Set Of Sensors Research Articles

An Industrial Internet-of-Things (IIoT) Open Architecture for Information and Decision Support Systems in Scientific Field Campaigns.

Information and decision support systems are essential to conducting scientific field campaigns in the atmospheric sciences. However, their development is costly and time-consuming since each field campaign has its own research goals, which result in using a unique set of sensors and various analysis procedures. To reduce development costs, we present a software framework that is based on the Industrial Internet of Things (IIoT) and an implementation using well-established and newly developed open-source components. This framework architecture and these components allow developers to customize the software to a campaign's specific needs while keeping the coding to a minimum. The framework's applicability was tested in two scientific field campaigns that dealt with questions regarding air quality by developing specialized IIoT applications for each one. Each application provided the online monitoring of the acquired data and an intuitive interface for the scientific team to perform the analysis. The framework presented in this study is sufficiently robust and adaptable to meet the diverse requirements of field campaigns.

Detecting floating litter in freshwater bodies with semi-supervised deep learning

Researchers and practitioners have extensively utilized supervised Deep Learning methods to quantify floating litter in rivers and canals. These methods require the availability of large amount of labeled data for training. The labeling work is expensive and laborious, resulting in small open datasets available in the field compared to the comprehensive datasets for computer vision, e.g., ImageNet. Fine-tuning models pre-trained on these larger datasets helps improve litter detection performances and reduces data requirements. Yet, the effectiveness of using features learned from generic datasets is limited in large-scale monitoring, where automated detection must adapt across different locations, environmental conditions, and sensor settings. To address this issue, we propose a two-stage semi-supervised learning method to detect floating litter based on the Swapping Assignments between multiple Views of the same image (SwAV). SwAV is a self-supervised learning approach that learns the underlying feature representation from unlabeled data. In the first stage, we used SwAV to pre-train a ResNet50 backbone architecture on about 100k unlabeled images. In the second stage, we added new layers to the pre-trained ResNet50 to create a Faster R-CNN architecture, and fine-tuned it with a limited number of labeled images (≈1.8k images with 2.6k annotated litter items). We developed and validated our semi-supervised floating litter detection methodology for images collected in canals and waterways of Delft (the Netherlands) and Jakarta (Indonesia). We tested for out-of-domain generalization performances in a zero-shot fashion using additional data from Ho Chi Minh City (Vietnam), Amsterdam and Groningen (the Netherlands). We benchmarked our results against the same Faster R-CNN architecture trained via supervised learning alone by fine-tuning ImageNet pre-trained weights. The findings indicate that the semi-supervised learning method matches or surpasses the supervised learning benchmark when tested on new images from the same training locations. We measured better performances when little data (≈200 images with about 300 annotated litter items) is available for fine-tuning and with respect to reducing false positive predictions. More importantly, the proposed approach demonstrates clear superiority for generalization on the unseen locations, with improvements in average precision of up to 12.7%. We attribute this superior performance to the more effective high-level feature extraction from SwAV pre-training from relevant unlabeled images. Our findings highlight a promising direction to leverage semi-supervised learning for developing foundational models, which have revolutionized artificial intelligence applications in most fields. By scaling our proposed approach with more data and compute, we can make significant strides in monitoring to address the global challenge of litter pollution in water bodies.

Optimization of Chemical Engineering Processes in the Mining and Metal Industry: A Review

Process optimization is acutely vital: mining and a metal industries research. Through applying modelling and optimization tools, businesses see tremendous improvement in process efficiencies, declining costs of production, and ensuring high quality. The valuable of simulation tools have also been reflected in the design of the virtual plants which make possible to conduct test runs of different process scenarios thereby providing the opportunity to optimize the performance of the plants. So, even if these issues are close to being resolved, some challenges must still be tackled to approach the full field of process optimization enjoyment. One of the main drawbacks is the integration of sustainable development and environmental evaluation into optimization phase. This can be achieved by developing models that are amended to an environmental impact of each process parameters and afterwards an optimization of processes will be based on environment factors. The second challenge is for the research community to come up with more advanced and sophisticated mathematical models that are capable of not only capturing but also depicting the diverse and complex interactions that take place between different processes variables. Such an approach indeed requires implementation of more precise data analysis tools and techniques, including neural networks and genetic algorithms. While there are many difficulties in it way, the process optimization of a bright future is foreseeable. The fast growth of the technological sphere, such as machine-2-machine and big data analytics, enables process optimization which was unavailable before. By implementation of a set of sensors and real-time data analysis plant operators are being provided with necessary information that enables this way to exercise real-time decisions for the sake of the increase of the plant performance. Minimizing energy consumption, increasing the product yield, and less damaging to the environment is a potential focus for the research. Through the application of mathematical models, optimization algorithms, and simulation-based approaches, one can compare the different methods of each process and the produced product yields.

