检索结果-内蒙古大学图书馆

In-Situ early anomaly detection and remaining useful lifetime prediction for high-power white LEDs with distance and entropy-based long short-term memory recurrent neural networks

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期238卷

作者： Wen, Minzhen Ibrahim, Mesfin Seid Meda, Abdulmelik Husen Zhang, Guoqi Fan, Jiajie Fudan Univ Inst Future Lighting Acad Engn & Technol Shanghai 200433 Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys State Key Lab Appl Opt Changchun 130033 Peoples R China Ctr Adv Reliabil & Safety Hong Kong Peoples R China Wollo Univ Kombolcha Inst Technol Coll Engn Kombolcha 208 Ethiopia Hong Kong Polytech Univ Hung Hom Hong Kong Peoples R China Delft Univ Technol EEMCS Fac NL-2628 Delft Netherlands Fudan Zhangjiang Inst Shanghai 201203 Peoples R China

High-power white light-emitting diodes (LEDs) have demonstrated superior efficiency and reliability compared to traditional white light sources. However, ensuring maximum performance for a prolonged lifetime use presents a significant challenge for manufacturers and end users, especially in safety-critical applications. Thus, identifying functional anomalies and predicting the remaining useful lifetime (RUL) is of enormous importance in the operational longevity of the device. To address such challenges, this study proposes a combination of distance-based Mahalanobis distance (MD), entropy generation rate (EGR), and deep learning models for improved anomaly detection and RUL prediction accuracy. Unlike conventional health indicators based on luminous flux data that are challenging to monitor relevant optical performance, the MD and EGR methods are employed to extract in-situ monitored thermal and electrical data as new health indicators. Long short-term memory recurrent neural networks (LSTM-RNN) and convolutional neural networks (CNN) are established to detect anomalies and predict the RUL. The accelerated degradation tests of 3 W high-power white LED have been conducted, and the online and offline collected experimental data are deployed for model development and performance evaluation. The performance of the proposed methods is compared against the Illuminating Engineering Society of North America (IESNA) TM-21 method. The results indicate that LSTM-RNN, when combined with either MD or EGR, can detect anomalies with significantly fewer data (70 %) than is typically required. Furthermore, a significant improvement in prediction accuracy in RUL prediction based on MD and EGRconstructed time series health indicators and employed with the LSTM-RNN model demonstrates the effectiveness of the proposed methods.

关键词： Light-emitting diodes (LEDs) Mahalanobis distance (MD) Entropy generation rate (EGR) deep learning algorithms Anomaly detection Remaining Useful Lifetime (RUL) Prediction

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

A New Paradigm for Assessing Detailed Dynamics of Forest Landscape Fragmentation

引用

FORESTS 2024年第7期15卷 1212页

作者： Lin, Xin Zhen, Shiyong Zhao, Qing Hu, Xisheng Putian Univ Coll Art & Design Putian 351100 Peoples R China Fujian Agr & Forestry Univ Coll Transportat & Civil Engn Fuzhou 350002 Peoples R China

There is an urgent need for a thorough assessment of forest landscape fragmentation to inform forest protection and restoration, and reforestation policies. However, there is currently a lack of an effective comprehensive index for forest landscape fragmentation, and detailed knowledge of the forest landscape fragmentation dynamics remains insufficient. Here, taking Putian City of Fujian Province in Southeastern China as a case, we employed a forest fragmentation comprehensive index (FFCI) to capture key features of forest landscape fragmentation, such as patch size, number, and distribution. Then, bivariate spatial autocorrelation analysis was employed to identify the spatial associations between the static forest landscape fragmentation (FFCI) and the dynamic forest landscape fragmentation (Delta FFCI), and the spatial coupling modes among the three individual components of FFCI (mean patch area, MPA;aggregation index, AI;patch density, PD) were identified to explore the detail process of forest landscape fragmentation. Finally, the random forest model was applied to observe the impact factors of forest landscape fragmentation dynamics. The findings showed that forest landscapes with different degrees of fragmentation exhibited more noticeable changes at both ends (i.e., either high or lower-level fragmentation), with the intermediate level remaining consistent from 2000 to 2020. Around 18.3% of forest landscapes experienced a decrease in fragmentation, particularly in the northern part of the study area, while approximately 81.7% of forest landscapes exhibited an increasing trend in fragmentation. The bivariate spatial autocorrelation analysis indicated that the proportion of Low-High-type grids was the highest at 17.3%, followed by the High-High type at 7.0%. We also identified eight forest landscape fragmentation modes, which indicate the most significant forest landscape fragmentation pattern is a decrease in MPA and an increase in PD. Moreover, the anthropoge

