Search

Reconfigurable intelligent surface (RIS) is pivotal for beyond 5G networks in regards to the surge demand for reliable communication in unmanned aerial vehicle (UAV) networks. This paper presents an innovative approach to maximize connectivity of UAV networks using RIS deployment and virtual partitioning, wherein an RIS is deployed to assist in the communications between an user-equipment (UE) and blocked UAVs. Closed-form (CF) expressions for signal-to-noise ratio (SNR) of the two-UAV setup are derived and validated. Then, an optimization problem is formulated to maximize network connectivity by optimizing the 3D deployment of the RIS and its partitioning subject to predefined quality-of-service (QoS) constraints. To tackle this problem, we propose a method of virtually partitioning the RIS given a fixed 3D location, such that the partition phase shifts are configured to create cascaded channels between the UE and the blocked two UAVs. Then, simulated-annealing (SA) method is used to find the 3D location of the RIS. Simulation results demonstrate that the proposed joint RIS deployment and partitioning framework can significantly improve network connectivity compared to benchmarks, including RIS-free and RIS with a single narrow-beam link., Comment: 6 pages, 5 figures, conference

This paper introduces a novel method to enhance the connectivity of multi-reconfigurable intelligent surface-assisted device-to-device networks, referred to as multi-RIS-assisted D2D networks, through a unique phase shift determination. The proposed method aims to optimize the power-domain array factor (PDAF), targeting specific azimuth angles of reliable user equipments (UEs) and enhancing network connectivity. We formulate an optimization problem that jointly optimizes RIS beamforming design, RIS-aided link selection, and RIS positioning. This problem is a mixed-integer non-binary programming. The optimization problem is divided into two sub-problems, which are solved individually and iteratively. The first sub-problem of RIS-aided link selection is solved using an efficient perturbation method while developing genetic algorithm (GA) to obtain RIS beamforming design. The GA optimizes the RIS phase shift to generate multiple RIS-aided narrowbeams that exhibit significant PDAF towards azimuth angles of interest while minimizing PDAF towards undesired azimuth angles. The second sub-problem of RIS positioning is addressed using the Adam optimizer. Numerical simulations verify the superiority of the proposed scheme in improving network connectivity compared to other schemes, including those utilizing distributed small RISs, each generating one RIS-aided link., Comment: 6 pages, 5 figures, conference

A reconfigurable intelligent surface (RIS) is composed of low-cost elements that manipulate the propagation environment from a transmitter by intelligently applying phase shifts to incoming signals before they are reflected. This paper explores a uni-polarized RIS with linear shape aimed at transmitting a common signal to multiple user equipments (UEs) spread across a wide angular region. To achieve uniform coverage, the uni-polarized RIS is designed to emit a broad and spectral-efficient beam featuring a spatially flat-like array factor, diverging from the conventional narrow beam approach. To achieve this objective, we start by deriving probabilistic lower and upper bounds for the average spectral efficiency (SE) delivered to the UEs. Leveraging the insights from the lower bound, we focus on optimizing the minimum value of the power domain array factor (PDAF) across a range of azimuth angles from \(-\frac{\pi}{2}\) to \(\frac{\pi}{2}\). We employ the continuous genetic algorithm (CGA) for this optimization task, aiming to improve the SE delivered to the UEs while also creating a wide beam. Extensive simulation experiments are carried out to assess the performance of the proposed code, focusing on key metrics such as the minimum and average values of the PDAF and the SE delivered to the UEs. Our findings demonstrate that the proposed code enhances the minimum SE delivered to the UEs while maintaining the desired attribute of a broad beam. This performance is notably superior to that of established codes, including the Barker, Frank, and Chu codes., Comment: 13 pages, 15 figures, Journal paper

Time series classification stands as a pivotal and intricate challenge across various domains, including finance, healthcare, and industrial systems. In contemporary research, there has been a notable upsurge in exploring feature extraction through random sampling. Unlike deep convolutional networks, these methods sidestep elaborate training procedures, yet they often necessitate generating a surplus of features to comprehensively encapsulate time series nuances. Consequently, some features may lack relevance to labels or exhibit multi-collinearity with others. In this paper, we propose a novel hierarchical feature selection method aided by ANOVA variance analysis to address this challenge. Through meticulous experimentation, we demonstrate that our method substantially reduces features by over 94% while preserving accuracy -- a significant advancement in the field of time series analysis and feature selection., Comment: 6 pages, 5 figures, IEEE Machine Learning and Signal processing 2024

