Screening of natural drug molecules against Fusarium oxysporum of ginseng root rot based on machine learning / 药学学报

italic>Fusarium oxysporum widely exists in farmland soil and is one of the main pathogenic fungi of root rot, which seriously affects the growth and development of plants and often causes serious losses of cash crops. In order to screen out natural compounds that inhibit the activity of Fusarium oxysporum more economically and efficiently, random forest, support vector machine and artificial neural network based on machine learning algorithms were constructed using the information of known inhibitory compounds in ChEMBL database in this study. And the antibacterial activity of the screened drugs was verified thereafter. The results showed that the prediction accuracy of the three models reached 77.58%, 83.03% and 81.21%, respectively. Based on the inhibition experiment, the best inhibition effect (MIC = 0.312 5 mg·mL-1) of ononin was verified. The virtual screening method proposed in this study provides ideas for the development and creation of new pesticides derived from natural products, and the screened ononin is expected to be a potential lead compound for the development of novel inhibitors of Fusarium oxysporum.

Prediction of concentration immediately dangerous to life or health of benzene and its derivatives based on quantitative structure-activity relationship / 环境与职业医学

Background With the increasing exposure to hazardous chemicals in the workplace and frequency of occupational injuries and occupational safety accidents, the acquisition of occupational exposure limits of hazardous chemicals is imminent. Objective To obtain more unknown immediately dangerous to life or health (IDLH) concentrations of hazardous chemicals in the workplace by exploring the application of quantitative structure-activity relationship (QSAR) prediction method to IDLH concentrations, and to provide a theoretical basis and technical support for the assessment and prevention of occupational injuries. Methods QSAR was used to correlate the IDLH values of 50 benzene and its derivatives with the molecular structures of target compounds. Firstly, affinity propagation algorithm was applied to cluster sample sets. Secondly, Dragon 2.1 software was used to calculate and pre-screen 537 molecular descriptors. Thirdly, the genetic algorithm was used to select six characteristic molecular descriptors as dependent variables and to construct a multiple linear regression model (MLR) and two nonlinear models using support vector machine (SVM) and artificial neural network (ANN) respectively. Finally, model performance was evaluated by internal and external validation and Williams diagram was drawn to determine the scopes of selected models. Results The ANN model results showed that \begin{document}$ {R}_{\mathrm{t}\mathrm{r}\mathrm{a}\mathrm{i}\mathrm{n}}

Application of artificial neural network algorithm in pathological diagnosis and prognosis prediction of digestive tract malignant tumors / 浙江大学学报·医学版

The application of artificial neural network algorithm in pathological diagnosis of gastrointestinal malignant tumors has become a research hotspot. In the previous studies, the algorithm research mainly focused on the model development based on convolutional neural networks, while only a few studies used the combination of convolutional neural networks and recurrent neural networks. The research contents included classical histopathological diagnosis and molecular typing of malignant tumors, and the prediction of patient prognosis by utilizing artificial neural networks. This article reviews the research progress on artificial neural network algorithm in the pathological diagnosis and prognosis prediction of digestive tract malignant tumors.

Outcome prediction for critical care patients with respiratory neoplasms using a multilayer perceptron neural network

ABSTRACT Objective: The variation in mortality rates of intensive care unit oncological patients may imply that clinical characteristics and prognoses are very different between specific subsets of patients with cancer. The specific characteristics of patients with cancer have not been included as risk factors in the established severity-of-illness scoring systems and comorbidity scores, showing limitations in predicting mortality risk. This study aimed to devise a predictive tool for in-hospital mortality for adult patients with a respiratory neoplasm admitted to the intensive care unit, using an artificial neural network. Methods: A total of 1,221 stays in the intensive care unit from the Beth Israel Deaconess Medical Center were studied. The primary endpoint was the all-cause in-hospital mortality prediction. An artificial neural network was developed and compared with six severity-of-illness scores and one comorbidity score. Model building was based on important predictors of lung cancer mortality, such as several laboratory parameters, demographic parameters, organ-supporting treatments, and other clinical information. Discrimination and calibration were assessed. Results: The AUROC for the multilayer perceptron was 0.885, while it was <0.74 for the conventional systems. The AUPRC for the multilayer perceptron was 0.731, whereas it was ≤0.482 for the conventional systems. The superiority of multilayer perceptron was statistically significant for all pairwise AUROC and AUPRC comparisons. The Brier Score was better for the multilayer perceptron (0.109) than for OASIS (0.148), SAPS III (0.163), and SAPS II (0.154). Conclusion: Discrimination was excellent for multilayer perceptron, which may be a valuable tool for assessing critically ill patients with lung cancer.

