Garuda - Garba Rujukan Digital

Yang, Qingxue

Unknown Affiliation

Author-ID : 8108987

Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance

Published : 5 Documents Claim Missing Document

Claim Missing Document

Articles

Title

1

Speech Enhancement using Sliding Window Empirical Mode Decomposition with Median Filtering Technique Selvaraj, Poovarasan; Maidin, Siti Sarah; Yang, Qingxue
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.470

The Empirical Mode Decomposition is raising significant interest since its first introduction among the nineties. The attention in varied fields such as medical engineering, space analysis, hydrology, synthetic aperture measuring, speech enhancement, watermarking and etc. Hurst exponent statistics was adopted for identifying and selecting the set of Intrinsic Mode Functions (IMF) that are most affected by the noise components. Moreover, the speech signal was reconstructed by subsequently the least degraded IMF. Hereafter, in this article, SWEMD method is enhanced by using Sliding Window (SW) procedure. This research work has come SDG goals for health and well-being and also this research work concentrated on hearing aid application using noise level adjustment. In this SWEMDH method, the calculation of EMD is performed based on the small and sliding window along with the time axis. For each component, the total of sifting iterations is unwavering by decomposition of many signal windows by standard algorithm and calculating the average amount of sifting steps for each component. The median filter used for removed nonlinear components of this work. SWEMDH technique removed for low frequency Noisy Components. The speech quality was evaluation by the performance matrices of Mean Square Error, Perceptual evaluation of speech quality, signal to noise ratio, peak signal to noise ratio. Finally, the experimental results show the considerable improvements in speech enhancement under non-stationary noise environments.

Cellular Traffic Prediction Models Using Convolutional Long Short-Term Memory Samson, A Sunil; Sumathi, N; Maidin, Siti Sarah; Yang, Qingxue
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.472

Precise cellular traffic modeling and prediction is essential to future big data-based cellular network management for providing autonomic control and user-satisfied stable mobile services. However, the traditional methods have difficulty learning the complex hidden patterns of the users’ traffic data from cross-domains because of their shallow learning characteristics. Deep learning (DL)-based methods could somewhat identify these hidden patterns by learning the underlying spatial and temporal features and their dependencies. Yet, they too have constraints in handling the noisy and sparse data, reducing the prediction accuracy with increased computation time and associated storage costs. Therefore, this paper presents an intelligent cellular traffic prediction model (ICTPM) using two improved deep learning algorithms to tackle the negative impacts of noisy and sparse traffic datasets. Firstly, the Enhanced Stacked Denoising Auto-Encoder (ESDAE) is introduced to eliminate the noise in the traffic data by an adaptive Morlet wavelet transform. Secondly, Multi-dimensional Spatiotemporal Sparse-representation Convolutional Long Short-Term Memory (MDSTS-CLSTM) is used to learn the hidden patterns by extracting the spatial-temporal dependencies and predict the cellular usage in the presence of data sparsity problem. This MDSTS-CLSTM is developed by combining the Long Short-Term Memory (LSTM) with the Convolutional Neural Networks (CNN) and improvising the multi-dimensional feature learning, spatial-temporal analysis, and sparse representation properties of the hybrid DL algorithm. Evaluated over real-world cellular traffic cross-domain datasets from Telecom Italia and Open-CellID, the proposed ICTPM outperforms the state-of-the-art methods with 5-10% better performance enhancements.

Optimizing Survival Prediction in Children Undergoing Hematopoietic Stem Cell Transplantation through Enhanced Chaotic Harris Hawk Deep Clustering Arthi, R.; Priscilla, G Maria; Maidin, Siti Sarah; Yang, Qingxue
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.468

Cancer can impact individuals of all ages, including both children and adults. Diagnosing the pediatric cancer can be challenging due to its rarity. Typically, it is not recommended to screen for pediatric cancer as it may lead to potential harm to the children. One of the specialized treatments for pediatric cancer is Hematopoietic Stem Cell Transplant (HSCT). HSCT performs replacement of existing one’s blood cells with the donor’s bone marrow healthy cells. However, forecasting the survival rates following the pediatric HSCT is crucial and poses challenges in early detection. Many machine learning algorithms have been developed to predict the risk of transplant outcomes which depends on the type of disease or patient’s comorbidity. In this work, the enhancement of survival prediction for children who have undergone hematopoietic stem cell transplantation (HSCT) is achieved through the introduction of a deep learning model that is based on behavioral characteristics. The primary aim of this model is to identify and differentiate between the patterns of malignancy, non-malignancy, and hematopoietic conditions within the dataset of bone marrow transplant patients. The existing unsupervised machine learning algorithms, performs clustering of instances with the randomly selected centroids, which often results in local optima and early convergence affects the accuracy rate. Hence, the present approach introduces Chaotic mapping Harris Hawk Optimization (CHHO) in order to enhance the conventional k-means clustering procedure due to its significantly reduced computational complexity. To understand the pattern of the bone marrow transplant dataset, the deep clustering model with its ability of auto encoder and decoder, discriminates the labelled instanced. With the inferred knowledge proposed CHHO with Deep clustering Model (CHHO-DCM) performs the effective clustering of instances with the advantage of both local and global optimization. The simulation outcomes have substantiated the effectiveness of the suggested CHHO-DCM model as it attains the highest level of precision when compared to the prevailing clustering models in predicting the survival of pediatric patients during Hematopoietic Stem Cell Transplantation (HSCT).s enduring HSCT.

Title Search

Found 3 Documents Search Journal : Journal of Applied Data Sciences

Abstract

Abstract

Abstract

Title

Found 3 Documents
Search
Journal : Journal of Applied Data Sciences