检索结果-内蒙古大学图书馆

An autoencoder for compressing angle-resolved photoemission spectroscopy data

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2025年第1期6卷

作者： Agustsson, Steinn ymir Haque, Mohammad Ahsanul Truong, Thi Tam Bianchi, Marco Klyuchnikov, Nikita Mottin, Davide Karras, Panagiotis Hofmann, Philip Aarhus Univ Dept Phys & Astron DK-8000 Aarhus Denmark Aarhus Univ Dept Comp Sci DK-8000 Aarhus C Denmark

Angle-resolved photoemission spectroscopy (ARPES) is a powerful experimental technique to determine the electronic structure of solids. Advances in light sources for ARPES experiments are currently leading to a vast increase of data acquisition rates and data quantity. On the other hand, access time to the most advanced ARPES instruments remains strictly limited, calling for fast, effective, and on-the-fly data analysis tools to exploit this time. In response to this need, we introduce ARPESNet, a versatile autoencoder network that efficiently summmarises and compresses ARPES datasets. We train ARPESNet on a large and varied dataset of 2-dimensional ARPES data extracted by cutting standard 3-dimensional ARPES datasets along random directions in k. To test the data representation capacity of ARPESNet, we compare k-means clustering quality between data compressed by ARPESNet, data compressed by discrete cosine transform, and raw data, at different noise levels. ARPESNet data excels in clustering quality despite its high compression ratio.

关键词： autoencoder angle-resolved photoemission spectroscopy data compression

来源：评论

学校读者我要写书评

暂无评论

State estimation and visualization of lithium-ion battery using transformer autoencoder model

引用

JOURNAL OF POWER ELECTRONICS 2025年第3期25卷 500-509页

作者： Woo, Tae-Geol Kim, Beom-Jun Cho, In-Ho Park, Kang-Moon Korea Natl Univ Transportat Dept Elect & Elect Engn Chungju South Korea

This study developed and evaluated artificial neural network models for estimating and visualizing the State of Health (SOH) of lithium-ion batteries (LIBs) used in railway vehicles. The models, which include autoencoder, Long Short-Term Memory (LSTM)-autoencoder, Attention LSTM-autoencoder, and Transformer autoencoder, were trained on large-scale time-series data of LIB voltage, current, and temperature. The Transformer autoencoder model demonstrated substantial performance improvements, achieving over a 99% enhancement compared to the basic autoencoder model and up to 82% improvement over the Attention LSTM-autoencoder model. Unlike classical Transformer models, which typically focus on compressing data into high-dimensional spaces, the autoencoder approach is applied to the Transformer model, facilitating low-dimensional compression and clustering of the data. This clustering technique was further employed to visualize battery health by converting the clustered data into RGB values, offering an intuitive representation of the SOH. By overcoming the limitations of traditional methods, this novel approach provides an effective means of assessing battery condition. These findings indicate that the proposed method could notably enhance battery management systems, leading to a safe and reliable operation of electric mobility systems.

关键词： Transformer autoencoder Deep learning Battery state State of health (SOH)

来源：评论

学校读者我要写书评

暂无评论

Analysis of time-of-flight secondary ion mass spectrometry data of human skin treated with diclofenac using sparse autoencoder

引用

ANALYTICAL AND BIOANALYTICAL CHEMISTRY 2025年第6期417卷 1049-1054页

作者： Shinozaki, Atsumi Matsuda, Kazuhiro Aoyagi, Satoka Seikei Univ Fac Sci & Technol 3-3-1 Kichijoji Kitamachi Musashino Tokyo 1808633 Japan Toray Res Ctr Ltd Surface Sci Labs 3-2-11 Sonoyama Otsu Shiga 5208567 Japan

Methods that facilitate molecular identification and imaging are required to evaluate drug penetration into tissues. Time-of-flight secondary ion mass spectrometry (ToF-SIMS), which has high spatial resolution and allows 3D distribution imaging of organic materials, is suitable for this purpose. However, the complexity of ToF-SIMS data, which includes nonlinear factors, makes interpretation challenging. Therefore, in this study, ToF-SIMS data of a stratum corneum treated with diclofenac were analyzed using machine learning to enable the evaluation of drug distribution. Diclofenac-related mass peaks were identified using autoencoder results, and the degree of penetration was evaluated across 2-20th stripped tapes. In addition, the permeation pathway was clarified by comparing the secondary ion images of phosphatidylethanolamine (PhEA;a marker of the inside of the cell);cholesterol, which is abundant in cell membranes;and diclofenac. Based on the biomolecule-related ion images showing the penetration pathway of diclofenac applied to the skin, diclofenac penetrates both the extracellular space and inside cells.

