scholarly journals The Integration of Linguistic and Geospatial Features Using Global Context Embedding for Automated Text Geocoding

2021 ◽  
Vol 10 (9) ◽  
pp. 572
Author(s):  
Zheren Yan ◽  
Can Yang ◽  
Lei Hu ◽  
Jing Zhao ◽  
Liangcun Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Classification Problem ◽  
Geographical Information ◽  
Local Context ◽  
Place Names ◽  
Global Features ◽  
Global Context ◽  
The Neural Network ◽  
Textual Data ◽  
Local And Global Features

Geocoding is an essential procedure in geographical information retrieval to associate place names with coordinates. Due to the inherent ambiguity of place names in natural language and the scarcity of place names in textual data, it is widely recognized that geocoding is challenging. Recent advances in deep learning have promoted the use of the neural network to improve the performance of geocoding. However, most of the existing approaches consider only the local context, e.g., neighboring words in a sentence, as opposed to the global context, e.g., the topic of the document. Lack of global information may have a severe impact on the robustness of the model. To fill the research gap, this paper proposes a novel global context embedding approach to generate linguistic and geospatial features through topic embedding and location embedding, respectively. A deep neural network called LGGeoCoder, which integrates local and global features, is developed to solve the geocoding as a classification problem. The experiments on a Wikipedia place name dataset demonstrate that LGGeoCoder achieves competitive performance compared with state-of-the-art models. Furthermore, the effect of introducing global linguistic and geospatial features in geocoding to alleviate the ambiguity and scarcity problem is discussed.

scholarly journals Remaining Useful Life Prediction of Rolling Bearings Based on Multiscale Convolutional Neural Network with Integrated Dilated Convolution Blocks

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Ran Wang ◽  
Ruyu Shi ◽  
Xiong Hu ◽  
Changqing Shen
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Receptive Fields ◽  
Remaining Useful Life ◽  
Global Features ◽  
Complex Signals ◽  
Dilated Convolution ◽  
Local And Global Features ◽  
Useful Life

Remaining useful life (RUL) prediction is necessary for guaranteeing machinery’s safe operation. Among deep learning architectures, convolutional neural network (CNN) has shown achievements in RUL prediction because of its strong ability in representation learning. Features from different receptive fields extracted by different sizes of convolution kernels can provide complete information for prognosis. The single size convolution kernel in traditional CNN is difficult to learn comprehensive information from complex signals. Besides, the ability to learn local and global features synchronously is limited to conventional CNN. Thus, a multiscale convolutional neural network (MS-CNN) is introduced to overcome these aforementioned problems. Convolution filters with different dilation rates are integrated to form a dilated convolution block, which can learn features in different receptive fields. Then, several stacked integrated dilated convolution blocks in different depths are concatenated to extract local and global features. The effectiveness of the proposed method is verified by a bearing dataset prepared from the PRONOSTIA platform. The results turn out that the proposed MS-CNN has higher prediction accuracy than many other deep learning-based RUL methods.

scholarly journals THE IMPLEMENTATION OF THE NEURAL NETWORK FOR THE CLASSIFICATION PROBLEM

2014 ◽  
pp. 119-126
Author(s):  
Ulyana Lisovik ◽  
Oleksandr Lipchanskiy
Keyword(s):  
Neural Network ◽  
Structural Model ◽  
Classification Problem ◽  
Model Description ◽  
Function Model ◽  
System Synthesis ◽  
The Neural Network ◽  
Hardware Costs ◽  
Vhdl Code ◽  
Characteristics Estimation

The example of NN realization is considered. Also description of all its design stages from NN function model description to its timing and hardware characteristics estimation is considered. NN structural model is presented in VHDL code. Through SynplifyPro 7.0 package from Synplicity® the system synthesis with the orientation on Virtex- II XC2V6000 family is made out. The estimation of the optimality of the synthesized NN model utilization is accomplished. NN structures are shown; hardware costs are taken to the table.

Endek Classification Based On GLCM Using Artificial Neural Networks with Adam Optimization

2020 ◽  
Vol 9 (2) ◽  
pp. 285
Author(s):  
Putu Wahyu Tirta Guna ◽  
Luh Arida Ayu Ayu Rahning Putri
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Back Propagation ◽  
Classification Problem ◽  
Model Accuracy ◽  
Computing Power ◽  
The Neural Network ◽  
Extraction Algorithm ◽  
Better Than

Not many people know that endek cloth itself has 4 known variances. .Nowadays. Computing and classification algorithm can be implemented to solve classification problem with respect to the features data as input. We can use this computing power to digitalize these endek pattern. The features extraction algorithm used in this research is GLCM. Where these data will act as input for the neural network model later. There is a lot of optimizer algorithm to use in back propagation phase. In this research we  prefer to use adam which is one of the newest and most popular optimizer algorithm. To compare its performace we also use SGD which is older and popular optimizer algorithm. Later we find that adam algorithm generate 33% accuracy which is better than what SGD algorithm give, it is 23% accuracy. Longer epoch also give affect for overall model accuracy.

