scholarly journals Convolutional Neural Networks for On-Board Cloud Screening

2019 ◽  
Vol 11 (12) ◽  
pp. 1417 ◽  
Author(s):  
Sina Ghassemi ◽  
Enrico Magli
Keyword(s):  
Network Performance ◽  
State Of The Art ◽  
High Accuracy ◽  
Resource Consumption ◽  
Processing Unit ◽  
Spectral Bands ◽  
Input Size ◽  
Satellite Platform ◽  
Screening Unit ◽  
Cloud Screening

A cloud screening unit on a satellite platform for Earth observation can play an important role in optimizing communication resources by selecting images with interesting content while skipping those that are highly contaminated by clouds. In this study, we address the cloud screening problem by investigating an encoder–decoder convolutional neural network (CNN). CNNs usually employ millions of parameters to provide high accuracy; on the other hand, the satellite platform imposes hardware constraints on the processing unit. Hence, to allow an onboard implementation, we investigate experimentally several solutions to reduce the resource consumption by CNN while preserving its classification accuracy. We experimentally explore approaches such as halving the computation precision, using fewer spectral bands, reducing the input size, decreasing the number of network filters and also making use of shallower networks, with the constraint that the resulting CNN must have sufficiently small memory footprint to fit the memory of a low-power accelerator for embedded systems. The trade-off between the network performance and resource consumption has been studied over the publicly available SPARCS dataset. Finally, we show that the proposed network can be implemented on the satellite board while performing with reasonably high accuracy compared with the state-of-the-art.

scholarly journals The Degree of Oxidation of Graphene Oxide

Nanomaterials ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 560
Author(s):  
Alexandra Carvalho ◽  
Mariana C. F. Costa ◽  
Valeria S. Marangoni ◽  
Pei Rou Ng ◽  
Thi Le Hang Nguyen ◽  
...  
Keyword(s):  
Graphene Oxide ◽  
Ab Initio ◽  
State Of The Art ◽  
High Accuracy ◽  
Precise Determination ◽  
Photoemission Spectroscopy ◽  
Pristine Graphene ◽  
X Ray ◽  
Degree Of Oxidation

We show that the degree of oxidation of graphene oxide (GO) can be obtained by using a combination of state-of-the-art ab initio computational modeling and X-ray photoemission spectroscopy (XPS). We show that the shift of the XPS C1s peak relative to pristine graphene, ΔEC1s, can be described with high accuracy by ΔEC1s=A(cO−cl)2+E0, where c0 is the oxygen concentration, A=52.3 eV, cl=0.122, and E0=1.22 eV. Our results demonstrate a precise determination of the oxygen content of GO samples.

scholarly journals A Machine Vision Approach for Bioreactor Foam Sensing

2021 ◽  
pp. 247263032110088
Author(s):  
Jonas Austerjost ◽  
Robert Söldner ◽  
Christoffer Edlund ◽  
Johan Trygg ◽  
David Pollard ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Vision ◽  
State Of The Art ◽  
Low Cost ◽  
High Accuracy ◽  
Consumer Electronics ◽  
Learning System ◽  
Automotive Applications ◽  
Fine Grained

Machine vision is a powerful technology that has become increasingly popular and accurate during the last decade due to rapid advances in the field of machine learning. The majority of machine vision applications are currently found in consumer electronics, automotive applications, and quality control, yet the potential for bioprocessing applications is tremendous. For instance, detecting and controlling foam emergence is important for all upstream bioprocesses, but the lack of robust foam sensing often leads to batch failures from foam-outs or overaddition of antifoam agents. Here, we report a new low-cost, flexible, and reliable foam sensor concept for bioreactor applications. The concept applies convolutional neural networks (CNNs), a state-of-the-art machine learning system for image processing. The implemented method shows high accuracy for both binary foam detection (foam/no foam) and fine-grained classification of foam levels.

scholarly journals Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes

2017 ◽  
Vol 25 (1) ◽  
pp. 93-98 ◽  
Author(s):  
Yuan Luo ◽  
Yu Cheng ◽  
Özlem Uzuner ◽  
Peter Szolovits ◽  
Justin Starren
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Graphics Processing Unit ◽  
Medical Problem ◽  
Feature Engineering ◽  
Processing Unit ◽  
Clinical Notes ◽  
Overall Evaluation ◽  
Relation Classification

Abstract We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2/VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem–treatment relations, 0.820 for medical problem–test relations, and 0.702 for medical problem–medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering.

scholarly journals Sea Ice Albedo from MISR and MODIS: Production, Validation, and Trend Analysis

2018 ◽  
Vol 11 (1) ◽  
pp. 9 ◽  
Author(s):  
Said Kharbouche ◽  
Jan-Peter Muller
Keyword(s):  
Sea Ice ◽  
Near Infrared ◽  
Time Window ◽  
Solar Spectrum ◽  
High Accuracy ◽  
Dynamic Surface ◽  
Spectral Bands ◽  
Langley Research Center ◽  
Terra Satellite ◽  
Cloud Mask

