January 29, 2020

3040 words 15 mins read

Paper Group ANR 657

A semi-supervised deep residual network for mode detection in Wi-Fi signals. High Dimensional Classification via Empirical Risk Minimization: Improvements and Optimality. Non-Structured DNN Weight Pruning – Is It Beneficial in Any Platform?. A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging. A Neural …

A semi-supervised deep residual network for mode detection in Wi-Fi signals


Title	A semi-supervised deep residual network for mode detection in Wi-Fi signals
Authors	Arash Kalatian, Bilal Farooq
Abstract	Due to their ubiquitous and pervasive nature, Wi-Fi networks have the potential to collect large-scale, low-cost, and disaggregate data on multimodal transportation. In this study, we develop a semi-supervised deep residual network (ResNet) framework to utilize Wi-Fi communications obtained from smartphones for the purpose of transportation mode detection. This framework is evaluated on data collected by Wi-Fi sensors located in a congested urban area in downtown Toronto. To tackle the intrinsic difficulties and costs associated with labelled data collection, we utilize ample amount of easily collected low-cost unlabelled data by implementing the semi-supervised part of the framework. By incorporating a ResNet architecture as the core of the framework, we take advantage of the high-level features not considered in the traditional machine learning frameworks. The proposed framework shows a promising performance on the collected data, with a prediction accuracy of 81.8% for walking, 82.5% for biking and 86.0% for the driving mode.
Tasks
Published	2019-02-17
URL	http://arxiv.org/abs/1902.06284v1
PDF	http://arxiv.org/pdf/1902.06284v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-supervised-deep-residual-network-for
Repo
Framework

High Dimensional Classification via Empirical Risk Minimization: Improvements and Optimality


Title	High Dimensional Classification via Empirical Risk Minimization: Improvements and Optimality
Authors	Xiaoyi Mai, Zhenyu Liao
Abstract	In this article, we investigate a family of classification algorithms defined by the principle of empirical risk minimization, in the high dimensional regime where the feature dimension $p$ and data number $n$ are both large and comparable. Based on recent advances in high dimensional statistics and random matrix theory, we provide under mixture data model a unified stochastic characterization of classifiers learned with different loss functions. Our results are instrumental to an in-depth understanding as well as practical improvements on this fundamental classification approach. As the main outcome, we demonstrate the existence of a universally optimal loss function which yields the best high dimensional performance at any given $n/p$ ratio.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13742v1
PDF	https://arxiv.org/pdf/1905.13742v1.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-classification-via-empirical
Repo
Framework

Non-Structured DNN Weight Pruning – Is It Beneficial in Any Platform?


Title	Non-Structured DNN Weight Pruning – Is It Beneficial in Any Platform?
Authors	Xiaolong Ma, Sheng Lin, Shaokai Ye, Zhezhi He, Linfeng Zhang, Geng Yuan, Sia Huat Tan, Zhengang Li, Deliang Fan, Xuehai Qian, Xue Lin, Kaisheng Ma, Yanzhi Wang
Abstract	Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy in the number of weights and can be performed in a non-structured, which has higher flexibility and pruning rate but incurs index accesses due to irregular weights, or structured manner, which preserves the full matrix structure with lower pruning rate. Weight quantization leverages the redundancy in the number of bits in weights. Compared to pruning, quantization is much more hardware-friendly, and has become a “must-do” step for FPGA and ASIC implementations. This paper provides a definitive answer to the question for the first time. First, we build ADMM-NN-S by extending and enhancing ADMM-NN, a recently proposed joint weight pruning and quantization framework. Second, we develop a methodology for fair and fundamental comparison of non-structured and structured pruning in terms of both storage and computation efficiency. Our results show that ADMM-NN-S consistently outperforms the prior art: (i) it achieves 348x, 36x, and 8x overall weight pruning on LeNet-5, AlexNet, and ResNet-50, respectively, with (almost) zero accuracy loss; (ii) we demonstrate the first fully binarized (for all layers) DNNs can be lossless in accuracy in many cases. These results provide a strong baseline and credibility of our study. Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structrued pruning is not competitive in terms of both storage and computation efficiency. Thus, we conclude that non-structured pruning is considered harmful. We urge the community not to continue the DNN inference acceleration for non-structured sparsity.
Tasks	Model Compression, Quantization
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02124v2
PDF	https://arxiv.org/pdf/1907.02124v2.pdf
PWC	https://paperswithcode.com/paper/non-structured-dnn-weight-pruning-considered
Repo
Framework

