Leaf Classification for Crop Pests and Diseases in the Compressed Domain.

Crop pests and diseases have been the main cause of reduced food production and have seriously affected food security. Therefore, it is very urgent and important to solve the pest problem efficiently and accurately. While traditional neural networks require complete processing of data when processing data, by compressed sensing, only one part of the data needs to be processed, which greatly reduces the amount of data processed by the network. In this paper, a combination of compressed perception and neural networks is used to classify and identify pest images in the compressed domain. A network model for compressed sampling and classification, CSBNet, is proposed to enable compression in neural networks instead of the sensing matrix in conventional compressed sensing (CS). Unlike traditional compressed perception, no reduction is performed to reconstruct the image, but recognition is performed directly in the compressed region, while an attention mechanism is added to enhance feature strength. The experiments in this paper were conducted on different datasets with various sampling rates separately, and our model was substantially less accurate than the other models in terms of trainable parameters, reaching a maximum accuracy of 96.32%, which is higher than the 93.01%, 83.58%, and 87.75% of the other models at a sampling rate of 0.7.

Clinical features and mortality-related factors of extensive burns among young adults: the Kunshan disaster experience.

BACKGROUND: The aim of the study was to identify the clinical features and the factors associated with burn induced mortality among young adults after exposure to indoor explosion and fire. METHODS: This is an observational study which included burn patients who were admitted to eighteen ICUs after a fire disaster. Epidemiologic and clinical characteristics, as well as therapy were recorded. The primary outcome was 90-day mortality. The mortality-related factors were also analyzed. RESULTS: There were 167 burn patients enrolled in the study, the median age was 38 years, 62 (37.1%) patients died within 90 days. Seventy-one percent of patients had a burn size ≥90% TBSA, and 73.7% of patients had a full-thickness burn area above 50% TBSA. The survivors had lower Baux scores, and received earlier escharectomy and autologous skin grafts. The 50% mortality rates (LA50s) for burn size and full-thickness burn area were 95.8% and 88.6% TBSA, respectively. The multivariate analysis showed that full-thickness burn area over 50% TBSA and residual burned surface area (RBSA)/TBSA at 28 days were strong predictors of mortality among burn patients (odds ratio 2.55; 95% CI, 1.01 to 6.44, P=0.047; odds ratio 1.07; 95% CI, 1.04 to 1.09, P<0.001). The ROC curve-based cut-off values of RBSA/TBSA at 28 days for predicting 90-day mortality were 62.5%. CONCLUSIONS: Burn size and full-thickness burn area were the main risk factors for poor outcome in patients with extensive burns. Earlier escharectomy and autologous skin grafts may improve outcomes.

[The expression of coxsackie B virus adenovirus receptor (CAR) in viral myocarditis and dilated cardiomyopathy patients].

OBJECTIVE: To explore etiology and pathogenesis of viral myocarditis (VMC) and dilated cardiomyopathy (DCM). METHODS: The expression of Coxsackie B virus and adenovirus receptors (CAR) were detected with modified immunohistochemical (IHC) technique in myocardium of left ventricle, right ventricle, interventricular septum, and septal papillary muscle from 28 patients with viral myocarditis, 31 patients with dilated cardiomyopathy and 17 control patients (including normal, hypertension heart disease, myocardial infarction and coronary atherosclerotic heart disease). RESULTS: The brown staining on the cell membrane of myocardium represents positive result. 100% (28 of 28) of VMC patients (IHC surface integral: 4.3975 +/- 0.0365) and 84% (26 of 31) of DCM patients (4.2064 +/- 0.052 6) had prevalent CAR expression compared to 0% (0 of 19) control patients (0.073 1 +/- 0.0362). There were statistically significant differences between VMC/DCM and control patients (P < 0.05). CONCLUSION: The prevalence of CAR expression was significantly higher in VMC and DCM patients (100% and 84% vs. 0% in control). In contrast, there was no difference found between VMC and DCM patients. These results suggest that both VMC and DCM involve viral etiology and could share a similar pathogenesis.

[The effects of somatostatin on serum interleukin-6 and tumor necrosis factor-alpha in lipopolysaccharide-induced septic shock: experiment with rats].

OBJECTIVE: To explore the effect of somatostatin on serum interleukin (IL)-6 and tumor necrosis factor (TNF)-alpha in lipopolysaccharide (LPS)-induced septic shock. METHODS: 24 male Wistar rats were randomly divided into 2 groups: intervention group (injected with LPS of Escherichia coli via femoral vein to induce septic shock) and control group (injected with LPS of Escherichia coli and then injected with somatostatin). The mean arterial pressure (MAP), heart rate, respiration rater, and mortality rate were observed before the injection of LPS, and 30, 90, and 360 min after the injection, and the serum IL-6 and TNF-alpha level were detected before the injection of LPS, 30, 90, and 360 min after the injection, or after the death. RESULTS: The IL-6 levels 30 min, 90 min, and 360 min after the injection of the somatostatin intervention group were 233 +/- 47, 212 +/- 33, and 217 +/- 26 mg/L respectively, all significantly lower then those of the control group (308 +/- 56, 260 +/- 32, and 230 +/- 92 mg/L, all P < 0.05). The TNF-alpha level 30 min, 90 min, and 360 min after the injection of the somatostatin intervention group were 450 +/- 82, 417 +/- 92, and 440 +/- 49 mg/L, all significantly lower than those of the control group (607 +/- 149, 517 +/- 74, and 474 +/- 219 mg/L, all P < 0.05). In addition, compared with the control group, the MAP of the somatostatin intervention group increased after 90 min. Two rats in the control group died 30 to 90 min later and 4 rats died 90 to 360 min later, however, 360 min later all rats in the somatostatin intervention group were alive (P = 0.0054). CONCLUSION: Somatostatin can inhibit the level of serum IL-6 and TNF-alpha in septic shock induced by LPS and improve the survival rate.