This paper introduces an indoor localization method using fixed reflector objects within the environment, leveraging a base station (BS) equipped with Angle of Arrival (AoA) and Time of Arrival (ToA) measurement capabilities. The localization process includes two phases. In the offline phase, we identify effective reflector points within a specific region using significantly fewer test points than typical methods. In the online phase, we solve a maximization problem to locate users based on BS measurements and offline phase information. We introduce the reflectivity parameter (\(n_r\)), which quantifies the typical number of first-order reflection paths from the transmitter to the receiver, demonstrating its impact on localization accuracy. The log-scale accuracy ratio (\(R_a\)) is defined as the logarithmic function of the localization area divided by the localization ambiguity area, serving as an accuracy indicator. We show that in scenarios where the Signal-to-Noise Ratio (SNR) approaches infinity, without a line of sight (LoS) link, \(R_a\) is upper-bounded by \(n_r \log_{2}\left(1 + \frac{\mathrm{Vol}(\mathcal{S}_A)}{\mathrm{Vol}(\mathcal{S}_{\epsilon}(\mathcal{M}_s))}\right)\). Here, \(\mathrm{Vol}(\mathcal{S}_A)\) and \(\mathrm{Vol}(\mathcal{S}_{\epsilon}(\mathcal{M}_s))\) represent the areas of the localization region and the area containing all reflector points with a probability of at least \(1 - \epsilon\), respectively.

Reconfigurable intelligent surfaces (RISs) are expected to make future 6G networks more connected and resilient against node failures, due to their ability to introduce controllable phase-shifts onto impinging electromagnetic waves and impose link redundancy. Meanwhile, unmanned aerial vehicles (UAVs) are prone to failure due to limited energy, random failures, or targeted failures, which causes network disintegration that results in information delivery loss. In this paper, we show that the integration between UAVs and RISs for improving network connectivity is crucial. We utilize RISs to provide path diversity and alternative connectivity options for information flow from user equipments (UEs) to less critical UAVs by adding more links to the network, thereby making the network more resilient and connected. To that end, we first define the criticality of UAV nodes, which reflects the importance of some nodes over other nodes. We then employ the algebraic connectivity metric, which is adjusted by the reflected links of the RISs and their criticality weights, to formulate the problem of maximizing the network connectivity. Such problem is a computationally expensive combinatorial optimization. To tackle this problem, we propose a relaxation method such that the discrete scheduling constraint of the problem is relaxed and becomes continuous. Leveraging this, we propose two efficient solutions, namely semi-definite programming (SDP) optimization and perturbation heuristic, which both solve the problem in polynomial time. For the perturbation heuristic, we derive the lower and upper bounds of the algebraic connectivity obtained by adding new links to the network. Finally, we corroborate the effectiveness of the proposed solutions through extensive simulation experiments., Comment: 14 pages, 8 figures, journal paper. arXiv admin note: text overlap with arXiv:2308.04675

This paper proposes a solution for energy-efficient communication in reconfigurable intelligent surface (RIS)-assisted unmanned aerial vehicle (UAV) networks. The limited battery life of UAVs is a major concern for their sustainable operation, and RIS has emerged as a promising solution to reducing the energy consumption of communication systems. The paper formulates the problem of maximizing the energy efficiency of the network as a mixed integer non-linear program, in which UAV placement, UAV beamforming, On-Off strategy of RIS elements, and phase shift of RIS elements are optimized. The proposed solution utilizes the block coordinate descent approach and a combination of continuous and binary genetic algorithms. Moreover, for optimizing the UAV placement, Adam optimizer is used. The simulation results show that the proposed solution outperforms the existing literature. Specifically, we compared the proposed method with the successive convex approximation (SCA) approach for optimizing the phase shift of RIS elements.

