Single Sensor System Research Articles

Stereo and LiDAR Loosely Coupled SLAM Constrained Ground Detection.

In many robotic applications, creating a map is crucial, and 3D maps provide a method for estimating the positions of other objects or obstacles. Most of the previous research processes 3D point clouds through projection-based or voxel-based models, but both approaches have certain limitations. This paper proposes a hybrid localization and mapping method using stereo vision and LiDAR. Unlike the traditional single-sensor systems, we construct a pose optimization model by matching ground information between LiDAR maps and visual images. We use stereo vision to extract ground information and fuse it with LiDAR tensor voting data to establish coplanarity constraints. Pose optimization is achieved through a graph-based optimization algorithm and a local window optimization method. The proposed method is evaluated using the KITTI dataset and compared against the ORB-SLAM3, F-LOAM, LOAM, and LeGO-LOAM methods. Additionally, we generate 3D point cloud maps for the corresponding sequences and high-definition point cloud maps of the streets in sequence 00. The experimental results demonstrate significant improvements in trajectory accuracy and robustness, enabling the construction of clear, dense 3D maps.

Research on On-Line Monitoring of Grinding Wheel Wear Based on Multi-Sensor Fusion.

The state of a grinding wheel directly affects the surface quality of the workpiece. The monitoring of grinding wheel wear state can allow one to efficiently identify grinding wheel wear information and to timely and effectively trim the grinding wheel. At present, on-line monitoring technology using specific sensor signals can detect abnormal grinding wheel wear in a timely manner. However, due to the non-linearity and complexity of the grinding wheel wear process, as well as the interference and noise of the sensor signal, the accuracy and reliability of on-line monitoring technology still need to be improved. In this paper, an intelligent monitoring system based on multi-sensor fusion is established, and this system can be used for precise grinding wheel wear monitoring. The proposed system focuses on titanium alloy, a typical difficult-to-process aerospace material, and addresses the issue of low on-line monitoring accuracy found in traditional single-sensor systems. Additionally, a multi-eigenvalue fusion algorithm based on an improved support vector machine (SVM) is proposed. In this study, the mean square value of the wavelet packet decomposition coefficient of the acoustic emission signal, the grinding force ratio of the force signal, and the effective value of the vibration signal were taken as inputs for the improved support vector machine, and the recognition strategy was adjusted using the entropy weight evaluation method. A high-precision grinding machine was used to carry out multiple sets of grinding wheel wear experiments. After being processed by the multi-sensor integrated precision grinding wheel wear intelligent monitoring system, the collected signals can accurately reflect the grinding wheel wear state, and the monitoring accuracy can reach more than 92%.

Optimization of activity-driven event detection for long-term ambulatory urodynamics.

Lower urinary tract dysfunction (LUTD) is a debilitating condition that affects millions of individuals worldwide, greatly diminishing their quality of life. The use of wireless, catheter-free implantable devices for long-term ambulatory bladder monitoring, combined with a single-sensor system capable of detecting various bladder events, has the potential to significantly enhance the diagnosis and treatment of LUTD. However, these systems produce large amounts of bladder data that may contain physiological noise in the pressure signals caused by motion artifacts and sudden movements, such as coughing or laughing, potentially leading to false positives during bladder event classification and inaccurate diagnosis/treatment. Integration of activity recognition (AR) can improve classification accuracy, provide context regarding patient activity, and detect motion artifacts by identifying contractions that may result from patient movement. This work investigates the utility of including data from inertial measurement units (IMUs) in the classification pipeline, and considers various digital signal processing (DSP) and machine learning (ML) techniques for optimization and activity classification. In a case study, we analyze simultaneous bladder pressure and IMU data collected from an ambulating female Yucatan minipig. We identified 10 important, yet relatively inexpensive to compute signal features, with which we achieve an average 91.5% activity classification accuracy. Moreover, when classified activities are included in the bladder event analysis pipeline, we observe an improvement in classification accuracy, from 81% to 89.0%. These results suggest that certain IMU features can improve bladder event classification accuracy with low computational overhead.Clinical Relevance: This work establishes that activity recognition may be used in conjunction with single-channel bladder event detection systems to distinguish between contractions and motion artifacts for reducing the incorrect classification of bladder events. This is relevant for emerging sensors that measure intravesical pressure alone or for data analysis of bladder pressure in ambulatory subjects that contain significant abdominal pressure artifacts.