On-Site Sensor Sensitivity Adjustment Technique for a Maintenance-Free Heat Flow Monitoring in Building Systems

In this paper, an advanced solution for measuring heat flow through opaque building elements is presented. The solution is based on the implementation of a computer-aided technique for continuous monitoring of heat flow sensor performance and silent checking of their accuracy. In principle, the technique provides an ex-post compensation of potential deviations and inaccuracies detected during the measurement, which can be done without interfering with the ongoing experiment. As a consequence, traditional ‘non-smart’ sensors can be turned into advanced sensors with self-sensing or self-adjustment features at nearly zero additional costs. The high efficiency of the proposed approach was validated against experimental data obtained from an independent set of advanced high-sensitive sensors. Considering the validation results, the proposed technique brings an entirely new potential for maintenance-free applications for thermal performance monitoring in the building sector, typically for long-term experiments or measurements under dynamic environments.

FPID-RCP: A Control Method for a Swing-Type Wave Compensation Platform System

With the rapid development of marine engineering in recent years, offshore operations have become increasingly common, making wave compensation platforms crucial for safe operations at sea. This paper presents a pendulum-type wave compensation platform specifically designed for wave compensation applications. The main components of this wave compensation platform include a chassis, support base, hydraulic cylinders, telescopic rods, upper platform, three sets of balancing mechanisms, three sets of tilt angle sensors, and a control system. Firstly, to thoroughly understand the compensatory motion of the pendulum-type three-degree-of-freedom wave compensation platform, kinematic analysis of the entire system was conducted, and the motion inverse solution curves of the mechanism were obtained through simulation using motion simulation software. Secondly, to enhance the compensatory response performance of the platform, a fuzzy PID control algorithm was employed to control the system and achieve attitude control of the platform. Finally, through control system simulation, compared to PID control, fuzzy PID reduces system response delay and successfully meets the expected technical requirements and application needs.

Operational and experimental snow observation systems in the upper Rofental: data from 2017 to 2023

Abstract. This publication presents a comprehensive hydrometeorological data set for three research sites in the upper Rofental (1891–3772 m a.s.l., Ötztal Alps, Austria) and is a companion publication to a data collection published in 2018. The time series presented here comprise data from 2017 to 2023 and originate from three meteorological and snow hydrological stations at 2737, 2805, and 2919 m a.s.l. The fully equipped automatic weather stations include a specific set of sensors to continuously record snow cover properties. These are automatic measurements of snow depth, snow water equivalent, volumetric solid and liquid water contents, snow density, layered snow temperature profiles, and snow surface temperature. One station is extended by a particular arrangement of two snow depth and water equivalent recording devices to observe and quantify wind-driven snow transport. These devices are installed at nearby wind-exposed and sheltered locations and are complemented by an acoustic-based snow drift sensor. We present data for temperature, precipitation, humidity, wind speed, and radiation fluxes and explore the continuous snow measurements by combined analyses of meteorological and snow data to show typical seasonal snow cover characteristics. The potential of the snow drift observations is demonstrated with examples of measured wind speeds, snow drift rates, and redistributed snow amounts during several blowing snow events. The data complement the scientific monitoring infrastructure in the research catchment and represent a unique time series of high-altitude mountain weather and snow observations. They enable comprehensive insights into the dynamics of high-altitude meteorological and snow processes and are collected to support the scientific community, local stakeholders, and the interested public, as well as operational warning and forecasting services. The data are publicly available from the GFZ Data Services repository: https://doi.org/10.5880/fidgeo.2023.037 (Department of Geography, University of Innsbruck, 2024).

IMSIS: An instrumented microphysiological system with integrated sensors for monitoring cellular metabolic activities

Well plates are widely used in biological experiments, particularly in pharmaceutical sciences and cell biology. Its popularity stems from its versatility to support a variety of fluorescent markers for high throughput monitoring of cellular activities. However, using fluorescent markers in traditional well plates has its own challenges, namely, they can be potentially toxic to cells, and thus, may perturb their biological functions; and it is difficult to monitor multiple analytes concurrently and in real-time inside each well. This paper presents a fully instrumented microphysiological system with integrated sensors (IMSIS) with a similar well format. Each well in the microphysiological system has a set of sensors for monitoring multiple metabolic analytes in real-time. The IMSIS platform is supported by integrated bioelectronic circuits and a graphical user interface for easy user configuration and monitoring. The system has integrated microfluidics to maintain its microphysiological environment within each well. The IMSIS platform currently incorporates O2, H2O2, and pH sensors inside each well, allowing up to six wells to perform concurrent measurements in real-time. Furthermore, the architecture is scalable to achieve an even higher level of throughput. The miniaturized design ensures portability, suitable for small offices and field applications.The IMSIS platform was successfully used to monitor in real-time the mitochondrial functions of live bovine embryos in O2 consumption, H2O2 release as an indication of ROS production, and extracellular acidity changes before and after the introduction of external substrates.

