检索结果-内蒙古大学图书馆

A novel electronic nose classification prediction method based on TETCN

SENSORS AND ACTUATORS B-CHEMICAL 2024年 405卷

作者： Wu, Fan Ma, Ruilong Li, Yiran Li, Fei Duan, Shukai Peng, Xiaoyan Southwest Univ Coll Artificial Intelligence Chongqing 400715 Peoples R China Chongqing Key Lab Brain Inspired Comp & Intelligen Chongqing 400715 Peoples R China Minist Educ Key Lab Luminescence Anal & Mol Sensing Chongqing 400715 Peoples R China

An efficient algorithm model is proposed to achieve good performance for gas detection based on electronic nose (E -nose) system. transformer encoder (TE) has been widely used in natural language processing and shown excellent performance in handling sequence data, which could help the model to learn the contextual information of E -nose data. Temporal Convolutional Network (TCN) is a novel convolutional neural network structure with a receptive field variable in length and the ability to capture long-term dependence, which is suitable for processing time series data. This work proposes a gas classification method based on TETCN which is composed of TE and TCN for processing the data of E -nose. Since hyperparameters have a significant impact on model performance, the Bayesian parameter optimization algorithm is used for TETCN. The data is weighted by TE, and then TCN can easily extract important features, resulting in a satisfactory classification accuracy of 99.8%. The experimental results indicate TETCN has better performance than the conventional methods such as convolutional neural network (CNN), long -short term memory (LSTM), and gated recurrent unit (GRU). Furthermore, network ablation has been implemented to demonstrate the necessity of combining TE and TCN. Finally, the feasibility of rapid detection of the proposed algorithm is discussed.

关键词： Electronic nose Classification transformer encoder Temporal Convolutional Network

来源：评论

学校读者我要写书评

暂无评论

A novel transformer-based DL model enhanced by position-sensitive attention and gated hierarchical LSTM for aero-engine RUL prediction

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-13页

作者： Chen, Xinping Chongqing Coll Elect Engn Coll Artificial Intelligence & Big Data Chongqing 401331 Peoples R China

Accurate prediction of remaining useful life (RUL) for aircraft engines is essential for proactive maintenance and safety assurance. However, existing methods such as physics-based models, classical recurrent neural networks, and convolutional neural networks face limitations in capturing long-term dependencies and modeling complex degradation patterns. In this study, we propose a novel deep-learning model based on the transformer architecture to address these limitations. Specifically, to address the issue of insensitivity to local context in the attention mechanism employed by the transformer encoder, we introduce a position-sensitive self-attention (PSA) unit to enhance the model's ability to incorporate local context by attending to the positional relationships of the input data at each time step. Additionally, a gated hierarchical long short-term memory network (GHLSTM) is designed to perform regression prediction at different time scales on the latent features, thereby improving the accuracy of RUL estimation for mechanical equipment. Experiments on the C-MAPSS dataset demonstrate that the proposed model outperforms existing methods in RUL prediction, showcasing its effectiveness in modeling complex degradation patterns and long-term dependencies.

关键词： RUL prediction transformer encoder Aero-engine Attention LSTM

来源：评论

学校读者我要写书评

暂无评论

Patch-transformer Network: A Wearable-Sensor-Based Fall Detection Method

引用

SENSORS 2023年第14期23卷 6360-6360页

作者： Wang, Shaobing Wu, Jiang Zhejiang Sci Tech Univ Sch Informat Sci & Engn Hangzhou 310018 Peoples R China

Falls can easily cause major harm to the health of the elderly, and timely detection can avoid further injuries. To detect the occurrence of falls in time, we propose a new method called Patch-transformer Network (PTN) wearable-sensor-based fall detection algorithm. The neural network includes a convolution layer, a transformer encoding layer, and a linear classification layer. The convolution layer is used to extract local features and project them into feature matrices. After adding positional coding information, the global features of falls are learned through the multi-head self-attention mechanism in the transformer encoding layer. Global average pooling (GAP) is used to strengthen the correlation between features and categories. The final classification results are provided by the linear layer. The accuracy of the model obtained on the public available datasets SisFall and UnMib SHAR is 99.86% and 99.14%, respectively. The network model has fewer parameters and lower complexity, with detection times of 0.004 s and 0.001 s on the two datasets. Therefore, our proposed method can timely and accurately detect the occurrence of falls, which is important for protecting the lives of the elderly.

