检索结果-内蒙古大学图书馆

Unsupervised Sequential Outlier Detection With Deep Architectures

IEEE TRANSACTIONS ON IMAGE PROCESSING 2017年第9期26卷 4321-4330页

作者： Lu, Weining Cheng, Yu Xiao, Cao Chang, Shiyu Huang, Shuai Liang, Bin Huang, Thomas Tsinghua Univ Dept Automat Beijing 100084 Peoples R China IBM TJ Watson Res Ctr Yorktown Hts NY 10562 USA Univ Washington Dept Ind & Syst Engn Seattle WA 98105 USA Univ Illinois Beckman Inst Urbana IL 61801 USA

Unsupervised outlier detection is a vital task and has high impact on a wide variety of applications domains, such as image analysis and video surveillance. It also gains longstanding attentions and has been extensively studied in multiple research areas. Detecting and taking action on outliers as quickly as possible are imperative in order to protect network and related stakeholders or to maintain the reliability of critical systems. However, outlier detection is difficult due to the one class nature and challenges in feature construction. Sequential anomaly detection is even harder with more challenges from temporal correlation in data, as well as the presence of noise and high dimensionality. In this paper, we introduce a novel deep structured framework to solve the challenging sequential outlier detection problem. We use autoencoder models to capture the intrinsic difference between outliers and normal instances and integrate the models to recurrent neural networks that allow the learning to make use of previous context as well as make the learners more robust to warp along the time axis. Furthermore, we propose to use a layerwise training procedure, which significantly simplifies the training procedure and hence helps achieve efficient and scalable training. In addition, we investigate a fine-tuning step to update all parameters set by incorporating the temporal correlation in the sequence. We further apply our proposed models to conduct systematic experiments on five real-world benchmark data sets. Experimental results demonstrate the effectiveness of our model, compared with other state-of-the-art approaches.

关键词： Sequential anomaly detection deep learning denoising autoencoder recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Parallel multi-head attention and term-weighted question embedding for medical visual question answering

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第22期82卷 34937-34958页

作者： Manmadhan, Sruthy Kovoor, Binsu C. Cochin Univ Sci & Technol Div Informat Technol Kochi 682022 Kerala India NSS Coll Engn Dept Comp Sci & Engn Palakkad 678008 Kerala India

The goal of medical visual question answering (Med-VQA) is to correctly answer a clinical question posed by a medical image. Medical images are fundamentally different from images in the general domain. As a result, using general domain Visual Question Answering (VQA) models to the medical domain is impossible. Furthermore, the large-scale data required by VQA models is rarely available in the medical arena. Existing approaches of medical visual question answering often rely on transfer learning with external data to generate good image feature representation and use cross-modal fusion of visual and language features to acclimate to the lack of labelled data. This research provides a new parallel multi-head attention framework (MaMVQA) for dealing with Med-VQA without the use of external data. The proposed framework addresses image feature extraction using the unsupervised denoising Auto-Encoder (DAE) and language feature extraction using term-weighted question embedding. In addition, we present qf-MI, a unique supervised term-weighting (STW) scheme based on the concept of mutual information (MI) between the word and the corresponding class label. Extensive experimental findings on the VQA-RAD public medical VQA benchmark show that the proposed methodology outperforms previous state-of-the-art methods in terms of accuracy while requiring no external data to train the model. Remarkably, the presented MaMVQA model achieved significantly increased accuracy in predicting answers to both close-ended (78.68%) and open-ended (55.31%) questions. Also, an extensive set of ablations are studied to demonstrate the significance of individual components of the system.

关键词： Multi-head attention denoising autoencoder Radiology images Supervised term weighting Visual question answering VQA-RAD

来源：评论

学校读者我要写书评

暂无评论

Homotopy optimisation based NMF for audio source separation

引用

IET SIGNAL PROCESSING 2018年第9期12卷 1099-1106页

作者： Koundinya, Sriharsha Karmakar, Abhijit CEERI CSIR Integrated Syst Grp Pilani Rajasthan India Acad Sci & Innovat Res Madras Tamil Nadu India

