Intelligent crowd sensing pickpocketing group identification using remote sensing data for secure smart cities.

As a public infrastructure service, remote sensing data provided by smart cities will go deep into the safety field and realize the comprehensive improvement of urban management and services. However, it is challenging to detect criminal individuals with abnormal features from massive sensing data and identify groups composed of criminal individuals with similar behavioral characteristics. To address this issue, we study two research aspects: pickpocketing individual detection and pickpocketing group identification. First, we propose an IForest-FD pickpocketing individual detection algorithm. The IForest algorithm filters the abnormal individuals of each feature extracted from ticketing and geographic information data. Through the filtered results, the factorization machines (FM) and deep neural network (DNN) (FD) algorithm learns the combination relationship between low-order and high-order features to improve the accuracy of identifying pickpockets composed of factorization machines and deep neural networks. Second, we propose a community relationship strength (CRS)-Louvain pickpocketing group identification algorithm. Based on crowdsensing, we measure the similarity of temporal, spatial, social and identity features among pickpocketing individuals. We then use the weighted combination similarity as an edge weight to construct the pickpocketing association graph. Furthermore, the CRS-Louvain algorithm improves the modularity of the Louvain algorithm to overcome the limitation that small-scale communities cannot be identified. The experimental results indicate that the IForest-FD algorithm has better detection results in Precision, Recall and F1score than similar algorithms. In addition, the normalized mutual information results of the group division effect obtained by the CRS-Louvain pickpocketing group identification algorithm are better than those of other representative methods.

Contrast-enhanced ultrasonography for identifying acute kidney injury in brain-dead donors.

Background: Acute kidney injury (AKI) is frequently found in deceased donors; however, few studies have reported the use of imaging to detect and identify this phenomenon. The purpose of this study was to detect renal microcirculatory perfusion in brain-dead donors using contrast-enhanced ultrasonography (CEUS), investigate the value of CEUS in identifying AKI, and analyze the correlation between CEUS and preimplantation biopsy results and early post-transplant renal function of grafts. Methods: This prospective study recruited 94 kidneys from brain-dead donors (AKI =44, non-AKI =50) from August 2020 to November 2022. The inclusion criteria were age ≥18 years and brain death. The exclusion criteria encompassed donors maintained with extracorporeal membrane oxygenation (ECMO) and the presence of irregular kidney anatomy. The mean age of the donors was 45.1±10.4 [standard deviation (SD)] years, and the majority were male (86.2%). CEUS was performed prior to organ procurement, and time-intensity curves (TICs) were constructed. The time to peak (TTP) and peak intensity (PI) of kidney segmental artery (KA), kidney cortex (KC), and kidney medulla (KM) were calculated using TIC analysis. Results: Arrival time (AT) of KA (P<0.001) and TTP of kidney cortex (TTPKC) (P<0.001) of the non-AKI group were significantly shorter than those of the AKI group. The PI of the KA (P=0.003), KM (P=0.005), and kidney cortex (PIKC; P<0.001) of the non-AKI group were significantly higher than those of the AKI group. Multivariable logistic regression analysis showed that serum creatinine [odds ratio (OR) =1.06; 95% CI: 1.03-1.1; P<0.001], TTPKC (OR =1.38; 95% CI: 1.03-1.84; P=0.03), and PIKC (OR =0.95; 95% CI: 0.91-1; P=0.046) were the independent factors of AKI. The area under the receiver operating characteristic curve (AUC) for identifying AKI for TTPKC and PIKC was 0.73 and 0.71, respectively. TTPKC showed a weak correlation with interstitial fibrosis (r=0.23; P=0.03), PIKC showed a weak correlation with arterial intimal fibrosis ((r=-0.29; P=0.004) and arteriolar hyalinosis (r=-0.27; P=0.008), and PIKC showed the strongest correlation with eGFR on postoperative day 7 (r=-0.46; P=0.046) in the donor kidneys with AKI. Conclusions: CEUS can be used to identify AKI in brain-dead donors. Furthermore, there is a correlation between CEUS-derived parameters and pretransplant biopsy results and early preimplantation renal function of grafts.

Contrast-enhanced ultrasonography-based renal blood perfusion in brain-dead donors predicts early graft function.

