We gratefully acknowledge support from
the Simons Foundation and member institutions.

Electrical Engineering and Systems Science

New submissions

[ total of 53 entries: 1-53 ]
[ showing up to 2000 entries per page: fewer | more ]

New submissions for Fri, 23 Aug 19

[1]  arXiv:1908.08035 [pdf, other]
Title: More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation
Comments: Accepted to MICCAI MIL3ID 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)

Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications. With a laparoscopic liver image segmentation application, we investigate the performance impact by altering the quantities of labelled and unlabelled training data, using a semi-supervised segmentation algorithm based on the mean teacher learning paradigm. We first report a significantly higher segmentation accuracy, compared with supervised learning. Interestingly, this comparison reveals that the training strategy adopted in the semi-supervised algorithm is also responsible for this observed improvement, in addition to the added unlabelled data. We then compare different combinations of labelled and unlabelled data set sizes for training semi-supervised segmentation networks, to provide a quantitative example of the practically useful trade-off between the two data planning strategies in this surgical guidance application.

[2]  arXiv:1908.08071 [pdf, other]
Title: Boundary Aware Networks for Medical Image Segmentation
Comments: Accepted to Machine Learning in Medical Imaging (MLMI 2019)
Journal-ref: Machine Learning in Medical Imaging (MLMI 2019)
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Fully convolutional neural networks (CNNs) have proven to be effective at representing and classifying textural information, thus transforming image intensity into output class masks that achieve semantic image segmentation. In medical image analysis, however, expert manual segmentation often relies on the boundaries of anatomical structures of interest. We propose boundary aware CNNs for medical image segmentation. Our networks are designed to account for organ boundary information, both by providing a special network edge branch and edge-aware loss terms, and they are trainable end-to-end. We validate their effectiveness on the task of brain tumor segmentation using the BraTS 2018 dataset. Our experiments reveal that our approach yields more accurate segmentation results, which makes it promising for more extensive application to medical image segmentation.

[3]  arXiv:1908.08074 [pdf, other]
Title: DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
Journal-ref: ICCV 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Positron emission tomography (PET) imaging is an imaging modality for diagnosing a number of neurological diseases. In contrast to Magnetic Resonance Imaging (MRI), PET is costly and involves injecting a radioactive substance into the patient. Motivated by developments in modality transfer in vision, we study the generation of certain types of PET images from MRI data. We derive new flow-based generative models which we show perform well in this small sample size regime (much smaller than dataset sizes available in standard vision tasks). Our formulation, DUAL-GLOW, is based on two invertible networks and a relation network that maps the latent spaces to each other. We discuss how given the prior distribution, learning the conditional distribution of PET given the MRI image reduces to obtaining the conditional distribution between the two latent codes w.r.t. the two image types. We also extend our framework to leverage 'side' information (or attributes) when available. By controlling the PET generation through 'conditioning' on age, our model is also able to capture brain FDG-PET (hypometabolism) changes, as a function of age. We present experiments on the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset with 826 subjects, and obtain good performance in PET image synthesis, qualitatively and quantitatively better than recent works.

[4]  arXiv:1908.08099 [pdf, other]
Title: Simple Thermal Noise Estimation of Switched Capacitor Circuits Based on OTAs -- Part I: Amplifiers with Capacitive Feedback
Subjects: Signal Processing (eess.SP)

This paper presents a simple method for estimating the thermal noise voltage variance in passive and active switched-capacitor (SC) circuits using operational transconductance amplifiers (OTA). The proposed method is based on the Bode theorem for passive network which is extended to active circuits based on OTAs with capacitive feedback. It allows for a precise estimation of the thermal noise voltage variance by simple inspection of three equivalent circuits avoiding the calculation of any transfer functions nor integrals. In this Part I, the method is applied to SC amplifiers and track&hold circuits and successfully validated by means of transient noise simulations. Part II extends the application of the method to integrators and active SC filters.

[5]  arXiv:1908.08109 [pdf, other]
Title: Simple Thermal Noise Estimation of Switched Capacitor Circuits Based on OTAs -- Part II: SC Filters
Subjects: Signal Processing (eess.SP)

In Part I of this paper, we have shown how to calculate the thermal noise voltage variances in switched-capacitor (SC) circuits using operational transconductance amplifiers (OTAs) with capacitive feedback by using the extended Bode theorem. The method allows a precise estimation of the thermal noise voltage variances by simple circuit inspection without the calculation of any transfer functions nor integrals. While Part I focuses on SC amplifiers and track&hold circuits, Part II shows how to use the extended Bode theorem for SC filters. It validates the method on the basic integrator and then on a first-order low-pass filter by comparing the analytical results to transient noise simulations showing an excellent match.

