scholarly journals Wildfire Segmentation Using Deep Vision Transformers

2021 ◽  
Vol 13 (17) ◽  
pp. 3527
Author(s):  
Rafik Ghali ◽  
Moulay A. Akhloufi ◽  
Marwa Jmal ◽  
Wided Souidene Mseddi ◽  
Rabah Attia
Keyword(s):  
Early Detection ◽  
Long Range ◽  
Forest Fires ◽  
State Of The Art ◽  
The Self ◽  
Convolution Operators ◽  
Sequence Prediction ◽  
Convolutional Networks ◽  
Input And Output ◽  
Global And Local

In this paper, we address the problem of forest fires’ early detection and segmentation in order to predict their spread and help with fire fighting. Techniques based on Convolutional Networks are the most used and have proven to be efficient at solving such a problem. However, they remain limited in modeling the long-range relationship between objects in the image, due to the intrinsic locality of convolution operators. In order to overcome this drawback, Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures. They have recently been used to determine the global dependencies between input and output sequences using the self-attention mechanism. In this context, we present in this work the very first study, which explores the potential of vision Transformers in the context of forest fire segmentation. Two vision-based Transformers are used, TransUNet and MedT. Thus, we design two frameworks based on the former image Transformers adapted to our complex, non-structured environment, which we evaluate using varying backbones and we optimize for forest fires’ segmentation. Extensive evaluations of both frameworks revealed a performance superior to current methods. The proposed approaches achieved a state-of-the-art performance with an F1-score of 97.7% for TransUNet architecture and 96.0% for MedT architecture. The analysis of the results showed that these models reduce fire pixels mis-classifications thanks to the extraction of both global and local features, which provide finer detection of the fire’s shape.

scholarly journals Self-Attention ConvLSTM for Spatiotemporal Prediction

2020 ◽  
Vol 34 (07) ◽  
pp. 11531-11538
Author(s):  
Zhihui Lin ◽  
Maomao Li ◽  
Zhuobin Zheng ◽  
Yangyang Cheng ◽  
Chun Yuan
Keyword(s):  
Long Range ◽  
State Of The Art ◽  
The Self ◽  
Time Step ◽  
Traffic Flow Prediction ◽  
Spatial Features ◽  
Gating Mechanism ◽  
Spatial Dependencies ◽  
Previous State ◽  
Global And Local

Spatiotemporal prediction is challenging due to the complex dynamic motion and appearance changes. Existing work concentrates on embedding additional cells into the standard ConvLSTM to memorize spatial appearances during the prediction. These models always rely on the convolution layers to capture the spatial dependence, which are local and inefficient. However, long-range spatial dependencies are significant for spatial applications. To extract spatial features with both global and local dependencies, we introduce the self-attention mechanism into ConvLSTM. Specifically, a novel self-attention memory (SAM) is proposed to memorize features with long-range dependencies in terms of spatial and temporal domains. Based on the self-attention, SAM can produce features by aggregating features across all positions of both the input itself and memory features with pair-wise similarity scores. Moreover, the additional memory is updated by a gating mechanism on aggregated features and an established highway with the memory of the previous time step. Therefore, through SAM, we can extract features with long-range spatiotemporal dependencies. Furthermore, we embed the SAM into a standard ConvLSTM to construct a self-attention ConvLSTM (SA-ConvLSTM) for the spatiotemporal prediction. In experiments, we apply the SA-ConvLSTM to perform frame prediction on the MovingMNIST and KTH datasets and traffic flow prediction on the TexiBJ dataset. Our SA-ConvLSTM achieves state-of-the-art results on both datasets with fewer parameters and higher time efficiency than previous state-of-the-art method.

scholarly journals Graph Convolutional Networks for Epigenetic State Prediction Using Both Sequence and 3D Genome Data

