April 2, 2020

3729 words 18 mins read

Paper Group ANR 389

Paper Group ANR 389

Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis. Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective. Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images. Threats to Federated Learning: A Su …

Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis

Title Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis
Authors K. Palani Thanaraj, B. Parvathavarthini, U. John Tanik, V. Rajinikanth, Seifedine Kadry, K. Kamalanand
Abstract This paper evaluates the approach of imaging timeseries data such as EEG in the diagnosis of epilepsy through Deep Neural Network (DNN). EEG signal is transformed into an RGB image using Gramian Angular Summation Field (GASF). Many such EEG epochs are transformed into GASF images for the normal and focal EEG signals. Then, some of the widely used Deep Neural Networks for image classification problems are used here to detect the focal GASF images. Three pre-trained DNN such as the AlexNet, VGG16, and VGG19 are validated for epilepsy detection based on the transfer learning approach. Furthermore, the textural features are extracted from GASF images, and prominent features are selected for a multilayer Artificial Neural Network (ANN) classifier. Lastly, a Custom Convolutional Neural Network (CNN) with three CNN layers, Batch Normalization, Max-pooling layer, and Dense layers, is proposed for epilepsy diagnosis from GASF images. The results of this paper show that the Custom CNN model was able to discriminate against the focal and normal GASF images with an average peak Precision of 0.885, Recall of 0.92, and F1-score of 0.90. Moreover, the Area Under the Curve (AUC) value of the Receiver Operating Characteristic (ROC) curve is 0.92 for the Custom CNN model. This paper suggests that Deep Learning methods widely used in image classification problems can be an alternative approach for epilepsy detection from EEG signals through GASF images.
Tasks EEG, Image Classification, Transfer Learning
Published 2020-03-08
URL https://arxiv.org/abs/2003.04534v1
PDF https://arxiv.org/pdf/2003.04534v1.pdf
PWC https://paperswithcode.com/paper/implementation-of-deep-neural-networks-to

Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective

Title Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective
Authors Kyungjun Lee, Daisuke Sato, Saki Asakawa, Hernisa Kacorri, Chieko Asakawa
Abstract Blind people have limited access to information about their surroundings, which is important for ensuring one’s safety, managing social interactions, and identifying approaching pedestrians. With advances in computer vision, wearable cameras can provide equitable access to such information. However, the always-on nature of these assistive technologies poses privacy concerns for parties that may get recorded. We explore this tension from both perspectives, those of sighted passersby and blind users, taking into account camera visibility, in-person versus remote experience, and extracted visual information. We conduct two studies: an online survey with MTurkers (N=206) and an in-person experience study between pairs of blind (N=10) and sighted (N=40) participants, where blind participants wear a working prototype for pedestrian detection and pass by sighted participants. Our results suggest that both of the perspectives of users and bystanders and the several factors mentioned above need to be carefully considered to mitigate potential social tensions.
Tasks Pedestrian Detection
Published 2020-03-26
URL https://arxiv.org/abs/2003.12122v1
PDF https://arxiv.org/pdf/2003.12122v1.pdf
PWC https://paperswithcode.com/paper/pedestrian-detection-with-wearable-cameras

Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images

Title Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images
Authors Zhenyu Tang, Wei Zhao, Xingzhi Xie, Zheng Zhong, Feng Shi, Jun Liu, Dinggang Shen
Abstract Background: Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of affected patients increase rapidly, manual severity assessment becomes a labor-intensive task, and may lead to delayed treatment. Purpose: Using machine learning method to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images, and to explore the severity-related features from the resulting assessment model. Materials and Method: Chest CT images of 176 patients (age 45.3$\pm$16.5 years, 96 male and 80 female) with confirmed COVID-19 are used, from which 63 quantitative features, e.g., the infection volume/ratio of the whole lung and the volume of ground-glass opacity (GGO) regions, are calculated. A random forest (RF) model is trained to assess the severity (non-severe or severe) based on quantitative features. Importance of each quantitative feature, which reflects the correlation to the severity of COVID-19, is calculated from the RF model. Results: Using three-fold cross validation, the RF model shows promising results, i.e., 0.933 of true positive rate, 0.745 of true negative rate, 0.875 of accuracy, and 0.91 of area under receiver operating characteristic curve (AUC). The resulting importance of quantitative features shows that the volume and its ratio (with respect to the whole lung volume) of ground glass opacity (GGO) regions are highly related to the severity of COVID-19, and the quantitative features calculated from the right lung are more related to the severity assessment than those of the left lung. Conclusion: The RF based model can achieve automatic severity assessment (non-severe or severe) of COVID-19 infection, and the performance is promising. Several quantitative features, which have the potential to reflect the severity of COVID-19, were revealed.
Tasks Computed Tomography (CT)
Published 2020-03-26
URL https://arxiv.org/abs/2003.11988v1
PDF https://arxiv.org/pdf/2003.11988v1.pdf
PWC https://paperswithcode.com/paper/severity-assessment-of-coronavirus-disease

