检索结果-内蒙古大学图书馆

Machine learning-based state of charge estimation: A comparison between CatBoost model and C-BLSTM-AE model

MACHINE LEARNING WITH APPLICATIONS 2025年 20卷

作者： Zilali, Abderrahim Adda, Mehdi Ziane, Khaled Berger, Maxime Univ Quebec Rimouski Dept Math informat & genie Rimouski PQ G56 3A1 Canada Ctr Rech & Innovat Intelligence Energet CR2Ie 175 Rue Verendrye Sept Iles PQ G4R 5B7 Canada

The State of Charge (SOC) is a key metric within a Lithium-ion battery management system (BMS). Accurate SOC estimation is essential for enhancing battery longevity and ensuring user safety, making it a critical component of an effective BMS. Although SOC estimation has become an active research area for the machine learning (ML) community, only a handful of works have considered its estimation at negative temperatures. This paper proposes the application of two machine learning-based approaches for SOC estimation that perform well at wide range of temperatures (positive and negative) and varying dynamic loads. The first one is a hybrid deep learning approach based on the Convolutional BLSTM auto-encoder (C-BLSTM-AE) model that relies on extracting abstract features from input data. The second one is a CatBoost model that leverages the gradient boosting technique to enhance the prediction made by its constituent trees. The performance of the models is evaluated by comparing their regression accuracy and computational resource utilization. The C-BLSTM-AE model achieves a low Mean Absolute Error (MAE) of 0.52 % under fixed ambient temperature conditions and maintains a MAE of 1.03 % for variable ambient temperatures. The CatBoost model achieves a MAE of 0.69 % with fixed temperature settings and a MAE of 1.09 % under variable temperature conditions.

关键词： SOC estimation Machine learning Deep learning auto-encoder Gradient Boosting

来源：评论

学校读者我要写书评

暂无评论

Multi-level Distributional Discrepancy Enhancement for Cross Domain Face Forgery Detection 7th

Multi-level Distributional Discrepancy Enhancement for Cross...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Qiu, Lingyu Jiang, Ke Liu, Sinan Tan, Xiaoyang Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China MIIT Key Lab Pattern Anal & Machine Intelligence Nanjing Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing Peoples R China

ISBN: (纸本)9789819784981;9789819784998

Face Forgery Detection (FFD) plays a pivotal role in preserving privacy and bolstering information security by identifying counterfeit face images sourced from the internet. However, FFD encounters a significant challenge in terms of its limited capacity to generalize across diverse datasets due to the striking similarities between genuine and forged images. To tackle this issue, this paper introduces a novel approach known as Multi-level Distributional Discrepancy Enhancement (MDDE). The primary objective of MDDE is to discern variations in the distribution patterns of real and fake data at multiple levels of latent representations. To further enhance its capabilities for generalization, we incorporate a deformable convolution module that extracts intricate features from genuine images. The integration of this module equips MDDE with the ability to generalize to a broader range of samples. Extensive experiments conducted on extensive datasets verify the efficacy of our proposed method and its superior performance compared to several stateof-the-art techniques.

关键词： Deep Learning Face Forgery Detection Variational auto-encoder Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Latent Space Interpolation of Synthesizer Parameters Using Timbre-Regularized auto-encoders

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 3379-3392页

作者： Le Vaillant, Gwendal Dutoit, Thierry Univ Mons Informat Signal & Artificial Intelligence Lab B-7000 Mons Belgium HE2B Inst Super Ind Bruxelles B-1000 Brussels Belgium

Sound synthesizers are ubiquitous in modern music production but manipulating their presets, i.e. the sets of synthesis parameters, demands expert skills. This study presents a novel variational auto-encoder model tailored for black-box synthesizer preset interpolation, which enables the intuitive generation of new presets from pre-existing ones. Leveraging multi-head self-attention networks, the model efficiently learns latent representations of synthesis parameters, aligning these with perceived timbre dimensions through attribute-based regularization. It is able to gradually transition between diverse presets, surpassing traditional linear parametric interpolation methods. Furthermore, we introduce an objective and reproducible evaluation method, based on linearity and smoothness metrics computed on a broad set of audio features. The model's efficacy is demonstrated through subjective experiments, whose results also highlight significant correlations with the proposed objective metrics. The model is validated using a widespread frequency modulation synthesizer with a large set of interdependent parameters. It can be adapted to various commercial synthesizers, and can perform other tasks such as modulations and extrapolations.

