检索结果-内蒙古大学图书馆

deep Hashing and Sparse Representation of Abnormal Events Detection

COMPUTER JOURNAL 2024年第1期67卷 3-17页

作者： Gnouma, Mariem Ejbali, Ridha Zaied, Mourad Univ Gabes Natl Engn Sch Gabes Res Team Intelligent Machines St Omar Ibn Khattab Zrig Eddakhlania Gabes 6029 Tunisia Fac Sci Gabes Dept Comp Sci Gabes 6072 Tunisia

Due to its widespread application in the field of public security, anomaly detection in crowd scenes has recently become a hot topic. Some deep learning-based methods led to significant accomplishments in this field. Nevertheless, due to the scarcity of data and the misclassification of queries which most of them suffer to some extent from a sudden and infrequent overfitting. Though, we tried to solve the above problems, understand the long video streams and establish an accurate and reliable security system in order to improve its performance in detecting anomalies. We also referred to the hash technique, which has proven to be the most efficient method used when researching about large-scale image recovery. Thus, this article offers a smart video anomaly detection solution. In this paper, we combine the advantages of both deep hashing and deep auto-encoders to show that tracking changes in deep hash components across time and can be used to detect local anomalies. More precisely, we start with a new technique to minimize the mass of input data and information in order to decrease the time of calculation using a new dynamic frame skipping technique. Then, we propose to measure local anomalies by combining semantic with low-level optical flows to balance the performance and perceptibility. The experimental results illustrate that the proposed methods surpass these baselines for the detection and localization of anomalies.

关键词： abnormal detection optical flow deep auto-encoder hashing code

来源：评论

学校读者我要写书评

暂无评论

Single-cell RNA-seq data clustering by deep information fusion

引用

BRIEFINGS IN FUNCTIONAL GENOMICS 2024年第2期23卷 128-137页

作者： Ren, Liangrui Wang, Jun Li, Wei Guo, Maozu Yu, Guoxian Shandong Univ Sch Software Jinan 250101 Peoples R China Shandong Univ Sch Software Jinan Peoples R China Shandong Univ Joint SDU NTU Ctr Artificial Intelligence Res C FA Jinan Peoples R China Shandong Univ Sch Control Sci & Engn Jinan Peoples R China Beijing Univ Civil Engn & Architecture Sch Elect & Informat Engn Beijing Peoples R China

Determining cell types by single-cell transcriptomics data is fundamental for downstream analysis. However, cell clustering and data imputation still face the computation challenges, due to the high dropout rate, sparsity and dimensionality of single-cell data. Although some deep learning based solutions have been proposed to handle these challenges, they still can not leverage gene attribute information and cell topology in a sensible way to explore the consistent clustering. In this paper, we present scdeepFC, a deep information fusion-based single-cell data clustering method for cell clustering and data imputation. Specifically, scdeepFC uses a deep auto-encoder (DAE) network and a deep graph convolution network to embed high-dimensional gene attribute information and high-order cell-cell topological information into different low-dimensional representations, and then fuses them to generate a more comprehensive and accurate consensus representation via a deep information fusion network. In addition, scdeepFC integrates the zero-inflated negative binomial (ZINB) into DAE to model the dropout events. By jointly optimizing the ZINB loss and cell graph reconstruction loss, scdeepFC generates a salient embedding representation for clustering cells and imputing missing data. Extensive experiments on real single-cell datasets prove that scdeepFC outperforms other popular single-cell analysis methods. Both the gene attribute and cell topology information can improve the cell clustering.

关键词： single-cell RNA-seq clustering graph convolution network deep auto-encoder ZINB transcriptomics

来源：评论

学校读者我要写书评

暂无评论

Towards Early Diagnosis Of Parkinson's Disease Through Speech Signals' Analysis Based on Advanced deep Learning Techniques 7

Towards Early Diagnosis Of Parkinson's Disease Through Speec...