It is anticipated that integrating unmanned aerial vehicles (UAVs) with reconfigurable intelligent surfaces (RISs), resulting in RIS-assisted UAV networks, will offer improved network connectivity against node failures for the beyond 5G networks. In this context, we utilize a RIS to provide path diversity and alternative connectivity options for information flow from user equipment (UE) to UAVs by adding more links to the network, thereby maximizing its connectivity. This paper employs the algebraic connectivity metric, which is adjusted by the reflected links of the RIS, to formulate the problem of maximizing the network connectivity in two cases. First, we consider formulating the problem for one UE, which is solved optimally using a linear search. Then, we consider the problem of a more general case of multiple UEs, which has high computational complexity. To tackle this problem, we formulate the problem of maximizing the network connectivity as a semi-definite programming (SDP) optimization problem that can be solved efficiently in polynomial time. In both cases, our proposed solutions find the best combination between UE(s) and UAVs through the RIS. As a result, it tunes the phase shifts of the RIS to direct the signals of the UEs to the appropriate UAVs, thus maximizing the network connectivity. Simulation results are conducted to assess the performance of the proposed solutions compared to the existing solutions., Comment: 7 pages, 5 figures, conference

Hypertension is commonly referred to as the "silent killer", since it can lead to severe health complications without any visible symptoms. Early detection of hypertension is crucial in preventing significant health issues. Although some studies suggest a relationship between blood pressure and certain vital signals, such as Photoplethysmogram (PPG), reliable generalization of the proposed blood pressure estimation methods is not yet guaranteed. This lack of certainty has resulted in some studies doubting the existence of such relationships, or considering them weak and limited to heart rate and blood pressure. In this paper, a high-dimensional representation technique based on random convolution kernels is proposed for hypertension detection using PPG signals. The results show that this relationship extends beyond heart rate and blood pressure, demonstrating the feasibility of hypertension detection with generalization. Additionally, the utilized transform using convolution kernels, as an end-to-end time-series feature extractor, outperforms the methods proposed in the previous studies and state-of-the-art deep learning models., Comment: 4 pages, 2 figures, 1 table, Accepted at IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 23), Oct. 15--18, 2023, Pittsburgh, Pennsylvania, USA

Reconfigurable intelligent surfaces (RISs) are expected to be a main component of future 6G networks, due to their capability to create a controllable wireless environment, and achieve extended coverage and improved localization accuracy. In this paper, we present a novel cooperative positioning use case of the RIS in mmWave frequencies, and show that in the presence of RIS, together with sidelink communications, localization with zero access points (APs) is possible. We show that multiple (at least three) half-duplex single-antenna user equipments (UEs) can cooperatively estimate their positions through device-to-device communications with a single RIS as an anchor without the need for any APs. We start by formulating a three-dimensional positioning problem with Cram\'er-Rao lower bound (CRLB) derived for performance analysis. After that, we discuss the RIS profile design and the power allocation strategy between the UEs. Then, we propose low-complexity estimators for estimating the channel parameters and UEs' positions. Finally, we evaluate the performance of the proposed estimators and RIS profiles in the considered scenario via extensive simulations and show that sub-meter level positioning accuracy can be achieved under multi-path propagation.

A smart city involves, among other elements, intelligent transportation, crowd monitoring, and digital twins, each of which requires information exchange via wireless communication links and localization of connected devices and passive objects (including people). Although localization and sensing (L&S) are envisioned as core functions of future communication systems, they have inherently different demands in terms of infrastructure compared to communications. Wireless communications generally requires a connection to only a single access point (AP), while L&S demand simultaneous line-of-sight propagation paths to several APs, which serve as location and orientation anchors. Hence, a smart city deployment optimized for communication will be insufficient to meet stringent L&S requirements. In this article, we argue that the emerging technologies of reconfigurable intelligent surfaces (RISs) and sidelink communications constitute the key to providing ubiquitous coverage for L&S in smart cities with low-cost and energy-efficient technical solutions. To this end, we propose and evaluate AP-coordinated and self-coordinated RIS-enabled L&S architectures and detail three groups of application scenarios, relying on low-complexity beacons, cooperative localization, and full-duplex transceivers. A list of practical issues and consequent open research challenges of the proposed L&S systems is also provided.

