Paper Group ANR 291
Detection of Obstructive Sleep Apnoea Using Features Extracted from Segmented Time-Series ECG Signals Using a One Dimensional Convolutional Neural Network. ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. Plant Disease Detection from Images. NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing. M …
Detection of Obstructive Sleep Apnoea Using Features Extracted from Segmented Time-Series ECG Signals Using a One Dimensional Convolutional Neural Network
| Title | Detection of Obstructive Sleep Apnoea Using Features Extracted from Segmented Time-Series ECG Signals Using a One Dimensional Convolutional Neural Network |
| Authors | Steven Thompson, Paul Fergus, Carl Chalmers, Denis Reilly |
| Abstract | The study in this paper presents a one-dimensional convolutional neural network (1DCNN) model, designed for the automated detection of obstructive Sleep Apnoea (OSA) captured from single-channel electrocardiogram (ECG) signals. The system provides mechanisms in clinical practice that help diagnose patients suffering with OSA. Using the state-of-the-art in 1DCNNs, a model is constructed using convolutional, max pooling layers and a fully connected Multilayer Perceptron (MLP) consisting of a hidden layer and SoftMax output for classification. The 1DCNN extracts prominent features, which are used to train an MLP. The model is trained using segmented ECG signals grouped into 5 unique datasets of set window sizes. 35 ECG signal recordings were selected from an annotated database containing 70 night-time ECG recordings. (Group A = a01 to a20 (Apnoea breathing), Group B = b01 to b05 (moderate), and Group C = c01 to c10 (normal). A total of 6514 minutes of Apnoea was recorded. Evaluation of the model is performed using a set of standard metrics which show the proposed model achieves high classification results in both training and validation using our windowing strategy, particularly W=500 (Sensitivity 0.9705, Specificity 0.9725, F1 Score 0.9717, Kappa Score 0.9430, Log Loss 0.0836, ROCAUC 0.9945). This demonstrates the model can identify the presence of Apnoea with a high degree of accuracy. |
| Tasks | Time Series |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00833v1 |
| https://arxiv.org/pdf/2002.00833v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-obstructive-sleep-apnoea-using |
| Repo | |
| Framework | |
ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds
| Title | ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds |
| Authors | Gopal Sharma, Difan Liu, Evangelos Kalogerakis, Subhransu Maji, Siddhartha Chaudhuri, Radomír Měch |
| Abstract | We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale dataset of man-made 3D shapes and captures high-level semantic priors for shape decomposition. It handles a much richer class of primitives than prior work, and allows us to represent surfaces with higher fidelity. It also produces repeatable and robust parametrizations of a surface compared to purely geometric approaches. We present extensive experiments to validate our approach against analytical and learning-based alternatives. |
| Tasks | |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.12181v2 |
| https://arxiv.org/pdf/2003.12181v2.pdf | |
| PWC | https://paperswithcode.com/paper/parsenet-a-parametric-surface-fitting-network |
| Repo | |
| Framework | |
Plant Disease Detection from Images
| Title | Plant Disease Detection from Images |
| Authors | Anjaneya Teja Sarma Kalvakolanu |
| Abstract | Plant disease detection is a huge problem and often require professional help to detect the disease. This research focuses on creating a deep learning model that detects the type of disease that affected the plant from the images of the leaves of the plants. The deep learning is done with the help of Convolutional Neural Network by performing transfer learning. The model is created using transfer learning and is experimented with both resnet 34 and resnet 50 to demonstrate that discriminative learning gives better results. This method achieved state of art results for the dataset used. The main goal is to lower the professional help to detect the plant diseases and make this model accessible to as many people as possible. |
| Tasks | Transfer Learning |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.05379v1 |
| https://arxiv.org/pdf/2003.05379v1.pdf | |
| PWC | https://paperswithcode.com/paper/plant-disease-detection-from-images |
| Repo | |
| Framework | |
NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing
| Title | NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing |
