检索结果-内蒙古大学图书馆

deep Optimisation: Multi-scale Evolution by Inducing and Searching in deep Representations 24th

Deep Optimisation: Multi-scale Evolution by Inducing and Sea...

24th International Conference on the Applications of Evolutionary Computation (EvoApplications) Held as Part of EvoStar Conference

作者： Caldwell, Jamie Knowles, Joshua Thies, Christoph Kubacki, Filip Watson, Richard Univ Southampton Agents Interact & Complex AIC Res Grp Southampton SO17 1BJ Hants England Invenia Labs Cambridge CB2 1AW England

ISBN: (纸本)9783030726980;9783030726997

The ability of evolutionary processes to innovate and scale up over long periods of time, observed in nature, remains a central mystery in evolutionary biology, and a challenge for algorithm designers to emulate and explain in evolutionary computation (EC). The Major Transitions in Evolution is a compelling theory that explains evolvability through a multi-scale process whereby individuality (and hence selection and variation) is continually revised by the formation of associations between formerly independent entities, a process still not fully explored in EC. deep Optimisation (DO) is a new type of model-building optimization algorithm (MBOA) that exploits deep learning methods to enable multi-scale optimization. DO uses an autoencoder model to induce a multi-level representation of solutions, capturing the relationships between the lower-level units that contribute to the quality of a solution. Variation and selection are then performed within the induced representations, causing model-informed changes to multiple solution variables simultaneously. Here, we first show that DO has impressive performance compared with other leading MBOAs (and other rival methods) on multiple knapsack problems, a standard combinatorial optimization problem of general interest. Going deeper, we then carry out a detailed investigation to understand the differences between DO and other MBOAs, identifying key problem characteristics where other MBOAs are afflicted by exponential running times, and DO is not. This study serves to concretize our understanding of the Major Transitions theory, and why that leads to evolvability, and also provides a strong motivation for further investigation of deep learning methods in optimization.

关键词： Model-Building Optimisation Algorithms deep autoencoder Multi-scale search Problem structure

来源：评论

学校读者我要写书评

暂无评论

Two-step residual-error based approach for anomaly detection in engineering systems using variational autoencoders

引用

COMPUTERS & ELECTRICAL ENGINEERING 2022年 101卷

作者： Gonzalez-Muniz, Ana Diaz, Ignacio Cuadrado, Abel A. Garcia-Perez, Diego Perez, Daniel Univ Oviedo Elect Engn Dept Edif Dept Oeste 2Campus Viesques S-N Gijon 33204 Spain Univ Leon Escuela Ingn SUPPRESS Res Grp Campus Vegazana Leon 24007 Spain

Anomaly detection is a crucial task in the engineering systems field. However, there is usually little or no information about all possible abnormal modes in systems. Hence, a common approach is to build a model of healthy behaviour, based on normal operation data, so that anomaly detection would depend on how well new data fit this model. According to this idea, we propose a residual-error based approach consisting of: a variational autoencoder, used to model the probability density function of the system's healthy behaviour;and a two-step classification algorithm, which classifies the incoming samples based on their residuals, and reports not only their normal/anomalous nature but also that of their components. We have tested this proposal in three different engineering contexts and we have compared its performance with that of state-of-the-art approaches, demonstrating its capability to successfully detect and characterize anomalies.

关键词： Anomaly detection Novelty detection deep autoencoder Variational autoencoder Engineering systems

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based Safe Reinforcement Learning for Power Augmentation in a Lower-limb Exoskeleton 9

AutoEncoder-based Safe Reinforcement Learning for Power Augm...

引用

9th RSI International Conference on Robotics and Mechatronics (ICRoM)

作者： Abbasi, Mohammadreza Vossoughi, Gholamreza Karami, Mohammad Koushki, Amirreza Sharif Univ Technol Dept Mech Engn Tehran Iran

ISBN: (纸本)9781665420945

Power augmentation in wearable robots has recently attracted the attention of researchers in industry and academia. Human-robot synchronized control is one of the most substantial goals that needs to be achieved. The change of gait patterns between different users and cycles, and the close interaction of human and robot necessitates the estimation of human motion intention in real-time. Reinforcement learning (RL) is beneficial in such situations mainly due to its online and model-free nature. However, RL algorithms struggle in high-dimensional continuous search spaces in terms of convergence speed and safety. Therefore, this paper proposes an RL-based control strategy for power augmentation in a lower-limb exoskeleton to extract the human motion and minimize the interaction force. A deep autoencoder (AE) neural network is trained and employed for dimensionality reduction to improve the convergence speed and safety. Simulation and two experiments were carried out with a lower-limb exoskeleton on a healthy participant. The results indicate the efficacy of the proposed control strategy and its superior performance compared to model-based approaches while improving speed and safety.

关键词： Reinforcement Learning deep autoencoder Power Augmentation Interaction Force Lower-limb Exoskeleton

来源：评论

学校读者我要写书评

暂无评论

deep Learning Prediction of Chlorophyll Content in Tomato Leaves 9

Deep Learning Prediction of Chlorophyll Content in Tomato Le...

