检索结果-内蒙古大学图书馆

An approach for medical event detection in Chinese clinical notes of electronic health records

BMC MEDICAL INFORMATICS AND DECISION MAKING 2019年第SUPPL 2期19卷 31-37页

作者： Zhou, Xuesi Xiong, Haoqi Zeng, Sihan Fu, Xiangling Wu, Ji Tsinghua Univ Dept Elect Engn Beijing Peoples R China Tsinghua iFlytek Joint Lab Beijing Peoples R China Beijing Univ Posts & Telecommun Sch Software Engn Beijing Peoples R China

BackgroundMedical event detection in narrative clinical notes of electronic health records (EHRs) is a task designed for reading text and extracting information. Most of the previous work of medical event detection treats the task as extracting concepts at word granularity, which omits the overall structural information of the clinical notes. In this work, we treat each clinical note as a sequence of short sentences and propose an end-to-end deep neural network *** redefined the task as a sequence labelling task at short sentence granularity, and proposed a novel tag system correspondingly. The dataset were derived from a third-level grade-A hospital, consisting of 2000 annotated clinical notes according to our proposed tag system. The proposed end-to-end deep neural network framework consists of a feature extractor and a sequence labeller, and we explored different implementations respectively. We additionally proposed a smoothed Viterbi decoder as sequence labeller without additional parameter training, which can be a good alternative to conditional random field (CRF) when computing resources are *** sequence labelling models were compared to four baselines which treat the task as text classification of short sentences. Experimental results showed that our approach significantly outperforms the baselines. The best result was obtained by using the convolutional neural networks (CNNs) feature extractor and the sequential CRF sequence labeller, achieving an accuracy of 92.6%. Our proposed smoothed Viterbi decoder achieved a comparable accuracy of 90.07% with reduced training parameters, and brought more balanced performance across all categories, which means better generalization *** on our annotated dataset, the comparison results demonstrated the effectiveness of our approach for medical event detection in Chinese clinical notes of EHRs. The best feature extractor is the CNNs feature extractor, and the best se

关键词： Medical event detection Sequence labelling neural network models

来源：评论

学校读者我要写书评

暂无评论

Event causality detection in tweets by context word extension and neural networks 20

Event causality detection in tweets by context word extensio...

引用

20th International conference on Parallel and distributed Computing, Applications and Technologies, PDCAT 2019

作者： Kayesh, Humayun Islam, Md. Saiful Wang, Junhu School of ICT Griffith University Australia

ISBN: (纸本)9781728126166

Twitter has become a great source of user-generated information about events. Very often people report causal relationships between events in their tweets. Automatic detection of causality information in these events might play an important role in prescriptive event analytics. Existing approaches include both rule-based and data-driven supervised methods. However, it is challenging to identify event causality accurately using linguistic rules due to the unstructured nature and grammatical incorrectness of social media short text such as tweets. Also, it is difficult to develop a data-driven supervised method for event causality detection in tweets due to insufficient contextual information. This paper proposes a novel event context word extension technique based on background knowledge. To demonstrate the effectiveness of our event context word extension technique, we develop a feed-forward neural network based approach to detect event causality from tweets. Extensive experiments demonstrate the superiority of our approach. © 2019 IEEE.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

MMA regularization: decorrelating weights of neural networks by maximizing the minimal angles 20

MMA regularization: decorrelating weights of neural networks...

引用

Proceedings of the 34th International conference on neural Information processing Systems

作者： Zhennan Wang Canqun Xiang Wenbin Zou Chen Xu Shenzhen Key Laboratory of Advanced Machine Learning and Applications Guangdong Key Laboratory of Intelligent Information Processing Institute of Artificial Intelligence and Advanced Communication College of Electronics and Information Engineering Shenzhen University Institute of Artificial Intelligence and Advanced Communication College of Mathematics and Statistics Shenzhen University

ISBN: (纸本)9781713829546

The strong correlation between neurons or filters can significantly weaken the generalization ability of neural networks. Inspired by the well-known Tammes problem, we propose a novel diversity regularization method to address this issue, which makes the normalized weight vectors of neurons or filters distributed on a hypersphere as uniformly as possible, through maximizing the minimal pairwise angles (MMA). This method can easily exert its effect by plugging the MMA regularization term into the loss function with negligible computational overhead. The MMA regularization is simple, efficient, and effective. Therefore, it can be used as a basic regularization method in neural network training. Extensive experiments demonstrate that MMA regularization is able to enhance the generalization ability of various modern models and achieves considerable performance improvements on CIFAR100 and TinyImageNet datasets. In addition, experiments on face verification show that MMA regularization is also effective for feature learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In-network hebbian plasticity for wireless sensor networks 1

引用

12th International conference on Internet and distributed Computing Systems, IDCS 2019

作者： van der Lee, Tim Exarchakos, Georgios de Groot, Sonia Heemstra Eindhoven University of Technology Eindhoven5612 AP Netherlands

