RESUMEN

Given the challenges of inter-domain information fusion and data sparsity in collaborative filtering algorithms, this paper proposes a cross-domain information fusion matrix decomposition algorithm to enhance the accuracy of personalized recommendations in artificial intelligence recommendation systems. The study begins by collecting Douban movie rating data and social network information. To ensure data integrity, Levenshtein distance detection is employed to remove duplicate scores, while natural language processing technology is utilized to extract keywords and topic information from social texts. Additionally, graph convolutional networks are utilized to convert user relationships into feature vectors, and a unique thermal coding method is used to convert discrete user and movie information into binary matrices. To prevent overfitting, the Ridge regularization method is introduced to gradually optimize potential feature vectors. Weighted average and feature connection techniques are then applied to integrate features from different fields. Moreover, the paper combines the item-based collaborative filtering algorithm with merged user characteristics to generate personalized recommendation lists.In the experimental stage, the paper conducts cross-domain information fusion optimization on four mainstream mathematical matrix decomposition algorithms: alternating least squares method, non-negative matrix decomposition, singular value decomposition, and latent factor model (LFM). It compares these algorithms with the non-fused approach. The results indicate a significant improvement in score accuracy, with mean absolute error and root mean squared error reduced by 12.8% and 13.2% respectively across the four algorithms. Additionally, when k = 10, the average F1 score reaches 0.97, and the ranking accuracy coverage of the LFM algorithm increases by 54.2%. Overall, the mathematical matrix decomposition algorithm combined with cross-domain information fusion demonstrates clear advantages in accuracy, prediction performance, recommendation diversity, and ranking quality, and improves the accuracy and diversity of the recommendation system. By effectively addressing collaborative filtering challenges through the integration of diverse techniques, it significantly surpasses traditional models in recommendation accuracy and variety.

RESUMEN

BACKGROUND: Automated coaches (eCoach) can help people lead a healthy lifestyle (e.g., reduction of sedentary bouts) with continuous health status monitoring and personalized recommendation generation with artificial intelligence (AI). Semantic ontology can play a crucial role in knowledge representation, data integration, and information retrieval. METHODS: This study proposes a semantic ontology model to annotate the AI predictions, forecasting outcomes, and personal preferences to conceptualize a personalized recommendation generation model with a hybrid approach. This study considers a mixed activity projection method that takes individual activity insights from the univariate time-series prediction and ensemble multi-class classification approaches. We have introduced a way to improve the prediction result with a residual error minimization (REM) technique and make it meaningful in recommendation presentation with a Naïve-based interval prediction approach. We have integrated the activity prediction results in an ontology for semantic interpretation. A SPARQL query protocol and RDF Query Language (SPARQL) have generated personalized recommendations in an understandable format. Moreover, we have evaluated the performance of the time-series prediction and classification models against standard metrics on both imbalanced and balanced public PMData and private MOX2-5 activity datasets. We have used Adaptive Synthetic (ADASYN) to generate synthetic data from the minority classes to avoid bias. The activity datasets were collected from healthy adults (n = 16 for public datasets; n = 15 for private datasets). The standard ensemble algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) serve as input for the classification models. Subsequently, we re-verify the classifiers on the private MOX2-5 dataset. The performance of the ontology has been assessed with reasoning and SPARQL query execution time. Additionally, we have verified our ontology for effective recommendation generation. RESULTS: We have tested several standard AI algorithms and selected the best-performing model with optimized configuration for our use case by empirical testing. We have found that the autoregression model with the REM method outperforms the autoregression model without the REM method for both datasets. Gradient Boost (GB) classifier outperforms other classifiers with a mean accuracy score of 98.00%, and 99.00% for imbalanced PMData and MOX2-5 datasets, respectively, and 98.30%, and 99.80% for balanced PMData and MOX2-5 datasets, respectively. Hermit reasoner performs better than other ontology reasoners under defined settings. Our proposed algorithm shows a direction to combine the AI prediction forecasting results in an ontology to generate personalized activity recommendations in eCoaching. CONCLUSION: The proposed method combining step-prediction, activity-level classification techniques, and personal preference information with semantic rules is an asset for generating personalized recommendations.

Asunto(s)

RESUMEN

Given the rise of the tourism industry, there is an increasing urgency among tourists to access information about various tourist attractions. To address this challenge, innovative solutions have emerged, utilizing recommendation algorithms to offer customers personalized product recommendations. Nonetheless, existing recommendation algorithms predominantly rely on textual data, which is insufficient to harness the full potential of online tourism data. The most valuable tourism information is often found in the multi-modal data on social media, characterized by its voluminous and content-rich nature. Against this backdrop, our article posits a groundbreaking travel recommendation algorithm that leverages multi-modal data mining techniques. The proposed algorithm uses a travel recommendation platform, designed using multi-vector word sense segmentation and multi-modal data fusion, to improve the recommendation performance by introducing topic words. In our final experimental comparison, we verify the recommendation performance of the proposed algorithm on the real data set of TripAdvisor. Our proposed algorithm has the best degree of confusion with various topics. With a LOP of 20, the Precision and MAP values reach 0.0026 and 0.0089, respectively. It has the potential to better serve the tourism industry in terms of tourist destination recommendations. It can effectively mine the multi-modal data of the tourism industry to generate more excellent economic and social value.