Gesture Recognition of Pigs Based on Wavelet Moment and Probabilistic Neural Network

2014 ◽  
Vol 687-691 ◽  
pp. 3691-3694
Author(s):  
Jin Jin Zhou ◽  
Wei Xing Zhu
Keyword(s):  
Neural Network ◽  
Ant Colony Algorithm ◽  
Probabilistic Neural Network ◽  
Image Feature ◽  
Global Features ◽  
Multi Scale ◽  
Invariant Moments ◽  
The Neural Network ◽  
Structural Details ◽  
Growth Method

For real-time monitoring the behavior of pigs in piggery, the method that combined the advantages of wavelet multi-scale analysis with invariant moments is proposed. Firstly, the original image is pre-processed by using ant colony algorithm to extract object contour. Then the target contour edge growth method and binary morphology are used, and the outlines of pigs are extracted by canny operator. Wavelet moment was used to get the global features of an image and increase the structural details of the image feature description. Finally, the neural network is applied to identify four behaviors including normal walking, walking down, looked up walking and lying of pigs. Experimental results show that the accuracy of the classification and identification of swine gesture reached more than 95%. This method has a better effect in the recognition of pigs and the noise resistance.

scholarly journals Simplicial-Map Neural Networks Robust to Adversarial Examples

Mathematics ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 169
Author(s):  
Eduardo Paluzo-Hidalgo ◽  
Rocio Gonzalez-Diaz ◽  
Miguel A. Gutiérrez-Naranjo ◽  
Jónathan Heras
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Algebraic Topology ◽  
Classification Problem ◽  
Classification Model ◽  
The Neural Network ◽  
Input Dataset ◽  
Adversarial Examples ◽  
Simplicial Map ◽  
Adversarial Example

Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data point produces a change on the output label assigned by the model. Such adversarial examples represent a weakness for the safety of neural network applications, and many different solutions have been proposed for minimizing their effects. In this paper, we propose a new approach by means of a family of neural networks called simplicial-map neural networks constructed from an Algebraic Topology perspective. Our proposal is based on three main ideas. Firstly, given a classification problem, both the input dataset and its set of one-hot labels will be endowed with simplicial complex structures, and a simplicial map between such complexes will be defined. Secondly, a neural network characterizing the classification problem will be built from such a simplicial map. Finally, by considering barycentric subdivisions of the simplicial complexes, a decision boundary will be computed to make the neural network robust to adversarial attacks of a given size.

scholarly journals Climatology at any point : A neural network solution

MAUSAM ◽  
2021 ◽  
Vol 64 (2) ◽  
pp. 231-250
Author(s):  
PULAK GUHATHAKURTA ◽  
AJIT TYAGI ◽  
B. MUKHOPADHYAY
Keyword(s):  
Neural Network ◽  
Atmospheric Pressure ◽  
Spatial Interpolation ◽  
Meteorological Parameters ◽  
Geographical Information ◽  
Maximum Temperature ◽  
Long Period ◽  
The Neural Network ◽  
Past Data ◽  
Advance Knowledge

lHkh mi;ksxdrkZvksa] ;kstuk cukus okyksa] vkink izca/ku dkfeZdksa] i;ZVu vkfn }kjk rkieku] vf/kdre rkieku] U;wure rkieku] ok;qeaMyh; nkc] o"kkZ vkfn tSls ekSle izkpyksa dh tyok;q foKku ij lwpukvksa dh mUur tkudkjh dh vR;kf/kd ek¡x jgh gSA fdlh LFkku fo'ks"k esa os/k’kkyk ds vHkko vkSj dHkh&dHkh nh?kZ vof/k ds igys ds vk¡dM+ksa dh vuqiyC/krk ds dkj.k ekSle foKku leqnk; ml LFkku fo’ks"k ds fy, visf{kr lwpukvksa dks miyC/k ugha djk ikrk gSA bl 'kks/k i= esa LFkkfud varosZ’ku ds {ks= esa U;wjy usVodZ ds rqyukRed u, vuqiz;ksx crk, x, gSaA iwjs ckjg eghuksa ds vf/kdre vkSj U;wure nksuksa rkiekuksa  ds fy, U;wjy usVodZ varosZ’ku fun’kZ fodflr fd, x, gSaA ;g ekWMy ml LFkku fo’ks"k ij lkekU; vf/kdre vkSj U;wure rkiekuksa dks rS;kj djus ds fy, lwpukvksa ds :i  esa v{kka’k] ns’kkUrj vkSj mUu;u tSlh HkkSxksfyd lwpukvksa dk mi;ksx djrk gSA varosZ’ku ds fy, LFkkfud ekWMyksa ds fu"iknuksa dh rqyuk vU; lkekU;r% iz;qDr i)fr ds lkFk dh xbZ gSA Advance knowledge of information on  climatology of meteorological parameters like temperature, maximum temperature, minimum temperature, atmospheric pressure, rainfall etc are of great demands from all the users, planners, disaster managements personals, tourism etc. The information is required at the place concerned but this cannot be fulfilled by the meteorological community due to absent of observatory at that place and also some time absent of past data of long period. The present paper has described a comparatively new application of the neural network in the field of spatial interpolation. Neural network interpolation models are developed for both maximum and minimum temperatures for all the twelve months. The model utilizes geographical information like latitude, longitude and elevation as inputs to generate normal maximum and minimum temperatures at a place. The performances of the models are compared with the other commonly used method for spatial interpolation.  

