International Journal of Computational Intelligence Studies (6 papers in press)

Regular Issues

• Solving differential equations with global optimization techniques  
  by Ioannis Tsoulos, Alexandros Tzallas, Dimitrios Tsalikakis 
  Abstract: The solution of differential equations finds many applications in a huge range of problems, and many techniques have been developed to approximate their solutions. For example, differential equations can be applied to physics problems, chemistry problems, economics, modelling, etc. This manuscript presents a number of global optimisation techniques that have been successfully applied to train machine learning models to approximate differential equation solutions. More specifically, two modified versions of genetic algorithms and particle swarm optimisation methods are proposed here. These methods have been successfully applied to solving ordinary differential equations and systems of differential equations as well as partial differential equations with Dirichlet boundary conditions.
  Keywords: differential equations; global optimisation; stochastic methods; machine learning.
  DOI: 10.1504/IJCISTUDIES.2024.10062128
   
  
• Digital Media Image Color Enhancement Processing Method Based on Multiscale Retinex  
  by Qiushi Li, Boya Dong, Xin Meng 
  Abstract: Aiming at the problems of poor enhancement effect and large colour error in digital media image colour enhancement, a method of digital media image colour enhancement based on multi-scale Retinex is proposed. First, build and HSI colour space model to analyse digital media image colour space. Then, wavelet threshold method is used to deal with colour space noise. Finally, multi-scale Retinex is introduced to optimise Retinex through Gaussian filtering and weighted fusion to achieve colour enhancement of digital media images. The experimental results show that the proposed method can effectively improve the colour enhancement effect of digital media images, and the error is less than 0.15%, and the time cost is 0.20 s. This method effectively improves the colour enhancement effect.
  Keywords: multi-scale Retinex; digital media image; colour enhancement; HSI colour space model; wavelet coefficients; hard threshold function.
  DOI: 10.1504/IJCISTUDIES.2024.10063664
   
  
• DhwaniClone Lite: A light-weight encoder framework for voice cloning  
  by Jay Doshi, Jay Jani, Ruhina Karani 
  Abstract: Voice cloning has garnered significant attention for its ability to replicate individuals’ voices using artificial intelligence. This study introduces an innovative voice cloning system that employs a lightweight feedforward neural network as an encoder, Tacotron2 as a synthesizer, and WaveNet as a vocoder. Unlike architectures relying on Generative Adversarial Networks (GANs), this research approach demands fewer data samples while achieving comparable outcomes. The feedforward neural network encoder effectively captures distinctive vocal characteristics, generating speaker embeddings for discerning individual voices. Tacotron2 generates mel spectrograms that represent synthesized speech, while WaveNet produces high-quality audio waveforms closely resembling natural human speech. Notably, this research demonstrates the system’s accessibility in lowdata scenarios, enabling expedited training. Objective evaluations, including MOS, PESQ, and SNR metrics, corroborate the superiority of this research. In conclusion, this study presents a lightweight and data-efficient voice cloning system with diverse applications in voice assistants, personalized speech synthesis, and entertainment domains.
  Keywords: Voice Cloning; Encoder; Feed-Forward neural network; voice embeddings; mel spectogram.
  DOI: 10.1504/IJCISTUDIES.2024.10065761
   
  

Special Issue on: Computational Techniques for Real-time Applications The Hidden Barriers to Innovation

• Multimodal Education Management Model for College Students in the Context of Big Data  
  by Wenxi Ou  
  Abstract: Under the background of big data informationisation, the construction of multimodal education management mode has become a hot topic of discussion for efficient teaching reform. This paper combines the connotation of multimodal teaching, establishes a teaching quality assessment model for college students based on big data technology, focuses on the main advantages of multimodal teaching management and how to use big data to predict the teaching quality of college students, makes the network model meet the expectation by means of deep learning technology, and strengthens the multimodal teaching management model for college students. The research results provide some reference for improving the multimodal teaching management model of college students in the context of big data.
  Keywords: big data; students’ education; multimodal; deep learning.
  DOI: 10.1504/IJCISTUDIES.2024.10066234
   
  
• Multimodal Sentiment Analysis of Tourism Evaluation Based on Attention Mechanism and Neural Network  
  by Mei Zhao  
  Abstract: Travel review text reviews objectively reflect travellers’ real perceptions of tourist destinations and services, and are also one of the important ways of internet word-of-mouth communication. According to the study, travellers will obtain information about products and other travellers’ reviews of tourism through various channels before making purchase decisions, and use them as the basis for whether to continue purchasing. With the help of the research method of big data, the text takes the travel virtual community and the online review text of tourism on the web platform as the research material. To address the problems of previous models, we propose an attention-based mechanism LSTM, called SA-BiLSTM, for travel evaluation sentiment analysis. We integrate the attention mechanism into the LSTM and use it to improve the representation capability of the LSTM. The attention mechanism ignores the distance between words, which effectively solves the gradient disappearance and gradient explosion problems encountered by LSTM, and the combination of LSTM and attention mechanism is equivalent to model fusion at the structural level, which enables the model to capture information in different directions in the text and enhances the robustness of the model. We validate the good results of our model relative to state-of-the-art models on numerous real datasets.
  Keywords: tourism evaluation analysis; attention mechanism; recurrent neural network; RNN; sentiment analysis.
  DOI: 10.1504/IJCISTUDIES.2024.10066235
   
  
• English Grammar Correction Based on Attention Mechanism Machine Translation  
  by Kuaile Zhao  
  Abstract: Grammatical error correction, which aims to use computer programs to automatically correct grammatical errors in written texts false. At present, the mainstream approach regards it as a monolingual translation task, and error correction is the process of translating
  Keywords: correction of English grammatical errors; MT attention mechanism; transformer.
  DOI: 10.1504/IJCISTUDIES.2024.10066236