WiFi sensing is an important part of the new WiFi 802.11bf standard, which can detect motion and measure distances. In recent years, some machine learning methods have been proposed for human activity recognition from WiFi signals. However, to the best of our knowledge, none of these methods have explored orientation prediction of the user using WiFi signals. Orientation prediction is particularly critical for human-machine interaction in an environment with multiple smart devices. In this paper, we propose a data collection setup and machine learning models for joint human orientation and activity recognition using WiFi signals from a single access point (AP) or multiple APs. The results show feasibility of joint orientation-activity recognition in an indoor environment with a high accuracy.

Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-D convolution kernels of different configurations. The output of the convolution operation on each time series is represented by a partial positive value (PPV). A concatenation of PPVs from all kernels is the input feature vector to a Ridge regression classifier. Unlike typical deep learning models, the kernels are not trained and there is no weighted/trainable connection between kernels or concatenated features and the classifier. Since these kernels are generated randomly, a portion of these kernels may not positively contribute in performance of the model. Hence, selection of the most important kernels and pruning the redundant and less important ones is necessary to reduce computational complexity and accelerate inference of Rocket for applications on the edge devices. Selection of these kernels is a combinatorial optimization problem. In this paper, we propose a scheme for selecting these kernels while maintaining the classification performance. First, the original model is pre-trained at full capacity. Then, a population of binary candidate state vectors is initialized where each element of a vector represents the active/inactive status of a kernel. A population-based optimization algorithm evolves the population in order to find a best state vector which minimizes the number of active kernels while maximizing the accuracy of the classifier. This activation function is a linear combination of the total number of active kernels and the classification accuracy of the pre-trained classifier with the active kernels. Finally, the selected kernels in the best state vector are utilized to train the Ridge regression classifier with the selected kernels.

Anatomical movements of the human body can change the channel state information (CSI) of wireless signals in an indoor environment. These changes in the CSI signals can be used for human activity recognition (HAR), which is a predominant and unique approach due to preserving privacy and flexibility of capturing motions in non-line-of-sight environments. Existing models for HAR generally have a high computational complexity, contain very large number of trainable parameters, and require extensive computational resources. This issue is particularly important for implementation of these solutions on devices with limited resources, such as edge devices. In this paper, we propose a lightweight human activity recognition (LiteHAR) approach which, unlike the state-of-the-art deep learning models, does not require extensive training of large number of parameters. This approach uses randomly initialized convolution kernels for feature extraction from CSI signals without training the kernels. The extracted features are then classified using Ridge regression classifier, which has a linear computational complexity and is very fast. LiteHAR is evaluated on a public benchmark dataset and the results show its high classification performance in comparison with the complex deep learning models with a much lower computational complexity., Comment: Accepted for presentation at IEEE ICASSP 2022. Copyright 2022 IEEE

This paper proposes a cooperative angle-of-arrival(AoA) estimation, taking advantage of co-processing channel state information (CSI) from a group of access points that receive signals of the same source. Since received signals are sparse, we use Compressive Sensing (CS) to address the AoA estimation problem. We formulate this problem as a penalized l0-norm minimization, reformulate it as an Ising energy problem, and solve it using Markov Chain Monte Carlo (MCMC). Simulation results show that our proposed method outperforms the existing methods in the literature.

A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to reducing the number of parameters in a DNN. In this paper, we propose a framework for pruning DNNs based on a population-based global optimization method. This framework can use any pruning objective function. As a case study, we propose a simple but efficient objective function based on the concept of energy-based models. Our experiments on ResNets, AlexNet, and SqueezeNet for the CIFAR-10 and CIFAR-100 datasets show a pruning rate of more than $50\%$ of the trainable parameters with approximately $<5\%$ and $<1\%$ drop of Top-1 and Top-5 classification accuracy, respectively., Comment: This paper is accepted for presentation at IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2021. arXiv admin note: text overlap with arXiv:2006.04270, arXiv:2102.05437

Pruning is one of the major methods to compress deep neural networks. In this paper, we propose an Ising energy model within an optimization framework for pruning convolutional kernels and hidden units. This model is designed to reduce redundancy between weight kernels and detect inactive kernels/hidden units. Our experiments using ResNets, AlexNet, and SqueezeNet on CIFAR-10 and CIFAR-100 datasets show that the proposed method on average can achieve a pruning rate of more than $50\%$ of the trainable parameters with approximately $<10\%$ and $<5\%$ drop of Top-1 and Top-5 classification accuracy, respectively., Comment: This paper is accepted for presentation at IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2021