Ensemble Learning Improves the Efficiency of Microseismic Signal Classification in Landslide Seismic Monitoring.

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms.

Monitoring system of dangerous and harmful factors in the production environment

The work presents the principles of building control systems of physical factors of the production environment. The set of information sources of control of physical harmful and dangerous factors of the production environment is considered as a set of sensors of random processes. It is shown that for the construction of a system of physical control of the production environment, it is expedient to use adaptive principles of system construction. The structural scheme of the system implementing the specified principle is presented.

Implementacja systemów elektronicznych w szelkach bezpieczeństwa i urządzeniach samohamownych

Implementation of electronic systems in safety harnesses and self-braking devices The aim of this publication is to discusses issues related to the use of electronic systems in equipment protecting against falls from height. They are used both in the form of light and sound modules, as well as in the form of sets of sensors, detectors, data transmission blocks, or even entire complex electronic systems. These systems are used to improve work safety, and personal protective equipment equipped in this way is called intelligent. The aim of the article is also to present the prototype of a self-locking device for the dynamic shortening of the fall path. The electronic-mechanical locking system in the self-locking device, developed at the Central Institute for Labour Protection – National Research Institute, allows for its dynamic activation, independent of the external energy generated during the fall of a person. Thanks to this construction, it is possible to reduce the free fall path, and thus the forces acting on a person when stopping him, as well as work the self-locking device in a horizontal or close to a horizontal position and use it as a device preventing the start of a fall. The construction and operation of the designed device were shown, and the possibilities of its use were presented in the article. Keywords: work at height, fall protection equipment, control electronic systems, intelligent personal protective equipment

Smart Medical Evacuation Support System for the Military.

Medical support in crisis situations is a major challenge. Efficient implementation of the medical evacuation process especially in operations with limited human resources that may occur during armed conflicts can limit the loss of these resources. Proper evacuation of wounded soldiers from the battlefield can increase the chances of their survival and rapid return to further military operations. This paper presents the technical details of the decision support system for medical evacuation to support this process. The basis for the functioning of this system is the continuous measurement of vital signs of soldiers via a specialized measurement module with a set of medical sensors. Vital signs values are then transmitted via the communication module to the analysis and inference module, which automatically determines the color of medical triage and the soldier's chance of survival. This paper presents the results of tests of our system to validate it, which were carried out using test vectors of soldiers' vital signs, as well as the results of the system's performance on a group of volunteers who performed typical activities of tactical operations. The results of this study showed the usefulness of the developed system for supporting military medical services in military operations.

All-in-One, Wireless, Multi-Sensor Integrated Athlete Health Monitor for Real-Time Continuous Detection of Dehydration and Physiological Stress.

Athletes are at high risk of dehydration, fatigue, and cardiac disorders due to extreme performance in often harsh environments. Despite advancements in sports training protocols, there is an urgent need for a non-invasive system capable of comprehensive health monitoring. Although a few existing wearables measure athlete's performance, they are limited by a single function, rigidity, bulkiness, and required straps and adhesives. Here, an all-in-one, multi-sensor integrated wearable system utilizing a set of nanomembrane soft sensors and electronics, enabling wireless, real-time, continuous monitoring of saliva osmolality, skin temperature, and heart functions is introduced. This system, using a soft patch and a sensor-integrated mouthguard, provides comprehensive monitoring of an athlete's hydration and physiological stress levels. A validation study in detecting real-time physiological levels shows the device's performance in capturing moments (400-500s) of synchronized acute elevation in dehydration (350%) and physiological strain (175%) during field training sessions. Demonstration with a few human subjects highlights the system's capability to detect early signs of health abnormality, thus improving the healthcare of sports athletes.