The Multi-angle Imaging SpectroRadiometer (MISR) sensor onboard the Terra satellite provides high accuracy albedo products. MISR deploys nine cameras each at different view angles, which allow a near-simultaneous angular sampling of the surface anisotropy. This is particularly important to measure the near-instantaneous albedo of dynamic surface features such as clouds or sea ice. However, MISR’s cloud mask over snow or sea ice is not yet sufficiently robust because MISR’s spectral bands are only located in the visible and the near infrared. To overcome this obstacle, we performed data fusion using a specially processed MISR sea ice albedo product (that was generated at Langley Research Center using Rayleigh correction) combining this with a cloud mask of a sea ice mask product, MOD29, which is derived from the MODerate Resolution Imaging Spectroradiometer (MODIS), which is also, like MISR, onboard the Terra satellite. The accuracy of the MOD29 cloud mask has been assessed as >90% due to the fact that MODIS has a much larger number of spectral bands and covers a much wider range of the solar spectrum. Four daily sea ice products have been created, each with a different averaging time window (24 h, 7 days, 15 days, 31 days). For each time window, the number of samples, mean and standard deviation of MISR cloud-free sea ice albedo is calculated. These products are publicly available on a predefined polar stereographic grid at three spatial resolutions (1 km, 5 km, 25 km). The time span of the generated sea ice albedo covers the months between March and September of each year from 2000 to 2016 inclusive. In addition to data production, an evaluation of the accuracy of sea ice albedo was performed through a comparison with a dataset generated from a tower based albedometer from NOAA/ESRL/GMD/GRAD. This comparison confirms the high accuracy and stability of MISR’s sea ice albedo since its launch in February 2000. We also performed an evaluation of the day-of-year trend of sea ice albedo between 2000 and 2016, which confirm the reduction of sea ice shortwave albedo with an order of 0.4–1%, depending on the day of year and the length of observed time window.

scholarly journals A Deep Learning Approach for Burned Area Segmentation with Sentinel-2 Data

2020 ◽  
Vol 12 (15) ◽  
pp. 2422
Author(s):  
Lisa Knopp ◽  
Marc Wieland ◽  
Michaela Rättich ◽  
Sandro Martinis
Keyword(s):  
Deep Learning ◽  
Network Performance ◽  
Near Infrared ◽  
Remote Sensing Data ◽  
Economic Consequences ◽  
Validation Dataset ◽  
Burned Area ◽  
Burned Areas ◽  
Spectral Bands ◽  
Sentinel 2

Wildfires have major ecological, social and economic consequences. Information about the extent of burned areas is essential to assess these consequences and can be derived from remote sensing data. Over the last years, several methods have been developed to segment burned areas with satellite imagery. However, these methods mostly require extensive preprocessing, while deep learning techniques—which have successfully been applied to other segmentation tasks—have yet to be fully explored. In this work, we combine sensor-specific and methodological developments from the past few years and suggest an automatic processing chain, based on deep learning, for burned area segmentation using mono-temporal Sentinel-2 imagery. In particular, we created a new training and validation dataset, which is used to train a convolutional neural network based on a U-Net architecture. We performed several tests on the input data and reached optimal network performance using the spectral bands of the visual, near infrared and shortwave infrared domains. The final segmentation model achieved an overall accuracy of 0.98 and a kappa coefficient of 0.94.

scholarly journals A k-Distribution-Based Spectral Module for Radiation Calculations in Multi-Phase Mixtures

2009 ◽  
Author(s):  
Gopalendu Pal ◽  
Anquan Wang ◽  
Michael F. Modest
Keyword(s):  
State Of The Art ◽  
Source Code ◽  
Computational Cost ◽  
High Accuracy ◽  
Grid Structure ◽  
Participating Media ◽  
Flow Solver ◽  
Domain Of Applicability ◽  
Code Module ◽  
Multi Phase

k-distribution-based approaches are promising models for radiation calculations in strongly nongray participating media. Advanced k-distribution methods were found to achieve close-to benchmark line-by-line (LBL) accuracy for strongly inhomogeneous multi-phase media accompanied by several orders of magnitude smaller computational cost. In this paper, a k-distribution-based portable spectral module is developed, incorporating several state-of-the-art k-distribution methods along with compact and high-accuracy databases of k-distributions. The module construction is flexible — the user can choose among various k-distribution methods with their relevant k-distribution databases, to carry out accurate radiation calculations. The spectral module is portable, such that it can be coupled to any flow solver code with its own grid structure, discretization scheme, and solver libraries. This open source code module is made available for free for all noncommercial purposes. This article outlines in detail the design and the use of the spectral module. The k-distribution methods included in the module are briefly described with a discussion of their advantages, disadvantages and their domain of applicability. Examples are provided for various sample radiation calculations in multi-phase mixtures using the new spectral module and the results are compared with LBL calculations.

