Search

Assessment of driver stress, crucial for road safety, can greatly benefit from the analysis of multimodal physiological signals. However, fusing such heterogeneous data poses significant challenges, particularly in intermediate fusion where noise can also be fused. In this study, we address this challenge by exploring a 1D convolutional neural network (CNN) with self-attention mechanisms on multimodal data. Electrocardiogram (ECG) signals (256 Hz) and respiration (RESP) signals (128 Hz) were obtained from ten subjects using textile electrodes while driving in different scenarios, namely normal driving and phone usage (calling). The obtained multimodal data is preprocessed and then applied to a self-attention mechanism (SAM) CNN (SAMcNN) to identify driver stress. Experiments are validated using Leave-one-outsubject cross validation. The proposed approach is capable of classifying driver stress. It is observed that shorter segments yield an accuracy of 64.16% compared to longer segment lengths. Thus, exploring self-attention mechanisms for multimodal signals using wearable shirts facilitates non-intrusive monitoring in real-world driving scenarios.

The local electricity system is a decentralized grid, one of the tasks of which is the optimized management of distributed energy resources. To achieve effective integration and interaction in the work of local systems at the level of residential and commercial buildings, a set of systems and algorithms that are combined into monitoring systems is required. A transactive energy system allows multiple interconnected buildings to exchange energy for greater energy efficiency. The article presents the peculiarities of monitoring such systems, the method of assessing the efficiency of the local sys-tem and the assessment of the unevenness of the energy consumption schedules when powering the elements of the local system. The introduction of modern programs (mechanisms) of demand side management to participate in the balanc-ing of supply and demand is considered. The application of demand management mechanisms for a local system with non-intrusive load monitoring and an energy management system based on transactive energy approaches and methods is considered. Bibl 14, fig. 2.

In modern industries, pipelines play a crucial role, both as an essential element in energy transportation (water, gas and electricity) and also in the distribution of these resources. The large size of piping infrastructures, their age and unpredictable external factors are the main difficulties in monitoring the piping system. In this context, the detection and the localization of leaks are challenging but essential, as leaks lead to substantial economic losses. Current methods have many limitations, involving invasive procedures, working only with short pipes or requiring a system shutdown. This paper presents a non-intrusive method based on acoustic signal processing. Leak detection is performed using matched filters, while localization is performed based on the phase diagram representation method and diagram-based entropy computation. Our continuous monitoring system was used for two months and a full comparison with the video inspection-based technique was conducted. The results indicate that this method has a high accuracy, regardless of the length of the pipe. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) generation systems are susceptible to various types of faults. Our objective is to identify unusual operating conditions in a photovoltaic string using only the voltage and current generated at its terminals. To achieve this, we collected voltage and current samples produced by a PV string consisting of six panels during typical operation and four possible types of faults: full panel shading, partial panel shading, panel short-circuits, and electrical arcs in conductor cables. The first three fault groups were further subdivided into six faults, one for each PV panel, resulting in 20 different operating conditions. We collected samples of the electrical system's generation under each state in different climatic situations. We used the resulting dataset to train a convolutional neural network (CNN) and a classic machine learning method, K-Nearest Neighbors (KNN). The results showed that the CNN's ability to learn the characteristics that identify each of the 20 operating conditions resulted in an average accuracy of 95.78%, while the KNN, taking into account previously defined features, achieved an accuracy of 86.34%. [ABSTRACT FROM AUTHOR]

Fabric pilling performance is one of the key indicators for evaluating textile quality, but there is limited research on the effectiveness of pilling detection traceability and non-intrusive monitoring of detection equipment operating status. In this paper, a multi-source data-driven method for classifying the working status of fabric pilling performance detection is proposed. This study constructs a real-time non-intrusive monitoring system for fabric pilling detection in a laboratory environment, collecting multiple types of data such as electrical parameters of pilling detection equipment, personnel behavior, and equipment noise. GoogLeNet convolutional neural network is used to recognize high-dimensional audio data and achieve feature dimension reduction. By constructing a multi-classification algorithm based on Decision Tree-Support Vector Machine (DT-SVM) for the pilling detection process, a minimum accuracy of 95.62% is achieved in practical operation. This system not only perceives the relevant influencing factors of detection activities without interfering with normal detection activities but also effectively distinguishes various detection working states, providing new ideas for the effectiveness traceability of pilling detection activities.

