Extracting the winter wheat using the decision tree based on time series dual-polarization SAR feature and NDVI.

Winter wheat is one of the most important crops in the world. It is great significance to obtain the planting area of winter wheat timely and accurately for formulating agricultural policies. Due to the limited resolution of single SAR data and the susceptibility of single optical data to weather conditions, it is difficult to accurately obtain the planting area of winter wheat using only SAR or optical data. To solve the problem of low accuracy of winter wheat extraction only using optical or SAR images, a decision tree classification method combining time series SAR backscattering feature and NDVI (Normalized Difference Vegetation Index) was constructed in this paper. By synergy using of SAR and optical data can compensate for their respective shortcomings. First, winter wheat was distinguished from other vegetation by NDVI at the maturity stage, and then it was extracted by SAR backscattering feature. This approach facilitates the semi-automated extraction of winter wheat. Taking Yucheng City of Shandong Province as study area, 9 Sentinel-1 images and one Sentinel-2 image were taken as the data sources, and the spatial distribution of winter wheat in 2022 was obtained. The results indicate that the overall accuracy (OA) and kappa coefficient (Kappa) of the proposed method are 96.10% and 0.94, respectively. Compared with the supervised classification of multi-temporal composite pseudocolor image and single Sentinel-2 image using Support Vector Machine (SVM) classifier, the OA are improved by 10.69% and 5.66%, respectively. Compared with using only SAR feature for decision tree classification, the producer accuracy (PA) and user accuracy (UA) for extracting the winter wheat are improved by 3.08% and 8.25%, respectively. The method proposed in this paper is rapid and accurate, and provide a new technical method for extracting winter wheat.

The effects of tissue proportions on blood volume change-induced variations using bio-impedance analysis: a simulation study.

Bioimpedance Analysis (BIA) along the radial artery has been widely investigated for hemodynamic monitoring. However, its applicability to different body type populations still lacks sufficient research. The Finite Element Method (FEM) was performed on three different wrist models using ANSYS HFSS, aiming to reveal the influences of different fat and muscle proportions on the sensitivity of blood volume change-induced bioimpedance change. The simulation results confirmed that the current density in each tissue mainly depended on the conductivity of tissues. The higher conductivity of the tissue, the higher current density inside said tissue. The amounts of flowing current were decided by both volume and conductivity of tissues. Moreover, increasing the fat layer thickness from 4 mm to 6 mm raised simulated impedance from 86.82 Ω to 100.39 Ω and impedance change from 0.63 Ω to 1.55 Ω. However, a higher muscle proportion occupied more injected current from the blood and resulted in lower impedance change. Therefore, for the overweight population, the placement of BIA is recommended to avoid the muscular body parts for the acquirement of better-quality pulse waves.Clinical Relevance-This establishes the bio-impedance analysis should avoid the muscular body parts for a better blood pulse wave quality for overweight populations.

The Investigation of Bio-impedance Analysis at a Wrist Phantom with Two Pulsatile Arteries.

PURPOSE: Bio-impedance analysis (BIA) has been widely investigated for hemodynamic monitoring. However, previous works rarely modelled two synchronously pulsatile arteries (representing the radial and ulnar arteries) in the wrist/forearm model. This work aims to clarify and quantify the influences of two pulsatile arteries on BIA. METHODS: First, two blood-filled arteries were structured in a 3D wrist segment using the finite element method (FEM). Afterwards, an easy-to-produce two-arteries artificial wrist was fabricated with two components: gelatine-based surrounding tissue phantom and saline blood phantom. A syringe driver was utilised to constrict the arteries, and the impedance signals were measured using a Multi-frequency Impedance Analyser (MFIA). RESULTS: Both simulation and experimental results demonstrated the non-negligible influences of the ulnar artery on the overall BIA, inducing unwanted resistance changes to the acquired signals from the radial artery. The phantom experiments revealed the summation of the individual resistance changes caused by a single pulsatile artery was approximately equal to the measured resistance change caused by two synchronously pulsatile arteries, confirming the measured impedance signal at the wrist contains the pulsatile information from both arteries. CONCLUSION: This work is the first simulation and phantom investigation into two synchronously pulsatile arteries under BIA in the distal forearm, providing a better insight and understanding in the morphology of measured impedance signals. Future research can accordingly select either a small spacing 4-spot electrode configuration for a single artery sensing or a band electrode configuration for overall pulsatile arteries sensing. A more accurate estimation of blood volume change and pulse wave analysis (PWA) could help to develop cuffless blood pressure measurement (BPM).