Prediction of Freezing of Gait in Parkinson’s disease based on multi-channel time-series neural network

Freezing of Gait (FOG) is a noticeable symptom of Parkinson’s disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

Reliability improvement of the dredging perception system: A sensor fault-tolerant strategy

In the dredging industry, the automation and accuracy of the Dredging Perception System (DPS) are vital for operational efficiency and environmental safety. Current DPS implementations face challenges with sensor fault tolerance, leading to system unreliability and increased false alarm rates that can disrupt dredging operations. We propose a Hybrid Redundancy Sensor Fault Tolerance (HRSFT) strategy that integrates matching physical sensors (PS) with two distinct types of virtual sensors (VS) driven by multi-sensor association and time-series prediction models. The HRSFT employs a voting-cold storage strategy to address the false alarm issues commonly associated with single virtual sensor systems. Through experimental validation, the HRSFT strategy has demonstrated its capability to provide accurate replacement information during both single and multi-sensor failure scenarios, effectively managing abnormal sensor data and enhancing the operational reliability of the DPS. The implementation of the HRSFT strategy significantly improves the accuracy and stability of the DPS, suggesting a substantial advancement in sensor fault tolerance that could be applied to similar systems in various industries, leading to safer and more reliable operations.

A single-sensor multi-scale quality monitoring methodology for laser-directed energy deposition: Example with height instability and porosity monitoring in additive manufacturing of ceramic thin-walled parts

Laser Additive Manufacturing (LAM) faces various technical challenges, encompassing issues with dimensional accuracy, mechanical properties, and processing-related defects, such as surface roughness, cracking, and residual porosity. Currently, the quality of safety-critical parts produced by LAM processes, which is still improved through trial-and-error adjustments of multiple process variables, have limited real-time monitoring capabilities. This study introduces an innovative method for real-time quality assessment of laser-directed energy deposition (LDED) procedures across multiple scales (macroscale, mesoscale, and microscale) utilizing a single sensor. This approach is founded on two fundamental components: the single-sensor system for data acquisition and the algorithm for simultaneous multi-scale quality monitoring. For the data acquisition system aspect, a single-sensor, high dynamic range (HDR), multi-scale information acquisition system has been developed to mitigate intense radiation, eliminate plume disturbances, and rectifies backlight shadows, facilitating clearer images of deposition contours and the molten pool region. In the realm of data monitoring algorithms, a physics model-driven supervisory algorithm is employed to enable monitoring of contour height instability, while a convolutional neural network (CNN), driven by image data, is utilized for porosity prediction. Then, this algorithm adeptly tackles the challenge of simultaneously monitoring macroscopic contour and mesoscale porosity. Regarding the validation of the method, the outcomes of single-sensor multi-scale quality monitoring in additive manufacturing of ceramic thin-wall parts indicate a 100% recognition rate for deposition contour and molten pools, contour feature recognition with a relative error of under 0.05%, porosity prediction accuracy surpassing 99%, and a monitoring time of 80.4 ms per frame. Single-sensor multi-scale real-time quality monitoring can serve as a methodological support for future real-time quality control in LDED.