2019 ◽  
Author(s):  
Jack Lanchantin ◽  
Yanjun Qi
Keyword(s):  
Long Range ◽  
Dna Sequences ◽  
State Of The Art ◽  
Convolutional Network ◽  
3D Genome ◽  
Convolutional Networks ◽  
Genome Data ◽  
Epigenetic State ◽  
State Prediction ◽  
Local Sequence

AbstractPredictive models of DNA epigenetic state such as transcription factor binding are essential for understanding regulatory processes and developing gene therapies. It is known that the 3D genome, or spatial structure of DNA, is highly influential in the epigenetic state. Deep neural networks have achieved state of the art performance on epigenetic state prediction by using short windows of DNA sequences independently. These methods, however, ignore the long-range dependencies when predicting the epigenetic states because modeling the 3D genome is challenging. In this work, we introduce ChromeGCN, a graph convolutional network for epigenetic state prediction by fusing both local sequence and long-range 3D genome information. By incorporating the 3D genome, we relax the i.i.d. assumption of local windows for a better representation of DNA. ChromeGCN explicitly incorporates known long-range interactions into the modeling, allowing us to identify and interpret those important long-range dependencies in influencing epigenetic states. We show experimentally that by fusing sequential and 3D genome data using ChromeGCN, we get a significant improvement over the state-of-the-art deep learning methods as indicated by three metrics. Importantly, we show that ChromeGCN is particularly useful for identifying epigenetic effects in those DNA windows that have a high degree of interactions with other DNA windows.

scholarly journals Graph convolutional networks for epigenetic state prediction using both sequence and 3D genome data

2020 ◽  
Vol 36 (Supplement_2) ◽  
pp. i659-i667
Author(s):  
Jack Lanchantin ◽  
Yanjun Qi
Keyword(s):  
Long Range ◽  
Dna Sequences ◽  
State Of The Art ◽  
Supplementary Information ◽  
Convolutional Network ◽  
3D Genome ◽  
Convolutional Networks ◽  
Genome Data ◽  
Epigenetic State ◽  
Local Sequence

Abstract Motivation Predictive models of DNA chromatin profile (i.e. epigenetic state), such as transcription factor binding, are essential for understanding regulatory processes and developing gene therapies. It is known that the 3D genome, or spatial structure of DNA, is highly influential in the chromatin profile. Deep neural networks have achieved state of the art performance on chromatin profile prediction by using short windows of DNA sequences independently. These methods, however, ignore the long-range dependencies when predicting the chromatin profiles because modeling the 3D genome is challenging. Results In this work, we introduce ChromeGCN, a graph convolutional network for chromatin profile prediction by fusing both local sequence and long-range 3D genome information. By incorporating the 3D genome, we relax the independent and identically distributed assumption of local windows for a better representation of DNA. ChromeGCN explicitly incorporates known long-range interactions into the modeling, allowing us to identify and interpret those important long-range dependencies in influencing chromatin profiles. We show experimentally that by fusing sequential and 3D genome data using ChromeGCN, we get a significant improvement over the state-of-the-art deep learning methods as indicated by three metrics. Importantly, we show that ChromeGCN is particularly useful for identifying epigenetic effects in those DNA windows that have a high degree of interactions with other DNA windows. Availability and implementation https://github.com/QData/ChromeGCN. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

scholarly journals Bin2vec: learning representations of binary executable programs for security tasks

Cybersecurity ◽  
2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Shushan Arakelyan ◽  
Sima Arasteh ◽  
Christophe Hauser ◽  
Erik Kline ◽  
Aram Galstyan
Keyword(s):  
Program Analysis ◽  
State Of The Art ◽  
Classification Error ◽  
New Approach ◽  
Convolutional Networks ◽  
Computational Program ◽  
Functional Algorithm ◽  
Binary Program ◽  
Vulnerability Discovery ◽  
Executable Programs

