检索结果-内蒙古大学图书馆

Deep autoencoder for false positive reduction in handgun detection

NEURAL COMPUTING & APPLICATIONS 2021年第11期33卷 5885-5895页

作者： Vallez, Noelia Velasco-Mata, Alberto Deniz, Oscar Univ Castilla La Mancha ETSI Ind VISILAB Ave Camilo Jose Cela SN Ciudad Real 13071 Spain

In an object detection system, the main objective during training is to maintain the detection and false positive rates under acceptable levels when the model is run over the test set. However, this typically translates into an unacceptable rate of false alarms when the system is deployed in a real surveillance scenario. To deal with this situation, which often leads to system shutdown, we propose to add a filter step to discard part of the new false positive detections that are typical of the new scenario. This step consists of a deep autoencoder trained with the false alarm detections generated after running the detector over a period of time in the new scenario. Therefore, this step will be in charge of determining whether the detection is a typical false alarm of that scenario or whether it is something anomalous for the autoencoder and, therefore, a true detection. In order to decide whether a detection must be filtered, three different approaches have been tested. The first one uses the autoencoder reconstruction error measured with the mean squared error to make the decision. The other two use thek-NN (k-nearest neighbors) and one-class SVMs (support vector machines) classifiers trained with the autoencoder vector representation. In addition, a synthetic scenario has been generated with Unreal Engine 4 to test the proposed methods in addition to a dataset with real images. The results obtained show a reduction in the number of false positives between 22.5% and 87.2% and an increase in the system's precision of 1.2%-47% when the autoencoder is applied.

关键词： Handgun detection False positive reduction autoencoder One-class classification

来源：评论

学校读者我要写书评

暂无评论

Data generation scheme for photovoltaic power forecasting using Wasserstein GAN with gradient penalty combined with autoencoder and regression models

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 257卷

作者： Park, Sungwoo Moon, Jaeuk Hwang, Eenjun Korea Univ Sch Elect Engn Seoul 02841 South Korea

Machine learning and deep learning (DL)-based forecasting models have shown excellent predictive performances, but they require a large amount of data for model construction. Insufficient data can be augmented using generative adversarial networks (GANs), but these are not effective for generating tabular data. In this paper, we propose a novel data generation scheme that can generate tabular data for photovoltaic power forecasting (PVPF). The proposed scheme consists of the Wasserstein GAN with gradient penalty (WGAN-GP), autoencoder (AE), and regression model. AE guides the WGAN-GP to generate input variables similar to the real data, and the regression model guides the WGAN-GP to generate output variables that well reflect the relationship with the input variables. We conducted extensive comparative experiments with various GAN-based models on different datasets to verify the effectiveness of the proposed scheme. Experimental results show that the proposed scheme generates data similar to real data compared to other models and, as a result, improves the performance of PVPF models. Especially the deep neural network showed 62% and 70% improvements in mean absolute error and root mean squared error, respectively, when using the data generated through the proposed scheme, indicating the effectiveness of the proposed scheme in DL-based forecasting models.

关键词： Smart Grid Photovoltaic Power Forecasting Wasserstein Generative Adversarial Network with Gradient Penalty autoencoder Regression Model

来源：评论

学校读者我要写书评

暂无评论

Transfer-AE: A novel autoencoder-based impact detection model for structural digital twin

引用

APPLIED SOFT COMPUTING 2024年 166卷

作者： Han, Chengjia Wang, Zixin Fu, Yuguang Dyke, Shirley Shahriar, Adnan Nanyang Technol Univ Sch Civil & Environm Engn Singapore 639798 Singapore Purdue Univ Lyles Sch Civil Engn W Lafayette IN 47907 USA L&T Technol Serv Plano TX 75093 USA