| Authors | Xin Huang, Zheng Ge, Zequn Jie, Osamu Yoshie |
| Abstract | Although significant progress has been made in pedestrian detection recently, pedestrian detection in crowded scenes is still challenging. The heavy occlusion between pedestrians imposes great challenges to the standard Non-Maximum Suppression (NMS). A relative low threshold of intersection over union (IoU) leads to missing highly overlapped pedestrians, while a higher one brings in plenty of false positives. To avoid such a dilemma, this paper proposes a novel Representative Region NMS approach leveraging the less occluded visible parts, effectively removing the redundant boxes without bringing in many false positives. To acquire the visible parts, a novel Paired-Box Model (PBM) is proposed to simultaneously predict the full and visible boxes of a pedestrian. The full and visible boxes constitute a pair serving as the sample unit of the model, thus guaranteeing a strong correspondence between the two boxes throughout the detection pipeline. Moreover, convenient feature integration of the two boxes is allowed for the better performance on both full and visible pedestrian detection tasks. Experiments on the challenging CrowdHuman and CityPersons benchmarks sufficiently validate the effectiveness of the proposed approach on pedestrian detection in the crowded situation. |
| Tasks | Pedestrian Detection |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12729v1 |
| https://arxiv.org/pdf/2003.12729v1.pdf | |
| PWC | https://paperswithcode.com/paper/nms-by-representative-region-towards-crowded |
| Repo | |
| Framework | |
Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
| Title | Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront |
| Authors | Peng Sun, Rui Hou, Jerome Lynch |
| Abstract | Physical activities and social interactions are essential activities that ensure a healthy lifestyle. Public open spaces (POS), such as parks, plazas and greenways, are key environments that encourage those activities. To evaluate a POS, there is a need to study how humans use the facilities within it. However, traditional approaches to studying use of POS are manual and therefore time and labor intensive. They also may only provide qualitative insights. It is appealing to make use of surveillance cameras and to extract user-related information through computer vision. This paper proposes a proof-of-concept deep learning computer vision framework for measuring human activities quantitatively in POS and demonstrates a case study of the proposed framework using the Detroit Riverfront Conservancy (DRFC) surveillance camera network. A custom image dataset is presented to train the framework; the dataset includes 7826 fully annotated images collected from 18 cameras across the DRFC park space under various illumination conditions. Dataset analysis is also provided as well as a baseline model for one-step user localization and activity recognition. The mAP results are 77.5% for {\it pedestrian} detection and 81.6% for {\it cyclist} detection. Behavioral maps are autonomously generated by the framework to locate different POS users and the average error for behavioral localization is within 10 cm. |
| Tasks | Activity Recognition, Pedestrian Detection |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01461v1 |
| https://arxiv.org/pdf/2002.01461v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-the-utilization-of-public-open |
| Repo | |
| Framework | |
Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution
| Title | Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution |
| Authors | Qi Wang, Qiang Li, Xuelong Li |
| Abstract | Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently. However, most existing models can not effectively explore spatial information and spectral information between bands simultaneously, obtaining relatively low performance. To address this issue, in this paper, we propose a novel spectral-spatial residual network for hyperspectral image super-resolution (SSRNet). Our method can effectively explore spatial-spectral information by using 3D convolution instead of 2D convolution, which enables the network to better extract potential information. Furthermore, we design a spectral-spatial residual module (SSRM) to adaptively learn more effective features from all the hierarchical features in units through local feature fusion, significantly improving the performance of the algorithm. In each unit, we employ spatial and temporal separable 3D convolution to extract spatial and spectral information, which not only reduces unaffordable memory usage and high computational cost, but also makes the network easier to train. Extensive evaluations and comparisons on three benchmark datasets demonstrate that the proposed approach achieves superior performance in comparison to existing state-of-the-art methods. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04609v1 |