引用

IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP)

作者： Qahmash, Ayman AlQahtani, Basmah Misfer King Khalid Univ Informat & Comp Syst Dept Abha Saudi Arabia

ISBN: (纸本)9798350351491;9798350351484

The utilization of Artificial Intelligence 'AI' techniques for analyzing speech signals is so promising nowadays especially for various medical applications. In our proposed research, dealing with early diagnosis of Parkinson's disease using speech analysis is a highly promising and innovative approach that has demonstrated considerable potential in identifying the disease during its initial phases. This study uses a combined methodology that utilizes deep Learning 'DL' approach for speech features' extraction followed by one Machine Learning approach as for final classification. In order to cultivate these profound features, a deep auto-encoder was hence utilized as a technique for feature extraction, while a multi-layer perceptron (MLP) was employed as a classifier. Our empirical findings indicate that the DL models proposed in this study yielded favorable outcomes, achieving a success rate of 90%. The preliminary findings of this study indicate that the proposed approach has the potential to early identifying Parkinson's disease through the analysis of speech signals. Such an important finding will not only help neurologists and considerably during their clinical investigations but also will enrich medical further assessments. A clinical aided tool could be conceived consequently in correlation with the future clinical feedback.

关键词： Parkinson's Disease deep auto-encoder multi-layer perceptron (MLP) Voice Diagnosis speech signals

来源：评论

学校读者我要写书评

暂无评论

Development of tool wear condition on-line monitoring method for impeller milling based on new data processing approach and DAE-BP-ANN-integrated modeling

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE 2024年第1-2期238卷 124-136页

作者： Zou, Zheng Gao, Xu Lei, Sicong Zhang, Hao Min, Rongcheng Yang, Yong Chongqing Univ Technol Sch Mech Engn Chongqing Peoples R China Chongqing Machine Tool Grp Co Ltd Chongqing Peoples R China Chongqing Univ Technol Sch Mech Engn 69 Honghuang Ave Chongqing 400054 Peoples R China

Tool wear condition monitoring plays an important role in the maintaining machining accuracy and machining efficiency of complex surface parts. In this study, a new on-line tool wear monitoring method based on a self-developed data processing approach for the impeller milling was proposed. To achieve that, a new tool wear experimental platform was first built to collect both the spindle current signal and thermal deformation data in entire life cycle of cutter. Based on collected data, features of the time domain, frequency domain and time-frequency domain were extracted indiscriminately, and a 38 x 156 feature-sample set was subsequently established. To further reduce the dimensions of this feature-sample set and rise its characterization capability, the feature set was further processed using the sensitivity analysis and deep auto-encoder algorithm. Finally, 12 synthesized features were filtered out and then used to build the mapping model of signal synthesized features to different tool wear conditions by adopting the structural artificial neural network (ANN) integrated with back propagation (BP) algorithm. To verify the reliability of the proposed BP-ANN-integrated tool wear condition monitoring model, another comparison analysis of different data processing approaches was conducted. The comparison results showed that the proposed method for tool wear condition online monitoring had reliable performance and the recognition accuracy was 88.9%.

关键词： Tool wear condition monitoring thermal deformation deep auto-encoder artificial neural network back propagation

来源：评论

学校读者我要写书评

暂无评论

A deep Learning Method for Rough Surface Clutter Reduction in GPR Image

A Deep Learning Method for Rough Surface Clutter Reduction i...

引用

IEEE Radar Conference (RadarConf)

作者： Zhang, Yan Huston, Dryver Xia, Tian Univ Vermont Burlington VT 05405 USA

ISBN: (纸本)9781665436694

The major clutter in a typical ground penetrating radar (GPR) B-scan image is the ground surface clutter. It can severely obscure or distort the subsurface target response, especially when the surface profile variation is large and the target reflection signal is overlapped with the surface clutter. In this paper, we propose a deep auto-encoder based method for reducing the rough surface clutter in GPR images. In our method, the rough surface clutter reduction is formulated as an anomaly detection problem. The rough surface region in a Bscan image is splitted into small patches which are used as the training data set to train a deep auto-encoder. The trained auto-encoder captures the patterns of the rough surface patches. After training, the whole B-scan image is divided into small patches of the same size as the training patches and each of which is fed into the auto-encoder to compute an anomaly score. To reduce the clutter, we design a novel method that adopts a weighted sum approach to aggregate all patches based on their anomaly scores. For performance evaluation, simulation and laboratory tests are conducted, and the clutter-to-rest ratios (CRR) are computed to quantify the clutter reduction effectiveness. The CRR of the simulated B-scan image is reduced from 4.24 dB to -14.06 dB, and the CRRs of two measured B-scans are reduced from 3.71 dB to -20.45 dB, and from 8.62 dB to -8.07 dB, respectively.