PURPOSE: The aim of this study was to quantify renal microcirculatory perfusion in braindead donors using contrast-enhanced ultrasonography (CEUS), and to establish an accurate, noninvasive, and convenient index for predicting delayed graft function (DGF) post-transplantation. METHODS: In total, 90 brain-dead donor kidneys (training group, n=60; validation group, n=30) examined between August 2020 and November 2022 were recruited in this prospective study. CEUS was performed on the kidneys of brain-dead donors 24 hours before organ procurement and time-intensity curves were constructed. The main measures were arrival time, time to peak, and peak intensity of the kidney segmental arteries, cortex, and medulla. Recipients were divided into DGF and non-DGF groups according to early post-transplant graft function. The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. RESULTS: The arrival time of the kidney segmental artery and cortex and the time interval between the time to peak of the segmental artery and cortex were identified as independent factors associated with DGF by multivariate stepwise regression analysis. A new index for the joint prediction model of three variables, the contrast-enhanced ultrasonography/Kidney Donor Profile index (CEUS-KDPI), was developed. CEUS-KDPI showed high accuracy for predicting DGF (training group: AUC, 0.91; sensitivity, 90.5%; specificity, 92.3%; validation group: AUC, 0.84; sensitivity, 75.0%; specificity, 92.3%). CONCLUSION: CEUS-KDPI accurately predicted DGF after kidney transplantation. CEUS may be a potential noninvasive tool for bedside examinations before organ procurement and may be used to predict early renal function after kidney transplants kidneys from donors after brain death.

Research on user recruitment algorithms based on user trajectory prediction with sparse mobile crowd sensing.

Sparse mobile crowd sensing saves perception cost by recruiting a small number of users to perceive data from a small number of sub-regions, and then inferring data from the remaining sub-regions. The data collected by different people on their respective trajectories have different values, and we can select participants who can collect high-value data based on their trajectory predictions. In this paper, we study two aspects of user trajectory prediction and user recruitment. First, we propose an STGCN-GRU user trajectory prediction algorithm, which uses the STGCN algorithm to extract features related to temporal and spatial information from the trajectory map, and then inputs the feature sequences into GRU for trajectory prediction, and this algorithm improves the accuracy of user trajectory prediction. Second, an ADQN (action DQN) user recruitment algorithm is proposed.The ADQN algorithm improves the objective function in DQN on the idea of reinforcement learning. The action with the maximum input value is found from the Q network, and then the output value of the objective function of the corresponding action Q network is found. This reduces the overestimation problem that occurs in Q networks and improves the accuracy of user recruitment. The experimental results show that the evaluation metrics FDE and ADE of the STGCN-GRU algorithm proposed in this paper are better than other representative algorithms. And the experiments on two real datasets verify the effectiveness of the ADQN user selection algorithm, which can effectively improve the accuracy of data inference under budget constraints.

Research on rainy day traffic sign recognition algorithm based on PMRNet.

The recognition of traffic signs is of great significance to intelligent driving and traffic systems. Most current traffic sign recognition algorithms do not consider the impact of rainy weather. The rain marks will obscure the recognition target in the image, which will lead to the performance degradation of the algorithm, a problem that has yet to be solved. In order to improve the accuracy of traffic sign recognition in rainy weather, we propose a rainy traffic sign recognition algorithm. The algorithm in this paper includes two modules. First, we propose an image deraining algorithm based on the Progressive multi-scale residual network (PMRNet), which uses a multi-scale residual structure to extract features of different scales, so as to improve the utilization rate of the algorithm for information, combined with the Convolutional long-short term memory (ConvLSTM) network to enhance the algorithm's ability to extract rain mark features. Second, we use the CoT-YOLOv5 algorithm to recognize traffic signs on the recovered images. In this paper, in order to improve the performance of YOLOv5 (You-Only-Look-Once, YOLO), the 3 × 3 convolution in the feature extraction module is replaced by the Contextual Transformer (CoT) module to make up for the lack of global modeling capability of Convolutional Neural Network (CNN), thus improving the recognition accuracy. The experimental results show that the deraining algorithm based on PMRNet can effectively remove rain marks, and the evaluation indicators Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) are better than the other representative algorithms. The mean Average Precision (mAP) of the CoT-YOLOv5 algorithm on the TT100k datasets reaches 92.1%, which is 5% higher than the original YOLOv5.

Preoperative evaluation and influencing factors of sentinel lymph node detection for early breast cancer with contrast-enhanced ultrasonography: What matters.

