scholarly journals Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks

2020 ◽  
Vol 6 (4) ◽  
pp. 24
Author(s):  
Michalis Giannopoulos ◽  
Anastasia Aidini ◽  
Anastasia Pentari ◽  
Konstantina Fotiadou ◽  
Panagiotis Tsakalides
Keyword(s):  
Remote Sensing ◽  
Classification Performance ◽  
Low Rank ◽  
Multispectral Images ◽  
Negative Effects ◽  
Compression Scheme ◽  
Sensing Platforms ◽  
The Impact ◽  
And Storage

Multispectral sensors constitute a core Earth observation image technology generating massive high-dimensional observations. To address the communication and storage constraints of remote sensing platforms, lossy data compression becomes necessary, but it unavoidably introduces unwanted artifacts. In this work, we consider the encoding of multispectral observations into high-order tensor structures which can naturally capture multi-dimensional dependencies and correlations, and we propose a resource-efficient compression scheme based on quantized low-rank tensor completion. The proposed method is also applicable to the case of missing observations due to environmental conditions, such as cloud cover. To quantify the performance of compression, we consider both typical image quality metrics as well as the impact on state-of-the-art deep learning-based land-cover classification schemes. Experimental analysis on observations from the ESA Sentinel-2 satellite reveals that even minimal compression can have negative effects on classification performance which can be efficiently addressed by our proposed recovery scheme.

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

scholarly journals Document representations for classification of short web-page descriptions

2008 ◽  
Vol 18 (1) ◽  
pp. 123-138 ◽  
Author(s):  
Milos Radovanovic ◽  
Mirjana Ivanovic
Keyword(s):  
Text Categorization ◽  
Web Search ◽  
Classification Performance ◽  
Document Representation ◽  
Web Page ◽  
Ve Bayes ◽  
Large Hierarchy ◽  
The Impact ◽  
Document Representations

Motivated by applying Text Categorization to classification of Web search results, this paper describes an extensive experimental study of the impact of bag-of- words document representations on the performance of five major classifiers - Na?ve Bayes, SVM, Voted Perceptron, kNN and C4.5. The texts, representing short Web-page descriptions sorted into a large hierarchy of topics, are taken from the dmoz Open Directory Web-page ontology, and classifiers are trained to automatically determine the topics which may be relevant to a previously unseen Web-page. Different transformations of input data: stemming, normalization, logtf and idf, together with dimensionality reduction, are found to have a statistically significant improving or degrading effect on classification performance measured by classical metrics - accuracy, precision, recall, F1 and F2. The emphasis of the study is not on determining the best document representation which corresponds to each classifier, but rather on describing the effects of every individual transformation on classification, together with their mutual relationships. .

scholarly journals Impact of the COVID-19 pandemic on the production and sales of cars in the world

2021 ◽  
pp. 63-70
Author(s):  
Inna Shevchenko ◽  
Illia Dmytriiev ◽  
Oksana Dmytriieva
Keyword(s):  
Automotive Industry ◽  
Global Financial Crisis ◽  
Negative Consequences ◽  
Negative Effects ◽  
The Past ◽  
The World ◽  
The Global Financial Crisis ◽  
The Impact ◽  
Insight Into

Problem. The global automotive industry has already had an experience of recovery from the global financial crisis of 2008, but the pandemic crisis of 2020 is quite different in nature and pattern of progress: in recent history it has had no analogues and it will be premature to state its completion. Therefore, it is important to determine the impact of the pandemic on the production and sale of cars in order to overcome the negative consequences. To address this issue, the article identifies the sensitivity of this subsector of mechanical engineering to destructive changes in the environment; an analysis of changes in the volume of production and sales of cars by countries of the world over the past period has been made. Goal. The aim of the work is to determine the destructive consequences and trends of the COVID-19 pandemic impact on the global automotive industry, namely the production and sale of cars. Methodology. To determine the impact of the COVID-19 pandemic, a vertical and horizontal analysis of car production and sales in the world has been conducted. Results. The results of the analysis allowed the authors to group the countries of the world by the destructive effects of the pandemic crisis of 2020 for the automotive industry. Originality. The carried out classification of countries by the destructive effects of the COVID-19 pandemic provided an opportunity to gain insight into its impact on the automotive industry, in particular on the production and sale of cars. Practical value. The obtained results can be recommended to identify further ways to overcome the negative effects of the COVID-19 pandemic in the automotive industry.