Optimization of Escherichia coli shake flask culture medium by artificial neural network / 中国生物制品学杂志

@#Objective To optimize a shake flask culture medium for Escherichia coli(E.coli)with high biomass and viability using artificial neural networks(ANN). Methods Using the proportion of glucose(Glu),yeast extract(YE),yeast peptone(YP),soy peptone(SP)and yeast nitrogen base(YNB)as the mixture component,and the A_(600)(A1)value of cell suspension,wet bacterial weight(G,g/L)of culture and cell viability(A2,A_(460))as the response values,the mixture design was used to screen the mixture components that had a significant effect on the response value. The ANN model was constructed with the test results of mixture design as training and verification data samples. The input variables were mixture components and restricted the upper and lower limits of the mixture components,and the output variables were mixture design response values. The optimized medium formula and reference values were obtained by the constructed ANN. The medium formula was further adjusted by Monte Carlo simulation to obtain the shake flask medium formula of E.coli,which was then verified for 10 times. Results The shake flask culture medium of E.coli was composed of Glu 26 g/L,SP 26 g/L,YNB13 g/L with the total concentration of 65 g/L. The verification results showed that the probability of A1 ≥ 14 was 60%,the probability of G ≥ 77 g/L was 50% and the probability of A2 ≥ 11 was 40%. The mean values of the incubation result data were equivalent to the reference values. Conclusion The shake flask culture medium of E.coli optimized in this study can obtain E.coli with high biomass and bacterial activity.

Progress on application of artificial intelligence technology in orthodontic diagnosis and treatment / 口腔疾病防治

@#In recent years, artificial intelligence technology has developed rapidly and has been gradually applied to the fields of clinical image data processing, auxiliary diagnosis and prognosis evaluation. Research has shown that it can simplify doctors’ clinical tasks, quickly provide analysis and processing results, and has high accuracy. In terms of orthodontic diagnosis and treatment, artificial intelligence can assist in the rapid fixation of two-dimensional and three-dimensional cephalometric measurements. In addition, it is also widely used in the efficient processing and analysis of three-dimensional dental molds data, and shows considerable advantages in determining deciding whether orthodontic treatment needs tooth extraction, thus assisting in judging the stage of growth and development, orthodontic prognosis and aesthetic evaluation. Although the application of artificial intelligence technology is limited by the quantity and quality of training data, combining it with orthodontic clinical diagnosis and treatment can provide faster and more effective analysis and diagnosis and support more accurate diagnosis and treatment decisions. This paper reviews the current application of artificial intelligence technology in orthodontic diagnosis and treatment in the hope that orthodontists can rationally treat and use artificial intelligence technology in the clinic, and make artificial intelligence better serve orthodontic clinical diagnosis and treatment, so as to promote the further development of intelligent orthodontic diagnosis and treatment processes.

Research advance and challenges of the application of machine learning in laboratory medicine / 中华检验医学杂志

The application of machine learning has become an important direction for the development of intelligent laboratory medicine. Recently, the rapid development of open-source software and publicly available data sources made the application of machine learning highly accessible. It reduced the requirement for developers to have necessary matter knowledge and also facilitated a surge in interest and publications. However, the practicality and reproducibility of machine learning models still remain unclear. In the face of these challenges, some countermeasures were proposed, including strict control of data quality, improvemrnt of model applicability, establishment of model selction and validation strategies, enhancement of model interpretability and reproducibility. Machine learning helps to break through the bottleneck of clinical translation of laboratory big data and improve the quality of diagnostic services in the laboratory medicine.

