Multi-Dimension Projection for Non-Linear Data Via Spearman Correlation Analysis (MD-SCA)

Khokhar, Muhammad Saddam; Cheng, Kang; Ayoub, Misbah; Zakria,; Eric, Lubamba Kasangu

doi:10.1109/icict47744.2019.9001973

Cited by 8 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The experiment divided into four major tasks. Start with the two-dimensional images [31] as an input, Deep learning models extracts the features via inception V-3 and Openface model. Along with transfer learning approach [32], The features used in PSO for selects the best feature among all extracted features individually.…”

Section: Methodology or Experimentsmentioning

confidence: 99%

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Khokhar¹,

Ayoub²,

Jamali³

et al. 2021

JISR-C

Self Cite

View full text Add to dashboard Cite

Face plays a vital role in the Recognition or Re-Identification of a person. Therefore, it is significant to identify and extract the facial visual features that automatically lead to face identification-based classification. Facial features comprise different ways of detection, for instance, they could be located at corners or midpoints of the facial features that rely on multiple components such as eyes, lips, nose with different emotions and expressions used in face recognition. This paper introduced a robust and efficient deep learning model with the use of a transfer learning approach for PSO for extraction and selection of the best facial features. Deep learning models “Openface via PSO and introduced customized Inception-V3 model via PSO is used and present detailed comparative accuracy of both models in terms of classification recognition. For this, the paper presents seven different algorithms to evaluate the efficiency of the model with four different face databases. It is evident from the result; neural network classifier shows a gradual hike to calculate accuracy with the proposed PSO-based OpenFace deep learning approach. On the other hand, random forest and AdaBoost algorithm were observed most compatible with the customized PSO-based Inception-V3 model.

show abstract

Section: Methodology or Experimentsmentioning

confidence: 99%

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Khokhar¹,

Ayoub²,

Jamali³

et al. 2021

JISR-C

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the testing, three trained models will give the inference result out of the voting weight average of the individual output of each meta learner, as shown in Figure 10. The time complexity of this computation of the HMM, VAE, and BLSTM is O(nlog n ), O n 2 , and O n 4 , where n is the number of multiplications of each unit in this case.…”

Section: Chipping Prediction Modelmentioning

confidence: 99%

Ensemble Meta-Learning-Based Robust Chipping Prediction for Wafer Dicing

Chang,

Tsai,

2024

Electronics

View full text Add to dashboard Cite

Our previous study utilized importance analysis, random forest, and Barnes–Hut t-SNE dimensionality reduction to analyze critical dicing parameters and used bidirectional long short-term memory (BLSTM) to predict wafer chipping occurrence successfully in a single dicing machine. However, each dicing machine of the same type may produce unevenly distributed non-IID dicing signals, which may lead to the undesirable result that a pre-trained model trained by dicing machine #1 could not effectively predict chipping occurrence in dicing machine #2. Therefore, regarding the model robustness, this study introduces an ensemble meta-learning-based model that can evaluate many dicing machines for chipping prediction with high stability and accuracy. This approach constructs several base learners, such as the hidden Markov model (HMM), the variational autoencoder (VAE), and BLSTM, to form an ensemble learning. We use model-agnostic meta-learning (MAML) to train and test the ensemble learning model by several prediction tasks from machine #1. After MAML learning, we call the trained model a meta learner. Then, we successfully apply a retrieved data set from machine #2 to the meta learner for training and testing wafer chipping occurrence in this machine. As a result, our contribution to the robust chipping prediction on cross-machines can improve the yield of wafer dicing with a prediction accuracy of 93.21%, preserve the practical wearing of dicing kerfs, and significantly cut wafer manufacturing costs.

show abstract

“…A Spearman correlation, also known as a Spearman's rank correlation coefficient (Spearman's rho), is a statistical measure used to evaluate the strength and direction of a monotonic relationship between two variables [79]. A Spearman correlation is suited for both linear and non-linear monotonic correlations, unlike a Pearson correlation, which only evaluates linear relationships [80]. In a Spearman correlation analysis, the two variables of interest should be ordinal, interval, or ratio data, as a Spearman correlation is not appropriate for nominal data.…”

Section: Spearman Correlation Analysismentioning

confidence: 99%

Evaluating the Impact of Environmental Performance and Socioeconomic and Demographic Factors on Land Use and Land Cover Changes in Kibira National Park, Burundi

Nyirarwasa,

Han,

Yang

et al. 2024

Sustainability

View full text Add to dashboard Cite

In Kibira National Park, Burundi, socioeconomic and demographic factors lead to environmental performance challenges that impede biodiversity; thus, understanding the impact of these determinants on land use and land cover change is important to address these challenges. In this study, a multivariate analysis of variance (MANOVA) model was used to quantify the impact of socioeconomic and demographic factors on land cover/land use (LCLU) changes using Landsat images captured between 1990 and 2021. In addition, the impact of the environmental performance index (EPI), particularly ecosystem vitality (ECO), on landscape fragmentation was examined using a Spearman correlation analysis. A Pearson correlation analysis and a principal component analysis (PCA) were used to investigate the connections between the indicators of relevance in this study. The results reveal a decrease in forestland from 86.1% to 81.32%, a decrease in water bodies from 0.352% to 0.178%, and a decrease in open land from 2.124% to 1.134%, whereas grassland increased from 11.43% to 17.37% between 1990 and 2021. The landscape fragmentation in the edge density, contagion (CONTAG), largest patch index (LPI), number of patches (NP), and patch density (PD) was reduced in 2011 but increased again from 2016 to 2021, when only the ED fragmentation continued to decrease. The MANOVA results show that the rural population had a significant impact on LCLU changes at the 5% level of significance. Demographic factors significantly contributed to changes in grassland and forestland at a probability of 5%. In addition, moderately significant connections were observed between population growth per year and water and between gross domestic product (GDP) and grassland at the 10% level. ECO issues in ecosystem services (ECSs) were statistically significant for the increased fragmentation metrics, while biodiversity and habitat (BDH) were important for reducing the edge density (ED) at a 5% level of significance. The Pearson correlations showed a substantial positive relationship between the socioeconomic and demographic components, whereas a negative connection was found between the forestland and BDH indicators. These findings are essential for understanding the significant drivers of LCLU changes and the influence of environmental performance on the landscape pattern.

show abstract

Multi-Dimension Projection for Non-Linear Data Via Spearman Correlation Analysis (MD-SCA)

Cited by 8 publications

References 9 publications

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Ensemble Meta-Learning-Based Robust Chipping Prediction for Wafer Dicing

Evaluating the Impact of Environmental Performance and Socioeconomic and Demographic Factors on Land Use and Land Cover Changes in Kibira National Park, Burundi

Contact Info

Product

Resources

About