Effects of elevated CO2 and 1-methylcyclopropene on storage-related disorders of Ontario-grown Empire apples

2014 ◽  
Vol 94 (5) ◽  
pp. 857-865 ◽  
Author(s):  
Kristen L. Deyman ◽  
Greta Chiu ◽  
Jingyun Liu ◽  
Carolyne J. Brikis ◽  
Christopher P. Trobacher ◽  
...  
Keyword(s):  
Storage Temperature ◽  
Rapid Development ◽  
Apple Fruit ◽  
Negative Effects ◽  
Multiple Treatment ◽  
Partial Pressures ◽  
Flesh Browning ◽  
Atmosphere Storage ◽  
The Impact ◽  
And Storage

Deyman, K. L., Chiu, G., Liu, J., Brikis, C. J., Trobacher, C. P., DeEll, J. R., Shelp, B. J. and Bozzo, G. G. 2014. Effects of elevated CO2 and 1-methylcyclopropene on storage-related disorders of Ontario-grown Empire apples. Can. J. Plant Sci. 94: 857–865. The impact of 1-methylcyclopropene (1-MCP) application on CO2-induced physiological injury in Empire apple fruit during controlled atmosphere storage was assessed over a 3-yr period using an experimental design involving multiple treatment replicates. Fruit harvested at optimal maturity from one or two orchards were treated with or without 1 µL L−1 1-MCP, then chilled at 0 or 3°C under various CO2 partial pressures (5, 2.5 or 0.03 kPa CO2) in the presence of 2.5 kPa O2 for up to 46 wk using a split-plot design. Fruit were sampled periodically for assessment of flesh browning and external peel injury. The maximal incidence of external CO2 injury varied from 15 to 100% over the 3 yr, and the most rapid development of this disorder was evident at 5 kPa CO2. The incidence of external CO2 injury as a function of storage time was influenced by orchard location and storage temperature. Moreover, the incidence of flesh browning at 0°C and 5 kPa CO2 was influenced slightly by orchard; this disorder was never higher than 30%, and the impact of elevated CO2 was inconsistent across years. Notably, there was no evidence for negative effects of 1-MCP on the incidence of storage-related disorders.

scholarly journals Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification

2021 ◽  
Vol 13 (14) ◽  
pp. 2728
Author(s):  
Qingjie Zeng ◽  
Jie Geng ◽  
Kai Huang ◽  
Wen Jiang ◽  
Jun Guo
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Image ◽  
Classification Performance ◽  
Scene Classification ◽  
Remote Sensing Images ◽  
Training Set ◽  
Shot Classification ◽  
Support Set ◽  
Feature Expression

Few-shot classification of remote sensing images has attracted attention due to its important applications in various fields. The major challenge in few-shot remote sensing image scene classification is that limited labeled samples can be utilized for training. This may lead to the deviation of prototype feature expression, and thus the classification performance will be impacted. To solve these issues, a prototype calibration with a feature-generating model is proposed for few-shot remote sensing image scene classification. In the proposed framework, a feature encoder with self-attention is developed to reduce the influence of irrelevant information. Then, the feature-generating module is utilized to expand the support set of the testing set based on prototypes of the training set, and prototype calibration is proposed to optimize features of support images that can enhance the representativeness of each category features. Experiments on NWPU-RESISC45 and WHU-RS19 datasets demonstrate that the proposed method can yield superior classification accuracies for few-shot remote sensing image scene classification.

scholarly journals Mapping the Effects of Anthropogenic Activities in the Catchment of Weija Reservoir using Remote Sensing Techniques

2020 ◽  
Vol 17 (2) ◽  
pp. 6-11
Author(s):  
N. D. Tagoe ◽  
S. Mantey
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Anthropogenic Activities ◽  
Wild Plants ◽  
Landsat Images ◽  
Dense Vegetation ◽  
Human Use ◽  
Remote Sensing Techniques ◽  
The Impact

Man has contributed to land cover alteration since time-immemorial through clearing of land for residential, agriculture, recreational and industrial purposes. The emergence of adapting wild plants and animals for human use as well as industrialisation have also contributed to the alteration of land cover. Over the years, anthropogenic activities have had great impact on the Weija catchment. This study seeks to map the catchment and determine the impact of anthropogenic activities using Remote Sensing techniques. Observations and measurements were made on the field as well as classification of land cover using Landsat images of years 1991, 2003 and 2017. Results showed an increase in built-up areas by 18% from 1991 to 2017. Other classes such as shrubs increased due to decrease in dense vegetation. This study confirms the use of Remote Sensing as a valuable tool for detecting change in land cover and determining the impact of anthropogenic activities in the Weija Catchment. Keywords: Land Cover, GIS, Remote Sensing, Weija Catchment, Anthropogenic Activities

scholarly journals Scene classification of remote sensing image based on compound pruning

2021 ◽  
Vol 336 ◽  
pp. 06030
Author(s):  
Fengbing Jiang ◽  
Fang Li ◽  
Guoliang Yang
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Image Data ◽  
Remote Sensing Image ◽  
Convolution Neural Network ◽  
Model Parameters ◽  
Scene Classification ◽  
Remote Sensing Image Classification ◽  
And Storage

Convolution neural network for remote sensing image scene classification consumes a lot of time and storage space to train, test and save the model. In this paper, firstly, elastic variables are defined for convolution layer filter, and combined with filter elasticity and batch normalization scaling factor, a compound pruning method of convolution neural network is proposed. Only the superparameter of pruning rate needs to be adjusted during training. in the process of training, the performance of the model can be improved by means of transfer learning. In this paper, algorithm tests are carried out on NWPU-RESISC45 remote sensing image data to verify the effectiveness of the proposed method. According to the experimental results, the proposed method can not only effectively reduce the number of model parameters and computation, but also ensure the accuracy of the algorithm in remote sensing image classification.

Sign in / Sign up

Export Citation Format

Share Document