引用

9th RSI International Conference on Robotics and Mechatronics (ICRoM)

作者： Khoshrou, Mohsen Imanzadeh Zarafshan, Payam Dehghani, Mohammad Chegini, Gholamreza Arabhosseini, Akbar Zakeri, Behzad Univ Tehran Dept Agrotechnol Coll Aburaihan Tehran Iran Univ Tehran Dept Food Technol Coll Aburaihan Tehran Iran

ISBN: (纸本)9781665420945

Precision agriculture has improved crops production around the world. Non-destructive evaluation of chlorophyll contents of plant leaves can be a useful solution, in the field of precision farming. In order to take the required measures, sometimes it is essential to precisely evaluate the chlorophyll content, without cutting the target leaves. In this work, a deep learning methodology is proposed to assess the quantity of chlorophyll in the leaves of the tomato plants, through image processing. This methodology can be extended to any other type of leaves. The proposed method consists of a convolutional denoising autoencoder, to reduce the ambient light noises. Then, using a deep autoencoder network, the valuable features of the plant leaf image are extracted and fed as input to another neural network that evaluates the chlorophyll content of the leaf, taking advantage of support vector regression. To validate the accuracy of the proposed method, measurements were performed using the SPAD chlorophyll meter. The validation results prove the desired accuracy and efficiency of the developed approach.

关键词： Chlorophyll estimation Convolutional neural network (CNN) deep autoencoder Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

deep Multi-view Subspace Clustering Network with Exclusive Constraint 40

Deep Multi-view Subspace Clustering Network with Exclusive C...

引用

40th Chinese Control Conference (CCC)

作者： Ma Rui Zhou Zhiping Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Engn Res Ctr Internet Things Technol Applicat Min Wuxi 214122 Jiangsu Peoples R China

ISBN: (纸本)9789881563804

Multi-view subspace clustering aims to find the inherent structure of data as much as possible by fusing complementary information of multiple views to achieve better clustering results. However, most of the traditional multi-view subspace clustering algorithms are only shallow clustering algorithms, which does not capture the deep information of the data well, and does not conduct in- depth research at the self- representation level of the data. To this end, this paper proposes a novel deep multi-view subspace clustering model that introduces exclusive constraints. A deep autoencoder is used to perform nonlinear low-dimensional subspace mapping for each view to learn the deep structure of the original data. To better retain multiple views' local structure and better reflect the complementarity, the exclusive constraints are introduced into the self-representation matrix which located in the middle layer of the deep autoencoder. The multi-view consensus self-representation matrix is used to capture the consistency information between the multi-view data. The update of autoencoder parameters and clustering parameters are iteratively optimized under the same learning framework to improve the clustering performance. Experiments on multi-view data sets prove that this method can better dig out the inherent complementary structure of multi-view data, which reflects the superiority of this method.

关键词： Multi-view clustering deep autoencoder Exclusive constraint Self-expression

来源：评论

学校读者我要写书评

暂无评论

Accelerating Robot Reinforcement Learning with Accumulation of Knowledge

Accelerating Robot Reinforcement Learning with Accumulation ...

引用

30th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD)

作者： Loncarevic, Zvezdan Gams, Andrej Jozef Stefan Inst Jamova Cesta 39 Ljubljana 1000 Slovenia Jozef Stefan Int Postgrad Sch Jamova Cesta 39 Ljubljana 1000 Slovenia

ISBN: (纸本)9783030752613;9783030752590;9783030752583

Reinforcement Learning (RL) can be applied in robotics to refine robot skills, but it may take several tens or even hundreds of attempts, which are typically just forgotten. In this paper, we show how all learning attempts, even those that do not fulfill the intended task, can be used to accelerate RL on the long-run. In a manner of non-continual lifelong learning we re-train a deep neural network that maps between the desired target/action outcome and the action in order to provide an initial estimate. Furthermore, for even faster learning, it is performed in reduced - latent space of a deep autoencoder. Robot throwing experiments clearly indicate, that the proposed methodology accelerates RL.

关键词： deep autoencoder Reinforcement learning Neural networks Robotic throwing

来源：评论

学校读者我要写书评

暂无评论

Data-driven learning to identify biomarkers in bipolar disorder

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022年 226卷 107112-107112页

作者： Li, Zhuangzhuang Li, Wenmei Yan, Wei Zhang, Rongrong Xie, Shiping Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Sch Geog & Biol Informat Nanjing 210023 Peoples R China Nanjing Med Univ Dept Psychiat Affiliated Nanjing Brain Hosp Nanjing 210029 Peoples R China