AbstractTackling binary program analysis problems has traditionally implied manually defining rules and heuristics, a tedious and time consuming task for human analysts. In order to improve automation and scalability, we propose an alternative direction based on distributed representations of binary programs with applicability to a number of downstream tasks. We introduce Bin2vec, a new approach leveraging Graph Convolutional Networks (GCN) along with computational program graphs in order to learn a high dimensional representation of binary executable programs. We demonstrate the versatility of this approach by using our representations to solve two semantically different binary analysis tasks – functional algorithm classification and vulnerability discovery. We compare the proposed approach to our own strong baseline as well as published results, and demonstrate improvement over state-of-the-art methods for both tasks. We evaluated Bin2vec on 49191 binaries for the functional algorithm classification task, and on 30 different CWE-IDs including at least 100 CVE entries each for the vulnerability discovery task. We set a new state-of-the-art result by reducing the classification error by 40% compared to the source-code based inst2vec approach, while working on binary code. For almost every vulnerability class in our dataset, our prediction accuracy is over 80% (and over 90% in multiple classes).

scholarly journals MLatom 2: An Integrative Platform for Atomistic Machine Learning

2021 ◽  
Vol 379 (4) ◽  
Author(s):  
Pavlo O. Dral ◽  
Fuchun Ge ◽  
Bao-Xin Xue ◽  
Yi-Fan Hou ◽  
Max Pinheiro ◽  
...  
Keyword(s):  
Machine Learning ◽  
Software Package ◽  
State Of The Art ◽  
Kernel Method ◽  
Automatic Learning ◽  
Hyperparameter Optimization ◽  
Input And Output ◽  
Spectrum Simulation ◽  
Farthest Point ◽  
Theoretical Foundations

AbstractAtomistic machine learning (AML) simulations are used in chemistry at an ever-increasing pace. A large number of AML models has been developed, but their implementations are scattered among different packages, each with its own conventions for input and output. Thus, here we give an overview of our MLatom 2 software package, which provides an integrative platform for a wide variety of AML simulations by implementing from scratch and interfacing existing software for a range of state-of-the-art models. These include kernel method-based model types such as KREG (native implementation), sGDML, and GAP-SOAP as well as neural-network-based model types such as ANI, DeepPot-SE, and PhysNet. The theoretical foundations behind these methods are overviewed too. The modular structure of MLatom allows for easy extension to more AML model types. MLatom 2 also has many other capabilities useful for AML simulations, such as the support of custom descriptors, farthest-point and structure-based sampling, hyperparameter optimization, model evaluation, and automatic learning curve generation. It can also be used for such multi-step tasks as Δ-learning, self-correction approaches, and absorption spectrum simulation within the machine-learning nuclear-ensemble approach. Several of these MLatom 2 capabilities are showcased in application examples.

scholarly journals Effects of Admixtures on the Self Compacting Concrete State of the Art Report

2020 ◽  
Vol 1006 ◽  
pp. 012038
Author(s):  
S Christopher Gnanaraj ◽  
Ramesh Babu Chokkalingam ◽  
G LiziaThankam
Keyword(s):  
State Of The Art ◽  
The Self ◽  
Self Compacting Concrete

Design and development of an intelligent system based on the Internet of Things for the early detection of forest fires

2022 ◽  
Vol 12 (2) ◽  
pp. 0-0
Keyword(s):  
Neural Network ◽  
Early Detection ◽  
Forest Fires ◽  
Mobile Applications ◽  
Intelligent System ◽  
The Internet ◽  
Scientific Practices ◽  
Depth Analysis ◽  
Neural Network Algorithm ◽  
The Internet Of Things

Automatic environmental monitoring is a field that encompasses several scientific practices for the assessment of risks that may negatively impact a given environment, such as the forest. A forest is a natural environment that hosts various forms of plant and animal life, so preserving the forest is a top priority. To this end, the authors of this paper will focus on the development of an intelligent system for the early detection of forest fires, based on an IoT solution. This latter will thus facilitate the exploitation of the functionalities offered by the Cloud and mobile applications. Detecting and predicting forest fires with accuracy is a difficult task that requires machine learning and an in-depth analysis of environmental conditions. This leads the authors to adopt the forward neural network algorithm by highlighting its contribution through real experiments, performed on the prototype developed in this paper.