关键词： ToF-SIMS Mass imaging autoencoder Machine learning Stratum corneum Diclofenac

来源：评论

学校读者我要写书评

暂无评论

Application of latent Dirichlet allocation and autoencoder to real estate datasets

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-24页

作者： Gu, Runhe Lin, Luchun Changzhou Univ Sch Comp Sci & Artificial Intelligence Aliyun Sch Big Data Sch Software 2468 Yanzheng West Ave Changzhou 213159 Jiangsu Peoples R China

At present, there are too many types and numbers of real estate features in the real estate market, and it is difficult to effectively recommend real estate to customers with more complicated needs. The datasets of real estate often encompass a wide array of features, including categories, numerical values, and textual descriptions, which complicates the process of delivering precise and satisfactory recommendations. To address this issue, a cluster-based hybrid method combining latent Dirichlet allocation and autoencoder is proposed in this paper. It can effectively improve the early input of clustering by the two-stage feature extraction of the data through the topic model and the autoencoder. Experimental findings demonstrate that our hybrid method surpasses standalone LDA and autoencoder, as well as other conventional clustering algorithms. The combined results of Silhouette coefficient, DB index, and CH index are significantly better than the results of traditional clustering. Moreover, we conduct a comprehensive analysis of the results, emphasizing the benefits of our approach in managing multi-type features, encompassing categorical, numerical, and string data. It is anticipated that this research will contribute valuable insights into the field of recommendation systems.

关键词： Latent Dirichlet allocation autoencoder Hybrid method Real estate recommendation Deeping clustering

来源：评论

学校读者我要写书评

暂无评论

Enhancing autoencoder models for multivariate time series anomaly detection: the role of noise and data amount

引用

JOURNAL OF SUPERCOMPUTING 2025年第4期81卷 1-27页

作者： Sefati, Seyedeh Tina Razavi, Seyed Naser Salehpour, Pedram Univ Tabriz Comp Engn Tabriz Iran

Unsupervised anomaly detection in multivariate time series is important in many applications including cyber intrusion detection and medical diagnostics. Both traditional and supervised techniques had limitations due to data scale, labeling complexity, and cluster imbalance. Also, deep learning methods have drawbacks such as sensitivity to noise and difficulty in capturing spatial-temporal correlations. To address these challenges, we propose MTSAD, a new AE-based anomaly detection model for multivariate time series data that uses ConvLSTM and transposed convolution to effectively learn spatio-temporal features. Furthermore, in this paper, we explore the effect of noise injection and data amount utilization that improves the model performance and prevents overfitting. It increases the robustness to real sensor noise and improves the robustness of anomaly detection in industrial environments. On SWaT and WADI datasets, MTSAD achieves higher F1 scores than the competing models. The results of the study also show that data amount and noise injection are very important factors that can be used to improve the performance of AE-based anomaly detection. This work offers new understandings of the optimization of reconstruction-based architectures for unsupervised multivariate time series anomaly detection.

关键词： Anomaly detection Unsupervised learning Multivariate time series autoencoder Reconstruction-based methods

来源：评论

学校读者我要写书评

暂无评论

Research on anomaly detection of steam power system based on the coupling of thermoeconomics and autoencoder

引用

ENERGY 2025年 318卷

作者： Li, Guolong Li, Yanjun Li, Site Sun, Shengdi Wang, Haotong Su, Jian Shi, Jianxin Zhou, Xin Harbin Engn Univ Coll Power & Energy Engn Harbin 150001 Peoples R China Harbin Marine Boiler & Turbine Res Inst Res Inst CSSC 703 35 Honghu Rd Harbin 150078 Peoples R China

