检索结果-内蒙古大学图书馆

1st International workshop on Education Technology and Computer Science

作者： Zhang Shuyin Guo Ying Wang Buhong AF Engn Univ Telecommun Engn Inst Xian Peoples R China

ISBN: (纸本)9780769535579

The paper analyzes short term auto-correlation property of speech signal and confirms it through detailed comparing experiment with other kind of signals. By applying the auto-correlation property of current speech frame and frames nearby, a new feature for voice activity detecting called weighted short-term summation of auto-correlation (WSAC) is formed. It is testified that the new VAD feature can robustly used in environment degraded by noise which has poor correlation, and its performance has little connection with various SNRs, changing of noise power etc., in contrast with traditional features commonly used in VAD. Properties of the new feature and principle of robust VAD algorithm based on it are explained in this paper, experiment results and correlative analysis are also given.

关键词： Speech signal processing Voice activity detection (VAD) Auto-correlation property

来源：评论

学校读者我要写书评

暂无评论

Parallel Data-Local Training for Optimizing Word2Vec Embeddings for Word and Graph Embeddings 5

Parallel Data-Local Training for Optimizing Word2Vec Embeddi...

引用

5th ieee/ACM workshop on machine learning in High Performance Computing Environments (MLHPC)

作者： Moon, Gordon E. Newman-Griffis, Denis Kim, Jinsung Sukumaran-Rajam, Aravind Fosler-Lussier, Eric Sadayappan, P. Ohio State Univ Comp Sci & Engn Columbus OH 43210 USA Univ Utah Sch Comp Salt Lake City UT USA

ISBN: (纸本)9781728159850

The Word2Vec model is a neural network-based unsupervised word embedding technique widely used in applications such as natural language processing, bioinformatics and graph mining. As Word2Vec repeatedly performs Stochastic Gradient Descent (SGD) to minimize the objective function, it is very compute-intensive. However, existing methods for parallelizing Word2Vec are not optimized enough for data locality to achieve high performance. In this paper, we develop a parallel data-locality-enhanced Word2Vec algorithm based on Skip-gram with a novel negative sampling method that decouples loss calculation with positive and negative samples;this allows us to efficiently reformulate matrix-matrix operations for the negative samples over the sentence. Experimental results demonstrate our parallel implementations on multi-core CPUs and GPUs achieve significant performance improvement over the existing state-of-the-art parallel Word2Vec implementations while maintaining evaluation quality. We also show the utility of ourWord2Vec implementation within the Node2Vec algorithm which accelerates embedding learning for large graphs.

关键词： Parallel machine learning Unsupervised learning learning Latent Representations Parallel Word2Vec Node2Vec Word Embedding Graph Embedding

来源：评论

学校读者我要写书评

暂无评论

ELMNET: FEATURE learning USING EXTREME learning machineS 24

ELMNET: FEATURE LEARNING USING EXTREME LEARNING MACHINES

引用

24th ieee International Conference on Image processing (ICIP)

作者： Cui, Dongshun Huang, Guang-Bin Kasun, L. L. Chamara Zhang, Guanghao Han, Wei Nanyang Technol Univ 50 Nanyang Ave Singapore 639798 Singapore

ISBN: (纸本)9781509021758

Feature learning is an initial step applied to computer vision tasks and is broadly categorized as: 1) deep feature learning;2) shallow feature learning. In this paper we focus on shallow feature learning as these algorithms require less computational resources than deep feature learning algorithms. In this paper we propose a shallow feature learning algorithm referred to as Extreme learning machine Network (ELMNet). ELMNet is module based neural network consist of feature learning module and a post-processing module. Each feature learning module in ELMNet performs the following operations: 1) patch-based mean removal;2) ELM auto-encoder (ELM-AE) to learn features. Post-processing module is inserted after the feature learning module and simplifies the features learn by the feature learning modules by hashing and block-wise histogram. Proposed ELMNet outperforms shallow feature learning algorithm PCANet on the MNIST hand-written dataset.