| https://arxiv.org/pdf/2001.04609v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-spectral-residual-network-for |
| Repo | |
| Framework | |
Learned Multi-View Texture Super-Resolution
| Title | Learned Multi-View Texture Super-Resolution |
| Authors | Audrey Richard, Ian Cherabier, Martin R. Oswald, Vagia Tsiminaki, Marc Pollefeys, Konrad Schindler |
| Abstract | We present a super-resolution method capable of creating a high-resolution texture map for a virtual 3D object from a set of lower-resolution images of that object. Our architecture unifies the concepts of (i) multi-view super-resolution based on the redundancy of overlapping views and (ii) single-view super-resolution based on a learned prior of high-resolution (HR) image structure. The principle of multi-view super-resolution is to invert the image formation process and recover the latent HR texture from multiple lower-resolution projections. We map that inverse problem into a block of suitably designed neural network layers, and combine it with a standard encoder-decoder network for learned single-image super-resolution. Wiring the image formation model into the network avoids having to learn perspective mapping from textures to images, and elegantly handles a varying number of input views. Experiments demonstrate that the combination of multi-view observations and learned prior yields improved texture maps. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04775v1 |
| https://arxiv.org/pdf/2001.04775v1.pdf | |
| PWC | https://paperswithcode.com/paper/learned-multi-view-texture-super-resolution |
| Repo | |
| Framework | |
Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization
| Title | Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization |
| Authors | Wei He, Yong Chen, Naoto Yokoya, Chao Li, Qibin Zhao |
| Abstract | Hyperspectral super-resolution (HSR) fuses a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) to obtain a high-resolution HSI (HR-HSI). In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR. The proposed CTRF approach simultaneously learns high spectral resolution core tensor from the HSI and high spatial resolution core tensors from the MSI, and reconstructs the HR-HSI via tensor ring (TR) representation (Figure~\ref{fig:framework}). The CTRF model can separately exploit the low-rank property of each class (Section \ref{sec:analysis}), which has been never explored in the previous coupled tensor model. Meanwhile, it inherits the simple representation of coupled matrix/CP factorization and flexible low-rank exploration of coupled Tucker factorization. Guided by Theorem~\ref{th:1}, we further propose a spectral nuclear norm regularization to explore the global spectral low-rank property. The experiments have demonstrated the advantage of the proposed nuclear norm regularized CTRF (NCTRF) as compared to previous matrix/tensor and deep learning methods. |
| Tasks | Super-Resolution |
| Published | 2020-01-06 |
| URL | https://arxiv.org/abs/2001.01547v1 |
| https://arxiv.org/pdf/2001.01547v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-super-resolution-via-coupled |
| Repo | |
| Framework | |
Transmission and navigation on disordered lattice networks, directed spanning forests and scaling limits
| Title | Transmission and navigation on disordered lattice networks, directed spanning forests and scaling limits |
| Authors | Subhroshekhar Ghosh, Kumarjit Saha |
| Abstract | Stochastic networks based on random point sets as nodes have attracted considerable interest in many applications, particularly in communication networks, including wireless sensor networks, peer-to-peer networks and so on. The study of such networks generally requires the nodes to be independently and uniformly distributed as a Poisson point process. In this work, we venture beyond this standard paradigm and investigate the stochastic geometry of networks obtained from \textit{directed spanning forests} (DSF) based on randomly perturbed lattices, which have desirable statistical properties as a models of spatially dependent point fields. In the regime of low disorder, we show in 2D and 3D that the DSF almost surely consists of a single tree. In 2D, we further establish that the DSF, as a collection of paths, converges under diffusive scaling to the Brownian web. |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06898v1 |
