arXiv subjects

Reza Arablouei

Publications and source records attributed to Reza Arablouei.

At least 37 records · Page 2Linked to original sources

arXiv2023

Efficient Privacy-Preserved Processing of Multimodal Data for Vehicular Traffic Analysis

We estimate vehicular traffic states from multimodal data collected by single-loop detectors while preserving the privacy of the individual vehicles contributing to the data. To this end, we propose a novel hybrid differential privacy (DP) approach that utilizes minimal randomization to preserve privacy by taking advantage of the relevant traffic state dynamics and the concept of DP sensitivity. Through theoretical analysis and experiments with real-world data, we show that the proposed approach significantly outperforms the related baseline non-private and private approaches in terms of accuracy and privacy preservation.

cs.CR↗

arXiv2022

Design and Analysis of Clustering-based Joint Channel Estimation and Signal Detection for NOMA

We propose a joint channel estimation and signal detection approach for the uplink non-orthogonal multiple access (NOMA) using unsupervised machine learning. We apply a Gaussian mixture model (GMM) to cluster the received signals, and accordingly optimize the decision regions to enhance the symbol error rate (SER) performance. We show that, when the received powers of the users are sufficiently different, the proposed clustering-based approach achieves an SER performance on a par with that of the conventional maximum-likelihood detector (MLD) with full channel state information (CSI). We study the tradeoff between the accuracy of the proposed approach and the blocklength, as the accuracy of the utilized clustering algorithm depends on the number of symbols available at the receiver. We provide a comprehensive performance analysis of the proposed approach and derive a theoretical bound on its SER performance. Our simulation results corroborate the effectiveness of the proposed approach and verify that the calculated theoretical bound can predict the SER performance of the proposed approach well. We further explore the application of the proposed approach to a practical grant-free NOMA scenario, and show that its performance is very close to that of the optimal MLD with full CSI, which usually requires long pilot sequences.

cs.IT↗

arXiv2022

In-situ animal behavior classification using knowledge distillation and fixed-point quantization

We explore the use of knowledge distillation (KD) for learning compact and accurate models that enable classification of animal behavior from accelerometry data on wearable devices. To this end, we take a deep and complex convolutional neural network, known as residual neural network (ResNet), as the teacher model. ResNet is specifically designed for multivariate time-series classification. We use ResNet to distill the knowledge of animal behavior classification datasets into soft labels, which consist of the predicted pseudo-probabilities of every class for each datapoint. We then use the soft labels to train our significantly less complex student models, which are based on the gated recurrent unit (GRU) and multilayer perceptron (MLP). The evaluation results using two real-world animal behavior classification datasets show that the classification accuracy of the student GRU-MLP models improves appreciably through KD, approaching that of the teacher ResNet model. To further reduce the computational and memory requirements of performing inference using the student models trained via KD, we utilize dynamic fixed-point quantization (DQ) through an appropriate modification of the computational graph of the considered models. We implement both unquantized and quantized versions of the developed KD-based models on the embedded systems of our purpose-built collar and ear tag devices to classify animal behavior in situ and in real time. Our evaluations corroborate the effectiveness of KD and DQ in improving the accuracy and efficiency of in-situ animal behavior classification.

cs.LG↗

arXiv2022

Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models, e.g., DGCNN, PointNet++, on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability. The code and data will be available upon publishing.

cs.CV↗

arXiv2022

Animal behavior classification via deep learning on embedded systems

We develop an end-to-end deep-neural-network-based algorithm for classifying animal behavior using accelerometry data on the embedded system of an artificial intelligence of things (AIoT) device installed in a wearable collar tag. The proposed algorithm jointly performs feature extraction and classification utilizing a set of infinite-impulse-response (IIR) and finite-impulse-response (FIR) filters together with a multilayer perceptron. The utilized IIR and FIR filters can be viewed as specific types of recurrent and convolutional neural network layers, respectively. We evaluate the performance of the proposed algorithm via two real-world datasets collected from total eighteen grazing beef cattle using collar tags. The results show that the proposed algorithm offers good intra- and inter-dataset classification accuracy and outperforms its closest contenders including two state-of-the-art convolutional-neural-network-based time-series classification algorithms, which are significantly more complex. We implement the proposed algorithm on the embedded system of the utilized collar tags' AIoT device to perform in-situ classification of animal behavior. We achieve real-time in-situ behavior inference from accelerometry data without imposing any strain on the available computational, memory, or energy resources of the embedded system.

