检索结果-内蒙古大学图书馆

2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

作者： Sheng, Leyuan Pavlovskiy, Evgeniy N. Novosibirsk State University Department of Mathematics and Mechanics Novosibirsk Russia Stream Data Analytics and Machine Learning Laboratory Novosibirsk State University Novosibirsk Russia

ISBN: (纸本)9781728144016

Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-To-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech. © 2019 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Development of an Application for Audio-Visual-Tactile Brainwave Entrainment in Patients with Affective and Psychosomatic Disorders 22

Development of an Application for Audio-Visual-Tactile Brain...

引用

22nd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2021

作者： Korshunov, Vadim A. Khazankin, Grigory R. Ivanishkin, Dmitry S. Novosibirsk State University Department of Information Technologies Novosibirsk Russia Stream Data Analytics and Machine Learning Laboratory Novosibirsk State University Novosibirsk Russia

ISBN: (纸本)9781665414982

Brainwave entrainment is used in different types of treatment, one of which is treating affective and psychosomatic disorders. The better result is achieved if individual alpha-peak frequency is taken into account during entrainment and when it includes audio visual and tactile stimulation. The program which allows running stimulation scenarios is required to be available on different platforms because patients need to continue the procedures even after finishing them in hospital. So they need to be able to download and install this control program on their personal computers. The required application was developed as a multiplatform one using. NET Core framework in order to reduce costs of further maintenance. © 2021 IEEE.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

Finding the transcription factor binding locations using novel algorithm segmentation to filtration (S2F)

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第9期15卷 3347-3358页

作者： Theepalakshmi, P. Srinivasulu Reddy, U. Department of Computer Science and Engineering Gandhi Institute of Technology and Management Karnataka Bengaluru India Machine Learning and Data Analytics Lab Center of Excellence in Artificial Intelligence Department of Computer Applications National Institute of Technology Tamilnadu Tiruchirappalli India

The primary aim of identifying the binding motifs in gene regulation is to understand the transcriptional regulation molecular mechanism systematically. In this study, the (, d) motif search issue was considered which entails finding the length motifs which differ by at most d substitutions. However, identifying the high-quality pattern (, d) is challenging. It is intended to address the above problem with motif discovery and handle it using the proposed algorithm S2F (Segmentation to Filtration) based on the qPMS (quorum Planted Motif Search) algorithm model. From the entire DNA sequences, five percent are chosen at random to be used in the motif discovery process. This random sub segment (subseg) portion is split up into base, sub k-mers, and its sizes (motif length ()) are determined by the iterative approach. Corresponding to the sizes of and d (mutations), the k-mers are chosen which participated in filtration techniques and the base k-mer count and frequency are updated. The highest frequency of k-mer is recognized as the motif. The algorithm’s performance was evaluated using the two real datasets Escherichia coli cyclic AMP receptor protein (CRP) and mouse Embryonic Stem Cell (mESC) ChIP-seq (Chromatin Immuno Precipitation) dataset. Results from the experiments show that S2F can identify the motifs and appear faster compared to previous state-of-the-art PMS (Planted Motif Search) and qPMS algorithms. Graphical Abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Minimum Cost Multicut Approach to Self-supervised Multiple Person Tracking 15th

A Two-Stage Minimum Cost Multicut Approach to Self-supervise...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Ho, Kalun Kardoost, Amirhossein Pfreundt, Franz-Josef Keuper, Janis Keuper, Margret Fraunhofer Center Machine Learning Sankt Augustin Germany CC-HPC Fraunhofer ITWM Kaiserslautern Germany Data and Web Science Group University of Mannheim Mannheim Germany Institute for Machine Learning and Analytics Offenburg University Offenburg Germany

ISBN: (纸本)9783030695316

Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without supervision. Clustering based on these cues enables us to learn the required appearance invariances for the tracking task at hand and train an AutoEncoder to generate suitable latent representations. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking. © 2021, Springer Nature Switzerland AG.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks 38

The Map Equation Goes Neural: Mapping Network Flows with Gra...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Blöcker, Christopher Tan, Chester Scholtes, Ingo Data Analytics Group Department of Informatics University of Zurich Switzerland Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science Julius-Maximilians-Universität Würzburg Germany

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-transformer mixed model for object detection

arXiv

引用

arXiv 2022年

作者： Li, Wenshuo Machine Learning for Visual Data Analytics United Kingdom

Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and location of an object. Therefore, the main direction to improve the accuracy of object detection tasks is to improve the neural network to extract features better. In this paper, I propose a convolutional module with a transformer[1], which aims to improve the recognition accuracy of the model by fusing the detailed features extracted by CNN[2] with the global features extracted by a transformer and significantly reduce the computational effort of the transformer module by deflating the feature mAP. The main execution steps are convolutional downsampling to reduce the feature map size, then self-attention calculation and upsampling, and finally concatenation with the initial input. In the experimental part, after splicing the block to the end of YOLOv5n[3] and training 300 epochs on the coco dataset, the mAP improved by 1.7% compared with the previous YOLOv5n, and the mAP curve did not show any saturation phenomenon, so there is still potential for improvement. After 100 rounds of training on the Pascal VOC dataset, the accuracy of the results reached 81%, which is 4.6 better than the faster RCNN[4] using resnet101[5] as the backbone, but the number of parameters is less than one-twentieth of it. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Reducing noise using neighbourhood pixel analysis and interpretable custom kernel in CNN model for CP handwritten digit recognition

