Sensor Selection Problem Research Articles

Gaussian process-based online sensor selection for source localization

This paper addresses the sensor selection problem for source localization within cyber–physical systems (CPSs). While recent machine learning and reinforcement learning approaches aim to optimize sensor selection and placement within the Area of Interest (AoI), their need for intensive data collection and training precludes online operation. Furthermore, these methods often require prior knowledge of the unknown source’s characteristics and lack adaptability to the dynamic nature of CPSs, leading to inefficiencies in unseen environments. This paper addresses these shortcomings using Gaussian process Optimization coupled with an active sensor selection mechanism to locate the unknown source within the AoI. The proposed approach first builds a probabilistic model of the environment, which is discretized into a grid, without prior training using a Gaussian Process surrogate model. Next, the model iteratively and systematically learns the underlying spatial phenomenon using Gaussian Process optimization. Concurrently, the approach selects a subset of sensors by optimizing a fitness function that advocates selecting informative and energy-efficient sensors. Next, the probabilistic model, having accurately learned the environment, directs the algorithm to the unknown source by identifying the cell with the highest likelihood of containing it. Finally, a peak refinement step is performed, which computes the exact location of the source within the designated cell. The proposed method’s efficacy is validated through experiments in radioactive source localization, validation studies, and adaptability assessments across various environments. In terms of quality of localization (QoL), it outperforms recent localization benchmarks, such as a reinforcement learning-based approach and DANS, by around 18% and 100%, respectively.

Group-feature (Sensor) selection with controlled redundancy using neural networks

In this work, we present a novel embedded feature selection method based on a Multi-layer Perceptron (MLP) network and generalize it for group-feature or sensor selection problems, which can control the level of redundancy among the selected features or groups and it is computationally more efficient than the existing ones in the literature. Additionally, we have generalized the group lasso penalty for feature selection to encompass a mechanism for selecting valuable groups of features while simultaneously maintaining control over redundancy. We establish the monotonicity and convergence of the proposed algorithm, with a smoothed version of the penalty terms, under suitable assumptions. The effectiveness of the proposed method for both feature selection and group feature selection is validated through experimental results on various benchmark datasets. The performance of the proposed methods is compared with some state-of-the-art methods.

Mobile Sensor Path Planning for Kalman Filter Spatiotemporal Estimation.

The estimation of spatiotemporal data from limited sensor measurements is a required task across many scientific disciplines. In this paper, we consider the use of mobile sensors for estimating spatiotemporal data via Kalman filtering. The sensor selection problem, which aims to optimize the placement of sensors, leverages innovations in greedy algorithms and low-rank subspace projection to provide model-free, data-driven estimates. Alternatively, Kalman filter estimation balances model-based information and sparsely observed measurements to collectively make better estimation with limited sensors. It is especially important with mobile sensors to utilize historical measurements. We show that mobile sensing along dynamic trajectories can achieve the equivalent performance of a larger number of stationary sensors, with performance gains related to three distinct timescales: (i) the timescale of the spatiotemporal dynamics, (ii) the velocity of the sensors, and (iii) the rate of sampling. Taken together, these timescales strongly influence how well-conditioned the estimation task is. We draw connections between the Kalman filter performance and the observability of the state space model and propose a greedy path planning algorithm based on minimizing the condition number of the observability matrix. This approach has better scalability and computational efficiency compared to previous works. Through a series of examples of increasing complexity, we show that mobile sensing along our paths improves Kalman filter performance in terms of better limiting estimation and faster convergence. Moreover, it is particularly effective for spatiotemporal data that contain spatially localized structures, whose features are captured along dynamic trajectories.