ABSTRACT: Sentinel lymph node (SLN) is important in the early diagnosis of breast cancer. We aimed to evaluate the role of contrast-enhanced ultrasonography (CEUS) in the preoperative evaluation for SLN and potentially influencing factors, to provide evidence to the management of breast cancer.Patients with breast cancer who treated in our hospital from May 2018 to May 2020 were selected. All patients underwent CEUS examination to find SLN and judged whether the lymph node had cancer metastasis. We evaluated the sensitivity, specificity, and accuracy of CEUS in predicting SLN, and its differences in pathological diagnosis results and related influencing factors were also analyzed.A total of 108 patients with breast cancer were included. And a total of 248 SLNs were detected. The sensitivity of CEUS to the preoperative evaluation of SLN was 84.67%, the specificity was 81.14%, the positive predictive value was 76.08%, and the negative predictive value was 89.27%, the positive likelihood ratio was 4.06, and the negative likelihood ratio was 0.14. The area under the curve of the preoperative evaluation of SLN in CEUS examination was 0.813 (95% confidence interval: 0.765-0.911), and there was significant difference in the size of SLNs between SLN-negative and SLN-positive groups (P = .043).Preoperative CEUS has good predictive value for the SLN detection in patients with breast cancer, and it is worthy of clinical application.

[Bi-level positive airway pressure ventilation for post-extubation respiratory support under deep anesthesia in hypertension patients].

OBJECTIVE: To evaluate the effect of bi-level positive airway pressure ventilation (BiPAP) for post-extubation respiratory support under deep anesthesia in hypertension patients. METHODS: Forty primary hypertension patients who were scheduled for lower abdominal surgery or total hip joint replacement were randomly divided into 2 groups: one was extubated when being awake (Group A, n = 20, and the other was extubated under deep anesthesia (Group B, n = 20). The combined inhalation and the intravenous general anesthesia were performed on all patients, and inhalation anesthesia was maintained with only continued infusion of propofol when major procedure of surgery had been finished. In Group A, anesthesia was ceased when the surgery was finished, and trachea was removed after the patients awoke. In Group B, anesthesia was ceased immediately before the extubation, and trachea was removed under deep anesthesia, followed by an uninvasive ventilation of BiPAP. Blood pressure (BP, heart rate ( HR, and bispectral index (BIS) before or after the extubation, artery blood-gass analysis in BIPAP, and the incidence rate of complication in the recovery period were recorded. RESULTS: In Group A, BP and HR increased significantly after the patients awoke (P < 0.01) and after the extubation (P < 0.05), compared with the data before the surgery and before the extubation. In Group B, however, BP and HR had no difference before and after the extubation, and the data of blood gas maintained approximately normal. The incidence rate of glos- soptosis in Group B was obviously higher than those in Group A (P < 0.01), while complications such as cough during the recovery stage in Group A were more than those in Group B (P <0.05). CONCLUSION: BiPAP is suitable for post-extubation respiratory support under deep anesthesia in hypertension patients.

[Effects of desflurane on auditory evoked potential index and quantitative electroencephalogram].

OBJECTIVE: To observe the effects of desflurane on A-line ARX Index (AAI), QEEG, MAP and HR, and to investigate the feasibility of AAI, QEEG, MAP and HR in monitoring the depth of anesthesia with desflurane. METHODS: Thirty patients classified as ASA physical status I approximately II were scheduled for elective lower abdominal surgery. Anesthesia was induced with propofol and vecuronum. After the tracheal intubation, the lungs were ventilated with desflurane in oxygen. End-tidal desflurane concentrations were maintained at 0.8, 1.0 and 1.3 MAC for 20 minutes, respectively. The parameters of record included AAI, BIS (bispectral index), SEF (95% spectral edge freqency), MF (midian freqency), MAP and HR. RESULTS: AAI, BIS, SEF and MF significantly decreased in a linear manner (r = 0.830, 0.930, 0.803, and 0.885, respectively, P < 0.01) with increasing end-tidal concentration of desflurane range of 0.8 approximately 1.3 MAC. MAP and HR did not change much. HR increased significantly at concentration 1.3 MAC than that of 1.0 MAC. CONCLUSION: Within end-tidal desflurane concentration range 0.8 approximately 1.3 MAC, both AAI and parameters derived from EEG (such as BIS, SEF, MF) can serve as parameters in monitoring the depth of anesthsia with desflurane, while MAP and HR can not.