Interactive Dimensionality Reduction for Comparative Analysis

Exploratory insights into prefrontal cortex activity in continuous glucose monitoring: findings from a portable wearable functional near-infrared spectroscopy system

The escalating global prevalence of diabetes highlights an urgent need for advancements in continuous glucose monitoring (CGM) technologies that are non-invasive, accurate, and user-friendly. Here, we introduce a groundbreaking portable wearable functional near-infrared spectroscopy (fNIRS) system designed to monitor glucose levels by assessing prefrontal cortex (PFC) activity. Our study delineates the development and application of this novel fNIRS system, emphasizing its potential to revolutionize diabetes management by providing a non-invasive, real-time monitoring solution. Fifteen healthy university students participated in a controlled study, where we monitored their PFC activity and blood glucose levels under fasting and glucose-loaded conditions. Our findings reveal a significant correlation between PFC activity, as measured by our fNIRS system, and blood glucose levels, suggesting the feasibility of fNIRS technology for CGM. The portable nature of our system overcomes the mobility limitations of traditional setups, enabling continuous, real-time monitoring in everyday settings. We identified 10 critical features related to blood glucose levels from extensive fNIRS data and successfully correlated PFC function with blood glucose levels by constructing predictive models. Results show a positive association between fNIRS data and blood glucose levels, with the PFC exhibiting a clear response to blood glucose. Furthermore, the improved regressive rule principal component analysis (PCA) method outperforms traditional PCA in model prediction. We propose a model validation approach based on leave-one-out cross-validation, demonstrating the unique advantages of K-nearest neighbor (KNN) models. Comparative analysis with existing CGM methods reveals that our paper's KNN model exhibits lower RMSE and MARD at 0.11 and 8.96%, respectively, and the fNIRS data were highly significant positive correlation with actual blood glucose levels (r = 0.995, p < 0.000). This study provides valuable insights into the relationship between metabolic states and brain activity, laying the foundation for innovative CGM solutions. Our portable wearable fNIRS system represents a significant advancement in effective diabetes management, offering a promising alternative to current technologies and paving the way for future advancements in health monitoring and personalized medicine.

Dimension Reduction With Prior Information for Knowledge Discovery

This paper addresses the problem of mapping high-dimensional data to a low-dimensional space, in the presence of other known features. This problem is ubiquitous in science and engineering as there are often controllable/measurable features in most applications. To solve this problem, this paper proposes a broad class of methods, which is referred to as conditional multidimensional scaling (MDS). An algorithm for optimizing the objective function of conditional MDS is also developed. The convergence of this algorithm is proven under mild assumptions. Conditional MDS is illustrated with kinship terms, facial expressions, textile fabrics, car-brand perception, and cylinder machining examples. These examples demonstrate the advantages of conditional MDS over conventional dimension reduction in improving the estimation quality of the reduced-dimension space and simplifying visualization and knowledge discovery tasks. Computer codes for this work are available in the open-source cml R package.

Sparse discriminant PCA based on contrastive learning and class-specificity distribution

Much mathematical effort has been devoted to developing Principal Component Analysis (PCA), which is the most popular feature extraction method. To suppress the negative effect of noise on PCA performance, there have been extensive studies and applications of a large number of robust PCAs achieving outstanding results. However, existing methods suffer from at least two shortcomings: (1) They expressed PCA as a reconstruction model measured by Euclidean distance, which only considers the relationship between the data and its reconstruction and ignores the differences between different data points; (2) They did not consider the class-specificity distribution information contained in the data itself, thus lacking discriminative properties. To overcome the above problems, we propose a Sparse Discriminant Principal Components Analysis (SDPCA) model based on contrastive learning and class-specificity distribution. Specifically, we use contrastive learning to measure the relationship between samples and their reconstructions, which fully takes the discriminative information between data into account in PCA. In order to make the extracted low-dimensional features profoundly reflect the class-specificity distribution of the data, we minimize the squared ℓ1,2-norm of the low-dimensional embedding. In addition, to reduce the effects of redundant features and noise and to improve the interpretability of PCA at the same time, we impose sparsity constraints on the projection matrix using the squared ℓ1,2-norm. Our experimental results on different types of benchmark databases demonstrate that our model has state-of-the-art performance.

Contrastive multiple correspondence analysis (cMCA): Using contrastive learning to identify latent subgroups in political parties

Scaling methods have long been utilized to simplify and cluster high-dimensional data. However, the general latent spaces across all predefined groups derived from these methods sometimes do not fall into researchers' interest regarding specific patterns within groups. To tackle this issue, we adopt an emerging analysis approach called contrastive learning. We contribute to this growing field by extending its ideas to multiple correspondence analysis (MCA) in order to enable an analysis of data often encountered by social scientists-containing binary, ordinal, and nominal variables. We demonstrate the utility of contrastive MCA (cMCA) by analyzing two different surveys of voters in the U.S. and U.K. Our results suggest that, first, cMCA can identify substantively important dimensions and divisions among subgroups that are overlooked by traditional methods; second, for other cases, cMCA can derive latent traits that emphasize subgroups seen moderately in those derived by traditional methods.

A Predictive Visual Analytics System for Studying Neurodegenerative Disease Based on DTI Fiber Tracts

Diffusion tensor imaging (DTI) has been used to study the effects of neurodegenerative diseases on neural pathways, which may lead to more reliable and early diagnosis of these diseases as well as a better understanding of how they affect the brain. We introduce a predictive visual analytics system for studying patient groups based on their labeled DTI fiber tract data and corresponding statistics. The system's machine-learning-augmented interface guides the user through an organized and holistic analysis space, including the statistical feature space, the physical space, and the space of patients over different groups. We use a custom machine learning pipeline to help narrow down this large analysis space and then explore it pragmatically through a range of linked visualizations. We conduct several case studies using DTI and T1-weighted images from the research database of Parkinson's Progression Markers Initiative.

The visual design of urban multimedia portals

In the visual design of a portal website, color is the first intuitive factor for users. It is relatively difficult for the designer of a city portal website to choose a color system that represents a city's unique color from among the many available options. Therefore, this study extracted a decision-making model of the urban color system, which can help decision-makers and designers choose among color systems, and then effectively design a portal website that conforms to local cultural attributes. The proposed method to solve the problem involved obtaining optimal color matching by performing weight analysis of colors through 123 sample color semantics, factor analysis, and a fuzzy analytic hierarchy process. Semantic analysis was used to classify colors into four categories of fashion, technology, calm, and dazzling. The fashion color matching scheme scored relatively high. Web page color matching schemes with a white background were popular, among which a white and green color matching scheme scored relatively high. At the same time, there are differences in color preferences between genders and cultures. This study is significant because it proposes a color decision model for portal websites, which provides a reference value that can also be applied to the selection of color schemes for other types of web pages in the future.