[6]  arXiv:1908.08124 [pdf, other]
Title: Statistical characterization of scattering delay in synthetic aperture radar imaging
Comments: 31 pages, 6 figures
Subjects: Image and Video Processing (eess.IV)

Distinguishing between the instantaneous and delayed scatterers in synthetic aperture radar (SAR) images is important for target identification and characterization. To perform this task, one can use the autocorrelation analysis of coordinate-delay images. However, due to the range-delay ambiguity the difference in the correlation properties between the instantaneous and delayed targets may be small. Moreover, the reliability of discrimination is affected by speckle, which is ubiquitous in SAR images, and requires statistical treatment.
Previously, we have developed a maximum likelihood based approach for discriminating between the instantaneous and delayed targets in SAR images. To test it, we employed simple statistical models. They allowed us to simulate ensembles of images that depend on various parameters, including aperture width and target contrast.
In the current paper, we enhance our previously developed methodology by establishing confidence levels for the discrimination between the instantaneous and delayed scatterers. Our procedure takes into account the difference in thresholds for different target contrasts without making any assumptions about the statistics of those contrasts.

[7]  arXiv:1908.08130 [pdf, other]
Title: cSeiz: An Edge-Device for Accurate Seizure Detection and Control for Smart Healthcare
Comments: 24 pages, 16 figures
Subjects: Signal Processing (eess.SP); Systems and Control (eess.SY)

Epilepsy is one of the most common neurological disorders affecting up to 1% of the world's population and approximately 2.5 million people in the United States. Seizures in more than 30% of epilepsy patients are refractory to anti-epileptic drugs. An important biomedical research effort is focused on the development of an energy efficient implantable device for the real-time control of seizures. In this paper we propose an Internet of Medical Things (IoMT) based automated seizure detection and drug delivery system (DDS) for the control of seizures. The proposed system will detect seizures and inject a fast acting anti-convulsant drug at the onset to suppress seizure progression. The drug injection is performed in two stages. Initially, the seizure detector detects the seizure from the electroencephalography (EEG) signal using a hyper-synchronous signal detection circuit and a signal rejection algorithm (SRA). In the second stage, the drug is released in the seizure onset area upon seizure detection. The design was validated using a system-level simulation and consumer electronics proof of concept. The proposed seizure detector reports a sensitivity of 96.9% and specificity of 97.5%. The use of minimal circuitry leads to a considerable reduction of power consumption compared to previous approaches. The proposed approach can be generalized to other sensor modalities and the use of both wearable and implantable solutions, or a combination of the two.

[8]  arXiv:1908.08164 [pdf]
Title: Building change detection based on multi-scale filtering and grid partition
Comments: 8 pages, 6 figures, conference paper
Journal-ref: 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS),2018,1-6
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Building change detection is of great significance in high resolution remote sensing applications. Multi-index learning, one of the state-of-the-art building change detection methods, still has drawbacks like incapability to find change types directly and heavy computation consumption of MBI. In this paper, a two-stage building change detection method is proposed to address these problems. In the first stage, a multi-scale filtering building index (MFBI) is calculated to detect building areas in each temporal with fast speed and moderate accuracy. In the second stage, images and the corresponding building maps are partitioned into grids. In each grid, the ratio of building areas in time T2 and time T1 is calculated. Each grid is classified into one of the three change patterns, i.e., significantly increase, significantly decrease and approximately unchanged. Exhaustive experiments indicate that the proposed method can detect building change types directly and outperform the current multi-index learning method.

[9]  arXiv:1908.08165 [pdf]
Title: Optimal step-size of least mean absolute fourth algorithm in low SNR
Subjects: Signal Processing (eess.SP); Information Theory (cs.IT)

There is a need to improve the capability of the adaptive filtering algorithm against Gaussian or multiple types of non-Gaussian noises, time-varying system, and systems with low SNR. In this paper, we propose an optimized least mean absolute fourth (OPLMF) algorithm, especially for a time-varying unknown system with low signal-noise-rate (SNR). The optimal step-size of OPLMF is obtained by minimizing the mean-square deviation (MSD) at any given moment in time. In addition, the mean convergence and steady-state error of OPLMF are derived. Also the theoretical computational complexity of OPLMF is analyzed. Furthermore, the simulation experiment results of system identification are used to illustrate the principle and efficiency of the OPLMF algorithm. The performance of the algorithm is analyzed mathematically and validated experimentally. Simulation results demonstrate that the proposed OPLMF is superior to the normalized LMF (NLMF) and variable step-size of LMF using quotient form (VSSLMFQ) algorithms.

[10]  arXiv:1908.08176 [pdf, other]
Title: Benchmarking air-conditioning energy performance of residential rooms based on regression and clustering techniques
Comments: 38 pages (single column), 7 figures, 6 tables. This manuscript is published in Applied Energy 253 (2019): 113548. Please refer to the published version at this https URL
Journal-ref: Applied Energy 253 (2019): 113548
Subjects: Systems and Control (eess.SY); Machine Learning (cs.LG)