ISBN: (数字)9783030349141

ISBN: (纸本)9783030349134

In typical Wireless Sensor networks (WSNs), all sensor data is routed to a more powerful computing entity. In the case of environmental monitoring, this enables data prediction and event detection. When the size of the network increases, processing all the input data outside the network will create a bottleneck at the gateway device. This creates delays and increases the energy consumption of the network. To solve this issue, we propose using Hebbian learning to pre-process the data in the wireless network. This method allows to reduce the dimension of the sensor data, without loosing spatial and temporal correlation. Furthermore, bottlenecks are avoided. By using a recurrent neural network to predict sensor data, we show that pre-processing the data in the network with Hebbian units reduces the computation time and increases the energy efficiency of the network without compromising learning. © Springer Nature Switzerland AG 2019.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Cascading Incremental Training Approach for Large-Scale distributed Data Based on Support Vector Machine

A Cascading Incremental Training Approach for Large-Scale Di...

引用

International conference on Wavelet Active Media Technology and Information processing (ICWAMTIP)

作者： Xu Yuan Yuan Shucheng Li Fan Li Xiaofeng Gu Sun Rui School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Sichuan shengtian new energy development co. ltd Chengdu China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9781665405058

ISBN: (纸本)9781665405065

In this paper, we present a cascading incremental training approach for large-scale and unevenly distributed data based on Support Vector Machine. Instead of using training data directly, data's distribution and scale are concerned, so Synthetic Minority Oversampling Technique and Generative Adversarial networks are both used to synthesize new samples and add them to the data set to achieve a balanced sample number. Then, we propose a cascading model and divide samples into groups and apply the multi-layer convolutional neural network for pre-training to collect the embedding vectors of training samples. Finally, features extracted from the pre-training will be used for incremental training on Support Vector Machine. A multi-layer convolutional network and cluster are applied to maintain some key information and train features for classification. Additionally, uncertainty strategy is used to obtain potential features. In the comparative experiments with the above dataset, our proposed method performs the state-of-the-art competitors.

关键词： Training Feature extraction Skin Uncertainty Entropy distributed databases Data mining

来源：评论

学校读者我要写书评

暂无评论

Bundle-based Channel Estimation for 5G NR with Supervised Learning

Bundle-based Channel Estimation for 5G NR with Supervised Le...

引用

GLOBECOM 2020 - 2020 IEEE Global Communications conference

作者： Hyukjoon Kwon Samsung Semiconductor Inc. San Diego CA USA

ISBN: (数字)9781728182988

ISBN: (纸本)9781728182995

This paper explores to improve the quality of channel estimation when a bundling structure is imposed under 3GPP new radio (NR) specification. When bundling is configured, the precoding per bundle is determined solely by a gNB, which is transparent to a user equipment (UE). Due to the possibility that each bundle is precoded in a different manner, the power delay profile (PDP) needs to be estimated within a bundle in a frequency domain, not in a time domain. One simple approach is to assume that PDP is uniformly distributed up to the maximum delay spread. This method is acceptable when a channel is propagated within a short delay spread, but is not in general. Alternatively, this paper utilizes channel correlation even across bundles in a frequency domain and estimates PDP values by using all the correlation directly. A deep learning technique is applied with a neural network to generate correlation as if not to be precoded. To stabilize the performance, post-processing has been added to the neural network such as filtering, truncation and normalization. Simulation results show that the proposed method achieves the performance close to that of ideal PDP and outperforms the uniform PDP assumption by more than 2 dB.

关键词： Correlation Channel estimation Precoding Estimation Delays Time-domain analysis neural networks

来源：评论

学校读者我要写书评

暂无评论

Identifying Hidden Sentiment in Text Using Deep neural network

Identifying Hidden Sentiment in Text Using Deep Neural Netwo...

引用

International conference on Data, Engineering and Applications (IDEA)

作者： Prakash Kumar Singh Sanjeev Sharma Sanchita Paul Birla Institute of Technology Mesra Ranchi India School of Information Technology U.T.D RGPV Bhopal Bhopal India

ISBN: (数字)9781728157184

ISBN: (纸本)9781728157191

Deep learning has emerged as de-facto standard in computer vision. Due to its wide spread success and popularity with image data almost every problem from other domain is now trying to finding its solution with deep learning and the case is no different for text analytics and language modeling in NLP. In sentiment analysis, identifying users' hidden sentiment in text review is a challenging task. Though there are many rule based and statistical machine learning based approaches for sentiment analysis. Most of these machine learning approaches are probabilistic based model and treats the problem as document classification problem based on the word count and their polarity often missing sentiment. With the introduction of the distributed word vector representation embedding models like word2vec, GloVe and FastText, capturing the meaning of the neighboring words for a give target word in the sentence, NLP expectation with deep learning in sentiment analysis has increased a lot. In this paper we used deep neural network based model to perform sentiment analysis on the IMDB movie review dataset. We compare deep learning based approach for sentiment analysis with other traditional machine learning approaches to evaluate the performance of the model. With experiment result we found that the deep learning based NLP model outperformed the traditional machine learning approaches in several ways.