Sparse sensor selection for distributed systems: An [formula omitted]-relaxation approach

We study the problem of sensor selection for distributed systems, where a large number of sensors are located spatially in many different locations. Specifically, we consider both perfect and packet-dropping communication channels. While the original problem is NP-hard, by adopting a sparse design, we can solve the problem via convex optimization and reduce the computation cost significantly. Our method not only handles correlated measurement noise but also can be easily extended to actuator selection or sensor-and-actuator (SaA) selection problems. Simulation shows that our sparsity-based approach performs similarly to the brute force optimal strategy while consuming significantly less computation time. Additionally, our method is shown to outperform the state-of-art method notably.

Optimal Placement of Sensors in Traffic Networks Using Global Search Optimization Techniques Oriented towards Traffic Flow Estimation and Pollutant Emission Evaluation

The relationship between estimating traffic flow and evaluating pollutant emissions lies in understanding how vehicular traffic patterns affect air quality. Traffic flow estimation is a complex field that involves a variety of analytical techniques to understand, predict, and manage the flow of vehicles on road networks. Different types of analyses commonly employed in this area are statistical analysis (e.g., descriptive statistics, inferential statistics, time series analysis), mathematical modeling (macroscopic models, microscopic models, mesoscopic models), computational methods (e.g., simulation modeling, machine learning, and AI techniques), geospatial analysis (e.g., geographic information systems (GISs), spatial data analysis), network analysis (e.g., graph theory and network flow models). In sensor network setups, the strategic placement of sensors is crucial, primarily due to the challenges posed by limited energy supplies, restricted storage capabilities, and the demands on processing and communication, all of which significantly impact maintenance costs and hardware limitations. To mitigate the burden on processing and communication, it is essential to deploy a limited number of sensors strategically. In practical applications, achieving an optimal layout of physical sensors (i.e., placing sensors within the network in such a way as to meet a specific optimality criterion, such as identifying the minimum number of sensors required to ensure the ability to design reliable state observers capable of reconstructing the network’s state based on the available data) is essential for the accurate monitoring of large-scale systems, including traffic flow or the distribution networks of water and gas. In the context of traffic systems, addressing the challenge of full link flow observability, that is, the ability to accurately monitor and assess the flow of entities (i.e., vehicles) across all the links or pathways within a network, entails selecting the smallest number of traffic sensors from a larger set to install. The goal is to choose a subset of p sensors, which may include redundancies, from a pool of n>>p potential sensors. This is conducted to maintain the structural observability of the entire traffic network. This concept pertains to deducing the complete internal state (traffic volume on each road link in the network) from external outputs and inputs (measurements from sensors). The traditional concept of system observability serves as a criterion for sensor placement. This article presents the development of a simulated annealing heuristic to address the selection problem. The selected sensors are then applied to construct a Luenberger observer, a mathematical construct used in control theory to accurately estimate the internal state of a dynamic system based on its inputs and outputs. Numerical simulations are carried out to demonstrate the effectiveness of this method, and a performance analysis using a digital twin of a transport network, designed using the Aimsun Next software, are also carried out to assess traffic flow and associated pollutant emissions. In particular, we examine a traffic network comprising 21 roads. We address the sensor selection problem by identifying an optimal set of six sensors, which facilitates the design of a Luenberger observer. This observer enables the reconstruction of traffic flow across the network with minimal estimation error. Furthermore, by integrating this observer with data from the Aimsun Next software, we assess the pollutant emissions related to traffic flow. The results indicate a high accuracy in estimating pollutant levels.

Black widow optimization for reducing the target uncertainties in localization wireless sensor networks