HCNN: A Neural Network Model for Combining Local and Global Features Towards Human-Like Classification

2015 ◽  
Vol 30 (01) ◽  
pp. 1655004 ◽  
Author(s):  
Tielin Zhang ◽  
Yi Zeng ◽  
Bo Xu
Keyword(s):  
Neural Network ◽  
Visual System ◽  
Image Classification ◽  
Network Model ◽  
Neural Network Model ◽  
Human Visual System ◽  
Experimental Results ◽  
Natural Images ◽  
Global Features ◽  
Local And Global Features

Brain-inspired algorithms such as convolutional neural network (CNN) have helped machine vision systems to achieve state-of-the-art performance for various tasks (e.g. image classification). However, CNNs mainly rely on local features (e.g. hierarchical features of points and angles from images), while important global structured features such as contour features are lost. Global understanding of natural objects is considered to be essential characteristics that the human visual system follows, and for developing human-like visual systems, the lost of consideration from this perspective may lead to inevitable failure on certain tasks. Experimental results have proved that well-trained CNN classifier cannot correctly distinguish fooling images (in which some local features from the natural images are chaotically distributed) from natural images. For example, a picture that is composed of yellow–black bars will be recognized as school bus with very high confidence by CNN. On the contrary, human visual system focuses on both the texture and contour features to form representation of images and would not mis-take them. In order to solve the upper problem, we propose a neural network model, named as histogram of oriented gradient (HOG) improved CNN (HCNN), that combines local and global features towards human-like classification based on CNN and HOG. The experimental results on MNIST datasets and part of ImageNet datasets show that HCNN outperforms traditional CNN for object classification with fooling images, which indicates the feasibility, accuracy and potential effectiveness of HCNN for solving image classification problem.

scholarly journals Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

2017 ◽  
Author(s):  
Wei Li ◽  
Xiatian Zhu ◽  
Shaogang Gong
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
State Of The Art ◽  
Feature Representation ◽  
Global Feature ◽  
Global Features ◽  
Joint Learning ◽  
Discriminative Feature ◽  
Wide Range ◽  
Local And Global Features

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly learning local and global features in a Convolutional Neural Network (CNN) by aiming to discover correlated local and global features in different context. Specifically, we formulate a method for joint learning of local and global feature selection losses designed to optimise person re-id when using generic matching metrics such as the L2 distance. We design a novel CNN architecture for Jointly Learning Multi-Loss (JLML) of local and global discriminative feature optimisation subject concurrently to the same re-id labelled information. Extensive comparative evaluations demonstrate the advantages of this new JLML model for person re-id over a wide range of state-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03, Market-1501).

scholarly journals Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

Mathematics ◽  
2021 ◽  
Vol 9 (21) ◽  
pp. 2722
Author(s):  
Ciprian-Octavian Truică ◽  
Elena-Simona Apostol ◽  
Maria-Luiza Șerban ◽  
Adrian Paschke
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Topic Modeling ◽  
Deep Neural Network ◽  
Local Context ◽  
Network Architectures ◽  
Word Embeddings ◽  
Contextual Cues ◽  
Global Context ◽  
Document Level

Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without considering the local context that can be extracted from the dataset, or they detect the overall topic polarity without considering both the local and global context. In this paper, we propose a novel document-topic embedding model, DocTopic2Vec, for document-level polarity detection in large texts by employing general and specific contextual cues obtained through the use of document embeddings (Doc2Vec) and Topic Modeling. In our approach, (1) we use a large dataset with game reviews to create different word embeddings by applying Word2Vec, FastText, and GloVe, (2) we create Doc2Vecs enriched with the local context given by the word embeddings for each review, (3) we construct topic embeddings Topic2Vec using three Topic Modeling algorithms, i.e., LDA, NMF, and LSI, to enhance the global context of the Sentiment Analysis task, (4) for each document and its dominant topic, we build the new DocTopic2Vec by concatenating the Doc2Vec with the Topic2Vec created with the same word embedding. We also design six new Convolutional-based (Bidirectional) Recurrent Deep Neural Network Architectures that show promising results for this task. The proposed DocTopic2Vecs are used to benchmark multiple Machine and Deep Learning models, i.e., a Logistic Regression model, used as a baseline, and 18 Deep Neural Networks Architectures. The experimental results show that the new embedding and the new Deep Neural Network Architectures achieve better results than the baseline, i.e., Logistic Regression and Doc2Vec.

Sign in / Sign up

Export Citation Format

Share Document