cs.LG↗

arXiv2022

Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data

In this paper, we examine the use of data from multiple sensing modes, i.e., accelerometry and global navigation satellite system (GNSS), for classifying animal behavior. We extract three new features from the GNSS data, namely, distance from water point, median speed, and median estimated horizontal position error. We combine the information available from the accelerometry and GNSS data via two approaches. The first approach is based on concatenating the features extracted from both sensor data and feeding the concatenated feature vector into a multi-layer perceptron (MLP) classifier. The second approach is based on fusing the posterior probabilities predicted by two MLP classifiers. The input to each classifier is the features extracted from the data of one sensing mode. We evaluate the performance of the developed multimodal animal behavior classification algorithms using two real-world datasets collected via smart cattle collar tags and ear tags. The leave-one-animal-out cross-validation results show that both approaches improve the classification performance appreciably compared with using data of only one sensing mode. This is more notable for the infrequent but important behaviors of walking and drinking. The algorithms developed based on both approaches require little computational and memory resources hence are suitable for implementation on embedded systems of our collar tags and ear tags. However, the multimodal animal behavior classification algorithm based on posterior probability fusion is preferable to the one based on feature concatenation as it delivers better classification accuracy, has less computational and memory complexity, is more robust to sensor data failure, and enjoys better modularity.

cs.LG↗

arXiv2022

Decentralized Optimization with Distributed Features and Non-Smooth Objective Functions

We develop a new consensus-based distributed algorithm for solving learning problems with feature partitioning and non-smooth convex objective functions. Such learning problems are not separable, i.e., the associated objective functions cannot be directly written as a summation of agent-specific objective functions. To overcome this challenge, we redefine the underlying optimization problem as a dual convex problem whose structure is suitable for distributed optimization using the alternating direction method of multipliers (ADMM). Next, we propose a new method to solve the minimization problem associated with the ADMM update step that does not rely on any conjugate function. Calculating the relevant conjugate functions may be hard or even unfeasible, especially when the objective function is non-smooth. To obviate computing any conjugate function, we solve the optimization problem associated with each ADMM iteration in the dual domain utilizing the block coordinate descent algorithm. Unlike the existing related algorithms, the proposed algorithm is fully distributed and does away with the conjugate of the objective function. We prove theoretically that the proposed algorithm attains the optimal centralized solution. We also confirm its network-wide convergence via simulations.

eess.SP↗

arXiv2021

Animal Behavior Classification via Accelerometry Data and Recurrent Neural Networks

We study the classification of animal behavior using accelerometry data through various recurrent neural network (RNN) models. We evaluate the classification performance and complexity of the considered models, which feature long short-time memory (LSTM) or gated recurrent unit (GRU) architectures with varying depths and widths, using four datasets acquired from cattle via collar or ear tags. We also include two state-of-the-art convolutional neural network (CNN)-based time-series classification models in the evaluations. The results show that the RNN-based models can achieve similar or higher classification accuracy compared with the CNN-based models while having less computational and memory requirements. We also observe that the models with GRU architecture generally outperform the ones with LSTM architecture in terms of classification accuracy despite being less complex. A single-layer uni-directional GRU model with 64 hidden units appears to offer a good balance between accuracy and complexity making it suitable for implementation on edge/embedded devices.

cs.LG↗

arXiv2020

Clustering-based Joint Channel Estimation and Signal Detection for Grant-free NOMA

We propose a joint channel estimation and signal detection technique for the uplink non-orthogonal multiple access using an unsupervised clustering approach. We apply the Gaussian mixture model to cluster received signals and accordingly optimize the decision regions to enhance the symbol error rate (SER). We show that when the received powers of the users are sufficiently different, the proposed clustering-based approach with no channel state information (CSI) at the receiver achieves an SER performance similar to that of the conventional maximum likelihood detector with full CSI. Since the accuracy of the utilized clustering algorithm depends on the number of the data points available at the receiver, the proposed technique delivers a tradeoff between the accuracy and block length.

eess.SP↗

arXiv2018

Fusing Multiple Multiband Images

We consider the problem of fusing an arbitrary number of multiband, i.e., panchromatic, multispectral, or hyperspectral, images belonging to the same scene. We use the well-known forward observation and linear mixture models with Gaussian perturbations to formulate the maximum-likelihood estimator of the endmember abundance matrix of the fused image. We calculate the Fisher information matrix for this estimator and examine the conditions for the uniqueness of the estimator. We use a vector total-variation penalty term together with nonnegativity and sum-to-one constraints on the endmember abundances to regularize the derived maximum-likelihood estimation problem. The regularization facilitates exploiting the prior knowledge that natural images are mostly composed of piecewise smooth regions with limited abrupt changes, i.e., edges, as well as coping with potential ill-posedness of the fusion problem. We solve the resultant convex optimization problem using the alternating direction method of multipliers. We utilize the circular convolution theorem in conjunction with the fast Fourier transform to alleviate the computational complexity of the proposed algorithm. Experiments with multiband images constructed from real hyperspectral datasets reveal the superior performance of the proposed algorithm in comparison with the state-of-the-art algorithms, which need to be used in tandem to fuse more than two multiband images.