Abstract Localization Wireless Sensor Networks (WSN) represent a research topic with increasing interest due to their numerous applications. However, the viability of these systems is compromised by the attained localization uncertainties once implemented, since the network performance is highly dependent on the sensors location. The Node Location Problem (NLP) aims to obtain the optimal distribution of sensors for a particular environment, a problem already categorized as NP-Hard. Furthermore, localization WSN usually perform a sensor selection for determining which nodes are to be utilized for maximizing the achieved accuracy. This problem, defined as the Sensor Selection Problem (SSP), has also been categorized as NP-Hard. While different metaheuristics have been proposed for attaining a near optimal solution in both problems, no approach has considered the two problems simultaneously, thus resulting in suboptimal solutions since the SSP is biased by the actual node distribution once deployed. In this paper, a combined approach of both problems simultaneously is proposed, thus considering the SSP within the NLP. Furthermore, a novel metaheuristic combining the Black Widow Optimization (BWO) algorithm and the Variable Neighbourhood Descent Chains (VND-Chains) local search, denominated as BWO-VND-Chains, is particularly devised for the first time in the author’s best knowledge for the NLP, resulting in a more efficient and robust optimization technique. Finally, a comparison of different metaheuristic algorithms is proposed over an actual urban scenario, considering different sensor selection criteria in order to attain the best methodology and selection technique. Results show that the newly devised algorithm with the SSP criteria optimization achieves mean localization uncertainties up to 19.66 % lower than traditional methodologies.

The Differentiated Creative Search (DCS): Leveraging differentiated knowledge-acquisition and creative realism to address complex optimization problems

This article introduces differentiated creative search (DCS), a groundbreaking optimization algorithm that revolutionizes traditional decision-making systems in complex environments. In contrast to conventional differential evolution methods, DCS integrates a unique knowledge-acquisition process with a creative realism paradigm, thereby transforming optimization strategies. The primary aim of DCS is to enhance decision-making efficacy by employing a newly proposed dual-strategy approach that balances divergent and convergent thinking within a team-based framework. High-performing members apply divergent thinking via the DCS/Xrand/Linnik(α,σ) strategy, which incorporates existing knowledge and Linnik flights. Conversely, the remaining team harnesses convergent thinking through the DCS/Xbest/Current-to-2rand strategy, which combines insights from both the team leader and fellow members. This division of labor, coupled with a strategy tailored to the performance levels of team members, allows for a dynamic and effective decision-making process. The methodology of DCS involves iterative cycles of divergent and convergent thinking, supported by a differentiated knowledge-acquisition process and retrospective assessments. The algorithm's novelty lies in its differentiated knowledge-acquisition, adjusted based on individual team member performance, fostering an environment of continuous learning and adaptation. The paper's contributions are demonstrated through rigorous testing of DCS on various benchmark functions, including CEC2017, classical, and sensor selection problems, as well as real-world applications such as car side impact design, gear train design, and FM sound wave parameter estimation. The results showcase the promising performance of DCS compared to that of existing algorithms, attributable to its innovative approach to problem solving and decision making in complex scenarios. The results and impact section highlights that DCS considerably outperforms traditional optimization algorithms, offering a robust and versatile tool for complex decision-making systems. Its impact is particularly notable in scenarios requiring a balance between innovative solutions and practical decision-making, making DCS a valuable asset in strategic planning and execution across various industries.

Optimal microphone selection for aero-engine acoustic measurement

Acoustic testing is crucial in the aero-engine design process, providing valuable information about the sound field in terms of acoustic modes. The conventional use of a uniform sampling array limits the achievable resolution for a given number of sensors, necessitating the use of a large number of sensors to achieve high-resolution estimates. This limitation may be overcome using a non-uniform sensing array. In this work, we propose an optimal microphone selection scheme to determine which microphone placements that are preferable given the typically available a priori knowledge of the relevant acoustic modes. Using a weighted A-optimality criterion, we formulate the sensor selection problem as the one minimizing the expected variance of the resulting parameter estimates. Using both numerical and measured data sets, we illustrate how the proposed scheme allows for improved performance as compared to random and uniform sensor placement schemes.