Discovering the anomalies of the steam power system in time can optimize the operating efficiency and avoid major losses. The existing single anomaly detection method is not effective outside its assumptions. Aiming at this problem, a new anomaly detection method based on the coupling of thermoeconomics and autoencoder is proposed. This method uses the autoencoder to reconstruct the normal values of the thermoeconomic calculation benchmark and other parameters. Then the endogenous irreversible loss of each component is calculated according to the benchmark. Finally, it is detected together with the reconstruction error of the parameters, and the deviation exceeding the threshold is abnormal. The experimental results show that under the premise of ensuring the precision, the traditional thermoeconomic anomaly detection method, the autoencoder anomaly detection method and the proposed coupling anomaly detection method can detect 58.7 %, 88.9 % and 94 % abnormal samples, respectively. In terms of the accuracy and F1-score, the coupling method is also the highest, reaching 93.9 % and 96.8 % respectively. It is proved that the coupling method is superior to the single thermoeconomic method or the autoencoder method, which is of great significance to ensure the safe and stable operation of the steam power system.

关键词： Steam power system Anomaly detection autoencoder Thermoeconomics Coupling method

来源：评论

学校读者我要写书评

暂无评论

Data-driven strategy: A robust battery anomaly detection method for short circuit fault based on mixed features and autoencoder

引用

APPLIED ENERGY 2025年 382卷

作者： Zhao, Hongyu Zhang, Chengzhong Liao, Chenglin Wang, Liye Liu, Weilong Wang, Lifang Chinese Acad Sci Inst Elect Engn Key Lab High Dens Electromagnet Power & Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Sifang Automat Co Ltd 9 Shangdi Fourth St Beijing 100085 Peoples R China

The anomaly detection of lithium-ion batteries for short circuit (SC) faults is crucial to ensure the safety of the energy storage system. Compared to the diagnosis fault of packs, individual cell fault diagnosis lacks a reference target, leading to difficulties in effectively detecting whether an abnormality exists. In this paper, a data-driven detection method based on the autoencoder strategy is proposed for early detection of battery faults without pack information. Within, the autoencoder strategy is used to reconstruct the voltage and detect potential faults. Using the generative adversarial network (GAN) framework for model training reduces its overfitting and improves efficiency. In addition, during anomaly detection, due to the lack of battery pack reference, some abnormal voltage changes due to current variations can lead to misdiagnosis. To address this concern, the mixed features input is proposed to reduce the misdiagnosis rate, which incorporates the equivalent circuit model parameters. Experiments demonstrate that the proposed method can accurately detect SC faults, in particular, it can detect some moderate or weak faults within 1.6 h. Compared to other methods, this method has better effectiveness and robustness. The method proposed in this paper is in line with the development trend for big data and opens up new perspectives for the development of energy storage safety technology.

关键词： Anomaly detection lithium-ion batteries Short circuit faults Mixed features autoencoder Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Predicting potential microbe-disease associations based on heterogeneous graph attention network and deep sparse autoencoder

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 147卷

作者： Wang, Bo Zhao, Wenlong Du, Xiaoxin Zhang, Jianfei Zhang, Chunyu Wang, Liping He, Yang Qiqihar Univ Sch Comp & Control Engn Qiqihar 161000 Heilongjiang Peoples R China Qiqihar Univ Heilongjiang Key Lab Big Data Network Secur Detect Qiqihar 161000 Heilongjiang Peoples R China Qiqihar Med Univ Sch Pathol Qiqihar 161000 Heilongjiang Peoples R China

Identifying potential associations between microbes and diseases is crucial for explaining disease pathogenesis and designing targeted therapeutic strategies. Basic biological experiments for microbe-disease association (MDA) prediction are costly, time-consuming, and labor-intensive, whereas computational methods can effectively complement traditional biological experiments. We propose a computational framework called graph attention convolutional deep sparse autoencoder microbe-disease association (GCDSAEMDA) to predict unknown MDAs. First, we calculate the semantic similarity and Gaussian interaction profile (GIP) similarity of diseases, as well as the functional similarity and GIP similarity of microbes, and integrate these similarity matrices to construct a heterogeneous graph. Next, a multi-head dynamic graph attention mechanism is employed to extract low-order features of microbe and disease nodes in the heterogeneous graph, while multiple convolutional neural networks with different kernels aggregate and concatenate these low-order features to form new high-order representations. Third, we apply a cosine distance-based k-means clustering to select reliable negative samples and use a deep sparse autoencoder to extract high-order features of microbe-disease pairs. Finally, an ensemble Light Gradient Boosting Machine (LightGBM) algorithm is used to predict potential MDAs. GCDSAEMDA was compared to four state-of-the-art MDA models on the Human Microbe-Disease Association Database (HMDAD) and Disbiome databases and validated through five-fold cross- validation on diseases, microbes, and microbe-disease pairs. Results indicate that GCDSAEMDA outperforms the other four models in MDA prediction. Additionally, case studies demonstrate the robust predictive capability of GCDSAEMDA. The source code and datasets for GCDSAEMDA are available at https://github. com/chenyunmolu/GCDSAEMDA.