Generally, an accurate model can describe the operating states of a system more effectively and provide a more reliable theoretical basis for the system optimization and control. Different from the traditional intrusive modeling, a non-intrusive modeling method based on two-stage generative adversarial network (TS-GAN) is proposed for integrated energy system (IES). By using this method, non-intrusive modeling for the IES including photovoltaic, wind power, energy storage, and energy coupling equipment can be carried out. First, the characteristics of IES are analyzed and extracted based on the meteorological data, energy output, and energy price, and then the characteristic database is established. Meanwhile, the loads are classified as uncontrollable loads and schedulable loads based on frequency domain decomposition to facilitate energy management. Furthermore, TS-GAN algorithm based on the Stackelberg game is designed. In the TS-GAN, the first-stage GAN is used to generate the operating data of each equipment identified by non-invasive monitoring, and the second-stage GAN distinguishes the accumulated data generated by first-stage GAN and further modifies the generator models of the first-stage GAN. Finally, the effectiveness and accuracy of the proposed method are verified by the simulation of an energy region.

The following article presents the results obtained in experiences that use the Impulse Frequency Response Analysis (IFRA) method with a transformer in service. The IFRA method has been implemented in order to transform the transient signals to the frequency domain using Discrete Fourier Transform (DFT). However, it can be considered that the DFT is not the most suitable tool for this type of analysis, since, by definition, this tool is useful for processing stationary signals. Taking that into consideration, the analysis of transient signals could be hypothetically improved by using continuous wavelet transform (CWT), given their variable time/frequency resolution. The analysis of transient signals in Wavelet domain has improved the repeatability of the frequency response curves, as it has been ob-served in experimental results. The proposed on-line IFRA method, based on Wavelet transform, was validated under load and no-load conditions on a 150 kVA three-phase transformer 13200/225 Volts, in the Campus of the Universidad del Valle, Cali, Colombia.

Demand response services and energy communities are set to be vital in bringing citizens to the core of the energy transition. The success of load flexibility integration in the electricity market, provided by demand response services, will depend on a redesign or adaptation of the current regulatory framework, which so far only reaches large industrial electricity users. However, due to the high contribution of the residential sector to electricity consumption, there is huge potential when considering the aggregated load flexibility of this sector. Nevertheless, challenges remain in load flexibility estimation and attaining data integrity while respecting consumer privacy. This study presents a methodology to estimate such flexibility by integrating a non-intrusive load monitoring approach to load disaggregation algorithms in order to train a machine-learning model. We then apply a categorization of loads and develop flexibility criteria, targeting each load flexibility amplitude with a corresponding time. Two datasets, Residential Energy Disaggregation Dataset (REDD) and Refit, are used to simulate the flexibility for a specific household, applying it to a grid balancing event request. Two algorithms are used for load disaggregation, Combinatorial Optimization, and a Factorial Hidden Markov model, and the U.K. demand response Short Term Operating Reserve (STOR) program is used for market integration. Results show a maximum flexibility power of 200−245 W and 180−500 W for the REDD and Refit datasets, respectively. The accuracy metrics of the flexibility models are presented, and results are discussed considering market barriers.

Occupancy detection for buildings is crucial to improving energy efficiency, user comfort, and space utility. However, existing methods require dedicated system setup, continuous calibration, and frequent maintenance. With the instrumentation of electricity meters in millions of homes and offices, however, power measurement presents a unique opportunity for a non-intrusive and cost-effective way to detect occupant presence. This study develops solutions to the problems when no data or limited data is available for training, as motivated by difficulties in ground truth collection. Experimental evaluations on data from both residential and commercial buildings indicate that the proposed methods for binary occupancy detection are nearly as accurate as models learned with sufficient data, with accuracies of approximately 78 to 93 percent for residences and 90 percent for offices. This study shows that power usage contains valuable and sensitive user information, demonstrating a virtual occupancy sensing approach with minimal system calibration and setup. [ABSTRACT FROM AUTHOR]