A Hydrogel-Based Electronic Skin for Touch Detection Using Electrical Impedance Tomography.

Recent advancement in wearable and robot-assisted healthcare technology gives rise to the demand for smart interfaces that allow more efficient human-machine interaction. In this paper, a hydrogel-based soft sensor for subtle touch detection is proposed. Adopting the working principle of a biomedical imaging technology known as electrical impedance tomography (EIT), the sensor produces images that display the electrical conductivity distribution of its sensitive region to enable touch detection. The sensor was made from a natural gelatin hydrogel whose electrical conductivity is considerably less than that of human skin. The low conductivity of the sensor enabled a touch-detection mechanism based on a novel short-circuiting approach, which resulted in the reconstructed images being predominantly affected by the electrical contact between the sensor and fingertips, rather than the conventionally used piezoresistive response of the sensing material. The experimental results indicated that the proposed sensor was promising for detecting subtle contacts without the necessity of exerting a noticeable force on the sensor.

Towards Estimating Arterial Diameter Using Bioimpedance Spectroscopy: A Computational Simulation and Tissue Phantom Analysis.

This paper improves the accuracy of quantification in the arterial diameter-dependent impedance variance by altering the electrode configuration. The finite element analysis was implemented with a 3D human wrist fragment using ANSYS Electronics Desktop, containing fat, muscle, and a blood-filled radial artery. Then, the skin layer and bones were stepwise added, helping to understand the dielectric response of multi-tissues and blood flow from 1 kHz to 1 MHz, the current distribution throughout the wrist, and the optimisation of electrode configurations for arterial pulse sensing. Moreover, a low-cost wrist phantom was fabricated, containing two components: the surrounding tissue simulant (20 wt % gelatine power and 0.017 M sodium chloride (NaCl) solution) and the blood simulant (0.08 M NaCl solution). The blood-filled artery was constricted using a desktop injection pump, and the impedance change was measured by the Multi-frequency Impedance Analyser (MFIA). The simulation revealed the promising capabilities of band electrodes to generate a more uniform current distribution than the traditional spot electrodes. Both simulation and phantom experimental results indicated that a longer spacing between current-carrying (CC) electrodes with shorter spacing between pick-up (PU) electrodes in the middle could sense a more uniform electric field, engendering a more accurate arterial diameter estimation. This work provided an improved electrode configuration for more accurate arterial diameter estimation from the numerical simulation and tissue phantom perspectives.

Neuroprotective effect of leptin on a primate model of cerebral ischemia.

The purpose of this study was to evaluate the neuroprotective effect of leptin on a non-human primate model of cerebral ischemia. A total of 39 Guangxi macaques were used to establish the primate cerebral-ischemia model. HE staining was used to evaluated the pathological changes. Moreover, magnetic resonance imaging was used for the detection of embolic area. The measurements of behavior observation and cerebral infarction area were also performed. They all received autologous thrombus operation. Furthermore, western blot and RT-PCR were also used to detect the protein and mRNA expression levels of apoptosis-related factors. Our results showed that leptin could reduce the volume of cerebral infarction by about 35%. Behavioral defects can be significantly improved. In addition, mid-term and long-term behavioral deficiencies had been significantly improved by leptin. Moreover, leptin significantly decreased the expression levels of caspase-3 and Bax, and increased the expression levels of Bcl-2. In conclusion, leptin has neuroprotective effects on cerebral ischemia by effectively reducing the volume of cerebral infarction.

A Flexible Strain Sensor Based on Embedded Ionic Liquid.

We present a simple-structured strain sensor based on a low-cost ionic liquid. The ionic liquid was made of sodium chloride/propylene glycol solution and was embedded in a linear microfluidic channel fabricated using Ecoflex. The proposed sensor is capable of measuring strain up to 100% with excellent repeatability. The highest gauge factor is obtained as 6.19 under direct current excitation and 3.40 under alternating current excitation at 1 kHz. The sensor shows negligible hysteresis and overshoot, and survived 10,000 rapid stretch-release cycles of a 100% peak strain with a minor deviation in the response signal. The sensor can be mounted to different locations on the human body and suits a variety of applications in the field of motion detection, human-machine interface and healthcare monitoring.

Multi-Person Pose Estimation Using an Orientation and Occlusion Aware Deep Learning Network.

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.