scholarly journals Colorado air quality impacted by long-range-transported aerosol: a set of case studies during the 2015 Pacific Northwest fires

2016 ◽  
Vol 16 (18) ◽  
pp. 12329-12345 ◽  
Author(s):  
Jessie M. Creamean ◽  
Paul J. Neiman ◽  
Timothy Coleman ◽  
Christoph J. Senff ◽  
Guillaume Kirgis ◽  
...  
Keyword(s):  
Air Quality ◽  
Case Studies ◽  
Pacific Northwest ◽  
Long Range ◽  
Biomass Burning ◽  
Forest Fires ◽  
Surface Radiation ◽  
Cloud Formation ◽  
Synoptic Scale ◽  
Transport Pathways

Abstract. Biomass burning plumes containing aerosols from forest fires can be transported long distances, which can ultimately impact climate and air quality in regions far from the source. Interestingly, these fires can inject aerosols other than smoke into the atmosphere, which very few studies have evidenced. Here, we demonstrate a set of case studies of long-range transport of mineral dust aerosols in addition to smoke from numerous fires (including predominantly forest fires and a few grass/shrub fires) in the Pacific Northwest to Colorado, US. These aerosols were detected in Boulder, Colorado, along the Front Range using beta-ray attenuation and energy-dispersive X-ray fluorescence spectroscopy, and corroborated with satellite-borne lidar observations of smoke and dust. Further, we examined the transport pathways of these aerosols using air mass trajectory analysis and regional- and synoptic-scale meteorological dynamics. Three separate events with poor air quality and increased mass concentrations of metals from biomass burning (S and K) and minerals (Al, Si, Ca, Fe, and Ti) occurred due to the introduction of smoke and dust from regional- and synoptic-scale winds. Cleaner time periods with good air quality and lesser concentrations of biomass burning and mineral metals between the haze events were due to the advection of smoke and dust away from the region. Dust and smoke present in biomass burning haze can have diverse impacts on visibility, health, cloud formation, and surface radiation. Thus, it is important to understand how aerosol populations can be influenced by long-range-transported aerosols, particularly those emitted from large source contributors such as wildfires.

Optimal Number and Location of Watchtowers for Immediate Detection of Forest Fires in a Small Island

2017 ◽  
Vol 8 (4) ◽  
pp. 1-19 ◽  
Author(s):  
Stavros Sakellariou ◽  
Fani Samara ◽  
Stergios Tampekis ◽  
Olga Christopoulou ◽  
Athanassios Sfougaris
Keyword(s):  
Early Detection ◽  
Spatial Structure ◽  
Forest Fires ◽  
Critical Time ◽  
Spatial Optimization ◽  
Optimal Number ◽  
Small Island ◽  
Environmental Consequences ◽  
Fire Ignitions ◽  
Visible Area

A crucial factor for prevention and immediate confrontation of destructive fires and their socioeconomic and environmental consequences constitutes the early detection and spatial localization of fire ignitions, so that the firefighting forces to be activated and act within the critical time of response. Thus, principal objective of the paper constitutes the spatial optimization of the most effective locations of watchtowers developing a constructive network for the immediate and early detection of forest fires. This optimization involves the exploration of the fewest locations for watchtowers with the maximum visible area and reduced degree of overlapping. The results highlighted 4 groups of watchtowers (20 observers in total) determining the optimum locations. The total visibility amounted to 70% of the island, while the visibility percentages per land cover are variable, since they are depended on the spatial structure of them. Definitely, the final selection of the final number and the spatial structure of the watchtowers purely constitute decisions of political nature and will.

Sign in / Sign up

Export Citation Format

Share Document