Subset Of Sensors Research Articles

A data-driven adaptive algorithm and decision support design of multisensory information fusion for prognostics and health management applications

Multisensory systems play a critical role in prognostics and health management (PHM), and utilise the information from multi-device synchronous measurements for fault diagnosis and predictive maintenance. But it is not suitable for specific systems with limited bandwidth and energy reservoirs since the increased sophistication of measurement devices requires more computation and power resources. This research explores a data-driven analytical framework for multisensory system analysis and design in PHM. The proposed framework provides the optimal subset of reliable sensors to make trade-offs between accuracy demands and system constraints. The integration definition for function modelling method is adopted for modelling and functional analysis of the proposed framework. An adaptive signal conversion algorithm is designed to process the data from all reliable sensors in the system. The convolutional neural network with residual learning is built for automatic feature extraction. Combined with the evaluation rules and expert knowledge, performance analyses are obtained, including qualitative results, fault diagnosis, and the optimal sensor combination. An open-source bearing dataset of the multisensory system with five measurements is conducted to demonstrate the effectiveness and feasibility of the proposed framework.

Cross-Chamber Data Transferability Evaluation for Fault Detection and Classification in Semiconductor Manufacturing

Unit-to-unit variation among the production chambers is a long-lasting challenge for Fault Detection and Classification (FDC) development in the semiconductor industry. Currently, various methods are applied for knowledge transfer among chambers and generalized FDC model development. However, the existing methods cannot give a quantitative or qualitative measure for cross-chamber data transferability evaluation. This research proposes a novel methodology for data transferability evaluation and important sensor screening, which can serve as a data quality evaluation tool for any FDC model. In this research, firstly, Time Series Alignment Kernel (TSAK) is incorporated into Multidomain Discriminant Analysis (MDA) algorithm to achieve sensor-based domain generalization. Then, domain-invariant features are directly extracted for sensor visualization. After that, Fisher’s criterion ratios of the labeled good wafer samples and defective ones are computed based on the domain-invariant features of each sensor to quantitatively estimate how easy it is to transfer knowledge of each sensor among chambers, i.e., data transferability evaluation. Lastly, the proposed method develops a Recursive Feature Elimination (RFE)-based sensor selection algorithm to qualitatively analyze the importance of each sensor channel and identify the critical sensor subset. In this study, validation of the proposed method is based on two open-source datasets from real production lines.

Sensor Rotational Measurement with Virtual Sensors Applying Pearson Generative Adversarial Imputation Nets

Recent advances in sensor technology have increased the ability of humans to measure a wide range of phenomena and events. Nevertheless, in some cases, due to a variety of limitations, only a few sensors can be deployed at a given site. Consequently, setting up enough sensors at the right places to provide uniform monitoring can be difficult. In addition, virtual sensing, which is a set of strategies for replacing a portion of physical sensors with virtual sensors, has recently been developed. Therefore, this work leverages the imputation capability of PGAIN-VS to develop a black-box data-driven virtual sensing approach named sensor rotational measurement for the purpose of reducing the number of physical devices to be used in reality while still ensuring monitoring accuracy. The approach takes advantage of the PGAIN-VS and Borda voting methods to determine the subset of real sensors that can take turns observing information within an interval of time. The approach is seen as a black-box objective optimization problem with constraints that is solved by the OpenBox tool. We evaluated our method on several real-world datasets and achieved promising results, with the overall number of physical sensors reduced by up to 20%.