关键词： auto-encoder black-box interpolation morphing preset synthesizer timbre auto-encoder black-box interpolation morphing preset synthesizer timbre

来源：评论

学校读者我要写书评

暂无评论

PDAE: Efficient network intrusion detection in IoT using parallel deep auto-encoders

引用

INFORMATION SCIENCES 2022年 598卷 57-74页

作者： Basati, Amir Faghih, Mohammad Mehdi Grad Univ Adv Technol Dept Elect & Comp Engn Kerman Iran

Network intrusion detection is one of the most important components of mobile networks security. In recent years, the application of neural networks has been very popular in network intrusion detection. However, due to limited resources of IoT devices, fast detection of the intrusion requires a high accuracy neural network with a lightweight and efficient architecture. Therefore, the conventional architectures of neural networks are not suitable for intrusion detection in IoT devices due to the use of a large number of parameters in these models concerning the limited processing resources in IoT devices. This paper presents a new and lightweight architecture based on Parallel Deep auto-encoder (PDAE) that uses both locally and surrounding information around individual values in the feature vector. This type of separation of features allows us to increase the accuracy of the model while greatly reducing the number of parameters, memory footprint, and the need for processing power. The effectiveness of the proposed model is evaluated using KDDCup99, CICIDS2017, and UNSW-NB15 datasets and the results shows the superiority of the proposed model over the state-of-the-art algorithms in terms of both accuracy and performance.(c) 2022 Elsevier Inc. All rights reserved.

关键词： Internet of things IoT KDD CICIDS2017 IDS Intrusion detection auto-encoder Convolutional neural networks Tube Model UNSW-NB15

来源：评论

学校读者我要写书评

暂无评论

Stacked convolutional auto-encoders for single space target image blind deconvolution

引用

NEUROCOMPUTING 2018年 313卷 295-305页

作者： Gao, Zhisheng Shen, Chen Xie, Chunzhi Xihua Univ Sch Comp & Software Engn Chengdu 610039 Sichuan Peoples R China

The blind restoration of a scene distorted by atmospheric turbulence remains a challenging problem for space target video surveillance. As there are multiple factors coupling the degradation of space target images, traditional methods based on a single, simplified image blind restoration model have difficulty achieving the desired results. In this paper, a new convolutional auto-encoder deep neural network is proposed for modeling the degradation and restoration process of spatial target images. The whole network consists of two parts, convolution and deconvolution, which are used to achieve the purpose of degraded feature learning and blind image restoration, respectively. Simulation image training data are constructed by a series of 3D space target models and combined with the turbulence multi-factor degradation model. The neural network model is then trained with this data. Contrast experiments are conducted using the simulation image data and real image data, and the results show that the proposed method is robust to noise and the reconstructed images have clearer edge details. The output images also have better continuous consistency and superior visual effects. (C) 2018 Elsevier B.V. All rights reserved.

关键词： auto-encoder Space target image Single image blind deconvolution Turbulence degradation

来源：评论

学校读者我要写书评

暂无评论

Cold-Start Next-Item Recommendation by User-Item Matching and auto-encoders

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2023年第4期16卷 2477-2489页

作者： Wu, Hanrui Wong, Chung Wang Zhang, Jia Yan, Yuguang Yu, Dahai Long, Jinyi Ng, Michael K. Jinan Univ Coll Informat Sci & Technol Guangzhou 510006 Peoples R China Jinan Univ Guangdong Key Lab Tradit Chinese Med Informat Tech Guangzhou 510006 Peoples R China Pazhou Lab Guangzhou 510330 Peoples R China Guangdong Univ Technol Sch Comp Guangzhou 510006 Peoples R China TCL Corp Res Hong Kong Hong Kong Peoples R China Univ Hong Kong Dept Math Hong Kong Peoples R China

Recommendation systems provide personalized service to users and aim at suggesting to them items that they may prefer. There is an increasing requirement of next-item recommendation systems to infer a user's next favor item based on his/her historical selection of items. In this article, we study the next-item recommendation under the cold-start situation, where the users in the system share no interaction with the new items. Specifically, we seek to address the problem from the perspective of zero-shot learning (ZSL), which classifies samples whose classes are unseen during training. To this end, we crystallize the relationship and setting from ZSL to cold-start next-item recommendation, and further propose a novel model called User-Item Matching and auto-encoders (UIMA) which learns the latent embeddings for both users and items by exploiting user historical preferences and item attributes. Concretely, UIMA consists of three components, i.e., two auto-encoders for learning user and item embeddings and a matching network to explore the relationship between the learned user and item embeddings. We perform experiments on several cold-start next-item recommendation datasets, including movies, music, and bookmarks. Promising results demonstrate the effectiveness of the proposed method for cold-start next-item recommendation.