Establishing prediction model of community-acquired pneumonia complicated with acute respiratory distress syndrome based on artificial neural network / 中华危重病急救医学

Objective:To investigate the independent risk factors of community-acquired pneumonia (CAP) complicated with acute respiratory distress syndrome (ARDS), and the accuracy and prevention value of ARDS prediction based on artificial neural network model in CAP patients.Methods:A case-control study was conducted. Clinical data of 414 patients with CAP who met the inclusion criteria and were admitted to the comprehensive intensive care unit and respiratory department of Changzhou Second People's Hospital Affiliated to Nanjing Medical University from February 2020 to February 2021 were analyzed. They were divided into two groups according to whether they had complicated with ARDS. The clinical data of the two groups were collected within 24 hours after admission, the influencing factors of ARDS were screened out by univariate analysis, and the artificial neural network model was constructed. Through the artificial neural network model, the importance of input layer independent variables (that was, the influence factors obtained from univariate analysis) on the output layer dependent variables (whether ARDS occurred) was drawn. The artificial neural network modeling data pairs were randomly divided into training group ( n = 290) and verification group ( n = 124) in a ratio of 7∶3. The overall prediction accuracy of the training group and the verification group was calculated respectively. At the same time, the receiver operator characteristic curve (ROC curve) was drawn, and the area under the ROC curve (AUC) was calculated. Results:All 414 patients were enrolled in the analysis, including 82 patients with ARDS and 332 patients without ARDS. Univariate analysis showed that gender, age, heart rate (HR), maximum systolic blood pressure (MSBP), maximum respiratory rate (MRR), source of admission, C-reactive protein (CRP), procalcitonin (PCT), erythrocyte sedimentation rate (ESR), neutrophil count (NEUT), eosinophil count (EOS), fibrinogen equivalent unit (FEU), activated partial thromboplastin time (APTT), total bilirubin (TBil), albumin (ALB), lactate dehydrogenase (LDH), serum creatinine (SCr), hemoglobin (Hb) and blood glucose (GLU) were significantly different between the two groups, which might be the risk factors of CAP patients complicated with ARDS. Taking the above 19 risk factors as the input layer and whether ARDS occurred as the output layer, the artificial neural network model was constructed. Among the input layer independent variables, the top five indicators with the largest influence weight on the neural network model were LDH (100.0%), PCT (74.4%), FEU (61.5%), MRR (56.9%), and APTT (51.6%), indicating that that these five indicators had a greater impact on the occurrence of ARDS in patients with CAP. The overall prediction accuracy of the artificial neural network model in the training group was 94.1% (273/290), and that of the verification group was 89.5% (111/124). The AUC predicted by the aforementioned artificial neural network model for ARDS in CAP patients was 0.977 (95% confidence interval was 0.956-1.000).Conclusion:The prediction model of ARDS in CAP patients based on artificial neural network model has good prediction ability, which can be used to calculate the accuracy of ARDS in CAP patients, and specific preventive measures can be given.

Establishment of artificial neural network model for predicting lymph node metastasis in patients with stage Ⅱ-Ⅲ gastric cancer / 中华胃肠外科杂志

