Search

We address the problem of distributed state estimation of a linear dynamical process in an attack-prone environment. Recent attempts to solve this problem impose stringent redundancy requirements on the measurement and communication resources of the network. In this paper, we take a step towards alleviating such strict requirements by exploring two complementary directions: (i) making a small subset of the nodes immune to attacks, or "trusted", and (ii) incorporating diversity into the network. We define graph-theoretic constructs that formally capture the notions of redundancy, diversity, and trust. Based on these constructs, we develop a resilient estimation algorithm and demonstrate that even relatively sparse networks that either exhibit node-diversity, or contain a small subset of trusted nodes, can be just as resilient to adversarial attacks as more dense networks. Finally, given a finite budget for network design, we focus on characterizing the complexity of (i) selecting a set of trusted nodes, and (ii) allocating diversity, so as to achieve a desired level of robustness. We establish that, unfortunately, each of these problems is NP-complete.

Autonomous driving research is an emerging area in the machine learning domain. Most existing methods perform single-task learning, while multi-task learning (MTL) is more efficient due to the leverage of shared information between different tasks. However, MTL is challenging because different tasks may have different significance and varying ranges. In this work, we propose an end-to-end deep learning architecture for statistically correlated MTL using a single input image. Statistical correlation of the tasks is handled by including shared layers in the architecture. Later network separates into different branches to handle the difference in the behavior of each task. Training a multi-task model with varying ranges may converge the objective function only with larger values. To this end, we explore different normalization schemes and empirically observe that the inverse validation-loss weighted scheme has best performed. In addition to estimating steering angle, braking, and acceleration, we also estimate the number of lanes on the left and the right side of the vehicle. To the best of our knowledge, we are the first to propose an end-to-end deep learning architecture to estimate this type of lane information. The proposed approach is evaluated on four publicly available datasets including Comma.ai, Udacity, Berkeley Deep Drive, and Sully Chen. We also propose a synthetic dataset GTA-V for autonomous driving research. Our experiments demonstrate the superior performance of the proposed approach compared to the current state-of-the-art methods. The GTA-V dataset and the lane annotations on the four existing datasets will be made publicly available via https://cvlab.lums.edu.pk/scmtl/.

Recent advancements in learning from graph-structured data have shown promising results on the graph classification task. However, due to their high time complexities, making them scalable on large graphs, with millions of nodes and edges, remains a challenge. In this paper, we propose NetKI, an algorithm to extract sparse representation from a given graph with n nodes and m edges in O ( m ∊ - 2 log 4 n ) time. Our approach follows the notion of Kirchhoff index that encodes the structure of the graph by estimating effective resistance - relying on this approach yields nearly linear time graph representation method that allows scalability on sufficiently large graphs. Through extensive experiments, we show that NetKI provides improved results in terms of running time on large networks and the classification accuracy is within range 2% from the state-of-the-art results.

Electroencephalography (EEG) is a method of the brain–computer interface (BCI) that measures brain activities. EEG is a method of (non-)invasive recording of the electrical activity of the brain. This can be used to build BCIs. From the last decade, EEG has grasped researchers’ attention to distinguish human activities. However, temporal information has rarely been retained to incorporate temporal information for multi-class (more than two classes) motor imagery classification. This research proposes a long-short-term-memory-based deep learning model to learn the hidden sequential patterns. Two types of features are used to feed the proposed model, including Fourier Transform Energy Maps (FTEMs) and Common Spatial Patterns (CSPs) filters. Multiple experiments have been conducted on a publicly available dataset. Extraction of spatial and spectro-temporal features using CSP filters and FTEM allow the sequence-to-sequence based proposed model to learn the hidden sequential features. The proposed method is trained, evaluated, and optimized for a publicly available benchmark data set and resulted in 0.81 mean kappa value. Obtained results depict the model robustness for the artifacts and suitable for real-life applications with comparable classification accuracy. The code and findings will be available at https://github.com/waseemabbaas/Motor-Imagery-Classification.git .

In this article, we demonstrate a conflicting relationship between two crucial properties— controllability and robustness —in linear dynamical networks of diffusively coupled agents. In particular, for any given number of nodes $N$ and diameter $D$ , we identify networks that are maximally robust using the notion of Kirchhoff's index and then analyze their strong structural controllability. For this, we compute the minimum number of leaders, which are the nodes directly receiving external control inputs, needed to make such networks controllable under all feasible coupling weights between agents. Then, for any $N$ and $D$ , we obtain a sharp upper bound on the minimum number of leaders needed to design strong structurally controllable networks with $N$ nodes and $D$ diameter. We also discuss that the bound is best possible for arbitrary $N$ and $D$ . Moreover, we construct a family of graphs for any $N$ and $D$ such that the graphs have maximal edge sets (maximal robustness) while being strong structurally controllable with the number of leaders in the proposed sharp bound. We then analyze the robustness of this graph family. The results suggest that optimizing robustness increases the number of leaders needed for strong structural controllability. Our analysis is based on graph-theoretic methods and can be applied to exploit network structure to co-optimize robustness and controllability in networks.

