检索结果-内蒙古大学图书馆

State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism

引用

JOURNAL OF POWER SOURCES 2023年 556卷

作者： Jiang, Yiyue Chen, Yuan Yang, Fangfang Peng, Weiwen Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen Campus Shenzhen 518107 Peoples R China Guangdong Prov Key Lab Fire Sci & Intelligent Emer Guangzhou Peoples R China Sci & Technol Reliabil Phys & Applicat Technol Ele Guangzhou Peoples R China

Accurate state of health (SOH) estimation is significantly important to ensure the safe and reliable operation of lithium-ion battery. Most existing data-driven estimation methods are based on feature engineering and rely heavily on expert experience and manual operation. However, manually extracting qualified health features requires rich prior knowledge, and these highly-designed features for one specific application may not generalize well to other situations. In this work, an automatic feature extraction method combining convolutional autoencoder and self-attention mechanism is proposed for battery SOH estimation. With preprocessed data fed into the convolutional autoencoder, efficient features characterizing battery health are automatically extracted without human intervention. A self-mechanism module is then further employed to map these high-dimensional abstract health features into battery SOH. Finally, experimental study of battery aging is implemented to demonstrate the proposed method, and comparisons of the proposed method with existing data-driven ap-proaches and the manual feature-based methods have also been presented. With the help of the convolutional autoencoder and self-attention module, the proposed method replaces the conventional manual feature engi-neering with automatic feature extraction, and reaches 0.0048 average test root-mean-squared error (RMSE) and 0.46% mean-absolute-percentage error (MAPE) on our dataset and 3.69% on the NASA public dataset.

关键词： Lithium -ion battery State of health estimation Automatic feature extraction convolutional autoencoder Self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Machine learning enhanced evaluation of semiconductor quantum dots

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-13页

作者： Corcione, Emilio Jakob, Fabian Wagner, Lukas Joos, Raphael Bisquerra, Andre Schmidt, Marcel Wieck, Andreas D. Ludwig, Arne Jetter, Michael Portalupi, Simone L. Michler, Peter Tarin, Cristina Univ Stuttgart Inst Syst Dynam Stuttgart Germany Univ Stuttgart Inst Halbleiteropt & Funkt Grenzflachen Stuttgart Germany Univ Stuttgart Res Ctr SCoPE Stuttgart Germany Univ Stuttgart Ctr Integrated Quantum Sci & Technol Stuttgart Germany Tech Univ Munich Munich Inst Robot & Machine Intelligence Munich Germany Ruhr Univ Bochum Lehrstuhl Angew Festkorperphys Bochum Germany

A key challenge in quantum photonics today is the efficient and on-demand generation of high-quality single photons and entangled photon pairs. In this regard, one of the most promising types of emitters are semiconductor quantum dots, fluorescent nanostructures also described as artificial atoms. The main technological challenge in upscaling to an industrial level is the typically random spatial and spectral distribution in their growth. Furthermore, depending on the intended application, different requirements are imposed on a quantum dot, which are reflected in its spectral properties. Given that an in-depth suitability analysis is lengthy and costly, it is common practice to pre-select promising candidate quantum dots using their emission spectrum. Currently, this is done by hand. Therefore, to automate and expedite this process, in this paper, we propose a data-driven machine-learning-based method of evaluating the applicability of a semiconductor quantum dot as single photon source. For this, first, a minimally redundant, but maximally relevant feature representation for quantum dot emission spectra is derived by combining conventional spectral analysis with an autoencoding convolutional neural network. The obtained feature vector is subsequently used as input to a neural network regression model, which is specifically designed to not only return a rating score, gauging the technical suitability of a quantum dot, but also a measure of confidence for its evaluation. For training and testing, a large dataset of self-assembled InAs/GaAs semiconductor quantum dot emission spectra is used, partially labelled by a team of experts in the field. Overall, highly convincing results are achieved, as quantum dots are reliably evaluated correctly. Note, that the presented methodology can account for different spectral requirements and is applicable regardless of the underlying photonic structure, fabrication method and material composition. We therefore consider it the fir

关键词： Quantum technology Semiconductor quantum dot Single photon source Machine-learning-based evaluation convolutional autoencoder Neural network regression