Objective: To establish a neural network model for predicting lymph node metastasis in patients with stage II-III gastric cancer. Methods: Case inclusion criteria: (1) gastric adenocarcinoma diagnosed by pathology as stage II-III (the 8th edition of AJCC staging); (2) no distant metastasis of liver, lung and abdominal cavity in preoperative chest film, abdominal ultrasound and upper abdominal CT; (3) undergoing R0 resection. Case exclusion criteria: (1) receiving preoperative neoadjuvant chemotherapy or radiotherapy; (2) incomplete clinical data; (3) gastric stump cancer.Clinicopathological data of 1231 patients with stage II-III gastric cancer who underwent radical surgery at the Fujian Medical University Union Hospital from January 2010 to August 2014 were retrospectively analyzed. A total of 1035 patients with lymph node metastasis were confirmed after operation, and 196 patients had no lymph node metastasis. According to the postoperative pathologic staging. 416 patients (33.8%) were stage Ⅱ and 815 patients (66.2%) were stage III. Patients were randomly divided into training group (861/1231, 69.9%) and validation group (370/1231, 30.1%) to establish an artificial neural network model (N+-ANN) for the prediction of lymph node metastasis. Firstly, the Logistic univariate analysis method was used to retrospectively analyze the case samples of the training group, screen the variables affecting lymph node metastasis, determine the variable items of the input point of the artificial neural network, and then the multi-layer perceptron (MLP) to train N+-ANN. The input layer of N+-ANN was composed of the variables screened by Logistic univariate analysis. Artificial intelligence analyzed the status of lymph node metastasis according to the input data and compared it with the real value. The accuracy of the model was evaluated by drawing the receiver operating characteristic (ROC) curve and obtaining the area under the curve (AUC). The ability of N+-ANN was evaluated by sensitivity, specificity, positive predictive values, negative predictive values, and AUC values. Results: There were no significant differences in baseline data between the training group and validation group (all P>0.05). Univariate analysis of the training group showed that preoperative platelet to lymphocyte ratio (PLR), preoperative systemic immune inflammation index (SII), tumor size, clinical N (cN) stage were closely related to postoperative lymph node metastasis. The N+-ANN was constructed based on the above variables as the input layer variables. In the training group, the accuracy of N+-ANN for predicting postoperative lymph node metastasis was 88.4% (761/861), the sensitivity was 98.9% (717/725), the specificity was 32.4% (44/136), the positive predictive value was 88.6% (717/809), the negative predictive value was 84.6% (44/52), and the AUC value was 0.748 (95%CI: 0.717-0.776). In the validation group, N+-ANN had a prediction accuracy of 88.4% (327/370) with a sensitivity of 99.7% (309/310), specificity of 30.0% (18/60), positive predictive value of 88.0% (309/351), negative predictive value of 94.7% (18/19), and an AUC of 0.717 (95%CI:0.668-0.763). According to the individualized lymph node metastasis probability output by N+-ANN, the cut-off values of 0-50%, >50%-75%, >75%-90% and >90%-100% were applied and patients were divided into N0 group, N1 group, N2 group and N3 group. The overall prediction accuracy of N+-ANN for pN staging in the training group and the validation group was 53.7% and 54.1% respectively, while the overall prediction accuracy of cN staging for pN staging in the training group and the validation group was 30.1% and 33.2% respectively, indicating that N+-ANN had a better prediction than cN stage. Conclusions: The N+-ANN constructed in this study can accurately predict postoperative lymph node metastasis in patients with stage Ⅱ-Ⅲ gastric cancer. The N+-ANN based on individualized lymph node metastasis probability has better accurate prediction for pN staging as compared to cN staging.

Cómo clasificar llanto del recién nacido mediante una red neuronal supervisada / How to classify newborn cry through a supervised neural network