Accurately detecting the location and intensity of impacts is crucial for ensuring structural safety. Currently, AIbased structural impact detection methods are widely used for their excellent detection accuracy. However, their generalization capability is limited by the scenarios present in the training data. Many complex and dangerous impact scenarios are difficult to conduct real-world experiments on to collect sufficient samples. To capture all impact scenarios and fully leverage the advantages of AI-based detection technologies, advanced methods involve combining real-world structural monitoring data with corresponding numerical models to construct digital twins. These methods continuously refine the created numerical models with limited real-world data and provide diverse impact scenarios through numerical model simulations. However, there are inevitable differences between digital models and physical models that are challenging to correct through mechanical means. This discrepancy in data distribution between the two models significantly hinders the application of digital twin technology in impact/event identification tasks. To address this challenge, this study proposes a novel model based on autoencoders, named Transfer-AE. Transfer-AE encodes the common features of digital twins in the latent space to bridge the uncertainty gap at a macro scale between numerical models and physical models and synchronously fits the magnitude and location of the impact load in the decoder. This enables consistent detection results for the same impact event, whether the sample comes from the numerical model or the physical model. Transfer-AE includes two operating modes: Mode 1 has a fixed computational complexity with stable inference speed, but the training cost and difficulty increase with data distribution. Mode 2's computational complexity increases with data distribution, but it has a fixed training cost and speed. In both cases involving the geodesic dome structure si

关键词： Digital Twin Impact quantification Impact localization Transfer learning autoencoder Generative network Domain adaptive

来源：评论

学校读者我要写书评

暂无评论

Model-Free Multiphase AC Signals Downscaling Method Using Orthogonal Phase-Lock autoencoder and Circular Harmonic Decomposition

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2024年第7期72卷 6573-6582页

作者： Qi, Xing Qiu, Tingting Aarniovuori, Lassi Zhang, Qian Xu, Jiazi Cao, Wenping Anhui Univ Dept Elect Engn Hefei 230601 Peoples R China LUT Univ Elect Drives Lab Lappeenranta 53850 Finland

Reference frame transformation methods are generally introduced in multiphase ac systems, so as to simplify system's high dimensional ac signals into low dimensional dc ones. Classical methods, such as Clark/Park transformations, are used in balanced systems whose models are known, but not suitable for model-unknown systems which may contain unbalanced components. To address this issue, this article proposes a model-free method, that can downscale both balanced and unbalanced multiphase ac signals into dc ones, without any access to prior model knowledge. The proposed method follows the principles of low rank and sparsity, and consists of two components: 1) a phase-lock orthogonal autoencoder is designed, to transform multiphase ac signals into two-phase orthogonal ac signals;2) a circular harmonic decomposition is introduced, to further simplify two-phase orthogonal ac signals into some dc constant values. The effectiveness of the proposed method is validated on a real-world model-unknown system, and the experimental results also indicate that the proposed method benefits of discovering some potential patterns of the system, which is helpful for an in-depth study of model-unknown systems. Comparative studies show that the proposed method is superior to classical methods in terms of interpretability, information integrity and scalability in model-unknown scenarios.

关键词： Harmonic analysis Vectors Power system harmonics Standards Induction motors Transforms Rotors Permanent magnets Gold Feature extraction autoencoder circular harmonic function decomposition model-free multiphase systems signal downscaling

来源：评论

学校读者我要写书评

暂无评论

Atrial fibrillation detection on reconstructed photoplethysmography signals collected from a smartwatch using a denoising autoencoder

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期237卷

作者： Mohagheghian, Fahimeh Han, Dong Ghetia, Om Chen, Darren Peitzsch, Andrew Nishita, Nishat Ding, Eric Y. Otabil, Edith Mensah Noorishirazi, Kamran Hamel, Alexander Dickson, Emily L. Dimezza, Danielle Tran, Khanh-Van Mcmanus, David D. Chon, Ki H. Univ Connecticut Dept Biomed Engn Storrs CT 06269 USA Univ Connecticut Hlth Dept Publ Hlth Sci Farmington CT USA Univ Massachusetts Div Cardiol Med Sch Worcester MA USA Des Moines Univ Coll Osteopath Med Des Moines IA USA

Photoplethysmography (PPG) signals collected by wearables have been shown to be effective in accurate detection of atrial fibrillation (AF), provided that the data are devoid of motion and noise artifacts (MNA). Many studies have been previously conducted to detect AF arrhythmia using PPG data;however, the subjects were mostly in clinics or controlled settings with data collection lasting several minutes to at most several hours with minimal MNA. Our study, Pulsewatch, differs from previous AF studies in that PPG data from smartwatches prescribed to stroke survivors were continuously collected for two weeks in real-life conditions, which invariably included a significant amount of MNA. Our aim is to provide a framework for a novel use of a denoising autoencoder to reconstruct motion-artifact-removed PPG signals so that we can improve the AF detection per-formance and to increase the amount of analyzable *** used more than 30,000 25-sec PPG segments from 129 subjects randomly selected from Pulsewatch and Stanford University's datasets. The training and testing datasets from these two databases came from smart-watches from different vendors with varying sampling frequencies and time duration of recordings in diverse and realistic settings. In this study, the highly corrupted PPG data were automatically detected and discarded, but those segments contaminated with low-to-moderate motion and noise artifacts (MNA) were subjected to a convolutional denoising autoencoder (CDA). To reconstruct the artifact-removed PPG segments, we proposed to employ two distinct CDA models for AF and non-AF data groups initially classified as AF or non-AF. Using the proposed approach, we significantly improved the performance of detecting occult AF. We achieved classifica-tion accuracy, sensitivity, and specificity of 91.02%, 91.54%, and 90.85%, respectively, for out-of-sample test data from both databases. By sanitizing data from low-to-moderate MNA, we were able to increase the usable

