Journal of Sensors

Recently, convolutional neural networks have demonstrated excellent performance on various visual tasks, including the classification of common two-dimensional images. In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain. More specifically, the architecture of the proposed classifier contains five layers with weights which are the input layer, the convolutional layer, the max pooling layer, the full connection layer, and the output layer. These five layers are implemented on each spectral signature to discriminate against others. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector machines and the conventional deep learning-based methods.

Land surface temperature is an important factor in many areas, such as global climate change, hydrological, geo-/biophysical, and urban land use/land cover. As the latest launched satellite from the LANDSAT family, LANDSAT 8 has opened new possibilities for understanding the events on the Earth with remote sensing. This study presents an algorithm for the automatic mapping of land surface temperature from LANDSAT 8 data. The tool was developed using the LANDSAT 8 thermal infrared sensor Band 10 data. Different methods and formulas were used in the algorithm that successfully retrieves the land surface temperature to help us study the thermal environment of the ground surface. To verify the algorithm, the land surface temperature and the near-air temperature were compared. The results showed that, for the first case, the standard deviation was 2.4°C, and for the second case, it was 2.7°C. For future studies, the tool should be refined within situmeasurements of land surface temperature.

Carbon nanotubes (CNTs) have received considerable attention in the field of electrochemical sensing, due to their unique structural, electronic and chemical properties, for instance, unique tubular nanostructure, large specific surface, excellent conductivity, modifiable sidewall, high conductivity, good biocompatibility, and so on. Here, we tried to give a comprehensive review on some important aspects of the applications of CNT‐based electrochemical sensors in biomedical systems, including the electrochemical nature of CNTs, the methods for dispersing CNTs in solution, the approaches to the immobilization of functional CNT sensing films on electrodes, and the extensive biomedical applications of the CNT‐based electrochemical sensors. In the last section, we mainly focused on the applications of CNT‐based electrochemical sensors in the analysis of various biological substances and drugs, the methods for constructing enzyme‐based electrochemical biosensors and the direct electron transfer of redox proteins on CNTs. Because several crucial factors (e.g., the surface properties of carbon nanotubes, the methods for constructing carbon nanotube electrodes and the manners for electrochemical sensing applications) predominated the analytical performances of carbon nanotube electrodes, a systematical comprehension of the related knowledge was essential to the acquaintance, mastery and development of carbon nanotube‐based electrochemical sensors.

Underwater wireless sensor networks are a newly emerging wireless technology in which small size sensors with limited energy and limited memory and bandwidth are deployed in deep sea water and various monitoring operations like tactical surveillance, environmental monitoring, and data collection are performed through these tiny sensors. Underwater wireless sensor networks are used for the exploration of underwater resources, oceanographic data collection, flood or disaster prevention, tactical surveillance systems, and unmanned underwater vehicles. Sensor nodes consist of a small memory, a central processing unit, and an antenna. Underwater networks are much different from terrestrial sensor networks as radio waves cannot be used in underwater wireless sensor networks. Acoustic channels are used for communication in deep sea water. Acoustic signals have many limitations, such as limited bandwidth, higher end-to-end delay, network path loss, higher propagation delay, and dynamic topology. Usually, these limitations result in higher energy consumption with a smaller number of packets delivered. The main aim nowadays is to operate sensor nodes having a smaller battery for a longer time in the network. This survey has discussed the state-of-the-art localization based and localization-free routing protocols. Routing associated issues in the area of underwater wireless sensor networks have also been discussed.

This numerical work proposes two novel designs of long‐range surface plasmon resonance sensors (LRSPR) using two different coupling prisms. The performance analysis of the proposed sensor has been investigated using the performance parameters like quality factor (Q), detection accuracy (DA), sensitivity (S), and full‐width half maximum (FWHM). The transfer matrix method (TMM) has been employed to compute reflectance. The role of the basic recognition element (BRE) has been played by the popular two‐dimensional (2D) material, black phosphorus (BP), due to its many optoelectrical features. The maximum obtained values for Q, DA, and S are 3333.25 (1/RIU), 250 (degree⁻¹), and 13.33333 degree/RIU for 2S2G coupled sensor design and 3055.5 (1/RIU), 83.33 (degree⁻¹), and 36.66667 degree/RIU for BK7 coupled sensor design. The operating wavelength of 633 nm, followed by the principle of attenuated total reflection (ATR), has been employed to carry out the theoretical investigation.