关键词： Microbe-disease associations Graph attention mechanism Convolutional neural network k-means clustering autoencoder

来源：评论

学校读者我要写书评

暂无评论

Adversarial regularize graph variational autoencoder based on encoder optimization strategy

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第3期58卷 1-28页

作者： Dai, Jin Peng, Yanhui Wang, Guoyin Hu, Feng Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing Peoples R China Univ Posts & Telecommun Sch Software Engn Chongqing Chongqing Peoples R China

Graph variational autoencoders (VAEs) have been widely used to address the representation problem of graph nodes. However, most existing graph VAEs focus on minimizing reconstruction loss and overlook the uncertainty in the latent distribution and the issue of posterior collapse during training. An Adversarial Regularize Graph Variational autoencoder Based on Encoder Optimization Strategy (MCM-ARVGE) is proposed from the perspective of network structure and loss function. MCM-ARVGE introduces a Multi-dimensional Cloud Generator (MCG) that transforms the traditional encoder, expanding the Gaussian distribution into a Gaussian cloud distribution. Furthermore, MCM-ARVGE employs the idea of adversarial regularization to train the Gaussian cloud distribution, reducing the randomness of the Gaussian cloud distribution. Finally, based on the Gaussian cloud distribution, an effective uncertainty similarity measurement method for cloud distributions is introduced to address the problem of posterior collapse. Experimental results validate the universality and effectiveness of MCM-ARVGE, as it outperforms the baseline model in graph embedding tasks.

关键词： autoencoder Adversarial network Graph embedding Multi-dimensional cloud

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Powered Secure and Scalable Threat Intelligence System With Graph Convolutional autoencoder and Reinforcement Learning Feedback Loop

引用

IEEE ACCESS 2025年 13卷 24736-24748页

作者： Khayat, Mohamad Barka, Ezedin Serhani, Mohamed Adel Sallabi, Farag Shuaib, Khaled Khater, Heba M. United Arab Emirates Univ Coll Informat Technol Al Ain U Arab Emirates Univ Sharjah Coll Comp & Informat Sharjah U Arab Emirates Zagazig Univ Fac Comp & Informat Zagazig 44519 Egypt

As the field of cybersecurity has experienced continual changes, up-to-date techniques have become increasingly necessary to analyze and defend against threats. Furthermore, the current methods consistently produce false alarms and sometimes completely miss real threats. This paper proposes an approach that integrates secure blockchain technology with data preprocessing, deep learning, and reinforcement learning to enhance threat detection and response capabilities. To secure the exchange of threat intelligence information, a safe blockchain network is used, which comprises Byzantine Fault Tolerance for high data integrity and Zero-Knowledge Proofs for access control. All relevant information is cleaned and standardized prior to analysis. Subsequently, graph convolutional neural networks with autoencoders are trained on large unlabeled sets of threat data to automatically label various types of threats, with the system employing fuzzy logic to rank and score possible threats. Furthermore, we implemented a feedback loop that incorporates reinforcement learning, thereby improving model performance over time according to guidance provided by cybersecurity specialists. The proposed system achieved high accuracy, precision, negative predictive value, and MCC, as well as notably low FPR and FNR values. The results establish that the proposed system is a reliable and effective measure for detecting cyberthreats.

关键词： Optimization Computer security autoencoders Fuzzy logic Security Blockchains Accuracy Fish Deep learning Training autoencoder blockchain cybersecurity hybrid optimization reinforcement 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：