关键词： deep auto-encoder rough surface clutter reduction ground penetrating radar

来源：评论

学校读者我要写书评

暂无评论

Unsupervised fault detection approach based on depth auto-encoder for photovoltaic power generation system

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2024年第2期24卷 849-861页

作者： Zhang, Jun Chen, Zongren Wu, Weimei Shao, Liuyang Deng, Kaihuan Gao, Shixiong Guangdong Polytechn Sci & Technol Comp Engn Tech Coll Artificial Intelligence Coll Zhuhai 519090 Guangdong Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China

Fault detection for photovoltaic power generation system is a challenging problem in condition monitoring and troubleshooting, which aims to maintain the safe operation of equipment and improve the benefit of photovoltaic industry. Aiming at the problems of frequent failures of photovoltaic power generation system, large amount of operating data and difficult to obtain fault samples, we propose an unsupervised fault detection approach for photovoltaic power generation system via bidirectional long/short memory deep auto-encoder which combines the auto-encoder in deep learning with the Bi-directional Long Short-Term Memory (BiLSTM). Specifically, We first take the statistical feature enhanced as the input of an auto-encoder based on BiLSTM. Then, we build a simulation model of Grid-connected PV system. Finally, we use the operation results under normal conditions to train the fault detection model to obtain the reconstruction error and determine the fault detection threshold, so as to judge the anomalies of the photovoltaic power generation system. We simulate the shadow occlusion fault and verify the effectiveness of the proposed method, and the fault detection accuracy of 0.95 is achieved. Compare with other models, the results show that it could set up better dependence on multi-dimensional data in time sequences, effectively testing solar panel failures and solving insufficient data labels problems.

关键词： Fault detection deep learning photovoltaic power generation system deep auto-encoder bidirectional long/short memory

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Enhanced Spatial-Temporal Coherence for Video Anomaly Detection

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 314-318页

作者： Cheng, Kai Liu, Yang Zeng, Xinhua Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

Video Anomaly Detection (VAD) is a critical yet challenging task in the signal processing community. Since part abnormal events cannot be detected by analyzing spatial or temporal information alone, learning spatial-temporal coherence has been proven the key to effective VAD. To this end, we propose a Graph Enhanced Spatial-Temporal Attention (GESTA) to address unsupervised VAD by learning the spatial-temporal coherence of normal events. Firstly, we propose a Dynamic Graph Recurrent Neural Network (DGRNN) to extract the motion patterns. Then, we propose a Spatial-Temporal Attention Module (STAM) to better model spatial-temporal coherence by integrating the prototypical spatial and temporal information. Finally, the fused spatial-temporal features are fed into the decoder to predict future frames. In testing phase, the anomaly with irregular information will result in poor prediction results. Experiments on three benchmarks demonstrate that our GESTA performs comparably to the state-of-the-art methods, and extensive analysis proves the effectiveness of DGRNN and STAM.

关键词： Optical signal processing Decoding Benchmark testing Task analysis Optical computing Coherence Predictive models Video anomaly detection unsupervised learning spatial-temporal attention deep auto-encoder graph network

来源：评论

学校读者我要写书评

暂无评论

A mixture of probabilistic predictable feature analysis for multi-mode dynamic process monitoring

引用

JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS 2023年第1期143卷

作者： Fan, Wei Ren, Shaojun Yu, Cong Yu, Haiquan Wang, Peng Si, Fengqi Southeast Univ Key Lab Energy Thermal Convers & Control Minist Educ Nanjing 210096 Jiangsu Peoples R China Jianghan Univ Sch Intelligent Mfg Wuhan 430056 Hubei Peoples R China

