Sensor Space Research Articles

Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—A review

Tropical cyclones (TCs) seriously endanger human life and the safety of property. Real-time monitoring of TCs has been one of the focal points in meteorological studies. With the development of space technology and sensor technology, satellite remote sensing has become the main means of monitoring TCs. Furthermore, with its superior data mining capability, deep learning has shown advantages over traditional physical or statistical-based algorithms in the geosciences. As a result, more deep-learning algorithms are being developed and applied to extract TC information. This paper systematically reviews the deep-learning frameworks used for TC information extraction and then gives two typical applications of deep-learning models for TC intensity and wind radius estimation. In addition, the authors present an outlook on the future perspectives of deep learning in TC information extraction.摘要热带气旋 (TC) 严重危害人类生命和财产安全, TC的实时监测一直是研究热点, 随着空间和传感器技术的发展, 卫星遥感已成为监测TC的主要手段. 此外, 深度学习具有卓越的数据挖掘能力, 在地球科学中的表现优于基于物理或统计的算法, 越来越多的深度学习算法被开发和应用于TC信息的提取, 本文系统地回顾了深度学习在TC信息提取中的应用, 并给出了深度学习模型在TC强度和风圈半径提取中的应用. 此外, 本文还展望了深度学习在TC信息提取中的应用前景.

A Fine-Tuning Based Approach for Daily Activity Recognition between Smart Homes

Daily activity recognition between different smart home environments faces some challenges, such as an insufficient amount of data and differences in data distribution. However, a deep network requires a large amount of labeled data for training. Additionally, inconsistent data distribution can lead to over-fitting of network learning. Additionally, the time cost of training the network from scratch is too high. In order to solve the above problems, this paper proposes a fine-tuning method suitable for daily activity recognition, which is the first application of this method in our field. Firstly, we unify the sensor space and activity space to reduce the variability in heterogeneous environments. Then, the Word2Vec algorithm is used to transform the activity samples into digital vectors recognizable by the network. Finally, the deep network is fine-tuned to transfer knowledge and complete the recognition task. Additionally, we try to train the network on public datasets. The results show that the network trained on a small dataset also has good transferability. It effectively improves the recognition accuracy and reduces the time cost and heavy data annotation.

Developing a digital twin model for monitoring building structural health by combining a building information model and a real-scene 3D model

Structural health monitoring (SHM) is a critical component of ensuring the safety of buildings, yet the effective management of sensors and their corresponding monitoring data is complex. Thus, a digital twin health monitoring information model for buildings was proposed to simultaneously locate sensors in space and monitor data. We described the requirements of this process and designed a conceptual model by combining a building information model (BIM) and a real-scene 3D model. The key steps in the fusion process include reconstructing the BIM into sub-BIMs considering building component types and geometric transformations, 3D spatial position registration with a rigid-body transformation method, and semantic information mapping. After the fusion process, monitoring data from sensors are stored in a database management system and integrated with the fused model. A digital twin model of the Nanjing Museum Old Hall was constructed as a case study, which evaluated the fusion method’s feasibility and usability.

Sex-Related Differences in Working Memory for Simple Visual Features. Analysis of Event-Related Potentials in the Space of Sensors and Dipole Sources

Sex-Related Differences in Working Memory for Simple Visual Features. Analysis of Event-Related Potentials in the Space of Sensors and Dipole Sources

Optimization of the Risk Functional to Control the Composition and Structure of a Heterogenous Grouping of Detection Sensors in Three-Dimensional Space

The steady growth in the scale and dynamics of the use of aerial weapons in the course of various conflicts necessitates the formulation and solution of the problems of building realistic systems to detect them. It should be noted that the priorities in the development of detection sensors is changing from solving problems to improve their characteristics to optimization and adaptability in controlling them. As an object, a heterogeneous grouping of sensors, which solves the problem of detecting a moving airborne object, is considered. The subject is the methodology for constructing control models for heterogeneous detection sensors. Based on the analysis of the antagonistic interaction of a heterogeneous grouping and airborne objects, as well as the processes of their functioning, a geometric approach to solve the problem of detecting a moving object (MO) is proposed, which uses an adapted and improved risk functional as one of the possible indicators for the further synthesis of the control algorithms. The practical effectiveness of the application of this functionality is substantiated and compared with other performance indicators through simulation modeling.

