Browsing by Subject "dietary habits"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    CLIQUES FOR IDENTIFICATION OF GENE SIGNATURES FOR COLORECTAL CANCER ACROSS POPULATION
    (Office of the Vice Chancellor for Research, 2012-04-13) Pradhan, Meeta P.; Nagulapalli, Kshithija; Palakal, Mathew J.
    Introduction: Colorectal cancer (CRC) is one of the most common cancers diagnosed worldwide. Studies have correlated CRC with dietary habits and environmental conditions. We developed a novel network based approach where cliques and their connectivity profiles explained the variation and similarity in CRC across four populations- China, Germany, Saudi Arabia and USA. Methods: Networks generated after data preprocessing were analyzed individually based on topological and biological features. Using greedy algorithm, cliques of various sizes were identified in each network and size 7 cliques were further analyzed based on their clique connectivity profile (CCP). Our algorithm considered the interaction of cliques based on two parameters: (i) Identification of common (links) genes; (ii) CliqueStrength. The cliques were evaluated by two conditions (a) Maximum number of common genes across cliques and highest CliqueStrength and (b) Minimum number of common genes across cliques and highest CliqueStrength. Results: Large numbers of genes are found to be common between USA, China and Germany. Highly scored nodes based on topological parameters are TP53, SRC, ESR1, SMAD3, GRB2, CREBBP, EGFR, SMAD2, and CSN2KA1. Signal transduction, protein phosphorylation etc., were found to be important GO biological processes. Number of unique size 7 cliques identified in all the population is 650. 49 common cliques identified included genes- EGFR, GRB2, PIK3R1, PTPN6, BRCA1, SMAD2, TP53, CSN2 etc. We found 20 cliques that are uniquely identified for USA, 10 for Germany and one for China. Cliques include genes that are both well studied, less-studied in CRC; but are targets in other cancers. Conclusion: With CCP, we were able to identify commonality, uniqueness and divergence among the populations. Furthermore, comparing all cliques (their CCP) as gene-signatures across populations can help to identify efficient drug targets. Results were consistent with other studies and demonstrate the power of cliques to study CRC across populations.
  • Thumbnail Image
    Item
    mmEat: Millimeter wave-enabled environment-invariant eating behavior monitoring
    (Elsevier, 2022-03) Xie, Yucheng; Jiang, Ruizhe; Guo , Xiaonan; Wang , Yan; Cheng , Jerry; Chen, Yingying; Computer Science, Luddy School of Informatics, Computing, and Engineering
    Dietary habits are closely related to people’s health condition. Unhealthy diet can cause obesity, diabetes, heart diseases, as well as increase the risk of cancers. It is necessary to have a monitoring system that helps people keep tracking his/her eating behaviors. Traditional sensor-based and camera-based dietary monitoring systems either require users to wear dedicated devices or may potentially incur privacy concerns. WiFi-based methods, though yielding reasonably robust performance in certain cases, have major limitations. The wireless signals usually carry substantial information that is specific to the environment where eating activities are performed. To overcome these limitations, we propose mmEat, a millimeter wave-enabled environment-invariant eating behavior monitoring system. In particular, we propose an environment impact mitigation method by analyzing mmWave signals in Dopper-Range domain. To differentiate dietary activities with various utensils (i.e., eating with fork, fork and knife, spoon, chopsticks, bare hand) for fine-grained eating behavior monitoring, we construct Spatial–Temporal Heatmap by integrating multiple dimensional measurements. We further utilize an unsupervised learning-based 2D segmentation method and an eating period derivation algorithm to estimate time duration of each eating activity. Our system has the potential to infer the food categories and eating speed. Extensive experiments with over 1000 eating activities show that our system can achieve dietary activity recognition with an average accuracy of 97.5% and a false detection rate of 5%.