检索结果-内蒙古大学图书馆

29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

作者： Shi Jinfei Zhang Tianqi He Guanghong Hao Fei Nanjing Inst Technol Kangni Ind Technol Res Inst Nanjing Peoples R China Nanjing Inst Technol Sch Mech Engn Nanjing Peoples R China

ISBN: (纸本)9798350325621

With the increasing demand for intelligent security on various occasions, the detection of personnel behavior in a variety of environments has become a current research hotspot through new detection methods. Based on the recent popular deep learning techniques, this paper gives a detailed review of abnormal behavior detection. First, abnormal behavior detection based on machine vision is the focus of this review and divide the research progress of deep learning on this basis into two categories, convolutional neural network and autoencoder network. According to the characteristics of detection methods and applicable environment, the research methods of different categories are described and analyzed. Next, in the light of the situation of person gathering in different environments, some commonly used public datasets are listed, and the experiment results of various detection methods on each dataset are compared and analyzed. Finally, abnormal behavior detection trends are analyzed and prospected.

关键词： behavior detection convolutional neural network autoencoder network datasets

来源：评论

学校读者我要写书评

暂无评论

Optimization Strategies for the k-Nearest Neighbor Classifier

引用

SN Computer Science 2023年第1期4卷 47页

作者： Yepdjio Nkouanga, Hermann Vajda, Szilárd Department of Computer Science Portland State University 1825 SW Broadway Portland 97201 OR United States Department of Computer Science Central Washington University 400 University Way Ellensburg 98926 WA United States

In this paper, we propose six (6) fast and efficient classification schemes for different type of images (digits, objects, characters) using the classical k-nearest neighbor (kNN) classifier. It is common knowledge that kNN is one of the most popular supervised classification algorithm. However, for large data collections, the classification is time consuming because of the distance calculations which increase with the number of training samples and the data dimensionality. To reduce the number of training samples, we propose two techniques that employ the notions of convex envelope and stratified sampling. For the convex envelope, only the data points building the convex hull will serve as designated prototypes (training samples), thus reducing considerably the computational burden. To reduce the dimensionality of the data, we considered auto-encoder networks and vector embedding. The former is learning a way to compact data representation using statistical machine learning and the latter is changing the data itself emphasizing how each data sample is organized in space compared to others. The experiments on multiple benchmark data collections such as MNIST, Fashion-MNIST and Lampung characters show a considerable classification speed up (up to 32×) with no significant drop in accuracy when compared to results obtained using the complete data. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： autoencoder network Character recognition Classification Convex envelope Digit recognition k-Nearest neighbor Stratified sampling Vector embedding

来源：评论

学校读者我要写书评

暂无评论

A simple yet efficient unsupervised anomaly detection network for industrial machine 6

A simple yet efficient unsupervised anomaly detection networ...

引用

6th IEEE International Conference on Automation, Electronics and Electrical Engineering, AUTEEE 2023

作者： Wu, Danxuan Chen, Qijun Tongji University Shanghai China

ISBN: (纸本)9798350305623

Anomaly detection, aiming to detect items, events, or observations that do not match expected patterns or other items in a data set, is a crucial problem in many fields such as network intrusion detection, fraud detection and so on. Due to the rarity of labeled anomalous datasets, the research aims at detecting anomalies without anomalous samples and only using normal ones which called unsupervised learning. While traditional machine learning devoted to find a hard marginal between abnormal and normal ones, some unavoidable disturbance along with the signal can cause deviation. Moreover, the deep learning research of this subject focus on construct an autoencoder network only using normal data to memory the patterns of the normality. However, considering the generalization ability of neural network, it may occur that abnormal ones can reconstruct well thus leading the mistake of predicting. In this passage, to overcome the above two problem, we design a noise generator to simulate some reasonable noises, utilize and combine the neural network and memory bank to strengthen the ability of the network to memorize the patterns of the normal instances. We experiment and compare our algorithm on the MIMII sound anomaly dataset and the corresponding results shows the effectiveness and efficiency of our approach. It reaches 91.37 % in Accuracy and 93.76 % in F1 score. To our knowledge, it is the state of the art work up to now. © 2023 IEEE.

