检索结果-内蒙古大学图书馆

Application of deep autoencoder as an one-class classifier for unsupervised network intrusion detection: a comparative evaluation

引用

PEERJ COMPUTER SCIENCE 2020年 6卷 e327页

作者： Vaiyapuri, Thavavel Binbusayyis, Adel Prince Sattam bin Abdulaziz Univ Coll Comp Engn & Sci Alkharj Saudi Arabia

The ever-increasing use of internet has opened a new avenue for cybercriminals, alarming the online businesses and organization to stay ahead of evolving thread landscape. To this end, intrusion detection system (IDS) is deemed as a promising defensive mechanism to ensure network security. Recently, deep learning has gained ground in the field of intrusion detection but majority of progress has been witnessed on supervised learning which requires adequate labeled data for training. In real practice, labeling the high volume of network traffic is laborious and error prone. Intuitively, unsupervised deep learning approaches has received gaining momentum. Specifically, the advances in deep learning has endowed autoencoder (AE) with greater ability for data reconstruction to learn the robust feature representation from massive amount of data. Notwithstanding, there is no study that evaluates the potential of different AE variants as one-class classifier for intrusion detection. This study fills this gap of knowledge presenting a comparative evaluation of different AE variants for one-class unsupervised intrusion detection. For this research, the evaluation includes five different variants of AE such as Stacked AE, Sparse AE, Denoising AE, Contractive AE and Convolutional AE. Further, the study intents to conduct a fair comparison establishing a unified network configuration and training scheme for all variants over the common benchmark datasets, NSL-KDD and UNSW-NB15. The comparative evaluation study provides a valuable insight on how different AE variants can be used as one-class classifier to build an effective unsupervised IDS. The outcome of this study will be of great interest to the network security community as it provides a promising path for building effective IDS based on deep learning approaches alleviating the need for adequate and diverse intrusion network traffic behavior.

关键词： Network intrusion detection deep learning algorithms deep autoencoders One-class classifier Unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Mono-temporal and multi-temporal approaches for burnt area detection using Sentinel-2 satellite imagery (a case study of Rokan Hilir Regency, Indonesia)

引用

ECOLOGICAL INFORMATICS 2022年第0期69卷

作者： Afira, Natasya Wijayanto, Arie Wahyu Politeknik Stat STIS Dept Stat Comp Jakarta 13330 Indonesia Stat Indonesia BPS Jl Dr Sutomo 6-8 Jakarta 10710 Indonesia

Accurate and up-to-date information about the burnt area is important in estimating environmental losses, prioritizing rehabilitation areas, and determining future planning strategies. The publicly available medium resolution optical Sentinel-2 satellite data provides a practical and effective solution for burnt area detection. In this study, we proposed two different approaches using mono-temporal and multi-temporal Sentinel-2 satellite imagery to detect burnt areas in Rokan Hilir Regency, Indonesia. The multi-temporal approaches utilized two different ensemble machine learning algorithms (Random Forest and XGBoost) and used six composite spectral indices of the differenced Normalized Burn Ratio (dNBR), differenced Normalized Burn Ratio 2 (dNBR2), differenced Normalized Difference Vegetation Index (dNDVI), differenced Soil Adjusted Vegetation Index (dSAVI), differenced Char Soil Index (dCSI), differenced Burnt area Index for Sentinel-2 (dBAIS2), and differenced Mid infrared Burn Index (dMIRBI) as model inputs. The burnt areas are labeled by combining hotspots with confidence intervals above 95%, fire spots, and change detection methods. The XGBoost model achieved the best performance with an F1 score of 0.97 and an accuracy of 96%. Furthermore, we use the SHapley Additive exPlanations (SHAP) to quantify the contribution of each feature as well as its correlation with the target class. The dNBR, dMIRBI, and dNBR2 indices contribute the most to the XGBoost model. In comparison, this study also investigates and compares a mono-temporal approach with One-dimensional Convolutional Neural Network (CNN-1D) architecture and the performance obtained is slightly better than both machine learning models. Overall, both mono-temporal and multi-temporal approaches satisfactorily detect the burnt area.

