No abstract

Most recommenders generate recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering top-K-items of high scores. Since sorting is not differentiable and is difficult to optimize with gradient descent, it is nontrivial to incorporate it in recommendation model training despite its relevance to top-K recommendations. As a result, inconsistency occurs between existing learning objectives and ranking metrics of recommenders. In this work, we present the Differentiable Ranking Metric (DRM) that mitigates the inconsistency between model training and generating top-K recommendations, aiming at improving recommendation performance by employing the differentiable relaxation of ranking metrics via joint learning. Using experiments with several real-world datasets, we demonstrate that the joint learning of the DRM objective and existing factor based recommenders significantly improves the quality of recommendations.

Early diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intelligence algorithm based on the graph convolutional network that integrates mRNA expression, DNA methylation, and DNA sequencing data. This NSCLC prediction model achieved a 93.7% macro F1-score, indicating that values for false positives and negatives were substantially low, which is desirable for accurate classification. Gene ontology enrichment and pathway analysis of features revealed that two major subtypes of NSCLC, lung adenocarcinoma and lung squamous cell carcinoma, have both specific and common GO biological processes. Numerous biomarkers (i.e., microRNA, long non-coding RNA, differentially methylated regions) were newly identified, whereas some biomarkers were consistent with previous findings in NSCLC (e.g., SPRR1B). Thus, using multi-omics data integration, we developed a promising cancer prediction algorithm.

In the tidal flats of the Nakdong Estuary, eight weirs were installed as part of the Four Major River Restoration Project in 2011, and the environment changed from a flowing stream to a still water stream. As the Nakdong River’s weir was permanently opened in February 2022, the topography and ecological environment are expected to large change. In this study, Unmanned Aerial Vehicle (UAV) photogrammetry was conducted on the tidal flats of the Nakdong Estuary in November 2021, the environment before the Nakdong River floodgates were opened. The study area was surveyed using the Network-RTK (Real-Time Kinematic) method to obtain Ground Control Point (GCP), and using an UAV, orthographic image and digital elevation model were generated for an area of 3.47 ㎢ near Jin-u island and 2.75 ㎢ near Shin-ja island. A result of spatial resolution of 1.8 cm was obtained, the result was verified using checkpoints, and results with accuracy exceeding 1 cm were obtained in both Sin-u Island and Jin-woo Island. In the future, changes in the topography and sedimentation environment of this area are expected, so it will be useful data for various research and conservation management.

Recent advances in deep learning (DL) and unmanned aerial vehicle (UAV) technologies have made it possible to monitor salt marshes more efficiently and precisely. However, studies have rarely compared the classification performance of DL with the pixel-based method for coastal wetland monitoring using UAV data. In particular, many studies have been conducted at the landscape level; however, little is known about the performance of species discrimination in very small patches and in mixed vegetation. We constructed a dataset based on UAV-RGB data and compared the performance of pixel-based and DL methods for five scenarios (combinations of annotation type and patch size) in the classification of salt marsh vegetation. Maximum likelihood, a pixel-based classification method, showed the lowest overall accuracy of 73%, whereas the U-Net classification method achieved over 90% accuracy in all classification scenarios. As expected, in a comparison of pixel-based and DL methods, the DL approach achieved the most accurate classification results. Unexpectedly, there was no significant difference in overall accuracy between the two annotation types and labeling data sizes in this study. However, when comparing the classification results in detail, we confirmed that polygon-type annotation was more effective for mixed-vegetation classification than the bounding-box type. Moreover, the smaller size of labeling data was more effective for detecting small vegetation patches. Our results suggest that a combination of UAV-RGB data and DL can facilitate the accurate mapping of coastal salt marsh vegetation at the local scale.