Search

Accurate prediction of NOx emissions under actual working conditions is crucial for managing regional pollutant emissions. Therefore, this study focuses on agricultural tractors and employs a Portable Emission Measurement System (PEMS) to gather NOx emission under real operating conditions. By conducting correlation analyses of factors affecting NOx emissions, the main factors affecting NOx emissions during the actual working conditions of tractors were determined, and the NOx emission prediction model was established by applying these factors. In the process of establishing a NOx emission prediction model for agricultural tractors, the research utilizes the Back Propagation (BP) neural network, and the Long Short-Term Memory (LSTM) neural network, and optimizes both the BP and LSTM neural networks using Genetic Algorithm (GA) for comparison and evaluation of their prediction performance. The results demonstrate that among the established models, the optimized GA-BP neural network model excels in predicting NOx emissions. This model outperforms other neural network models in various evaluation metrics, including Root Mean Square Error(RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²), with values of 5.679 x 10-3, 4.057 x 10-3, 3.751% and 0.991 5, respectively. Therefore, it is feasible to use the GA-BP neural network model to predict NOx emissions from agricultural tractors. [ABSTRACT FROM AUTHOR]

Background18F-Flutemetamol (18F-FMM) PET/CT imaging has been widely applied to the diagnosis of mild cognitive impairment and Alzheimer's disease.PurposeThis study aims to explore the distributions of 18F-FMM in different brain regions of mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients and the factors that may affect the combination of 18F-FMM, evaluating the use of 18F-FMM PET/CT imaging in the diagnosis of MCI and AD patients.MethodsFrom July 2020 to April 2021, 24 subjects with MCI (12 males, 12 females, aged of (70.54±9.27) years old), 25 subjects with AD (11 males, 14 females, aged (70.56±7.30) years old) and 9 subjects as normal controls (NC, 2 males, 7 females, aged (57.67±9.00) years old) were recruited from Shanghai. The 18F-FMM PET/CT brain imaging of all subjects were qualitatively and semi-quantitatively analyzed by visual evaluation and standardized uptake value ratio (SUVR), respectively. Student's t-test, one-way analysis of variance and rank sum test were used for the comparison of quantitative variables. Pearson's chi-squared test and Fisher's exact test were used for the comparison of qualitative variables. The diagnostic efficiency was obtained by ROC curve. Multiple linear regression analysis was used to analyze the factors that might affect the combination of 18F-FMM.ResultsThe positive rate of visual assessment was significantly different in NC, MCI and AD groups (χ2=26.85, p < 0.001), and significant differences existed statistically in SUVR of all brain regions among the three groups (H value: 11.54~19.34, F value: 7.43, 11.48, all p < 0.01). The mean values of SUVR in the whole brain of the three groups were statistically different (Z value: -3.87, -2.79, -2.45, all p < 0.016 7). Compared with MCI group, the positive rate in occipital lobe, temporal lobe, parietal lobe and posterior cingulate gyrus was statistically significant (χ2=7.53~10.89, all p < 0.01). With respect to NC, SUVR of all brain regions was lower than that in AD, while SUVR of temporal lobe, frontal lobe and precuneu were lower than that in MCI. Meanwhile, SUVR of occipital lobe, temporal lobe, frontal lobe and parietal lobe in MCI were lower than that in AD. Receiver operating characteristic (ROC) curves showed that the SUVR value of temporal lobe and the mean value of SUVR in the whole brain had the ability to distinguish NC, MCI and AD in sequence. Multiple linear regression analysis showed that cognitive level was significantly negatively correlated with 18F-FMM SUVR in different brain regions.Conclusion18F-FMM PET/CT brain imaging could reflect the cognitive level of middle-aged and elderly people intuitively and has clear diagnostic value for MCI and AD.

