Structural quality of soil in plantation： a case study on the mixed plantation of Alnus cremastogyne and Cupressus funebris in upper reaches of Yangtze River

In process of ecological construction in typical region of upper reaches of Yangtze River, China, the mixed plantations at the ages of 10-20 present a trend to be pure forests and degeneration. Soil samples including stratified soil and total soil were taken from 4 typical profiles in the mixed plantation ofAlnus cremastogyne and Cupressus funebris in Yanting County in central Sichuan, China. Soil indices of the plantation were compared with those of natural forest in Gongga Mountain in the same region, The results revealed that structural quality of soil in plantation was significantly lower than that in natural forests. The degradation of structural quality of soil in plantation was one of key factors for plantation degeneration, The degradation causes of structural quality of soil were analyzed. Aanthtopogenic disturbance and absence of effective protection and scientific management are the main reason for degradation of structural quality of soil in plantation. The main countermeasures, e.g. foresl reservation, ecological rehabilitation, litter horizon rebuilding as well as organic fertilizer application, were proposed to improve the structural quality of soil in plantation.

A New Hidden Markov Model for Protein Quality Assessment Using Compatibility Between Protein Sequence and Structure

Protein structure Quality Assessment（QA） is an essential component in protein structure prediction and analysis. The relationship between protein sequence and structure often serves as a basis for protein structure QA.In this work, we developed a new Hidden Markov Model（HMM） to assess the compatibility of protein sequence and structure for capturing their complex relationship. More specifically, the emission of the HMM consists of protein local structures in angular space, secondary structures, and sequence profiles. This model has two capabilities：（1） encoding local structure of each position by jointly considering sequence and structure information, and（2）assigning a global score to estimate the overall quality of a predicted structure, as well as local scores to assess the quality of specific regions of a structure, which provides useful guidance for targeted structure refinement. We compared the HMM model to state-of-art single structure quality assessment methods OPUSCA, DFIRE, GOAP,and RW in protein structure selection. Computational results showed our new score HMM.Z can achieve better overall selection performance on the benchmark datasets.

Denoising Letter Images from Scanned Invoices Using Stacked Autoencoders

Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In this paper,letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method.A stacked denoising autoencoder(SDAE)is implemented with two hidden layers each in encoder network and decoder network.In order to capture the most salient features of training samples,a undercomplete autoencoder is designed with non-linear encoder and decoder function.This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy.A dataset consisting of 59,119 letter images,which contains both English alphabets(upper and lower case)and numbers(0 to 9)is prepared from many scanned invoices images and windows true type(.ttf)files,are used for training the neural network.Performance is analyzed in terms of Signal to Noise Ratio(SNR),Peak Signal to Noise Ratio(PSNR),Structural Similarity Index(SSIM)and Universal Image Quality Index(UQI)and compared with other filtering techniques like Nonlocal Means filter,Anisotropic diffusion filter,Gaussian filters and Mean filters.Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values.Results show the superior performance of proposed SDAE method.

Measuring Structural Quality of Object-Oriented Softwares via Bug Propagation Analysis on Weighted Software Networks

The quality of a software system is partially determined by its structure（topological structure）,so the need to quantitatively analyze the quality of the structure has become eminent.In this paper a novel metric called software quality of structure（SQoS） is presented for quantitatively measuring the structural quality of object-oriented（OO） softwares via bug propagation analysis on weighted software networks（WSNs）.First,the software systems are modeled as a WSN,weighted class dependency network（WCDN）,in which classes are nodes and the interaction between every pair of classes if any is a directed edge with a weight indicating the probability that a bug in one class will propagate to the other.Then we analyze the bug propagation process in the WCDN together with the bug proneness of each class,and based on this,a metric（SQoS） to measure the structural quality of OO softwares as a whole is developed.The approach is evaluated in two case studies on open source Java programs using different software structures（one employs design patterns and the other does not） for the same OO software.The results of the case studies validate the effectiveness of the proposed metric.The approach is fully automated by a tool written in Java.