In this study, the authors propose a novel framework for audio source separation based on a cascaded non-negative matrix factorisation (NMF) using homotopy optimisation with perturbation and ensemble (HOPE) and denoising autoencoder. NMF using traditional optimisation has a problem of finding a global solution, and hence could not achieve complete separation of the sources from the mixture. This problem has been addressed using homotopy optimisation in this study. Subsequently, using denoising autoencoder the residual sounds that are usually observed in the separated sources are removed. The enhanced audio signals are filtered using Wiener techniques to obtain the separated signals. The homotopy-based NMF is applied for separating singing voice and drums from song samples using a single-channel mixture. The separated signals are compared with other NMF algorithms by using Blind Source Separation (BSS) Eval objective quality measures. The NMF with HOPE and denoising autoencoder is shown to provide an improvement of up to 6dB in comparison with other NMF algorithms.

关键词： audio signal processing blind source separation source separation matrix decomposition denoising autoencoder traditional optimisation complete separation separated sources enhanced audio signals separated signals homotopy-based NMF separating singing voice drums NMF algorithms homotopy optimisation-based NMF audio source separation nonnegative matrix factorisation noise figure 6 0 dB

来源：评论

学校读者我要写书评

暂无评论

A novel Enhanced Collaborative autoencoder with knowledge distillation for top-N recommender systems

引用

NEUROCOMPUTING 2019年 332卷 137-148页

作者： Pan, Yiteng He, Fazhi Yu, Haiping Wuhan Univ Sch Comp Sci Wuhan Hubei Peoples R China

In most recommender systems, the data of user feedbacks are usually represented with a set of discrete values, which are difficult to exactly describe users' interests. This problem makes it not easy to exactly model users' latent preferences for recommendation. Intuitively, a basic idea for this issue is to predict continuous values through a trained model to reveal users' essential feedbacks, and then make use of the generated data to retrain another model to learn users' preferences. However, since these continuous data are generated by an imperfect model which are trained by discrete data, there exists a lot of noise among the generated data. This problem may have a severe adverse impact on the performance. Towards this problem, we propose a novel Enhanced Collaborative autoencoder (ECAE) to learn robust information from generated soft data with the technique of knowledge distillation. First, we propose a tightly coupled structure to incorporate the generation and retraining stages into a unified framework. So that the generated data can be fine tuned to reduce the noise by propagating training errors of retraining network. Second, for that each unit of the generated data contains different level of noise, we propose a novel distillation layer to balance the influence of noise and knowledge. Finally, we propose to take both predict results of generation and retraining network into account to make final recommendations for each user. The experimental results on four public datasets for top-N recommendation show that the ECAE model performs better than several state-of-the-art algorithms on metrics of MAP and NDCG. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Recommender system Knowledge distillation Neural network denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Software Defect Prediction Based on Non-Linear Manifold Learning and Hybrid Deep Learning Techniques

引用

Computers, Materials & Continua 2020年第11期65卷 1467-1486页

作者： Kun Zhu Nana Zhang Qing Zhang Shi Ying Xu Wang School of Computer Science Wuhan UniversityWuhan430072China School of Information Science and Engineering Qufu Normal UniversityRizhao276826China Department of Computer Science Vrije University AmsterdamAmsterdam1081HVThe Netherlands

Software defect prediction plays a very important role in software quality assurance,which aims to inspect as many potentially defect-prone software modules as ***,the performance of the prediction model is susceptible to high dimensionality of the dataset that contains irrelevant and redundant *** addition,software metrics for software defect prediction are almost entirely traditional features compared to the deep semantic feature representation from deep learning *** address these two issues,we propose the following two solutions in this paper:(1)We leverage a novel non-linear manifold learning method-SOINN Landmark Isomap(SL-Isomap)to extract the representative features by selecting automatically the reasonable number and position of landmarks,which can reveal the complex intrinsic structure hidden behind the defect data.(2)We propose a novel defect prediction model named DLDD based on hybrid deep learning techniques,which leverages denoising autoencoder to learn true input features that are not contaminated by noise,and utilizes deep neural network to learn the abstract deep semantic *** combine the squared error loss function of denoising autoencoder with the cross entropy loss function of deep neural network to achieve the best prediction performance by adjusting a *** compare the SL-Isomap with seven state-of-the-art feature extraction methods and compare the DLDD model with six baseline models across 20 open source software *** experimental results verify that the superiority of SL-Isomap and DLDD on four evaluation indicators.