关键词： fall detection deep learning feature extraction CNN transformer encoder

来源：评论

学校读者我要写书评

暂无评论

C3DBed: Facial micro-expression recognition with three-dimensional convolutional neural network embedding in transformer model

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期123卷

作者： Pan, Hang Xie, Lun Wang, Zhiliang Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

Facial micro-expression is often used for emotional recognition of people in a high-risk or pressure scene, which may reflect genuine emotions due to the low intensity of facial action units. Current methods focus on locating regions with emotional changes and cropping these regions for local feature extraction. However, these methods may lead to the problem of information redundancy caused by overlapping cropped regions. This paper proposes a novel three-dimensional convolutional neural network embedding in the transformer model (C3DBed). This model learns the attention weight of each local region of the micro-expression image, thereby perceiving the detail changes of the facial image and extracting robust local detail features. Solve the problem of model complexity and information redundancy caused by low-intensity local area positioning of facial muscle movement. The experiment results demonstrated that the proposed C3DBed model achieved competitive performance with accuracy rates of 78.04%, 77.64%, and 75.73% on SMIC, CASME II, and SAMM datasets, respectively.

关键词： Micro-expression recognition C3D embedding transformer encoder Attention weight

来源：评论

学校读者我要写书评

暂无评论

Heart Sound Classification Network Based on Convolution and transformer

引用

SENSORS 2023年第19期23卷 8168页

作者： Cheng, Jiawen Sun, Kexue Nanjing Univ Posts & Telecommun Coll Elect & Opt Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Flexible Elect Future Technol Nanjing 210023 Peoples R China Nation Local Joint Project Engn Lab RF Integrat & Nanjing 210023 Peoples R China

Electronic auscultation is vital for doctors to detect symptoms and signs of cardiovascular diseases (CVDs), significantly impacting human health. Although progress has been made in heart sound classification, most existing methods require precise segmentation and feature extraction of heart sound signals before classification. To address this, we introduce an innovative approach for heart sound classification. Our method, named Convolution and transformer encoder Neural Network (CTENN), simplifies preprocessing, automatically extracting features using a combination of a one-dimensional convolution (1D-Conv) module and a transformer encoder. Experimental results showcase the superiority of our proposed method in both binary and multi-class tasks, achieving remarkable accuracies of 96.4%, 99.7%, and 95.7% across three distinct datasets compared with that of similar approaches. This advancement holds promise for enhancing CVD diagnosis and treatment.

关键词： electronic auscultation CVDs heart sound classification neural network one-dimensional convolution transformer encoder

来源：评论

学校读者我要写书评

暂无评论

Generalizable and Robust Log Anomaly Detection Based on transformer 18th

Generalizable and Robust Log Anomaly Detection Based on Tr...

引用

18th China Conference on Wireless Sensor Networks, CWSN 2024

作者： Lou, Zhaoyang Chai, Xiaolin Shang, Ce Sun, Yan Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9789819621859

Log anomaly detection plays a crucial role in maintaining the security and reliability of Internet of Things devices. Unsupervised deep learning methods have made significant progress in anomaly detection by modeling normal log sequences. However, the approach of only considering the normal patterns of sequences leads to limited generalization ability of the model. To address this problem, we propose GRLog to enhance the performance and generalization ability of anomaly detection models based on log sequences. First, we introduce auxiliary datasets to enhance the model’s ability to represent log sequences when learning the local and global information of log sequences based on transformer. Second, we propose a similar log detection method to handle previously unseen logs. GRLog achieves higher F1 scores on three public datasets and their evolution datasets, which shows that our proposed model can better detect anomalies in log sequences and effectively address log evolution. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anomaly Detection Generalization Ability Log Evolution transformer encoder

来源：评论

学校读者我要写书评

暂无评论

Another scale-guided parallel transformer for image aesthetic assessment

引用

JOURNAL OF ELECTRONIC IMAGING 2023年第2期32卷 023035-023035页

作者： Shen, Lili Xu, Shaohu Zhang, Jing Peng, Bo Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Tianjin Univ Tianjin Int Engn Inst Tianjin Peoples R China

Image aesthetic assessment (IAA) is a challenging task in computer vision fields, which aims to automatically evaluate image beauty by simulating human perception on image aesthetic. With the development of deep learning, although convolutional neural network (CNN)-based IAA approaches have achieved extraordinary progress, CNN experiences difficulty to capture long-distance relationships among visual elements. There is a strong correlation between image layout and image semantic information for image aesthetic. In order to solve this problem, an another scale-guided parallel transformer is proposed, including a multiscale local feature extractor (ME), a feature projection (FP), and an another scale-guided parallel feature fusion transformer (AST). The ME captures primary local features with classic ResNet at multiple scales. The FP performs dimension transformation on feature maps for each scale, which can obtain feature token and aesthetic token. The AST with two parallel transformer encoders is exploited to highlight the significant regions in the holistic image, in which the feature tokens and the aesthetic token from another scale are grouped together to obtain interscale guidance. The final score distribution is achieved by weighting multiple aesthetic tokens with learnable parameters for unified aesthetics assessment. Extensive experiments on two public datasets, including aesthetic visual analysis and aesthetics and attributes database, demonstrate that the proposed method outperforms the state-of-the-art methods across three different tasks.

