Detection of reed using cnn method and analysis of the dry reed (phragmites australis) for a sustainable lake area.

BACKGROUND: Common reed (Phragmites australis L.) is a highly productive wetland plant and a possible valuable resource of renewable biomass worldwide. For a sustainable management the exploitation of reed is beneficial because the increasing demand for sustainable biomass which presents reed bed areas and wetlands. Knowing the properties of plant biomass obtained from reeds is essential both for the effect on combustion equipment and for the impact on the environment. Brates Lake, situated in Galati, Romania is a natural watershed with reed plantations. RESULTS: We used the convolutional neural network method combined with the cropped image techniques represent a powerful tool for high-precision image-based biomass detection in lake areas. The study aimed to investigate the morphological and chemical parameters through SEM-EDX analysis and pH, conductivity, nitrate anion, nitrite anion, total nitrogen, sulphate anion, sulphide anion, phosphate anion concentrations were determined from reed extract. The samples have a moderately acidic reaction pH 4.91-4.98. The number of soluble salts in the reed extract is in the range of 3.24-4.70 g/L, the values are within normal limits, providing the plant with the necessary nutrients. CONCLUSIONS: This is the first time that neural networks are used for the detection and prediction of areas at risk for biodiversity (reduction of water gloss until it disappears, imbalances caused by keeping reeds dry in water) caused by the aggressive and uncontrolled growth of reeds.

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks.

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5-10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.