| https://arxiv.org/pdf/2002.06898v1.pdf | |
| PWC | https://paperswithcode.com/paper/transmission-and-navigation-on-disordered |
| Repo | |
| Framework | |
Sharp Concentration Results for Heavy-Tailed Distributions
| Title | Sharp Concentration Results for Heavy-Tailed Distributions |
| Authors | Milad Bakhshizadeh, Arian Maleki, Victor H. de la Pena |
| Abstract | We obtain concentration and large deviation for the sums of independent and identically distributed random variables with heavy-tailed distributions. Our concentration results are concerned with random variables whose distributions satisfy $P(X>t) \leq {\rm e}^{- I(t)}$, where $I: \mathbb{R} \rightarrow \mathbb{R}$ is an increasing function and $I(t)/t \rightarrow \alpha \in [0, \infty)$ as $t \rightarrow \infty$. Our main theorem can not only recover some of the existing results, such as the concentration of the sum of subWeibull random variables, but it can also produce new results for the sum of random variables with heavier tails. We show that the concentration inequalities we obtain are sharp enough to offer large deviation results for the sums of independent random variables as well. Our analyses which are based on standard truncation arguments simplify, unify and generalize the existing results on the concentration and large deviation of heavy-tailed random variables. |
| Tasks | |
| Published | 2020-03-30 |
| URL | https://arxiv.org/abs/2003.13819v1 |
| https://arxiv.org/pdf/2003.13819v1.pdf | |
| PWC | https://paperswithcode.com/paper/sharp-concentration-results-for-heavy-tailed |
| Repo | |
| Framework | |
Trees and Forests in Nuclear Physics
| Title | Trees and Forests in Nuclear Physics |
| Authors | Marco Carnini, Alessandro Pastore |
| Abstract | We present a detailed introduction to the decision tree algorithm using some simple examples taken from the domain of nuclear physics. We show how to improve the accuracy of the classical liquid drop nuclear mass model by performing Feature Engineering while using a decision tree. Finally, we apply the method to the Duflo-Zucker mass model showing that, despite their simplicity, decision trees are capable of obtaining a level of accuracy comparable to more complex neural networks, but using way less adjustable parameters and obtaining easier to explain models. |
| Tasks | Feature Engineering |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10290v1 |
| https://arxiv.org/pdf/2002.10290v1.pdf | |
| PWC | https://paperswithcode.com/paper/trees-and-forests-in-nuclear-physics |
| Repo | |
| Framework | |
Comparative Analysis of Single and Hybrid Neuro-Fuzzy-Based Models for an Industrial Heating Ventilation and Air Conditioning Control System
| Title | Comparative Analysis of Single and Hybrid Neuro-Fuzzy-Based Models for an Industrial Heating Ventilation and Air Conditioning Control System |
| Authors | Sina Ardabili, Bertalan Beszedes, Laszlo Nadai, Karoly Szell, Amir Mosavi, Felde Imre |
| Abstract | Hybridization of machine learning methods with soft computing techniques is an essential approach to improve the performance of the prediction models. Hybrid machine learning models, particularly, have gained popularity in the advancement of the high-performance control systems. Higher accuracy and better performance for prediction models of exergy destruction and energy consumption used in the control circuit of heating, ventilation, and air conditioning (HVAC) systems can be highly economical in the industrial scale to save energy. This research proposes two hybrid models of adaptive neuro-fuzzy inference system-particle swarm optimization (ANFIS-PSO), and adaptive neuro-fuzzy inference system-genetic algorithm (ANFIS-GA) for HVAC. The results are further compared with the single ANFIS model. The ANFIS-PSO model with the RMSE of 0.0065, MAE of 0.0028, and R2 equal to 0.9999, with a minimum deviation of 0.0691 (KJ/s), outperforms the ANFIS-GA and single ANFIS models. |
| Tasks | |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.11042v1 |
| https://arxiv.org/pdf/2002.11042v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-analysis-of-single-and-hybrid |
| Repo | |
| Framework | |
Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets
| Title | Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets |
| Authors | Thu Dinh, Bao Wang, Andrea L. Bertozzi, Stanley J. Osher |