SCP model based on the new energy vehicle collaborative detection configuration method research

Abstract To address the problem of inaccurate positioning of new energy vehicles during cooperative detection, this paper investigates the positioning accuracy of different combinations of radar and infrared sensors. In order to meet the control requirements of the vehicle co-detection formation, a distributed control method considering the vehicle dynamics characteristics is adopted for this purpose. And considering the cost of sensors, the optimal parameters are calculated, and an optimal aircraft co-detection configuration design scheme based on the SCP model (structure-behavior-performance model) is proposed. At the working level of multi-craft cooperative detection guidance, a two-layer cooperative guidance structure is designed based on the basic framework. Research on vehicle configuration design, vehicle data transmission, processing technology, and cooperative detection and guidance is carried out. The basic principles of the particle swarm optimization algorithm and the algorithmic flow of the discrete particle swarm algorithm are applied to calculate the assignment of targets by the particle swarm optimization algorithm. The GDOP values are analyzed according to the simulation results, and it can be concluded that: the change rate of 2~5 sensors accuracy can reach 71.1%, 71.6%, and 71.5%, respectively, when the infrared sensor spacing is 1km~3km. 5~10 sensors accuracy change rate is only 53.3%, 52.2%, and 49.7%, respectively, which shows that the value is improved by 20%, indicating that the collaborative sensing accuracy of the aircraft has been effectively improved, which is of great help to the collaborative detection of new energy vehicles based on SCP model.

Efficient Underwater Acoustical Localization Method Based on TDOA with Sensor Position Errors

Underwater acoustic localization (UWAL) is extremely challenging due to the multipath nature of extreme underwater environments, the sensor position uncertainty caused by unpredictable ocean currents, and the lack of underwater observation data due to sparse array, which all affect localization performance. Addressing these issues, this paper proposes a simple and effective underwater acoustic localization method using the time difference of arrival (TDOA) measurements based on the multipath channel effect of the underwater environment. By introducing the calibration source, localization performance was improved, and the sensor position error was corrected. The Cramér–Rao lower bound (CRLB) was derived, and the proposed method was able to achieve the CRLB with small deviation. Numerical simulations confirm the improved performance of the proposed method, including (1) a 20 dB and 30 dB reduction in the CRLB for far and near source scenarios, respectively, indicating improved accuracy and reliability when estimating unknown sources; (2) better Mean Squared Error (MSE) performance compared to existing methods and an efficiency of over 90% in low noise and above 80% in moderate noise in several scenarios, with a delayed threshold effect; and (3) achieving CRLB performance with only three sensors in a 3D space, even under moderate noise, while existing methods require at least five sensors for comparable performance. Our results demonstrate the efficacy of the proposed method in enhancing the accuracy and efficiency of source localization.

Inter-individual single-trial classification of MEG data using M-CCA

Neuroscientific studies often involve some form of group analysis over multiple participants. This requires alignment of recordings across participants. A naive solution is to assume that participants’ recordings can be aligned anatomically in sensor space. However, this assumption is likely violated due to anatomical and functional differences between individual brains. In magnetoencephalography (MEG) recordings the problem of inter-subject alignment is exacerbated by the susceptibility of MEG to individual cortical folding patterns as well as the inter-subject variability of sensor locations over the brain due to the use of a fixed helmet. Hence, an approach to combine MEG data over individual brains should relax the assumptions that a) brain anatomy and function are tightly linked and b) that the same sensors capture functionally comparable brain activation across individuals. Here we use multiset canonical correlation analysis (M-CCA) to find a common representation of MEG activations recorded from 15 participants performing a grasping task. The M-CCA algorithm was applied to transform the data of a set of multiple participants into a common space with maximum correlation between participants. Importantly, we derive a method to transform data from a new, previously unseen participant into this common representation. This makes it useful for applications that require transfer of models derived from a group of individuals to new individuals. We demonstrate the usefulness and superiority of the approach with respect to previously used approaches. Finally, we show that our approach requires only a small number of labeled data from the new participant. The proposed method demonstrates that functionally motivated common spaces have potential applications in reducing training time of online brain-computer interfaces, where models can be pre-trained on previous participants/sessions. Moreover, inter-subject alignment via M-CCA has the potential for combining data of different participants and could become helpful in future endeavors on large open datasets.