El llanto es una vía de comunicación del recién nacido con el medio circundante. Investigaciones acerca del llanto infantil han correlacionado características acústicas de éste con patologías, demostrándose que el llanto puede reflejar la integridad neurofisiológica del niño y dar una medida de su interacción con el ambiente y su desarrollo cognitivo y social. Esta contribución muestra cómo clasificar el llanto de neonatos con hipoxia y de un grupo de control, en normal o patológico, a través de una red neuronal artificial supervisada. Para implementar la red neuronal se aprovechan las posibilidades de la plataforma MATLAB®. El diseño y estructuración de la red considera algoritmo de aprendizaje o entrenamiento, iteraciones, pruebas e intervalos de clasificación, obteniéndose arquitectura y topología, y funcionalidades de la red neuronal que en la generalización proporciona la mejor clasificación. En el trabajo se aplica el método de selección de casos, el método acústico para extraer parámetros cuantitativos de la señal de llanto en tiempo, intensidad y frecuencia, así como métodos vinculados con el diseño, implementación y validación, con pruebas diagnósticas, de la red neuronal artificial obtenida para cumplir el objetivo del trabajo que es la generación de clases (clasificación del llanto). Con precisión del resultado de clasificación del 90 por ciento se está en condición de concebir una solución informática (agregando interfaz para interactuar con base de datos) para ayudar complementariamente al diagnóstico médico no invasivo usando el llanto del neonato provocado ante dolor(AU)

Cry from newborn (0-28 days) is a way of communication for the interaction with surrounding world. Infant cry researches provide information that correlate among cries acoustic features with pathologies. It has been demonstrated that the infant cry is able to reflect child neurophysiology integrity and give meaning from newborn interaction with environment, also cognitive and social development from child. This contribution shows how to classify the cry of neonates with hypoxia and of a control group, into normal or pathological, through a supervised artificial neural network. Network implementation makes use of MATLAB® platform possibilities. Design and structuring of network take into consideration aspects as training algorithm, iterations, tests and classification intervals. All these referred aspects give as result an architectural, topology and functionalities from neural network able to classify cry in generalization stage offering good outcome. Different methods are applied in this paper as selection of cases, acoustic methods in order to obtain quantitative parameters from cry signals (in time, intensity and frequency domain). Methods related with design, implementation and validation (diagnostic test) of an artificial neural network able to carry out the goal of this paper (classification of cry) are used. With accuracy results in cry classification about 90 percent, authors get ready conditions for an informatic solution (with addition of interface for data base interaction) for help as a non-invasive complement to medical diagnosis using cry from neonate induced by pain(AU)

Wavelet packet transform and multilayer perceptron to identify voices with a mild degree of vocal deviation / Transformada Wavelet packet y Perceptrón Multicapa para identificación de voces con grado leve de desvío vocal

Introduction. Laryngeal disorders are characterized by a change in the vibratory pattern of the vocal folds. This disorder may have an organic origin described by anatomical fold modification, or a functional origin caused by vocal abuse or misuse. The most common diagnostic methods are performed by invasive imaging features that cause patient discomfort. In addition, mild voice deviations do not stop the in-dividual from using their voices, which makes it difficult to identify the problem and increases the possibility of complications. Aim. For those reasons, the goal of the present paper was to develop a noninvasive alternative for the identification of voices with a mild degree of vocal deviation ap-plying the Wavelet Packet Transform (WPT) and Multilayer Perceptron (MLP), an Artificial Neural Network (ANN). Methods. A dataset of 74 audio files were used. Shannon energy and entropy mea-sures were extracted using the Daubechies 2 and Symlet 2 families and then the processing step was performed with the MLP ANN. Results. The Symlet 2 family was more efficient in its generalization, obtaining 99.75% and 99.56% accuracy by using Shannon energy and entropy measures, re-spectively. The Daubechies 2 family, however, obtained lower accuracy rates: 91.17% and 70.01%, respectively. Conclusion. The combination of WPT and MLP presented high accuracy for the identification of voices with a mild degree of vocal deviation