In many cooperative networks, individuals participate actively as long as they recognize a sufficient value in participation, which depends not only on the number, but also on the attributes of other participating members. In this paper, we present a generalized model of individuals’ participation in such networks, and a strategy to maximize the number of participating individuals. Unlike most of the existing literature, our model incorporates both the network structure and the heterogeneity of individuals in terms of their attributes and resources. We consider that each individual possesses a subset of available resources (attributes), which it shares with neighbors as long as neighbors reciprocate and provide the missing resources to the individual. However, individual leaves the network if it cannot find all the resources in its neighborhood. To model this phenomenon, we introduce a graph-theoretic notion of the $(r,s)$ -core, which is the sub-network consisting of only those individuals who can access all the resources by collaborating with their neighbors. Since disengagement of an individual could initiate a cascading withdrawal of more individuals from the network, one of our main goals is to prevent this unraveling and maximize the number of participating individuals. For this purpose, we utilize the notion of anchors—individuals that continue to participate (due to incentives) even if they cannot find all of the resources in their neighborhood. By introducing only a few anchors, we can significantly increase the number of participating individuals, which in our model corresponds to increasing the size of the $(r,s)$ -core. We formulate and thoroughly analyze the anchors’ selection problem by classifying the cases in which the problem is polynomial-time solvable, NP-complete, and inapproximable. Further, we provide greedy and metaheuristic search algorithms to compute a set of anchors and evaluate our results on various networks. Our results are applicable to a large number of cooperative networking applications, including participatory sensing in which users develop an elaborate knowledge of their environment through sharing measurements.

Retinal blood vessels, the diagnostic bio-marker of ophthalmologic and diabetic retinopathy, utilise thick and thin vessels for diagnostic and monitoring purposes. The existing deep learning methods attempt to segment the retinal vessels using a unified loss function. However, a difference in spatial features of thick and thin vessels and a biased distribution creates an imbalanced thickness, rendering the unified loss function to be useful only for thick vessels. To address this challenge, a patch-based generative adversarial network-based technique is proposed which iteratively learns both thick and thin vessels in fundoscopic images. It introduces an additional loss function that allows the generator network to learn thin and thick vessels, while the discriminator network assists in segmenting out both vessels as a combined objective function. Compared with state-of-the-art techniques, the proposed model demonstrates the enhanced accuracy, sensitivity, specificity, and area under the receiver operating characteristic curves on STARE, DRIVE, and CHASEDB1 datasets.

In this research, scalable framework for Smart Logistics based Cyber-Physical System (SLCPS) is emulated for stable coverage and connectivity of Internet of Things (IoT) devices. This work is modern manifestation of three laws of computing. Moore’s and Koomey’s laws recommend performance gain and energy efficiency whereas Metcalfe’s law imply network scalability. Combination of these laws suggests the research proposition that development of scalable and performance efficient IoT networks is inevitable. Although IoT has improved specific logistics modules considerably, but incorporation of IoT in complete supply chain of food and random placement of IoT devices due to which unstable coverage and connectivity occurred are major challenges in logistics. The proposed SLCPS framework is designed firstly, to develop apt IoT protocol stack for logistics. Secondly, for bonded connectivity and coverage, mathematical models are proposed instead of random placement and coverage map is based on binary coverage model. Thirdly, for scalability supply chain of food for smart logistics process is designed in terms of container, storehouse and warehouse comprising of varying number of IoT devices. The architecture of SLCPS framework has three modules i.e. internal IoT network, border router and external network, emulated in Cooja simulator. The contikimac protocol is used for efficient traffic flow and power consumption. Single hop, multiple hops and random IoT devices placement scenarios are used for results comparison and validation. The performance evaluation results, i.e. throughput, network convergence time, packet delivery ratio, average latency, power consumption and timeline investigation validated utilization of proposed framework in terms of enhanced network performance. Significance of proposed SLCPS framework results in cost minimization, reducing communication and computation overhead, resilience to IoT device failures and an interference free network connectivity and coverage. Coverage and connectivity are measure of quality of service in IoT network. Therefore, this research provided bonded coverage and connectivity in smart logistics using mathematical models. In addition, a baseline framework is provided for extended research in CPS and IoT applications.

The broad accessibility of affordable and reliable recording equipment and its relative ease of use has enabled neuroscientists to record large amounts of neurophysiological and behavioral data. Given that most of this raw data is unlabeled, great effort is required to adapt it for behavioral phenotyping or signal extraction, for behavioral and neurophysiological data, respectively. Traditional methods for labeling datasets rely on human annotators which is a resource and time intensive process, which often produce data that that is prone to reproducibility errors. Here, we propose a deep learning-based image segmentation framework to automatically extract and label limb movements from movies capturing frontal and lateral views of head-fixed mice. The method decomposes the image into elemental regions (superpixels) with similar appearance and concordant dynamics and stacks them following their partial temporal trajectory. These 3D descriptors (referred as motion cues) are used to train a deep convolutional neural network (CNN). We use the features extracted at the last fully connected layer of the network for training a Long Short Term Memory (LSTM) network that introduces spatio-temporal coherence to the limb segmentation. We tested the pipeline in two video acquisition settings. In the first, the camera is installed on the right side of the mouse (lateral setting). In the second, the camera is installed facing the mouse directly (frontal setting). We also investigated the effect of the noise present in the videos and the amount of training data needed, and we found that reducing the number of training samples does not result in a drop of more than 5% in detection accuracy even when as little as 10% of the available data is used for training.

Wafer maps provide engineers with important information about the root causes of failures during the semiconductor manufacturing process. Through the efficient recognition of the wafer map failure pattern type, the semiconductor manufacturing process and its product performance can be improved, as well as reducing the product cost. Therefore, this paper proposes an accurate model for the automatic recognition of wafer map failure types using a deep learning-based convolutional neural network (DCNN). For this experiment, we use WM811K, which is an open-source real-time wafer map dataset containing wafer map images of nine failure classes. Our research contents can be briefly summarized as follows. First, we use random sampling to extract 500 images from each class of the original image dataset. Then we propose a deep convolutional neural network model to generate a multi-class classification model. Lastly, we evaluate the performance of the proposed prediction model and compare it with three other popular machine learning-based models—logistic regression, random forest, and gradient boosted decision trees—and several well-known deep learning models—VGGNet, ResNet, and EfficientNet. Consequently, the comprehensive analysis showed that the performance of the proposed DCNN model outperformed those of other popular machine learning and deep learning-based prediction models.