BackgroundSubjective cognitive decline (SCD) and mild cognitive impairment (MCI) are a transitional state between normal aging and mild dementia, and most of them have potential Alzheimer's Disease (AD) pathology. Studying the pathophysiological characteristics of SCD and MCI is helpful to the early diagnosis of AD.PurposeThis study aims to investigate the brain perfusion differences among SCD, MCI and AD, and to evaluate the application value of brain perfusion SPECT/CT imaging combined with NeuroGamTM software in these diseases.MethodsFrom July 2020 to April 2021, 15 patients with SCD, 29 patients with MCI and 36 patients with AD were collected from several general hospitals in Shanghai. All subjects underwent neuropsychological test and 99mTc-ECD brain perfusion SPECT/CT imaging. The perfusion levels of Brodmann areas (BA) in the three groups were semi-quantitatively analyzed by NeuroGamTM, and compared with normal database. Student's t-test, one-way analysis of variance and rank sum test were used for the comparison of quantitative variables. Pearson's chi-squared test was used for the comparison of qualitative variables.ResultsThere is no significant difference in BA 4~11, 17~25, 28, 31~32, 36~40 and 44~47 between SCD group and MCI group. The mean perfusion values of BA 8-right(R), 20-left(L), 21R, 23L, 23R, 24L, 31L, 38L, 38R and 45R in SCD group are significantly higher than those in AD group (p

Objective: To compare the predictive value of anatomic scoring system, physiological scoring system, and the combination of two systems in death prediction of patients with severe trauma in intensive care unit (ICU)., Methods: A retrospective analysis of patients with severe trauma admitted to department of critical care medicine of Daping Hospital, the Third Military Medical University, and Zunyi Medical University from January 2011 to December 2014 was conducted. The patients meeting the following criteria were enrolled: over 16 years old, admitted to hospital shorter than 24 hours after trauma, length of ICU stay ≥ 48 hours, and injury severity score ( ISS ) ≥ 16. Patients were divided into two groups: survivors and non-survivors. The data of anatomic scoring system, including ISS and new injury severity score (NISS), and physiological scoring system, including acute physiology and chronic health evaluation II (APACHEII) score were collected. The predictive power for death of the scoring system alone or combination in patients with severe trauma was evaluated., Results: A total of 614 patients with severe trauma were enrolled, and there were 153 deaths with a mortality rate of 24.9%. ISS, NISS, APACHEII, ISS + APACHEII, NISS + APACHEII of non-survivors were significantly higher than those of survivors (ISS: 29.15 ± 7.75 vs. 24.31 ± 6.50, NISS: 41.96±12.01 vs. 29.64 ± 8.19, APACHEII: 23.71 ± 6.58 vs. 17.02 ± 5.49, ISS + APACHEII: 52.86 ± 10.00 vs. 41.33 ± 8.70, NISS + APACHEII: 65.67 ± 13.46 vs. 46.66 ± 10.43, all P < 0.01). The area under receiver operating characteristic curve (AUC) of ISS, NISS, APACHEII, ISS + APACHEII, NISS + APACHEII was 0.687, 0.792, 0.782, 0.809, and 0.860, respectively. Both of ISS + APACHEII and NISS + APACHEII had higher AUC than that of ISS, NISS or APACHEII alone; and the AUC of NISS + APACHEII was significantly larger than that of ISS + APACHEII (all P < 0.05). NISS + APACHEII showed the largest AUC in death prediction of severe trauma patients. The cut-off value, sensitivity, specificity, positive predict value (+PV), negative predict value (-PV), positive likelihood ratio (+LR), negative likelihood ratio (-LR), and Youden index of NISS + APACHEII, which had the greatest AUC, were 56, 75.2%, 82.0%, 58.1%, 90.9%, 4.17, 0.30, and 0.572, respectively., Conclusions: The combination of anatomic scoring system and physiological scoring system is better than single scoring system for death prediction in patients with severe trauma in ICU, and it may be considered to be a new method for early identification of death risk in patients with severe trauma.