Threats to Federated Learning: A Survey

Title Threats to Federated Learning: A Survey
Authors Lingjuan Lyu, Han Yu, Qiang Yang
Abstract With the emergence of data silos and popular privacy awareness, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges. Federated learning (FL) has recently emerged as a promising solution under this new reality. Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and without the system to compromise data privacy. It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation. Currently, there is no survey on this topic. In this paper, we bridge this important gap in FL literature. By providing a concise introduction to the concept of FL, and a unique taxonomy covering threat models and two major attacks on FL: 1) poisoning attacks and 2) inference attacks, this paper provides an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks, and discuss promising future research directions towards more robust privacy preservation in FL.
Published 2020-03-04
URL https://arxiv.org/abs/2003.02133v1
PDF https://arxiv.org/pdf/2003.02133v1.pdf
PWC https://paperswithcode.com/paper/threats-to-federated-learning-a-survey

Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection

Title Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection
Authors Xinzheng Zhang, Guo Liu, Ce Zhang, Peter M Atkinson, Xiaoheng Tan, Xin Jian, Xichuan Zhou, Yongming Li
Abstract Change detection is one of the fundamental applications of synthetic aperture radar (SAR) images. However, speckle noise presented in SAR images has a much negative effect on change detection. In this research, a novel two-phase object-based deep learning approach is proposed for multi-temporal SAR image change detection. Compared with traditional methods, the proposed approach brings two main innovations. One is to classify all pixels into three categories rather than two categories: unchanged pixels, changed pixels caused by strong speckle (false changes), and changed pixels formed by real terrain variation (real changes). The other is to group neighboring pixels into segmented into superpixel objects (from pixels) such as to exploit local spatial context. Two phases are designed in the methodology: 1) Generate objects based on the simple linear iterative clustering algorithm, and discriminate these objects into changed and unchanged classes using fuzzy c-means (FCM) clustering and a deep PCANet. The prediction of this Phase is the set of changed and unchanged superpixels. 2) Deep learning on the pixel sets over the changed superpixels only, obtained in the first phase, to discriminate real changes from false changes. SLIC is employed again to achieve new superpixels in the second phase. Low rank and sparse decomposition are applied to these new superpixels to suppress speckle noise significantly. A further clustering step is applied to these new superpixels via FCM. A new PCANet is then trained to classify two kinds of changed superpixels to achieve the final change maps. Numerical experiments demonstrate that, compared with benchmark methods, the proposed approach can distinguish real changes from false changes effectively with significantly reduced false alarm rates, and achieve up to 99.71% change detection accuracy using multi-temporal SAR imagery.
Published 2020-01-17
URL https://arxiv.org/abs/2001.06252v1
PDF https://arxiv.org/pdf/2001.06252v1.pdf
PWC https://paperswithcode.com/paper/two-phase-object-based-deep-learning-for

Multi-Scale Neural network for EEG Representation Learning in BCI

Title Multi-Scale Neural network for EEG Representation Learning in BCI
Authors Wonjun Ko, Eunjin Jeon, Seungwoo Jeong, Heung-Il Suk
Abstract Recent advances in deep learning have had a methodological and practical impact on brain-computer interface research. Among the various deep network architectures, convolutional neural networks have been well suited for spatio-spectral-temporal electroencephalogram signal representation learning. Most of the existing CNN-based methods described in the literature extract features at a sequential level of abstraction with repetitive nonlinear operations and involve densely connected layers for classification. However, studies in neurophysiology have revealed that EEG signals carry information in different ranges of frequency components. To better reflect these multi-frequency properties in EEGs, we propose a novel deep multi-scale neural network that discovers feature representations in multiple frequency/time ranges and extracts relationships among electrodes, i.e., spatial representations, for subject intention/condition identification. Furthermore, by completely representing EEG signals with spatio-spectral-temporal information, the proposed method can be utilized for diverse paradigms in both active and passive BCIs, contrary to existing methods that are primarily focused on single-paradigm BCIs. To demonstrate the validity of our proposed method, we conducted experiments on various paradigms of active/passive BCI datasets. Our experimental results demonstrated that the proposed method achieved performance improvements when judged against comparable state-of-the-art methods. Additionally, we analyzed the proposed method using different techniques, such as PSD curves and relevance score inspection to validate the multi-scale EEG signal information capturing ability, activation pattern maps for investigating the learned spatial filters, and t-SNE plotting for visualizing represented features. Finally, we also demonstrated our method’s application to real-world problems.
Tasks EEG, Representation Learning
Published 2020-03-02
URL https://arxiv.org/abs/2003.02657v1
PDF https://arxiv.org/pdf/2003.02657v1.pdf
PWC https://paperswithcode.com/paper/multi-scale-neural-network-for-eeg