Optimization of the Risk Functional to Control the Composition and Structure of a Heterogenous Grouping of Detection Sensors in Three-Dimensional Space

Optimization of the Risk Functional to Control the Composition and Structure of a Heterogenous Grouping of Detection Sensors in Three-Dimensional Space

Transfer Learning in Trajectory Decoding: Sensor or Source Space?

In this study, across-participant and across-session transfer learning was investigated to minimize the calibration time of the brain-computer interface (BCI) system in the context of continuous hand trajectory decoding. We reanalyzed data from a study with 10 able-bodied participants across three sessions. A leave-one-participant-out (LOPO) model was utilized as a starting model. Recursive exponentially weighted partial least squares regression (REW-PLS) was employed to overcome the memory limitation due to the large pool of training data. We considered four scenarios: generalized with no update (Gen), generalized with cumulative update (GenC), and individual models with cumulative (IndC) and non-cumulative (Ind) updates, with each one trained with sensor-space features or source-space features. The decoding performance in generalized models (Gen and GenC) was lower than the chance level. In individual models, the cumulative update (IndC) showed no significant improvement over the non-cumulative model (Ind). The performance showed the decoder's incapability to generalize across participants and sessions in this task. The results suggested that the best correlation could be achieved with the sensor-space individual model, despite additional anatomical information in the source-space features. The decoding pattern showed a more localized pattern around the precuneus over three sessions in Ind models.

Image quality and computer vision performance: assessing the effects of image distortions and modeling performance relationships using the general image quality equation

Substantial research has explored methods to optimize convolutional neural networks (CNNs) for tasks such as image classification and object detection, but research into the image quality drivers of computer vision performance has been limited. Additionally, there are indications that image degradations such as blur and noise affect human visual interpretation and machine interpretation differently. The general image quality equation (GIQE) predicts overhead image quality for human analysis using the National Image Interpretability Rating Scale, but no such model exists to predict image quality for interpretation by CNNs. Here, we assess the relationship between image quality variables and CNN performance. Specifically, we examine the impacts of resolution, blur, and noise on CNN performance for models trained with in-distribution and out-of-distribution distortions. Using two datasets, we observe that while generalization remains a significant challenge for CNNs faced with out-of-distribution image distortions, CNN performance against low visual quality images remains strong with appropriate training, indicating the potential to expand the design trade space for sensors providing data to computer vision systems. Additionally, we find that CNN performance predictions using the functional form of the GIQE can predict CNN performance as a function of image degradation, but we observe that the legacy form of the GIQE (from GIQE versions 3 and 4) does a better job of modeling the impact of blur/relative edge response in our experiments.

Effects of Early Nutrition Factors on Baseline Neurodevelopment during the First 6 Months of Life: An EEG Study.

Throughout infancy, the brain undergoes rapid changes in structure and function that are sensitive to environmental influences, such as diet. Breastfed (BF) infants score higher on cognitive tests throughout infancy and into adolescence than formula fed (FF) infants, and these differences in neurocognitive development are reflected in higher concentrations of white and grey matter as measured by MRI. To further explore the effect diet has on cognitive development, electroencephalography (EEG) is used as a direct measure of neuronal activity and to assess specific frequency bands associated with cognitive processes. Task-free baseline EEGs were collected from infants fed with human milk (BF), dairy-based formula (MF), or soy-based formula (SF) at 2, 3, 4, 5, and 6 months of age to explore differences in frequency bands in both sensor and source space. Significant global differences in sensor space were seen in beta and gamma bands between BF and SF groups at ages 2 and 6 months, and these differences were further observed through volumetric modeling in source space. We conclude that BF infants exhibit earlier brain maturation reflected in greater power spectral density in these frequency bands.