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Histopathological Images Segmentation Using Deep Learning

引用

SENSORS 2023年第17期23卷 7318-7318页

作者： Drioua, Wafaa Rajaa Benamrane, Nacera Sais, Lakhdar Univ Sci & Technol Oran Mohamed Boudiaf USTO MB Dept Informat Lab SIMPA Oran 31000 Algeria Univ Artois Ctr Rech Informat Lens CRIL CNRS F-62307 Lens France

Hospitals generate a significant amount of medical data every day, which constitute a very rich database for research. Today, this database is still not exploitable because to make its valorization possible, the images require an annotation which remains a costly and difficult task. Thus, the use of an unsupervised segmentation method could facilitate the process. In this article, we propose two approaches for the semantic segmentation of breast cancer histopathology images. On the one hand, an autoencoder architecture for unsupervised segmentation is proposed, and on the other hand, an improvement U-Net architecture for supervised segmentation is proposed. We evaluate these models on a public dataset of histological images of breast cancer. In addition, the performance of our segmentation methods is measured using several evaluation metrics such as accuracy, recall, precision and F1 score. The results are competitive with those of other modern methods.

关键词： semantic segmentation histopathology breast cancer U-Net convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

State of health prediction for li-ion batteries with end-to-end deep learning

引用

JOURNAL OF ENERGY STORAGE 2023年 65卷

作者： Zhu, Chunxiang Gao, Mingyu He, Zhiwei Wu, Heng Sun, Changcheng Zhang, Zhaowei Bao, Zhengyi Hangzhou Dianzi Univ Sch Elect & Informat Engn Hangzhou 310018 Peoples R China Zhejiang Prov Key Lab Equipment Elect Hangzhou 310018 Peoples R China China Jiliang Univ Coll Engn Training Ctr Hangzhou 310018 Peoples R China Univ Hong Kong Fac Engn Pokfulam Rd Hong Kong Peoples R China

State of health prediction for li-ion batteries is one of the hottest research topics of electric vehicles. The complexity of the capacity degradation mechanism makes it possible for deep learning methods to replace modelling and experimental methods. An end-to-end model based on a convolutional autoencoder and bidirectional LSTM combined with data interpolation and augmentation is proposed. First, key fused timing features, such as voltage, current, and temperature, are extracted directly from raw data through a convolutional autoencoder. Then, the fused features are used as the input of the bi-directional LSTM network with dropout technology and a fully connected layer to map to the battery state of health. Finally, the approach is demonstrated on the public NASA and Oxford battery datasets, and the experimental results show that the proposed method predicts capacity degradation well and that the mean absolute error is within 2 %, even when the capacity fluctuates greatly, thus proving its effectiveness.

关键词： Li-ion batteries State of health convolutional autoencoder Bi-directional LSTM Data interpolation and augmentation

来源：评论

学校读者我要写书评

暂无评论

Learning configurations of wires for real-time shape estimation and manipulation planning

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期121卷

作者： Mishani, Itamar Sintov, Avishai Carnegie Mellon Univ Robot Inst 5000 Forbes Ave Pittsburgh PA 12513 USA Tel Aviv Univ Sch Mech Engn Haim Levanon St IL-6997801 Tel Aviv Israel

Robotic manipulation of a wire by its ends requires rapid reasoning of its shape in real-time. A recent development of an analytical model has shown that sensing of the force and torque on one end can be used to determine its shape. However, the model relies on assumptions that may not be met in real world wires and do not take into account gravity and non-linearity of the Force/Torque (F/T) sensor. Hence, the model cannot be applied to any wire with accurate shape estimation. In this paper, we explore the learning of a model to estimate the shape of a wire based solely on measurements of F/T states and without any visual perception. Visual perception is only used for off-line data collection. We propose to train a Supervised autoencoder with convolutional layers that reconstructs the spatial shape of the wire while enforcing the latent space to resemble the space of F/T. Then, the encoder operates as a descriptor of the wire where F/T states can be mapped to its shape. On the other hand, the decoder of the model is the inverse problem where a desired goal shape can be mapped to the required F/T state. With the same collected data, we also learn the mapping from F/T states to grippers poses. Then, a motion planner can plan a path within the F/T space to a goal while avoiding obstacles. We validate the proposed data-based approach on Nitinol and standard electrical wires, and demonstrate the ability to accurately estimate their shapes.