Modern deep neural networks are often too large to use in many practical scenarios. Neural network pruning is an important technique for reducing the size of such models and accelerating inference. Gibbs pruning is a novel framework for expressing and designing neural network pruning methods. Combining approaches from statistical physics and stochastic regularization methods, it can train and prune a network simultaneously in such a way that the learned weights and pruning mask are well-adapted for each other. It can be used for structured or unstructured pruning and we propose a number of specific methods for each. We compare our proposed methods to a number of contemporary neural network pruning methods and find that Gibbs pruning outperforms them. In particular, we achieve a new state-of-the-art result for pruning ResNet-56 with the CIFAR-10 dataset., Comment: v1 was presented at IEEE GLOBECOM 2020. v2 is a substantially expanded revision, also written in 2020

Dropout is a well-known regularization method by sampling a sub-network from a larger deep neural network and training different sub-networks on different subsets of the data. Inspired by the dropout concept, we propose EDropout as an energy-based framework for pruning neural networks in classification tasks. In this approach, a set of binary pruning state vectors (population) represents a set of corresponding sub-networks from an arbitrary provided original neural network. An energy loss function assigns a scalar energy loss value to each pruning state. The energy-based model stochastically evolves the population to find states with lower energy loss. The best pruning state is then selected and applied to the original network. Similar to dropout, the kept weights are updated using backpropagation in a probabilistic model. The energy-based model again searches for better pruning states and the cycle continuous. Indeed, this procedure is in fact switching between the energy model, which manages the pruning states, and the probabilistic model, which updates the temporarily unpruned weights, in each iteration. The population can dynamically converge to a pruning state. This can be interpreted as dropout leading to pruning the network. From an implementation perspective, EDropout can prune typical neural networks without modification of the network architecture. We evaluated the proposed method on different flavours of ResNets, AlexNet, and SqueezeNet on the Kuzushiji, Fashion, CIFAR-10, CIFAR-100, and Flowers datasets, and compared the pruning rate and classification performance of the models. On average the networks trained with EDropout achieved a pruning rate of more than $50\%$ of the trainable parameters with approximately $<5\%$ and $<1\%$ drop of Top-1 and Top-5 classification accuracy, respectively.

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic regularization while explicitly averaging outputs. This provides stronger regularization with no additional computational cost at test time. We show consistent improvement on various image classification tasks using standard network topologies.

Dropout methods are a family of stochastic techniques used in neural network training or inference that have generated significant research interest and are widely used in practice. They have been successfully applied in neural network regularization, model compression, and in measuring the uncertainty of neural network outputs. While original formulated for dense neural network layers, recent advances have made dropout methods also applicable to convolutional and recurrent neural network layers. This paper summarizes the history of dropout methods, their various applications, and current areas of research interest. Important proposed methods are described in additional detail.

This paper aims at the problem of time-of-flight (ToF) estimation using channel state information (CSI) obtainable from commercialized MIMO-OFDM WLAN receivers. It was often claimed that the CSI phase is contaminated with errors of known and unknown natures rendering ToF-based positioning difficult. To search for an answer, we take a bottom-up approach by first understanding CSI, its constituent building blocks, and the sources of error that contaminate it. We then model these effects mathematically. The correctness of these models is corroborated based on the CSI collected in extensive measurement campaign including radiated, conducted and chamber tests. Knowing the nature of contamination in CSI phase and amplitude, we proceed with introducing pre-processing methods to clean CSI from those errors and make it usable for range estimation. To check the validity of proposed algorithms, the MUSIC super-resolution algorithm is applied to post-processed CSI to perform range estimates. Results substantiate that median accuracy of 0.6m, 0.8m, and 0.9m is achievable in highly multipath line-of-sight environment where transmitter and receiver are 5m, 10m, and 15m apart.

Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the training data and negatively affects the generalization performance of the model for unseen data. The original dropout is a regularization technique to drop hidden units randomly during training. In this paper, we propose an adaptive technique to wisely drop the visible and hidden units in a deep neural network using Ising energy of the network. The preliminary results show that the proposed approach can keep the classification performance competitive to the original network while eliminating optimization of unnecessary network parameters in each training cycle. The dropout state of units can also be applied to the trained (inference) model. This technique could compress the network in terms of number of parameters up to 41.18% and 55.86% for the classification task on the MNIST and Fashion-MNIST datasets, respectively., Comment: This paper is accepted at 44th IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2019

In this paper, we propose a novel technique for sampling sequential images using a cylindrical transform in a cylindrical coordinate system for kidney semantic segmentation in abdominal computed tomography (CT). The images generated from a cylindrical transform augment a limited annotated set of images in three dimensions. This approach enables us to train contemporary classification deep convolutional neural networks (DCNNs) instead of fully convolutional networks (FCNs) for semantic segmentation. Typical semantic segmentation models segment a sequential set of images (e.g. CT or video) by segmenting each image independently. However, the proposed method not only considers the spatial dependency in the x-y plane, but also the spatial sequential dependency along the z-axis. The results show that classification DCNNs, trained on cylindrical transformed images, can achieve a higher segmentation performance value than FCNs using a limited number of annotated images., Comment: This paper is accepted for presentation at IEEE Global Conference on Signal and Information Processing (IEEE GlobalSIP), California, USA, 2018

Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time-series data. The RNNs have a stack of non-linear units where at least one connection between units forms a directed cycle. A well-trained RNN can model any dynamical system; however, training RNNs is mostly plagued by issues in learning long-term dependencies. In this paper, we present a survey on RNNs and several new advances for newcomers and professionals in the field. The fundamentals and recent advances are explained and the research challenges are introduced., Comment: arXiv admin note: text overlap with arXiv:1602.04335

Medical datasets are often highly imbalanced with over-representation of common medical problems and a paucity of data from rare conditions. We propose simulation of pathology in images to overcome the above limitations. Using chest X-rays as a model medical image, we implement a generative adversarial network (GAN) to create artificial images based upon a modest sized labeled dataset. We employ a combination of real and artificial images to train a deep convolutional neural network (DCNN) to detect pathology across five classes of chest X-rays. Furthermore, we demonstrate that augmenting the original imbalanced dataset with GAN generated images improves performance of chest pathology classification using the proposed DCNN in comparison to the same DCNN trained with the original dataset alone. This improved performance is largely attributed to balancing of the dataset using GAN generated images, where image classes that are lacking in example images are preferentially augmented., Comment: This paper is accepted for presentation at IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2018

Radiology reports are an important means of communication between radiologists and other physicians. These reports express a radiologist's interpretation of a medical imaging examination and are critical in establishing a diagnosis and formulating a treatment plan. In this paper, we propose a Bi-directional convolutional neural network (Bi-CNN) model for the interpretation and classification of mammograms based on breast density and chest radiographic radiology reports based on the basis of chest pathology. The proposed approach helps to organize databases of radiology reports, retrieve them expeditiously, and evaluate the radiology report that could be used in an auditing system to decrease incorrect diagnoses. Our study revealed that the proposed Bi-CNN outperforms the random forest and the support vector machine methods., Comment: This paper is submitted for peer-review

In this article, we present a survey of recent advances in passive human behaviour recognition in indoor areas using the channel state information (CSI) of commercial WiFi systems. Movement of human body causes a change in the wireless signal reflections, which results in variations in the CSI. By analyzing the data streams of CSIs for different activities and comparing them against stored models, human behaviour can be recognized. This is done by extracting features from CSI data streams and using machine learning techniques to build models and classifiers. The techniques from the literature that are presented herein have great performances, however, instead of the machine learning techniques employed in these works, we propose to use deep learning techniques such as long-short term memory (LSTM) recurrent neural network (RNN), and show the improved performance. We also discuss about different challenges such as environment change, frame rate selection, and multi-user scenario, and suggest possible directions for future work., Comment: 4 figures

Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the data available to train these networks is often limited or imbalanced. We propose a sampling method based on the radial transform in a polar coordinate system for image augmentation to facilitate the training of deep learning models from limited source data. This pixel-wise transform provides representations of the original image in the polar coordinate system by generating a new image from each pixel. This technique can generate radial transformed images up to the number of pixels in the original image to increase the diversity of poorly represented image classes. Our experiments show improved generalization performance in training deep convolutional neural networks with radial transformed images., Comment: This paper is accepted for presentation at IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2018