关键词： ELMNet Feature learning ELM-AE

来源：评论

学校读者我要写书评

暂无评论

learning from the Best: Active learning for Wireless Communications

引用

ieee WIRELESS COMMUNICATIONS 2024年第4期31卷 177-183页

作者： Soltani, Nasim Zhang, Jifan Salehi, Batool Roy, Debashri Nowak, Robert Chowdhury, Kaushik Northeastern Univ Boston MA 02115 USA Northeastern Univ Comp Engn Boston MA USA Univ Wisconsin Madison Comp Sci Dept Madison WI USA Univ Wisconsin Madison Elect & Comp Engn Madison WI USA Univ Texas Arlington Arlington TX USA

Collecting an over-the-air wireless communications training dataset for deep learning-based communication tasks is relatively simple. However, labeling the dataset requires expert involvement and domain knowledge, may involve private intellectual properties, and is often computationally and financially expensive. Active learning is an emerging area of research in machine learning that aims to reduce the labeling overhead without accuracy degradation. Active learning algorithms identify the most critical and informative samples in an unlabeled dataset and label only those samples, instead of the complete set. In this article, we introduce active learning for deep learning applications in wireless communications, and present its different categories. We present a case study of deep learning-based mmWave beam selection, where labeling is performed by a compute-intensive algorithm based on exhaustive search. We evaluate the performance of different active learning algorithms on a publicly available multi-modal dataset with different modalities including image and LiDAR. Our results show that using an active learning algorithm for class-imbalanced datasets can reduce labeling overhead by up to 50 percent for this dataset while maintaining the same accuracy as classical training.

关键词： Training Labeling Radio frequency signal processing algorithms Task analysis Classification algorithms Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Audio-visual scene classification via contrastive event-object alignment and semantic-based fusion 24

Audio-visual scene classification via contrastive event-obje...

引用

ieee 24th International workshop on Multimedia signal processing (MMSP)

作者： Hou, Yuanbo Kang, Bo Botteldooren, Dick Univ Ghent WAVES Res Grp Ghent Belgium Univ Ghent IDLAB Ghent Belgium

ISBN: (数字)9781665471893

ISBN: (纸本)9781665471893

Previous works on scene classification are mainly based on audio or visual signals, while humans perceive the environmental scenes through multiple senses. Recent studies on audio-visual scene classification separately fine-tune the large-scale audio and image pre-trained models on the target dataset, then either fuse the intermediate representations of the audio model and the visual model, or fuse the coarse-grained decision of both models at the clip level. Such methods ignore the detailed audio events and visual objects in audio-visual scenes (AVS), while humans often identify a scene through both audio events and visual objects within, and the congruence between them. To exploit the fine-grained information of audio events and visual objects in AVS, and coordinate the implicit relationship between audio events and visual objects, this paper proposes a multi-branch model equipped with contrastive event-object alignment (CEOA) and semantic-based fusion (SF) for AVSC. CEOA aims to align the learned embeddings of audio events and visual objects by comparing the difference between audio-visual event-object pairs. Then, visual objects associated with certain audio events and vice versa are accentuated by cross-attention and undergo SF for semantic-level fusion. Experiments show that: 1) the proposed AVSC model equipped with CEOA and SF outperforms the results of audio-only and visual-only models, i.e., the audio-visual results are better than the results from a single modality. 2) CEOA aligns the embeddings of audio events and related visual objects on a fine-grained level, and the SF effectively integrates both;3) Compared with other large-scale integrated systems, the proposed model shows competitive performance, even without using additional datasets and data augmentation tricks.

关键词： audio-visual scene classification audio event visual object contrastive learning semantic-based fusion attention

来源：评论

学校读者我要写书评

暂无评论

Supercm: Revisiting Clustering for Semi-Supervised learning 48

Supercm: Revisiting Clustering for Semi-Supervised Learning

引用

48th ieee International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Singh, Durgesh Boubekki, Ahcène Jenssen, Robert Kampffmeyer, Michael C. UiT the Arctic University of Norway Department of Physics and Technology Tromsø Norway

ISBN: (纸本)9781728163277

The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance. © 2023 ieee.

关键词： Clustering Gaussian mixture models Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Combining Deep learning with Traditional machine learning to Improve Phonocardiography Classification Accuracy

Combining Deep Learning with Traditional Machine Learning to...

引用

2021 ieee signal processing in Medicine and Biology Symposium, SPMB 2021

作者： Chowdhury, M. Li, C. Poudel, K. Middle Tennessee State University Computational Science MurfreesboroTN37132 United States Middle Tennessee State University Department of Computer Science MurfreesboroTN United States Embry-Riddle Aeronautical University Department of Mathematics and Computer Science Florida United States