ntroducción. Los trastornos laríngeos se caracterizan por un cambio en el patrón vibratorio de los pliegues vocales. Este trastorno puede tener un origen orgánico, descrito como la modificación anatómica de los pliegues vocales, o de origen fun-cional, provocado por abuso o mal uso de la voz. Los métodos de diagnóstico más comunes se realizan mediante procedimientos invasivos que causan malestar al pa-ciente. Además, los desvíos vocales de grado leve no impiden que el individuo utilice la voz, lo que dificulta la identificación del problema y aumenta la posibilidad de complicaciones futuras.Objetivo. Por esas razones, el objetivo de esta investigación es desarrollar una he-rramienta alternativa, no invasiva para la identificación de voces con grado leve de desvío vocal aplicando Transformada Wavelet Packet (WPT) y la red neuronal artifi-cial del tipo Perceptrón Mutlicapa (PMC). Métodos. Fue utilizado un banco de datos con 78 voces. Fueron extraídas las me-didas de energía y entropía de Shannon usando las familias Daubechies 2 y Symlet 2 para después aplicar la red neuronal PMC. Resultados. La familia Symlet 2 fue más eficiente en su generalización, obteniendo un 99.75% y un 99.56% de precisión mediante el uso de medidas de energía y en-tropía de Shannon, respectivamente. La familia Daubechies 2, sin embargo, obtuvo menores índices de precisión: 91.17% y 70.01%, respectivamente. Conclusión. La combinación de WPT y PMC presentó alta precisión para la iden-tificación de voces con grado leve de desvío vocal

Application of artificial neural network in evaluation of IVF embryo / 中华检验医学杂志

Artificial neural network (ANN) is a network framework that drives artificial intelligence (AI). Classical convolutional neural networks (CNN) are mainly used for cell count and image recognition at fixed time in embryo evaluation. Fully connected deep neural networks (DNN), with increased accuracy of image recognition, are suitable for the units equipped with high configuration hardware and need comprehensive prediction according to the integrated clinical information. Residual networks improve the accuracy by increasing layers and solving the gradient disappearance problem through jump connection to realize dynamic embryo assessment. Bayesian networks (BN) and multi-layer perceptron (MLP) are two machine learning methods. The former is especially used for comprehensive prediction combined with complex clinical information in case of lack of conditions. The latter has gradient disappearance and explosion problem, and is easy to lose some spatial features of images, so it is used for small sample volumes. ANN has advantages in the prediction of implantation rate and aneuploidy and reducing invasive detection in quality assessment of embryos, which is an important research direction of human-assisted reproductive technology (ART).

Establishment of artificial neural network predication model of postoperative fatigue syndrome in patients with painless colonoscopy / 中华麻醉学杂志

Objective:To establish an artificial neural network (ANN) model for predication of postoperative fatigue syndrome (POFS) in patients with painless colonoscopy.Methods:The out-patients received painless colonoscopy from October 2016 to February 2017 were selected.A total of 38 factors influencing POFS during perioperative period were collected.Christensen postoperative fatigue score was performed when resuscitation achieved the standard.The patients were divided into POFS group (Christensen score≥3) and non-POFS group (Christensen score<3) according to whether POFS occurred.Logistic regression predication model and ANN predication model were established and tested, respectively.The areas under the receiver operating characteristic curve were used to compare the efficacy of the two models for predication of POFS.Results:The error rates of the ANN prediction model training set and test set were 23.1% and 28.1%, respectively.The sensitivity and specificity of the training set were 88.6% and 52.7%, respectively.The sensitivity and specificity of the test set were 91.6% and 71.1%, respectively.The areas under the curves of logistic regression predication model and ANN predication model were 0.698 and 0.776, respectively.Conclusion:ANN prediction model has been successfully established, which provides better efficacy than logistic regression predication model for predication of POFS in patients with painless colonoscopy .

Application of Data Mining Technology in Risk Prediction Model for Lung Cancer / 肿瘤防治研究

Objective To establish a lung cancer risk prediction model using data mining technology and compare the performance of decision tree C5.0 and artificial neural networks in the application of risk prediction model, and to explore the value of data mining techniques in lung cancer risk prediction. Methods We collected the data of 180 patients with lung cancer and 240 patients with benign lung lesion which contained 17 variables of risk factors and clinical symptoms. Decision tree C5.0 and artificial neural networks models were established to compare the prediction performance. Results There were 420 valid samples collected in total and proportioned with the ratio of 7:3 for the training set and testing set. The accuracy, sensitivity, specificity, Youden index, positive predictive value, negative predictive value and AUC of artificial neural networks model were 65.3%, 61.7%, 73.3%, 0.350, 54.9%, 73.1% and 0.675 (95%CI: 0.628-0.720) in testing set; those of decision tree C5.0 model were 61.0%, 47.8%, 80.4%, 0.282, 35.3%, 80.6% and 0.641 (95%CI: 0.593-0.687) in testing set. Conclusion The artificial neural networks model is superior to the decision tree C5.0 model at overall performance and it has potential application value in the risk prediction of lung cancer.