关键词： image aesthetic assessment scale guidance global and local features transformer encoder long-distance dependence

来源：评论

学校读者我要写书评

暂无评论

Graph attention network with dynamic representation of relations for knowledge graph completion

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期219卷

作者： Zhang, Xin Zhang, Chunxia Guo, Jingtao Peng, Cheng Niu, Zhendong Wu, Xindong Beijing Inst Technol Sch Comp Sci & Technol Beijing 100381 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ China Hefei 230009 Anhui Peoples R China

Knowledge graph completion (KGC) aims to predict the missing element in a triple based on known triples or facts. Recently, plenty of representation learning methods for KGC have achieved the promising performance, especially ones based on graph neural networks and their variants. Those methods exploit local neighborhood information to update the embedding of target entities. However, the existing works have the following two problems. First, those approaches focus on the representation learning of entities, while the relation representation usually adopts a simple linear transformation, which cannot capture the distinctive semantic intensions of the same relation in different triples. Second, different types of entity information are simply combined together, resulting in the loss of global properties including the type and the global importance of entities, which is prone to cause over smoothing phenomenon. To address these two problems, we propose a Graph Attention Network with Dynamic representation of Relations and global information (DRR-G VI) for knowledge graph completion. Specifically, the task of dynamic representation of relations is to learn the distinctive representation of the same relation in different triples. This goal is achieved via a path transformer. To this end, path transformer is designed to take the path information as its input, where only those paths from the target entity to the neighborhood relations with the same type as the target relation are considered. Sequentially, the mechanism of global embeddings is incorporated into graph attention network to capture the global information of entities and relations. Experimental performance outperforms the state-of the-art methods, indicating the effectiveness of our proposed approach.

关键词： Knowledge graph completion Dynamic representation of relation Global information embedding transformer encoder Graph attention network

来源：评论

学校读者我要写书评

暂无评论

EfficientNet-based multi-dimensional network optimization for Deepfake video detection 23

EfficientNet-based multi-dimensional network optimization fo...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Yong Zhang Xinqi Zhang Bingjie Li School of Computer Science and Technology Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

The rapid development of deep learning techniques, especially generative adversarial networks, has led to the generation of very realistic forged faces. Deepfake technology has brought convenience to society and also produced a large number of undesirable effects. Many detectors have been developed to defend videos generated by Deepfake manipulation techniques. In this paper, we take low overhead and high performance as the task of Deepfake detection and propose a new EfficientNet-B0 combined with ViT Deepfake detection network, which consists of two key components: (1) ConvFFN block, which brings a larger receptive field to the network; (2) transformer encoder with Hilo, which separates the high and low frequencies of the attention layer to focus on the global structure. We conducted extensive experiments on the DFDC dataset and the FF++ dataset to demonstrate the stability and practical applicability of the proposed method.

关键词： ConvFFN Deepfake HiLo transformer encoder

来源：评论

学校读者我要写书评

暂无评论

基于自适应位置编码的心电图重构算法

引用

中国医学物理学杂志 2023年第10期40卷 1285-1290页

作者：纪洁维常胜王豪黄启俊武汉大学物理科学与技术学院湖北武汉430072

可穿戴心电检测的主要挑战是较多导联影响被测者的身体活动,如果减少导联会使心电数据信息减少使检测效果变差。为了平衡被测者日常穿戴舒适性和检测准确性,笔者设计了一个基于transformer encoder的自适应相对位置编码重构算法,通过前... 详细信息

可穿戴心电检测的主要挑战是较多导联影响被测者的身体活动,如果减少导联会使心电数据信息减少使检测效果变差。为了平衡被测者日常穿戴舒适性和检测准确性,笔者设计了一个基于transformer encoder的自适应相对位置编码重构算法,通过前后重叠的切片方式使相邻片段的信息具备关联性,相对位置编码时加入可训练参数对任意片段进行重构,从而有效地提取位置信息。用3个导联的EGG信号重构标准12导联EGG信号,实验结果表明,重构的ECG数据均方根误差低至0.02758,平均相关系数高达98.43%,显示出本文算法在应用于可穿戴心电检测设备的应用前景。

关键词：心电图重构位置编码 transformer encoder

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：