关键词： auto-encoder cold-start item recommendation recommendation systems

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task Graph Neural Network with Variational Graph auto-encoders for Session-Based Travel Packages Recommendation

引用

ACM TRANSACTIONS ON THE WEB 2023年第3期17卷 1-30页

作者： Zhu, Guixiang Cao, Jie Chen, Lei Wang, Youquan Bu, Zhan Yang, Shuxin Wu, Jianqing Wang, Zhiping Nanjing Univ Finance & Econ 3 Wenyuan St Nanjing 210023 Jiangsu Peoples R China Hefei Univ Technol 193Tunxi Rd Hefei 230009 Anhui Peoples R China Nanjing Forestry Univ 159Longpan Rd Nanjing 210094 Jiangsu Peoples R China Nanjing Audit Univ 86Yushan West Rd Nanjing 210023 Jiangsu Peoples R China Jiangxi Univ Sci & Technol 86Red flag Ave Ganzhou 341000 Jiangxi Peoples R China Jiangsu United Credit Co Ltd Nanjing 210023 Jiangsu Peoples R China

Session-based travel packages recommendation aims to predict users' next click based on their current and historical sessions recorded by Online Travel Agencies (OTAs). Recently, an increasing number of studies attempted to apply Graph Neural Networks (GNNs) to the session-based recommendation and obtained promising results. However, most of them do not take full advantage of the explicit latent structure from attributes of items, making learned representations of items less effective and difficult to interpret. Moreover, they only combine historical sessions (long-term preferences) with a current session (short-term preference) to learn a unified representation of users, ignoring the effects of historical sessions for the current session. To this end, this article proposes a novel session-based model named STR-VGAE, which fills subtasks of the travel packages recommendation and variational graph auto-encoders simultaneously. STR-VGAE mainly consists of three components: travel packages encoder, users behaviors encoder, and interaction modeling. Specifically, the travel packages encoder module is used to learn a unified travel package representation from co-occurrence attribute graphs by using multi-view variational graph auto-encoders and a multi-view attention network. The users behaviors encoder module is used to encode user' historical and current sessions with a personalized GNN, which considers the effects of historical sessions on the current session, and coalesce these two kinds of session representations to learn the high-quality users' representations by exploiting a gated fusion approach. The interaction modeling module is used to calculate recommendation scores over all candidate travel packages. Extensive experiments on a real-life tourism e-commerce dataset from China show that STRVGAE yields significant performance advantages over several competitive methods, meanwhile provides an interpretation for the generated recommendation list.

关键词： Travel recommendation graph mining session-based recommendation auto-encoder multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Deep auto-encoders With Sequential Learning for Multimodal Dimensional Emotion Recognition

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2022年 24卷 1313-1324页

作者： Nguyen, Dung Nguyen, Duc Thanh Zeng, Rui Nguyen, Thanh Thi Tran, Son N. Nguyen, Thin Sridharan, Sridha Fookes, Clinton Deakin Univ Sch Informat Technol Geelong Vic 3216 Australia Monash Univ Fac Informat Technol Clayton Vic 3216 Australia Univ Sydney Brain & Mind Ctr Sydney NSW 2006 Australia Univ Tasmania Informat & Commun Technol Hobart Tas 7005 Australia Deakin Univ Appl Artificial Intelligence Inst Geelong Vic 3216 Australia Queensland Univ Technol Speech Audio Image & Video Technol Res Lab Brisbane Qld 4000 Australia Queensland Univ Technol Brisbane Qld Australia

Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making a significant progress in this area. However, several questions still remain unanswered for most of existing approaches including: (i) how to simultaneously learn compact yet representative features from multimodal data, (ii) how to effectively capture complementary features from multimodal streams, and (iii) how to perform all the tasks in an end-to-end manner. To address these challenges, in this paper, we propose a novel deep neural network architecture consisting of a two-stream auto-encoder and a long short term memory for effectively integrating visual and audio signal streams for emotion recognition. To validate the robustness of our proposed architecture, we carry out extensive experiments on the multimodal emotion in the wild dataset: RECOLA. Experimental results show that the proposed method achieves state-of-the-art recognition performance.