A PROSAIL model with a vegetation index lookup table optimized with in-situ statistics for rapeseed leaf area index estimation using diverse unmanned aerial vehicle sensors in the Yangtze River Basin

For winter rapeseed, timely monitoring of the leaf area index (LAI) near the winter solstice is critical for estimating its overwintering survival rate and yield. While unmanned aerial vehicle (UAV) remote sensing techniques have emerged as a promising means for crop LAI monitoring, many existing crop LAI models have only been evaluated using a single sensor system, a single cultivar, a single development stage, and/or a single site. As a result, the generalization capability of these LAI models is limited. In this study, four empirical statistical models (ESMs) and a new PROSAIL-based lookup table (LUT) method were developed to estimate the LAI of 24 winter rapeseed cultivars mainly grown in the Yangtze River Basin. The raw LUT was optimized using a vegetation index (VI) strategy after screening out inefficient parameter combinations using in-situ UAV reflectance and measured LAIs. The model transferability was evaluated across three years, six regional sites around Yangtze River Basin, different development stages, and two data sources from different sensors. An artificial neural network model in the ESMs performed best for data acquired in 2019 and 2020, but could not be used to estimate the LAI in 2018 due to the use of different sensors for data acquisition. In contrast, the optimized VI-LUT method was robust and outperformed the raw LUT for LAI retrieval with a root mean squared error of <0.7 for all data sets. These findings suggest that the optimized VI-LUT method has potential for estimating LAI at different spatial and temporal scales, especially for the situation where sensor types are difficult to be unified in multiple locations. Moreover, the genotype in these cultivars did not appear to dominate LAI generation before overwintering, but the climatic zone did. These findings have implications for the study of genotype-environment interactions in rapeseed cultivation.

Two-stage quality monitoring of a laser welding process using machine learning

Abstract In production, quality monitoring is essential to detect defective elements. State-of-the-art approaches are single-sensor systems (SSS) and multi-sensor systems (MSS). Yet, these approaches might not be suitable: Nowadays, one component may comprise several hundred meters of the weld seam, necessitating high-speed welding to produce enough components. To detect as many defects as possible in time, fast yet precise monitoring is required. However, information captured by SSS might not be sufficient and MSS suffer from long inference times. Therefore, we present a confidence-based cascaded system (CS). The key idea of the CS is that not all data are analyzed to obtain the quality weld, but only selected ones. As evidenced by our results, all CS outperform SSS in terms of accuracy and inference time. Further, compared to MSS, the CS has hardware advantages.

A single-sensor system for length estimation of unknown piles using guided waves

The practice of reusing unknown foundations in construction projects involves using existing foundations, even though there may be limited knowledge about their geometric and physical characteristics, conditions, and stability of the soil layer and the buried structure. Accurately estimating the pile length is a critical aspect of this practice. In this study, we introduce a new pile length estimation method based on guided wave theory and utilizing only one sensor for data collection. The objective is to enhance operational flexibility in the characterization of unknown piles, in terms of data acquisition, sensor placement, and accuracy in pile length estimation. The sensor can be positioned either on the lateral side of the pile or on its top surface. The recorded responses in the frequency domain are analyzed, and their normalized magnitude is calculated. Using the dispersion relation determined by the guided wave model, we obtain the dispersion analysis diagram of the wavenumber as a function of the normalized magnitude of the recorded response. By performing periodic analysis of the dispersion analysis diagram, the pile length can be estimated. Our proposed method has been verified using both synthetic and experimental data. The results demonstrate the efficacy and accuracy of the proposed method.

Multiposture leg tracking for temporarily vision restricted environments based on fusion of laser and radar sensor data

AbstractLeg tracking is an established field in mobile robotics and machine vision in general. These algorithms, however, only distinguish the scene between leg and nonleg detections. In application fields like firefighting, where people tend to choose squatting or crouching over standing postures, those methods will inevitably fail. Further, tracking based on a single sensor system may reduce the overall reliability if brought to outdoor or complex environments with limited vision on the target objectives. Therefore, we extend our recent work to a multiposture detection system based on laser and radar sensors, that are fused to allow for maximal reliability and accuracy in scenarios as complex as indoor firefighting with vastly limited vision. The proposed tracking pipeline is trained and extensively validated on a new data set. We show that the radar tracker reaches state‐of‐the‐art performance, and that laser and fusion tracker outperform recent methods.