关键词： Software defect prediction non-linear manifold learning denoising autoencoder deep neural network loss function deep learning

来源：评论

学校读者我要写书评

暂无评论

IMDAC: A robust intelligent software defect prediction model via multi-objective optimization and end-to-end hybrid deep learning networks

引用

SOFTWARE-PRACTICE & EXPERIENCE 2024年第2期54卷 308-333页

作者： Zhu, Kun Zhang, Nana Jiang, Changjun Zhu, Dandan Tongji Univ Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai Peoples R China Tongji Univ Natl Prov Minist Joint Collaborat Innovat Ctr Fina Shanghai Peoples R China Donghua Univ Sch Comp Sci & Technol Shanghai Peoples R China East China Normal Univ Inst AI Educ Shanghai Peoples R China Donghua Univ Sch Comp Sci & Technol 2999Renmin North Rd Shanghai 201620 Peoples R China

Software defect prediction (SDP) aims to build an effective prediction model for historical defect data from software repositories by some specialized techniques or algorithms, and predict the defect proneness of new software modules. Nevertheless, the complex internal intrinsic structure hidden behind the defect data makes it challenging for the built prediction model to capture the most expressive defect feature representations, and largely limits the SDP performance. Fortunately, artificial intelligence is interacting closely with humans and provides powerful intelligent technical support for addressing these SDP issues. In this article, we propose a robust intelligent SDP model called IMDAC based on deep learning and soft computing techniques. This model has three main advantages: (1) an effective deep generative network-InfoGAN (information maximizing GANs) is employed to conduct data augmentation, namely generating sufficient defect instances and achieving defect class balance simultaneously. (2) Select the fewest representative feature subset for the minimum error via an advanced multi-objective optimization approach-MSEA (multi-stage evolutionary algorithm). (3) Build a powerful end-to-end deep defect predictor by hybrid deep learning techniques-DAE (denoising autoencoder) and CNN (convolutional neural network), which can not only reconstruct a clean "repaired" input with strong robustness and generalization capabilities via DAE, but also learn the abstract deep semantic features with strong discriminating capability via CNN. Experimental results verify the superiority and robustness of the IMDAC model across 15 software projects.

关键词： convolutional neural network deep learning denoising autoencoder multi-objective optimization software defect prediction

来源：评论

学校读者我要写书评

暂无评论

Fast learning in Deep Neural Networks

引用

NEUROCOMPUTING 2016年 171卷 1205-1215页

作者： Chandra, B. Sharma, Rajesh K. Indian Inst Technol Dept Math Comp Sci Grp Delhi India Indian Inst Technol Dept Math Delhi India

The paper aims at speeding up Deep Neural Networks (DNN) since this is one of the major bottlenecks in deep learning. This has been achieved by parameterizing the weight matrix using low rank factorization and periodic functions. By parameterization, the weight matrix is split into two matrices of smaller size of rank K with periodic functions. A shrinkage parameter has been introduced which helps in reducing the number of parameters and thus helps in increasing the speed to a great extent. Performance of the proposed parameterization is compared with standard DNN, DNN based on weight factorization alone and on periodic-bounded weights. This has been demonstrated on benchmark datasets MNIST and MNIST variants. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Deep learning Deep Neural Network denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based motion artifact removal in functional near-infrared spectroscopy

引用

NEUROPHOTONICS 2022年第4期9卷 41406页

作者： Gao, Yuanyuan Chao, Hanqing Cavuoto, Lora Yan, Pingkun Kruger, Uwe Norfleet, Jack E. Makled, Basiel A. Schwaitzberg, Steven De, Suvranu Intes, Xavier Rensselaer Polytech Inst Ctr Modeling Simulat & Imaging Med Troy NY 12180 USA Rensselaer Polytech Inst Dept Biomed Engn Troy NY 12180 USA Univ Buffalo Dept Ind & Syst Engn Buffalo NY USA US Army Combat Capabil Dev Command Soldier Ctr Orlando FL USA SFC Paul Ray Smith Simulat & Training Technol Ctr Orlando FL USA Med Simulat Res Branch Orlando FL USA Univ Buffalo Dept Surg Buffalo NY USA