Currently, due to the rapid development and popularization of smartphones, the usage of ubiquitous smartphones has attracted growing interest in the field of structural health monitoring (SHM). The portable and rapid cable force measurement for cable-supported structures, such as a cable-stayed bridge and a suspension bridge, has an important and practical significance in the evaluation of initial damage and the recovery of transportation networks. The extraction of dynamic characteristics (natural frequencies) of cable is considered as an essential issue in the cable force estimation. Therefore, in this study, a vision-based approach is proposed for identifying the natural frequencies of cable using handheld shooting of smartphone camera. The boundary of cable is selected as a target to be tracked in the region of interest (ROI) of video image sequence captured by smartphone camera, and the dynamic characteristics of cable are identified according to its dynamic displacement responses in frequency domain. The moving average is adopted to eliminate the noise associated with the shaking of smartphone camera during measurement. A laboratory scale cable model test and a pedestrian cable-stayed bridge test are carried out to evaluate the proposed approach. The results demonstrate the feasibility of using smartphone camera for cable force estimation.

After roadway excavation, the deformation and failure of roadway surrounding rocks typically results in roadway damage or collapse. Conventional monitoring techniques, such as extensometers, stress meters, and convergence stations, are only capable to detect the stress or strain data with the shallow layers of surrounding rocks, and they require arduous manual works. Moreover, in the abovementioned monitoring techniques, the monitoring instruments are installed behind the excavation face; therefore, the strain and deformation occurring in front of excavation face cannot be detected. In order to eliminate these shortcomings, an innovative monitoring system for surrounding rock deformation control has been developed base on Brillouin optical time domain reflectometry. Compared with conventional monitoring systems, the proposed system provides a reliable, accurate, and real-time monitoring measure for roadway surrounding rock deformation control over wide extension. The optical fiber sensors are installed in boreholes which are situated ahead of the excavation face; therefore, the sensors can be protected well and the surrounding rock deformation behaviors can be studied. The proposed system has been applied within a TBM-excavated roadway in Zhangji coal mine, China. The surrounding rock deformation behaviors have been detected accurately, and the monitoring results provided essential references for surrounding rock deformation control works.

This study is focused on investigating the impact of topography and tidal height on ALOS PALSAR polarimetric measurements on HH and HV for estimating aboveground biomass (AGB) of mangrove forest in Indonesia. We used multitemporal ALOS PALSAR polarimetric measurement that covered mangrove zone in Banyuasin, Cilacap, and Teluk Bintuni and also collected tidal height data within the same acquisition date with multitemporal ALOS PALSAR polarimetric measurement. We analyzed the distribution of flooding and nonflooding areas based on tidal height and SRTM topography data, created three profiles as region of interest (ROI), and got characteristics of backscatter value on HH and HV with different tidal height. The result of this study showed backscatter of the open mangrove zones during high tide with HH value less than −20 dB and HV value less than −25 dB whereas during low tide it showed an HH value around −20 to −10 dB and HV value around −25 to −10 dB. Backscatter of the middle mangrove zones at Cilacap, with low and flat topography, showed a deviation of backscatter on HV value of 1.6 dB. Finally, the average AGB of mangrove forest in Indonesia was estimated based on ALOS PALSAR polarimetric measurements.

A new highly accurate closed-form capacitance calculation model has been developed to calculate the capacitance of capacitive micromachined ultrasonic transducers (CMUTs) built with square diaphragms. The model has been developed by using a two-dimensional polynomial function that more accurately predicts the deflection curve of a square diaphragm deformed under the influence of a uniform external pressure and also takes account of the fringing field capacitances. The model has been verified by comparing the model-predicted deflection profiles and capacitance values with experimental results published elsewhere and finite element analysis (FEA) carried out by the authors for different material properties, geometric specifications, and loading conditions. New model-calculated capacitance values are found to be in excellent agreement with published experimental results with a maximum deviation of 1.7%, and a maximum deviation of 1.5% has been observed when compared with FEA results. The model can help in improving the accuracy of the design methodology of CMUT devices and other MEMS-based capacitive type sensors built with square diaphragms.

Data-driven fault detection and diagnosis (FDD) methods, referring to the newer generation of artificial intelligence (AI) empowered classification methods, such as data science analysis, big data, Internet of things (IoT), industry 4.0, etc., become increasingly important for facility management in the smart building design and smart city construction. While data-driven FDD methods nowadays outperform the majority of traditional FDD approaches, such as the physically based models and mathematically based models, in terms of both efficiency and accuracy, the interpretability of those methods does not grow significantly. Instead, according to the literature survey, the interpretability of the data-driven FDD methods becomes the main concern and creates barriers for those methods to be adopted in real-world industrial applications. In this study, we reviewed the existing data-driven FDD approaches for building mechanical & electrical engineering (M&E) services faults and discussed the interpretability of the modern data-driven FDD methods. Two data-driven FDD strategies integrating the expert reasoning of the faults were proposed. Lists of expert rules, knowledge of maintainability, international/local standards were concluded for various M&E services, including heating, ventilation air-conditioning (HVAC), plumbing, fire safety, electrical and elevator systems based on surveys of 110 buildings in Singapore. The surveyed results significantly enhance the interpretability of data-driven FDD methods for M&E services, potentially enhance the FDD performance in terms of accuracy and promote the data-driven FDD approaches to real-world facility management practices.