The Hidden Markov Model as a suitable model for time sequence modeling is used in this project for estimation of speech synthesis parameters. In our approach, HMMs generate cepstral coefficients and pitch parameter which are then feed to a speech synthesis filter named MLSA. To generate the parameters of speech synthesis using HMMs, an algorithm is used which utilizes the context dependent information of speech units provided by cepstral coefficients, and their first and second derivatives. In our project, a phone with known left and right context, named triphone, is used as speech unit. For speech unit modeling, we compare observations of each triphone in the database with its HMM model. The result of this comparison is a sequence of HMM states. The comparison is done using viterbi algorithm. Average number of presence times in each state of each triphone, constitute a model for triphone duration. During speech synthesis, in order to obtain necessary parameters for synthesizing a triphone, HMM parameters such as mean and variance vectors of each state are repeated based on duration model. Using mean and variances obtained from HMM models, cepstral coefficients and pitch frequency are calculated and then transformed to speech using MLSA filter. In order to take into account the effects of various parameters on the pronunciation of triphones, cart DECISION TREES are also used. These TREES generate pitch and the duration of phonemes. In another way for automatic generation of pitch contour, we used the method proposed by Fujisaki. In this method, there is a global component for pitch contour and some local components for modeling of accents. To evaluate the performance of our speech synthesis system, MOS and DRT tests were conducted. The results of the MOS test were 3.8 for intelligibility, 3.9 for naturalness, and 3.5 for pleasantness when no DECISION tree was used for duration and pitch modeling. In another MOS test, pitch and duration were modeled using DECISION TREES. The results of the MOS test were 4.2, 4.4, and 4.1 for sentences existing in training database. These results were 4.3, 4.2, and 3.4 respectively for sentences out of training database. Pitch contour was also modeled using Fujisaki method. The results of the MOS test for this kind of pitch modeling were 4.6, 4.3, and 4.5 for sentences existing in training data base. These results were 4.5, 4.0, and 4.4 respectively for sentences out of training database. The DRT test result was 88% for word pairs synthesized using DECISION TREES for both duration and pitch modeling. These results show the suitability of the method used in this project.  

Background: Malaria is an infectious disease infecting 200-300 million people annually. Environmental factors such as precipitation, temperature, and humidity can affect its geographical distribution and prevalence. The environmental factors are also effective in the abundance and activity of malaria vectors. The present study aimed at presenting a model to predict the type of malaria. Methods: This cross-sectional study was conducted using the data of 285 people referring to a health center in Saravan from June 2009 to December 2016. Clementine 12. 0 was used for data analysis. The modeling was done using classification and regression DECISION TREES, chi-squared automatic interaction detector, C 5. 0, and neural network algorithms. Results: The accuracy of classification and regression DECISION TREES, chi-squared automatic interaction detector, C5. 0, and neural network was 0. 7217, 0. 6698, 0. 6840, and 0. 6557, respectively. Classification and regression DECISION TREES performed better than the other algorithms in terms of sensitivity, specificity, accuracy, precision, negative predictive value, and area under the ROC curve. The sensitivity and area under the ROC curve were 0. 5787 and 0. 66 for classification and regression DECISION TREES. Conclusions: Applying data mining methods for the analysis of malaria’ s data can change the current attitude toward malaria type determination. Faster and more precise identification of malaria type helps determine the proper cure and improve the performance of health organizations.

Digital soil mapping (DSM) can be defined as a production of spatial soil information. DECISION tree (DT) algorithm is one of the most popular machine learning methods which was applied in several recent DSM studies. This study was carried out to evaluate the capability of DT in mapping soils in Miandarband region with area of 50, 000 ha in Kermanshah province. The C5. 0 DECISION tree algorithm (with and without boosting meta-algorithm) used to establish spatial relationships between known soil taxonomic classes and environmental variables. Using simple systematic sampling, 78 pedons were studied and 6 great groups and 14 subgroups of Soil Taxonomy (ST) were identified. Thirty environmental items were derived from a digital elevation model (DEM) file and a landsat-8 OLI/TIRS (July/Tir 1394) image of the area. Predictions made by C5. 0 algorithm showed OA values of 73 percent for great group and subgroup, while comparable values for Kappa Index were 0. 61 and 0. 63, respectively. Combination of boosting meta-algorithm with C5. 0 increased OA values for ST categories 0. 80 and 0. 76 and Kappa Index values to 72 percent and 66 percent. Results showed a considerable capability for DT in recognition of soil pattern over the study area and the topographic variables seems to be most important. Also, analysis of the produced maps, compared with the observed soil pattern during the field survey, revealed a reasonable agreement of DECISION tree algorithm predictions with reality.

DECISION TREES as one of the data mining techniques, is used in credit scoring of bank customers. The main problem is the construction of DECISION TREES in that they can classify customers optimally. This paper proposes an appropriate model based on genetic algorithm for credit scoring of banks customers in order to offer credit facilities to each class. Genetic algorithm can help in credit scoring of customers by choosing appropriate features and building optimum DECISION TREES. Development process in pattern recognition and CRISP process are used in credit scoring of customers in construction of this model. The proposed classification model is based on clustering, feature selection, DECISION TREES and genetic algorithm techniques. This model select and combine the best DECISION tree based on the optimality criteria and constructs the final DECISION tree for credit scoring of customers. Results show that the accuracy of proposed classification model is more than almost the entire DECISION tree models compared in this paper. Also the number of leaves and the size of DECISION tree i.e. its complexity is less than the other models.

Investors are always looking for information about their investment choices to have a favorable investment and an optimized allocation of their resources. Bankruptcy prediction of the firm is one of the most important subjects that can help investors in this way. Many studies have been done in the field of bankruptcy prediction. However, the majority of them provide a general model for all industries as a unit. The main objective of this study is presenting a bankruptcy prediction model, specific for each industry, for three industries including automobile and parts manufacturing, chemical products, and Food, except for sugar products, using DECISION TREES model. To determine bankruptcy of the firm we used the criteria of Article 141 in Commercial Code. This research was performed from 2002 to 2014. The results show that the designed model has a prediction accuracy of 95.95, 96.83 and 97.83 percent for automobile and parts manufacturing industry, chemical products industry, and Food, except for sugar products industry, respectively. These findings reflect high accuracy of these three models, especially for Food, except for sugar products industry.

Security is one of the most important issues in modern computer systems. Among the major challenges in these systems is identifying normal and abnormal behaviors. But the boundary between these two is not well defined and it is a very complicated task to accomplish. Intrusion detection systems are one of the techniques that are used to maintain security in computer networks. Incorrect report of the intrusion alarm system is one of the major problems of security systems. Intrusion is defined as a set of activities and the purpose of these activities is jeopardizing the integrity, reliability and unauthorized system access to a particular resource. This paper proposes a mechanism based on the DECISION tree technique to detect intrusions in the network. Simulation results show that by the proposed method not only the duration of the training phase was reducedbut also the detection rate and falsealarm rate were improved.