Establishment and Application of Artificial Neural Network Model in Predicting Clinical Efficacy of Interferon for Chronic Hepatitis B / 中国药房

OBJECTIVE：To establ ish artificial neural netw orks（ANN）model to predict the interferon in the treatment of chronic hepatitis B （CHB），and to provide evidence for selecting suitable CHB therapy plan in clinic. METHODS ：The clinical data of 92 CHB patients treated by interferon ，from Guangzhou Eighth People ’s Hospital were retrospectively analyzed from Jul. 2011 to Dec. 2019. The basic information ，biochemical indexes ，blood routine indexes and virological markers of patients were collected. According to the effect of interferon ，the patients were divided into response group （73 cases）and non-response group （19 cases）. Minitab 18.0 software was used for multivariate Logistic regression analysis to screen the factors influencing the efficacy of interferon. Neurosolutions 5.0 software was used to randomly select 30％ of patients with CHB （27 cases）as the test group to establish and verify the ANN model. RESULTS ：The mean platelet volume ，platelet distribution width ，direct bilirubin ， hepatitis B e antigen and hepatitis B virus DNA more than 4×107 IU/mL had significant effect on interferon response （P＜0.05）. The accuracy ，specificity and area under characteristic curve of ANN test group were significantly higher than those of Logistic regression（P＜0.05）. CONCLUSIONS ：ANN model is accurate in predicting the efficacy of interferon in the treatment of CHB.

Application of neural network model and logistic regression in the prediction of chronic obstructive pulmonary disease / 公共卫生与预防医学

Objective To establish a mathematical prediction model for chronic obstructive pulmonary disease (COPD) by applying an artificial neural network (ANN) and logistic regression analysis method. Methods A cross-sectional survey was conducted in 2015 to collect epidemiological data of COPD of 2 400 residents from Hubei Province. Subjects were randomized into training group and test group at a ratio of 7:3. The prediction models of COPD were established using ANN and logistic multiple regression. The predictive performance of the two models was compared. Results Information from a total of 1 569 subjects was valid and analyzed, including 1,099 cases in the training group and 470 cases in the test group. The area under curve (AUC) of ANN for training group and test group was 0.80 and 0.78, respectively. The AUC of logistic regression for training group and test group was 0.75 and 0.74, respectively. Conclusion It is feasible to apply ANN and logistic regression models to predict COPD, which can provide scientific evidence for COPD prevention and treatment.

Analysis of Artificial Neural Networks for Forecasting Photovoltaic Energy Generation with Solar Irradiance

Abstract The growth in the use of solar energy has encouraged the development of techniques for short-term prediction of solar photovoltaic energy generation (PSPEG). Machine learning with Artificial Neural Networks (ANNs) is the most widely used technique to solve this problem. However, comparative studies of these networks with distinct structural configurations, input parameters and prediction horizon, have not been observed in the literature. In this context, the aim of this study is to evaluate the prediction accuracy of the Global Horizontal Irradiance (GHI), which is often used in the PSPEG, generated by ANN models with different construction structures, sets of input meteorological variables and in three short-term prediction horizons, considering a unique database. The analyses were performed with controlled environment and experimental configuration. The results suggest that ANNs using the input GHI variable provide better accuracy (approximately 10%), and their absence increases error variability. No significant difference (p>0.05) was identified in the prediction error models trained with distinct meteorological input data sets. The prediction errors were similar for the same ANN model in the different prediction horizons, and ANNs with 30 and 60 neurons with one hidden layer demonstrated similar or higher accuracy than those with two hidden layers.