关键词： forest landscape fragmentation bivariate spatial autocorrelation analysis random forest model deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Forecasting Pedestrian Movements Using Recurrent Neural Networks: An Application of Crowd Monitoring Data

引用

SENSORS 2019年第2期19卷 382-382页

作者： Duives, Dorine C. Wang, Guangxing Kim, Jiwon Delft Univ Technol Transport & Planning NL-2628 CN Delft Netherlands Univ Queensland Sch Civil Engn St Lucia Qld 4072 Australia

Currently, effective crowd management based on the information provided by crowd monitoring systems is difficult as this information comes in at the moment adverse crowd movements are already occurring. Up to this moment, very little forecasting techniques have been developed that predict crowd flows a longer time period ahead. Moreover, most contemporary state estimation methods apply demanding pre-processing steps, such as map-matching. The objective of this paper is to design, train and benchmark a data-driven procedure to forecast crowd movements, which can in real-time predict crowd movement. This procedure entails two steps. The first step comprises of a cell sequence derivation method that allows the representation of spatially continuous GPS traces in terms of discrete cell sequences. The second step entails the training of a Recursive Neural Network (RNN) with a Gated Recurrent Unit (GRU) and six benchmark models to forecast the next location of pedestrians. The RNN-GRU is found to outperform the other tested models. Some additional tests of the ability of the RNN-GRU to forecast illustrate that the RNN-GRU preserves its predictive power when a limited amount of data is used from the first few hours of a multi-day event and temporal information is incorporated in the cell sequences.

关键词： deep learning algorithms forecasting pedestrian crowd movements GPS trajectories Recursive Neural Network (RNN) with Gated Recurrent Unit (GRU)

来源：评论

学校读者我要写书评

暂无评论

Nakagami-m Fading Channel Identification Using Adaptive Continuous Wavelet Transform and Convolutional Neural Networks

引用

algorithms 2023年第6期16卷 277-277页

作者： Baldini, Gianmarco Bonavitacola, Fausto European Commiss Joint Res Ctr I-21027 Ispra Italy Fincons I-20871 Vimercate Italy

Channel identification is a useful function to support wireless telecommunication operations because the knowledge of the radio frequency propagation channel characteristics can improve communication efficiency and robustness. In recent times, the application of machine learning (ML) algorithms to the problem of channel identification has been proposed in the literature. In particular, deep learning (DL) has demonstrated superior performance to 'shallow' machine learning algorithms for many wireless communication functions. Inspired by the success of DL in literature, the authors in this paper apply Convolutional Neural Networks (CNN) to the problem of channel identification, which is still an emerging research area. CNN is a deep learning algorithm that has demonstrated superior performance to ML algorithms, in particular for image processing tasks. Because the digitized RF signal is a one-dimensional time series, different algorithms are applied to convert the time series to images using various Time Frequency Transform (TFT) including the CWTs, spectrogram, and Wigner Ville distribution. The images are then provided as input to the CNN. The approach is applied to a data set based on weather radar pulse signals generated in the laboratory of the author's facilities on which different fading models are applied. These models are inspired by the tap-delay-line 3GPP configurations defined in the standards, but they have been customized with Nakagami-m fading distribution (3GPP-like fading models). The results show the superior performance of time-frequency CNN in comparison to 1D CNN for different values of Signal to Noise Ratio (SNR) in dB. In particular, the study shows that the Continuous Wavelet Transform (CWT) has the optimal performance in this data set, but the choice of the mother wavelet remains a problem to be solved (this is a well-known problem in the research literature). Then, this study also proposes an adaptive technique for the choice of the optimal m

关键词： deep learning algorithms wireless propagation fading channels

来源：评论

学校读者我要写书评

暂无评论

Optimizing knee osteoarthritis severity prediction on MRI images using deep stacking ensemble technique