In modern industrial processes, the demand for safety and reliability is increasingly prioritized, spawning quantities of related research on process monitoring models. It is significant for process monitoring to consider multi-mode operating conditions simultaneously. This work proposes an efficient method based on multi-mode probabilistic predictable feature analysis (MPPFA) for complex industrial process monitoring. A strategy combining deep auto-encoder (DAE) and Gaussian mixture model (GMM) is first designed to extract low dimensional features and identify possible running modes. In line with the obtained features, original training samples are classified into corresponding Gaussian distributions with reasonable probabilities. Further, local PPFA models are established based on the separated training batches. Five monitoring statistics, including T2P, SPEP, and DIP for PPFAs, T2D and SPED for DAE, are defined to detect abnormalities. The proposed method is first applied to a three-phase flow facility, and its superiority over comparison methods has been verified. The effectiveness of the proposed method is further demonstrated through an experiment on a practical coal pulverising system.

关键词： Probabilistic predictable feature analysis Dynamic process monitoring Multi-mode industrial process Gaussian mixture model deep auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular risk detection using Harris Hawks optimization with ensemble learning model on PPG signals

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2023年第8期17卷 4503-4512页

作者： Divya, R. Shadrach, Finney Daniel Padmaja, S. PSG Coll Technol Dept Elect & Elect Engn Coimbatore India KPR Inst Engn & Technol Dept Elect & Commun Engn Coimbatore Tamil Nadu India Keshav Mem Inst Technol Hyderabad India

Cardiovascular (CVD) risk detection using Electrocardiography (ECG) and photoplethysmography (PPG) signals is an emerging field of research in the area of machine learning and biomedical engineering. ECG is an electrical measurement that captures cardiac actions and is the gold standard for identifying CVD. But, ECG cannot be used for continuous cardiac monitoring because of its necessity for user participation. PPG is an optically attained signal for detecting blood volume changes in the microvascular bed of tissues. deep learning (DL) methods have shown remarkable performance in predicting and detecting CVD disease using PPG signals. Therefore, this study designs a new Cardiovascular Risk Detection using Harris Hawks Optimization with Ensemble Learning (CRDHHO-EL) model on PPG Signals. The presented CRDHHO-EL technique examines the PPG signals to identify the risks of cardiovascular diseases. To accomplish this, the CRDHHO-EL technique uses an ensemble of three classifiers, namely deep belief network (DBN), deep auto-encoder (DAE), and extreme learning machine (ELM) models. Moreover, the HHO algorithm is used for adjusting the hyperparameter values of the classifier models, boosting overall performance. The experimental result analysis of the CRDHHO-EL on the open-access dataset showcases the significant performance of the CRDHHO-EL technique over other existing approaches.

关键词： Cardiovascular disease deep auto-encoder PPG signals Computer aided detection deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-view deep unsupervised transfer leaning via joint auto-encoder coupled with dictionary learning

引用

INTELLIGENT DATA ANALYSIS 2019年第3期23卷 555-571页

作者： Diasse, Abdoullahi Li, Zhiyong Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China

Transfer learning empowers machine learning algorithms the ability to train a model on a given task, capture the existing relationship in the data and reuse it for another task in the same or similar domain. In this paper, we present a Multiview deep unsupervised transfer leaning via joint auto-encoder coupled with dictionary learning (MVT-DAE). In the proposed approach knowledge transfer is done in two stages. First, we perform multi-view dictionary learning based on low-rank tensor regularization in the source domain to learn the common intrinsic relationship among views. Then we transfer the learned dictionaries to the target domain, and we construct a new representation of both domain via sparse coding. In the second stage, we use two deep auto-encoders (DAE) from both sources to perform parameters transfer. Each DAE consist of an embedding layer and a label layer. The embedding layer reconstructs the input while the label layer is used to encode the label information. To relax the distribution distance of the embedding and label layer between the source and the target domain a joint maximum mean discrepancy (JMMD) is employed. Learning can be done via Stochastic gradient descent by sharing the embedding and label layer weights with the target domain. We conduct extensive experiments in two real-world datasets which demonstrated the effectiveness of our approach compared with the different state of the art baseline.

关键词： Transfer learning multi-view deep auto-encoder dictionary learning

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：