From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling

AbstractThe behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation.

Download Full-text

Detection of Target Persons Using Deep Learning and Training Data Generation for Tsukuba Challenge

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2018.p0513 ◽

2018 ◽

Vol 30 (4) ◽

pp. 513-522 ◽

Cited By ~ 3

Author(s):

Yuichi Konishi ◽

◽

Kosuke Shigematsu ◽

Takashi Tsubouchi ◽

Akihisa Ohya

Keyword(s):

Deep Learning ◽

Autonomous Navigation ◽

Detection System ◽

Computational Cost ◽

Weather Conditions ◽

Recognition System ◽

Training Data ◽

Urban Setting ◽

Data Generation ◽

And Training

The Tsukuba Challenge is an open experiment competition held annually since 2007, and wherein the autonomous navigation robots developed by the participants must navigate through an urban setting in which pedestrians and cyclists are present. One of the required tasks in the Tsukuba Challenge from 2013 to 2017 was to search for persons wearing designated clothes within the search area. This is a very difficult task since it is necessary to seek out these persons in an environment that includes regular pedestrians, and wherein the lighting changes easily because of weather conditions. Moreover, the recognition system must have a light computational cost because of the limited performance of the computer that is mounted onto the robot. In this study, we focused on a deep learning method of detecting the target persons in captured images. The developed detection system was expected to achieve high detection performance, even when small-sized input images were used for deep learning. Experiments demonstrated that the proposed system achieved better performance than an existing object detection network. However, because a vast amount of training data is necessary for deep learning, a method of generating training data to be used in the detection of target persons is also discussed in this paper.

Download Full-text

Design of sparse arrays via deep learning for enhanced DOA estimation

EURASIP Journal on Advances in Signal Processing ◽

10.1186/s13634-021-00727-5 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Steven Wandale ◽

Koichi Ichige

Keyword(s):

Deep Learning ◽

Linear Array ◽

Antenna Selection ◽

Computational Cost ◽

Doa Estimation ◽

Classification Problem ◽

Training Data ◽

Sparse Linear Array ◽

Selection Approach ◽

Selection For

AbstractThis paper introduces an enhanced deep learning-based (DL) antenna selection approach for optimum sparse linear array selection for direction-of-arrival (DOA) estimation applications. Generally, the antenna selection problem yields a combination of subarrays as a solution. Previous DL-based methods designated these subarrays as classes to fit the problem into a classification problem to which a convolutional neural network (CNN) is employed to solve it. However, these methods sample the combination set randomly to reduce computational cost related to the generation of training data, and it often leads to sub-optimal solutions due to ill-sampling issues. Hence, in this paper, we propose an improved DL-based method by constraining the combination set to retain the hole-free subarrays to enhance the method’s performance and sparse subarrays rendered. Numerical examples show that the proposed method yields sparser subarrays with better beampattern properties and improved DOA estimation performance than conventional DL techniques.

Download Full-text

An Advanced SAR Image Despeckling Method by Bernoulli-Sampling-Based Self-Supervised Deep Learning

Remote Sensing ◽

10.3390/rs13183636 ◽

2021 ◽

Vol 13 (18) ◽

pp. 3636

Author(s):

Ye Yuan ◽

Yanxia Wu ◽

Yan Fu ◽

Yulei Wu ◽

Lidan Zhang ◽

...

Keyword(s):

Big Data ◽

Deep Learning ◽

Noise Suppression ◽

Speckle Noise ◽

Training Data ◽

Superior Performance ◽

Sar Image ◽

Sar Images ◽

Image Despeckling ◽

Image Pairs

As one of the main sources of remote sensing big data, synthetic aperture radar (SAR) can provide all-day and all-weather Earth image acquisition. However, speckle noise in SAR images brings a notable limitation for its big data applications, including image analysis and interpretation. Deep learning has been demonstrated as an advanced method and technology for SAR image despeckling. Most existing deep-learning-based methods adopt supervised learning and use synthetic speckled images to train the despeckling networks. This is because they need clean images as the references, and it is hard to obtain purely clean SAR images in real-world conditions. However, significant differences between synthetic speckled and real SAR images cause the domain gap problem. In other words, they cannot show superior performance for despeckling real SAR images as they do for synthetic speckled images. Inspired by recent studies on self-supervised denoising, we propose an advanced SAR image despeckling method by virtue of Bernoulli-sampling-based self-supervised deep learning, called SSD-SAR-BS. By only using real speckled SAR images, Bernoulli-sampled speckled image pairs (input–target) were obtained as the training data. Then, a multiscale despeckling network was trained on these image pairs. In addition, a dropout-based ensemble was introduced to boost the network performance. Extensive experimental results demonstrated that our proposed method outperforms the state-of-the-art for speckle noise suppression on both synthetic speckled and real SAR datasets (i.e., Sentinel-1 and TerraSAR-X).