Longitudinal thermal imaging for scalable non-residential HVAC and occupant behaviour characterization

This work presents a study on the characterization of the air-conditioning (AC) usage pattern of non-residential buildings from longitudinal thermal images collected at the urban scale. The operational pattern of two different air-conditioning systems (water-cooled systems operating on a pre-set schedule and window AC units operated by the occupants) are studied from the thermal images. It is observed that for the water-cooled system, the difference between the rate of change of the window and wall temperature can be used to extract the operational pattern. While, in the case of the window AC units, wavelet transform of the AC unit temperature is used to extract the frequency and time domain information of the AC unit operation. The results of the analysis are compared against the indoor temperature sensors installed in the office spaces of the building. This forms one of the first few studies on the operational behavior of HVAC systems for non-residential buildings using the longitudinal thermal imaging technique. The output from this study can be used to better understand the operational and occupant behavior, without requiring to deploy a large array of sensors in the building space.

An azimuthal mode detection method based on angular deviation and its application in compressor

A deep understanding of the generation of rotating pressure fluctuations is a prerequisite for designing compressors with higher efficiency, lower noise, and a broader operating range. Azimuth modal analysis is an effective method to analyze the characteristics and sources of rotating pressure fluctuations. This study proposes a method for azimuthal mode detection based on equally spaced sensors with uncertain angular deviations, combining the spatial Fourier transform (SFT) method with the compressed sensing (CS) technique. The result of numerical experiments indicates that the angular deviation of the sensors causes an error in mode reconstruction, especially when the mode order is high. Two optimization schemes are developed to obtain the angular deviation. The effectiveness of the optimization schemes was analyzed through numerical experiments. Finally, the effectiveness of the proposed method was verified by a compressor mode test. The general procedure of this method for a fan/compressor test is given.

Theoretical error formation and evaluation of acoustic source localization for cluster-based techniques

In this paper, the formation of theoretical error is presented to investigate the acoustic source localization (ASL) error that can be expected from traditional L-shaped, cross-shaped, square-shaped, and modified square-shaped sensor cluster arrangements. The response surface model based on the optimal Latin hypercube design is developed to theoretically study the effects of sensor placement parameters on the error evaluation index of root mean squared relative error (RMSRE) for the four techniques. The ASL results from the four techniques with the optimal placement parameters are analyzed theoretically. The relevant experiments are conducted for verifying the above theoretical research. The results show that the theoretical error, formed by the difference between the true and the predicted wave propagation directions is related to arrangement of sensors. The results also show that the sensor spacing and the cluster spacing are the two parameters that affect the ASL error most. Between these two parameters the sensor spacing has the stronger influence. The RMSRE increases with an increasing sensor spacing and a decreasing cluster spacing. Meanwhile, the interaction effect of placement parameters should be also emphasized, especially that between the sensor spacing and the cluster spacing for the L-shaped sensor cluster-based technique. Among the four cluster-based techniques, the newly modified square-shaped sensor cluster-based technique shows the smallest RMSRE and not the largest number of sensors. This research on error generation and analysis will provide guidance for the optimal sensor arrangements in cluster-based techniques.

Technology roadmap for cold-atoms based quantum inertial sensor in space

Recent developments in quantum technology have resulted in a new generation of sensors for measuring inertial quantities, such as acceleration and rotation. These sensors can exhibit unprecedented sensitivity and accuracy when operated in space, where the free-fall interrogation time can be extended at will and where the environment noise is minimal. European laboratories have played a leading role in this field by developing concepts and tools to operate these quantum sensors in relevant environment, such as parabolic flights, free-fall towers, or sounding rockets. With the recent achievement of Bose–Einstein condensation on the International Space Station, the challenge is now to reach a technology readiness level sufficiently high at both component and system levels to provide “off the shelf” payload for future generations of space missions in geodesy or fundamental physics. In this roadmap, we provide an extensive review on the status of all common parts, needs, and subsystems for the application of atom-based interferometers in space, in order to push for the development of generic technology components.