Effect of moisture on the sensing capabilities of piezoelectric actuator/sensor pairs on flax fibre reinforced composite laminates

The sensitivity of the piezoelectric actuators’ response to the moisture uptake has been investigated on flax fibre reinforced composite laminates. Non-woven flax fabric was impregnated with epoxy and composite laminates were fabricated using hand lay-up and cured in a compression moulding machine. The laminates were initially impacted with a drop-weight impact machine at a low energy level, with the aim to generate an artificial surface crack that will allow the moisture to enter the fibre-matrix interface more effectively. A set of piezoelectric actuators and sensors were adhered on the surfaces of the composite panels in a specific rectangular arrangement to allow for wave capturing at various directions. The wave characteristics of the samples were extracted in pristine stage and then the samples were impacted and immersed in distilled water until saturation. At regular intervals after the water immersion, the panels’ weight was measured using a laboratory scale and the wave propagation characteristics of the materials ware measured in order to investigate the gradual effect of moisture on the capabilities of the actuators and sensors. The propagation of stress waves in the dry and wet samples was investigated and the effect of moisture absorption was examined experimentally using piezoelectric wafers until the saturation was reached. Finally, a continuum damage mechanics layerwise time domain spectral finite element model, both for the composite laminate and the rich resin layers, was also developed to simulate the materials’ performance under impact and evaluate the wave propagation within the material at the dry state.

An optimal sensor layout method based on noise reduction estimation for active road noise control

Active noise control (ANC) is an effective method to suppress vehicle road noise. The rapid selection of the reference sensor set and rational selection of its layout position are crucial for determining the vibration noise transmission paths with high contributions, which determines the noise reduction performance of the active road noise control (ARNC) system. The reference sensor set selected by the conventional multiple coherence function (MCOH) method does not always ensure the optimal noise reduction performance and the matrix singularity problem based on the Fisher information matrix (FIM) expansion method. To alleviate this problem, this paper proposes a method based on the overall level of noise reduction (OANR) and the FIM to select a set of reference sensors and determine their positions. This method uses an optimal causally constrained Wiener filter to estimate the theoretical OANR for each control area to ensure the reference sensor selected has the optimal noise reduction performance, and it expands efficiently based on the FIM method to select a set of reference sensors. Besides, the matrix singularity problems in the FIM-based expansion method are solved using noise frequency summation and matrix operation, which makes the method more universally applicable. Numerical simulations are performed to analyze and evaluate the noise reduction performance and selection efficiency of the proposed method under different conditions. In addition, a series of real vehicle ANC experiments are conducted. The results show that the reference sensor set selected based on the proposed method has an obvious advantage in noise reduction performance, and only four reference sensors are needed to achieve 4.63 dB(A) noise reduction in ARNC experiments. It fully confirms the effectiveness of the proposed method in real vehicle applications.

Neural network-based estimation of lower limb joint kinematics: A minimally intrusive approach for gait analysis

The establishment of a quantitative gait analysis system holds paramount importance, particularly in the context of functional rehabilitation of the lower limbs. Clinicians emphasize the imperative for sensors to be portable, compact, integrated, and non-intrusive, crucial characteristics in the rehabilitation field to facilitate their use and ensure optimal integration into care protocols. This study investigates an innovative approach aimed at reducing the reliance on body-fixed sensors by harnessing their data within a neural network, thus concentrating on the joint kinematics of the lower limbs. The primary objective is to estimate the flexion-extension angles of the hip, knee, and ankle during walking, utilizing data collected by two sensors positioned on the subject's legs. Initially, the neural network undergoes training with calculated data (leg tilt angles and angular velocities) sourced from the OpenSim database, followed by further refinement with experimental data obtained from a subject walking on a treadmill, wherein leg tilt angles and angular velocities are measured. The significance of this research is underscored by the demonstrated capability, through conducted tests, of the implemented networks to efficiently fuse data from a minimal set of sensors. Consequently, the proposed approach emerges as both practical and minimally intrusive, facilitating a robust evaluation of gait kinematic parameters.

A study on active road noise control based on operational transfer path analysis and selective subband adaptive filtering

In the feedforward active road noise control (ARNC) system, the noise reduction performance relies on the correlation between the reference signals and the target noise signals. To achieve better noise reduction performance, the operational transfer path analysis (OTPA) model with singular value decomposition was proposed to separate the road noise component from the target noise. Combined with OTPA and multi-coherence sorting method (MCSM), simulation analysis and real vehicle tests under various speeds both showed that the system with optimized reference sensor set had better road noise reduction performance, especially at the peak frequencies. To further improve noise reduction performance and reduce computational load, a selective subband adaptive filtering (SSAF) algorithm was proposed to build an active road noise control model with optimized reference sensor set. Simulation results, employing real vehicle test data, showed that the proposed method further improved the noise reduction performance and effectively reduced the amount of computational load.