Air conditioning (AC) accounts for a critical portion of the global energy consumption. To improve its energy performance, it is important to fairly benchmark its energy performance and provide the evaluation feedback to users. However, this task has not been well tackled in the residential sector. In this paper, we propose a data-driven approach to fairly benchmark the AC energy performance of residential rooms. First, regression model is built for each benchmarked room so that its power consumption can be predicted given different weather conditions and AC settings. Then, all the rooms are clustered based on their areas and usual AC temperature set points. Lastly, within each cluster, rooms are benchmarked based on their predicted power consumption under uniform weather conditions and AC settings. A real-world case study was conducted with data collected from 44 residential rooms. Results show that the constructed regression models have an average prediction accuracy of 85.1% in cross-validation tests, and support vector regression with Gaussian kernel is the overall most suitable model structure for building the regression model. In the clustering step, 44 rooms are successfully clustered into seven clusters. By comparing the benchmarking scores generated by the proposed approach with two sets of scores computed from historical power consumption data, we demonstrate that the proposed approach is able to eliminate the influences of room areas, weather conditions, and AC settings on the benchmarking results. Therefore, the proposed benchmarking approach is valid and fair. As a by-product, the approach is also shown to be useful to investigate how room areas, weather conditions, and AC settings affect the AC power consumption of rooms in real life.

[11]  arXiv:1908.08180 [pdf, other]
Title: Networked Synthetic Dynamic PMU Data Generation: A Generative Adversarial Network Approach
Comments: This manuscript has been submitted to IEEE Transactions on Power Systems
Subjects: Signal Processing (eess.SP)

This paper introduces a machine learning-based approach to synthetically create multiple phasor measurement unit (PMU) data streams at different buses in a power system. In contrast to the existing literature of creating synthetic power grid network and then using simulation software to output synthetic PMU data, we propose a generative adversarial network (GAN) based approach to synthesize multiple PMU measurement streams directly from historical data. The proposed method can simultaneously create multiple PMU measurement streams that reflect practically meaningful electromechanical dynamics which observe the Kirchhoff's laws. We further validate the synthetic data via the statistical resemblance and the modal analysis. The efficacy of this new approach is demonstrated by numerical studies on a 39-bus system and a 200-bus system.

[12]  arXiv:1908.08187 [pdf, other]
Title: A CNN toolbox for skin cancer classification
Comments: DFKI Technical Report
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

We describe a software toolbox for the configuration of deep neural networks in the domain of skin cancer classification. The implemented software architecture allows developers to quickly set up new convolutional neural network (CNN) architectures and hyper-parameter configurations. At the same time, the user interface, manageable as a simple spreadsheet, allows non-technical users to explore different configuration settings that need to be explored when switching to different data sets. In future versions, meta leaning frameworks can be added, or AutoML systems that continuously improve over time. Preliminary results, conducted with two CNNs in the context melanoma detection on dermoscopic images, quantify the impact of image augmentation, image resolution, and rescaling filter on the overall detection performance and training time.

[13]  arXiv:1908.08193 [pdf, other]
Title: Dynamic Weight Importance Sampling for Low Cost Spatiotemporal Sensing
Authors: Hadi Alasti
Comments: 5 pages, 6 figures, article
Subjects: Signal Processing (eess.SP)

A simple and low cost dynamic weight importance sampling (DWIS) implementation is presented and discussed for spatiotemporal sensing of unknown correlated signals in sensor field. The spatial signal is compressed into its contour lines and a partitioned subset of sensors that their observations are in a given margin of the contour levels, is used for importance sampling. The selected sensor population is changed dynamically to maintain the low cost and acceptable spatial signal estimation from limited observations. The estimation performance, cost and convergence of the proposed approach is evaluated for spatial and temporal monitoring, using three different contour level definition schemes. The results show that using DWIS and modeling the spatial signal with contour lines is low cost. In this study the presence of noise in sensor observations is ignored. The number of participant sensors is taken as modeling cost.

[14]  arXiv:1908.08195 [pdf, other]
Title: An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

This paper proposes a novel multi-exposure image fusion (MEF) scheme for single-shot high dynamic range imaging with spatially varying exposures (SVE). Single-shot imaging with SVE enables us not only to produce images without color saturation regions from a single-shot image, but also to avoid ghost artifacts in the producing ones. However, the number of exposures is generally limited to two, and moreover it is difficult to decide the optimum exposure values before the photographing. In the proposed scheme, a scene segmentation method is applied to input multi-exposure images, and then the luminance of the input images is adjusted according to both of the number of scenes and the relationship between exposure values and pixel values. The proposed method with the luminance adjustment allows us to improve the above two issues. In this paper, we focus on dual-ISO imaging as one of single-shot imaging. In an experiment, the proposed scheme is demonstrated to be effective for single-shot high dynamic range imaging with SVE, compared with conventional MEF schemes with exposure compensation.

