检索结果-内蒙古大学图书馆

A Hybrid deep Ensemble for Speech Disfluency Classification

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2021年第8期40卷 3968-3995页

作者： Pravin, Sheena Christabel Palanivelan, M. Rajalakshmi Engn Coll Dept ECE Chennai Tamil Nadu India

In this paper, a novel Hybrid deep Ensemble (HDE) is proposed for automatic speech disfluency classification on a sparse speech dataset. Categorizations of speech disfluencies for diagnosis of speech disorders have so long relied on sophisticated deep learning models. Such a task can be accomplished by a straightforward approach with high accuracy by the proposed model which is an optimal combination of diverse machine learning and deep learning algorithms in a hierarchical arrangement which includes a deep autoencoder that yields the compressed latent features. The proposed model has shown considerable improvement in downgrading processing time overcoming the issues of cumbersome hyper-parameter tuning and huge data demand of the deep learning algorithms with high classification accuracy. Experimental results show that the proposed Hybrid deep Ensemble has superior performance compared to the individual base learners, and the deep neural network as well. The proposed model and the baseline models were evaluated in terms of Cohen's kappa coefficient, Hamming loss, Jaccard score, F-score and classification accuracy.

关键词： Hybrid deep Ensemble Speech disfluency classification Sparse speech dataset deep autoencoder Latent features

来源：评论

学校读者我要写书评

暂无评论

Edge2vec: Edge-based Social Network Embedding

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2020年第4期14卷 45-45页

作者： Wang, Changping Wang, Chaokun Wang, Zheng Ye, Xiaojun Yu, Philip S. Tsinghua Univ Sch Software Beijing Peoples R China Univ Illinois Dept Comp Sci Chicago IL USA

Graph embedding, also known as network embedding and network representation learning, is a useful technique which helps researchers analyze information networks through embedding a network into a low-dimensional space. However, existing graph embedding methods are all node-based, which means they can just directly map the nodes of a network to low-dimensional vectors while the edges could only be mapped to vectors indirectly. One important reason is the computational cost, because the number of edges is always far greater than the number of nodes. In this article, considering an important property of social networks, i.e., the network is sparse, and hence the average degree of nodes is bounded, we propose an edge-based graph embedding (edge2vec) method to map the edges in social networks directly to low-dimensional vectors. Edge2vec takes both the local and the global structure information of edges into consideration to preserve structure information of embedded edges as much as possible. To achieve this goal, edge2vec first ingeniously combines the deep autoencoder and Skip-gram model through a well-designed deep neural network. The experimental results on different datasets show edge2vec benefits from the direct mapping in preserving the structure information of edges.

关键词： Graph embedding deep autoencoder skip-gram Edge2vec

来源：评论

学校读者我要写书评

暂无评论

A transfer learning-based efficient spatiotemporal human action recognition framework for long and overlapping action classes

引用

JOURNAL OF SUPERCOMPUTING 2022年第2期78卷 2873-2908页

作者： Bilal, Muhammad Maqsood, Muazzam Yasmin, Sadaf Ul Hasan, Najam Rho, Seungmin COMSATS Univ Islamabad Dept Comp Sci Attock Campus Attock Pakistan Dhofar Univ Coll Engn Dept Elect & Comp Engn Salalah Oman Chung Ang Univ Dept Ind Secur Seoul 06974 South Korea

deep learning base solutions for computer vision made life easier for humans. Video data contain a lot of hidden information and patterns, that can be used for Human Action Recognition (HAR). HAR can apply to many areas, such as behavior analysis, intelligent video surveillance, and robotic vision. Occlusion, viewpoint variation, and illumination are some issues that make the HAR task more difficult. Some action classes have similar actions or some overlapping parts in them. This, among many other problems, is the main reason that contributes the most to misclassification. Traditional hand-engineering and machine learning-based solutions lack the ability to handle overlapping actions. In this paper, we propose a deep learning-based spatiotemporal HAR framework for overlapping human actions in long videos. Transfer learning techniques are used for deep feature extraction. Fine-tuned pre-trained CNN models learn the spatial relationship at the frame level. An optimized deep autoencoder was used to squeeze high-dimensional deep features. An RNN with LSTM was used to learn the long-term temporal relationships. An iterative module added at the end to fine-tune the trained model on new videos that learns and adopt changes. Our proposed framework achieved state-of-the-art performance in spatiotemporal HAR for overlapping human actions in long visual data streams for non-stationary surveillance environments.