Download Full-text

Deep Learning Techniques to Address Issues in Data Quality and Data Variety

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.d9018.118419 ◽

2019 ◽

Vol 8 (4) ◽

pp. 5950-5956

Keyword(s):

Decision Making ◽

Big Data ◽

Deep Learning ◽

Data Quality ◽

Data Analytics ◽

Medical Information ◽

Big Data Analytics ◽

Training Data ◽

Huge Amount ◽

Learning Techniques

Deep Learning and Big Data Analytics are key focus in current rapidly growing environment. The use of large data has become crucial to different organizations as they collecting huge amount of domain-specific data, which contains critical information about cyber security, theft detection, national resources, business economics, marketing, and medical information. The assessment of this huge amount of data needs advanced and improved analytical techniques for surveying and guessing future courses of action by making advanced decision-making strategies. Deep learning algorithms utilize the collected training data, to create a representation model. This model uses the computer for predictions or decision making about new data without needing to train the machine explicitly to perform user task. These techniques and algorithms infer greater level complicated abstractions as data are represented through tree like structure. A major use of Deep Learning is processing, learning and training from the huge amounts of unsupervised data, analyze patterns from the data and can be used for large Datasets in which the raw data is largely unlabeled and not classified. In this paper, Deep Learning techniques for addressing Data of different variety/formats is analyzed, enabling fast and full processing and integration of large amounts of different variety of information i.e. Data transformation is also addressed. It also addresses the quality of data as the performances of a machine improve depending on the data quality. Further exploration on the deep learning techniques to assist Big Data by focusing on two key topics: (1) is it possible for Deep Learning to assist some of the specific problems like Data Variety and Data Quality in Big Data Analytics, and (2) Whether these techniques can aid in processing the Big Data

Download Full-text

Intelligence artificielle : le futur de l’Orthodontie ?

Revue d Orthopédie Dento-Faciale ◽

10.1051/odf/2019026 ◽

2019 ◽

Vol 53 (3) ◽

pp. 281-294

Author(s):

Jean-Michel Foucart ◽

Augustin Chavanne ◽

Jérôme Bourriau

Keyword(s):

Big Data ◽

Deep Learning ◽

Intelligence Artificielle ◽

Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Download Full-text

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

10.26434/chemrxiv.7151435.v2 ◽

2018 ◽

Author(s):

Roman Zubatyuk ◽

Justin S. Smith ◽

Jerzy Leszczynski ◽

Olexandr Isayev

Keyword(s):

Neural Network ◽

Molecular System ◽

Computational Cost ◽

Chemical Properties ◽

The State ◽

Molecular Properties ◽

Training Data ◽

Dft Methods ◽

Benchmark Datasets ◽

Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Download Full-text

Improving Sentiment Analysis using Hybrid Deep Learning Model

Recent Advances in Computer Science and Communications ◽

10.2174/2213275912666190328200012 ◽

2020 ◽

Vol 13 (4) ◽

pp. 627-640 ◽

Cited By ~ 1

Author(s):

Avinash Chandra Pandey ◽

Dharmveer Singh Rajpoot

Keyword(s):

Neural Network ◽

Deep Learning ◽

Sentiment Analysis ◽

Classification Accuracy ◽

Short Term Memory ◽

Computational Cost ◽

Extraction Process ◽

Learning Model ◽

Sentiment Classification ◽

Deep Learning Model

Background: Sentiment analysis is a contextual mining of text which determines viewpoint of users with respect to some sentimental topics commonly present at social networking websites. Twitter is one of the social sites where people express their opinion about any topic in the form of tweets. These tweets can be examined using various sentiment classification methods to find the opinion of users. Traditional sentiment analysis methods use manually extracted features for opinion classification. The manual feature extraction process is a complicated task since it requires predefined sentiment lexicons. On the other hand, deep learning methods automatically extract relevant features from data hence; they provide better performance and richer representation competency than the traditional methods. Objective: The main aim of this paper is to enhance the sentiment classification accuracy and to reduce the computational cost. Method: To achieve the objective, a hybrid deep learning model, based on convolution neural network and bi-directional long-short term memory neural network has been introduced. Results: The proposed sentiment classification method achieves the highest accuracy for the most of the datasets. Further, from the statistical analysis efficacy of the proposed method has been validated. Conclusion: Sentiment classification accuracy can be improved by creating veracious hybrid models. Moreover, performance can also be enhanced by tuning the hyper parameters of deep leaning models.

Download Full-text

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

10.2196/preprints.22865 ◽

2020 ◽

Author(s):

Anusha Ampavathi ◽

Vijaya Saradhi T

Keyword(s):

Feature Extraction ◽

Big Data ◽

Deep Learning ◽

Weight Function ◽

Optimization Algorithm ◽

Large Scale ◽

Heuristic Algorithms ◽

Disease Prediction ◽

Health Care Decisions ◽

Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

Download Full-text