| Abstract | Deep neural nets (DNNs) compression is crucial for adaptation to mobile devices. Though many successful algorithms exist to compress naturally trained DNNs, developing efficient and stable compression algorithms for robustly trained DNNs remains widely open. In this paper, we focus on a co-design of efficient DNN compression algorithms and sparse neural architectures for robust and accurate deep learning. Such a co-design enables us to advance the goal of accommodating both sparsity and robustness. With this objective in mind, we leverage the relaxed augmented Lagrangian based algorithms to prune the weights of adversarially trained DNNs, at both structured and unstructured levels. Using a Feynman-Kac formalism principled robust and sparse DNNs, we can at least double the channel sparsity of the adversarially trained ResNet20 for CIFAR10 classification, meanwhile, improve the natural accuracy by $8.69$% and the robust accuracy under the benchmark $20$ iterations of IFGSM attack by $5.42$%. The code is available at \url{https://github.com/BaoWangMath/rvsm-rgsm-admm}. |
| Tasks | |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.00631v1 |
| https://arxiv.org/pdf/2003.00631v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparsity-meets-robustness-channel-pruning-for-1 |
| Repo | |
| Framework | |
365 Dots in 2019: Quantifying Attention of News Sources
| Title | 365 Dots in 2019: Quantifying Attention of News Sources |
| Authors | Alexander C. Nwala, Michele C. Weigle, Michael L. Nelson |
| Abstract | We investigate the overlap of topics of online news articles from a variety of sources. To do this, we provide a platform for studying the news by measuring this overlap and scoring news stories according to the degree of attention in near-real time. This can enable multiple studies, including identifying topics that receive the most attention from news organizations and identifying slow news days versus major news days. Our application, StoryGraph, periodically (10-minute intervals) extracts the first five news articles from the RSS feeds of 17 US news media organizations across the partisanship spectrum (left, center, and right). From these articles, StoryGraph extracts named entities (PEOPLE, LOCATIONS, ORGANIZATIONS, etc.) and then represents each news article with its set of extracted named entities. Finally, StoryGraph generates a news similarity graph where the nodes represent news articles, and an edge between a pair of nodes represents a high degree of similarity between the nodes (similar news stories). Each news story within the news similarity graph is assigned an attention score which quantifies the amount of attention the topics in the news story receive collectively from the news media organizations. The StoryGraph service has been running since August 2017, and using this method, we determined that the top news story of 2018 was the “Kavanaugh hearings” with attention score of 25.85 on September 27, 2018. Similarly, the top news story for 2019 so far (2019-12-12) is “AG William Barr’s release of his principal conclusions of the Mueller Report,” with an attention score of 22.93 on March 24, 2019. |
| Tasks | |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.09989v1 |
| https://arxiv.org/pdf/2003.09989v1.pdf | |
| PWC | https://paperswithcode.com/paper/365-dots-in-2019-quantifying-attention-of |
| Repo | |
| Framework | |
Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
| Title | Stealing Black-Box Functionality Using The Deep Neural Tree Architecture |
| Authors | Daniel Teitelman, Itay Naeh, Shie Mannor |
| Abstract | This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the black-box model, and clone its task-specific behavior. We propose to train the DNT using an active learning algorithm to obtain faster and more sample-efficient training. In contrast to prior work, we study a complex “victim” black-box model based solely on input-output interactions, while at the same time the attacker and the victim model may have completely different internal architectures. The attacker is a ML based algorithm whereas the victim is a generally unknown module, such as a multi-purpose digital chip, complex analog circuit, mechanical system, software logic or a hybrid of these. The trained DNT module not only can function as the attacked module, but also provides some level of explainability to the cloned model due to the tree-like nature of the proposed architecture. |
| Tasks | Active Learning |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09864v1 |
| https://arxiv.org/pdf/2002.09864v1.pdf | |
| PWC | https://paperswithcode.com/paper/stealing-black-box-functionality-using-the |
| Repo | |
| Framework | |
