Data-driven models perform poorly on part-of-speech tagging problems with the square Hmong language, a low-resource corpus. This paper designs a weight evaluation function to reduce the influence of unknown words. It proposes an improved harmony search algorithm utilizing the roulette and local evaluation strategies for handling the square Hmong part-of-speech tagging problem. The experiment shows that the average accuracy of the proposed model is 6%, 8% more than HMM and BiLSTM-CRF models, respectively. Meanwhile, the average F1 of the proposed model is also 6%, 3% more than HMM and BiLSTM-CRF models, respectively.
Recognition is one of the basic characteristics of human brain, and also for the living creatures. It is possible to recognize images, persons, or patterns according to their characteristics. This recognition could be done using eyes or dedicated proposed methods. There are numerous applications for pattern recognition such as recognition of printed or handwritten letters, for example reading post addresses automatically and reading documents or check reading in bank.
One of the challenges which faces researchers in character recognition field is the recognition of digits, which are written by hand. This paper describes a classification method for on-line handwrit
... Show MoreThis paper studies the adaptive coded modulation for coded OFDM system using punctured convolutional code, channel estimation, equalization and SNR estimation. The channel estimation based on block type pilot arrangement is performed by sending pilots at every sub carrier and using this estimation for a specific number of following symbols. Signal to noise ratio is estimated at receiver and then transmitted to the transmitter through feedback channel ,the transmitter according to the estimated SNR select appropriate modulation scheme and coding rate which maintain constant bit error rate
lower than the requested BER. Simulation results show that better performance is confirmed for target bit error rate (BER) of (10-3) as compared to c
In this paper, a new method of selection variables is presented to select some essential variables from large datasets. The new model is a modified version of the Elastic Net model. The modified Elastic Net variable selection model has been summarized in an algorithm. It is applied for Leukemia dataset that has 3051 variables (genes) and 72 samples. In reality, working with this kind of dataset is not accessible due to its large size. The modified model is compared to some standard variable selection methods. Perfect classification is achieved by applying the modified Elastic Net model because it has the best performance. All the calculations that have been done for this paper are in
It is frequently asserted that an advantage of a binary search tree implementation of a set over linked list implementation is that for reasonably well balanced binary search trees the average search time (to discover whether or not a particular element is present in the set) is O(log N) to the base 2 where N is the number of element in the set (the size of the tree). This paper presents an experiment for measuring and comparing the obtained binary search tree time with the expected time (theoretical), this experiment proved the correctness of the hypothesis, the experiment is carried out using a program in turbo Pascal with recursion technique implementation and a statistical method to prove th
... Show MoreString matching is seen as one of the essential problems in computer science. A variety of computer applications provide the string matching service for their end users. The remarkable boost in the number of data that is created and kept by modern computational devices influences researchers to obtain even more powerful methods for coping with this problem. In this research, the Quick Search string matching algorithm are adopted to be implemented under the multi-core environment using OpenMP directive which can be employed to reduce the overall execution time of the program. English text, Proteins and DNA data types are utilized to examine the effect of parallelization and implementation of Quick Search string matching algorithm on multi-co
... Show MoreLearning the vocabulary of a language has great impact on acquiring that language. Many scholars in the field of language learning emphasize the importance of vocabulary as part of the learner's communicative competence, considering it the heart of language. One of the best methods of learning vocabulary is to focus on those words of high frequency. The present article is a corpus based approach to the study of vocabulary whereby the research data are analyzed quantitatively using the software program "AntWordprofiler". This program analyses new input research data in terms of already stored reliable corpora. The aim of this article is to find out whether the vocabularies used in the English textbook for Intermediate Schools in Iraq are con
... Show MoreThis work implements the face recognition system based on two stages, the first stage is feature extraction stage and the second stage is the classification stage. The feature extraction stage consists of Self-Organizing Maps (SOM) in a hierarchical format in conjunction with Gabor Filters and local image sampling. Different types of SOM’s were used and a comparison between the results from these SOM’s was given.
The next stage is the classification stage, and consists of self-organizing map neural network; the goal of this stage is to find the similar image to the input image. The proposal method algorithm implemented by using C++ packages, this work is successful classifier for a face database consist of 20
... Show MoreIn this paper we introduce two Algorithms, the first Algorithms when it is odd order and how we calculate magic square and rotation for it. The second Algorithms when it be even order and how to find magic square and rotation for it.