Designing and Manufacturing of Industrial Robots with Dual-Angle Sensors Taking into Account Vibration Signal Fusion

Industrial robots are an important way to realize the development of industrial industry intelligence and automation, an important driving force to accelerate the construction of Industry 4.0, and an important basic force to improve the professional level of industrial industry. The development of industrial robot technology has enhanced the requirements of its detection quality and the demand for data comprehensiveness. Most of the previous robots obtain the corresponding data through a single sensor system, which has a large error and a high limitation of the range of data obtained. The detection method of industrial robots has the problems of high cost and high professionalism. Therefore, this paper constructs a dual-angle sensor industrial robot detection system based on the fusion of multisource vibration signals and achieves the fusion of multisensor signals through Kalman filtering to provide reliable analysis data for the dual-angle sensor detection system. The experimental results show that Kalman filtering can effectively remove noise while preserving the original vibration signal characteristics and structure and improve the reliability and validity of the vibration signal. In addition, the dual-angle sensor detection system can realize the position detection of industrial robots according to the command standard and obtain the corresponding residual and standard values through system data analysis. The overall optimization of the system algorithm enhances the accuracy and reliability of the measurement.

A sensor review for human detection with robotic systems in regular and smoky environments

Search and rescue robots gained a significant attention in the past, as they assist firefighters during their rescue missions. The opportunity to move autonomously or remotely controlled with intelligent sensor technology, to detect victims in unknown fire smoke environments, introduces a growing technology in fire engineering. Since sensor systems are a component of mobile robots, there is a demand for intelligent robot vision, especially for human detection in fire smoke environments. In this article, an overview of sensor technologies and their algorithms for human detection in regular and smoky environments is presented. These sensor technologies are categorized into single sensor and multi-sensor systems. Novel sensor approaches are led by artificial intelligence, 3D mapping and multi-sensor fusion. The article provides a contribution for future research directions in algorithms and applications and supports decision-makers in fire engineering to get knowledge in trends, novel applications and challenges in this field of research.

A 3-D-Printed Portable EMG Wristband for the Quantitative Detection of Finger Motion

It is highly required to develop an affordable surface electromyography (EMG) wristband for the improved control of prostheses that is suitable to mimic human hand functions. By using the 3D-printing technology, the wristband is customizable and feasible for various arm sizes or shapes. In this paper, we have developed the 3D printed wristband for the control application. It consists of five pairs of custom-made serpentine dry electrodes, one EMG sensor, and one signal processing printed circuit board (PCB) to detect the user’s finger movements simultaneously. The wristband demonstrated its stability in EMG signal processing with a single-sensor system, which differed from other multi-sensor system devices. We verified the stability of the serpentine electrodes as bendable and stretchable. The serpentine electrodes have improved signal detection by providing conformal contact to the skin surface compared with the existing rigid dry electrodes. The flexibility allowed the electrodes to be placed in any shape of the skin surface. In a series of tests performed by the volunteer, we showed that the collected EMG signals reflected the muscle movements through signal processing. Under the muscle contraction of 75 lb, the wristband showed a signal sensitivity of 0.556 mV/lb with a 27 dB signal-to-noise ratio (SNR) for its valid EMG sensing capability. In addition, we also demonstrated the relationship between signal intensities and muscle forces at the different levels quantitatively. This work shows promising potential toward the advanced control system of prosthetic fields and its corresponding market.

