Міжнародна співпраця в рамках професійної організації RAMECS принесла результатом публікацію у новому 2024 році двох статей у видаництві MECS Press, які індексуються в Скопус.
Information Technology for Generating Lyrics for Song Extensions Based on Transformers
The article develops technology for generating song lyrics extensions using large language models, in particular the T5 model, to speed up, supplement, and increase the flexibility of the process of writing lyrics to songs with/without taking into account the style of a particular author. To create the data, 10 different artists were selected, and then their lyrics were selected. A total of 626 unique songs were obtained. After splitting each song into several pairs of input-output tapes, 1874 training instances and 465 test instances were obtained. Two language models, NSA and SA, were retrained for the task of generating song lyrics. For both models, t5-base was chosen as the base model. This version of T5 contains 223 million parameters. The analysis of the original data showed that the NSA model has less degraded results, and for the SA model, it is necessary to balance the amount of text for each author. Several text metrics such as BLEU, RougeL, and RougeN were calculated to quantitatively compare the results of the models and generation strategies. The value of the BLEU metric is the most diverse, and its value varies significantly depending on the strategy. At the same time, Rouge metrics have less variability and a smaller range of values. In total, for comparison, we used 8 different decoding methods for text generation supported by the transformers library, including Greedy search, Beam search, Diverse beam search, Multinomial sampling, Beam-search multinomial sampling, Top-k sampling, Top-p sampling, and Contrastive search. All the results of the lyrics comparison show that the best method for generating lyrics is beam search and its variations, including ray sampling. The contrastive search usually outperformed the usual greedy approach. The top-p and top-k methods do not have a clear advantage over each other, and in different situations, they produced different results.
Oleksandr Mediakov , Victoria Vysotska, Dmytro Uhryn, Yuriy Ushenko, Cennuo Hu, “Information Technology for Generating Lyrics for Song Extensions Based on Transformers”, International Journal of Modern Education and Computer Science(IJMECS), Vol.16, No.1, pp. 23-36, 2024. DOI:10.5815/ijmecs.2024.01.03
Algorithms for Polarization-singular processing of Mueller-matrix images of Soft Tissues for Biomedical Applications
Traditional methods of imaging Muller-matrix polarimetry ensure obtaining large arrays of experimental data in the form of 16 Muller-matrix images. Processing and comparative analysis of the received information is quite time-consuming and requires a long time. A new algorithmic polarization-singular approach to the analysis of coordinate distributions of matrix elements (Mueller-matrix maps) of polycrystalline birefringent structure of biological tissues is considered. A Mueller-matrix model for describing the optical anisotropy of biological layers is proposed. Analytical correlations between polarization-singular states of the object field and characteristic values of Mueller-matrix images of birefringence soft tissue objects were found. The proposed algorithmic polarization-singular theory is experimentally verified. Examples of polarization singularities networks of Mueller-matrix maps of histological preparations of real tissues of female reproductive sphere are given. Diagnostic possibilities of the developed polarization-singular algorithms in diagnostics and differentiation of the stages of extragenital endometriosis are illustrated. Another area of biomedical diagnostics has been successfully tested: polarization-singular criteria for forensic Mueller-matrix determination of the age of myocardial injury of the deceased have been defined.
Liliya Diachenko, Edgar Vatamanitsa, Oleksandr Ushenko, Oleksandr Salega, Oleksandra Litvinenko, Zhengbing Hu, “Algorithms for Polarization-singular processing of Mueller-matrix images of Soft Tissues for Biomedical Applications”, International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.16, No.1, pp. 14-24, 2024. DOI:10.5815/ijigsp.2024.01.02
