Hot news recommendation system from heterogeneous websites based on bayesian model.
Ontology highlight
ABSTRACT:
SUBMITTER: Xia Z
PROVIDER: S-EPMC4100368 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:To extract finer-grained segment features from news and represent users accurately and exhaustively, this article develops a news recommendation (NR) model based on a sub-attention news encoder. First, by using convolutional neural network (CNN) and sub-attention mechanism, this model extracts a rich feature matrix from the news text. Then, from the perspective of image position and channel, the granular image data is retrieved. Next, the user's news browsing history is injected with a multi-head self-attention mechanism, and time series prediction is applied to the user's interests. Finally, the experimental results show that the proposed model performs well on the indicators: mean reciprocal rank (MRR), Normalized Discounted Cumulative Gain (NDCG) and area under the curve (AUC), with an average increase of 4.18%, 5.63% and 6.55%, respectively. The comparative results demonstrate that the model performs best on a variety of datasets and has fastest convergence speed in all cases. The proposed model may provide guidance for the design of the news recommendation system in the future.
| S-EPMC10280677 | biostudies-literature
Project description:In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.
| S-EPMC8725661 | biostudies-literature
Project description:Deep learning, a subset of artificial intelligence, gives easy way for the analytical and physical tasks to be done automatically. There is a less necessity for human intervention while performing these tasks. Deep hybrid learning is a blended approach to combine machine learning with deep learning. A hybrid deep learning (HDL) model using convolutional neural network (CNN), residual network (ResNet) and long short term memory (LSTM) is proposed for better course selection of the enrolled candidates in an online learning platform. In this work, a hybrid framework that facilitates the analysis and design of a recommendation system for course selection is developed. A student's schedule for the next course should consist of classes in which the student has shown interest. For universities to schedule classes optimally, they need to know what courses each student wants to take before each course begins. The proposed recommendation system selects the most appropriate course that can encourage students to base their selection on informed decision making. This system will enable learners to obtain the correct choices of courses to be studied.
| S-EPMC10703022 | biostudies-literature
Project description:BackgroundAn increasing number of people are visiting hospital websites to seek better services and treatments compared to the past. It is therefore important for hospitals to develop websites to meet the needs of their patients. However, few studies have investigated whether and how the current hospital websites meet the patient's needs. Above all, in radiation departments, it may be difficult for patients to obtain the desired information regarding modality and diagnosis because such information is subdivided when described on a website.ObjectiveThe purpose of this study is to suggest a hospital website search behavior model by analyzing the browsing behavior model using a Bayesian network from the perspective of one-to-one marketing.MethodsFirst, we followed the website access log of Hokkaido University Hospital, which was collected from September 1, 2016, to August 31, 2017, and analyzed the access log using Google Analytics. Second, we specified the access records related to radiology from visitor browsing pages and keywords. Third, using these resources, we structured 3 Bayesian network models based on specific patient needs: radiotherapy, nuclear medicine examination, and radiological diagnosis. Analyzing each model, this study considered why some visitors could not reach their desired page and improvements to meet the needs of visitors seeking radiology-related information.ResultsThe radiotherapy model showed that 74% (67/90) of the target visitors could reach their requested page, but only 2% (2/90) could reach the Center page where inspection information, one of their requested pages, is posted. By analyzing the behavior of the visitors, we clarified that connecting with the radiotherapy and radiological diagnosis pages is useful for increasing the proportion of patients reaching their requested page.ConclusionsWe proposed solutions for patient web-browsing accessibility based on a Bayesian network. Further analysis is necessary to verify the accuracy of the proposed model in comparison to other models. It is expected that information provided on hospital websites will be improved using this method.
| S-EPMC7854043 | biostudies-literature
Project description:MotivationWe propose a drug recommendation model that integrates information from both structured data (patient demographic information) and unstructured texts (patient reviews). It is based on multitask learning to predict review ratings of several satisfaction-related measures for a given medicine, where related tasks can learn from each other for prediction. The learned models can then be applied to new patients for drug recommendation. This is fundamentally different from most recommender systems in e-commerce, which do not work well for new customers (referred to as the cold-start problem). To extract information from review texts, we employ both topic modeling and sentiment analysis. We further incorporate variable selection into the model via Bayesian LASSO, which aims to filter out irrelevant features. To our best knowledge, this is the first Bayesian multitask learning method for ordinal responses. We are also the first to apply multitask learning to medicine recommendation. The sample code and data are made available at GitHub: https://github.com/thrushcyc-github/BMull.ResultsWe evaluate the proposed method on two sets of drug reviews involving 17 depression/high blood pressure-related drugs. Overall, our method performs better than existing benchmark methods in terms of accuracy and AUC (area under the receiver operating characteristic curve). It is effective even with a small sample size and only a few available features, and more robust to possible noninformative covariates. Due to our model explainability, insights generated from our model may work as a useful reference for doctors. In practice, however, a final decision should be carefully made by combining the information from the proposed recommender with doctors' domain knowledge and past experience.Availability and implementationThe sample code and data are publicly available at GitHub: https://github.com/thrushcyc-github/BMull.