关键词： Human action recognition Overlapping actions Transfer learning Video content analysis deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Subspace Clustering via Adaptive Graph Regularized autoencoder

引用

IEEE ACCESS 2019年 7卷 74122-74133页

作者： Ji, Qiang Sun, Yanfeng Gao, Junbin Hu, Yongli Yin, Baocai Beijing Adv Innovat Ctr Future Internet Technol Beijing 100124 Peoples R China Univ Sydney Business Sch Discipline Business Analyt Sydney NSW 2006 Australia Dalian Univ Technol Fac Elect Informat & Elect Engn Coll Comp Sci & Technol Dalian 116620 Peoples R China

Most existing subspace clustering methods focus on learning a meaningful (e.g., sparse or low-rank) representation of the data. However, they have the following two problems which greatly limit the performance: 1) They neglect the intrinsic local geometrical structures within the data to result in locality preserving property be missing. 2) They neglect the feature learning of the raw data which is usually so complex that the learned representation coefficient is not an optimal graph for clustering. This paper addresses the above problems and proposes a novel nonlinear subspace clustering model via adaptive graph regularized autoencoder (NSC-AGA). This model unifies feature learning, locality preserving, and representation matrix learning into a framework, and a new adaptive graph regularizer is introduced, which takes the representation coefficient matrix as a learnable similarity graph imposed on the Euclidean distance matrix of the deep features. Two matrices interact with each other to make the representation coefficient matrix reflect both the global linear correlation and the local geometric distance relationship. A number of experimental results on the five public image database demonstrate that the proposed NSC-AGA model achieves superior clustering performance compared with the state-of-the-art methods.

关键词： Nonlinear subspace clustering adaptive graph regularizer deep autoencoder feature learning

来源：评论

学校读者我要写书评

暂无评论

An Overview of deep Generative Models

引用

IETE TECHNICAL REVIEW 2015年第2期32卷 131-139页

作者： Xu, Jungang Li, Hui Zhou, Shilong Univ Chinese Acad Sci Sch Comp & Control Engn Beijing 101408 Peoples R China

As an important category of deep models, deep generative model has attracted more and more attention with the proposal of deep Belief Networks (DBNs) and the fast greedy training algorithm based on restricted Boltzmann machines (RBMs). In the past few years, many different deep generative models are proposed and used in the area of Artificial Intelligence. In this paper, three important deep generative models including DBNs, deep autoencoder, and deep Boltzmann machine are reviewed. In addition, some successful applications of deep generative models in image processing, speech recognition and information retrieval are also introduced and analysed.

关键词： deep belief networks Restricted boltzmann machine deep autoencoder deep generative model deep boltzmann machine

来源：评论

学校读者我要写书评

暂无评论

Index tracking through deep latent representation learning

引用

QUANTITATIVE FINANCE 2020年第4期20卷 639-652页

作者： Kim, Saejoon Kim, Soong Sogang Univ Dept Comp Sci & Engn 35 Baekbeom Ro Seoul 04107 South Korea

We consider the problem of index tracking whose goal is to construct a portfolio that minimizes the tracking error between the returns of a benchmark index and the tracking portfolio. This problem carries significant importance in financial economics as the tracking portfolio represents a parsimonious index that facilitates a practical means to trade the benchmark index. For this reason, extensive studies from various optimization and machine learning-based approaches have ensued. In this paper, we solve this problem through the latest developments from deep learning. Specifically, we associate a deep latent representation of asset returns, obtained through a stacked autoencoder, with the benchmark index's return to identify the assets for inclusion in the tracking portfolio. Empirical results indicate that to improve the performance of previously proposed deep learning-based index tracking, the deep latent representation needs to be learned in a strictly hierarchical manner and the relationship between the returns of the index and the assets should be quantified by statistical measures. Various deep learning-based strategies have been tested for the stock market indices of the S&P 500, FTSE 100 and HSI, and it is shown that our proposed methodology generates the best index tracking performance.

关键词： Index tracking Index replication deep learning deep autoencoder Stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Priori Knowledge-Incorporating Method for the Determination of Polycyclic Aromatic Hydrocarbons (PAHs) in Edible Vegetable Oils by Time Resolved Fluorescence

引用

ANALYTICAL LETTERS 2022年第8期55卷 1217-1234页

作者： Chen, Hui Feng, Meiqin Li, Jing Lu, Jie Gu, Haiyang Chen, Junhong He, Shihang Qi, Xingpu Chen, Wenjun Chen, Tong Jinling Inst Technol Sch Anim Sci & Food Engn Nanjing Jiangsu Peoples R China Jinling Inst Technol Sch Sci Nanjing Jiangsu Peoples R China Chuzhou Univ Sch Biol Sci & Food Engn Chuzhou Anhui Peoples R China Jiangsu Agrianim Husb Vocat Coll Taizhou Jiangsu Peoples R China Jinling Inst Technol Sch Software Engn Nanjing Jiangsu Peoples R China Guangxi Univ Sci & Technol Sch Biol & Chem Engn 268 Donghuan Ave Liuzhou 545006 Guangxi Peoples R China