Event-Based Angular Velocity Regression with Spiking Networks

Title Event-Based Angular Velocity Regression with Spiking Networks
Authors Mathias Gehrig, Sumit Bam Shrestha, Daniel Mouritzen, Davide Scaramuzza
Abstract Spiking Neural Networks (SNNs) are bio-inspired networks that process information conveyed as temporal spikes rather than numeric values. A spiking neuron of an SNN only produces a spike whenever a significant number of spikes occur within a short period of time. Due to their spike-based computational model, SNNs can process output from event-based, asynchronous sensors without any pre-processing at extremely lower power unlike standard artificial neural networks. This is possible due to specialized neuromorphic hardware that implements the highly-parallelizable concept of SNNs in silicon. Yet, SNNs have not enjoyed the same rise of popularity as artificial neural networks. This not only stems from the fact that their input format is rather unconventional but also due to the challenges in training spiking networks. Despite their temporal nature and recent algorithmic advances, they have been mostly evaluated on classification problems. We propose, for the first time, a temporal regression problem of numerical values given events from an event camera. We specifically investigate the prediction of the 3-DOF angular velocity of a rotating event camera with an SNN. The difficulty of this problem arises from the prediction of angular velocities continuously in time directly from irregular, asynchronous event-based input. Directly utilising the output of event cameras without any pre-processing ensures that we inherit all the benefits that they provide over conventional cameras. That is high-temporal resolution, high-dynamic range and no motion blur. To assess the performance of SNNs on this task, we introduce a synthetic event camera dataset generated from real-world panoramic images and show that we can successfully train an SNN to perform angular velocity regression.
Published 2020-03-05
URL https://arxiv.org/abs/2003.02790v1
PDF https://arxiv.org/pdf/2003.02790v1.pdf
PWC https://paperswithcode.com/paper/event-based-angular-velocity-regression-with

Deep Synthetic Minority Over-Sampling Technique

Title Deep Synthetic Minority Over-Sampling Technique
Authors Hadi Mansourifar, Weidong Shi
Abstract Synthetic Minority Over-sampling Technique (SMOTE) is the most popular over-sampling method. However, its random nature makes the synthesized data and even imbalanced classification results unstable. It means that in case of running SMOTE n different times, n different synthesized in-stances are obtained with n different classification results. To address this problem, we adapt the SMOTE idea in deep learning architecture. In this method, a deep neural network regression model is used to train the inputs and outputs of traditional SMOTE. Inputs of the proposed deep regression model are two randomly chosen data points which are concatenated to form a double size vector. The outputs of this model are corresponding randomly interpolated data points between two randomly chosen vectors with original dimension. The experimental results show that, Deep SMOTE can outperform traditional SMOTE in terms of precision, F1 score and Area Under Curve (AUC) in majority of test cases.
Published 2020-03-22
URL https://arxiv.org/abs/2003.09788v1
PDF https://arxiv.org/pdf/2003.09788v1.pdf
PWC https://paperswithcode.com/paper/deep-synthetic-minority-over-sampling

On Adaptive Attacks to Adversarial Example Defenses

Title On Adaptive Attacks to Adversarial Example Defenses
Authors Florian Tramer, Nicholas Carlini, Wieland Brendel, Aleksander Madry
Abstract Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at ICLR, ICML and NeurIPS—and chosen for illustrative and pedagogical purposes—can be circumvented despite attempting to perform evaluations using adaptive attacks. While prior evaluation papers focused mainly on the end result—showing that a defense was ineffective—this paper focuses on laying out the methodology and the approach necessary to perform an adaptive attack. We hope that these analyses will serve as guidance on how to properly perform adaptive attacks against defenses to adversarial examples, and thus will allow the community to make further progress in building more robust models.
Published 2020-02-19
URL https://arxiv.org/abs/2002.08347v1
PDF https://arxiv.org/pdf/2002.08347v1.pdf
PWC https://paperswithcode.com/paper/on-adaptive-attacks-to-adversarial-example

AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite

Title AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
Authors Wanling Gao, Fei Tang, Jianfeng Zhan, Chuanxin Lan, Chunjie Luo, Lei Wang, Jiahui Dai, Zheng Cao, Xiongwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Xu Wen, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Gang Lu, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
Abstract Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process as it provides not only relevant design inputs but also relevant metrics, and tools. Unfortunately, modern workloads like Big data, AI, and Internet services dwarf the traditional one in terms of code size, deployment scale, and execution path, and hence raise serious benchmarking challenges. This paper proposes an agile domain-specific benchmarking methodology. Together with seventeen industry partners, we identify ten important end-to-end application scenarios, among which sixteen representative AI tasks are distilled as the AI component benchmarks. We propose the permutations of essential AI and non-AI component benchmarks as end-to-end benchmarks. An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application. We design and implement a highly extensible, configurable, and flexible benchmark framework, on the basis of which, we propose the guideline for building end-to-end benchmarks, and present the first end-to-end Internet service AI benchmark. The preliminary evaluation shows the value of our benchmark suite—AIBench against MLPerf and TailBench for hardware and software designers, micro-architectural researchers, and code developers. The specifications, source code, testbed, and results are publicly available from the web site \url{http://www.benchcouncil.org/AIBench/index.html}.
Published 2020-02-17
URL https://arxiv.org/abs/2002.07162v1
PDF https://arxiv.org/pdf/2002.07162v1.pdf
PWC https://paperswithcode.com/paper/aibench-an-agile-domain-specific-benchmarking

Gradient descent with momentum — to accelerate or to super-accelerate?

Title Gradient descent with momentum — to accelerate or to super-accelerate?
Authors Goran Nakerst, John Brennan, Masudul Haque
Abstract We consider gradient descent with momentum', a widely used method for loss function minimization in machine learning. This method is often used with Nesterov acceleration’, meaning that the gradient is evaluated not at the current position in parameter space, but at the estimated position after one step. In this work, we show that the algorithm can be improved by extending this acceleration' --- by using the gradient at an estimated position several steps ahead rather than just one step ahead. How far one looks ahead in this super-acceleration’ algorithm is determined by a new hyperparameter. Considering a one-parameter quadratic loss function, the optimal value of the super-acceleration can be exactly calculated and analytically estimated. We show explicitly that super-accelerating the momentum algorithm is beneficial, not only for this idealized problem, but also for several synthetic loss landscapes and for the MNIST classification task with neural networks. Super-acceleration is also easy to incorporate into adaptive algorithms like RMSProp or Adam, and is shown to improve these algorithms.
Published 2020-01-17
URL https://arxiv.org/abs/2001.06472v1
PDF https://arxiv.org/pdf/2001.06472v1.pdf
PWC https://paperswithcode.com/paper/gradient-descent-with-momentum-to-accelerate

Extracting Semantic Indoor Maps from Occupancy Grids

Title Extracting Semantic Indoor Maps from Occupancy Grids
Authors Ziyuan Liu, Georg von Wichert
Abstract The primary challenge for any autonomous system operating in realistic, rather unconstrained scenarios is to manage the complexity and uncertainty of the real world. While it is unclear how exactly humans and other higher animals master these problems, it seems evident, that abstraction plays an important role. The use of abstract concepts allows to define the system behavior on higher levels. In this paper we focus on the semantic mapping of indoor environments. We propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning. The result of this procedure is a probabilistic generative model of the environment defined over abstract concepts. It is well suited for higher-level reasoning and communication purposes. We demonstrate the effectiveness of the approach using real-world data.
Published 2020-02-19
URL https://arxiv.org/abs/2002.08348v1
PDF https://arxiv.org/pdf/2002.08348v1.pdf
PWC https://paperswithcode.com/paper/extracting-semantic-indoor-maps-from