Novel Secure Data Transmission Methods for IoT Based on STP-CS With Multilevel Critical Information Concealment Function

The Internet of Things (IoT) is a large-scale network of various sensing devices connected via the Internet to achieve intelligent functions. Efficient secure data transmission is a significant guarantee for specific functions of IoT. In recent years, compressive sensing (CS) has been applied to the field of the IoT and a substantial number of CS-based IoT data transmission schemes have been proposed. While existing IoT data transmission schemes based on CS could mostly accomplish signal sampling, data compression, and encrypted transmission, the goal of privacy protection has rarely been achieved. Based on chaos theory and semi-tensor product CS (STP-CS), this article proposes two novel secure data transmission methods for different scenarios of IoT: 1) multiple concealing method (MC method) and 2) precise concealing method (PC method). Both methods can provide different levels of reconstruction results for different receivers with various authorization levels. The feasibility, storage requirements, robustness, and security of the proposed methods are theoretically analyzed and experimentally simulated. The results show that the proposed methods ensure both the stability and security of data transmission, save storage space of sensors, and flexibly protect the privacy of the content of data transmitted.

Detecting and tracking hypersonic glide vehicles: A cybersecurity-engineering analysis of academic literature

Hypersonic vehicles are vehicles travelling faster than Mach 5 (five times the speed of sound). Hypersonic technologies have existed since the end of the 1950s, but recent developments of defence applications have led to their resurgence. Hypersonic weapons can be hypersonic (powered) cruise missiles or hypersonic glide vehicles (HGVs). The near-space trajectories of HGV, combined with their superior manoeuvrability, enable HGVs to evade existing space and terrestrial sensors used to track ballistic missiles, posing an immediate threat to today’s radar networks and making HGVs well-suited for intercontinental (> 5500 km) targets. Securing HGV detection and tracking systems is of great interest to at-risk nations and cybersecurity researchers alike.
 
 However, like hypersonic flight technologies, HGV defence technologies are heavily guarded secrets. The shortage of public-domain information did not stop academia from proposing various detection and tracking schemes, but a reasonable question is: “How credible and useful is current public-domain information, including academic publications, on HGV detection and tracking for academic researchers to base their cybersecurity research on?” To answer this question, we scanned and critically reviewed public-domain literature on HGV detection and tracking. We then identified ambiguities and knowledge gaps in the literature. In this paper, we provide a concise version of our multivocal literature review and an analysis of the identified ambiguities and knowledge gaps in our attempt to answer our earlier question.

Determining the pressure increase in the hydraulic cylinders of powered roof support based on actual measurements

Powered roof support in a longwall operation is designed to maintain a safe working area and allow the immediate roof to fail and collapse behind the support. The powered supports are loaded using large hydraulic pumps with non-return and preset-yielding valves. In addition to providing support to the immediate roof in the longwall production area, it also moves the armoured face conveyor and shearer forward as coal mining progresses. The research aimed to analyse the changes in the pressure values in the powered roof support section's hydraulic cylinders in relation to the occurrence of rock mass movements in the roof. The pressure measurements are based on the sensors in the sub-piston space of the powered roof support hydraulic prop located in the steel wall. The results allow a correlation to be developed between the roof movement and the loads generated in the hydraulic cylinders.

Simulations for Planning of Liquid Hydrogen Spill Test

In order to better understand the complex pooling and vaporization of a liquid hydrogen spill, Sandia National Laboratories is conducting a highly instrumented, controlled experiment inside their Shock Tube Facility. Simulations were run before the experiment to help with the planning of experimental conditions, including sensor placement and cross wind velocity. This paper describes the modeling used in this planning process and its main conclusions. Sierra Suite’s Fuego, an in-house computational fluid dynamics code, was used to simulate a RANS model of a liquid hydrogen spill with five crosswind velocities: 0.45, 0.89, 1.34, 1.79, and 2.24 m/s. Two pool sizes were considered: a diameter of 0.85 m and a diameter of 1.7. A grid resolution study was completed on the smaller pool size with a 1.34 m/s crosswind. A comparison of the length and height of the plume of flammable hydrogen vaporizing from the pool shows that the plume becomes longer and remains closer to the ground with increasing wind speed. The plume reaches the top of the facility only in the 0.45 m/s case. From these results, we concluded that it will be best for the spacing and location of the concentration sensors to be reconfigured for each wind speed during the experiment.