关键词： autoencoder network noise simulator unsupervised anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Organic and Recyclable Waste Classification Using Integrated Feature Selection Method

Organic and Recyclable Waste Classification Using Integrated...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Vijayaraj, A. Shreya, S. Deepana, G. Senthilvel, P. Gururama Jebakumar, R. Department of IT R.M.K Engineering College RSM Nagar Kavaraipettai Chennai601 206 India Department of Civil Engineering S.A. Engineering College Thiruverkadu Chennai600077 India Chennai602 105 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350305708

This paper suggests a new approach to enhancing waste classification performance using deep learning algorithms. Specifically, the proposed approach integrates an autoencoder network with a feature selection method in convolutional neural network models. This approach aims to identify valuable features from waste material images while reducing noise and improving the accuracy of the model. autoencoder networks are utilised to learn a compressed representation of input data, which can be used as a feature vector for classification tasks. The feature selection method is then applied to remove irrelevant features, improving the accuracy of the model. The proposed approach has the potential to provide an efficient and effective solution for waste classification tasks, contributing to sustainable waste management and environmental conservation. Experimental results demonstrate the effectiveness of the proposed approach in enhancing the accuracy of waste classification tasks. © 2023 IEEE.

关键词： autoencoder network sustainable waste management Waste classification

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-based model for forest disturbance detection using Landsat time series data

引用

International Journal of Digital Earth 2021年第9期14卷 1087-1102页

作者： Gaoxiang Zhou Ming Liu Xiangnan Liu Department of Information and Engineering Engineering University of People’s Armed PoliceXi’anPeople’s Republic of China School of Land Engineering Chang’An UniversityXi’anPeople’s Republic of China School of Information and Engineering China University of GeosciencesBeijingPeople’s Republic of China

Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration *** this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal *** autoencoder network is established and trained to reconstruct intact forest ***,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest *** assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,***,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the ***,comparing three common methods,the proposed model performs better,especially for intact forest detection *** study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.

关键词： Forest disturbance detection autoencoder network Unsupervised learning Landsat time series

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised DEnoising UltraSound network (DEUS-Net)

引用

IFAC-PapersOnLine 2024年第24期58卷 614-619页

作者： Christian Janorschke Jan Meyer Daniel Wulff

Ultrasound is one of the most widespread technologies for medical imaging. This is due to its many benefits, like being non-invasive, radiation free and portable. However, one of the biggest challenges for ultrasound is image quality due to speckle noise interfering with most image processing algorithms. Many mathematical methods are used to combat this, but modern neural networks offer new perspectives. In this paper, we propose a self-supervised neural network approach that enhances image quality for images from different anatomical domains and ultrasound systems, thus achieving domain translation, real-time computation and denoising performance on par with the best traditional algorithms.

关键词： Ultrasound imaging Image denoising AI Machine learning autoencoder network

来源：评论

学校读者我要写书评

暂无评论

Functional connectome fingerprinting: Identifying individuals and predicting cognitive functions via autoencoder

引用

HUMAN BRAIN MAPPING 2021年第9期42卷 2691-2705页

作者： Cai, Biao Zhang, Gemeng Zhang, Aiying Xiao, Li Hu, Wenxing Stephen, Julia M. Wilson, Tony W. Calhoun, Vince D. Wang, Yu-Ping Tulane Univ Biomed Engn Dept New Orleans LA 70118 USA Mind Res Network Albuquerque NM USA Univ Nebraska Med Ctr UNMC Dept Neurol Sci Omaha NE 68182 USA Emory Univ Georgia Inst Technol Georgia State Univ Triinst Ctr Translat Res Neuroimaging & Data Sci Atlanta GA USA

Functional network connectivity has been widely acknowledged to characterize brain functions, which can be regarded as "brain fingerprinting" to identify an individual from a pool of subjects. Both common and unique information has been shown to exist in the connectomes across individuals. However, very little is known about whether and how this information can be used to predict the individual variability of the brain. In this paper, we propose to enhance the uniqueness of individual connectome based on an autoencoder network. Specifically, we hypothesize that the common neural activities shared across individuals may reduce the individual identification. By removing contributions from shared activities, inter-subject variability can be enhanced. Our experimental results on HCP data show that the refined connectomes obtained by utilizing autoencoder with sparse dictionary learning can distinguish an individual from the remaining participants with high accuracy (up to 99.5% for the rest-rest pair). Furthermore, high-level cognitive behaviors (e.g., fluid intelligence, executive function, and language comprehension) can also be better predicted with the obtained refined connectomes. We also find that high-order association cortices contribute more to both individual discrimination and behavior prediction. In summary, our proposed framework provides a promising way to leverage functional connectivity networks for cognition and behavior study, in addition to a better understanding of brain functions.