关键词： Burnt area detection Machine learning algorithms deep learning algorithms Sentinel-2 Fire

来源：评论

学校读者我要写书评

暂无评论

Human-like evaluation method for object motion detection algorithms

引用

IET COMPUTER VISION 2020年第8期14卷 674-682页

作者： Guzman-Pando, Abimael Ignacio Chacon-Murguia, Mario Chacon-Diaz, Lucia B. Tecnol Nacl Mexico Visual Percept Lab Grad & Res Dept IT Chihuahua Ave Tecnol 2909 Chihuahua Mexico Ohio State Univ Coll Educ & Human Ecol Dept Teaching & Learning 1945 North High St Columbus OH 43210 USA

This study proposes a new method to evaluate the performance of algorithms for moving object detection (MODA) in video sequences. The proposed method is based on human performance metric intervals, instead of ideal metric values (0 or 1) which are commonly used in the literature. These intervals are proposed to establish a more reliable evaluation and comparison, and to identify areas of improvement in the evaluation of MODA. The contribution of the study includes the determination of human segmentation performance metric intervals and their comparison with state-of-the-art MODA, and the evaluation of their segmentation results in a tracking task to establish the impact between performance and practical utility. Results show that human participants had difficulty with achieving a perfect segmentation score. deep learning algorithms achieved performance above the human average, while other techniques achieved a performance between 88 and 92%. Furthermore, the authors demonstrate that algorithms not ranked at the top of the quantitative metrics worked satisfactorily in a tracking experiment;and therefore, should not be discarded for real applications.

关键词： image segmentation learning (artificial intelligence) object detection image motion analysis video signal processing image sequences evaluation method object motion detection algorithms object detection video sequences human performance metric intervals ideal metric values reliable evaluation human segmentation performance metric intervals state‐of‐the‐art MODA human participants perfect segmentation score deep learning algorithms human average quantitative metrics

来源：评论

学校读者我要写书评

暂无评论

Intelligent Video Surveillance Systems for Vehicle Identification Based on Multinet Architecture

引用

INFORMATION 2022年第7期13卷 325-325页

作者： Gonzalez-Cepeda, Jacobo Ramajo, Alvaro Maria Armingol, Jose Carlos III Univ Dept Elect Elect & Automat Engn Madrid 28912 Spain

Security cameras have been proven to be particularly useful in preventing and combating crime through identification tasks. Here, two areas can be mainly distinguished: person and vehicle identification. Automatic license plate readers are the most widely used tool for vehicle identification. Although these systems are very effective, they are not reliable enough in certain circumstances. For example, due to traffic jams, vehicle position or weather conditions, the sensors cannot capture an image of the entire license plate. However, there is still a lot of additional information in the image which may also be of interest, and that needs to be analysed quickly and accurately. The correct use of the processing mechanisms can significantly reduce analysis time, increasing the efficiency of video cameras significantly. To solve this problem, we have designed a solution based on two technologies: license plate recognition and vehicle re-identification. For its development and testing, we have also created several datasets recreating a real environment. In addition, during this article, it is also possible to read about some of the main artificial intelligence techniques for these technologies, as they have served as the starting point for this research.

关键词： surveillance systems vehicle re-identification ALPR real-time applications deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Leakage detection in water pipelines using supervised classification of acceleration signals

引用

AUTOMATION IN CONSTRUCTION 2020年 117卷 103256-103256页

作者： Shukla, Harshit Piratla, Kalyan Clemson Univ Glenn Dept Civil Engn 109 Lowry Hall Clemson SC 29634 USA

Loss of treated water through buried pipeline leakage is one of the pressing challenges faced by water utilities across the world. Many current pipeline inspection techniques are ad-hoc in nature and only provide a snapshot status of the system. Although a few embedded sensor-based systems offer promise for continuous monitoring, they are limited in their ability to detect leakages of all magnitudes. Lack of a comprehensive understanding of the pipeline system's structural dynamics and the correlation to leakage detection is a primary challenge. To overcome this challenge, a deep learning algorithm that uses scalogram images of vibration signals collected from accelerometers attached to the pipeline surface is developed and validated in this study. The advantage is that the complex structural features of the water pipeline systems need not be modeled if sufficient leak-based vibration signal data is available for training purposes. A convolutional neural network (CNN) model adapted from a pre-trained AlexNet network is leveraged to demonstrate the proposed approach using vibration data collected from an experimental pipeline test bed. The CNN model is found to be able to detect leakages on polyvinyl chloride (PVC) pipelines with up to 95% accuracy. A maximum accuracy of 98% is observed with acceleration signal data collected from carefully selected locations. The approach presented in this study can be adapted for effective leakage detection in real world scenarios with minimum human intervention.