关键词： Sentiment Analysis Deep neural network LSTM Dimension Reduction Word embedding Sentiment analysis Machine Learning Artificial Intelligence Natural Language processing NINL gene texts modelling languages based target words neural network image data

来源：评论

学校读者我要写书评

暂无评论

DeepNautilus: A Deep Learning Based System for Nautical Engines' Live Vibration processing 18th

DeepNautilus: A Deep Learning Based System for Nautical Engi...

引用

18th international conference on Computer Analysis of Images and Patterns (CAIP)

作者： Carbone, Rosario Montella, Raffaele Narducci, Fabio Petrosino, Alfredo Univ Naples Parthenope Dept Sci & Technol Naples Italy

ISBN: (纸本)9783030298913;9783030298906

Recent advances in sensor technologies and data analysis techniques allow reliable and efficient systems for the early diagnosis of breakdowns in the production chain of the car industry and, more generally, of engines. The performance of these systems is based fundamentally on the quality of the features extracted and on the learning technique. In this paper, we show our preliminary, but encouraging, results carried out through our research effort in the field of using deep neural network to recognize and eventually predict engine failures. We present the prototypal blueprint of the system DeepNautilius devoted to detect failures in marine engines using deep learning with the ambitious goal of reducing marine pollution. Our envision comprises a distributed sensor data acquisition system based on the fog/edge/cloud computing paradigm, with a consistent part of the computation located on the edge side. While our architectural approach is described as a design oriented issue, in this work we present our experience with the deep neural network (DNN) computational core, using a literature dataset from an air compression engine. We demonstrate that our approach is not only comparable with the one in literature but is even better performing.

关键词： Deep neural network Edge computing Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Study of Action Recognition using Pose Data toward distributed processing over Edge and Cloud 11

A Study of Action Recognition using Pose Data toward Distrib...

引用

11th IEEE Int Conf on Cloud Comp Technol and Sci (CloudCom) / 19th IEEE Int Conf Comp and Informat Technol (CIT) / 2019 Int Workshop on Resource Brokering with Blockchain (RBchain) / Asia-Pacific Serv Comp Conf (APSCC)

作者： Takasaki, Chikako Takefusa, Atsuko Nakada, Hidemoto Oguchi, Masato Ochanomizu Univ Bunkyo Ku 2-1-1 Otsuka Tokyo 1128610 Japan Natl Inst Informat Chiyoda Ku 2-1-2 Hitotsubashi Tokyo 1018430 Japan Natl Inst Adv Ind Sci & Technol 1-1-1 Umezono Tsukuba Ibaraki 3058560 Japan

ISBN: (纸本)9781728150116

With the development of cameras and sensors, and the spread of cloud computing, life logs can be acquired and stored in general households for various services using the logs. However, it is difficult to analyze moving images acquired by a home sensor in real time using machine learning because the data size and the computational complexity are large. New computing paradigm called edge computing or fog computing, which enables distributed computing over edge and cloud, has the possibility to address this issue. The feature vectors are extracted from moving images by preprocessing on the sensor side and the only small feature vectors are sent to the cloud and used for learning. But, it is not clear how accurately we can recognize actions using only the feature vectors in the learning and inferring. We investigate the accuracies of action recognition with various machine learning methods using feature vector information obtained from moving images. We use the pose estimation library OpenPose for detection of the feature vectors and recognize actions using logistic regression, random forest, support vector machine, and neural network (NN) models, general NN and LSTM, as machine learning methods. The experimental results show that it is possible to recognize an action with 80% accuracy or higher when using random forest and neural network models. We also discuss a method to further improve the accuracy based on the experimental results.

关键词： distributed system moving image recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

Back-Propagated neural network on MapReduce Frameworks: A Survey 2nd

Back-Propagated Neural Network on MapReduce Frameworks: A Su...

引用

2nd International conference on Smart Innovations in Communications and Computational Sciences ICSICCS-2018

作者： Dhanani, Jenish Mehta, Rupa Rana, Dipti Tidke, Bharat S. V. National Institute of Technology Surat India

ISBN: (纸本)9789811324130

Back-propagated neural network (BPNN) is a popular supervised learning technique utilized in machine learning and deep learning to extract knowledge. However, BPNN has shown poor time and space complexity with large volume of data due to its in-memory processing. Huge amount of data sourced by ample of applications and services on the Internet needs to be distributed and parallel environment like MapReduce framework for processing and storage. The large volume of data is divided into smaller chunks and MapReduce framework exploits the cluster of commodity hardware to process these chunks. This research focuses on various MapReduce-based BPNN algorithms such as single-pass and multi-pass MapReduce-based BPNN. The research is intended to perform in-depth comparisons of these techniques considering various parameters such as computation complexity of Mapper and Reducer, granularity of Mapper’s output, number of MapReduce jobs required to build BPNN, and Mapper’s pairs. © 2019, Springer Nature Singapore Pte Ltd.

关键词： MapReduce

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：