Online Memorization of Random Firing Sequences by a Recurrent Neural Network

Title Online Memorization of Random Firing Sequences by a Recurrent Neural Network
Authors Patrick Murer, Hans-Andrea Loeliger
Abstract This paper studies the capability of a recurrent neural network model to memorize random dynamical firing patterns by a simple local learning rule. Two modes of learning/memorization are considered: The first mode is strictly online, with a single pass through the data, while the second mode uses multiple passes through the data. In both modes, the learning is strictly local (quasi-Hebbian): At any given time step, only the weights between the neurons firing (or supposed to be firing) at the previous time step and those firing (or supposed to be firing) at the present time step are modified. The main result of the paper is an upper bound on the probability that the single-pass memorization is not perfect. It follows that the memorization capacity in this mode asymptotically scales like that of the classical Hopfield model (which, in contrast, memorizes static patterns). However, multiple-rounds memorization is shown to achieve a higher capacity (with a nonvanishing number of bits per connection/synapse). These mathematical findings may be helpful for understanding the functions of short-term memory and long-term memory in neuroscience.
Published 2020-01-09
URL https://arxiv.org/abs/2001.02920v1
PDF https://arxiv.org/pdf/2001.02920v1.pdf
PWC https://paperswithcode.com/paper/online-memorization-of-random-firing

Early-detection and classification of live bacteria using time-lapse coherent imaging and deep learning

Title Early-detection and classification of live bacteria using time-lapse coherent imaging and deep learning
Authors Hongda Wang, Hatice Ceylan Koydemir, Yunzhe Qiu, Bijie Bai, Yibo Zhang, Yiyin Jin, Sabiha Tok, Enis Cagatay Yilmaz, Esin Gumustekin, Yair Rivenson, Aydogan Ozcan
Abstract We present a computational live bacteria detection system that periodically captures coherent microscopy images of bacterial growth inside a 60 mm diameter agar-plate and analyzes these time-lapsed holograms using deep neural networks for rapid detection of bacterial growth and classification of the corresponding species. The performance of our system was demonstrated by rapid detection of Escherichia coli and total coliform bacteria (i.e., Klebsiella aerogenes and Klebsiella pneumoniae subsp. pneumoniae) in water samples. These results were confirmed against gold-standard culture-based results, shortening the detection time of bacterial growth by >12 h as compared to the Environmental Protection Agency (EPA)-approved analytical methods. Our experiments further confirmed that this method successfully detects 90% of bacterial colonies within 7-10 h (and >95% within 12 h) with a precision of 99.2-100%, and correctly identifies their species in 7.6-12 h with 80% accuracy. Using pre-incubation of samples in growth media, our system achieved a limit of detection (LOD) of ~1 colony forming unit (CFU)/L within 9 h of total test time. This computational bacteria detection and classification platform is highly cost-effective (~$0.6 per test) and high-throughput with a scanning speed of 24 cm2/min over the entire plate surface, making it highly suitable for integration with the existing analytical methods currently used for bacteria detection on agar plates. Powered by deep learning, this automated and cost-effective live bacteria detection platform can be transformative for a wide range of applications in microbiology by significantly reducing the detection time, also automating the identification of colonies, without labeling or the need for an expert.
Published 2020-01-29
URL https://arxiv.org/abs/2001.10695v1
PDF https://arxiv.org/pdf/2001.10695v1.pdf
PWC https://paperswithcode.com/paper/early-detection-and-classification-of-live

Flexible numerical optimization with ensmallen

Title Flexible numerical optimization with ensmallen
Authors Ryan R. Curtin, Marcus Edel, Rahul Ganesh Prabhu, Suryoday Basak, Zhihao Lou, Conrad Sanderson
Abstract This report provides an introduction to the ensmallen numerical optimization library, as well as a deep dive into the technical details of how it works. The library provides a fast and flexible C++ framework for mathematical optimization of arbitrary user-supplied functions. A large set of pre-built optimizers is provided, including many variants of Stochastic Gradient Descent and Quasi-Newton optimizers. Several types of objective functions are supported, including differentiable, separable, constrained, and categorical objective functions. Implementation of a new optimizer requires only one method, while a new objective function requires typically only one or two C++ methods. Through internal use of C++ template metaprogramming, ensmallen provides support for arbitrary user-supplied callbacks and automatic inference of unsupplied methods without any runtime overhead. Empirical comparisons show that ensmallen outperforms other optimization frameworks (such as Julia and SciPy), sometimes by large margins. The library is available at https://ensmallen.org and is distributed under the permissive BSD license.
Published 2020-03-09
URL https://arxiv.org/abs/2003.04103v3
PDF https://arxiv.org/pdf/2003.04103v3.pdf
PWC https://paperswithcode.com/paper/flexible-numerical-optimization-with
comments powered by Disqus