Large-scale real-world radio signal recognition with deep learning

With the popularity of smartphones and the development of hardware, mobile devices are widely used by people. To ensure availability and security, how to protect private data in mobile devices without disturbing users has become a key issue. Mobile user authentication methods based on motion sensors have been proposed by many works, but the existing methods have a series of problems such as poor de-noising ability, insufficient availability, and low coverage of feature extraction. Based on the shortcomings of existing methods, this paper proposes a hybrid deep learning system for complex real-world mobile authentication. The system includes: (1) a variational mode decomposition (VMD) based de-noising method to enhance the singular value of sensors, such as discontinuities and mutations, and increase the extraction range of the feature; (2) semi-supervised collaborative training (Tri-Training) methods to effectively deal with mislabeling problems in complex real-world situations; and (3) a combined convolutional neural network (CNN) and support vector machine (SVM) model for effective hybrid feature extraction and training. The training results under large-scale, real-world data show that the proposed system can achieve 95.01% authentication accuracy, and the effect is better than the existing frontier methods.

Download Full-text

Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures

Entropy ◽

10.3390/e23121608 ◽

2021 ◽

Vol 23 (12) ◽

pp. 1608

Author(s):

Benjamin Kompa ◽

Jasper Snoek ◽

Andrew L. Beam

Keyword(s):

Deep Learning ◽

Uncertainty Quantification ◽

Real World ◽

Large Scale ◽

Prediction Interval ◽

Brier Score ◽

Distribution Data ◽

Calibration Error ◽

Learning Models ◽

Frequentist Coverage

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model’s uncertainty is evaluated using point-prediction metrics, such as the negative log-likelihood (NLL), expected calibration error (ECE) or the Brier score on held-out data. Marginal coverage of prediction intervals or sets, a well-known concept in the statistical literature, is an intuitive alternative to these metrics but has yet to be systematically studied for many popular uncertainty quantification techniques for deep learning models. With marginal coverage and the complementary notion of the width of a prediction interval, downstream users of deployed machine learning models can better understand uncertainty quantification both on a global dataset level and on a per-sample basis. In this study, we provide the first large-scale evaluation of the empirical frequentist coverage properties of well-known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and reinforce coverage as an important metric in developing models for real-world applications.

Download Full-text

Physics-Based Graphics Models in 3D Synthetic Environments as Autonomous Vision-Based Inspection Testbeds

Sensors ◽

10.3390/s22020532 ◽

2022 ◽

Vol 22 (2) ◽

pp. 532

Author(s):

Vedhus Hoskere ◽

Yasutaka Narazaki ◽

Billie F. Spencer

Keyword(s):

Deep Learning ◽

Data Acquisition ◽

Real World ◽

Large Scale ◽

Visual Inspection ◽

Civil Infrastructure ◽

Damage State ◽

End To End ◽

Real World Datasets ◽

Autonomous Inspection

Manual visual inspection of civil infrastructure is high-risk, subjective, and time-consuming. The success of deep learning and the proliferation of low-cost consumer robots has spurred rapid growth in research and application of autonomous inspections. The major components of autonomous inspection include data acquisition, data processing, and decision making, which are usually studied independently. However, for robust real-world applicability, these three aspects of the overall process need to be addressed concurrently with end-to-end testing, incorporating scenarios such as variations in structure type, color, damage level, camera distance, view angle, lighting, etc. Developing real-world datasets that span all these scenarios is nearly impossible. In this paper, we propose a framework to create a virtual visual inspection testbed using 3D synthetic environments that can enable end-to-end testing of autonomous inspection strategies. To populate the 3D synthetic environment with virtual damaged buildings, we propose the use of a non-linear finite element model to inform the realistic and automated visual rendering of different damage types, the damage state, and the material textures of what are termed herein physics-based graphics models (PBGMs). To demonstrate the benefits of the autonomous inspection testbed, three experiments are conducted with models of earthquake damaged reinforced concrete buildings. First, we implement the proposed framework to generate a new large-scale annotated benchmark dataset for post-earthquake inspections of buildings termed QuakeCity. Second, we demonstrate the improved performance of deep learning models trained using the QuakeCity dataset for inference on real data. Finally, a comparison of deep learning-based damage state estimation for different data acquisition strategies is carried out. The results demonstrate the use of PBGMs as an effective testbed for the development and validation of strategies for autonomous vision-based inspections of civil infrastructure.

Download Full-text

Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

ACM Transactions on Intelligent Systems and Technology ◽

10.1145/3480970 ◽

2022 ◽

Vol 13 (2) ◽

pp. 1-20

Author(s):

Zhe Jiang ◽

Wenchong He ◽

Marcus Stephen Kirby ◽

Arpan Man Sainju ◽

Shaowen Wang ◽

...