Objective: This paper introduces a methodology for the non-intrusive detection of von Kármán vortex street cavitation. It is based on the cyclostationary analysis of the airborne noise radiated by the collapsing bubbles. Materials and methods: A hydrodynamic profile is mounted in the test section of a high-speed cavitation tunnel, and the phenomenon is reproduced under controlled conditions of flow and pressure. The angle of incidence is kept constant. Flow velocity is varied to regulate the vortex generation frequency, and the pressure is adjusted to control the cavitation onset. Highspeed photography is used to confirm the occurrence of cavitation in the core of the vortices. A laser vibrometer pointing to the upper surface of the profile validates the fluid-structure interaction due to the vortex shedding. A microphone is used to sense the sound produced by the phenomenon and transmitted to the environment. Results and discussion: The cyclic coherence showed uncoupled evidence of the periodic detachment of vortices and the presence or absence of cavitation in their cores, reaching values close to 0.7 for specific frequencies. Conclusion: A non-intrusive monitoring approach and a statistical indicator were implemented to allow the diagnosis of such phenomena. [ABSTRACT FROM AUTHOR]

• Distributed acoustic sensing (DAS) is used for flow monitoring, which overcomes complex networking and limited monitoring range in single-point flow measurement. • An exponential relationship between flow rate and pressure is obtained through theoretical analysis and validated by intrusive and non-intrusive simulations. • Through distributed experiments, the intrusive monitoring is verified to have a better degree of fitting up to 0.99432 and uncertainty less than 1%. Distributed optical fiber acoustic sensing has become a research hotspot in the field of microflow monitoring due to its simple structure and wide monitoring range. In this paper, a new method of modal frequency analysis is proposed based on the dynamic pressure of pipeline flow. Theoretical analysis and simulation results demonstrate that the pressure has an exponential relationship with the flow rate. Secondarily, an experimental system of intrusive and non-intrusive flow measuring based on distributed acoustic sensing is designed. With the flow rate range of 0.258–0.349 m/s, experimental result shows that the excellent exponential relationship between dynamic pressure and flow rate can be obtained by using the intrusive monitoring with the frequency band of 450 Hz-550 Hz and the non-intrusive monitoring with the frequency range of 750–850 Hz, respectively. The intrusive method has a better fitting and relative measurement error, with the degree of fitting verified up to 0.99432 and the optimal relative measurement error less than 1%. [ABSTRACT FROM AUTHOR]

This paper presents a new method based on Higher-order Statistics for non-intrusive residential electrical load identification. Basically, the proposed method extracts cumulants of second and fourth order from the electric current signal of the residential electrical loads and presents these cumulants to a previously trained artificial neural network for classification. The neural network output identifies the residential electric load class of the processed signal. This study considered eleven different classes of residential electrical loads. Results were carried out from experimental electric signals and the achieved overall performance was over to 97%. [ABSTRACT FROM PUBLISHER]

Copyright of Revista Ingeniería e Investigación is the property of Universidad Nacional de Colombia, Facultad de Ingenieraia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, a new approach is proposed for the assessment of a vortex in fluid flow using an active acoustic system. The experiment is done on a reduced scale experimental pipe with ultrasonic transceivers. The purpose of the paper is to point out the presence of cavitation appearing in this pipe using wide band signals in the active acoustic system mode. Therefore, the Recurrence Plot Analysis (RPA) method which constitutes an interesting tool for the characterization of a dynamical system is used in terms of signal processing. The investigation is done varying the flow from steady flow to cavitation flow and backwards. [ABSTRACT FROM AUTHOR]

Abstract: When operated far from their optimum conditions, pump-turbines may exhibit strong hydrodynamic instabilities, often called rotating stall, which lead to substantial increase of vibration and risk of mechanical failure. In the present study, we have investigated the flow filed in a model of radial pump-turbine with the help of tuft visualization, wall pressure measurement and structure-borne noise monitoring. As the rotation speed is increased, the machine is brought from its optimum operation to runaway with zero torque on the shaft. The runaway operation is characterized by a significant increase of pressure fluctuation at the rotor–stator interaction frequency. As the speed is further increased, the flow exhibits sub-synchronous instability, which rotates at 70% of the rotation frequency. Tuft visualization clearly shows that, as the instability evolves, the flow in a given distributor channel suddenly stalls and switches to reverse pumping mode in periodic way. We have also investigated the monitoring of the rotating stall with the help of vibration signals. A specific signal processing method, based on amplitude demodulation, was developed. The use of 2 accelerometers allows for the identification of the optimum carrier frequency by computing the cyclic coherence of vibration signals. This non-intrusive method is proved to be efficient in detecting the rotating stall instability and the number of stall cells. We strongly believe that it could be implemented in full scale pump-turbines. [Copyright &y& Elsevier]