Greedy selection of sensors with measurements under correlated noise

We address the sensor selection problem where linear measurements under correlated noise are gathered at the selected nodes to estimate the unknown parameter. Since finding the best subset of sensor nodes that minimizes the estimation error requires a prohibitive computational cost especially for a large number of nodes, we propose a greedy selection algorithm that uses the log-determinant of the inverse estimation error covariance matrix as the metric to be maximized. We further manipulate the metric by employing the QR and LU factorizations to derive a simple analytic rule which enables an efficient selection of one node at each iteration in a greedy manner. We also make a complexity analysis of the proposed algorithm and compare with different selection methods, leading to a competitive complexity of the proposed algorithm. For performance evaluation, we conduct numerical experiments using randomly generated measurements under correlated noise and demonstrate that the proposed algorithm achieves a good estimation accuracy with a reasonable selection complexity as compared with the previous novel selection methods.

Decentralized fused-learner architectures for Bayesian reinforcement learning

Decentralized training is a robust solution for learning over an extensive network of distributed agents. Many existing solutions involve the averaging of locally inferred parameters which constrain the architecture to independent agents with identical learning algorithms. Here, we propose decentralized fused-learner architectures for Bayesian reinforcement learning, named fused Bayesian-learner architectures (FBLAs), that are capable of learning an optimal policy by fusing potentially heterogeneous Bayesian policy gradient learners, i.e., agents that employ different learning architectures to estimate the gradient of a control policy. The novelty of FBLAs relies on fusing the full posterior distributions of the local policy gradients. The inclusion of higher-order information, i.e., probabilistic uncertainty, is employed to robustly fuse the locally-trained parameters. FBLAs find the barycenter of all local posterior densities by minimizing the total Kullback–Leibler divergence from the barycenter distribution to the local posterior densities. The proposed FBLAs are demonstrated on a sensor-selection problem for Bernoulli tracking, where multiple sensors observe a dynamic target and only a subset of sensors is allowed to be active at any time.

A General Scheme of a Branch-and-Bound Approach for the Sensor Selection Problem in Near-Field Broadband Beamforming.

This paper is devoted to the sensor selection problem. A broadband receiver beamforming working in a near-field is considered. The system response should be as close as possible to the desired one, which is optimized in the sense of L2 norm. The problem considered is at least NP-hard. Therefore, the branch-and-bound algorithm is developed to solve the problem. The proposed approach is universal and can be applied not only to microphone arrays but also to antenna arrays; that is, the methodology for the generation of consecutive solutions can be applied to different types of sensor selection problems. Next, for a larger microphone array, an efficient metaheuristic algorithm is constructed. The algorithm implemented is a hybrid genetic algorithm based on the ITÖ process. Numerical experiments show that the proposed approach can be successfully applied to the sensor selection problem.

Convex optimization approach to design sensor networks using information theoretic measures

AbstractAccurate and precise estimation of process variables is key to effective process monitoring. The estimation accuracy depends on the choice of the sensor network. Therefore, the article aims at developing convex optimization formulations for designing the optimal sensor network using information‐theoretic measures in linear steady‐state data reconciliation. To this end, the estimation errors are characterized by a multivariate Gaussian distribution, and thus the analytical form for entropy and Kullback–Leibler divergences (forward, reverse, and symmetric) of estimation errors can be obtained to formulate the optimal sensor network design. The proposed information theoretic‐based optimal sensor selection problems are shown to be integer semi‐definite programming problems where the relaxation of binary decision variables results in solving a convex optimization problem. Thus, we use a branch and bound method to obtain a globally optimal sensor network design. Demonstrative case studies are presented to illustrate the efficacy of the proposed optimal sensor selection formulations.

Sensor selection for remote state estimation with QoS requirement constraints

In this paper, we study the sensor selection problem for remote state estimation under the Quality-of-Service (QoS) requirement constraints. Multiple sensors are employed to observe a linear time-invariant system, and their measurements should be transmitted to a remote estimator for state estimation. However, due to the limited communication resources and the QoS requirement constraints, only some of the sensors can be allowed to transmit their measurements. To estimate the system state as accurately as possible, it is essential to select sensors for transmission appropriately. We formulate the sensor selection problem as a non-convex optimization problem. It is difficult to solve such a problem and even to find a feasible solution. To obtain a solution which can achieve good estimation performance, we first reformulate and relax the formulated problem. Then, we propose an algorithm based on successive convex approximation (SCA) to solve the relaxed problem. By utilizing the solution of the relaxed problem, we propose a heuristic sensor selection algorithm which can provide a good suboptimal solution. Simulation results are presented to show the effectiveness of the proposed heuristic.