Deep learning algorithms for detecting freezing of gait in Parkinson’s disease: A cross-dataset study

Freezing of gait is a complex and disabling symptom of Parkinson’s disease, which has a significant impact on the patients’ quality of life and increases the risk of falls and related injuries. This study aims to evaluate the generalization capability of deep learning algorithms in freezing of gait detection. To address this task, various machine learning and deep learning algorithms were implemented, fine-tuned, and evaluated using diverse data splitting and validation strategies. The experiments performed yielded mixed results. Although the implementations demonstrated competitive performance in single-dataset settings (area under the curve ranging from 0.77 to 0.94), all approaches showed limited robustness in cross-dataset tests and suboptimal generalization across different datasets (area under the curve ranging from 0.65 to 0.84). These results highlight the importance of standardized data collection procedures to ensure uniformity. The specification of sensor settings and predefined sensor locations can foster homogeneity in datasets, even when dealing with diverse subjects and environments. Such standardization efforts are crucial for advancing generalized methodologies in the detection of freezing of gait, applicable to both research and clinical applications.

Social media sensors as early signals of influenza outbreaks at scale

Detecting early signals of an outbreak in a viral process is challenging due to its exponential nature, yet crucial given the benefits to public health it can provide. If available, the network structure where infection happens can provide rich information about the very early stages of viral outbreaks. For example, more central nodes have been used as social network sensors in biological or informational diffusion processes to detect early contagious outbreaks. We aim to combine both approaches to detect early signals of a biological viral process (influenza-like illness, ILI), using its informational epidemic coverage in public social media. We use a large social media dataset covering three years in a country. We demonstrate that it is possible to use highly central users on social media, more precisely high out-degree users from Twitter, as sensors to detect the early signals of ILI outbreaks in the physical world without monitoring the whole population. We also investigate other behavioral and content features that distinguish those early sensors in social media beyond centrality. While high centrality on Twitter is the most distinctive feature of sensors, they are more likely to talk about local news, language, politics, or government than the rest of the users. Our new approach could detect a better and smaller set of social sensors for epidemic outbreaks and is more operationally efficient and privacy respectful than previous ones, not requiring the collection of vast amounts of data.

Generating Hidden Markov Models from Process Models Through Nonnegative Tensor Factorization

Monitoring of industrial processes is a critical capability in industry and in government to ensure reliability of production cycles, quick emergency response, and national security. Process monitoring allows users to gauge the progress of an organization in an industrial process or predict the degradation or aging of machine parts in processes taking place at a remote location. Similar to many data science applications, we usually only have access to limited raw data, such as satellite imagery, short video clips, event logs, and signatures captured by a small set of sensors. To combat data scarcity, we leverage the knowledge of Subject Matter Experts (SMEs) who are familiar with the actions of interest. SMEs provide expert knowledge of the essential activities required for task completion and the resources necessary to carry out each of these activities. Various process mining techniques have been developed for this type of analysis; typically such approaches combine theoretical process models built based on domain expert insights with ad-hoc integration of available pieces of raw data. Here, we introduce a novel mathematically sound method that integrates theoretical process models (as proposed by SMEs) with interrelated minimal Hidden Markov Models (HMM), built via nonnegative tensor factorization. Our method consolidates: (a) theoretical process models, (b) HMMs, (c) coupled nonnegative matrix-tensor factorizations, and (d) custom model selection. To demonstrate our methodology and its abilities, we apply it on simple synthetic and real world process models.

Automatic Detection and Intensity Classification of Pitch Misalignment of Wind Turbine Blades: a Learning-based Approach

In recent years, monitoring wind turbine operations, especially in offshore and remote installations, has become crucial. System failures, challenging assessments, and costly maintenance operations are notable concerns. Blade pitch misalignment poses one of the most significant threats, being a leading cause of downtime and energy production reduction. Traditional assessments through frequent inspections are resource-intensive and time-consuming; still they are frequently required as turbines lack routine implementation of effective automatic detection systems.To address this, our study introduces a novel machine learning-based method for autonomous pitch misalignment recognition, which relies on signals measured by a limited set of sensors, already integrated into modern wind turbines. From those signals, frequency domain features derived by harmonic analysis are extracted, ensuring robust detection also in turbulent wind conditions.This innovative method lays the groundwork for early and precise wind turbine diagnostics, promoting the shift from time-based to condition-based inspections. This transition aims to reduce maintenance costs and unexpected downtime, ultimately enhancing energy production.