As the Industrial Internet of Things (IIoT) becomes more ubiquitous in critical application domains, such as smart water-distribution and transportation systems, providing security and resilience a...

Adversaries may cause significant damage to smart infrastructure using malicious attacks. To detect and mitigate these attacks before they can cause physical damage, operators can deploy anomaly detection systems (ADS), which can alarm operators to suspicious activities. However, detection thresholds of ADS need to be configured properly, as an oversensitive detector raises a prohibitively large number of false alarms, while an undersensitive detector may miss actual attacks. This is an especially challenging problem in dynamical environments, where the impact of attacks may significantly vary over time. Using a game-theoretic approach, we formulate the problem of computing optimal detection thresholds which minimize both the number of false alarms and the probability of missing actual attacks as a two-player Stackelberg security game. We provide an efficient dynamic programming-based algorithm for solving the game, thereby finding optimal detection thresholds. We analyze the performance of the proposed algorithm and show that its running time scales polynomially as the length of the time horizon of interest increases. In addition, we study the problem of finding optimal thresholds in the presence of both random faults and attacks. Finally, we evaluate our result using a case study of contamination attacks in water networks, and show that our optimal thresholds significantly outperform fixed thresholds that do not consider that the environment is dynamical.

Cyber-Physical Systems (CPS) allow us to manipulate objects in the physical world by providing a communication bridge between computation and actuation elements. In the current scheme of things, this sought-after control is marred by limitations inherent in the underlying communication network(s) as well as by the uncertainty found in the physical world. These limitations hamper fine-grained control of elements that may be separated by large-scale distances. In this regard, soft computing is an emerging paradigm that can help to overcome the vulnerabilities, and unreliability of CPS by using techniques including fuzzy systems, neural network, evolutionary computation, probabilistic reasoning and rough sets. In this paper, we present a comprehensive contemporary review of soft computing techniques for CPS dependability modeling, analysis, and improvement. This paper provides an overview of CPS applications, explores the foundations of dependability engineering, and highlights the potential role of soft computing techniques for CPS dependability with various case studies, while identifying common pitfalls and future directions. In addition, this paper provides a comprehensive survey on the use of various soft computing techniques for making CPS dependable., IEEE Access

A miniaturized on-chip substrate integrated waveguide (SIW) bandpass filter (BPF) and diplexer are designed in a 65nm CMOS process. The miniaturization of 42% is achieved by carving slots in the top layer of the SIW cavity. The designed two pole bandpass filter has a simulated 3 dB bandwidth of 11.1% around 70 GHz, while the diplexer has 3-dB bandwidths of 15.3% GHz and 14.86% around 71 and 90.9 GHz, respectively. Moreover, the isolation between two output ports of the diplexer is greater than -27.3 dB.

In this paper, we study the relationship between resilience and accuracy in the resilient distributed multi-dimensional consensus problem. We consider a network of agents, each of which has a state in $\mathbb{R}^d$. Some agents in the network are adversarial and can change their states arbitrarily. The normal (non-adversarial) agents interact locally and update their states to achieve consensus at some point in the convex hull $\calC$ of their initial states. This objective is achievable if the number of adversaries in the neighborhood of normal agents is less than a specific value, which is a function of the local connectivity and the state dimension $d$. However, to be resilient against adversaries, especially in the case of large $d$, the desired local connectivity is large. We discuss that resilience against adversarial agents can be improved if normal agents are allowed to converge in a bounded region $\calB\supseteq\calC$, which means normal agents converge at some point close to but not necessarily inside $\calC$ in the worst case. The accuracy of resilient consensus can be measured by the Hausdorff distance between $\calB$ and $\calC$. As a result, resilience can be improved at the cost of accuracy. We propose a resilient bounded consensus algorithm that exploits the trade-off between resilience and accuracy by projecting $d$-dimensional states into lower dimensions and then solving instances of resilient consensus in lower dimensions. We analyze the algorithm, present various resilience and accuracy bounds, and also numerically evaluate our results., Comment: IEEE Conference on Decision and Control (CDC) 2020

The detection of lungs nodule cancer by Computer Aided Diagnosis (CAD) system, provide a great support to the medical experts and can lower the death rate. In this research, CAD system is established for early detection of lungs nodule cancer. First, the contrast of an input image is enhanced by applying Contrast Limited Adaptive Histogram Equalization (CLAHE). The Otsu thresholding is applied for segmentation of lungs tumor followed by morphological filters to remove background and other geometrical objects. The resultant image is de-noised by applying Discrete Wavelet Transform (DWT). Gray Level Co-occurrence Matrix (GLCM) is used for features extraction such as correlation, energy, etc. Principle Component Analysis (PCA) is employed for feature selection. Finally, Support Vector Machine (SVM) is used to classify the image into benign (non-cancerous) or malignant (cancerous). The performance parameters such as accuracy, sensitivity, specificity, Peak Signal to Noise Ratio (PSNR), Root Mean Square Errors (RMSE) and Area under the Curve are used for the evaluation of the proposed method. The proposed system is verified on the LIDC dataset. The visual and parametric results of the proposed method are computed and compared with other existing methods.