cs.CV↗

arXiv2017

Multi-mode Tracking of a Group of Mobile Agents

We consider the problem of tracking a group of mobile nodes with limited available computational and energy resources given noisy RSSI measurements and position estimates from group members. The multilateration solutions are known for energy efficiency. However, these solutions are not directly applicable to dynamic grouping scenarios where neighbourhoods and resource availability may frequently change. Existing algorithms such as cluster-based GPS duty-cycling, individual-based tracking, and multilateration-based tracking can only partially deal with the challenges of dynamic grouping scenarios. To cope with these challenges in an effective manner, we propose a new group-based multi-mode tracking algorithm. The proposed algorithm takes the topological structure of the group as well as the availability of the resources into consideration and decides the best solution at any particular time instance. We consider a clustering approach where a cluster head coordinates the usage of resources among the cluster members. We evaluate the energy-accuracy trade-off of the proposed algorithm for various fixed sampling intervals. The evaluation is based on the 2D position tracks of 40 nodes generated using Reynolds' flocking model. For a given energy budget, the proposed algorithm reduces the mean tracking error by up to $20\%$ in comparison to the existing energy-efficient cooperative algorithms. Moreover, the proposed algorithm is as accurate as the individual-based tracking while using almost half the energy.

cs.IT↗

arXiv2017

RSSI-Based Self-Localization with Perturbed Anchor Positions

We consider the problem of self-localization by a resource-constrained mobile node given perturbed anchor position information and distance estimates from the anchor nodes. We consider normally-distributed noise in anchor position information. The distance estimates are based on the log-normal shadowing path-loss model for the RSSI measurements. The available solutions to this problem are based on complex and iterative optimization techniques such as semidefinite programming or second-order cone programming, which are not suitable for resource-constrained environments. In this paper, we propose a closed-form weighted least-squares solution. We calculate the weights by taking into account the statistical properties of the perturbations in both RSSI and anchor position information. We also estimate the bias of the proposed solution and subtract it from the proposed solution. We evaluate the performance of the proposed algorithm considering a set of arbitrary network topologies in comparison to an existing algorithm that is based on a similar approach but only accounts for perturbations in the RSSI measurements. We also compare the results with the corresponding Cramer-Rao lower bound. Our experimental evaluation shows that the proposed algorithm can substantially improve the localization performance in terms of both root mean square error and bias.

cs.IT↗

arXiv2017

WLS-Based Self-Localization Using Perturbed Anchor Positions and RSSI Measurements

We consider the problem of self-localization by a resource-constrained node within a network given radio signal strength indicator (RSSI) measurements from a set of anchor nodes where the RSSI measurements as well as the anchor position information are subject to perturbation. In order to achieve a computationally efficient estimate for the unknown position, we minimize a weighted sum-square-distance-error cost function in an iterative fashion utilizing the gradient-descent method. We calculate the weights in the cost function by taking into account perturbations in both RSSI measurements and anchor node position information while assuming normal distribution for the perturbations in the anchor node position information and log-normal distribution for the RSSI-induced distance estimates. The latter assumption is due to considering the log-distance path-loss model with normally-distributed perturbations for the RSSI measurements in the logarithmic scale. We also derive the Cramer-Rao lower bound associated with the considered position estimation problem. We evaluate the performance of the proposed algorithm considering various arbitrary network topologies and compare it with an existing algorithm that is based on a similar approach but only accounts for perturbations in the RSSI measurements. The experimental results show that the proposed algorithm yields significant improvement in localization performance over the existing algorithm while maintaining its computational efficiency. This makes the proposed algorithm suitable for real-world applications where the information available about the positions of anchor nodes often suffer from uncertainty due to observational noise or error and the computational and energy resources of mobile nodes are limited, prohibiting the use of more sophisticated techniques such as those based on semidefinite or second-order cone programming.