[15]  arXiv:1908.08204 [pdf, other]
Title: Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Subjects: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Machine Learning (stat.ML)

Surface mount technology (SMT) is a process for producing printed circuit boards. Solder paste printer (SPP), package mounter, and solder reflow oven are used for SMT. The board on which the solder paste is deposited from the SPP is monitored by solder paste inspector (SPI). If SPP malfunctions due to the printer defects, the SPP produces defective products, and then abnormal patterns are detected by SPI. In this paper, we propose a convolutional recurrent reconstructive network (CRRN), which decomposes the anomaly patterns generated by the printer defects, from SPI data. CRRN learns only normal data and detects anomaly pattern through reconstruction error. CRRN consists of a spatial encoder (S-Encoder), a spatiotemporal encoder and decoder (ST-Encoder-Decoder), and a spatial decoder (S-Decoder). The ST-Encoder-Decoder consists of multiple convolutional spatiotemporal memories (CSTMs) with ST-Attention mechanism. CSTM is developed to extract spatiotemporal patterns efficiently. Additionally, a spatiotemporal attention (ST-Attention) mechanism is designed to facilitate transmitting information from the ST-Encoder to the ST-Decoder, which can solve the long-term dependency problem. We demonstrate the proposed CRRN outperforms the other conventional models in anomaly detection. Moreover, we show the discriminative power of the anomaly map decomposed by the proposed CRRN through the printer defect classification.

[16]  arXiv:1908.08245 [pdf, ps, other]
Title: Distributed Cooperative Online Estimation With Random Observation Matrices, Communication Graphs and Time-Delays
Authors: Jiexiang Wang, Tao Li
Comments: 38 pages
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG); Systems and Control (eess.SY)

We analyze convergence of distributed cooperative online estimation algorithms by a network of multiple nodes via information exchanging in an uncertain environment. Each node has a linear observation of an unknown parameter with randomly time-varying observation matrices. The underlying communication network is modeled by a sequence of random digraphs and is subjected to nonuniform random time-varying delays in channels. Each node runs an online estimation algorithm consisting of a consensus term taking a weighted sum of its own estimate and delayed estimates of neighbors, and an innovation term processing its own new measurement at each time step. By stochastic time-varying system, martingale convergence theories and the binomial expansion of random matrix products, we transform the convergence analysis of the algorithm into that of the mathematical expectation of random matrix products. Firstly, for the delay-free case, we show that the algorithm gains can be designed properly such that all nodes' estimates converge to the real parameter in mean square and almost surely if the observation matrices and communication graphs satisfy the stochastic spatial-temporal persistence of excitation condition. Especially, this condition holds for Markovian switching communication graphs and observation matrices, if the stationary graph is balanced with a spanning tree and the measurement model is spatially-temporally jointly observable. Secondly, for the case with time-delays, we introduce delay matrices to model the random time-varying communication delays between nodes, and propose a mean square convergence condition, which quantitatively shows the intensity of spatial-temporal persistence of excitation to overcome time-delays.

[17]  arXiv:1908.08251 [pdf, other]
Title: Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation
Comments: Submitted to SPIE Medical Imaging 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.

[18]  arXiv:1908.08254 [pdf, other]
Title: Motion correction of dynamic contrast enhanced MRI of the liver
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Motion correction of dynamic contrast enhanced magnetic resonance images (DCE-MRI) is a challenging task, due to changes in image appearance. In this study a groupwise registration, using a principle component analysis (PCA) based metric,1 is evaluated for clinical DCE MRI of the liver. The groupwise registration transforms the images to a common space, rather than to a reference volume as conventional pairwise methods do, and computes the similarity metric on all volumes simultaneously. This groupwise registration method is compared to a pairwise approach using a mutual information metric. Clinical DCE MRI of the abdomen of eight patients were included. Per patient one lesion in the liver was manually segmented in all temporal images (N=16). The registered images were compared for accuracy, spatial and temporal smoothness after transformation, and lesion volume change. Compared to a pairwise method or no registration, groupwise registration provided better alignment. In our recently started clinical study groupwise registered clinical DCE MRI of the abdomen of nine patients were scored by three radiologists. Groupwise registration increased the assessed quality of alignment. The gain in reading time for the radiologist was estimated to vary from no difference to almost a minute. A slight increase in reader confidence was also observed. Registration had no added value for images with little motion. In conclusion, the groupwise registration of DCE MR images results in better alignment than achieved by pairwise registration, which is beneficial for clinical assessment.

[19]  arXiv:1908.08294 [pdf, other]
Title: Robustly segmenting quadriceps muscles of ultra-endurance athletes with weakly supervised U-Net
Comments: MIDL 2019 [arXiv:1907.08612]
Subjects: Image and Video Processing (eess.IV)

In this study, segmentation of quadriceps muscle heads of ultra-endurance athletes was done using a multi-atlas segmentation and corrective leaning framework where the registration based multi-atlas segmentation step was replaced with weakly supervised U-Net. For the case with remarkably different morphology, our method produced improved accuracy, while reduced significantly the computation time.

[20]  arXiv:1908.08307 [pdf, other]
Title: Image Colorization By Capsule Networks
Authors: Gökhan Özbulak
Comments: Accepted to New Trends in Image Restoration and Enhancement(NTIRE) Workshop at CVPR 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

In this paper, a simple topology of Capsule Network (CapsNet) is investigated for the problem of image colorization. The generative and segmentation capabilities of the original CapsNet topology, which is proposed for image classification problem, is leveraged for the colorization of the images by modifying the network as follows:1) The original CapsNet model is adapted to map the grayscale input to the output in the CIE Lab colorspace, 2) The feature detector part of the model is updated by using deeper feature layers inherited from VGG-19 pre-trained model with weights in order to transfer low-level image representation capability to this model, 3) The margin loss function is modified as Mean Squared Error (MSE) loss to minimize the image-to-imagemapping. The resulting CapsNet model is named as Colorizer Capsule Network (ColorCapsNet).The performance of the ColorCapsNet is evaluated on the DIV2K dataset and promising results are obtained to investigate Capsule Networks further for image colorization problem.

