Artificial neural networks (ANN): prediction of sensory measurements from instrumental data

The objective of this study was to predict by means of Artificial Neural Network (ANN), multilayer perceptrons, the texture attributes of light cheesecurds perceived by trained judges based on instrumental texture measurements. Inputs to the network were the instrumental texture measurements of light cheesecurd (imitative and fundamental parameters). Output variables were the sensory attributes consistency and spreadability. Nine light cheesecurd formulations composed of different combinations of fat and water were evaluated. The measurements obtained by the instrumental and sensory analyses of these formulations constituted the data set used for training and validation of the network. Network training was performed using a back-propagation algorithm. The network architecture selected was composed of 8-3-9-2 neurons in its layers, which quickly and accurately predicted the sensory texture attributes studied, showing a high correlation between the predicted and experimental values for the validation data set and excellent generalization ability, with a validation RMSE of 0.0506.

Filmes poliméricos ultrafinos produzidos pela técnica de automontagem: preparação, propriedades e aplicações

The self-assembly technique is a powerful tool to fabricate ultrathin films from organic compounds aiming at technological applications in molecular electronics. This relatively new approach allows molecularly flat films to be obtained on a simple and cheap fashion from various types of material, including polyelectrolytes, conducting polymers, dyes and proteins. The resulting multilayer films may be fabricated according to specific requirements since their structural and physical properties may be controlled at the molecular level. In this review we shall comment upon the evolution of preparation methods for ultrathin films, the process of adsorption and their main properties, as well as some examples of technological applications of layer-by-layer or self-assembled films.

Redes neurais e suas aplicações em calibração multivariada

Neural Networks are a set of mathematical methods and computer programs designed to simulate the information process and the knowledge acquisition of the human brain. In last years its application in chemistry is increasing significantly, due the special characteristics for model complex systems. The basic principles of two types of neural networks, the multi-layer perceptrons and radial basis functions, are introduced, as well as, a pruning approach to architecture optimization. Two analytical applications based on near infrared spectroscopy are presented, the first one for determination of nitrogen content in wheat leaves using multi-layer perceptrons networks and second one for determination of BRIX in sugar cane juices using radial basis functions networks.

Aplicação de redes neurais artificiais na identificação de gasolinas adulteradas comercializadas na região de Londrina - Paraná

The multilayer perceptron network was used to classify the gasoline. The main parameters used in the classification were established by the Ordinance nº 309 of the Agência Nacional do Petróleo, but without informing the network the legal limits of these parameters. The network used had 10 neurons in a single hidden layer, learning rate of 0.04 and 250 training epochs. The application of artificial neural network served classify 100% of the commercialized gas in the region of Londrina-PR and to identify the tampered gasoline even those suspected of tampering.

Aplicação de técnicas multivariadas e inteligência artificial na análise de espectros de infravermelho para determinação de matéria orgânica em amostras de solos

In this paper studies based on Multilayer Perception Artificial Neural Network and Least Square Support Vector Machine (LS-SVM) techniques are applied to determine of the concentration of Soil Organic Matter (SOM). Performances of the techniques are compared. SOM concentrations and spectral data from Mid-Infrared are used as input parameters for both techniques. Multivariate regressions were performed for a set of 1117 spectra of soil samples, with concentrations ranging from 2 to 400 g kg-1. The LS-SVM resulted in a Root Mean Square Error of Prediction of 3.26 g kg-1 that is comparable to the deviation of the Walkley-Black method (2.80 g kg-1).

Ajuste do modelo de Schumacher e Hall e aplicação de redes neurais artificiais para estimar volume de árvores de eucalipto

Objetivou-se, neste trabalho, avaliar o ajuste do modelo volumétrico de Schumacher e Hall por diferentes algoritmos, bem como a aplicação de redes neurais artificiais para estimação do volume de madeira de eucalipto em função do diâmetro a 1,30 m do solo (DAP), da altura total (Ht) e do clone. Foram utilizadas 21 cubagens de povoamentos de clones de eucalipto com DAP variando de 4,5 a 28,3 cm e altura total de 6,6 a 33,8 m, num total de 862 árvores. O modelo volumétrico de Schumacher e Hall foi ajustado nas formas linear e não linear, com os seguintes algoritmos: Gauss-Newton, Quasi-Newton, Levenberg-Marquardt, Simplex, Hooke-Jeeves Pattern, Rosenbrock Pattern, Simplex, Hooke-Jeeves e Rosenbrock, utilizado simultaneamente com o método Quasi-Newton e com o princípio da Máxima Verossimilhança. Diferentes arquiteturas e modelos (Multilayer Perceptron MLP e Radial Basis Function RBF) de redes neurais artificiais foram testados, sendo selecionadas as redes que melhor representaram os dados. As estimativas dos volumes foram avaliadas por gráficos de volume estimado em função do volume observado e pelo teste estatístico L&O. Assim, conclui-se que o ajuste do modelo de Schumacher e Hall pode ser usado na sua forma linear, com boa representatividade e sem apresentar tendenciosidade; os algoritmos Gauss-Newton, Quasi-Newton e Levenberg-Marquardt mostraram-se eficientes para o ajuste do modelo volumétrico de Schumacher e Hall, e as redes neurais artificiais apresentaram boa adequação ao problema, sendo elas altamente recomendadas para realizar prognose da produção de florestas plantadas.