Joint near-isometry and optimal sparse recovery: Nonuniform recovery from multi-sensor measurements

Parallel acquisition systems are widely used in practical applications as they are effective in problems that cannot guarantee the quality of signal reconstruction in case of using a single-sensor system. Many authors have already demonstrated the superiority of the multi-sensor system over the single-sensor system by revealing the nonuniform recovery conditions of the multi-sensor system for optimal recovery in the sense that the number of measurements required per sensor decreases linearly with the total number of sensors, however, the condition on the sensor profile matrices are quite stringent. In this paper, we present nonuniform recovery guarantees based on the so-called joint near-isometry condition, while preserving the advantage of the multi-sensor system and the possibility of stable and robust recovery. The relaxed condition on the sensor profile matrices opens up the possibility of design of considerably wide range of sensor profile. On the other hand, numerical experiments not only show the validity of our theoretical result, but also provide several interesting results such as effectiveness of random sensor profile.

Machine learning techniques to increase the performance of indirect methane quantification from a single, stationary sensor

Researchers are searching for ways to better quantify methane emissions from natural gas infrastructure. Current indirect quantification techniques (IQTs) allow for more frequent or continuous measurements with fewer personnel resources than direct methods but lack accuracy and repeatability. Two IQTs are Other Test Method (OTM) 33A and Eddy Covariance (EC). We examined a novel approach to improve the accuracy of single sensor IQT whereby the results from both OTM and EC were combined with two machine learning (ML) models, a random forest (RF) and a neural network (NN). Then, models were enhanced with feature reduction and hyper-parameter tuning and compared to traditional quantification methods. The NN and RF improved upon the default OTM by an average of 44% and 78%, respectively. When compared to traditional OTM estimates with low Data Quality Indicators (DQIs), RF and NN models reduced 1σ errors from ±66% to ±13% and ±34%, respectively. Models also reduced the standard deviation of estimates with 93% and 85% of estimates falling within ±50% of the known release rate. This approach can be deployed with single sensor systems at well sites to improve confidence in reported emissions, reducing the number of anomalous overestimates that would trigger unnecessary site evaluations. Additional improvements could be realized by expanding training datasets with more methane release rates. Further, deployment of such models in a variety of situations could enhance their ability help close the gap between bottom-up inventory and top-down studies by enabling continuous monitoring of temporal emissions that could identify with improved confidence, atypically higher emissions. Accurate remote single sensor systems are key in developing an improved understanding of methane emissions to enable industry to identify and reduce methane emissions.

Probabilistic Fusion for Pedestrian Detection from Thermal and Colour Images.

Pedestrian detection is an important research domain due to its relevance for autonomous and assisted driving, as well as its applications in security and industrial automation. Often, more than one type of sensor is used to cover a broader range of operating conditions than a single-sensor system would allow. However, it remains difficult to make pedestrian detection systems perform well in highly dynamic environments, often requiring extensive retraining of the algorithms for specific conditions to reach satisfactory accuracy, which, in turn, requires large, annotated datasets captured in these conditions. In this paper, we propose a probabilistic decision-level sensor fusion method based on naive Bayes to improve the efficiency of the system by combining the output of available pedestrian detectors for colour and thermal images without retraining. The results in this paper, obtained through long-term experiments, demonstrate the efficacy of our technique, its ability to work with non-registered images, and its adaptability to cope with situations when one of the sensors fails. The results also show that our proposed technique improves the overall accuracy of the system and could be very useful in several applications.

Classification of lower limb rehabilitation exercises with multiple and individual inertial measurement units

Straight leg raise rehabilitation exercises (for both lying and seated position) for lower limb injuries play a critical role in terms of stress on joints after the injury. The primary objective of the paper is to find how accurately and efficiently a single and a two IMU sensor-based system could classify SSLR (Seated straight leg raise) and LSLR (Lying straight leg raise) exercises using machine learning. Inertial Measurement Units (IMUs) that include accelerometer and gyroscope were calibrated and tested, individual and combined, for classified seating as well as lying exercise and for different demanded personalities. Individual IMUs achieved about 96 % accuracy in binary classification. However, the combined (two) IMUs achieved about 96.8 % accuracy. The merits of the proposed IMU based sensor system are that it is easy to install, cost effective and very useful for telemedical operations in pandemic situations like COVID19. On the basis of these results, it could be concluded that the accuracy of a single IMU sensor system and a two IMU sensor-based system is approximately 96% and both were efficiently able to classify SSLR and LSLR exercises as well as identify the individual performing the exercise.