[21]  arXiv:1908.08314 [pdf, other]
Title: LEAP nets for power grid perturbations
Journal-ref: ESANN, Apr 2019, Bruges, Belgium
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG); Machine Learning (stat.ML)

We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architeture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements a form of transfer learning, permitting to train on a few source domains, then generalize to new target domains, without learning on any example of that domain. We evaluate the viability of this technique to rapidly assess cu-rative actions that human operators take in emergency situations, using real historical data, from the French high voltage power grid.

[22]  arXiv:1908.08329 [pdf, other]
Title: Sequential Rib Labeling and Segmentation in Chest X-Ray using Mask R-CNN
Comments: MIDL 2019 [arXiv:1907.08612]
Subjects: Image and Video Processing (eess.IV)

Mask R-CNN is a state-of-the-art network architecture for the detection and segmentation of object instances in the computer vision domain. In this contribution, it is used to localize, label and segment individual ribs in anterior-posterior chest X-ray images. For this purpose, several extensions have been made to the original architecture, in order to address the specific challenges of this application. This includes the use of rib specific networks, facilitating dedicated anchor boxes sampled from a training set, as well as a sequential processing of all ribs. Here, the segmentation result of the upper neighbor rib is used as additional input to the network. This approach is the first addressing both rib segmentation and anatomical labeling in chest radiographs. The results are comparable or even better than existing methods aiming only at segmentation.

[23]  arXiv:1908.08380 [pdf, other]
Title: Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting
Comments: 10 pages, 10 figures, Proceedings of the Neuro-inspired Computational Elements Workshop (NICE '19), March 26-28, 2019, Albany, NY, USA
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Machine Learning (stat.ML)

Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While these networks are increasingly applied to nontrivial forecasting tasks, there is a need for comprehensive performance analysis of deep reservoirs. In this work, we study the influence of partitioning neurons given a budget and the effect of parallel reservoir pathways across different datasets exhibiting multi-scale and nonlinear dynamics.

[24]  arXiv:1908.08431 [pdf, other]
Title: Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning
Comments: Aceppted at SASHIMI2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Medical Physics (physics.med-ph)

The ability to synthesise Computed Tomography images - commonly known as pseudo CT, or pCT - from MRI input data is commonly assessed using an intensity-wise similarity, such as an L2-norm between the ground truth CT and the pCT. However, given that the ultimate purpose is often to use the pCT as an attenuation map ($\mu$-map) in Positron Emission Tomography Magnetic Resonance Imaging (PET/MRI), minimising the error between pCT and CT is not necessarily optimal. The main objective should be to predict a pCT that, when used as $\mu$-map, reconstructs a pseudo PET (pPET) which is as close as possible to the gold standard PET. To this end, we propose a novel multi-hypothesis deep learning framework that generates pCTs by minimising a combination of the pixel-wise error between pCT and CT and a proposed metric-loss that itself is represented by a convolutional neural network (CNN) and aims to minimise subsequent PET residuals. The model is trained on a database of 400 paired MR/CT/PET image slices. Quantitative results show that the network generates pCTs that seem less accurate when evaluating the Mean Absolute Error on the pCT (69.68HU) compared to a baseline CNN (66.25HU), but lead to significant improvement in the PET reconstruction - 115a.u. compared to baseline 140a.u.

[25]  arXiv:1908.08466 [pdf, other]
Title: U-Net Training with Instance-Layer Normalization
Comments: 8 pages, 3 figures, accepted by MICCAI-MMMI 2019 workshop
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Normalization layers are essential in a Deep Convolutional Neural Network (DCNN). Various normalization methods have been proposed. The statistics used to normalize the feature maps can be computed at batch, channel, or instance level. However, in most of existing methods, the normalization for each layer is fixed. Batch-Instance Normalization (BIN) is one of the first proposed methods that combines two different normalization methods and achieve diverse normalization for different layers. However, two potential issues exist in BIN: first, the Clip function is not differentiable at input values of 0 and 1; second, the combined feature map is not with a normalized distribution which is harmful for signal propagation in DCNN. In this paper, an Instance-Layer Normalization (ILN) layer is proposed by using the Sigmoid function for the feature map combination, and cascading group normalization. The performance of ILN is validated on image segmentation of the Right Ventricle (RV) and Left Ventricle (LV) using U-Net as the network architecture. The results show that the proposed ILN outperforms previous traditional and popular normalization methods with noticeable accuracy improvements for most validations, supporting the effectiveness of the proposed ILN.