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-14页

作者： Panwar, Punita Chaurasia, Sandeep Gangrade, Jayesh Bilandi, Ashwani Pruthviraja, Dayananda Manipal Univ Jaipur Sch Comp Sci & Engn Dept Comp Sci & Engn Jaipur Rajasthan India Manipal Univ Jaipur Dept Artificial Intelligence & Machine Learning Comp Sci & Engn Jaipur Rajasthan India Mahatma Gandhi Med Coll Dept Orthoped Jaipur Rajasthan India Manipal Acad Higher Educ Manipal Inst Technol Bengaluru Dept Informat Technol Manipal Karnataka India

Knee osteoarthritis (KOA) represents a well-documented degenerative arthropathy prevalent among the elderly population. KOA is a persistent condition, also referred to as progressive joint Disease, stemming from the continual deterioration of cartilage. Predominantly afflicting individuals aged 45 and above, this ailment is commonly labeled as a "wear and tear" joint disorder, targeting joints such as the knee, hand, hips, and spine. Osteoarthritis symptoms typically increase gradually, contributing to the deterioration of articular cartilage. Prominent indicators encompass pain, stiffness, tenderness, swelling, and the development of bone spurs. Diagnosis typically involves the utilization of Radiographic X-ray images, Magnetic Resonance Imaging (MRI), and Computed Tomography (CT) Scan by medical professionals and experts. However, this conventional approach is time-consuming, and also sometimes tedious for medical professionals. In order to address the limitation of time and expedite the diagnostic process, deep learning algorithms have been implemented in the medical field. In the present investigation, four pre-trained models, specifically CNN, AlexNet, ResNet34 and ResNet-50, were utilized to predict the severity of KOA. Further, a deep stack ensemble technique was employed to achieve optimal performance resulting to the accuracy of 99.71%.

关键词： Knee osteoarthritis Magnetic resonance imaging (MRI) deep learning algorithms Convolutional neural network deep Stack Ensemble

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

deep Belief Network enhanced intrusion detection system to prevent security breach in the Internet of Things

引用

INTERNET OF THINGS 2021年 14卷

作者： Balakrishnan, Nagaraj Rajendran, Arunkumar Pelusi, Danilo Ponnusamy, Vijayakumar Karpagam Coll Engn Dept Elect & Commun Engn Coimbatore Tamil Nadu India Univ Teramo Fac Commun Sci Teramo Italy

Internet of Things (IoT) is a new age technology, developed with the vision to connect and interconnect all the objects everywhere. This technology enables an overwhelming smartness, which helps the humankind in many ways. Connecting the objects around us, make them communicate with each other towards a mission of intelligent healthcare, safety, Industrial processing applications. As the Internet of Things involved in many various entities and diverse applications, that the vulnerability to unauthorized access is much higher. Today, cyber-attacks faced by the communication networks are very strong and critically alarming. This research represents an intelligent technique or methodology to defend the security breach, developed with the enhancement of deep learning algorithms (deep Belief Network), i.e., deep Belief Network. This intelligent intrusion detection methodology scrutinizes the malicious activity that is active inside the network, and one tries to get its entry. In this paper, the investigation of embedding the deep learning methodology is discussed. The DBN enhancement to the security network is compared with standard DGAs and IDS algorithms, and the results are analyzed. (C) 2019 Elsevier B.V. All rights reserved.

关键词： deep learning algorithms DBN IDS Security breach Internet of Things

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

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

引用

SENSORS 2018年第4期18卷 1229-1229页

作者： He, Ziyang Zhang, Xiaoqing Cao, Yangjie Liu, Zhi Zhang, Bo Wang, Xiaoyan Zhengzhou Univ Collaborat Innovat Ctr Internet Healthcare 75 Univ North Rd Zhengzhou 450000 Henan Peoples R China Zhengzhou Univ Sch Software Engn 97 Culture Rd Zhengzhou 450000 Henan Peoples R China Shizuoka Univ Dept Math & Syst Engn 5-6273-5-1 Johoku Hamamatsu Shizuoka 4328561 Japan Ibaraki Univ Coll Engn 4-12-1 Nakanarusawa Hitachi Ibaraki 3168511 Japan

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database;the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

关键词： deep learning algorithms lightweight neural network resource-constrained mobile devices electrocardiogram

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：