Personalized and Energy-Efficient Health Monitoring: A Reinforcement Learning Approach

We consider a network of controlled sensors that monitor the unknown health state of a patient. We assume that the health state process is a Markov chain with a transition matrix that is unknown to the controller. At each timestep, the controller chooses a subset of sensors to activate, which incurs an energy (i.e., battery) cost. Activating more sensors improves the estimation of the unknown state, which introduces an energy-accuracy tradeoff. Our goal is to minimize the combined energy and state misclassification costs over time. Activating sensors now also provides measurements that can be used to learn the model, improving future decisions. Therefore, the learning aspect is intertwined with the energy-accuracy tradeoff. While Reinforcement Learning (RL) is often used when the model is unknown, it cannot be directly applied in health monitoring since the controller does not know the (health) state. Therefore, the monitoring problem is a partially observable Markov decision process (POMDP) where the cost feedback is also only partially available since the misclassification cost is unknown. To overcome this difficulty, we propose a monitoring algorithm that combines RL for POMDPs and online estimation of the expected misclassification cost based on a Hidden Markov Model (HMM). We show empirically that our algorithm achieves comparable performance with a monitoring system that assumes a known transition matrix and quantizes the belief state. It also outperforms the model-based approach where the estimated transition matrix is used for value iteration. Thus, our algorithm can be useful in designing energy-efficient and personalized health monitoring systems.

Traffic Sensors Selection for Complete Link Flow Observability through Simulated Annealing

Sensor selection is a key issue in sensor network design. Due to limited equipment and maintenance costs, and to minimize processing and communication overhead, only a limited number of sensors can reasonably be used, and they must also be reasonably placed. Indeed, the selection of an appropriate number of physical sensors is critical to ensure reliable estimates when monitoring large-scale systems such as traffic flows, water or gas transport infrastructures, or underwater wireless sensor networks. Regarding traffic systems, the full link flow observability problem consists of selecting the minimum number of traffic sensors to be installed from a given larger set (Salari, 2019). In particular, it involves selecting a subset of p, possibly redundant, sensors from a larger set of n ≫ p potential sensors in order to preserve the structural observability property of the entire traffic network. To solve this problem, the classical concept of system observability is exploited as a criterion for sensor selection. In this paper, we refer to the design of a simulated annealing heuristic to approximately solve the problem. The resulting subset of sensors is then used to design a Luenberger observer to properly estimate the system state. Some numerical simulations demonstrate the effectiveness of the proposed approach.

Secondary Control for the Safety of LTI Systems under Attacks

We consider the problem of controller design for linear time-invariant cyber-physical systems (CPSs) controlled over a network. Specifically, we adopt the set-up that a controller has already been designed to stabilize the plant. However, the closed loop system may be subject to actuator and sensor attacks. We first perform a reachability analysis to see the effect of potential attacks. To further ensure the safety of the states of the system, we choose a subset of sensors that can be locally secured and made free of attacks. Using these limited resources, an extra controller is designed to enhance the safety of the new closed loop. The safety of the system will be characterized by the notion of safe sets. Lyapunov based analysis will be used to derive sufficient conditions that ensure the states always stay in the safe set. The conditions will then be stated as convex optimization problems which can be solved efficiently. Lastly, our theoretical results are illustrated through numerical simulations.

Energy-Efficient Sparsity-Driven Speech Enhancement in Wireless Acoustic Sensor Networks

Wireless acoustic sensor network (WASN) has shown a superiority over conventional microphone arrays in many aspects. There exists an important tradeoff between the performance and power consumption, as usually the sensors are power driven with a limited amount of battery resource. Given a prescribed performance bound, in literature sensor selection (SS) and rate allocation (RA) methods can be leveraged to optimize the energy efficiency. In this work, we propose a joint rate allocation and sensor selection (RASS) approach to simultaneously optimize the sensor subset and rate distribution, which is formulated by minimizing the total transmission power in terms of selection and bit-rate variables and constraining the residual noise power. It can be shown that under a set of linear constraints on beamforming, the linearly-constrained minimum variance (LCMV) beamformer is the optimal noise reduction filter. Based on this, the RASS reduces to a mixed semi-definite and bilinear programming problem, which is then solved using a two-step algorithm. As the selection and bit-rate unknowns are bilinear, we first consider to optimize their product, resulting in an upper bound of RASS. Then, we use McCormick envelopes to relax the bilinear constraint, resulting in a linear program. The final selection and bit-rate solutions are obtained by posterior randomized rounding. It can be shown that SS and RA are special cases of the proposed RASS. Numerical results using simulated WASNs validate the power efficiency of the proposed method as well as the robustness against dynamic factors.