Pathfinding in hospitals is challenging for patients, visitors, and even employees. Many people have experienced getting lost due to lack of clear guidance, large footprint of hospitals, and confusing array of hospital wings. In this paper, we propose Halo; An indoor navigation application based on voice-user interaction to help provide directions for users without assistance of a localization system. The main challenge is accurate detection of origin and destination search terms. A custom convolutional neural network (CNN) is proposed to detect origin and destination search terms from transcription of a submitted speech query. The CNN is trained based on a set of queries tailored specifically for hospital and clinic environments. Performance of the proposed model is studied and compared with Levenshtein distance-based word matching., Comment: This paper is accepted for presentation at 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications

In this paper, we propose an OCR (optical character recognition)-based localization system called OCRAPOSE II, which is applicable in a number of indoor scenarios including office buildings, parkings, airports, grocery stores, etc. In these scenarios, characters (i.e. texts or numbers) can be used as suitable distinctive landmarks for localization. The proposed system takes advantage of OCR to read these characters in the query still images and provides a rough location estimate using a floor plan. Then, it finds depth and angle-of-view of the query using the information provided by the OCR engine in order to refine the location estimate. We derive novel formulas for the query angle-of-view and depth estimation using image line segments and the OCR box information. We demonstrate the applicability and effectiveness of the proposed system through experiments in indoor scenarios. It is shown that our system demonstrates better performance compared to the state-of-the-art benchmarks in terms of location recognition rate and average localization error specially under sparse database condition., Comment: 14 pages, 22 Figures

In this paper, we first remodel the line coverage as a 1D discrete problem with co-linear targets. Then, an order-based greedy algorithm, called OGA, is proposed to solve the problem optimally. It will be shown that the existing order in the 1D modeling, and especially the resulted Markov property of the selected sensors can help design greedy algorithms such as OGA. These algorithms demonstrate optimal/efficient performance and have lower complexity compared to the state-of-the-art. Furthermore, it is demonstrated that the conventional continuous line coverage problem can be converted to an equivalent discrete problem and solved optimally by OGA. Next, we formulate the well-known weak barrier coverage problem as an instance of the continuous line coverage problem (i.e. a 1D problem) as opposed to the conventional 2D graph-based models. We demonstrate that the equivalent discrete version of this problem can be solved optimally and faster than the state-of-the-art methods using an extended version of OGA, called K-OGA. Moreover, an efficient local algorithm, called LOGM, is proposed to mend barrier gaps due to sensor failure. In the case of m gaps, LOGM is proved to select at most 2m-1 sensors more than the optimal while being local and implementable in distributed fashion. We demonstrate the optimal/efficient performance of the proposed algorithms via extensive simulations., Comment: 10 Pages, 11 Figures

One major bottleneck in the practical implementation of received signal strength (RSS) based indoor localization systems is the extensive deployment efforts required to construct the radio maps through fingerprinting. In this paper, we aim to design an indoor localization scheme that can be directly employed without building a full fingerprinted radio map of the indoor environment. By accumulating the information of localized RSSs, this scheme can also simultaneously construct the radio map with limited calibration. To design this scheme, we employ a source data set that possesses the same spatial correlation of the RSSs in the indoor environment under study. The knowledge of this data set is then transferred to a limited number of calibration fingerprints and one or several RSS observations with unknown locations, in order to perform direct localization of these observations using manifold alignment. We test two different source data sets, namely a simulated radio propagation map and the environments plan coordinates. For moving users, we exploit the correlation of their observations to improve the localization accuracy. The online testing in two indoor environments shows that the plan coordinates achieve better results than the simulated radio maps, and a negligible degradation with 70-85% reduction in calibration load.

We introduce the novel concept of mobility diversity for mobile sensor or communication networks as the diversity introduced by transmitting data over different topologies of the network. We show how node mobility can provide diversity by changing the topology of the network. More specifically, we consider a mobile network of a sensor node and a number of sink nodes which are all moving randomly according to different Wiener process mobility models. Assuming that the network topology evolves with time and assuming that the connectivity of the sensor node to at least one sink node is needed for successful communication, we calculate three performance measures for this network, i) the expected number of time instants, where the sensor node is connected to at least one sink node, ii) the probability of outage, being the probability that no sink node is in the vicinity of the sensor node during the observation interval, and finally, iii) the maximum number of consequent failures in the communication. Our theoretical and numerical analysis show that increasing the mobility parameter of the sensor node increases the average number of successful transmissions, decreases the probability of outage, and reduces the maximum delay in the senor-sink communication.