ISBN: (纸本)9781665428972

Phonocardiography (PCG) is a widely used technique to detect and diagnose cardiovascular diseases. We have combined the advantages of traditional machine learning (ML) and deep learning (DL) techniques to build deep hybrid PCG classification models. We have shown that, though DL models usually outperform ML models in classifying PCG signals, optimal classification can be achieved if we combine these two architectures to build a single PCG classification model. A Convolutional Neural Network (CNN) is used along with 7 traditional machine learning methods including Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), Naive Bayes (NB), Support Vector machine (SVM), and AdaBoost (AB) to build hybrid PCG classification models. Our experimental results have shown that significant improvements in the classification accuracy can be achieved by using deep hybrid models compared to traditional machine learning models. We have also shown that some hybrid models performed better than the single deep learning model in classifying PCG signals. We have also compared the performance of the best hybrid model to 11 other PCG classification models and obtained better accuracy. © 2021 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sparse Codes Auto-Extractor for Classification: A Joint Embedding and Dictionary learning Framework for Representation

引用

ieee TRANSACTIONS ON signal processing 2016年第14期64卷 3790-3805页

作者： Zhang, Zhao Li, Fanzhang Chow, Tommy W. S. Zhang, Li Yan, Shuicheng Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China Soochow Univ Joint Int Res Lab Machine Learning & Neuromorph C Suzhou 215006 Peoples R China Collaborat Innovat Ctr Novel Software Technol & I Nanjing 210023 Jiangsu Peoples R China City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China Natl Univ Singapore Dept Elect & Comp Engn Singapore 119077 Singapore

In this paper, we discuss the sparse codes auto-extractor based classification. A joint label consistent embedding and dictionary learning approach is proposed for delivering a linear sparse codes auto-extractor and a multi-class classifier by simultaneously minimizing the sparse reconstruction, discriminative sparse-code, code approximation and classification errors. The auto-extractor is characterized with a projection that bridges signals with sparse codes by learning special features from input signals for characterizing sparse codes. The classifier is trained based on extracted sparse codes directly. In our setting, the performance of the classifier depends on the discriminability of sparse codes, and the representation power of the extractor depends on the discriminability of input sparse codes, so we incorporate label information into the dictionary learning to enhance the discriminability of sparse codes. So, for inductive classification, our model forms an integration process from test signals to sparse codes and finally to assigned labels, which is essentially different from existing sparse coding based approaches that involve an extra sparse reconstruction with the trained dictionary for each test signal. Remarkable results are obtained by our model compared with other state-of-the-arts.

关键词： Sparse codes auto-extractor embedding learning dictionary learning feature representation joint classification

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT NEURAL NETWORK ARCHITECTURE FOR TOPOLOGY IDENTIFICATION IN SMART GRID

EFFICIENT NEURAL NETWORK ARCHITECTURE FOR TOPOLOGY IDENTIFIC...

引用

ieee Global Conference on signal and Information processing (GlobalSIP)

作者： Zhao, Yue Chen, Jianshu Poor, H. Vincent SUNY Stony Brook Dept Elect & Comp Engn Stony Brook NY 11794 USA Microsoft Res Redmond WA 98052 USA Princeton Univ Dept Elect Engn Princeton NJ 08544 USA

ISBN: (纸本)9781509045457

Identifying arbitrary power grid topologies in real time based on measurements in the grid is studied. A learning based approach is developed: binary classifiers are trained to approximate the maximum a-posteriori probability (MAP) detectors that each identifies the status of a distinct line. An efficient neural network architecture in which features are shared for inferences of all line statuses is developed. This architecture enjoys a significant computational complexity advantage in the training and testing processes. The developed classifiers based on neural networks are evaluated in the ieee 30-bus system. It is demonstrated that, using the proposed feature sharing neural network architecture, a) the training and testing times are drastically reduced compared with training a separate neural network for each line status inference, and b) a small amount of training data is sufficient for achieving a very good real-time topology identification performance.

关键词： Online power grid topology identification line outage detection machine learning neural networks cascading failures

来源：评论

学校读者我要写书评

暂无评论

A Path Algorithm for Localizing Anomalous Activity in Graphs

A Path Algorithm for Localizing Anomalous Activity in Graphs

引用

1st ieee Global Conference on signal and Information processing (GlobalSIP)

作者： Sharpnack, James Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA

ISBN: (纸本)9781479902484

The localization of anomalous activity in graphs is a statistical problem that arises in many applications, such as network surveillance, disease outbreak detection, and activity monitoring in social networks. We will address the localization of a cluster of activity in Gaussian noise in directed, weighted graphs. We develop a penalized likelihood estimator (we call the relaxed graph scan) as a relaxation of the NP-hard graph scan statistic. We review how the relaxed graph scan (RGS) can be solved using graph cuts, and outline the max-flow min-cut duality. We use this combinatorial duality to derive a path algorithm for the RGS by solving successive max flows. We demonstrate the effectiveness of the RGS on two simulations, over an undirected and directed graph.

关键词： Line graph Anomalous scanning activity Gaussian noise Social Networks

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：