关键词： autoencoder network common connectivity patterns functional connectivity high‐ level cognition prediction individual identification refined connectomes

来源：评论

学校读者我要写书评

暂无评论

Deep Monocular Depth Estimation Based on Content and Contextual Features

引用

SENSORS 2023年第6期23卷 2919-2919页

作者： Abdulwahab, Saddam Rashwan, Hatem A. Sharaf, Najwa Khalid, Saif Puig, Domenec Univ Rovira & Virgil Dept Comp Engn & Math Campus SesceladesAvinguda dels Paisos Catalans 26 Tarragona 43007 Spain

Recently, significant progress has been achieved in developing deep learning-based approaches for estimating depth maps from monocular images. However, many existing methods rely on content and structure information extracted from RGB photographs, which often results in inaccurate depth estimation, particularly for regions with low texture or occlusions. To overcome these limitations, we propose a novel method that exploits contextual semantic information to predict precise depth maps from monocular images. Our approach leverages a deep autoencoder network incorporating high-quality semantic features from the state-of-the-art HRNet-v2 semantic segmentation model. By feeding the autoencoder network with these features, our method can effectively preserve the discontinuities of the depth images and enhance monocular depth estimation. Specifically, we exploit the semantic features related to the localization and boundaries of the objects in the image to improve the accuracy and robustness of the depth estimation. To validate the effectiveness of our approach, we tested our model on two publicly available datasets, NYU Depth v2 and SUN RGB-D. Our method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy of 85%, while minimizing the error Rel by 0.12, RMS by 0.523, and log10 by 0.0527. Our approach also demonstrated exceptional performance in preserving object boundaries and faithfully detecting small object structures in the scene.

关键词： deep learning monocular depth estimation autoencoder network contextual semantic information

来源：评论

学校读者我要写书评

暂无评论

Extended-Aggregated Strategy for Hyperspectral Unmixing Based on Dilated Convolution

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2023年 20卷 1页

作者： Gao, Yuyou Pan, Bin Song, Xinyu Xu, Xia Nankai Univ Sch Stat & Data Sci KLMDASR LEBPS Tianjin 300071 Peoples R China Nankai Univ LPMC Tianjin 300071 Peoples R China Nankai Univ Coll Comp Sci Tianjin 300071 Peoples R China

autoencoder unmixing is a popular deep learning-based spectral unmixing algorithm, which decomposes the mixed pixels into pure endmembers and their fractional proportions, but the existing methods cannot fully exploit the spatial correlation features of hyperspectral image (HIS). In this letter, we propose a dilated convolution extended-aggregated strategy (DEAS), which enhances the ability of autoencoder unmixing algorithms to extract spatial correlation features. This strategy constructs a module utilizing various combinations of dilated convolutions with different scales. DEAS extracts the spatial relationships within multiple ranges around each pixel. Compared with the full connection and convolution commonly used in the encoder layers, autoencoder algorithms with DEAS expand the acceptance domain of the network. Furthermore, DEAS aggregates the spatial information in different ranges to obtain the feature map fully acquiring the relationship between pixels, which improves the unmixing performance. In particular, DEAS can be inserted into the existing autoencoder unmixing algorithms to get more abundant spatial information, and the methods using DEAS can show better unmixing effects. We apply the DEAS to two autoencoder methods using full connection and convolution, respectively. Experiments indicate the competitiveness of the algorithms using this strategy in hyperspectral unmixing tasks.

关键词： autoencoder network dilated convolution hyperspectral unmixing spatial correlation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Framework Applied For Predicting Anomaly of Respiratory Sounds

Deep Learning Framework Applied For Predicting Anomaly of Re...

引用

International Symposium on Electrical and Electronics Engineering (ISEE)

作者： Dat Ngo Lam Pham Anh Nguyen Ben Phan Khoa Tran Truong Nguyen VNU HCM HCMUT Dept Elect & Elect Engn Ho Chi Minh City Vietnam UT DUT Dept Elect & Elect Engn Da Nang City Vietnam

ISBN: (纸本)9781665414876

This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles. Initially, our framework starts with front-end feature extraction step. This step aims to transform the respiratory input sound into a two-dimensional spectrogram where both spectral and temporal features are well presented. Next, an ensemble of C-DNN and autoencoder networks is then applied to classify into four categories of respiratory anomaly cycles. In this work, we conducted experiments over 2017 Internal Conference on Biomedical Health Informatics (ICBHI) benchmark dataset. As a result, we achieve competitive performances with ICBHI average score of 0.49, ICBHI harmonic score of 0.42.

关键词： Respiratory disease wheeze crackle ensemble C-DNN autoencoder network

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：