Machine learning techniques are proven as a vital tool for the diagnosis and treatment of disease. The researchers are actively exploring new technology that may strengthen the state-of-the-practice in the clinical field. Automated bone fracture detection and classification have remained one of the popular research areas. However, traditionally developed techniques for the lower leg bone fracture method have faced the problem of detecting the existence of fractures and their location of occurrence. To overcome these problems, we proposed a transfer learning, Faster R-CNN deep learning model for fracture detection and classification with Region Proposal Network (RPN). Also, we retrained the top layer of the model by using inception v2 (version2) network architecture upon 50 x-ray images. This model was trained in 40k steps and its training stopped when loss remains only 0.0005. We evaluated the proposed model concerning detection and classification. We classify bone fracture x-ray images into two classes fracture and non-fracture also locate the location of fractures with a rectangle box. The overall accuracy has achieved from this method is 94% with respect to classification and detection. Our study shows that the proposed method is simple and efficient, which is worthwhile for dynamic detection, classification of fracture, now doctors and radiologists interact with more and more patient and overcome the workload. Furthermore, this approach improves the results, the run time performance and detection quality as compared to state-of-the-art techniques.

A 4-channel low power 2 7 -1 differential Pseudo Random Bit Sequence Generator is designed in a 28 nm CMOS process. It works with different seed settings for each channel using a single clock input, which makes it suitable for testing advanced communication systems such as QPSK transmitters. A simulated data rate of up to 30 Gb/s is achieved for all 4-channel. The Current Mode Logic is used for D Flip-Flop formation. A single channel consumes 48 mW power with 1.2 V power supply. The active chip area is 0.05 mm 2 , while with probing pads, it is 1.2 mm 2 .

We consider the problem of networked agents cooperating together to perform a task of optimizing the parameters of a global cost function. Agents receive linearly correlated noisy streaming data that can be used to learn the target parameters via Least-Mean-Squares (LMS) approaches. Diffusion scheme is incorporated such that at each step after agents adapt the parameters by the current received data, a combination step is included for agents to aggregate the information coming from its one-hop neighbors. It has been demonstrated that by introducing the aggregation step, diffusion algorithms greatly improve the learning accuracy of the parameters measured by the network Mean-Square-Deviation (MSD) [1]. However, the aggregation step is susceptible to attacks. In the presence of Byzantine agents, the aggregation of Byzantine information can easily disrupt the convergence of normal robots and even one Byzantine agent can drive its normal neighbors to converge to some point desired by the attacker [2]. To address this, we propose a resilient aggregation rule based on the notion of centerpoint [3], which is a generalization of median in the higher dimensional Euclidean space. We show that if a normal robot implements the centerpoint based aggregation rule for distributed diffusion, then it can guarantee the aggregated result to lie inside the convex hull of its normal neighbors, given at most [EQUATION] neighbors are Byzantine with n total negihbors and d-dimensional state vectors exchanged among agents. Further, we demonstrate all normal robots implementing centerpoint based distributed diffusion converge resiliently to the true target state. In addition, we demonstrate that widely adopted aggregation rules such as coordinate-wise median [4] and geometric median [5] based are not resilient under certain conditions. The main reason is that unlike centerpoint based aggregation, these rules do not guarantee the aggregation result to be inside the convex hull of the states of normal agents. We carried out experiments on Robotarium, a multirobot testbed developed at the Georgia Institute of Technology to demonstrate the cases where diffusion with coordinate-wise median and geometric median based aggregation rules fail to converge to the true target state, whereas diffusion with centerpoint based rule resiliently converge to the true target state in the same scenario.

In this paper, we study the resilient vector consensus problem in multi-agent networks and improve resilience guarantees of existing algorithms. In resilient vector consensus, agents update their states, which are vectors in $\mathbb{R}^d$, by locally interacting with other agents some of which might be adversarial. The main objective is to ensure that normal (non-adversarial) agents converge at a common state that lies in the convex hull of their initial states. Currently, resilient vector consensus algorithms, such as approximate distributed robust convergence (ADRC) are based on the idea that to update states in each time step, every normal node needs to compute a point that lies in the convex hull of its normal neighbors' states. {To compute such a point, the idea of Tverberg partition is typically used, which is computationally hard. Approximation algorithms for Tverberg partition negatively impact the resilience guarantees of consensus algorithm.} To deal with this issue, we propose to use the idea of centerpoint, which is an extension of median in higher dimensions, instead of Tverberg partition. We show that the resilience of such algorithms to adversarial nodes is improved if we use the notion of centerpoint. Furthermore, using centerpoint provides a better characterization of the necessary and sufficient conditions guaranteeing resilient vector consensus. We analyze these conditions in two, three, and higher dimensions separately. Finally, we numerically evaluate the performance of our approach through various experiments.

In this paper, we consider a network of agents with Laplacian dynamics, and study the problem of improving network robustness by adding a maximum number of edges within the network while preserving a lower bound on its strong structural controllability (SSC) at the same time. Edge augmentation increases network's robustness to noise and structural changes, however, it could also deteriorate network controllability. Thus, by exploiting relationship between network controllability and distances between nodes in graphs, we formulate an edge augmentation problem with a constraint to preserve distances between certain node pairs, which in turn guarantees that a lower bound on SSC is maintained even after adding edges. In this direction, first we choose a node pair and maximally add edges while maintaining the distance between selected nodes. We show that an optimal solution belongs to a certain class of graphs called clique chains. Then, we present an algorithm to add edges while preserving distances between a certain collection of nodes. Further, we present a randomized algorithm that guarantees a desired approximation ratio with high probability to solve the edge augmentation problem. Finally, we evaluate our results on various networks., American Control Conference (ACC)2020, Denver

The information technology’s new revolution is Internet of Things (IoT), where physical world is connected to the internet. IoT applications are diversified such as smart health, smart industry, smart homes and most importantly smart logistics for perishable items conservation. Although IoT devices have revolutionized world but due to their constrained nature they are at the cost of a greater risk of personal data loss, security breaches and misuse. In this research, a review is presented for proposing two state of the art modules i.e. communication model of smart logistics and security of IoT devices in Smart Logistics. As the smart logistics have perishable items i.e. fruits, vegetables, meat, medicine, chemicals, and cosmetics etc. which are sensitive to temperature, humidity and pressure etc. If the sensors monitoring these items have been handled abnormally due to security attacks, it will give huge loss. Therefore, security of smart logistics is of paramount importance in this research. In order to expedite research in this emergent area of IoT, in this research paper a brief review on progress of IoT in smart logistics, and its security has been presented.