A priori knowledge-incorporating method based on time resolved fluorescence was successfully developed for the determination of polycyclic aromatic hydrocarbons in edible vegetable oils. Specifically, fluorescence decay functions of polycyclic aromatic hydrocarbons at characteristic emission wavelengths were used as the priori models and incorporated into the deep-autoencoder. The priori model-incorporating deep-autoencoder models were shown to be effective for the determination of polycyclic aromatic hydrocarbons in edible vegetable oils and root-mean-square errors of prediction lower than 2% were achieved. The influence of analyte, matrix and proportion of priori model were characterized. Increasing the proportion of priori model appropriately was beneficial to the performance of models and 16% was shown to be the best incorporated proportion.

关键词： Chemometrics deep autoencoder polycyclic aromatic hydrocarbons priori model-incorporating deep-autoencoder models time resolved fluorescence

来源：评论

学校读者我要写书评

暂无评论

Learning of Labeling Room Space for Mobile Robots Based on Visual Motor Experience 26th

Learning of Labeling Room Space for Mobile Robots Based on V...

引用

26th International Conference on Artificial Neural Networks (ICANN)

作者： Yamada, Tatsuro Ito, Saki Arie, Hiroaki Ogata, Tetsuya Waseda Univ Dept Intermedia Art & Sci Tokyo Japan Waseda Univ Dept Modern Mech Engn Tokyo Japan

ISBN: (纸本)9783319686004;9783319685991

A model was developed to allow a mobile robot to label the areas of a typical domestic room, using raw sequential visual and motor data, no explicit information on location was provided, and no maps were constructed. The model comprised a deep autoencoder and a recurrent neural network. The model was demonstrated to (1) learn to correctly label areas of different shapes and sizes, (2) be capable of adapting to changes in room shape and rearrangement of items in the room, and (3) attribute different labels to the same area, when approached from different angles. Analysis of the internal representations of the model showed that a topological structure corresponding to the room structure was self-organized as the trajectory of the internal activations of the network.

关键词： Symbol grounding Mobile robots deep autoencoder Recurrent neural network Indoor scene labeling

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Insider Detection Through Neural Feature Learning and Model Optimisation 13th

Unsupervised Insider Detection Through Neural Feature Learni...

引用

13th International Conference on Network and System Security (NSS)

作者： Liu, Liu Chen, Chao Zhang, Jun De Vel, Olivier Xiang, Yang Swinburne Univ Technol Sch Software & Elect Engn Hawthorn Vic 3122 Australia Dept Def Def Sci & Technol Grp Edinburgh SA 5111 Australia

ISBN: (纸本)9783030369385;9783030369378

The insider threat is a significant security concern for both organizations and government sectors. Traditional machine learning-based insider threat detection approaches usually rely on domain focused feature engineering, which is expensive and impractical. In this paper, we propose an autoencoder-based approach aiming to automatically learn the discriminative features of the insider behaviours, thus alleviating security experts from tedious inspection tasks. Specifically, a Word2vec model is trained with a corpus transformed from various security logs to generate event representations. Instead of manually selecting Word2vec model parameters, we develop an autoencoder-based "parameter tuner" for the model to produce an optimal feature set. Then, the detection is undertaken by examining the reconstruction error of an autoencoder for each transformed event using the Carnegie Mellon University (CMU) CERT Programs insider threat database. Experimental results demonstrate that our proposed approach could achieve an extremely low false-positive rate (FPR) with all malicious events identified.

关键词： Insider threats Data analytics deep autoencoder Cyber security

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Fusion Combined with Neural Network Applied to UAV Attitude Estimation

Unsupervised Feature Fusion Combined with Neural Network App...

引用

IEEE International Conference on Robotics and Biomimetics (ROBIO)

作者： Dai, Xin Zhou, Yimin Meng, Shan Wu, Qingtian Shenzhen Univ Coll Informat Engn Shenzhen Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Shenzhen ACUS Tech Co Inc Shenzhen Peoples R China

ISBN: (纸本)9781728103778

In the field of an unmanned aerial vehicle (UAV), the navigation algorithm with high precision and easy implementation is a hot topic of research, and the key of UAV control is to obtain accurate and real-time attitude information. In this paper, a feature fusion algorithm based on unsupervised deep autoencoder (DAE) is proposed. It is used for data fusion of multiple sensors. The experimental results show that the unsupervised feature fusion algorithm can effectively improve the accuracy and has the potential to be applied to the data fusion of UAV sensors.

关键词： Attitude estimation deep autoencoder UAV Unsuperviesd 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：