Significance: Functional near-infrared spectroscopy (fNIRS), a well-established neuroimaging technique, enables monitoring cortical activation while subjects are unconstrained. However, motion artifact is a common type of noise that can hamper the interpretation of fNIRS data. Current methods that have been proposed to mitigate motion artifacts in fNIRS data are still dependent on expert-based knowledge and the post hoc tuning of parameters. Aim: Here, we report a deep learning method that aims at motion artifact removal from fNIRS data while being assumption free. To the best of our knowledge, this is the first investigation to report on the use of a denoising autoencoder (DAE) architecture for motion artifact removal. Approach: To facilitate the training of this deep learning architecture, we (i) designed a specific loss function and (ii) generated data to mimic the properties of recorded fNIRS sequences. Results: The DAE model outperformed conventional methods in lowering residual motion artifacts, decreasing mean squared error, and increasing computational efficiency. Conclusion: Overall, this work demonstrates the potential of deep learning models for accurate and fast motion artifact removal in fNIRS data. (c) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

关键词： functional near-infrared spectroscopy motion artifact deep learning denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals

引用

WIRELESS NETWORKS 2019年第7期25卷 3735-3746页

作者： Xu, Yu Li, Dezhi Wang, Zhenyong Guo, Qing Xiang, Wei Harbin Inst Technol Sch Elect & Informat Engn Harbin Peoples R China

Automatic modulation classification plays an important role in many fields to identify the modulation type of wireless signals in order to recover signals by demodulation. In this paper, we contribute to explore the suitable architecture of deep learning method in the domain of communication signal recognition. Based on architecture analysis of the convolutional neural network, we used real signal data generated by instrument as dataset, and achieved compatible recognition accuracy of modulation classification compared with several representative structure. We state that the deeper network architecture is not suitable for the signal recognition due to its different characteristic. In addition, we also discuss the difficult of training algorithm in deep learning methods and employ the transfer learning method in order to reap the benefits, which stabilize the training process and lift the performance. Finally, we adopt the denoising autoencoder to preprocess the received data and provide the ability to resist finite perturbations of the input. It contributes to a higher recognition accuracy and it also provide a new idea to design the denoising modulation recognition model.

关键词： Modulation classification Deep learning Convolutional neural network Wireless signal Transfer learning denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Opening the Black Box: Towards inherently interpretable energy data imputation models using building physics insight

引用

ENERGY AND BUILDINGS 2024年 310卷

作者： Liguori, Antonio Quintana, Matias Fu, Chun Miller, Clayton Frisch, Jerome van Treeck, Christoph Rhein Westfal TH Aachen E3D Inst Energy Efficiency & Sustainable Bldg Mathieustr 30 D-52074 Aachen Germany Singapore ETH Ctr Future Cities Lab Global Singapore Singapore Natl Univ Singapore NUS Coll Design & Engn Dept Built Environm Singapore Singapore

Missing data are frequently observed by practitioners and researchers in the building energy modeling community. In this regard, advanced data-driven solutions, such as Deep Learning methods, are typically required to reflect the non-linear behavior of these anomalies. As an ongoing research question related to Deep Learning, a model's applicability to limited data settings can be explored by introducing prior knowledge in the network. This same strategy can also lead to more interpretable predictions, hence facilitating the field application of the approach. For that purpose, the aim of this paper is to propose the use of Physics-informed denoising autoencoders (PI-DAE) for missing data imputation in commercial buildings. In particular, the presented method enforces physics-inspired soft constraints to the loss function of a denoising autoencoder (DAE). In order to quantify the benefits of the physical component, an ablation study between different DAE configurations is conducted. First, three univariate DAEs are optimized separately on indoor air temperature, heating, and cooling data. Then, two multivariate DAEs are derived from the previous configurations. Eventually, a building thermal balance equation is coupled to the last multivariate configuration to obtain PI-DAE. Additionally, two commonly used benchmarks are employed to support the findings. It is shown how introducing physical knowledge in a multivariate denoising autoencoder can enhance the inherent model interpretability through the optimized physics-based coefficients. While no significant improvement is observed in terms of reconstruction error with the proposed PI-DAE, its enhanced robustness to varying rates of missing data and the valuable insights derived from the physics-based coefficients create opportunities for wider applications within building systems and the built environment.

关键词： Physics-informed neural networks denoising autoencoder Building energy data Interpretability Missing data

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：