关键词： Emotion recognition Feature extraction Long short term memory Visualization Streaming media Convolution Two dimensional displays auto-encoder dimensional emotion recognition long short term memory multimodal emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A New Method for Sentiment Analysis Using Contextual auto-encoders

引用

Journal of Computer Science & Technology 2018年第6期33卷 1307-1319页

作者： Hanen Ameur Salma Jamoussi Abdelmajid Ben Hamadou Multimedia Information Systems and Advanced Computing Laboratory Sfax University Sfax Technopole Sfa 3021 Tunisia

Sentiment analysis, a hot research topic, presents new challenges for understanding users＇ opinions and judg-ments expressed online. They aim to classify the subjective texts by assigning them a polarity label. In this paper, weintroduce a novel machine learning framework using auto-encoders network to predict the sentiment polarity label at theword level and the sentence level. Inspired by the dimensionality reduction and the feature extraction capabilities of theauto-encoders, we propose a new model for distributed word vector representation ＂PMI-SA＂ using as input pointwise-mutual-information ＂PMI＂ word vectors. The resulted continuous word vectors are combined to represent a sentence. Anunsupervised sentence embedding method, called Contextual Recursive auto-encoders ＂CoRAE＂, is also developed forlearning sentence representation. Indeed, CoRAE follows the basic idea of the recursive auto-encoders to deeply composethe vectors of words constituting the sentence, but without relying on any syntactic parse tree. The CoRAE model consistsin combining recursively each word with its context words （neighbors＇ words： previous and next） by considering the wordorder. A support vector machine classifier with fine-tuning technique is also used to show that our deep compositionalrepresentation model CoRAE improves significantly the accuracy of sentiment analysis task. Experimental results demon-strate that CoRAE remarkably outperforms several competitive baseline methods on two databases, namely, Sanders twittercorpus and Facebook comments corpus. The CoRAE model achieves an efficiency of 83.28% with the Facebook dataset and97.57% with the Sanders dataset.

关键词： sentiment analysis recursive auto-encoder stacked auto-encoder pointwise mutual information deep embed-ding representation

来源：评论

学校读者我要写书评

暂无评论

A machine learning classification methodology for Raman Hyperspectral imagery based on auto-encoders

引用

JOURNAL OF RAMAN SPECTROSCOPY 2022年第6期53卷 1126-1139页

作者： Goedhart, Jonne J. Papadakis, Vassilis M. Univ Amsterdam Fac Sci Amsterdam Netherlands Fdn Res & Technol Hellas Inst Mol Biol & Biotechnol N Plastira 100 Iraklion 70013 Greece

Raman spectroscopy is a very sensitive, non-destructive optical technique that is able to characterize the composition of a material. Although it is a very useful technique, its signals are rather complex and therefore require a lot of knowledge and skills to understand their meaning. This complexity increases further, when it is combined with spatial mapping, creating a three-dimensional dataset named Raman hyperspectral imagery. The common methodology of analysing such a dataset is to use a generic supervised classification algorithm (i.e., non-negative least square) combined with reference data. If reference data are not available, unsupervised algorithms are used to perform spectral clusterization of similar areas. This is typically achieved using standard PCA and k-means methods. The most common problem of processing that significantly affects the results of analysis is that a raw Raman Signal consists of three sources: Raman scattering, photoluminescence and noise. The contribution weights of those components are not standard and are changing based on the sample's chemistry, which makes it very difficult to be solved. This creates the necessity for pre-processing methods that can split this raw signal to its components. The goals of this project are to improve the unmixing performance using AI and to achieve a successful split of the raw signal into its three components. Through this study, various unsupervised methods are explored to identify the method that fits best to our microscopic RHSI data sets. Our focus is on using autoencoders for the data analysis and on a Gaussian smoothing filter combined with polynomial fittings to split the data. Results show that the selection of a classification methodology depends greatly on the application, but when a large RHSI dataset is available, the newly proposed splitting technique combined with an autoencoder classification presents the best solution.

关键词： Raman hyperspectral imaging auto-encoder machine learning spectral signal separation unsupervised 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：