SELECTION OF WEARABLE SENSORS FOR HEALTH AND SAFETY USE IN THE CONSTRUCTION INDUSTRY

Construction industry workers; are exposed to serious safety and health risks, hazardous work environments, and intense physical work. This situation causes fatal and non-fatal accidents, reduces productivity, and causes a loss of money and time. Construction safety management can use wearable sensors to improve safety performance. Since there are many types of sensors and not all sensors can be used in construction applications, it is necessary to identify suitable and reliable sensors. This requirement causes a sensor selection problem. The study aims to determine the priority order of physiological and kinematic sensors in preventing risks in the construction industry. Within the scope of this purpose, five criteria and seven alternatives were determined in line with the literature research and expert opinions. The criteria weights were calculated with the AHP method, and the alternatives were ranked with PROMETHEE and AHP. Providing a proactive approach to the use of sensors in the construction industry will provide safer working conditions, identify workers at risk, and help identify and predict potential health and safety risks. It will contribute to the literature on improving construction health and safety management.

Sensor network design for post-combustion CO[formula omitted] capture plants: Computational efficiency and robustness

State estimation is crucial for the monitoring and control of post-combustion CO2 capture plants (PCCPs). The performance of state estimation is highly reliant on the configuration of sensors. In this work, we consider the problem of sensor selection for PCCPs and propose a computationally efficient method to determine an appropriate number of sensors and the corresponding placement of the sensors. The objective is to find the (near-)optimal set of sensors that provides the maximum degree of observability for state estimation while satisfying the budget constraint. Specifically, we resort to the information in the sensitivity matrix calculated around the operating region of a PCCP to quantify the degree of observability of the entire system corresponding to the placed sensors. The sensor selection problem is converted to an optimization problem and is efficiently solved by a one-by-one removal approach through sensitivity analysis. Next, we extend our approach to study the fault tolerance of the selected sensors to sensor malfunction. The robust sensor selection problem is to find a sensor network that gives good estimation performance even when some of the sensors fail, thereby improving the overall system robustness. The robust sensor selection problem is formulated as a max–min optimization problem. We show how the proposed approach can be adapted to solve the sensor selection max–min optimization problem. By implementing the proposed approaches, the sensor network is configured for the PCCP efficiently.

Randomized Group-Greedy Method for Large-Scale Sensor Selection Problems

The randomized group-greedy method and its customized method for large-scale sensor selection problems are proposed. The randomized greedy sensor selection algorithm is applied straightforwardly to the group-greedy method, and a customized method is also considered. In the customized method, a part of the compressed sensor candidates is selected using the common greedy method or other low-cost methods. This strategy compensates for the deterioration of the solution due to compressed sensor candidates. The proposed methods are implemented based on the D- and E-optimal design of experiments, and numerical experiments are conducted using randomly generated sensor candidate matrices with potential sensor locations of 10,000--1,000,000. The proposed method can provide better optimization results than those obtained by the original group-greedy method when a similar computational cost is spent as for the original group-greedy method. This is because the group size for the group-greedy method can be increased as a result of the compressed sensor candidates by the randomized algorithm. Similar results were also obtained in the real dataset. The proposed method is effective for the E-optimality criterion, in which the objective function that the optimization by the common greedy method is difficult due to the absence of submodularity of the objective function. The idea of the present method can improve the performance of all optimizations using a greedy algorithm.