A Human Gait Tracking System Using Dual Foot-Mounted IMU and Multiple 2D LiDARs.

This paper proposes a human gait tracking system using a dual foot-mounted IMU and multiple 2D LiDARs. The combining system aims to overcome the disadvantages of each single sensor system (the short tracking range of the single 2D LiDAR and the drift errors of the IMU system). The LiDARs act as anchors to mitigate the errors of an inertial navigation algorithm. In our system, two 2D LiDARs are used. LiDAR 1 is placed around the starting point, and LiDAR 2 is placed at the ending point (in straight walking) or at the turning point (in rectangular path walking). Using the LiDAR 1, we can estimate the initial headings and positions of each IMU without any calibration process. We also propose a method to calibrate two LiDARs that are placed far apart. Then, the measurement from two LiDARs can be combined in a Kalman filter and the smoother algorithm to correct the two estimated feet trajectories. If straight walking is detected, we update the current stride heading and the foot position using the previous stride headings. Then, it is used as a measurement update in the Kalman filter. In the smoother algorithm, a step width constraint is used as a measurement update. We evaluate the stride length estimation through a straight walking experiment along a corridor. The root mean square errors compared with an optical tracking system are less than 3 cm. The performance of proposed method is also verified with a rectangular path walking experiment.

Interpretable Passive Multi-Modal Sensor Fusion for Human Identification and Activity Recognition.

Human monitoring applications in indoor environments depend on accurate human identification and activity recognition (HIAR). Single modality sensor systems have shown to be accurate for HIAR, but there are some shortcomings to these systems, such as privacy, intrusion, and costs. To combat these shortcomings for a long-term monitoring solution, an interpretable, passive, multi-modal, sensor fusion system PRF-PIR is proposed in this work. PRF-PIR is composed of one software-defined radio (SDR) device and one novel passive infrared (PIR) sensor system. A recurrent neural network (RNN) is built as the HIAR model for this proposed solution to handle the temporal dependence of passive information captured by both modalities. We validate our proposed PRF-PIR system for a potential human monitoring system through the data collection of eleven activities from twelve human subjects in an academic office environment. From our data collection, the efficacy of the sensor fusion system is proven via an accuracy of 0.9866 for human identification and an accuracy of 0.9623 for activity recognition. The results of the system are supported with explainable artificial intelligence (XAI) methodologies to serve as a validation for sensor fusion over the deployment of single sensor solutions. PRF-PIR provides a passive, non-intrusive, and highly accurate system that allows for robustness in uncertain, highly similar, and complex at-home activities performed by a variety of human subjects.

Imidazolium-Modified Bispyrene-Based Fluorescent Aggregates for Discrimination of Multiple Anions in Aqueous Solution.

A great number of anions exist in biological systems and natural environment, and are highly relevant to human health and environment quality. It is necessary to develop simple and effective sensors to differentiate and identify those similar or different anions. Here, an imidazolium-modified bispyrene-based fluorescent amphiphilic probe DPyDIM was synthesized and its aggregates were applied to detect and discriminate various anions. The fluorescent aggregates exhibit ratiometric responses to different types of anions. Moreover, the ratiometric responses to different types of anions are featured with multiple-wavelength cross-reactivity. The collection of fluorescence variation at four typical wavelengths can generate distinct recognition patterns to specific anions. The heat map and principal component analysis results verify that this single fluorescent sensor system can effectively and sensitively identify 16 kinds of anions that belong to phosphorus-containing, sulfur-containing anions, and anionic surfactants. The cross-reactive sensing of the amphiphilic fluorescent aggregates was attributed to the different influences on the aggregation behaviors of the probes by different anions. The present work provides a promising strategy for effective detection and discrimination of multiple anions by employing dynamic fluorescent aggregates as a sensing platform.