cs.IT↗

arXiv2017

Fast and robust pushbroom hyperspectral imaging via DMD-based scanning

We describe a new pushbroom hyperspectral imaging device that has no macro moving part. The main components of the proposed hyperspectral imager are a digital micromirror device (DMD), a CMOS image sensor with no filter as the spectral sensor, a CMOS color (RGB) image sensor as the auxiliary image sensor, and a diffraction grating. Using the image sensor pair, the device can simultaneously capture hyperspectral data as well as RGB images of the scene. The RGB images captured by the auxiliary image sensor can facilitate geometric co-registration of the hyperspectral image slices captured by the spectral sensor. In addition, the information discernible from the RGB images can lead to capturing the spectral data of only the regions of interest within the scene. The proposed hyperspectral imaging architecture is cost-effective, fast, and robust. It also enables a trade-off between resolution and speed. We have built an initial prototype based on the proposed design. The prototype can capture a hyperspectral image datacube with a spatial resolution of 192x192 pixels and a spectral resolution of 500 bands in less than thirty seconds.

cs.CV↗

arXiv2016

Hyperspectral Image Recovery via Hybrid Regularization

Natural images tend to mostly consist of smooth regions with individual pixels having highly correlated spectra. This information can be exploited to recover hyperspectral images of natural scenes from their incomplete and noisy measurements. To perform the recovery while taking full advantage of the prior knowledge, we formulate a composite cost function containing a square-error data-fitting term and two distinct regularization terms pertaining to spatial and spectral domains. The regularization for the spatial domain is the sum of total-variation of the image frames corresponding to all spectral bands. The regularization for the spectral domain is the l1-norm of the coefficient matrix obtained by applying a suitable sparsifying transform to the spectra of the pixels. We use an accelerated proximal-subgradient method to minimize the formulated cost function. We analyze the performance of the proposed algorithm and prove its convergence. Numerical simulations using real hyperspectral images exhibit that the proposed algorithm offers an excellent recovery performance with a number of measurements that is only a small fraction of the hyperspectral image data size. Simulation results also show that the proposed algorithm significantly outperforms an accelerated proximal-gradient algorithm that solves the classical basis-pursuit denoising problem to recover the hyperspectral image.

cs.CV↗

arXiv2016

Fast Reconstruction Algorithm for Perturbed Compressive Sensing Based on Total Least-Squares and Proximal Splitting

We consider the problem of finding a sparse solution for an underdetermined linear system of equations when the known parameters on both sides of the system are subject to perturbation. This problem is particularly relevant to reconstruction in fully-perturbed compressive-sensing setups where both the projected measurements of an unknown sparse vector and the knowledge of the associated projection matrix are perturbed due to noise, error, mismatch, etc. We propose a new iterative algorithm for tackling this problem. The proposed algorithm utilizes the proximal-gradient method to find a sparse total least-squares solution by minimizing an l1-regularized Rayleigh-quotient cost function. We determine the step-size of the algorithm at each iteration using an adaptive rule accompanied by backtracking line search to improve the algorithm's convergence speed and preserve its stability. The proposed algorithm is considerably faster than a popular previously-proposed algorithm, which employs the alternating-direction method and coordinate-descent iterations, as it requires significantly fewer computations to deliver the same accuracy. We demonstrate the effectiveness of the proposed algorithm via simulation results.

eess.SY↗

arXiv2016

On the Asymptotic Bias of the Diffusion-Based Distributed Pareto Optimization

We revisit the asymptotic bias analysis of the distributed Pareto optimization algorithm developed based on the diffusion strategies. We propose an alternative way to analyze the asymptotic bias of this algorithm at small step-sizes and show that the asymptotic bias descends to zero with a linear dependence on the largest step-size parameter when this parameter is sufficiently small. In addition, through the proposed analytic approach, we provide an expression for the small-step-size asymptotic bias when a condition assumed jointly on the combination matrices and the step-sizes does not strictly hold. This is a likely scenario in practice, which has not been considered in the original paper that introduced the algorithm. Our methodology provides new insights into the inner workings of the diffusion Pareto optimization algorithm while being considerably less involved than the small-step-size asymptotic bias analysis presented in the original work. This is because we take advantage of the special eigenstructure of the composite combination matrix used in the algorithm without calling for any eigenspace decomposition or matrix inversion.

cs.DC↗

arXiv2015

On the Mean-Square Performance of the Constrained LMS Algorithm

The so-called constrained least mean-square algorithm is one of the most commonly used linear-equality-constrained adaptive filtering algorithms. Its main advantages are adaptability and relative simplicity. In order to gain analytical insights into the performance of this algorithm, we examine its mean-square performance and derive theoretical expressions for its transient and steady-state mean-square deviation. Our methodology is inspired by the principle of energy conservation in adaptive filters. Simulation results corroborate the accuracy of the derived formula.

eess.SY↗