List of Articles hidden Markov model

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - Persian digit recognition system in aerial writing based on depth image
  reza maleki Shahram Mohammadi
  Recognizing handwriting on paper, screen or in the air are some of the challenges in machine vision. Recognizing aerial text has many challenges due to its three-dimensional nature. In this research work, Persian digit recognition is considered in aerial text in which t More

  Recognizing handwriting on paper, screen or in the air are some of the challenges in machine vision. Recognizing aerial text has many challenges due to its three-dimensional nature. In this research work, Persian digit recognition is considered in aerial text in which the user writes the digits zero to nine in front of the Kinect sensor in the air and the system is able to detect the above digits using the sensor depth information. In the proposed system, the k-means automatic clustering method is used to separate the hand and fingertip from the background, the proposed linear slope change method is used to extract the feature, and the hidden Markov model (HMM) category is used to identify the feature and figure. The detection accuracy of the proposed system for Persian cultivars with local database and 10-fold cross-validation is 98%. The proposed system was compared with the results of several similar works, these comparisons show that the proposed system works relatively better than the systems under comparison. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - Using Discrete Hidden Markov Model for Modelling and Forecasting the Tourism Demand in Isfahan
  Khatereh Ghasvarian Jahromi Vida Ghasvarian Jahromi
  10.7508/jist.2018.02.007
  Tourism has been increasingly gaining acceptance as a driving force to enhance the economic growth because it brings the per capita income, employment and foreign currency earnings. Since tourism affects other industries, in many countries, tourism is considered in the More

  Tourism has been increasingly gaining acceptance as a driving force to enhance the economic growth because it brings the per capita income, employment and foreign currency earnings. Since tourism affects other industries, in many countries, tourism is considered in the economic outlook. The perishable nature of most sections dependent on the tourism has turned the prediction of tourism demand an important issue for future success. The present study, for the first time, uses the Discrete Hidden Markov Model (DHMM) to predict the tourism demand. DHMM is the discrete form of the well-known HMM approach with the capability of parametric modeling the random processes. MATLAB Software is applied to simulate and implement the proposed method. The statistic reports of Iranian and foreign tourists visiting Isfahan gained by Iran Cultural Heritage, Handicrafts, and Tourism Organization (ICHHTO)-Isfahan Tourism used for simulation of the model. To evaluate the proposed method, the prediction results are compared to the results from Artificial Neural Network, Grey model and Persistence method on the same data. Three errors indexes, MAPE (%), RMSE, and MAE, are also applied to have a better comparison between them. The results reveal that compared to three other methods, DHMM performs better in predicting tourism demand for the next year, both for Iranian and foreign tourists. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - Extraction and Modeling Context Dependent Phone Units for Improvement of Continuous Speech Recognition Accuracy by Phonemes Clustering
  Mohammad Bahrani H. Sameti
  This paper proposes a proper context dependent method for improving the accuracy of a Persian continuous speech recognition system. Due to some constraints in speech recognition system, the multiple phone units approach is utilized for extracting context dependent phone More

  This paper proposes a proper context dependent method for improving the accuracy of a Persian continuous speech recognition system. Due to some constraints in speech recognition system, the multiple phone units approach is utilized for extracting context dependent phone units. In this approach, each phoneme is clustered to some phoneme variations, and then each phoneme variation is modeled separately. Unsupervised phoneme clustering is done using k-means clustering algorithm. The new effective method is proposed for calculating the centroid of clusters. The proper number of cluster for each phoneme is determined according to amount of training data for that phoneme and recognition accuracy of that phoneme using context independent models. The number of clusters is then optimized by try and error methods. Then each cluster is modeled as a context dependent phone unit. The reduction in word error rate is about 22% using these models. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  4 - Robust Persian Isolated Digit Recognition Based on LSTM and Speech Spectral Features
  شیما طبیبیان
  One of the challenges of isolated Persian digit recognition is similar pronunciation of some digits such as "zero and three", "nine and two" and "five, seven and eight". This challenge leads to the high substitution errors and reduces the recognition accuracy. In this p More

  One of the challenges of isolated Persian digit recognition is similar pronunciation of some digits such as "zero and three", "nine and two" and "five, seven and eight". This challenge leads to the high substitution errors and reduces the recognition accuracy. In this paper, a combined solution based on short-term memory (LSTM) and hidden Markov model (HMM) is proposed to solve the mentioned challenge. The proposed approach increases the recognition rate of Persian digits on average 2 percent and in the best case 8 percent in comparison to the HMM-based approach. In the following of this work, due to the intensification of the mentioned challenge in noisy conditions, the robust recognition of Persian digits with similar pronunciation was considered. In order to increase the robustness of the LSTM-based recognizer, robust features extracted from the speech spectrum such as spectral entropy, burst degree, bisector frequency, spectral flatness, first formant and autocorrelation-based zero crossing rate were used. Using these features, while reducing the number of features for recognizing similar Persian digits from 39 coefficients to a maximum of 4 and a minimum of 1 coefficient, on average improved the robustness of the isolated digit recognizer in different noisy conditions (30 different situations resulting from five noise types of white, pink, babble, factory and car noises and six signal-to-noise ratios of -5, 0, 5, 10, 15 and 20 decibels) by 10%, 13%, 15% and 13% compared to the HMM-based, LSTM-based, deep belief network-based recognizers with Mel-Cepstrum coefficients and a convolutional neural network-recognizer with Mel Spectrogram features. Manuscript profile