Endovascular treatment of popliteal artery aneurysm. Early and midterm results

OBJECTIVE: to evaluate the efficacy of endovascular repair of popliteal artery aneurysms on maintaining patency of the stent in the short and medium term. METHODS: this was a retrospective, descriptive and analytical study, conducted at the Integrated Vascular Surgery Service at the Hospital da Beneficência Portuguesa de São Paulo. We followed-up 15 patients with popliteal aneurysm, totaling 18 limbs, treated with stent from May 2008 to December 2012. RESULTS: the mean follow-up was 14.8 months. During this period, 61.1% of the stents were patent. The average aneurysm diameter was 2.5cm, ranging from 1.1 to 4.5cm. The average length was 5cm, ranging from 1.5 to 10 cm. In eight cases (47.1%), the lesion crossed the joint line, and in four of these occlusion of the prosthesis occurred. In 66.7% of cases, treatment was elective and only 33.3% were symptomatic patients treated on an emergency basis. The stents used were Viabahn (Gore) in 12 cases (66.7%), Fluency (Bard) in three cases (16.7%), Multilayer (Cardiatis) in two cases (11.1%) and Hemobahn (Gore) in one case (5.6%). In three cases, there was early occlusion (16.6%). During follow-up, 88.2% of patients maintained antiplatelet therapy. There was no leakage at ultrasound (endoleak). No fracture was observed in the stents. CONCLUSION: the results of this study are similar to other published series. Probably, with the development of new devices that support the mechanical characteristics found on the thighs, there will be improved performance and prognosis of endovascular restoration.

Automated grading of left ventricular segmental wall motion by an artificial neural network using color kinesis images

The present study describes an auxiliary tool in the diagnosis of left ventricular (LV) segmental wall motion (WM) abnormalities based on color-coded echocardiographic WM images. An artificial neural network (ANN) was developed and validated for grading LV segmental WM using data from color kinesis (CK) images, a technique developed to display the timing and magnitude of global and regional WM in real time. We evaluated 21 normal subjects and 20 patients with LVWM abnormalities revealed by two-dimensional echocardiography. CK images were obtained in two sets of viewing planes. A method was developed to analyze CK images, providing quantitation of fractional area change in each of the 16 LV segments. Two experienced observers analyzed LVWM from two-dimensional images and scored them as: 1) normal, 2) mild hypokinesia, 3) moderate hypokinesia, 4) severe hypokinesia, 5) akinesia, and 6) dyskinesia. Based on expert analysis of 10 normal subjects and 10 patients, we trained a multilayer perceptron ANN using a back-propagation algorithm to provide automated grading of LVWM, and this ANN was then tested in the remaining subjects. Excellent concordance between expert and ANN analysis was shown by ROC curve analysis, with measured area under the curve of 0.975. An excellent correlation was also obtained for global LV segmental WM index by expert and ANN analysis (R² = 0.99). In conclusion, ANN showed high accuracy for automated semi-quantitative grading of WM based on CK images. This technique can be an important aid, improving diagnostic accuracy and reducing inter-observer variability in scoring segmental LVWM.

Estimate of respiration rate and physicochemical changes of fresh-cut apples stored under different temperatures

In this study, the influence of storage temperature and passive modified packaging (PMP) on the respiration rate and physicochemical properties of fresh-cut Gala apples (Malus domestica B.) was investigated. The samples were packed in flexible multilayer bags and stored at 2 °C, 5 °C, and 7 °C for eleven days. Respiration rate as a function of CO2 and O2 concentrations was determined using gas chromatography. The inhibition parameters were estimated using a mathematical model based on Michaelis-Menten equation. The following physicochemical properties were evaluated: total soluble solids, pH, titratable acidity, and reducing sugars. At 2 °C, the maximum respiration rate was observed after 150 hours. At 5 °C and 7 °C the maximum respiration rates were observed after 100 and 50 hours of storage, respectively. The inhibition model results obtained showed a clear effect of CO2 on O2 consumption. The soluble solids decreased, although not significantly, during storage at the three temperatures studied. Reducing sugars and titratable acidity decreased during storage and the pH increased. These results indicate that the respiration rate influenced the physicochemical properties.

Physiological and enzymatic alterations in papaya seed during storage

This study was done to evaluate the physiological and enzymatic alterations in papaya (Carica papaya L.) seeds during storage period. Seeds were extracted from mature fruits of Formosa group papaya hybrid Tainung 01. The sarcotesta was removed by rubbing the seeds on a wire screen under running water and then dried to the moisture content (MC) of 5, 8 or 11% The seeds were packed in multilayer paper bags, polyethylene bags, aluminum foil pouch and metallic canisters and stored for 15 months under laboratory conditions. Seeds were evaluated, at three month interval, for MC, germination, and the activity of acid phosphotase (AP) and malate dehyrogenase (MDH) was evaluated with the use of amide gel (12%) electrophoresis. The fresh seeds had post-harvest dormancy, which was broken after six month storage. Independent of the package type, the seeds could be stored for 12 months with 8 or 11% MC under ambient conditions. There was no association between seed deterioration and alterations in AP and MDH activity.