RESUMEN

ObjectiveIn view of the standardization of clinical diagnosis and treatment of the acute abdomen and the inheritance of diagnosis and treatment experience of prestigious veteran traditional Chinese medicine（TCM） doctors， a diagnosis and treatment reasoning algorithm based on association rule mining under incomplete evidence（AMIE）+ random walk was proposed to provide information services and technical support for primary doctors by recommending personalized diagnosis and treatment plans based on medical records. MethodThe experience of diagnosis and treatment of acute abdomen of prestigious veteran TCM doctors and the text data of clinical diagnosis and treatment guidelines of integrated TCM and western medicine were collected to complete the task of knowledge extraction and construct acute abdomen knowledge graph based on Neo4j. On the basis of ontology-supported rule-based reasoning， the rule reasoning based on similar syndromes was used to expand the syndrome combinations whose Jaccard similarity was greater than the threshold in the syndrome recommendation results. The semantic path coverage algorithm was used to calculate the semantic similarity between the symptom nodes. The symptom nodes were divided into 10 categories， and the symptom nodes in the same category were extended. The random walk algorithm was used to search the symptom nodes connected with the syndrome， and the connection rules between the syndrome and symptom nodes were extended to realize the knowledge reasoning of AMIE+ random walk. ResultThe acute abdomen knowledge graph included 1 320 nodes and 2 464 relationships. According to the link prediction evaluation index of knowledge reasoning， the reasoning results of the three algorithms in the auxiliary diagnosis and treatment of acute abdomen were compared. The AMIE+ random walk algorithm complemented the knowledge graph by extending the similar syndrome connection rules and the syndrome-symptom connection rules. Compared with the knowledge reasoning algorithm based on ontology rules， the area under the curve （AUC） was 15.18% higher and the accuracy was 30.36% higher， which achieved more accurate and effective knowledge inference. ConclusionThis study used knowledge graph technology to visualize the diagnosis and treatment of acute abdomen with TCM and western medicine， assisting primary clinicians in intuitively viewing the diagnosis and treatment process and data relationship. The proposed diagnosis and treatment reasoning algorithm can realize the personalized diagnosis and treatment plan recommendation at the level of "disease-syndrome-diagnosis-treatment-prescription"， which can assist primary doctors in disease diagnosis and treatment and clinical decision-making， contribute to the knowledge sharing and application of diagnosis and treatment experience and clinical guidelines of prestigious veteran TCM doctors， improve the level of primary clinical diagnosis and treatment， and promote the normalization and standardization of the diagnosis and treatment process of acute abdomen with integrated TCM and western medicine.

RESUMEN

Under the background of information overload, the recommendation system has attracted wide attention as one of the most important means for this problem. Feature interaction considers not only the impact of each feature but also the combination of two or more features, which has become an important research field in recommendation systems. There are two essential problems in current feature interaction research. One is that not all feature interactions can generate positive gains, and some may lead to an increase in noise. The other is that the process of feature interactions is implicit and uninterpretable. In this paper, a Hierarchical Dual-level Graph Feature Interaction (HDGFI) model is proposed to solve these problems in the recommendation system. The model regards features as nodes and edges as interactions between features in the graph structure. Interaction noise is filtered by beneficial interaction selection based on a hierarchical edge selection module. At the same time, the importance of interaction between nodes is modeled in two perspectives in order to learn the representation of feature nodes at a finer granularity. Experimental results show that the proposed HDGFI model has higher accuracy than the existing models.

RESUMEN

The last decades have witnessed a vast amount of interest and research in feature representation learning from multiple disciplines, such as biology and bioinformatics. Among all the real-world application scenarios, feature extraction from knowledge graph (KG) for personalized recommendation has achieved substantial performance for addressing the problem of information overload. However, the rating matrix of recommendations is usually sparse, which may result in significant performance degradation. The crucial problem is how to extract and extend features from additional side information. To address these issues, we propose a novel feature representation learning method for the recommendation in this paper that extends item features with knowledge graph via triple-autoencoder. More specifically, the comment information between users and items is first encoded as sentiment classification. These features are then applied as the input to the autoencoder for generating the auxiliary information of items. Second, the item-based rating, the side information, and the generated comment representations are incorporated into the semi-autoencoder for reconstructed output. The low-dimensional representations of this extended information are learned with the semi-autoencoder. Finally, the reconstructed output generated by the semi-autoencoder is input into a third autoencoder. A serial connection between the semi-autoencoder and the autoencoder is designed here to learn more abstract and higher-level feature representations for personalized recommendation. Extensive experiments conducted on several real-world datasets validate the effectiveness of the proposed method compared to several state-of-the-art models.