关键词： Photoplethysmography Atrial fibrillation Deep learning Denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Modeling and spatio-temporal analysis on CO2 emissions in the Guangdong-Hong Kong-Macao greater bay area and surrounding cities based on neural network and autoencoder

引用

SUSTAINABLE CITIES AND SOCIETY 2024年 103卷

作者： Luo, Xichun Liu, Chengkun Zhao, Honghao Macau Univ Sci & Technol Inst Sustainable Dev Taipa 999078 Macao Peoples R China Macau Univ Sci & Technol Sch Business Taipa 999078 Macao Peoples R China

Significant attention has been given to the issue of CO2 emissions worldwide, especially for China as the largest emitter. Cities, as the main carriers of China's economic development, account for up to 85 % of CO2 emissions from energy use in the country. The Guangdong-Hong Kong-Macao Greater Bay Area (GBA) and surrounding cities play important leading roles in low-carbon development. However, compiling city-level CO2 emissions is challenging due to the limited availability of data. In this paper, a new idea is proposed by using SSA-BP for estimating provincial-level CO2 emissions and downscaling provincial-level CO2 emissions to city-level CO2 emissions by reconstructing missing values of city-level CO2 emissions with an autoencoder. This study compiles a city-level CO2 emissions inventory and conducts a spatio-temporal analysis of CO2 emissions in the GBA and surrounding cities. The results show that CO2 emissions exhibit a spatial distribution pattern with spatial dependence. Furthermore, according to the analysis of spatio-temporal heterogeneity, GDP influenced CO2 emissions the most within the five influencing factors, and the influences of GDP, population, and energy intensity were mainly positive, while the influence of patents was mainly negative, and that of trade was both positive and negative.

关键词： Guangdong-Hong Kong -Macao Greater Bay area CO 2 emissions inventory Neural network autoencoder Geographically and temporally weighted regression

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Image Inpainting Using autoencoder 5

Low Complexity Image Inpainting Using AutoEncoder

引用

5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)

作者： Elbehery, Abeer Fahmy, Yasmine Kafafy, Mai Cairo Univ Fac Engn Giza 12613 Egypt

ISBN: (纸本)9781665482370

Image inpainting is filling the missing or corrupted pixels in an image in a realistic way that cannot be differentiated by human eye. Deep learning is widely used in image inpainting and it exhibits better performance than classical inpainting methods, but it requires high processing resources and longer time to train the model. In this paper, we propose an autoencoder architecture that outperforms other deep learning techniques in literature methods with lower processing and time complexity.

关键词： Image inpainting autoencoder Skip connections Low complexity Adam optimizer

来源：评论

学校读者我要写书评

暂无评论

EXTRACTING RELEVANCE FROM SAR TEMPORAL PROFILES ON A GLACIER AND AN ALPINE WATERSHED BY A DEEP autoencoder 24

EXTRACTING RELEVANCE FROM SAR TEMPORAL PROFILES ON A GLACIER...

