检索结果-内蒙古大学图书馆

2022 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2022

作者： Khue, Luu Minh Sao Pavlovskiy, Evgeniy Novosibirsk State University Stream Data Analytics and Machine Learning Laboratory Novosibirsk Russia

ISBN: (数字)9781665460927

ISBN: (纸本)9781665460927

In this study, we provide segmentations of brain tumors as semantic features to a simple convolutional neural network (CNN) to improve the classification results. The Siberian Brain Tumor dataset (SBT) of 1452 magnetic resonance (MR) images of Russian people's brains is used for training, validation, and testing. We preprocess MR images by removing the swelling region surrounding a brain tumor (edema) from the segmentation and eliminating slices that contain less than 163 pixels of tumor. The binary classifier is a simple network of four convolutional layers for feature extractions and two linear layers for classification. The network is trained and validated with 5-fold cross-validation. We train another CNN with similar configuration on images without provided segmentation and compare the testing results. The two networks are evaluated with four metrics: accuracy, sensitivity, specificity, and F1 scores. The classifier trained with segmentation achieve the highest accuracy score of 0.92, sensitivity of 0.934, specificity of 0.91, and F1 score of 0.90 using ensemble approach. © 2022 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Improving Brain Tumor Multiclass Classification With Semantic Features

Improving Brain Tumor Multiclass Classification With Semanti...

引用

2022 Ural-Siberian Conference on Computational Technologies in Cognitive Science, Genomics and Biomedicine, CSGB 2022

作者： Sao Khue, Luu Minh Pavlovskiy, Evgeniy Novosibirsk State University Stream Data Analytics and Machine Learning Laboratory Novosibirsk Russia

ISBN: (数字)9781665452885

ISBN: (纸本)9781665452885

Histopathological examination of biopsy tissues is still utilized to diagnose and classify brain cancers today. The current approach is inconvenient, time-consuming, and prone to human mistake. These disadvantages emphasize the significance of establishing a fully automated deep learning-based system for classifying brain tumors. In this paper, we suggest an approach to improve the classification for four types of brain tumors by providing the classifier with segmentation as semantic features. 1,452 multi model magnetic resonance images from the Siberian Brain Tumor dataset (SBT) are used for training, validation, and testing. The training and validation are implemented with our experimental simple convolutional neural network and a pre-trained VGG16. Best performed models are selected and tested on both SBT and the Brain Tumor Segmentation Challenge 2020 dataset (BraTS). The models with segmentation outperform all models without segmentation on the same dataset. We also found that, compare to a general purposed network such as VGG16, a simple convolutional neural network trained on a specific task have better generalization when tested with a public dataset. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Problems and Prospectives of Big data Storage and Processing Standartization

Problems and Prospectives of Big Data Storage and Processing...

引用

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

作者： Pavlovskiy, Evgeniy N. Stream Data Analytics and Machine Learning Lab Novosibirsk State University Novosibirsk Russia

ISBN: (纸本)9781728144016

In the paper, we analyze the problem of standardization in the domain of storage and processing of big data in the application to the Internet of things. We highlight the underlying problems of big data;analyze the scientific, technological and economic barriers to the development of big data. We offer perspective research directions in the domain of development of standards of data representation. © 2019 IEEE.

关键词： data structures

来源：评论

学校读者我要写书评

暂无评论

Reducing over-smoothness in speech synthesis using Generative Adversarial Networks

Reducing over-smoothness in speech synthesis using Generativ...

引用

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

Harnessing Ensemble machine learning Models for Timely Diagnosis of Breast Cancer Metastasis: A Case Study on CatBoost, XGBoost, and LGBM 25

Harnessing Ensemble Machine Learning Models for Timely Diagn...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Luu, Minh Sao Khue Banerjee, Santanu Pavlovskiy, Evgeniy N. Tuchinov, Bair N. Stream Data Analytics and Machine Learning Laboratory Novosibirsk State University Novosibirsk Russia Kharagpur West Bengal Kharagpur721302 India

