Reducing Dimensionality of Data Using Autoencoders

Janakiramaiah, B.; Kalyani, G.; Narayana, S.; Krishna, T. Bala Murali

doi:10.1007/978-981-32-9690-9_6

Cited by 5 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Even with the reduced number of features, clustering the remaining high-dimensional dataset is problematic due to lack of scalability of clustering methods. To address this problem, we explored dimension reduction methods (see Methods ), and focus on the well-established method PCA, and a more recent approached based on deep-learning using auto encoders (AE) [ 14 ]. An important tuning parameter for these methods is the number of reduced dimensions (i.e., number of PCs, number of AE embeddings).…”

Section: Resultsmentioning

confidence: 99%

Multi-omics subtyping pipeline for chronic obstructive pulmonary disease

et al. 2021

View full text Add to dashboard Cite

Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of mortality in the United States; however, COPD has heterogeneous clinical phenotypes. This is the first large scale attempt which uses transcriptomics, proteomics, and metabolomics (multi-omics) to determine whether there are molecularly defined clusters with distinct clinical phenotypes that may underlie the clinical heterogeneity. Subjects included 3,278 subjects from the COPDGene cohort with at least one of the following profiles: whole blood transcriptomes (2,650 subjects); plasma proteomes (1,013 subjects); and plasma metabolomes (1,136 subjects). 489 subjects had all three contemporaneous -omics profiles. Autoencoder embeddings were performed individually for each -omics dataset. Embeddings underwent subspace clustering using MineClus, either individually by -omics or combined, followed by recursive feature selection based on Support Vector Machines. Clusters were tested for associations with clinical variables. Optimal single -omics clustering typically resulted in two clusters. Although there was overlap for individual -omics cluster membership, each -omics cluster tended to be defined by unique molecular pathways. For example, prominent molecular features of the metabolome-based clustering included sphingomyelin, while key molecular features of the transcriptome-based clusters were related to immune and bacterial responses. We also found that when we integrated the -omics data at a later stage, we identified subtypes that varied based on age, severity of disease, in addition to diffusing capacity of the lungs for carbon monoxide, and precent on atrial fibrillation. In contrast, when we integrated the -omics data at an earlier stage by treating all data sets equally, there were no clinical differences between subtypes. Similar to clinical clustering, which has revealed multiple heterogenous clinical phenotypes, we show that transcriptomics, proteomics, and metabolomics tend to define clusters of COPD patients with different clinical characteristics. Thus, integrating these different -omics data sets affords additional insight into the molecular nature of COPD and its heterogeneity.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-omics subtyping pipeline for chronic obstructive pulmonary disease

et al. 2021

View full text Add to dashboard Cite

show abstract

“…According to Fournier and Aloise [9], working with a large number of dimensions in the feature space causes the volume of the data space to increase exponentially fast with the dimension and, therefore, the data becomes sparse. This problem, called curse of dimensionality, leads to the problem of overfitting as the machine learning model can easily get an accurate solution due to the data sparseness [10]. In order to tackle this problem, high-dimensional data can be projected into a lower-dimensional or latent space using different linear or non-linear techniques.…”

Section: A Autoencoder-based Dimensionality Reductionmentioning

confidence: 99%

Standard Latent Space Dimension for Network Intrusion Detection Systems Datasets

et al. 2023

View full text Add to dashboard Cite

Machine learning is a branch of artificial intelligence that provides computers the ability to create or improve algorithms without being explicitly programmed by directly learning from data. It is widely used in automation or decision-making tasks in fields such as image or speech recognition, sentiment analysis, or self-driving cars. However, its application in the field of communication networks is limited by the lack of appropriate research resources, such as rich datasets for training or the definition of a standard set of features. In this context, a standard latent space dimension is proposed by performing an autoencoder-based dimensionality reduction process. Different network security datasets are projected onto a lower-dimensional space to determine a standard or convergent dimension. The convergent dimension is determined by identifying the threshold above which diminishing returns begin to occur in the autoencoder loss as the latent space dimension increases. The experimental validation showed that four machine learning classification models, trained with a standard latent space of ten dimensions, performed as well as the models that used the non-reduced versions of the datasets in terms of F1-score and accuracy. Furthermore, a Wilcoxon statistical test showed that the mean accuracy of all classification models trained with the standard latent space dimension had a difference of less than 0.0235 in comparison to the models trained with the original inputs. A negligible difference in accuracy is a significant outcome because researchers can use only the latent space to perform experiments with certainty that the performance of ML models will not be constrained.

show abstract

“…AEs are Neural Networks with the same input and output dimensions, which are trained to compress the input into a lower-dimensional space (also called latent space), in such a way that the input can again be recovered from the latent space with minimal error [4]. In the literature, AEs have been used for several applications, including dimensionality reduction [5] and detection of errors and anomalies [6]- [8].…”

Section: A Autoencoders For Snr Estimationmentioning

confidence: 99%

Machine Learning-Based Characterization of SNR in Digital Satellite Communication Links

Dhuyvetters

Delaruelle²,

Rogier

et al. 2021

2021 15th European Conference on Antennas and Propagation (EuCAP)

View full text Add to dashboard Cite

Signals traveling through a Satellite Communication (SatCom) channel are subject to noise and interference effects, impacting their Signal-to-Noise ratio (SNR). Furthermore, nonlinear distortion arising from the nonlinear characteristic of the amplifiers in the system also adversely impacts performance. Current state-of-the-art techniques estimate these effects by including a sequence of known pilot symbols in the transmitted signals. While robust, a downside of these approaches is that pilot symbols do not include useful information, thus introducing overhead. This paper presents a Machine Learning (ML) approach to characterize the SNR, using the received signal in the return link of SatCom systems, independent of the signal's distortion level and without relying on pilot symbols. The proposed technique is validated through a suitable application example: the characterization of SNR in a SatCom system using a 16-APSK modulation scheme.

show abstract

Reducing Dimensionality of Data Using Autoencoders

Cited by 5 publications

References 4 publications

Multi-omics subtyping pipeline for chronic obstructive pulmonary disease

Multi-omics subtyping pipeline for chronic obstructive pulmonary disease

Standard Latent Space Dimension for Network Intrusion Detection Systems Datasets

Machine Learning-Based Characterization of SNR in Digital Satellite Communication Links

Contact Info

Product

Resources

About