No abstract

No abstract

Current music recommender systems typically act in a greedy manner by recommending songs with the highest user ratings. Greedy recommendation, however, is suboptimal over the long term: it does not actively gather information on user preferences and fails to recommend novel songs that are potentially interesting. A successful recommender system must balance the needs to explore user preferences and to exploit this information for recommendation. This article presents a new approach to music recommendation by formulating this exploration-exploitation trade-off as a reinforcement learning task. To learn user preferences, it uses a Bayesian model that accounts for both audio content and the novelty of recommendations. A piecewise-linear approximation to the model and a variational inference algorithm help to speed up Bayesian inference. One additional benefit of our approach is a single unified model for both music recommendation and playlist generation. We demonstrate the strong potential of the proposed approach with simulation results and a user study.

Accumulating evidence indicates that microRNAs are implicated in tumor initiation and progression through negatively regulating oncogenes or tumor suppressor genes. In the present study, we report that the expression of miR-200a was significantly lower in renal cell carcinoma (RCC) specimens and RCC cell lines. Restoration of miR-200a suppressed cell growth, arrested cell cycle progression, and promoted cell apoptosis in RCC cell lines. We next used qRT-PCR array technology to identify Sirtuin 1 (SIRT1) as one of the downregulated proteins during miR-200a overexpression in 786-O cells. Following a further assay by luciferase reporter system, SIRT1 was validated as a direct target of miR-200a. Moreover, siRNA-mediated knockdown of SIRT1 could partially phenocopy the effects of miR-200a overexpression. In contrast, overexpression of truncated SIRT1 (without an endogenous 3'-UTR) could rescue the effect of miR-200a overexpression on 786-O cells, which suggested that SIRT1 3'-UTR is targeted by miR-200a specifically. These observations provide further evidence for a critical tumor-suppressive role of the miR-200a in RCC in addition to identifying a novel regulatory mechanism, which may contribute to SIRT1 upregulation in RCC.

Based on 35-yr (1982-2016) best track and Statistical Hurricane Intensity Prediction Scheme data, this study examined climatology of rapidly intensifying (RI) and slowly intensifying (SI) events as well as their time evolutions of storm-related, and environmental parameters for tropical cyclones (TCs) in both North Atlantic (AL) and Eastern North Pacific (EP) basins. Major hurricanes were intensified mainly through RI while tropical depression and tropical storms through SI. The percentage of TCs that underwent RI peaks in the late hurricane season while that underwent SI peaks early. For the first time in the literature, this study found that RI events have significantly different storm-related and environmental characteristics than SI events for before-, during-, and after-event stages. In both AL and EP basins, RI events always intensify significantly faster during the previous 12 hours, locate further south, and have warmer sea surface and 200 hPa temperatures, greater ocean heat content, larger 200 hPa divergence, weaker vertical wind shear, and weaker 200 hPa westerly flow than SI events for all event-relative stages. In the AL basin, RI events have larger low-level and mid-level relative humidity and larger 850 hPa relative vorticity than SI events for all event-relative stages in the AL and most event-relative stages in the EP. RI events are associated with more convectively unstable atmosphere and further away from their maximum potential intensities than SI events for most event-relative stages in the AL and for all event-relative stages in the EP.

Social tagging can provide rich semantic information for largescale retrieval in music discovery. Such collaborative intelligence, however, also generates a high degree of tags unhelpful to discovery, some of which obfuscate critical information. Towards addressing these shortcomings, tag recommendation for more robust music discovery is an emerging topic of significance for researchers. However, current methods do not consider diversity of music attributes, often using simple heuristics such as tag frequency for filtering out irrelevant tags. Music attributes encompass any number of perceived dimensions, for instance vocalness, genre, and instrumentation. Many of these are underrepresented by current tag recommenders. We propose a scheme for tag recommendation using Explicit Multiple Attributes based on tag semantic similarity and music content. In our approach, the attribute space is explicitly constrained at the outset to a set that minimizes semantic loss and tag noise, while ensuring attribute diversity. Once the user uploads or browses a song, the system recommends a list of relevant tags in each attribute independently. To the best of our knowledge, this is the first method to consider Explicit Multiple Attributes for tag recommendation. Our system is designed for large-scale deployment, on the order of millions of objects. For processing largescale music data sets, we design parallel algorithms based on the MapReduce framework to perform large-scale music content and social tag analysis, train a model, and compute tag similarity. We evaluate our tag recommendation system on CAL-500 and a largescale data set (N = 77, 448 songs) generated by crawling Youtube and Last.fm. Our results indicate that our proposed method is both effective for recommending attribute-diverse relevant tags and efficient at scalable processing.

No abstract

No abstract