引用

International Journal of Information Technology (Singapore) 2024年 1-11页

作者： Muthureka, K. Srinivasulu Reddy, U. Janet, B. Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India Information Processing Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India

Individuals with Cerebral Palsy (CP) are impacted lifetime barriers in their everyday activities, especially in writing phrase, which results from innate neural motor in co-ordination. Numerous studies have focused on recognizing normal people’s handwritten digits using benchmark datasets. However, there has been limited exploration into recognizing handwritten digits by individuals with CP. The handwriting of CP individuals is significantly more difficult to recognize than that of normal people because the CP digits are inaccurate, uneven, and complex to recognize. In this study, the authors improve the digit recognition accuracy of existing Convolutional Neural Network (CNN) models on collected CP handwritten digit’s dataset using two notable methods, first one is to reduce the noise using neighbourhood pixel analysis through Fast Non-Local Means (FNLM) algorithm and second one is to extract the feature using customized kernel technique. The experimental results show that the accuracy of existing state of art models are improved by 3% to 7.14% with the integration of aforementioned techniques. Moreover, a custom CNN model hybridised with the Prewit, Laplacian, Sobel filters, and custom kernel has following CP digit recognition accuracy values of 97.96%, 98.08%, 99.17%, and 99.60% respectively. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Cerebral Palsy CNN Customized kernel initialization Edge detection Handwritten digit recognition

来源：评论

学校读者我要写书评

暂无评论

Bias Bubbles: Using Semi-Supervised learning to Measure How Many Biased News Articles Are Around Us 29

Bias Bubbles: Using Semi-Supervised Learning to Measure How ...

引用

29th Irish Conference on Artificial Intelligence and Cognitive Science, AICS 2021

作者： Ruan, Qin Namee, Brian Mac Dong, Ruihai School of Computer Science University College Dublin Dublin Ireland Insight Centre for Data Analytics Science Foundation Ireland Centre for Research Training in Machine Learning Ireland

The proliferation of web 2.0 technology allows us to easily create and share online content, but also leads to the rapid spread of misinformation and biased media, which has considerable negative effects on society. Deep learning-based classifiers are one common way of identifying media bias, but they suffer from a lack of large-scale labelled datasets. In this paper, we first explore the use of pseudo-labelling technology to mitigate this problem. Second, we exploit a masking method to identify biased sentences in news articles by iteratively masking each sentence from an article and observing the change in output of a bias detection model. These identified sentences not only contribute to evaluating the proposed model, but also enable end-users to understand where media bias arises in an article. Finally, we apply our well-trained bias detection model to a well-known news article dataset to show how widespread media bias is-the results show that it is rampant and has become a serious social problem that we cannot ignore. © 2021 CEUR-WS. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Finding latent causes in causal networks: An efficient approach based on Markov blankets

Finding latent causes in causal networks: An efficient appro...

引用

22nd Annual Conference on Neural Information Processing Systems, NIPS 2008

作者： Pellet, Jean-Philippe Elisseeff, André Pattern Recognition and Machine Learning Group Swiss Federal Institute of Technology Zurich 8092 Zurich Switzerland Data Analytics Group IBM Research GmbH 8803 Ruschlikon Switzerland

ISBN: (纸本)9781605609492

Causal structure-discovery techniques usually assume that all causes of more than one variable are observed. This is the so-called causal sufficiency assumption. In practice, it is untestable, and often violated. In this paper, we present an efficient causal structure-learning algorithm, suited for causally insufficient data. Similar to algorithms such as IC* and FCI, the proposed approach drops the causal sufficiency assumption and learns a structure that indicates (potential) latent causes for pairs of observed variables. Assuming a constant local density of the data-generating graph, our algorithm makes a quadratic number of conditional-independence tests w.r.t. the number of variables. We show with experiments that our algorithm is comparable to the state-of-the-art FCI algorithm in accuracy, while being several orders of magnitude faster on large problems. We conclude that MBCS* makes a new range of causally insufficient problems computationally tractable.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Superposition as data Augmentation Using Lstm and Hmm in Small Training Sets

arXiv

引用

arXiv 2019年

作者： Sivaswamy, Akilesh Pavlovskiy, Evgeniy Stream Data Analytics and Machine Learning lab Novosibirsk State University

Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3% improvement (from 68% to 71%) by using 38% lesser number of training samples in Russian audio-digits recognition task and 7,16% better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1% better accuracy than mix-up on first 900 samples in MNIST using 3-layer stacked LSTM. Copyright © 2019, The Authors. All rights reserved.

关键词： Quantum theory

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：