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Real World ◽

Large Scale ◽

Model Parameters ◽

Vector Representation ◽

High Quality ◽

Geometric Properties ◽

Location Errors ◽

Weakly Supervised

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy.

Download Full-text

Deep learning based network similarity for model selection

Data Science ◽

10.3233/ds-210033 ◽

2021 ◽

pp. 1-21

Author(s):

Kushal Veer Singh ◽

Ajay Kumar Verma ◽

Lovekesh Vig

Keyword(s):

Deep Learning ◽

Model Selection ◽

Complex Networks ◽

Real World ◽

Network Architecture ◽

Large Scale ◽

Generative Models ◽

Generative Model ◽

Data Set ◽

Feed Forward Network

Capturing data in the form of networks is becoming an increasingly popular approach for modeling, analyzing and visualising complex phenomena, to understand the important properties of the underlying complex processes. Access to many large-scale network datasets is restricted due to the privacy and security concerns. Also for several applications (such as functional connectivity networks), generating large scale real data is expensive. For these reasons, there is a growing need for advanced mathematical and statistical models (also called generative models) that can account for the structure of these large-scale networks, without having to materialize them in the real world. The objective is to provide a comprehensible description of the network properties and to be able to infer previously unobserved properties. Various models have been developed by researchers, which generate synthetic networks that adhere to the structural properties of real networks. However, the selection of the appropriate generative model for a given real-world network remains an important challenge. In this paper, we investigate this problem and provide a novel technique (named as TripletFit) for model selection (or network classification) and estimation of structural similarities of the complex networks. The goal of network model selection is to select a generative model that is able to generate a structurally similar synthetic network for a given real-world (target) network. We consider six outstanding generative models as the candidate models. The existing model selection methods mostly suffer from sensitivity to network perturbations, dependency on the size of the networks, and low accuracy. To overcome these limitations, we considered a broad array of network features, with the aim of representing different structural aspects of the network and employed deep learning techniques such as deep triplet network architecture and simple feed-forward network for model selection and estimation of structural similarities of the complex networks. Our proposed method, outperforms existing methods with respect to accuracy, noise-tolerance, and size independence on a number of gold standard data set used in previous studies.

Download Full-text

AI-Powered Oracle Bone Inscriptions Recognition and Fragments Rejoining

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/779 ◽

2020 ◽

Author(s):

Chongsheng Zhang ◽

Ruixing Zong ◽

Shuang Cao ◽

Yi Men ◽

Bofeng Mo

Keyword(s):

Deep Learning ◽

Real World ◽

Template Matching ◽

Large Scale ◽

Matching Algorithm ◽

Domain Experts ◽

Detection Algorithms ◽

Scene Text Detection ◽

Large Scale Dataset ◽

Scene Text

Oracle Bone Inscriptions (OBI) research is very meaningful for both history and literature. In this paper, we introduce our contributions in AI-Powered Oracle Bone (OB) fragments rejoining and OBI recognition. (1) We build a real-world dataset OB-Rejoin, and propose an effective OB rejoining algorithm which yields a top-10 accuracy of 98.39%. (2) We design a practical annotation software to facilitate OBI annotation, and build OracleBone-8000, a large-scale dataset with character-level annotations. We adopt deep learning based scene text detection algorithms for OBI localization, which yield an F-score of 89.7%. We propose a novel deep template matching algorithm for OBI recognition which achieves an overall accuracy of 80.9%. Since we have been cooperating closely with OBI domain experts, our effort above helps advance their research. The resources of this work are available at https://github.com/chongshengzhang/OracleBone.

Download Full-text

1588-P: Therapy Trends in Initial 6 Months of the First Large-Scale Longitudinal Nationwide Study on Management and Real-World Outcomes of Diabetes in India (LANDMARC)

Diabetes ◽

10.2337/db20-1588-p ◽

2020 ◽

Vol 69 (Supplement 1) ◽

pp. 1588-P ◽

Cited By ~ 1

Author(s):

ROMIK GHOSH ◽

ASHOK K. DAS ◽

AMBRISH MITHAL ◽

SHASHANK JOSHI ◽

K.M. PRASANNA KUMAR ◽

...

Keyword(s):

Real World ◽

Large Scale ◽

Nationwide Study

Download Full-text

2258-PUB: Impact of Cardiovascular (CV) Risk Factors during the Initial 6 Months of the First Large-Scale Longitudinal Nationwide Study on Management and Real-World Outcomes of Diabetes in India (LANDMARC)

Diabetes ◽

10.2337/db20-2258-pub ◽

2020 ◽

Vol 69 (Supplement 1) ◽

pp. 2258-PUB

Author(s):

ROMIK GHOSH ◽

ASHOK K. DAS ◽

SHASHANK JOSHI ◽

AMBRISH MITHAL ◽

K.M. PRASANNA KUMAR ◽

...

Keyword(s):

Risk Factors ◽

Real World ◽

Large Scale ◽

Nationwide Study

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