关键词： Elastic wires convolutional autoencoder Shape estimation

来源：评论

学校读者我要写书评

暂无评论

Identifying Cetacean Mammals in High-Resolution Optical Imagery Using Anomaly Detection Approach Employing Machine Learning Models

引用

MOSCOW UNIVERSITY PHYSICS BULLETIN 2023年第SUPPL 1期78卷 S149-S156页

作者： Khabutdinov, I. A. Krinitskiy, M. A. Belikov, R. A. Moscow Inst Phys & Technol Dolgoprudnyi 141701 Moscow Oblast Russia Russian Acad Sci Shirshov Inst Oceanol Moscow 117997 Russia Kazan Fed Univ Kazan 420008 Russia

Cetacean mammal populations, particularly dolphins, have recently experienced significant declines due to various artificial and natural factors. A crucial aspect of studying these populations is determining their numbers and assessing spatial distributions. In our study, we focus onmonitoring dolphin populations in the Black Sea using high-resolution photographs taken from helicopters for counting purposes. Currently, expert analysts manually count dolphins in these images, which is a time-consuming process. To address this issue, we propose the use of machine learning (ML) approaches, specifically, anomaly detection usingMLmodels. We examine a dataset collected during accounting marine expeditions of the Shirshov Institute of Oceanology of the Russian Academy of Sciences (IORAS) in the Black Sea from 2018 to 2019. The dataset consists of 3730 high-resolution photographs, with dolphins present in 205 images (5.5%). Each dolphin occupies approximately 0.005% of an image area (around 49 x 49 pixels), making their presence a rare event. Thus, we treat dolphin identification as an anomaly detection task. Our study compares classical and naive anomaly detectionmethods with reconstruction-based approaches that discriminate anomalies based on the magnitude of reconstruction errors. Within this latter approach, we utilize various artificial neural networks, such as convolutional autoencoders (CAE) and U-Net, for image reconstruction. Overall, our research aims to streamline the process of counting and monitoring dolphin populations in high-resolution imagery using advanced ML techniques.

关键词： anomaly detection machine learning deep learning artificial neural networks U-Net convolutional autoencoder cetacean mammals computer vision

来源：评论

学校读者我要写书评

暂无评论

Research on Multimodal 3D Face Recognition Method Based on Deep Learning

引用

ENGINEERING LETTERS 2023年第4期31卷 1740页

作者： Zhang, Jie Pan, Chengqing Huang, Jinlin Jiangsu Univ Technol Sch Comp Engn Changzhou 213001 Peoples R China China Univ Min & Technol Sch Econ & Management Xuzhou 221116 Peoples R China Jiangsu Univ Technol Sch Elect & Informat Engn Changzhou 213001 Peoples R China

In order to improve the effectiveness and accuracy of multimodal 3D face recognition, this paper proposes a multimodal 3D face recognition method based on deep learning. Firstly, a 3D facial dataset is selected;secondly, noise is removed from the original multimodal 3D facial image by filling in holes, denoising, and removing sharp points. The denoised results in each pixel have a value between 0 and 1. Then, the multimodal 3D facial image dataset is trained using the multimodal fusion network of convolutional autoencoder in deep learning methods to achieve multimodal 3D facial image fusion;finally, mathematical relationships are used to divide facial regions, and DSC descriptors are used to extract contextual features of the 3D model shape. Based on this, facial similarity is calculated to achieve multimodal 3D face recognition based on deep learning. The results show that the algorithm proposed in this paper outperforms the other two algorithms in all cases, regardless of the threshold value. The error recognition rate is low, and the face recognition time is less than 9.6 seconds. This indicates that the method proposed in this paper can effectively improve multimodal 3D face recognition in efficiency and accuracy, with strong application performance.

