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Face Anti-Spoofing Transformer (MFAST) 19

Multi-modal Face Anti-Spoofing Transformer (MFAST)

引用

19th International Bhurban Conference on Applied sciences and Technology, IBCAST 2022

作者： Samar, Abraar Raza Umer Farooq, M. Tariq, Tayyab Khan, Bostan Beg, Mirza Omer Mumtaz, Adeel Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Department of Control and Signal Processing Center of Excellence in Science and Applied Technologies Islamabad Pakistan

ISBN: (数字)9781665460514

ISBN: (纸本)9781665460514

Facial recognition systems are increasingly being adopted throughout the world for their ease-of-use and noninvasive nature, however, this convenience comes with its fair share of risks in the form of spoofing (presentation) attacks. Researchers have presented numerous classical and deep learning techniques for finding practicable solutions for the detection of presentation attacks. These techniques may use data from RGB, infrared (IR) or depth sensors. In this paper, we propose a novel multimodal face anti-spoofing (FAS) transformer (MFAST) approach that utilizes two separate transformer modules for RGB and Thermal (long-wave IR) sensors. The features from each of these transformer modules are fused together to detect spoofing attacks. The proposed methodology demonstrates better anti-spoofing performance as compared to existing FAS architectures. Due to the requirement of diverse amount of data to train FAS models, researchers have proposed numerous datasets that involve several types of presentation attacks in different modalities. By inspecting these datasets, we observe that there is little work done on the ethnic aspect of the persons involved. Most of the data gathered in these datasets is related to Caucasian, East Asian or African ethnicity with only a small amount of data pertaining to the South Asian descent. Therefore, keeping in view this gap within the available datasets, we have collected a new dataset that provides large number of subjects related to South Asian ethnicity with RGB and Thermal modalities. Hence, our contributions in this paper are two-fold;not only do we propose a transformer-based presentation attack detection model, but we also provide a new FAS dataset for South Asian ethnicity. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Context-Based Narrative Generation Transformer (NGen-Transformer) 19

Context-Based Narrative Generation Transformer (NGen-Transfo...

引用

19th International Bhurban Conference on Applied sciences and Technology, IBCAST 2022

作者： Raza Samar, Abraar Khan, Bostan Mumtaz, Adeel Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Department of Control and Signal Processing Center of Excellence in Science and Applied Technologies Islamabad Pakistan

ISBN: (数字)9781665460514

ISBN: (纸本)9781665460514

Text generation is an important domain of natural language processing where the plausibility of the generated text depends upon the context assimilation capabilities of the architecture being used. Recently the performance of automatic text generation task have greatly improved with the use of attention based language models. In this paper, we have explored the task of story generation based on some user defined context or prompt. We have proposed a GP2 based narrative generation architecture called NGen-Transformer. Our proposed architectures focuses specifically on the context provided by the user to produce meaningful stories. For the purpose of evaluation of our proposed model, we have used the WritingPrompts dataset which consists of a large number of human written sample stories based on corresponding titles or sentences (prompts). Experimental results show that our proposed NGen- Transformer model outperforms several sequence to sequence as well as attention based architectures on the task of story generation. © 2022 IEEE.

关键词： Natural language processing systems

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：