In this article, we study resilient distributed diffusion for multi-task estimation in the presence of adversaries where networked agents must estimate distinct but correlated states of interest by processing streaming data. We show that in general diffusion strategies are not resilient to malicious agents that do not adhere to the diffusion-based information processing rules. In particular, by exploiting the adaptive weights used for diffusing information, we develop time-dependent attack models that drive normal agents to converge to states selected by the attacker. We show that an attacker that has complete knowledge of the system can always drive its targeted agents to its desired estimates. Moreover, an attacker that does not have complete knowledge of the system including streaming data of targeted agents or the parameters they use in diffusion algorithms, can still be successful in deploying an attack by approximating the needed information. The attack models can be used for both stationary and non-stationary state estimation. In addition, we present and analyze a resilient distributed diffusion algorithm that is resilient to any data falsification attack in which the number of compromised agents in the local neighborhood of a normal agent is bounded. The proposed algorithm guarantees that all normal agents converge to their true target states if appropriate parameters are selected. We also analyze trade-off between the resilience of distributed diffusion and its performance in terms of steady-state mean-square-deviation (MSD) from the correct estimates. Finally, we evaluate the proposed attack models and resilient distributed diffusion algorithm using stationary and non-stationary multi-target localization.

Embedding networks into a fixed dimensional feature space, while preserving its essential structural properties is a fundamental task in graph analytics. These feature vectors (graph descriptors) are used to measure the pairwise similarity between graphs. This enables applying data mining algorithms (e.g classification, clustering, or anomaly detection) on graph-structured data which have numerous applications in multiple domains. State-of-the-art algorithms for computing descriptors require the entire graph to be in memory, entailing a huge memory footprint, and thus do not scale well to increasing sizes of real-world networks. In this work, we propose streaming algorithms to efficiently approximate descriptors by estimating counts of sub-graphs of order \(k\le 4\), and thereby devise extensions of two existing graph comparison paradigms: the Graphlet Kernel and NetSimile. Our algorithms require a single scan over the edge stream, have space complexity that is a fraction of the input size, and approximate embeddings via a simple sampling scheme. Our design exploits the trade-off between available memory and estimation accuracy to provide a method that works well for limited memory requirements. We perform extensive experiments on real-world networks and demonstrate that our algorithms scale well to massive graphs.

In this paper, we study the resilient vector consensus problem in networks with adversarial agents and improve resilience guarantees of existing algorithms. A common approach to achieving resilient vector consensus is that every non-adversarial (or normal) agent in the network updates its state by moving towards a point in the convex hull of its normal neighbors’ states. Since an agent cannot distinguish between its normal and adversarial neighbors, computing such a point, often called safe point, is a challenging task. To compute a safe point, we propose to use the notion of centerpoint , which is an extension of the median in higher dimensions, instead of the Tverberg partition of points, which is often used for this purpose. We discuss that the notion of centerpoint provides a complete characterization of safe points in R d . In particular, we show that a safe point is essentially an interior centerpoint if the number of adversaries in the neighborhood of a normal agent i is less than N i d + 1 , where d is the dimension of the state vector and N i is the total number of agents in the neighborhood of i . Consequently, we obtain necessary and sufficient conditions on the number of adversarial agents to guarantee resilient vector consensus. Further, by considering the complexity of computing centerpoints, we discuss improvements in the resilience guarantees of vector consensus algorithms and compare with the other existing approaches. Finally, we numerically evaluate our approach.

To observe and control a networked system, especially in failure-prone circumstances, it is imperative that the underlying network structure be robust against node or link failures. A common approach for increasing network robustness is redundancy: deploying additional nodes and establishing new links between nodes, which could be prohibitively expensive. This paper addresses the problem of improving structural robustness of networks without adding extra links. The main idea is to ensure that a small subset of nodes, referred to as the trusted nodes, remains intact and functions correctly at all times. We extend two fundamental metrics of structural robustness with the notion of trusted nodes, network connectivity, and $r$ -robustness, and then show that by controlling the number and location of trusted nodes, any desired connectivity and robustness can be achieved without adding extra links. We study the complexity of finding trusted nodes and construction of robust networks with trusted nodes. Finally, we present a resilient consensus algorithm with trusted nodes and show that, unlike existing algorithms, resilient consensus is possible in sparse networks containing few trusted nodes.

Background The preparation consisting of a head-fixed mouse on a spherical or cylindrical treadmill offers unique advantages in a variety of experimental contexts. Head fixation provides the mechanical stability necessary for optical and electrophysiological recordings and stimulation. Additionally, it can be combined with virtual environments such as T-mazes, enabling these types of recording during diverse behaviors. New method In this paper we present a low-cost, easy-to-build acquisition system, along with scalable computational methods to quantitatively measure behavior (locomotion and paws, whiskers, and tail motion patterns) in head-fixed mice locomoting on cylindrical or spherical treadmills. Existing methods Several custom supervised and unsupervised methods have been developed for measuring behavior in mice. However, to date there is no low-cost, turn-key, general-purpose, and scalable system for acquiring and quantifying behavior in mice. Results We benchmark our algorithms against ground truth data generated either by manual labeling or by simpler methods of feature extraction. We demonstrate that our algorithms achieve good performance, both in supervised and unsupervised settings. Conclusions We present a low-cost suite of tools for behavioral quantification, which serve as valuable complements to recording and stimulation technologies being developed for the head-fixed mouse preparation.