ISBN: (纸本)9798350389234

This study employs three advanced gradient boosting machine learning algorithms to assess potential disparities in healthcare delivery. We specifically investigate which factors contribute to a patient's timely diagnosis of metastatic breast cancer using a public healthcare dataset. Our approach involves training and testing three separate models, as well as an ensemble model with automatically optimized weights. The models try to predict whether patients received a diagnosis of metastatic breast cancer within 90 days. Each model has different preprocessing and feature selection steps. The hyperparameter optimization is performed using the Optuna library in Python. Models are evaluated on the Kaggle platform, with our metrics indicating strong predictive performance;Categorical Boosting achieved an Area Under the Receiver Operating Characteristic Curve score of 0.813, Extreme Gradient Boosting reached 0.808, Light Gradient Boosting machine scored 0.805, and the ensemble model culminated at 0.808. Additionally, we analyze the set of features being used by all the best models and examine the impact of hyperparameters on the models' overall performance. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

System Architecture for Reading and Interpreting Physical Printouts of Medical Forms 22

System Architecture for Reading and Interpreting Physical Pr...

引用

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

作者： Snegireva, Ekaterina Khazankin, Grigory R. Mikheenko, Igor Stream Data Analytics and Machine Learning Laboratory Novosibirsk State University Novosibirsk Russia Novosibirsk State University Novosibirsk Russia Meshalkin National Medical Research Center Novosibirsk Russia

ISBN: (纸本)9781665414982

This article describes the developed architecture of the system module for processing and interpreting analog medical data. Patients often undergo examinations in various medical institutions, and since their results are often handed out to the patient in printed form, the receiving institution transfers them to its database manually. There is also a tendency to completely refuse analog media and use only digital ones. But in this case, another problem appears-either loss or conversion of the accumulated analog base into digital format. These days, automatic document management systems for medical institutions-Health information systems (HIS)-are actively developing. The software module developed in accordance with the architecture described in the article can be used by developers of various HIS to automate the work with analog data. If it is necessary, it can also be freely expanded by adding new modules for working with various analog data. In this article, we take ECG scans and medical test results as examples of such data. As a result of the work undertaken the prototype of the designed system was developed and tested. © 2021 IEEE.

关键词： Medical information systems

来源：评论

学校读者我要写书评

暂无评论

Development of water flood model for oil production enhancement

Development of water flood model for oil production enhancem...

引用

2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

作者： Tsvaki, Jetina J. Tailakov, Dmitry O. Pavlovskiy, Evgeniy N. Novosibirsk State University Dept. of Mathematics and Mechanics Novosibirsk Russia Kutateladze Institute of Thermophysics Sb Ras Laboratory for Fundamentals of Energy Technologies Novosibirsk Russia Novosibirsk State University Stream Data Analytics and Machine Learning Laboratory Novosibirsk Russia

ISBN: (纸本)9780738131115

Main goal of any industry is to increase productivity which in oil and gas field is to increase reservoir oil asset by producing oil in an effective and economically efficient manner. The objective of the study is to develop a water flood model for oil production enhancement using artificial neural networks and provide a model that maximizes oil production for a given water injection that in turn will extend mature fields life and decrease operational costs. Using the data comprising of daily water injection rates, oil production rates, water production, and gas production from the year 2004 to 2016 for 577 injection wells, 1344 production wells, and 36 events which had occurred during the course. Comparative analysis on the deep neural models such as Multi-Layer Perception, Convolutional Neural Networks, Long Short-Term Memory, and Gated Recurrent Neural Networks are used, and Gated Recurrent Neural Networks outperformed them. To minimize the loss and improve the performance of the water flood model tabular data mix-up was adopted on all the models above. The results showed that the data mixed up Gated Recurrent Neural Network outperformed all the other models. To maximize the oil production Nelder-Mead optimization method was adopted to find appropriate water injection rates. A simple two-layered multi-layer perceptron was used in modeling the nonlinear relationship between water injection and oil production to avoid function complexity. © 2020 IEEE.

关键词： Floods

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

Reducing over-smoothness in speech synthesis using Generative Adversarial Networks

Reducing over-smoothness in speech synthesis using Generativ...

引用

IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Leyuan Sheng Evgeniy N. Pavlovskiy Novosibirsk State University Novosibirsk Russia Stream Data Analytics and Machine Learning laboratory Novosibirsk State University Novosibirsk Russia

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.

关键词： Generative adversarial networks Speech synthesis Spectrogram Generators Hidden Markov models Training

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：