Background and Objective: Bipolar disorder (BD) is one of the primary causes of disability globally and can be easily misdiagnosed as schizophrenia or major depression due to their similar symptoms. Hence, it is of great significance to explore the pathogenesis of BD. Statistical analysis is currently the most common method for exploring the neuropathological mechanisms of psychiatric disorders. However, this method only considers the relationship between groups and does not reflect the individual-level diagnosis. There-fore, we developed machine learning algorithms to measure pathological brain changes in psychiatric dis-orders. Methods: An autoencoder and a feature selection method are proposed to identify the abnormal structural patterns of BD in this study. The autoencoder was constructed using structural imaging data from 1113 healthy controls, which aims to define the normal range of anatomical deviations to distin-guish healthy individuals from BD patients. The biomarkers of BD were identified by the reconstruction errors in each brain region. The proposed feature selection (FS)-select framework aimed to determine the optimal FS method and identify the most reproducible feature associated with BD. Results: We found that the left orbital region of the middle frontal gyrus had the greatest difference between healthy controls and BD patients using a trained autoencoder. The most reproducible feature was the left orbital region of the middle frontal gyrus by FS-select framework when using the different cross-validation strategies. Conclusions: A consistent result was obtained from the above two proposed methods wherein a signifi-cant difference between healthy controls and BD patients was identified in the left orbital region of the middle frontal gyrus.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Bipolar disorder Structural magnetic functional imaging deep autoencoder Feature selection

来源：评论

学校读者我要写书评

暂无评论

Bagging deep autoencoders with Dynamic Threshold for Semi-Supervised Anomaly Detection 2

Bagging Deep Autoencoders with Dynamic Threshold for Semi-Su...

引用

2nd International Conference on Image and Video Processing, and Artificial Intelligence (IPVAI)

作者： Guo, Bingjun Song, Lei Zheng, Taisheng Liang, Haoran Wang, Hongfei Chinese Acad Sci Technol & Engn Ctr Space Utilizat Key Lab Space Utilizat Beijing 100094 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (数字)9781510634107

ISBN: (纸本)9781510634107

In the field of anomaly detection, anomalies are usually very rare compared with normal samples, which is not conducive to the construction of anomaly detection model. In this paper, we propose a semi-supervised anomaly detection algorithm based on deep autoencoder. With this algorithm, only normal samples are needed to train anomaly detection model. To improve the robustness of the algorithm, Bagging ensemble method is used to train and combine multiple deep autoencoders. In the process of Bagging, dynamic threshold for anomaly detection is applied to increase the diversity of individual autoencoder. Compared with other semi-supervised methods including one-class SVM, SOM and K-Means, our proposed method has obvious superiority in the behavior of anomaly detection.

关键词： Anomaly detection deep autoencoder Bagging dynamic threshold

来源：评论

学校读者我要写书评

暂无评论

deep learning shear capacity prediction of fibrous recycled aggregate concrete beams strengthened by side carbon fiber-reinforced polymer sheets

引用

COMPOSITE STRUCTURES 2022年 300卷

作者： Ghoniem, Amr Zagazig Univ Fac Engn Struct Engn Dept Zagazig 44519 Egypt

The goal of this paper is to evaluate the shear capacity of fibrous recycled aggregate concrete beams side bonded with carbon fiber-reinforced polymer (CFRP) based on numerical modeling and deep learning. Forty-five models were numerically investigated in ANSYS with different lengths and layers of vertical CFRP sheets. Concrete properties built for coarse recycled aggregate and various fibers as 3D and 5D steel, synthetic, and hybrid fibers added at a 0.75% volume fraction. Finally, feedforward, cascade-forward backpropagation, and NARX network algorithms were adopted to predict the shear capacity. Shear capacity improvement was significantly affected by CFRP rehabilitation. Double-layered rehabilitation applied on the zone between support and load was the most adequate. The performance of cascade-forward backpropagation in the estimation of shear capacity was superior to the other deep autoencoder models. The present paper offers good guidance on the practice field as a valuable supplement to the laboratory investigation and theoretical calculations.

关键词： CFRP Concrete properties deep autoencoder Hybrid fiber Numerical RCA

来源：评论

学校读者我要写书评

暂无评论

Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection

引用

INFORMATION PROCESSING & MANAGEMENT 2022年第2期59卷 102844-102844页

作者： An, Peng Wang, Zhiyuan Zhang, Chunjiong Ningbo Univ Technol Coll Elect & Informat Engn Ningbo 315211 Zhejiang Peoples R China Tongji Univ Int Coll Football Shanghai 200092 Peoples R China Tongji Univ Dept Comp Sci Shanghai 201804 Peoples R China

Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distribution for each domain, ignoring the robust testing of data skewness. This paper proposes to use unsupervised ensemble autoencoders connected to the Gaussian mixture model (GMM) to adapt to multiple domains regardless of the skewness of each domain. In the hidden space of the ensemble autoencoder, the attention-based latent representation and reconstructed features of the minimum error are utilized. The expectation maximization (EM) algorithm is used to estimate the sample density in the GMM. When the estimated sample density exceeds the learning threshold obtained in the training phase, the sample is identified as an outlier related to an attack anomaly. Finally, the ensemble autoencoder and the GMM are jointly optimized, which transforms the optimization of objective function into a Lagrangian dual problem. Experiments conducted on three public data sets validate that the performance of the proposed model is significantly competitive with the selected anomaly detection baselines.

关键词： Multidomain data Cyberattacks deep autoencoder GMM

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：