Comparison between Thin-Layer Models and Non-Traditional Methods in the Modelling of Drying Kinetics of Crustacean Wastes

Abstract This research aims to compare the classical thin-layer models, stepwise fit regression method (SRG) and artificial neural networks (ANN) in the modelling of drying kinetics of shrimp shell and crab exoskeleton. Thus, drying curves were obtained using a convective dryer (3.0 m/s) at temperatures of 30.45 and 60oC. The results showed a decreasing tendency for the drying time as the temperature increased for both materials. Drying curves modelling of both materials showed fitted results with R 2 adj >0.998 and MRE<13.128% for some thin-layer models. On the other hand, by SRG a simple model could be obtained as a function of time and temperature, with the greatest accuracy being found in the modelling of experimental data of crab exoskeleton, with MRE<10.149%. Finally, the ANNs were employed successfully in the modelling of drying kinetics, showing high prediction quality with the trained recurrent ANN models.

Analysis of the technical feasibility of using artificial intelligence for smoothing active power in a photovoltaic system connected to the power system

Abstract Recent technological advances and increased participation of energy systems based on photovoltaic solar energy place this renewable energy source in a prominent position in the current scenario. With the increase in the share of solar photovoltaic systems, the impact of power fluctuations in these sources has worsened, which can affect the quality of electrical energy and the reliability of the electrical power system. Therefore, with the use of energy storage together with control algorithms based on artificial intelligence, it is possible to control and perform power smoothing. In this context, the study presents a technical feasibility study on the use of artificial neural network (ANN) to perform the power smoothing of the photovoltaic system connected to the network. Being studied the performance of a real photovoltaic system operating in conjunction with an ideal energy storage for comparative analysis of the performance of the artificial neural network when the numbers of neurons and layers are modified for different real operating conditions considered as temperature variation, humidity, irradiation, pressure and wind speed, which are considered to be ANN input data. The results obtained point to the feasibility of using ANN, with acceptable precision, for power smoothing. According to the analyzes carried out, it is clear that ANN's with few neurons, the smoothing profile tends to be more accurate when compared to larger amounts of neurons. In the current state of the study, it was not possible to determine a relationship between the variations in the number of neurons with the most accurate results, it is important to note that the development of the curve pointed by the neural network can be influenced by the database. It should be noted that, when ANN exceeds or does not reach the optimal smoothing curve, the storage system compensates for the lack or excess of power, and there is a need for other mechanisms to optimize power smoothing.

Estimating Hydroxymethyfurfural (HMF) Concentration Via Modified Seliwanoff Test Using Artificial Neural Network (ANN)

Abstract Hydroxymethylfurfural (HMF) is a quality indicator, especially in foods where changes in protein-carbohydrate interactions are observed during the applied process. In this study absorbance and L*, a*, b* values of red color emerged due to the relationship between hydroxymethylfurfural (HMF) and resorcinol during the modified Seliwanoff test were used as input data artificial neural network (ANN) to determine the HMF concentration for the first time. A linear relationship, between HMF concentration and absorbance of red color, can be represented by equation absorbance = 0.0020 + 0.0012* concentration of HMF (mg L-1) with R2 = 99.6%, Fisher ratio: 0.18, p value of lack of fit: 0.975, correlation coefficient: 0.9960. Intra-day and inter-day precision expressed as relative standard deviation (RSD) %, were 2.35 - 3.65% and 3.16 - 4.73%, respectively. Recovery rates and RSDs were in the range of 99.34 - 100.47% and 1.58 - 3.68%. It showed high correlation compared to HPLC method used as reference method (0.998). The R2 values of ANN for estimation of HMF concentration were found 0.90 for training, 0.96 for validation, and 0.99 for testing and AARD was found 8.85%. Evaluation of the absorbance and L*, a*, b* values of the red color with artificial intelligence is a reliable way to determine the HMF concentration.