scholarly journals Multistructure-Based Collaborative Online Distillation

Entropy ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. 357
Author(s):  
Liang Gao ◽  
Xu Lan ◽  
Haibo Mi ◽  
Dawei Feng ◽  
Kele Xu ◽  
...  
Keyword(s):  
Performance Improvement ◽  
Network Performance ◽  
State Of The Art ◽  
Autonomous Driving ◽  
Supplementary Information ◽  
Training Method ◽  
Machine Learning Methods ◽  
Information Diversity ◽  
Knowledge Distillation ◽  
Memory Resources

Recently, deep learning has achieved state-of-the-art performance in more aspects than traditional shallow architecture-based machine-learning methods. However, in order to achieve higher accuracy, it is usually necessary to extend the network depth or ensemble the results of different neural networks. Increasing network depth or ensembling different networks increases the demand for memory resources and computing resources. This leads to difficulties in deploying depth-learning models in resource-constrained scenarios such as drones, mobile phones, and autonomous driving. Improving network performance without expanding the network scale has become a hot topic for research. In this paper, we propose a cross-architecture online-distillation approach to solve this problem by transmitting supplementary information on different networks. We use the ensemble method to aggregate networks of different structures, thus forming better teachers than traditional distillation methods. In addition, discontinuous distillation with progressively enhanced constraints is used to replace fixed distillation in order to reduce loss of information diversity in the distillation process. Our training method improves the distillation effect and achieves strong network-performance improvement. We used some popular models to validate the results. On the CIFAR100 dataset, AlexNet’s accuracy was improved by 5.94%, VGG by 2.88%, ResNet by 5.07%, and DenseNet by 1.28%. Extensive experiments were conducted to demonstrate the effectiveness of the proposed method. On the CIFAR10, CIFAR100, and ImageNet datasets, we observed significant improvements over traditional knowledge distillation.

scholarly journals Bringing state-of-the-art diagnostics to vulnerable populations: The use of a mobile screening unit in active case finding for tuberculosis in Palawan, the Philippines

PLoS ONE ◽  
2017 ◽  
Vol 12 (2) ◽  
pp. e0171310 ◽  
Author(s):  
Fukushi Morishita ◽  
Anna Marie Celina Gonzales Garfin ◽  
Woojin Lew ◽  
Kyung Hyun Oh ◽  
Rajendra-Prasad Yadav ◽  
...  
Keyword(s):  
Vulnerable Populations ◽  
State Of The Art ◽  
The Philippines ◽  
Case Finding ◽  
Active Case Finding ◽  
Active Case ◽  
Screening Unit ◽  
Mobile Screening

scholarly journals An improved real-time object proposals generation method based on local binary pattern

2017 ◽  
Vol 14 (4) ◽  
pp. 172988141772467 ◽  
Author(s):  
Yanting Jiang ◽  
Jia Yan ◽  
Ci’en Fan ◽  
Wenxuan Shi ◽  
Dexiang Deng
Keyword(s):  
Local Binary Pattern ◽  
Sliding Window ◽  
High Accuracy ◽  
Processing Unit ◽  
Data Set ◽  
Central Processing ◽  
Lighting Conditions ◽  
Occluded Objects ◽  
Object Proposals ◽  
Short Time

Generating a group of category-independent proposals of objects in an image within a very short time is an effective approach to accelerate traditional sliding window search, which has been widely used in preprocessing step of object recognition. In this article, we propose a novel object proposals generation method to produce an order set of candidate windows covering most of object instances. With combination of gradient and local binary pattern, our approach achieves better performance than BING in finding occluded objects and objects in dim lighting conditions. In experiments on the challenging PASCAL VOC 2007 data set, we show that our approach is significantly more accurate than BING. In particular, using 2000 proposals, we achieve 97.6% object detection rate and 69.3% mean average best overlap. Moreover, our proposed method is very efficient and takes only about 0.006 s per image on a laptop central processing unit. The detection speed and high accuracy of proposed method mean that it can be applied to recognizing specific objects in robot visions.

scholarly journals Relation Extraction Using Supervision from Topic Knowledge of Relation Labels

2019 ◽  
Author(s):  
Haiyun Jiang ◽  
Li Cui ◽  
Zhe Xu ◽  
Deqing Yang ◽  
Jindong Chen ◽  
...  
Keyword(s):  
Semantic Similarity ◽  
State Of The Art ◽  
Relation Extraction ◽  
High Accuracy ◽  
Sampling Strategies ◽  
Training Process ◽  
Matching Problem ◽  
Topic Knowledge ◽  
Matching Score ◽  
Model Relation

Explicitly exploring the semantics of a relation is significant for high-accuracy relation extraction, which is, however, not fully studied in previous work. In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. That is, the matching score between a sentence and a candidate relation is predicted for an entity pair. To this end, we propose a deep matching network to precisely model the semantic similarity between a sentence-relation pair. Besides, the topic knowledge also allows us to derive the importance information of samples as well as two knowledge-guided negative sampling strategies in the training process. We conduct extensive experiments to evaluate the proposed framework and observe improvements in AUC of 11.5% and max F1 of 5.4% over the baselines with state-of-the-art performance.

Sign in / Sign up

Export Citation Format

Share Document