A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging


Title	A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging
Authors	Davood Karimi, Golnoosh Samei, Yanan Shao, Septimiu Salcudean
Abstract	We propose a novel automatic method for accurate segmentation of the prostate in T2-weighted magnetic resonance imaging (MRI). Our method is based on convolutional neural networks (CNNs). Because of the large variability in the shape, size, and appearance of the prostate and the scarcity of annotated training data, we suggest training two separate CNNs. A global CNN will determine a prostate bounding box, which is then resampled and sent to a local CNN for accurate delineation of the prostate boundary. This way, the local CNN can effectively learn to segment the fine details that distinguish the prostate from the surrounding tissue using the small amount of available training data. To fully exploit the training data, we synthesize additional data by deforming the training images and segmentations using a learned shape model. We apply the proposed method on the PROMISE12 challenge dataset and achieve state of the art results. Our proposed method generates accurate, smooth, and artifact-free segmentations. On the test images, we achieve an average Dice score of 90.6 with a small standard deviation of 2.2, which is superior to all previous methods. Our two-step segmentation approach and data augmentation strategy may be highly effective in segmentation of other organs from small amounts of annotated medical images.
Tasks	Data Augmentation
Published	2019-01-27
URL	https://arxiv.org/abs/1901.09462v2
PDF	https://arxiv.org/pdf/1901.09462v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-based-method-for-prostate
Repo
Framework

A Neural Entity Coreference Resolution Review


Title	A Neural Entity Coreference Resolution Review
Authors	Nikolaos Stylianou, Ioannis Vlahavas
Abstract	Entity Coreference Resolution is the task of resolving all the mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. While in it is not an end task, it has been proved to improve downstream natural language processing tasks such as entity linking, machine translation, summarization and chatbots. We conducted a systematic a review of neural-based approached and provide a detailed appraisal of the datasets and evaluation metrics in the field. Emphasis is given on Pronoun Resolution, a subtask of Coreference Resolution, which has seen various improvements in the recent years. We conclude the study by highlight the lack of agreed upon standards and propose a way to expand the task even further.
Tasks	Coreference Resolution, Entity Linking, Machine Translation
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09329v1
PDF	https://arxiv.org/pdf/1910.09329v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-entity-coreference-resolution-review
Repo
Framework

Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding


Title	Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding
Authors	Rui Fan, Mohammud Junaid Bocus, Yilong Zhu, Jianhao Jiao, Li Wang, Fulong Ma, Shanshan Cheng, Ming Liu
Abstract	Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. In this paper, we propose a novel road crack detection algorithm based on deep learning and adaptive image segmentation. Firstly, a deep convolutional neural network is trained to determine whether an image contains cracks or not. The images containing cracks are then smoothed using bilateral filtering, which greatly minimizes the number of noisy pixels. Finally, we utilize an adaptive thresholding method to extract the cracks from road surface. The experimental results illustrate that our network can classify images with an accuracy of 99.92%, and the cracks can be successfully extracted from the images using our proposed thresholding algorithm.
Tasks	Semantic Segmentation
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08582v1
PDF	http://arxiv.org/pdf/1904.08582v1.pdf
PWC	https://paperswithcode.com/paper/road-crack-detection-using-deep-convolutional
Repo
Framework

Forecasting Weakly Correlated Time Series in Tasks of Electronic Commerce


Title	Forecasting Weakly Correlated Time Series in Tasks of Electronic Commerce
Authors	Lyudmyla Kirichenko, Tamara Radivilova, Illya Zinkevich
Abstract	Forecasting of weakly correlated time series of conversion rate by methods of exponential smoothing, neural network and decision tree on the example of conversion percent series for an electronic store is considered in the paper. The advantages and disadvantages of each method are considered.
Tasks	Time Series
Published	2019-04-16
URL	http://arxiv.org/abs/1904.10927v1
PDF	http://arxiv.org/pdf/1904.10927v1.pdf
PWC	https://paperswithcode.com/paper/190410927
Repo
Framework

Rewarding High-Quality Data via Influence Functions


Title	Rewarding High-Quality Data via Influence Functions
Authors	Adam Richardson, Aris Filos-Ratsikas, Boi Faltings
Abstract	We consider a crowdsourcing data acquisition scenario, such as federated learning, where a Center collects data points from a set of rational Agents, with the aim of training a model. For linear regression models, we show how a payment structure can be designed to incentivize the agents to provide high-quality data as early as possible, based on a characterization of the influence that data points have on the loss function of the model. Our contributions can be summarized as follows: (a) we prove theoretically that this scheme ensures truthful data reporting as a game-theoretic equilibrium and further demonstrate its robustness against mixtures of truthful and heuristic data reports, (b) we design a procedure according to which the influence computation can be efficiently approximated and processed sequentially in batches over time, (c) we develop a theory that allows correcting the difference between the influence and the overall change in loss and (d) we evaluate our approach on real datasets, confirming our theoretical findings.
Tasks
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11598v1
PDF	https://arxiv.org/pdf/1908.11598v1.pdf
PWC	https://paperswithcode.com/paper/rewarding-high-quality-data-via-influence
Repo
Framework