Graph Signal Reconstruction Techniques for IoT Air Pollution Monitoring Platforms

Air pollution monitoring platforms play a very important role in preventing and mitigating the effects of pollution. Recent advances in the field of graph signal processing have made it possible to describe and analyze air pollution monitoring networks using graphs. One of the main applications is the reconstruction of the measured signal in a graph using a subset of sensors. Reconstructing the signal using information from sensor neighbors can help improve the quality of network data, examples are filling in missing data with correlated neighboring nodes, or correcting a drifting sensor with neighboring sensors that are more accurate. This paper compares the use of various types of graph signal reconstruction methods applied to real data sets of Spanish air pollution reference stations. The methods considered are Laplacian interpolation, graph signal processing low-pass based graph signal reconstruction, and kernel-based graph signal reconstruction, and are compared on actual air pollution data sets measuring O3, NO2, and PM10. The ability of the methods to reconstruct the signal of a pollutant is shown, as well as the computational cost of this reconstruction. The results indicate the superiority of methods based on kernel-based graph signal reconstruction, as well as the difficulties of the methods to scale in an air pollution monitoring network with a large number of low-cost sensors. However, we show that scalability can be overcome with simple methods, such as partitioning the network using a clustering algorithm.

Efficient Estimation of Empirical Green’s Function by Removing Transients From Sensor Data Using Time–Frequency Normalization Technique

Clean ambient noise data is the preliminary requirement to perform ambient noise tomography of the earth. Conventional 1-bit time-domain normalization (TDN) is the most popular method to remove the effect of earthquakes and other transient signals obscured by the continuous recording of ambient noise at the sensors. The presence of monochromatic noise sources is also reduced by performing spectral whitening. In this manner, recorded ambient noise data is first normalized in the time domain and then in the frequency domain. It is observed that these normalization procedures do not make the amplitude “even” within the small segments of the complete normalized ambient noise time series and hence, ambient noise remains nondiffusive within these segments. Therefore, in this article, a time–frequency normalization technique is proposed to efficiently remove the temporal and spectral components of the unwanted signals. In this article, continuous wavelet transform (CWT) is used to transform raw ambient noise time series to time–frequency domain to exploit its time–frequency localization property. Complex Morlet wavelet best captures the oscillations present in the raw ambient noise data and then upon normalizing CWT coefficients, a nearly diffusive ambient noise data is retrieved which is suitable to estimate empirical Green’s function (EGF). The performance of the proposed method is tested using synthetic data and the EGFs are estimated using real ambient noise data of a subset of STS-2 USArray sensors. The EGFs are evaluated quantitatively by calculating the signal-to-noise ratio (SNR) and comparing them with those estimated using the conventional method.

Frequency-Invariant Sensor Selection for MVDR Beamforming in Wireless Acoustic Sensor Networks

Wireless acoustic sensor network (WASN) has a wide range of applications in internet of things, where signal estimation is one of the network design objectives. Due to the existence of ambient noises, the recorded audio signals are inevitably corrupted, resulting in a low signal-to-noise ratio (SNR), which triggers the necessity of signal enhancement. As using all sensor measurements brings a large amount of data transmissions and computational cost, the narrowband sensor selection was proposed to choose an informative subset of sensors to perform noise reduction in the audio context. However, the resulting frequency-dependent selection status has to be switched across frequencies. In order to avoid the complicated switching operations, we consider frequency-invariant sensor selection in this work. We propose to minimize the total power consumption over the WASN by constraining the broadband SNR, which can be solved using broadband semi-definite optimization (BroadOpt) or narrowband voting (NaVo) approaches. In order to further reduce the time complexity, we propose two near-optimal greedy methods, including gradient removal (GradR) and weighted input SNR removal (SnrR). As comparison, we also show a broadband energy removal (EnergyR) method. The greedy methods remove one sensor at each iteration from the complete network until the performance constraint is not satisfied. Numerical results using a simulated large-scale WASN show that the greedy methods can achieve a comparable performance compared to the optimization based counterparts, while the corresponding time complexity is much lower. In general, the sensors around the target source and the fusion center are more likely to be selected.