Nest monitoring is commonly used to gather important seabird demographic data, but monitoring itself can affect seabird behaviour and offspring survival. The effect of monitoring on grey-headed albatrossesThalassarche chrysostomaat Subantarctic Marion Island was investigated. The behaviour of chicks close to fledging and of brooding adults was recorded in research and non-research sections of the colony. This was done prior to, during and after researcher/s entered the research sections of the colony. During disturbance, both chicks and adults in research sections were more likely to be standing and to be more responsive than during the pre-disturbance phase. However, adults appeared to be more sensitised to disturbance and this is likely because of being previously handled. Offspring survival in research sections was compared with survival in (a) sections less-frequently entered (2004/2005) and (b) sections monitored through fixed-point photography (2005/2006 and 2006/2007). In February of each of the three years of study, offspring survival was 62.5%, 55.8% and 71.8% respectively. Disturbance level, size of section and the interaction of these two factors did not explain significant amounts of the among-section survival variance, but rainfall explained almost all of the temporal variation in offspring survival in 2006/2007. Although research activities influenced the short-term behavioural responses of chicks and adults in the research sections of the colony, it did not seem to influence the survival of offspring. Nevertheless, fixed-point photography is recommended as a non-intrusive monitoring method. [ABSTRACT FROM AUTHOR]

Sand monitoring gives the benefits of avoiding equipment erosion and production failure in the oil industry. This paper presents the design and implementation of a reliable and cost-effective sand monitoring system for measuring sand production in gas and oil flows in real time. The designed monitoring system involves two acoustic emission (AE) sensors and one Doppler sensor for gauging the sand impaction and the velocity of sand particles in a nonintrusive manner, respectively. It is implemented on a field programmable gate array (FPGA) as a prototype for real-time data acquisition and processing, and evaluated using a testbed pump skid available in our laboratory. Relying on a low-cost FPGA board to integrate all acquisition and processing functionality, our monitoring system can measure the sand production amount on-the-fly reliably with high accuracy, according to our experimental evaluation. It is likely to achieve better accuracy than one without the Doppler sensor. The proposed monitoring system is affordable for wide deployment, given its high accuracy, good resilience to surrounding noise, and low cost (when compared with commercially available systems whose price tags can be some tenfold higher). [ABSTRACT FROM PUBLISHER]

Abstract: Bivalve mollusks are of major ecological and economical importance in coastal ecosystems. They are natural archives of environmental information extractable from its shell. The formation and size of growth increments delimited by striae are affected by environmental stressors. The mechanisms linking shell growth and striae deposition in relation to environmental variations are poorly understood but are likely associated with the animal''s valve-movement behavior. Here, we present a first attempt to record scallop valve movement using passive acoustics. This method has the advantage of being totally non-intrusive and deployable continuously, over the long term (months) and on a large number of individuals. By comparing simultaneous acoustic recordings with data from animal-attached movement sensors, we show that bivalve (Pecten maximus) adduction movements (here ‘coughs’) produce a specific sound. To evaluate the use of passive acoustic monitoring of these sounds in natural environments, we estimated if scallop coughing sounds are detectable in typical scallop habitats with different ambient noise levels. We found that scallop coughing sounds can be detected from a few to several tens of meters in different ambient noise environments. Furthermore, their acoustic characteristics are distinctive from those of other known benthic organisms. These results indicate that scallop valve movements can be monitored using passive acoustics in situ. We emphasize that acoustic recording is likely to become a powerful, non-intrusive method for the long-term monitoring of the behavior of a pectinid species and its responses to environmental changes affecting growth. [Copyright &y& Elsevier]

Remote, non-intrusive monitoring of elusive mammals remains problematic, particularly in running waters. The utility of using submerged infrared counters for monitoring non-intrusively the activity of Eurasian otters Lutra lutra was assessed in three tributaries of the River Dee (Beltie, Cattie, Feardar; Scotland) during 2003–2004. Otters passing through the infrared counters were strongly nocturnal and displayed a bimodal diel activity pattern. Seasonal activity indices varied fourfold between tributaries and peaked during the salmonid breeding season. The median time elapsing between consecutive night visits was 2.02±0.79 days and did not differ between tributaries. The median head–body length of adult otters was estimated at 75.0±1.1 cm, whereas median upstream swimming speed was calculated at 0.97±0.01 m s−1. Minimum census estimates revealed the activity of at least two adults in the Beltie, two adults and three juveniles in the Cattie, and two adults with one juvenile in the Feardar. Our study indicates that, under suitable conditions, infrared technology can be used effectively to examine non-intrusively the activity of free-ranging otters in running waters, offering some advantages over previous, more intrusive techniques that relied on the collection of spraints, the use of radioisotopes or the tracking of marked individuals. [ABSTRACT FROM AUTHOR]