关键词： Deep learning Multimodal Normalization processing convolutional autoencoder Facial pose parameters

来源：评论

学校读者我要写书评

暂无评论

Deep Structural Contrastive Subspace Clustering 13

Deep Structural Contrastive Subspace Clustering

引用

13th Asian Conference on Machine Learning (ACML)

作者： Peng, Bo Zhu, Wenjie China Jiliang Univ Coll Informat Engn Hangzhou Peoples R China Univ Queensland Brisbane Qld Australia

Deep subspace clustering based on data self-expression is devoted to learning pairwise affinities in the latent feature space. Existing methods tend to rely on an autoencoder framework to learn representations for an affinity matrix. However, the representation learning driven largely by pixel-level data reconstruction is somewhat incompatible with the subspace clustering task. With the unavailability of ground truth, can structural representations, which is exactly what subspace clustering favors, be achieved by simply exploiting the supervision information in the data itself? In this paper, we formulate this intuition as a structural contrastive prediction task and propose an end-to-end trainable framework referred as Deep Structural Contrastive Subspace Clustering (DSCSC). Specifically, DSCSC makes use of data augmentation technique to mine positive pairs and constructs a data similarity graph in the embedding feature space to search negative pairs. A novel structural contrastive loss is proposed on the latent representations to achieve positive-concentrated and negative-separated property for subspace preserving. Extensive experiments on the benchmark datasets demonstrate that our method outperforms the state-of-the-art deep subspace clustering methods and imply the necessity of the proposed structural contrastive loss.

关键词： Deep subspace clustering convolutional autoencoder Contrastive representations

来源：评论

学校读者我要写书评

暂无评论

Agglomerative Clustering of Data Collected by Honeypots 11

Agglomerative Clustering of Data Collected by Honeypots

引用

11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems - Technology and Applications (IDAACS)

作者： Kashtalian, Antonina Savenko, Oleg Sachenko, Anatoliy Khmelnytskyi Natl Univ Khmelnytskyi Ukraine West Ukrainian Natl Univ Ternopol Ukraine

ISBN: (纸本)9781665426053

Identifying new and modified attacks is an important task to ensure the normal operation of computer networks connected to the Internet. Using honeypots and honeynets is one of the effective ways to get information about attackers and their actions as soon as possible. The paper proposes a method of the determination of attack patterns based on information collected by honeypots. To detect patterns, agglomerative clustering of time series of intruders' activity preprocessed by a convolutional encoder is used, the obtained clustering rand index is 82-84%.

关键词： honeypot aglomerative clustering time series convolutional autoencoder attack patterns

来源：评论

学校读者我要写书评

暂无评论

Using ECG signals for hypotensive episode prediction in trauma patients

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022年 223卷 106955-106955页

作者： Rosenfeld, Neta Last, Mark Ben Gurion Univ Negev Dept Software & Informat Syst Engn Negev Israel

Background and objectives: Bleeding is the leading cause of death among trauma patients both in military and civilian scenarios, and it is also the most common cause of preventable death. Identifying a casualty who suffers from an internal bleeding and may deteriorate rapidly and develop hemorrhagic shock and multiorgan failure is a profound challenge. Blood pressure and heart rate are the main vital signs used nowadays for the casualty clinical evaluation in the battlefield and in intensive care unit. However, these vitals tend to deteriorate at a relatively late stage, when the ability to prevent hazardous complications is limited. Identifying, treating, and rapidly evacuating such casualties might mitigate these complications. In this work, we try to improve a state-of-the-art method for early identification of Hypotensive Episode (HE), by adding electrocardiogram signals to several vital ***: In this research, we propose to extend the state-of-the-art HE early detection method, In Window Segmentation (InWise), by adding new types of features extracted from ECG signals. The new predictive features can be extracted from ECG signals both manually and automatically by a convolutional auto-encoder. In addition to InWise, we are trying to predict HE using a Transformer model. The Transformer is using the encoder output as an embedding of the ECG signal. The proposed approach is evaluated on trauma patients data from the MIMIC III ***: We evaluated the InWise prediction algorithm using four different groups of features. The first feature group contains the 93 original features extracted from vital signs. The second group contains, in addition to the original features, 24 features extracted manually from ECG signal (117 features in total). The third group contains the original features and 20 ECG features extracted by the AE (113 features in total), and the last group is the union of all three previous groups containing 137 features. The results s

关键词： Time series analysis Clinical episode prediction Intensive care Patient monitoring Trauma patients Feature extraction convolutional autoencoder XGBoost classifier Transformers

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：