关键词： Infrastructure monitoring Automated pipeline leakage detection deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive multilayer neural network for solving elliptic partial differential equations with different boundary conditions

引用

DIGITAL SIGNAL PROCESSING 2021年 118卷 103223-103223页

作者： Wang, Zheng Hounye, Alphonse Houssou Wang, Jiaoju Cao, Cong Hou, Muzhou Cent South Univ Sch Math & Stat Changsha 410083 Peoples R China Hunan First Normal Univ Sci & Engn Sch Changsha 410205 Peoples R China Cent South Univ HNP LAMA Sch Math & Stat Changsha 410083 Hunan Peoples R China

In recent years, elliptic partial differential equations (PDEs) have been challenging in numerical mathematics, engineering, and physics. In this paper, we proposed a novel approach called Multilayer Neural Network for Partial Differential Equations (MLNPDE) based on deep learning algorithms by exploring the elliptic PDE family under certain conditions such as initial conditions and boundary conditions to govern approximation solutions of PDEs. In the proposed model, we include a multilayer neural network using a densely connected network. Moreover, the approximation solution underlying PDEs can be expressed in two terms: the first term satisfies the boundary conditions, and the second term is a function of the unknown parameters that were estimated by our proposed model. Furthermore, we derive a normal form of the boundary conditions on the first term of the approximation solution for two-dimensional elliptic partial differential equation problems with an arbitrary domain. The numerical results show that our method achieved tremendous state-of-the-art performance in accuracy and efficiency compared to the classical methods. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Artificial intelligence Partial differential equations Boundary conditions deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Sudden cardiac death in adults with congenital heart disease: Lessons to Learn from the ATROPOS registry

引用

INTERNATIONAL JOURNAL OF CARDIOLOGY CONGENITAL HEART DISEASE 2022年 9卷 100396-100396页

作者： Fischer, Alicia Jeanette Bauer, Ulrike M. M. Frey, Michael Beudt, Jens Baumgartner, Helmut Diller, Gerhard-Paul Univ Hosp Muenster Dept Cardiol Adult Congenital & Valvular Heart Dis Munster Germany Natl Register Congenital Heart Defects Berlin Germany DZHK German Ctr Cardiovasc Res Berlin Germany Univ Hosp Muenster Dept Cardiol Adult Congenital & Valvular Heart Dis Albert Schweitzer Str 33 D-48149 Munster Germany

Sudden cardiac death (SCD) is one of the most frequent causes of death in adult patients with congenital heart disease (ACHD). Despite the rare frequency of its occurrence, the incident appears often when unexpected, and many affected patients had not been identified priorly. Data on predictors for SCD are limited since the total number of ACHD is low. As the cohort is heterogeneous, it is difficult to define uniform risk factors that apply to all ACHD. Complexity of the congenital heart disease appears to play a role, but other factors may also be relevant and have not been sufficiently identified yet. In current guidelines, recommendations are primarily based on data of patients without congenital heart *** the ATROPOS registry, we are aiming to identify reliable risk factors for SCD. The registry enables physicians globally to include patients with congenital heart disease who died of or survived SCD. After acquisition, the data will be compared to an age and complexity of disease matched cohort to perform a case control analysis. Subsequently, a further analysis will be performed using deep learning algorithms with artificial intelligence to amplify the gathered information and find reliable risk factors.

关键词： Sudden cardiac death Congenital heart disease Predictors deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Tree counting with high spatial-resolution satellite imagery based on deep neural networks

引用

ECOLOGICAL INDICATORS 2021年 125卷 107591-107591页

作者： Yao, Ling Liu, Tang Qin, Jun Lu, Ning Zhou, Chenghu Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing Peoples R China Southern Marine Sci & Engn Guangdong Lab Guangzhou Peoples R China China Univ Geosci Beijing Peoples R China Jiangsu Ctr Collaborat Innovat Geog Informat Reso Nanjing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Forest inventory at single-tree level is of great importance to modern forest management. The inventory contains two critical parameters about trees, including their numbers and spatial locations. Traditional methods to catalogue single trees are laborious, while deep neural networks enable to discover the multi-scale features hidden in images and thus make it possible to count trees with remote sensing imagery. In this study, four different tree counting networks, which were constructed by remodeling four different classical deep convolutional neural networks, were evaluated to determine their abilities to grasp the relationship between remote sensing images and tree locations for automatic tree counting end-to-end. To this end, a tree counting dataset was constructed with remote sensing images of 0.8-m spatial resolution in distinct regions. This dataset consisted of 24 GF-II images and the corresponding manually annotated locations of trees based on these images. Thereafter, a large number of experiments were conducted to examine the performance of these networks in regards to tree counting. The results demonstrated that all networks could achieve the competitive performance (above 0.91) in terms of the determination coefficient (R-2) between the ground truth and the estimated values. The average accuracy of the Encoder-Decoder Network (one of the four networks) was greater than 91.58% and its R-2 was equal to 0.97, achieving the best performance. It has been found that the deep learning is an efficient and effective means for tree counting task.