Human activity recognition is essential for various smart-home applications. With the development of sensing technology, various approaches have been proposed for occupancy monitoring indoors. However, such approaches have practical limitations that they require additional occupancy sensors, which may raise privacy issues and obtrude on occupants' daily lives. In this research, a Wi-Fi-based occupancy monitoring system, Wi-Sensing, is proposed to recognize occupant's activities of daily living in a non-intrusive way by exploiting commercial off-the-shelf Wi-Fi devices. Channel State Information (CSI) has been extracted from Wi-Fi signals collected from multiple Wi-Fi devices, which could be replaced by Internet of Things (IoT) devices. While multiple receivers are needed to cover the entirety of an indoor space, previous approaches have been proposed to extract numerous features from a single transmitter–receiver pair. In this context, this study presents a new approach toward extracting spatial–temporal features from multiple receivers deployed throughout an indoor space. In this approach, a Short-Time Fourier Transform (STFT) was used to convert time-series CSI data into image data. The converted image data from each receiver was then integrated as large image data, which preserved the temporal-spatial information of all the receiver data. A Convolutional Neural Network (CNN) was used as a feature extractor for the image data, and Long Short-Term Memory (LSTM) was exploited to classify basic activities in daily life (e.g., personal hygiene, eating, mobility, etc.). Wi-Sensing provides over 96% classification accuracy in two different indoor environments. [ABSTRACT FROM AUTHOR]

Detection of vehicles on the road can contribute to the establishment of an intelligent transportation management system to allow smooth transportation and the reduction of road accidents. Thus far, an efficient and low-cost polymer flexible pressure sensor for vehicle detection is lacking. This paper presents a flexible sensor for vehicle sensing and demonstrates a wireless system for monitoring vehicles on the road. A vehicle sensor was fabricated by sandwiching a polyurethane material between aluminum top/bottom electrodes. The sensing mechanism was based on changes in capacitance due to variation in the distance between the two electrodes at an applied external pressure. A clear response against a pressure load of 0.65 Mpa was observed, which is the same pressure as that of the car tire area in contact with the road. Significantly, the sensor was easy to embed on the road line due to its mechanical flexibility and large size. A field test was carried out by embedding the sensor on the road and crossing the sensor with a car. Moreover, the signal displayed on the tablet indicated that the sensing system can be used for wireless detection of the axle, speed, or weight of the vehicle on the road. The findings suggest that the flexible pressure sensor is a promising tool for use as a low-cost vehicle detector in future intelligent transportation management. [ABSTRACT FROM AUTHOR]

Demand response services and energy communities are set to be vital in bringing citizens to the core of the energy transition. The success of load flexibility integration in the electricity market, provided by demand response services, will depend on a redesign or adaptation of the current regulatory framework, which so far only reaches large industrial electricity users. However, due to the high contribution of the residential sector to electricity consumption, there is huge potential when considering the aggregated load flexibility of this sector. Nevertheless, challenges remain in load flexibility estimation and attaining data integrity while respecting consumer privacy. This study presents a methodology to estimate such flexibility by integrating a non-intrusive load monitoring approach to load disaggregation algorithms in order to train a machine-learning model. We then apply a categorization of loads and develop flexibility criteria, targeting each load flexibility amplitude with a corresponding time. Two datasets, Residential Energy Disaggregation Dataset (REDD) and Refit, are used to simulate the flexibility for a specific household, applying it to a grid balancing event request. Two algorithms are used for load disaggregation, Combinatorial Optimization, and a Factorial Hidden Markov model, and the U.K. demand response Short Term Operating Reserve (STOR) program is used for market integration. Results show a maximum flexibility power of 200–245 W and 180–500 W for the REDD and Refit datasets, respectively. The accuracy metrics of the flexibility models are presented, and results are discussed considering market barriers. [ABSTRACT FROM AUTHOR]