A cognitive radio network has a high promise to improve spectrum utilization, through exploitation of spectrum holes from the primary network. However, in a distributed environment, employing contention based random access, collisions and unattempted slots result in waste of the discovered holes. This waste is even costlier for a CRN as resources are consumed in finding the holes. In this paper, we have proposed a self-organizing distributed CR-MAC protocol so that the contention is not required for medium access, thereby, minimizing the waste of opportunity due to collisions or for being left idle in random access, consequently, improving the spectral efficiency. This is achieved by organizing and queuing the active secondary users through a timer value and directing them in an orderly fashion to use the discovered holes. The proposed scheme successfully assigns a channel to more than 99% of the secondary users in less than 5% of the idle slots from the primary network, compared to that required in contention based random access schemes.

Sensor networks monitoring spatially distributed physical systems often comprise battery-powered sensor devices. To extend lifetime, battery power may be conserved using sleep scheduling : activating and deactivating some of the sensors from time to time. Scheduling sensors with the goal of maximizing average coverage, which is the average fraction of time for which each monitoring target is covered by some active sensor, have been studied extensively. However, many applications also require time-critical monitoring in the sense that one has to minimize the average delay until an unpredictable change or event at a monitoring target is detected. In this letter, we study the problem of sleep scheduling sensors to minimize the average delay in detecting such time-critical events in the context of monitoring physical systems that can be modeled using graphs, such as water-distribution networks. We provide a game-theoretic solution that computes schedules with near optimal average delays. We illustrate that schedules that optimize average coverage may result in large average detection delays, whereas schedules minimizing average detection delays using our proposed scheme also result in near optimal average coverage.

We investigate the impact of players with heterogeneous update rules on the long-term behavior of a population under stochastic learning dynamics. We show that under certain conditions, the presence of even a single heterogeneous player with a different decision making strategy can significantly alter the long-term behavior of the entire population. To quantify the impact of a heterogeneous player, we define a new notion of robustness of stochastic learning dynamics to player heterogeneity. Based on our proposed notion, an action profile that is stochastically stable under the standard setup is robust to player heterogeneity if it can still explain the long-run behavior of all the players other than the heterogeneous players. We consider two types of heterogeneous players: A confused player who randomly updates his actions and a stubborn player who never updates his action. For each of these types, we present a qualitative description of scenarios in which an action profile that is stochastically stable under the standard setup is not robust to the presence of a heterogeneous player of a particular type.

A network of agents with linear dynamics is strong structurally controllable if agents can be maneuvered from any initial state to any final state independently of the coupling strengths between agents. If a network is not strong structurally controllable with given input nodes (leaders), then the dimension of strong structurally controllable subspace quantifies the extent to which a network can be controlled by the same inputs. Computing this dimension exactly is computationally challenging. In this paper, we study the problem of computing a sharp lower bound on the dimension of strong structurally controllable subspace in networks with Laplacian dynamics. The bound is based on a sequence of vectors containing distances between leaders and the remaining nodes in the underlying network graph. Such vectors are referred to as the distance-to-leader vectors. We provide a polynomial time algorithm to compute a desired sequence of distance-to-leader vectors with a fixed set of leaders, which directly provides a lower bound on the dimension of strong structurally controllable subspace. We also present a linearithmic approximation algorithm to compute such a sequence, which provides near optimal solutions in practice. Finally, we numerically evaluate and compare our bound with other bounds in the literature on various networks.

A networked system can be made resilient against adversaries and attacks if the underlying network graph is structurally robust. For instance, to achieve distributed consensus in the presence of adversaries, the underlying network graph needs to satisfy certain robustness conditions. A typical approach to making networks structurally robust is to strategically add extra links between nodes, which might be prohibitively expensive. In this paper, we propose an alternative way of improving network's robustness, that is by considering heterogeneity of nodes. Nodes in a network can be of different types and can have multiple variants. As a result, different nodes can have disjoint sets of vulnerabilities, which means that an attacker can only compromise a particular type of nodes by exploiting a particular vulnerability. We show that, by such a diversification of nodes, attacker's ability to change the underlying network structure is significantly reduced. Consequently, even a sparse network with heterogeneous nodes can exhibit the properties of a structurally robust network. Using these ideas, we propose a distributed control policy that utilizes heterogeneity in the network to achieve resilient consensus in adversarial environment. We extend the notion of $(r,s)$-robustness to incorporate the diversity of nodes and provide necessary and sufficient conditions to guarantee resilient distributed consensus in heterogeneous networks. Finally we study the properties and construction of robust graphs with heterogeneous nodes., 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems (NecSys) 2019

In this paper, we demonstrate a conflicting relationship between two crucial properties---controllability and robustness---in linear dynamical networks of diffusively coupled agents. In particular, for any given number of nodes $N$ and diameter $D$, we identify networks that are maximally robust using the notion of Kirchhoff index and then analyze their strong structural controllability. For this, we compute the minimum number of leaders, which are the nodes directly receiving external control inputs, needed to make such networks controllable under all feasible coupling weights between agents. Then, for any $N$ and $D$, we obtain a sharp upper bound on the minimum number of leaders needed to design strong structurally controllable networks with $N$ nodes and diameter $D$. We also discuss that the bound is best possible for arbitrary $N$ and $D$. Moreover, we construct a family of graphs for any $N$ and $D$ such that the graphs have maximal edge sets (maximal robustness) while being strong structurally controllable with the number of leaders in the proposed sharp bound. We then analyze the robustness of this graph family. The results suggest that optimizing robustness increases the number of leaders needed for strong structural controllability. Our analysis is based on graph-theoretic methods and can be applied to exploit network structure to co-optimize robustness and controllability in networks., IEEE Transactions on Control of Network Systems