Detection and Tracking of Multiple Mice Using Part Proposal Networks


Title	Detection and Tracking of Multiple Mice Using Part Proposal Networks
Authors	Zheheng Jiang, Zhihua Liu, Long Chen, Lei Tong, Xiangrong Zhang, Xiangyuan Lan, Danny Crookes, Ming-Hsuan Yang, Huiyu Zhou
Abstract	The study of mouse social behaviours has been increasingly undertaken in neuroscience research. However, automated quantification of mouse behaviours from the videos of interacting mice is still a challenging problem, where object tracking plays a key role in locating mice in their living spaces. Artificial markers are often applied for multiple mice tracking, which are intrusive and consequently interfere with the movements of mice in a dynamic environment. In this paper, we propose a novel method to continuously track several mice and individual parts without requiring any specific tagging. Firstly, we propose an efficient and robust deep learning based mouse part detection scheme to generate part candidates. Subsequently, we propose a novel Bayesian Integer Linear Programming Model that jointly assigns the part candidates to individual targets with necessary geometric constraints whilst establishing pair-wise association between the detected parts. There is no publicly available dataset in the research community that provides a quantitative test-bed for the part detection and tracking of multiple mice, and we here introduce a new challenging Multi-Mice PartsTrack dataset that is made of complex behaviours and actions. Finally, we evaluate our proposed approach against several baselines on our new datasets, where the results show that our method outperforms the other state-of-the-art approaches in terms of accuracy.
Tasks	Object Tracking
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02831v2
PDF	https://arxiv.org/pdf/1906.02831v2.pdf
PWC	https://paperswithcode.com/paper/detection-and-tracking-of-multiple-mice-using
Repo
Framework

Lotka-Volterra competition mechanism embedded in a decision-making method


Title	Lotka-Volterra competition mechanism embedded in a decision-making method
Authors	Tomoaki Niiyama, Genki Furuhata, Atsushi Uchida, Makoto Naruse, Satoshi Sunada
Abstract	Decision making is a fundamental capability of living organisms, and has recently been gaining increasing importance in many engineering applications. Here, we consider a simple decision-making principle to identify an optimal choice in multi-armed bandit (MAB) problems, which is fundamental in the context of reinforcement learning. We demonstrate that the identification mechanism of the method is well described by using a competitive ecosystem model, i.e., the competitive Lotka–Volterra (LV) model. Based on the “winner-take-all” mechanism in the competitive LV model, we demonstrate that non-best choices are eliminated and only the best choice survives; the failure of the non-best choices exponentially decreases while repeating the choice trials. Furthermore, we apply a mean-field approximation to the proposed decision-making method and show that the method has an excellent scalability of $O(\log N)$ with respect to the number of choices $N$. These results allow for a new perspective on optimal search capabilities in competitive systems.
Tasks	Decision Making
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12399v2
PDF	https://arxiv.org/pdf/1907.12399v2.pdf
PWC	https://paperswithcode.com/paper/lotka-volterra-competition-mechanism-embedded
Repo
Framework

History-based Anomaly Detector: an Adversarial Approach to Anomaly Detection


Title	History-based Anomaly Detector: an Adversarial Approach to Anomaly Detection
Authors	Pierrick Chatillon, Coloma Ballester
Abstract	Anomaly detection is a difficult problem in many areas and has recently been subject to a lot of attention. Classifying unseen data as anomalous is a challenging matter. Latest proposed methods rely on Generative Adversarial Networks (GANs) to estimate the normal data distribution, and produce an anomaly score prediction for any given data. In this article, we propose a simple yet new adversarial method to tackle this problem, denoted as History-based anomaly detector (HistoryAD). It consists of a self-supervised model, trained to recognize ‘normal’ samples by comparing them to samples based on the training history of a previously trained GAN. Quantitative and qualitative results are presented evaluating its performance. We also present a comparison to several state-of-the-art methods for anomaly detection showing that our proposal achieves top-tier results on several datasets.
Tasks	Anomaly Detection
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11843v2
PDF	https://arxiv.org/pdf/1912.11843v2.pdf
PWC	https://paperswithcode.com/paper/history-based-anomaly-detector-an-adversarial
Repo
Framework

Scrubbing Sensitive PHI Data from Medical Records made Easy by SpaCy – A Scalable Model Implementation Comparisons