Adaptive Simultaneous Magnetic Actuation and Localization for WCE in a Tubular Environment

Simultaneous magnetic actuation and localization is a promising technology to realize active wireless capsule endoscopy. In this article, an adaptive approach is proposed to efficiently propel and precisely locate a magnetically actuated capsule in unknown complex tubular environments. In order to track the capsule in real time in a large workspace, we improve upon our previous external sensor-based magnetic localization strategies by proposing an adaptive method to automatically activate an optimal subset of sensors during the capsule movement and developing a simplified multiple objects tracking algorithm to estimate the six-dimensional pose of the capsule in real time. Moreover, based on a study of capsule locomotion in tubular environments with different shapes, we propose to dynamically adjust the pose of the actuator to achieve efficient and robust propulsion of the capsule in an unknown tubular environment. The effectiveness of our proposed system is validated in extensive experiments on phantoms and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ex vivo</i> animal organs. Compared with the state-of-the-art, our method can realize the closed-loop control of a magnetic capsule without requiring sensing modules to be placed inside the capsule, which can reduce the space constraints and energy consumption of the capsule. Moreover, the system and algorithms for adaptive actuation and localization can provide an improved propulsion speed, workspace range, and localization update frequency as well as a comparable localization accuracy.

A sensor selection approach to maneuvering target tracking based on trajectory function of time

In this paper, we propose a computationally efficient sensor selection approach for maneuvering target tracking using a sensor network with communication bandwidth constraints, given limited prior information on the target maneuvering models. We formulate the stochastic sensor selection problem as a linear programming problem which consists of two easily implementable steps. First, the Cramér–Rao lower bound corresponding to the sensor subset is derived as the objective function of the proposed sensor selection method based on a partially observable Markov decision process. Second, the target trajectory is modeled by a function of time to enable online target tracking which is free of the conventional, a priori Markov modeling of the target dynamics. We demonstrate the effectiveness of our method through several numerical examples.

Sensor selection and tool wear prediction with data‐driven models for precision machining

AbstractEstimation of tool wear in precision machining is vital in the traditional subtractive machining industry to reduce processing cost, improve manufacturing efficiency and product quality. In this vein, fusion of time and frequency‐domain features of commonly sensed signals can provide an early indication of tool wear and improve its prediction accuracy for prognostics and health management. This paper presents a data‐driven methodology and a complete tool chain for the inference of precision machining tool wear from fused machine measurements, such as cutting force, power, audio and vibration signals, and quantify the usefulness of each measurement. Indicators of tool wear are extracted from time‐domain signal statistics, frequency‐domain analysis, and time‐frequency domain analysis. Correlation coefficients between the extracted features (indicators) and the tool wear are used to select the most informative features. Principal Component Analysis and Partial Least‐Squares are used to reduce the dimensionality of the feature space. Regression models, including linear regression, support vector regression, Decision tree regression, neural network regression and Gaussian process regression, are used to predict the tool wear using data from a Haas milling machine performing spiral boss face milling. The performance of the regression models based on subsets of sensors validates the preliminary estimates about the saliency of the sensors. The experimental results show that the proposed methods can predict the machine tool wear precisely, with readily available sensor measurements. Neural network and Gaussian process regression were able to achieve good estimates of tool wear at different machine operating conditions. The most informative signal in predicting tool wear was shown to be the vibration signal. Time‐frequency domain features were the most informative features among the combination of features of three domains. In addition, using partial least squares components extracted from the original features of signals led to higher prediction accuracy.

Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking

In multi-sensor systems (MSSs), sensor selection is a critical technique for obtaining high-quality sensing data. However, when the number of sensors to be selected is unknown in advance, sensor selection is essentially non-deterministic polynomial-hard (NP-hard), and finding the optimal solution is computationally unacceptable. To alleviate these issues, we propose a novel sensor selection approach based on evolutionary computational intelligence for tracking multiple targets in the MSSs. The sensor selection problem is formulated in a partially observed Markov decision process framework by modeling multi-target states as labeled multi-Bernoulli random finite sets. Two conflicting task-driven objectives are considered: minimization of the uncertainty in posterior cardinality estimates and minimization of the number of selected sensors. By modeling sensor selection as a multi-objective optimization problem, we develop a binary constrained evolutionary multi-objective algorithm based on non-dominating sorting and dynamically select a subset of sensors at each time step. Numerical studies are used to evaluate the performance of the proposed approach, where the MSS tracks multiple moving targets with nonlinear/linear dynamic models and nonlinear measurements. The results show that our method not only significantly reduces the number of selected sensors but also provides superior tracking accuracy compared to generic sensor selection methods.

High-Performance Room-Temperature Conductometric Gas Sensors: Materials and Strategies

Chemiresistive sensors have gained increasing interest in recent years due to the necessity of low-cost, effective, high-performance gas sensors to detect volatile organic compounds (VOC) and other harmful pollutants. While most of the gas sensing technologies rely on the use of high operation temperatures, which increase usage cost and decrease efficiency due to high power consumption, a particular subset of gas sensors can operate at room temperature (RT). Current approaches are aimed at the development of high-sensitivity and multiple-selectivity room-temperature sensors, where substantial research efforts have been conducted. However, fewer studies presents the specific mechanism of action on why those particular materials can work at room temperature and how to both enhance and optimize their RT performance. Herein, we present strategies to achieve RT gas sensing for various materials, such as metals and metal oxides (MOs), as well as some of the most promising candidates, such as polymers and hybrid composites. Finally, the future promising outlook on this technology is discussed.

A machine learning framework for predicting downstream water end-use events with upstream sensors

AbstractUnderstanding the end-use of water is essential to a plethora of critical research in premise plumbing. However, direct access to end-use data through physical sensors is prohibitively expensive for most researchers, building owners, operators, and practitioners. Therefore, machine learning models can alleviate these costs by predicting downstream end-use events (e.g., sink, shower, dishwasher, and washing machine) via an affordable subset of upstream sensors. Choosing which upstream sensors, as well as data preprocessing methods, are best for machine learning has historically been a manual process. This paper proposes a novel approach to systematically configure the machine platform automatically. The optima were determined through a Pareto analysis of the exhaustive combinations of upstream predictors and preprocessing methods. The model was trained and validated with real-world data obtained from a house that has been extensively monitored for over a year. Results from the analysis suggested that downstream events can be effectively predicted with minimum overfitting error for most categories, using as few as two to four upstream sensors. This study automatically implemented highly accurate machine learning models to predict downstream features within premise plumbing systems, significantly lowering the costs of researching residential plumbing best practices such as water conservation.

Sensor Selection for Hybrid AOA-TOA Localization with Correlated Measurement Noise in Underwater Wireless Sensor Networks

Underwater target localization is the most crucial part of the underwater wireless sensor network (UWSN). Due to limited communication range and energy constraints in underwater scenarios, only a subset of sensors can be selected to localize. This paper investigates the sensor selection schemes for hybrid angle-of-arrival (AOA) and time-of-arrival (TOA) localization in the underwater scenario. We first develop the Cramér-Rao lower bound (CRLB) for the hybrid AOA-TOA localization with correlated measurement noise model with Gaussian priors, and a Boolean vector is introduced to denote the selected sensors for hybrid measurement. Secondly, the sensor selection schemes are formulated as an optimization problem, and the optimality criterion is to minimize the trace of CRLB. The original nonconvex problem has been modified to the semidefinite problem program (SDP) by convex relaxation, and then, a randomization algorithm is chosen to advance the result of the SDP method. Finally, simulations verify that the proposed algorithm approaches the exhaustive search algorithm, and the effect of correlated measurement noise on the estimation performance in the hybrid localization system is proved.