| S-EPMC10425196 | biostudies-literature
Project description:Heterogeneous nucleation processes are involved in many important phenomena in nature, including devastating human diseases caused by amyloid structures or the harmful frost formed on fruits. However, understanding them is challenging due to the difficulties of characterizing the initial stages of the process occurring at the interface between the nucleation medium and the substrate surfaces. This work implements a model system based on gold nanoparticles to investigate the effect of particle surface chemistry and substrate properties on heterogeneous nucleation processes. Using widely available techniques such as UV-vis-NIR spectroscopy and light microscopy, gold nanoparticle-based superstructure formation was studied in the presence of substrates with different hydrophilicity and electrostatic charges. The results were evaluated on grounds of classical nucleation theory (CNT) to reveal kinetic and thermodynamic contributions of the heterogeneous nucleation process. In contrast to nucleation from ions, the kinetic contributions toward nucleation turned out to be larger than the thermodynamic contributions for the nanoparticle building blocks. Electrostatic interactions between substrates and nanoparticles with opposite charges were crucial to enhancing the nucleation rates and decreasing the nucleation barrier of superstructure formation. Thereby, the described strategy is demonstrated advantageous for characterizing physicochemical aspects of heterogeneous nucleation processes in a simple and accessible manner, which could be potentially explored to study more complex nucleation phenomena.
| S-EPMC10018769 | biostudies-literature
Project description:Today, due to the expansion of the Internet and social networks, people are faced with a vast amount of dynamic information. To mitigate the issue of information overload, recommender systems have become pivotal by analyzing users' activity histories to discern their interests and preferences. However, most available social image recommender systems utilize a static strategy, meaning they do not adapt to changes in user preferences. To overcome this challenge, our paper introduces a dynamic image recommender system that leverages a deep reinforcement learning (DRL) framework, enriched with a novel set of features including emotion, style, and personality. These features, uncommon in existing systems, are instrumental in crafting a user's characteristic vector, offering a personalized recommendation experience. Additionally, we overcome the challenge of state representation definition in reinforcement learning by introducing a new state representation. The experimental results show that our proposed method, compared to some related works, significantly improves Recall@k and Precision@k by approximately 7%-10% (for the top 100 images recommended) for personalized image recommendation.
| S-EPMC10994284 | biostudies-literature
Project description:BackgroundLocus heterogeneity, wherein a disease can be caused in different individuals by different genes and/or environmental factors, is a ubiquitous feature of complex traits. A Bayesian approach has been proposed to account for variable rates of heterogeneity across families in a parametric linkage analysis setup [Biswas and Lin: J Am Stat Assoc 2006;101:1341-1351]. As with any parametric approach, its application requires specification of the disease model, which limits its practical utility.MethodsWe address this limitation by proposing a Bayesian model averaging (BMA) approach. We consider a finite number of disease models and treat the model as an unknown parameter. In practice, we use simple single-locus disease models as various categories for model.ResultsOur simulations as well as analysis of Genetic Analysis Workshop 13 simulated data show that BMA retains at least 80% of the power that is obtained by analyzing under the true disease model. The coverage probability of interval for disease gene is maintained around the nominal level. Finally, we apply BMA to a Late-Onset Alzheimer's Disease dataset and find evidence for linkage on chromosomes 19, 9, and 21.ConclusionWe conclude that the BMA approach utilizing simple single-locus models for averaging is effective for mapping heterogeneous traits.
| S-EPMC2889260 | biostudies-literature
Project description:MotivationMetabolomics has shown great potential to improve the understanding of complex diseases, potentially leading to therapeutic target identification. However, no single analytical method allows monitoring all metabolites in a sample, resulting in incomplete metabolic fingerprints. This incompleteness constitutes a stumbling block to interpretation, raising the need for methods that can enrich those fingerprints. We propose MetaboRank, a new solution inspired by social network recommendation systems for the identification of metabolites potentially related to a metabolic fingerprint.ResultsMetaboRank method had been used to enrich metabolomics data obtained on cerebrospinal fluid samples from patients suffering from hepatic encephalopathy (HE). MetaboRank successfully recommended metabolites not present in the original fingerprint. The quality of recommendations was evaluated by using literature automatic search, in order to check that recommended metabolites could be related to the disease. Complementary mass spectrometry experiments and raw data analysis were performed to confirm these suggestions. In particular, MetaboRank recommended the overlooked ?-ketoglutaramate as a metabolite which should be added to the metabolic fingerprint of HE, thus suggesting that metabolic fingerprints enhancement can provide new insight on complex diseases.Availability and implementationMethod is implemented in the MetExplore server and is available at www.metexplore.fr. A tutorial is available at https://metexplore.toulouse.inra.fr/com/tutorials/MetaboRank/2017-MetaboRank.pdf.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6330003 | biostudies-literature
Project description:Following the publication of our paper regarding a population-based model of doxorubicin pharmacokinetics in children in Clinical Pharmacokinetics last year (Voller et al. 54:1139-1149, 2015), we have received many inquiries on the practical clinical consequences of this model; however, a population-based model is only one of the aspects to be taken into account when developing dosing algorithms. In addition, any new method of dose calculation would need clinical validation and, subsequently, a new clinical trial. However, such a trial, especially with regard to burden to the children involved, requires optimal preparation and the selection of the best hypotheses. The European Paediatric Oncology Off-Patent Medicines Consortium (EPOC), represented by the authors, would therefore like to initiate an interdisciplinary discussion on the clinical and pharmacological goals for dose calculation. This current opinion summarizes the existing knowledge on the pharmacokinetics and pharmacodynamics of doxorubicin. Our aim was to define the clinical needs as precisely as possible, with the intention of stimulating discussion between the clinical pediatric oncologist and the pediatric pharmacologist. By doing so, we hope to define surrogates for best practice of a common doxorubicin dose in children. The intent is for a trial to validate a rational dose calculation rule, leading to a regulatory process and subsequent labeling.
| S-EPMC5315724 | biostudies-literature