Optimal sensor selection for diagnosability enforcement of discrete event systems using labeled petri net

AbstractThis paper addresses the problem of optimal sensor selection for ensuring diagnosability of discrete event systems. Given a nondiagnosable discrete event system modeled with labeled Petri nets, a new labeling function can be designed to enforce the system to be diagnosable. An ad‐hoc parallel composition of non‐deterministic finite automata (derived from the original labeled Petri net model) that are observed at multiple observation sites is employed. In order to optimize a given labeling function as well as a sensor selection, an integer linear programming problem is formulated to associate numerical sensor costs with transition relabelings. In a multi‐fault system, this method can determine the type of faults that occur and the fault sequences pertaining to this fault type if multiple faults occur. Examples are presented to demonstrate the proposed method.

Energy-efficient secure data fusion scheme for IoT based healthcare system

The Internet of Medical Things (IoMT) ecosystem is enormous and complicated, with several smart devices constantly transferring large amounts of data. Many IoT-based healthcare devices are used to gather and transmit medical data. Consequently, IoMT faces many challenges related to energy efficiency, security, and privacy-preserving due to heterogeneous data. In IoMT, healthcare devices generate a huge volume of data and transfer it to the server, which is less secure and results in data redundancy. Therefore, there is a requirement for an energy-efficient secure data aggregation scheme as the traditional data aggregation paradigms encountered several issues for safely aggregating and transmitting healthcare data, including higher energy consumption, security, privacy, and vulnerability to attacks. In this paper, a secure data fusion-based data aggregation scheme is proposed, which optimizes energy usage and improves data quality. The proposed method uses extended belief propagation to determine the link quality of the shortest routes between sensor nodes and base station (BS) for data transmission and to reduce energy consumption. Further, the active sensor selection problem is optimized using the Archimedes Optimization Algorithm (AOA), which maximizes the spatial and temporal correlation with the passive sensor nodes to improve data quality. The proposed scheme has been implemented in NS2.35 by generating trace files and extracting results with AWK scripts. The simulation results demonstrate that our method outperforms the other state-of-the-art methods in terms of energy usage, network connectivity, reliability, computational cost, latency, and communication overhead. Thus, the proposed method is an efficient and secure data aggregation scheme for IoT-based healthcare.

Sensors Scheduling for Remote State Estimation Over an Unslotted CSMA/CA Channel

This article investigates the sensor selection problem for remote state estimation. A set of sensors measures a process's state and sends the measurements to a remote estimator over an unslotted carrier sense multiple access/collision avoidance (CSMA/CA) channel in IEEE 802.15.4-based wireless body area networks. This article aims to answer which sensors should be selected according to probability so that the state estimation error covariance and the energy consumption of sensors can be optimized. A common assumption in most existing methods about sensor scheduling is that the packet loss process is unrelated to the channel input. This article analyzes the relationship between channel input and packet loss rate by modeling the communication process. A scheduling scheme is proposed to increase channel utilization from the perspective of sensor information fusion. Then the constraint on the performance metrics is presented. By transforming the sensor selection problem into a constrained optimization problem, the solution to the optimization problem is obtained by a numerical algorithm. Finally, the validity of the model and the feasibility of the sensor scheduling are demonstrated by a numerical simulation.

Combined sensor selection and node location optimization for reducing the localization uncertainties in wireless sensor networks

Local Positioning Systems (LPS) address the limitations of Global Navigation Satellite Systems in harsh environments. LPS must attain the optimal location of their sensors in space for optimal performance, which is known as the Node Location Problem. In addition, not all the sensors under coverage present the best performance for determining the location. For this purpose, the optimal selection of the best combination of nodes requires addressing the Sensor Selection Problem. In this paper, for the first time in the literature, we present a methodology for the combined optimization of both problems which may attain improved results than separated optimizations. Results show that the consideration of SSP based sensor selection strategies during the NLP suppose a reduction up to 10% in the localization uncertainties with respect to traditional baseline sensor selection strategies of the NLP, thus proving the effectiveness of the devised technique.