[26]  arXiv:1908.08476 [pdf]
Title: WiFi Motion Detection: A Study into Efficacy and Classification
Subjects: Signal Processing (eess.SP)

WiFi and security pose both an issue and act as a growing presence in everyday life. Today's motions detection implementations are severely lacking in the areas of secrecy, scope, and cost. To combat this problem, we aim to develop a motion detection system that utilizes WiFi Channel State Information (CSI), which describes how a wireless signal propagates from the transmitter to the receiver. The goal of this study is to develop a real-time motion detection and classification system that is discreet, cost-effective, and easily implementable. The system would only require an Ubuntu laptop with an Intel Ultimate N WiFi Link 5300 and a standard router. The system will be developed in two parts: (1) a robust system to track CSI variations in real-time, and (2) an algorithm to classify the motion. The system used to track CSI variance in real-time was completed in August 2018. Initial results show that introduction of motion to a previously motionless area is detected with high confidence. We present the development of (1) anomaly detection, utilizing the moving average filter implemented in the initial program and/or unsupervised machine learning, and (2) supervised machine learning algorithms to classify a set of simple motions using a proposed feature extraction methods. Lastly, classification methods such as Decision Tree, Naive Bayes, and Long Short-Term Memory can be used to classify basic actions regardless of speed, location, or orientation.

Cross-lists for Fri, 23 Aug 19

[27]  arXiv:1810.11474 (cross-list from nlin.CD) [pdf, other]
Title: Generating Multi-Scroll Chua's Attractors via Simplified Piecewise-Linear Chua's Diode
Comments: 14 pages, 15 figures
Journal-ref: IEEE Transactions on Circuits and Systems I: Regular Papers, 2019
Subjects: Chaotic Dynamics (nlin.CD); Signal Processing (eess.SP)

High implementation complexity of multi-scroll circuit is a bottleneck problem in real chaos-based communication. Especially, in multi-scroll Chua's circuit, the simplified implementation of piecewise-linear resistors with multiple segments is difficult due to their intricate irregular breakpoints and slopes. To solve the challenge, this paper presents a systematic scheme for synthesizing a Chua's diode with multi-segment piecewise-linearity, which is achieved by cascading even-numbered passive nonlinear resistors with odd-numbered ones via a negative impedance converter. The traditional voltage mode op-amps are used to implement nonlinear resistors. As no extra DC bias voltage is employed, the scheme can be implemented by much simpler circuits. The voltage-current characteristics of the obtained Chua's diode are analyzed theoretically and verified by numerical simulations. Using the Chua's diode and a second-order active Sallen-Key high-pass filter, a new inductor-free Chua's circuit is then constructed to generate multi-scroll chaotic attractors. Different number of scrolls can be generated by changing the number of passive nonlinear resistor cells or adjusting two coupling parameters. Besides, the system can be scaled by using different power supplies, satisfying the low-voltage low-power requirement of integrated circuit design. The circuit simulations and hardware experiments both confirmed the feasibility of the designed system.

[28]  arXiv:1908.08098 (cross-list from stat.ML) [pdf, ps, other]
Title: BRIDGE: Byzantine-resilient Decentralized Gradient Descent
Comments: 18 pages, 1 figure, 1 table; preprint of a conference paper
Subjects: Machine Learning (stat.ML); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Signal Processing (eess.SP)

Decentralized optimization techniques are increasingly being used to learn machine learning models from data distributed over multiple locations without gathering the data at any one location. Unfortunately, methods that are designed for faultless networks typically fail in the presence of node failures. In particular, Byzantine failures---corresponding to the scenario in which faulty/compromised nodes are allowed to arbitrarily deviate from an agreed-upon protocol---are the hardest to safeguard against in decentralized settings. This paper introduces a Byzantine-resilient decentralized gradient descent (BRIDGE) method for decentralized learning that, when compared to existing works, is more efficient and scalable in higher-dimensional settings and that is deployable in networks having topologies that go beyond the star topology. The main contributions of this work include theoretical analysis of BRIDGE for strongly convex learning objectives and numerical experiments demonstrating the efficacy of BRIDGE for both convex and nonconvex learning tasks.

[29]  arXiv:1908.08160 (cross-list from cs.SD) [pdf]
Title: Sound Localization and Separation in Three-dimensional Space Using a Single Microphone with a Metamaterial Enclosure
Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS); Applied Physics (physics.app-ph)

Conventional approaches to sound localization and separation are based on microphone arrays in artificial systems. Inspired by the selective perception of human auditory system, we design a multi-source listening system which can separate simultaneous overlapping sounds and localize the sound sources in three-dimensional space, using only a single microphone with a metamaterial enclosure. The enclosure modifies the frequency response of the microphone in a direction-dependent way by giving each direction a signature. Thus, the information about the location and audio content of sound sources can be experimentally reconstructed from the modulated mixed signals using compressive sensing algorithm. Owing to the low computational complexity of the proposed reconstruction algorithm, the designed system can also be applied in source identification and tracking. The effectiveness of the system in multiple real scenarios has been proved through multiple random listening tests. The proposed metamaterial-based single-sensor listening system opens a new way of sound localization and separation, which can be applied to intelligent scene monitoring and robot audition.