引用

24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow

作者： Charrier, Laurane di Martino, Thomas Koeniguer, Elise Colin Weissgerber, Flora Plyer, Aurelien Univ Paris Saclay DTIS ONERA Gif Sur Yvette France Univ Savoie Mt Blanc LISTIC Annecy France Univ Paris Saclay Cent Supelec SONDRA Gif Sur Yvette France

This paper proposes to use methods for compressing the temporal profiles of Sentinel-1 images, in order to be able to evaluate and analyze the richness of the temporal dynamics, both on a glacier and on a watershed. We propose to use unsupervised deep learning to auto-encode the temporal information in 3 dimensions, allowing to use the three descriptors as three RGB components to produce a colored composition synthesizing the information. We compare this Convolutional autoencoder (CAE) approach with a dimensionality reduction based on a Principal Component Analysis (PCA) of the temporal profiles. The two methods, CAE and PCA, are applied to a time series over the Kyagar Glacier before and after a surge event, and on an alpine watershed to compare the differences in dynamic evolution associated with different terrain classes with and without snow. On the one hand, on the glacier, the stacks of 10 images used are too short for CAE to extract more than two really significant axes. On the other hand, with longer profiles available over the alpine watershed, the CAE is interesting to improve the clustering results obtained from the decomposition.

关键词： deep learning autoencoder glacier visualization surge clustering

来源：评论

学校读者我要写书评

暂无评论

DEEP autoencoder FOR ULTRASOUND-BASED RAIL FLAW DETECTION

DEEP AUTOENCODER FOR ULTRASOUND-BASED RAIL FLAW DETECTION

引用

Joint Rail Conference (JRC) on Kicking Off the Next 100 Years of Rail Innovation

作者： Wu, Yuning Zhu, Xuan Baillargeon, Jay Univ Utah Salt Lake City UT USA Fed Railroad Adm Pueblo CO USA

ISBN: (纸本)9780791885758

Safety is the principal concern of the railway industry, and rail internal defects can pose significant risks to safe and efficient railroad operations. Effective rail flaw detection, especially for transverse defects, is critical to prevent accidents and derailments due to broken rails. Both industrial and research communities have invested much effort in solving this problem. For example, the rail industry relies heavily on ultrasonic bulk waves and, more recently, began exploring ultrasonic guided waves for rail internal defect detection. This study developed an improved semi-supervised learning algorithm based on a deep autoencoder (DAE) for ultrasoundbased rail flaw detection. The DAE algorithm identifies observations in a dataset that deviate significantly from the remaining observations. First, the team trained a DAE to reconstruct ultrasonic signals obtained from clean rail segments. To improve the robustness for defect detection, we then optimized the architecture and hyperparameters of the DAE models. Also, we adopted mean squared error (MSE) as a feature to highlight rail defects. Lastly, the team fed the test set of ultrasonic signals into the trained DAE model and evaluated its capability for rail defect detection. We found the proposed DAE can support a superior and robust ultrasonic rail defect detection capability compared to conventional knowledge-driven approaches.

关键词： Anomaly Detection Rail Defect Detection autoencoder Feature Learning Structural Health Monitoring

来源：评论

学校读者我要写书评

暂无评论

Probability Correlation Learning for Anomaly Detection based on Distribution-Constrained autoencoder 23

Probability Correlation Learning for Anomaly Detection based...

引用

23rd Asia-Pacific Network Operations and Management Symposium (APNOMS)

作者： Wu, Jihua Zhang, Lei Liu, Cong Qi, Qi Wang, Jingyu Xu, Tong Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China China United Telecommun Co Ltd Beijing Peoples R China China Mobile Res Inst Beijing Peoples R China

ISBN: (数字)9784885523397

ISBN: (纸本)9784885523397

Network anomaly detection provides a reliable and stable service to detect faults and prevent security attacks effectively. However, existing detection methods still encounter many challenges. The supervised learning method is unsuitable because the anomaly samples are seriously sparse and hard to label. Unsupervised learning, as a promising method, is widely used while the discriminative features are ignored when reconstructing from the normal feature space. This paper proposes a novel probability correlation learning based on autoencoder called PCDetect, a semi-supervised learning method. Since we assumed the anomaly samples deviate from the distribution of normal samples, approximating the distribution of original data is proposed as an efficient preprocessing methodology to capture the discriminative features. Moreover, an encoder-decoder neural network associated with the proposed loss function is designed to learn the low-dimensional feature representation from raw data and constrain the latent representation to follow different referenced distributions based on a few anomaly labels. In this way, The correlation of the referenced distribution and the reconstruction of latent representation will be used to quantify the probability of anomaly. Extensive experiments are conducted on two public real-world datasets, NSL-KDD and UNSW-NB15. Results show the proposed PCDetect can efficiently cope with the imbalance and high-dimensional issues compared with several popular supervised learning methods, significantly improve the accuracy, and reduce the false rate as a whole compared with unsupervised learning.

关键词： anomaly detection autoencoder expectation maximization class imbalance

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：