In this paper, we study the multicast completion and decoding delay minimization problems of instantly decodable network coding (IDNC) in the case of lossy feedback. In such environments, the sender falls into uncertainties about packet reception at the different receivers, which forces it to perform partially blind selections of packet combinations in subsequent transmissions. To determine efficient partially blind policies that handle the completion and decoding delays of IDNC in such environment, we first extend the perfect feedback formulation in [2], [3] to the lossy feedback environment, by incorporating the uncertainties resulting from unheard feedback events in these formulations. For the completion delay problem, we use this formulation to identify the maximum likelihood state of the network in events of unheard feedback, and employ it to design a partially blind graph update extension to the multicast IDNC algorithm in [3]. For the decoding delay problem, we derive an expression for the expected decoding delay increment for any arbitrary transmission. This expression is then used to derive the optimal policy to reduce the decoding delay in such lossy feedback environment. Results show that our proposed solution both outperforms other approaches and achieves a tolerable degradation even at relatively high feedback loss rates.

In this paper, we aim to identify the strategies that can maximize and monotonically increase the density of the coding opportunities in instantly decodable network coding (IDNC).Using the well-known graph representation of IDNC, first derive an expression for the exact evolution of the edge set size after the transmission of any arbitrary coded packet. From the derived expressions, we show that sending commonly wanted packets for all the receivers can maximize the number of coding opportunities. Since guaranteeing such property in IDNC is usually impossible, this strategy does not guarantee the achievement of our target. Consequently, we further investigate the problem by deriving the expectation of the edge set size evolution after ignoring the identities of the packets requested by the different receivers and considering only their numbers. We then employ this expected expression to show that serving the maximum number of receivers having the largest numbers of missing packets and erasure probabilities tends to both maximize and monotonically increase the expected density of coding opportunities. Simulation results justify our theoretical findings. Finally, we validate the importance of our work through two case studies showing that our identified strategy outperforms the step-by-step service maximization solution in optimizing both the IDNC completion delay and receiver goodput.

In this paper, we consider the problem of minimizing the completion delay for instantly decodable network coding (IDNC), in wireless multicast and broadcast scenarios. We are interested in this class of network coding due to its numerous benefits, such as low decoding delay, low coding and decoding complexities and simple receiver requirements. We first extend the IDNC graph, which represents all feasible IDNC coding opportunities, to efficiently operate in both multicast and broadcast scenarios. We then formulate the minimum completion delay problem for IDNC as a stochastic shortest path (SSP) problem. Although finding the optimal policy using SSP is intractable, we use this formulation to draw the theoretical guidelines for the policies that can efficiently reduce the completion delay in IDNC. Based on these guidelines, we design a maximum weight clique selection algorithm, which can efficiently reduce the IDNC completion delay in polynomial time. We also design a quadratic time heuristic clique selection algorithm, which can operate in real-time applications. Simulation results show that our proposed algorithms efficiently reduce the IDNC completion delay compared to the random and maximum-rate algorithms, and almost achieve the global optimal completion delay performance over all network codes in broadcast scenarios.

It is shown that bandwidth estimation in packet networks can be viewed in terms of min-plus linear system theory. The available bandwidth of a link or complete path is expressed in terms of a {\em service curve}, which is a function that appears in the network calculus to express the service available to a traffic flow. The service curve is estimated based on measurements of a sequence of probing packets or passive measurements of a sample path of arrivals. It is shown that existing bandwidth estimation methods can be derived in the min-plus algebra of the network calculus, thus providing further mathematical justification for these methods. Principal difficulties of estimating available bandwidth from measurement of network probes are related to potential non-linearities of the underlying network. When networks are viewed as systems that operate either in a linear or in a non-linear regime, it is argued that probing schemes extract the most information at a point when the network crosses from a linear to a non-linear regime. Experiments on the Emulab testbed at the University of Utah evaluate the robustness of the system theoretic interpretation of networks in practice. Multi-node experiments evaluate how well the convolution operation of the min-plus algebra provides estimates for the available bandwidth of a path from estimates of individual links., Comment: 23 pages