[30]  arXiv:1908.08185 (cross-list from cs.CV) [pdf, other]
Title: Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion
Comments: Accepted by ICCV 2019. Project homepage: this http URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Image and Video Processing (eess.IV)

In this paper, we propose a novel projector-camera system for practical and low-cost acquisition of a dense object 3D model with the spectral reflectance property. In our system, we use a standard RGB camera and leverage an off-the-shelf projector as active illumination for both the 3D reconstruction and the spectral reflectance estimation. We first reconstruct the 3D points while estimating the poses of the camera and the projector, which are alternately moved around the object, by combining multi-view structured light and structure-from-motion (SfM) techniques. We then exploit the projector for multispectral imaging and estimate the spectral reflectance of each 3D point based on a novel spectral reflectance estimation model considering the geometric relationship between the reconstructed 3D points and the estimated projector positions. Experimental results on several real objects demonstrate that our system can precisely acquire a dense 3D model with the full spectral reflectance property using off-the-shelf devices.

[31]  arXiv:1908.08279 (cross-list from astro-ph.IM) [pdf, ps, other]
Title: Contour Detection in Cassini ISS images based on Hierarchical Extreme Learning Machine and Dense Conditional Random Field
Subjects: Instrumentation and Methods for Astrophysics (astro-ph.IM); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)

In Cassini ISS (Imaging Science Subsystem) images, contour detection is often performed on disk-resolved object to accurately locate their center. Thus, the contour detection is a key problem. Traditional edge detection methods, such as Canny and Roberts, often extract the contour with too much interior details and noise. Although the deep convolutional neural network has been applied successfully in many image tasks, such as classification and object detection, it needs more time and computer resources. In the paper, a contour detection algorithm based on H-ELM (Hierarchical Extreme Learning Machine) and DenseCRF (Dense Conditional Random Field) is proposed for Cassini ISS images. The experimental results show that this algorithm's performance is better than both traditional machine learning methods such as SVM, ELM and even deep convolutional neural network. And the extracted contour is closer to the actual contour. Moreover, it can be trained and tested quickly on the general configuration of PC, so can be applied to contour detection for Cassini ISS images.

[32]  arXiv:1908.08338 (cross-list from cs.NI) [pdf, other]
Title: Centralized and Distributed Machine Learning-Based QoT Estimation for Sliceable Optical Networks
Comments: accepted for presentation at the IEEE GLOBECOM 2019
Subjects: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG); Signal Processing (eess.SP)

Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G's diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work we examine the ML-based Quality-of-Transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different QoT requirement. We examine ML-based QoT frameworks with the aim of finding QoT model/s that are fine-tuned according to the diverse QoT requirements. Centralized and distributed frameworks are examined and compared according to their accuracy and training time. We show that the distributed QoT models outperform the centralized QoT model, especially as the number of diverse QoT requirements increases.

[33]  arXiv:1908.08453 (cross-list from cs.CV) [pdf, other]
Title: Noise Flow: Noise Modeling with Conditional Normalizing Flows
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)

Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a coarse approximation of real sensor noise. This paper introduces Noise Flow, a powerful and accurate noise model based on recent normalizing flow architectures. Noise Flow combines well-established basic parametric noise models (e.g., signal-dependent noise) with the flexibility and expressiveness of normalizing flow networks. The result is a single, comprehensive, compact noise model containing fewer than 2500 parameters yet able to represent multiple cameras and gain factors. Noise Flow dramatically outperforms existing noise models, with 0.42 nats/pixel improvement over the camera-calibrated noise level functions, which translates to 52% improvement in the likelihood of sampled noise. Noise Flow represents the first serious attempt to go beyond simple parametric models to one that leverages the power of deep learning and data-driven noise distributions.

[34]  arXiv:1908.08485 (cross-list from cs.RO) [pdf]
Title: Simulation Model of Two-Robot Cooperation in Common Operating Environment
Comments: 6 pages, 6 figures
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Systems and Control (eess.SY)

The article considers a simulation modelling problem related to the chess game process occurring between two three-tier manipulators. The objective of the game construction lies in developing the procedure of effective control of the autonomous manipulator robots located in a common operating environment. The simulation model is a preliminary stage of building a natural complex that would provide cooperation of several manipulator robots within a common operating environment. The article addresses issues of training and research.

[35]  arXiv:1908.08505 (cross-list from cs.MM) [pdf, other]
Title: ColorNet -- Estimating Colorfulness in Natural Images
Comments: Accepted to IEEE International Conference on Image Processing (ICIP) 2019
Subjects: Multimedia (cs.MM); Graphics (cs.GR); Machine Learning (cs.LG); Image and Video Processing (eess.IV)

Measuring the colorfulness of a natural or virtual scene is critical for many applications in image processing field ranging from capturing to display. In this paper, we propose the first deep learning-based colorfulness estimation metric. For this purpose, we develop a color rating model which simultaneously learns to extracts the pertinent characteristic color features and the mapping from feature space to the ideal colorfulness scores for a variety of natural colored images. Additionally, we propose to overcome the lack of adequate annotated dataset problem by combining/aligning two publicly available colorfulness databases using the results of a new subjective test which employs a common subset of both databases. Using the obtained subjectively annotated dataset with 180 colored images, we finally demonstrate the efficacy of our proposed model over the traditional methods, both quantitatively and qualitatively.