In a networked system, any change in the underlying network structure, such as node and link removals due to an attack, could severely affect the overall system behavior. Typically, by adding more links and connections between nodes, networks can be made structurally robust. However, this approach is not always feasible, especially in sparse networks. In this paper, we aim to improve the structural robustness in networks using the notions of diversity and trustiness. Diversity means that nodes in a network are of different types and have many variants. Trustiness means that a small subset of nodes are immune to failures and attacks. We show that by combining diversity and trustiness within the network, we can significantly limit the attacker's ability to change the underlying network structure by strategically removing nodes. Using pairwise connectivity as a measure, we show that by appropriately distributing trusted nodes and assigning types to nodes, network robustness can be significantly improved. We analyze the complexity of diversifying and computing a set of trusted nodes, and then present heuristics to compute attacks consisting of node removals. We also present heuristics to defend networks against such attacks by distributing node types and trusted nodes. Finally, we evaluate our results on various networks to demonstrate the usefulness of our approach.

Multi-task learning aims to enhance the performance of a model by inductive transfer of information among tasks. However, joint optimization of multiple tasks is challenging due to unbalanced data ranges and variations in task difficulties which can cause the model to converge only for a single task which has large values. To address these problems, we propose a novel weighting scheme based on validation loss. The proposed weighted scheme is evaluated on three datasets, including publicly available Comma.ai and Udacity benchmark dataset and GTA-V dataset. Our experiments demonstrate the superior performance of the proposed approach compared to the current state-of-the-art methods.

In Wireless Sensor Networks (WSNs) packet size optimization is serious issue concerned with the performance of the network. In WSNs environment the packets which are longer in size may experience the loss rates which are higher and as a result there will be a lot of retransmission whereas the packets which are shorter in size may experience more overhead because the overhead is associated with each packet. For that reason the optimum packet size selection is very significant for the performance of WSNs environment. In this research different techniques of packet optimization for Terrestrial Wireless Sensor Networks (TWSNs) environment are analyzed in detail. This research will encourage the research community for further exploring this area of research in order to identify and resolve more challenging issues.

Retinal blood vessels are considered to be the reliable diagnostic biomarkers of ophthalmologic and diabetic retinopathy. Monitoring and diagnosis totally depends on expert analysis of both thin and thick retinal vessels which has recently been carried out by various artificial intelligent techniques. Existing deep learning methods attempt to segment retinal vessels using a unified loss function optimized for both thin and thick vessels with equal importance. Due to variable thickness, biased distribution, and difference in spatial features of thin and thick vessels, unified loss function are more influential towards identification of thick vessels resulting in weak segmentation. To address this problem, a conditional patch-based generative adversarial network is proposed which utilizes a generator network and a patch-based discriminator network conditioned on the sample data with an additional loss function to learn both thin and thick vessels. Experiments are conducted on publicly available STARE and DRIVE datasets which show that the proposed model outperforms the state-of-the-art methods.

We address the problem of distributed state estimation of a linear dynamical process in an attack-prone environment. A network of sensors, some of which can be compromised by adversaries, aim to estimate the state of the process. In this context, we investigate the impact of making a small subset of the nodes immune to attacks, or “trusted”. Given a set of trusted nodes, we identify separate necessary and sufficient conditions for resilient distributed state estimation. We use such conditions to illustrate how even a small trusted set can achieve a desired degree of robustness (where the robustness metric is specific to the problem under consideration) that could otherwise only be achieved via additional measurement and communication-link augmentation. We then establish that, unfortunately, the problem of selecting trusted nodes is NP-hard. Finally, we develop an attack-resilient, provably-correct distributed state estimation algorithm that appropriately leverages the presence of the trusted nodes.

Use of Motor Imagery in EEG signals is gaining importance to develop Brain Computer Interface (BCI) applications in various fields ranging from bio-medical to entertainment. Filter Bank Common Spatial Pattern (FBCSP) algorithm is a promising feature extraction technique to deal with subject-specific behavior in Motor Imagery classification. Using FBCSP on EEG we have developed an accurate but less computationally expensive approach by making use of Time Domain Parameters (TDP) and Band Power (BP) features to form a combined feature set. The novelty of our approach is also the use of optimal time segmentation to overcome non-stationary state behavior of Event-Related Desynchronization (ERD) and Event-Related Synchronization (ERS) over time. We analyzed the impact of parameter variations on classification accuracy and achieved 0.59 mean kappa value for Dataset 2a BCI competition IV, the highest reported for FBCSP approaches, along with the lowest inter-subject variation.

Use of Motor Imagery in EEG signals is gaining importance to develop Brain Computer Interface (BCI) applications in various fields ranging from bio-medical to entertainment and its classification at lower complexity in EEG signals is gaining importance. Filter Bank Common Spatial Pattern (FBCSP) has been a promising feature extraction approach to deal with subject-specific behavior in Motor Imagery classification. Though its computational complexity has been on the lower side, the approach has not yet matched the classification accuracy of non-FBCSP approaches. By introducing a combined feature set of Band Power (BP) features and Time Domain (TDP) features in FBCSP approach we have succeeded in proposing an approach of high classification accuracy while out competing the computational complexity of the best reported non-FBCSP approaches. We have also analyzed the impact of parameter variations on classification accuracy and achieved 0.59 mean kappa value for Dataset 2a BCI competition IV on four class problem. This is the highest reported for FBCSP approaches along with the lowest inter-subject variation.