Partial coverage optimization under network connectivity constraints in heterogeneous sensor networks

The maximum network lifetime problem (MLP) in heterogeneous wireless sensor networks under connectivity and coverage constraints is addressed in this paper. Two main variants of the studied problem are considered. The first variant is α-coverage where a portion ((1 - α) percent) of the targets are allowed to be left uncovered. The second one is called β-coverage or β-constraint where each target has a minimum coverage rate β during the network’s lifetime service. When the two variants are considered at the same time, the problem is called αβ−Connected Maximum Lifetime Problem (αβ−CMLP) where we consider both global (whole targets) resp. local (individual target) monitoring level thresholds to improve the coverage quality of the deployed WSN. Unlike earlier works devoted to only α coverage, we deal with both local (α) and global (β) coverage leveling thresholds under network connectivity constraint. One approach to optimize the network’s lifetime is to divide the sensor nodes into Non-Disjoint subsets of sensors, or cover sets, and to schedule these covers with variable activation time periods, so that the global time lifespan of the network is optimized. To this end, we provide both exact and heuristic approaches in this study. First, a novel mathematical Mixed Integer Linear Programming (MILP) is presented to solve the αβ-coverage with network connectivity requirement to optimality. Unfortunately, due to the NP-Completeness of the addressed problem, the MILP’s resolution becomes impracticable for large optimization problems. To remedy this and to cope with large instances, we propose a new exact approach based on column generation able to achieve optimal solutions in reasonable time. In addition, since the CG’s subproblem resolution is also an NP-Hard problem, a new dedicated Heuristic (DH) is designed to solve the CG’s subproblem in polynomial time complexity. Moreover, we propose an exact ILP formulation for the CG’s subproblem if the DH heuristic fails to compute an attractive solution in each iteration of the CG computation process. Finally, several experiments are performed to evaluate the performances of our proposals.

Machine-learning flow control with few sensor feedback and measurement noise

A comparative assessment of machine-learning (ML) methods for active flow control is performed. The chosen benchmark problem is the drag reduction of a two-dimensional Kármán vortex street past a circular cylinder at a low Reynolds number (Re = 100). The flow is manipulated with two blowing/suction actuators on the upper and lower side of a cylinder. The feedback employs several velocity sensors. Two probe configurations are evaluated: 5 and 11 velocity probes located at different points around the cylinder and in the wake. The control laws are optimized with Deep Reinforcement Learning (DRL) and Linear Genetic Programming Control (LGPC). By interacting with the unsteady wake, both methods successfully stabilize the vortex alley and effectively reduce drag while using small mass flow rates for the actuation. DRL has shown higher robustness with respect to different initial conditions and to noise contamination of the sensor data; on the other hand, LGPC is able to identify compact and interpretable control laws, which only use a subset of sensors, thus allowing for the reduction of the system complexity with reasonably good results. Our study points at directions of future machine-learning control combining desirable features of different approaches.

A Data Driven Approach for Predicting Preferred Ankle Stiffness of a Quasi-Passive Prosthesis

Emerging variable-stiffness ankle prostheses can modulate their stiffness to meet differing biomechanical demands. To this end, knowledge of the optimal ankle stiffness is required for each user and activity. One approach is to match the stiffness of prosthesis to the user&#x2019;s preference, but this requires a tuning process to determine each user&#x2019;s preferences. In this work, we seek to estimate user-preferred ankle stiffness using biomechanical data collected from seven subjects during walking at stiffness settings around their preferred stiffness; our hope is an automated method may reduce the time and experimental burden of determining user preferences. We investigated different machine learning algorithms, sensor subsets, and the impact of user-specific training data on estimation accuracy. We found that a long short term memory (LSTM) algorithm trained on user-specific data from only the affected side, were able to predict user preferred ankle stiffness with an RMSE of 5.2&#x0025; <inline-formula><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> 0.3&#x0025;. The prediction error was less than prosthesis users&#x2019; ability to reliably sense stiffness changes (7.7&#x0025;), which highlights the significance of the performance of our proposed method. This study provides a foundation for an automated approach for predicting user-preferred prosthesis mechanics that would ease the burden of tuning these systems in a clinical setting.