Replacements for Fri, 23 Aug 19

[36]  arXiv:1809.08066 (replaced) [pdf, other]
Title: Cross-Gramian-Based Dominant Subspaces
Subjects: Optimization and Control (math.OC); Systems and Control (eess.SY); Numerical Analysis (math.NA)
[37]  arXiv:1810.03900 (replaced) [pdf, other]
Title: Iterative Decision Feedback Equalization Using Online Prediction
Comments: 8 pages, 9 figures, paper submitted to IEEE
Subjects: Signal Processing (eess.SP)
[38]  arXiv:1810.11950 (replaced) [pdf, other]
Title: Passivity-Based Analysis of Sampled and Quantized Control Implementations
Subjects: Optimization and Control (math.OC); Systems and Control (eess.SY)
[39]  arXiv:1811.04769 (replaced) [pdf, other]
Title: ExcitNet vocoder: A neural excitation model for parametric speech synthesis systems
Comments: Accepted to the conference of EUSIPCO 2019. arXiv admin note: text overlap with arXiv:1811.03311
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
[40]  arXiv:1902.09686 (replaced) [pdf, ps, other]
Title: Maximum Marginal Likelihood Estimation of Phase Connections in Power Distribution Systems
Comments: Several updates in this version. First, more comprehensive and difficult numerical tests are added, in which we compare our method with existing methods on different test feeders, with missing measurements and erroneous models. Second, we clarify and re-write theoretical derivations and assumptions so that it is easier to understand
Subjects: Systems and Control (eess.SY)
[41]  arXiv:1904.05742 (replaced) [pdf, other]
Title: One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization
Comments: Interspeech 2019
Subjects: Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS); Machine Learning (stat.ML)
[42]  arXiv:1904.06063 (replaced) [pdf, other]
Title: Building a mixed-lingual neural TTS system with only monolingual data
Comments: To appear in INTERSPEECH 2019
Subjects: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[43]  arXiv:1904.07110 (replaced) [pdf, ps, other]
Title: Trick or Heat? Manipulating Critical Temperature-Based Control Systems Using Rectification Attacks
Comments: Accepted at the ACM Conference on Computer and Communications Security (CCS), 2019
Subjects: Cryptography and Security (cs.CR); Systems and Control (eess.SY)
[44]  arXiv:1906.02031 (replaced) [pdf, ps, other]
Title: OctopusNet: A Deep Learning Segmentation Network for Multi-modal Medical Images
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
[45]  arXiv:1906.07644 (replaced) [pdf, other]
Title: Towards White-box Benchmarks for Algorithm Control
Comments: 8 pages, 9 figures
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY); Machine Learning (stat.ML)
[46]  arXiv:1906.08839 (replaced) [pdf, other]
Title: Autonomous Navigation of MAVs in Unknown Cluttered Environments
Subjects: Robotics (cs.RO); Systems and Control (eess.SY)
[47]  arXiv:1907.10275 (replaced) [pdf, other]
Title: All-Analog Adaptive Equalizer for Coherent Data Center Interconnects
Subjects: Signal Processing (eess.SP)
[48]  arXiv:1908.06319 (replaced) [pdf, other]
Title: Locally Linear Embedding and fMRI feature selection in psychiatric classification
Authors: Gagan Sidhu
Comments: Main article is 10 pages. Supplementary Information is 15 pages and includes figures/results for six additional datasets, awith performance plots (as a function of dimensionality 'd'), proportion(s) of brain regions defined by the respective atlases, subject ID partitioning for all eleven datasets. statmaps_datasets.zip and cobre_schiz_grph.zip are on supplementary material of journal website
Journal-ref: IEEE Journal of Translational Engineering in Health & Medicine 7:10, 2019
Subjects: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Machine Learning (stat.ML)
[49]  arXiv:1908.06933 (replaced) [pdf, other]
Title: Deep Active Lesion Segmentation
Comments: Accepted to Machine Learning in Medical Imaging (MLMI 2019)
Journal-ref: MLMI 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[50]  arXiv:1908.06948 (replaced) [pdf, other]
Title: Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography
Subjects: Image and Video Processing (eess.IV)
[51]  arXiv:1908.07409 (replaced) [pdf, other]
Title: Onset detection: A new approach to QBH system
Comments: 30 pages, 26 figures
Subjects: Applications (stat.AP); Information Retrieval (cs.IR); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[52]  arXiv:1908.07934 (replaced) [pdf, other]
Title: Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
Comments: 5pages, 6figures, 14conference
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG)
[53]  arXiv:1908.07957 (replaced) [pdf, other]
Title: DISCo for the CIA: Deep learning, Instance Segmentation, and Correlations for Calcium Imaging Analysis
Subjects: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
[ total of 53 entries: 1-53 ]
[ showing up to 2000 entries per page: fewer | more ]

Disable MathJax (What is MathJax?)

Links to: arXiv, form interface, find, eess, recent, 1908, contact, help  (Access key information)