Title	Scrubbing Sensitive PHI Data from Medical Records made Easy by SpaCy – A Scalable Model Implementation Comparisons
Authors	Rashmi Jain, Dinah Samuel Anand, Vijayalakshmi Janakiraman
Abstract	De-identification of clinical records is an extremely important process which enables the use of the wealth of information present in them. There are a lot of techniques available for this but none of the method implementation has evaluated the scalability, which is an important benchmark. We evaluated numerous deep learning techniques such as BiLSTM-CNN, IDCNN, CRF, BiLSTM-CRF, SpaCy, etc. on both the performance and efficiency. We propose that the SpaCy model implementation for scrubbing sensitive PHI data from medical records is both well performing and extremely efficient compared to other published models.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.06968v1
PDF	https://arxiv.org/pdf/1906.06968v1.pdf
PWC	https://paperswithcode.com/paper/scrubbing-sensitive-phi-data-from-medical
Repo
Framework

Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network


Title	Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network
Authors	Guangyi Zhang, Vandad Davoodnia, Alireza Sepas-Moghaddam, Yaoxue Zhang, Ali Etemad
Abstract	Classifying limb movements using brain activity is an important task in Brain-computer Interfaces (BCI) that has been successfully used in multiple application domains, ranging from human-computer interaction to medical and biomedical applications. This paper proposes a novel solution for classification of left/right hand movement by exploiting a Long Short-Term Memory (LSTM) network with attention mechanism to learn the electroencephalogram (EEG) time-series information. To this end, a wide range of time and frequency domain features are extracted from the EEG signals and used to train an LSTM network to perform the classification task. We conduct extensive experiments with the EEG Movement dataset and show that our proposed solution our method achieves improvements over several benchmarks and state-of-the-art methods in both intra-subject and cross-subject validation schemes. Moreover, we utilize the proposed framework to analyze the information as received by the sensors and monitor the activated regions of the brain by tracking EEG topography throughout the experiments.
Tasks	Deep Attention, EEG, Time Series
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02252v2
PDF	https://arxiv.org/pdf/1908.02252v2.pdf
PWC	https://paperswithcode.com/paper/classification-of-hand-movements-from-eeg
Repo
Framework

An Efficient Tensor Completion Method via New Latent Nuclear Norm


Title	An Efficient Tensor Completion Method via New Latent Nuclear Norm
Authors	Jinshi Yu, Weijun Sun, Yuning Qiu, Shengli Xie
Abstract	In tensor completion, the latent nuclear norm is commonly used to induce low-rank structure, while substantially failing to capture the global information due to the utilization of unbalanced unfolding scheme. To overcome this drawback, a new latent nuclear norm equipped with a more balanced unfolding scheme is defined for low-rank regularizer. Moreover, the new latent nuclear norm together with the Frank-Wolfe (FW) algorithm is developed as an efficient completion method by utilizing the sparsity structure of observed tensor. Specifically, both FW linear subproblem and line search only need to access the observed entries, by which we can instead maintain the sparse tensors and a set of small basis matrices during iteration. Most operations are based on sparse tensors, and the closed-form solution of FW linear subproblem can be obtained from rank-one SVD. We theoretically analyze the space-complexity and time-complexity of the proposed method, and show that it is much more efficient over other norm-based completion methods for higher-order tensors. Extensive experimental results of visual-data inpainting demonstrate that the proposed method is able to achieve state-of-the-art performance at smaller costs of time and space, which is very meaningful for the memory-limited equipment in practical applications.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.05986v1
PDF	https://arxiv.org/pdf/1910.05986v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-tensor-completion-method-via-new
Repo
Framework

Seizure Prediction Using Bidirectional LSTM


Title	Seizure Prediction Using Bidirectional LSTM
Authors	Hazrat Ali, Feroz Karim, Junaid Javed Qureshi, Adnan Omer Abuassba, Mohammad Farhad Bulbul
Abstract	Approximately, 50 million people in the world are affected by epilepsy. For patients, the anti-epileptic drugs are not always useful and these drugs may have undesired side effects on a patient’s health. If the seizure is predicted the patients will have enough time to take preventive measures. The purpose of this work is to investigate the application of bidirectional LSTM for seizure prediction. In this paper, we trained EEG data from canines on a double Bidirectional LSTM layer followed by a fully connected layer. The data was provided in the form of a Kaggle competition by American Epilepsy Society. The main task was to classify the interictal and preictal EEG clips. Using this model, we obtained an AUC of 0.84 on the test dataset. Which shows that our classifier’s performance is above chance level on unseen data. The comparison with the previous work shows that the use of bidirectional LSTM networks can achieve significantly better results than SVM and GRU networks.
Tasks	EEG, Seizure prediction
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06385v1
PDF	https://arxiv.org/pdf/1912.06385v1.pdf
PWC	https://paperswithcode.com/paper/seizure-prediction-using-bidirectional-lstm
Repo
Framework