As the Industrial Internet of Things (IIot) becomes more prevalent in critical application domains, ensuring security and resilience in the face of cyber-attacks is becoming an issue of paramount importance. Cyber-attacks against critical infrastructures, for example, against smart water-distribution and transportation systems, pose serious threats to public health and safety. Owing to the severity of these threats, a variety of security techniques are available. However, no single technique can address the whole spectrum of cyber-attacks that may be launched by a determined and resourceful attacker. In light of this, we consider a multi-pronged approach for designing secure and resilient IIoT systems, which integrates redundancy, diversity, and hardening techniques. We introduce a framework for quantifying cyber-security risks and optimizing IIoT design by determining security investments in redundancy, diversity, and hardening. To demonstrate the applicability of our framework, we present two case studies in water distribution and transportation a case study in water-distribution systems. Our numerical evaluation shows that integrating redundancy, diversity, and hardening can lead to reduced security risk at the same cost.

In recent years, state-of-the-art traffic-control devices have evolved from standalone hardware to networked smart devices. Smart traffic control enables operators to decrease traffic congestion and environmental impact by acquiring real-time traffic data and changing traffic signals from fixed to adaptive schedules. However, these capabilities have inadvertently exposed traffic control to a wide range of cyber-attacks, which adversaries can easily mount through wireless networks or even through the Internet. Indeed, recent studies have found that a large number of traffic signals that are deployed in practice suffer from exploitable vulnerabilities, which adversaries may use to take control of the devices. Thanks to the hardware-based failsafes that most devices employ, adversaries cannot cause traffic accidents directly by setting compromised signals to dangerous configurations. Nonetheless, an adversary could cause disastrous traffic congestion by changing the schedule of compromised traffic signals, thereby effectively crippling the transportation network. To provide theoretical foundations for the protection of transportation networks from these attacks, we introduce a game-theoretic model of launching, detecting, and mitigating attacks that tamper with traffic-signal schedules. We show that finding optimal strategies is a computationally challenging problem, and we propose efficient heuristic algorithms for finding near optimal strategies. We also introduce a Gaussian-process based anomaly detector, which can alert operators to ongoing attacks. Finally, we evaluate our algorithms and the proposed detector using numerical experiments based on the SUMO traffic simulator.

In Brain-Computer Interface (BCI) Research,Electroencephalography (EEG) has obtained great attention for biomedical applications. In BCI system, feature representation and classification are important tasks as the accuracy of classification highly depends on these stages. In this paper, we propose a model in which Common Spatial Pattern (CSP) is used to discriminate inter-class data using co-variance maximization and Fast Fourier Transform Energy Map (FFTEM) is used for feature selection and mapping of 1D data into 2D data (energy maps). Convolutional Neural Network is used for classification of multi-class Motor Imagery (MI) signals. Further, this paper investigates near-optimal parameter selection for feature mapping, frequency bands selection, and temporal segmentation. It is shown that our proposed method outperformed the reported methods by achieving 0.61 mean kappa value.

A necessary condition for global performance guarantees in most of the motion coordination algorithms is connectivity of the underlying network topology. In proximity networks, connectivity maintenance becomes critical because the neighborhood set of each agent is dynamic and depends on the locations of all the other agents in the network. We present an efficient framework for distributed motion coordination in proximity networks. The proposed framework relies on identifying agents in a so called weakly connected dominating (WCD) set of the underlying network graph. Maintaining only the edges incident to the agents in WCD, which we call as critical edges, preserves the connectivity of the overall network. The proposed framework is presented in the context of rendezvous problem, which is selected because of its canonical importance in distributed systems with mobile agents. We propose a controller that drives all the agents to a common point by preserving the critical edges only. The proposed scheme is robust to failure of edges that are not critical and nodes that do not belong to WCD. Moreover, it performs well in terms of energy consumption and computational complexity.

Routing hole problem is one of the most important issues in the underwater wireless sensor networks (UWSNs). It aims to analyze the routing hole boundary to prevent the formation of routing hole such that network lifetime and all other parameters are also increased. In this paper, we have proposed the two techniques to transmit the data in the presence of routing hole. In our protocol, the nodes transmit the data on the basis of an energy gradation (EG) and depth adjustment (DA) of the void nodes. However, these techniques are used for avoidance of routing hole. The efficient load balanced routing (ELBAR) using DA performed better than other two schemes. Simulation results depict that our schemes perform the better role in terms of energy efficiency, lifetime, deviation of energy consumption, path length and euclidean stretch.

We investigate the coverage efficiency of a sensor network consisting of sensors with circular sensing footprints of different radii. The objective is to completely cover a region in an efficient manner through a controlled (or deterministic) deployment of such sensors. In particular, it is shown that when sensing nodes of two different radii are used for complete coverage, the coverage density is increased, and the sensing cost is significantly reduced as compared to the homogeneous case, in which all nodes have the same sensing radius. Configurations of heterogeneous disks of multiple radii to achieve efficient circle coverings are presented and analyzed.

Automatic recognition of isolated spoken digits is one of the most challenging tasks in the area of Automatic Speech Recognition. In this paper, Database Development and Automatic Speech Recognition of Isolated Pashto Spoken Digits from Sefer (0) to Naha (9) has been presented. A number of 50 individual Pashto native speakers (25 male and 25 female) of different ages, ranging from 18 to 60 years, were involved to utter from Sefer (0) to Naha (9) digits separately. Sony PCM-M 10 linear recorder is used for recoding purpose in the office and home in noise free environment. Adobe audition version 1.0 is used to split the audio of digits into individual digits and result is saved in .wav format. Mel frequency cepstral coefficients is used to extract speech features. K nearest neighbor classifier is used for the first time up to author knowledge in Pashto language to classify the features of speech and compare its accuracy with linear discriminate analysis. The experimental results are evaluated, and the overall average recognition exactitude of 76.8 % is obtained.