关键词： Forestry deep learning algorithms Remote sensing Density estimation Tree counting

来源：评论

学校读者我要写书评

暂无评论

Towards application of machine learning algorithms for prediction temperature distribution within CFB boiler based on specified operating conditions

引用

ENERGY 2021年 237卷 121538-121538页

作者： Grochowalski, Jaroslaw Jachymek, Piotr Andrzejczyk, Marek Klajny, Marcin Widuch, Agata Morkisz, Pawel Hernik, Bartlomiej Zdeb, Janusz Adamczyk, Wojciech Tauron Wytwarzanie SA Promienna 51 PL-43603 Jaworzno Poland Silesian Tech Univ Fac Energy & Environm Engn Dept Thermal Engn Konarskiego 22 PL-44100 Gliwice Poland Silesian Tech Univ Fac Energy & Environm Engn Dept Power Engn & Turbomachinery Konarskiego 18 PL-44100 Gliwice Poland AGH Univ Sci & Technol Fac Appl Math Al Mickiewicza 30 PL-30059 Krakow Poland Sumitomo SHI FW Ul Konstantynow PL-41200 Sosnowiec Poland

The availability of the power unit for electricity production is one of the most important issues of the power plant operator. Considering the power unit, boiler is the main source of its malfunction. Depending of the boiler construction, source of problem can be different. In case of usage of the circulating fluidized bed boiler the potential issue that can lead to interruption of the energy production is its failure caused by leakages of heating surfaces. In order to mitigate this risk different treatments or procedures are introduced. Nowadays, thanks to continuous development of mathematical tools its is possible to introduce a new solution to reduce the risk of heating surface erosion cause by the friction of solid material used in fluidization. One of possible option, that can help to resolve such a problem is application of machine learning technique. Based on real observation of the boiler operation and data analysis, it is believed that the uniform temperature distribution at the lower part of the combustion chamber should has positive impact on erosion reduction at the kick-out level where tapered walls changed to vertical one. This can be attain by careful manipulation of selected boiler operating parameters. Due to the reason that in order to find requires setup dozen of input data configuration need to be considered appropriate toll need to be developed. That is the main reason way the machine learning technique need to be applied for such purpose. Indeed, of this work is to develop artificial models that can help in adjustment boiler setup. In order to check models functionality, they were on-site tested by boiler operator. Developed model shows tremendous potential and confirm that it is worth to investigated this topic farther. (c) 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Prediction Machine learning CFB Erosion Boiler malfunction deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Ultra-broadband infrared gas sensor for pollution detection: the TRIAGE project

引用

JOURNAL OF PHYSICS-PHOTONICS 2021年第3期3卷

作者： Napier, Bruce Bang, Ole Markos, Christos Moselund, Peter Huot, Laurent Harren, Frans J. M. Khodabakhsh, Amir Martin, Hans Briano, Floria Ottonello Balet, Laurent Lecomte, Steve Petersen, Christian R. Israelsen, Niels Bastviken, David Galfalk, Magnus Kubiszyn, Lukasz Warzybok, Piotr Vivid Components Paderborn Germany Tech Univ Denmark DTU Foton Lyngby Denmark NKT Photon AS Birkerod Denmark Radboud Univ Nijmegen Trace Gas Res Grp IMM Nijmegen Netherlands Senseair AB Delsbo Sweden CSEM SA Neuchatel Switzerland NORBLIS IVS Virum Denmark Linkoping Univ Dept Themat Studies Environm Change Linkoping Sweden VIGO Syst SA Ozarow Mazowiecki Poland

Air pollution is one of the largest risk factors for disease or premature death globally, yet current portable monitoring technology cannot provide adequate protection at a local community level. Within the TRIAGE project, a smart, compact and cost-effective air quality sensor network will be developed for the hyperspectral detection of gases which are relevant for atmospheric pollution monitoring or dangerous for human health. The sensor is based on a mid-infrared supercontinuum source, providing ultra-bright emission across the 2-10 mu m wavelength region. Within this spectral range, harmful gaseous species can be detected with high sensitivity and selectivity. The spectroscopic sensor, which includes a novel multi-pass cell and detector, enables a smart robust photonic sensing system for real-time detection. With built-in chemometric analysis and cloud connection, the sensor will feed advanced deep-learning algorithms for various analyses, ranging from long-term continental trends in air pollution to urgent local warnings and alerts. Community-based distributed pollution sensing tests will be verified on municipal building rooftops and local transport platforms.

关键词： trace gas detection supercontinuum source spectroscopy mid-infrared deep learning algorithms big data repositories

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：