RESUMEN

Abstract: Peer-to-peer accommodation is developing rapidly in the era of sharing economy, and the visual recommendation of accommodation is also an urgent problem to be solved. Meanwhile, user-generated content is critical in P2P accommodations, because they contain a wealth of information about the opinions and experiences of users, which helps understand consumer decisions and improve products and services better. However, the huge volume of reviews makes it difficult for potential customers to gain useful insights and for managers to track customer opinions. In this paper, we propose a complete pipeline for recommending personalized accommodations for consumers, while also providing insights for managers. First, we use topic modeling techniques to mining opinions from review. Second, we build a deep learning network for review sentiment analysis. Third, we perform sentiment analysis of the reviews at the aspect level to obtain the sentiment vector representation of the accommodation. Finally, we propose a personalized accommodation recommendation method based on the above work. Moreover, we design a visual analytic system with a user-friendly interface to facilitate interactive analysis. Evaluation including user and case studies demonstrates the usefulness and effectiveness of our method and system.

RESUMEN

Cloud computing is an attractive model that provides users with a variety of services. Thus, the number of cloud services on the market is growing rapidly. Therefore, choosing the proper cloud service is an important challenge. Another major challenge is the availability of diverse cloud services with similar performance, which makes it difficult for users to choose the cloud service that suits their needs. Therefore, the existing service selection approaches is not able to solve the problem, and cloud service recommendation has become an essential and important need. In this paper, we present a new way for context-aware cloud service recommendation. Our proposed method seeks to solve the weakness in user clustering, which itself is due to reasons such as 1) lack of full use of contextual information such as cloud service placement, and 2) inaccurate method of determining the similarity of two vectors. The evaluation conducted by the WSDream dataset indicates a reduction in the cloud service recommendation process error rate. The volume of data used in the evaluation of this paper is 5 times that of the basic method. Also, according to the T-test, the service recommendation performance in the proposed method is significant.

Asunto(s)

RESUMEN

BACKGROUND: We aimed to investigate the efficacy of the lifestyle intervention (LSI) program in controlling blood glucose regulation and health promotion in type 2 diabetic (T2D) patients. METHODS: Thirty adults with a diagnosed with diabetes were randomly assigned to LSI and control groups. The LSI group maintained their daily routines after participating twice in the LSI program, while control group maintained 4 weeks of daily life without participating in an intervention. RESULTS: HbA1c levels in the LSI group decreased significantly after participation (p = 0.025) compared with levels before the study, but there was no significant difference between the groups. The weight and body mass index (BMI) of the LSI group tended to decrease significantly compared with the control group (p = 0.054 and p = 0.055, respectively), and the waist circumference (WC) of the LSI group decreased significantly compared with that of the control group (p = 0.048). In the effects of the LSI program according to the polymorphism of GCKR genes, changes in glycated albumin (GA) (%), HbA1c, WC, BMI, and weight showed a significant decrease in the non-risk (TT genotype) GCKR group compared with the risk group (CC and TC genotype). CONCLUSION: Application of the four-week LSI program to diabetics revealed positive effects on blood-glucose control and improvement in obesity indicators. In particular, the risk group with variations in the GCKR gene was associated with more genetic effects on indicators such as blood glucose and obesity than was the non-risk group.

RESUMEN

Despite advancements in the Internet of Things (IoT) and social networks, developing an intelligent service discovery and composition framework in the Social IoT (SIoT) domain remains a challenge. In the IoT, a large number of things are connected together according to the different objectives of their owners. Due to this extensive connection of heterogeneous objects, generating a suitable recommendation for users becomes very difficult. The complexity of this problem exponentially increases when additional issues, such as user preferences, autonomous settings, and a chaotic IoT environment, must be considered. For the aforementioned reasons, this paper presents an SIoT architecture with a personalized recommendation framework to enhance service discovery and composition. The novel contribution of this study is the development of a unique personalized recommender engine that is based on the knowledge-desire-intention model and is suitable for service discovery in a smart community. Our algorithm provides service recommendations with high satisfaction by analyzing data concerning users' beliefs and surroundings. Moreover, the algorithm eliminates the prevalent cold start problem in the early stage of recommendation generation. Several experiments and benchmarking on different datasets are conducted to investigate the performance of the proposed personalized recommender engine. The experimental precision and recall results indicate that the proposed approach can achieve up to an approximately 28% higher F-score than conventional approaches. In general, the proposed hybrid approach outperforms other methods.

RESUMEN

With the development of wireless Internet and the popularity of location sensors in mobile phones, the coupling degree between social networks and location sensor information is increasing. Many studies in the Location-Based Social Network (LBSN) domain have begun to use social media and location sensing information to implement personalized Points-of-interests (POI) recommendations. However, this approach may fall short when a user moves to a new district or city where they have little or no activity history and social network friend information. Thus, a need to reconsider how we model the factors influencing a user's preferences in new geographical regions in order to make personalized and relevant recommendation. A POI in LBSNs is semantically enriched with annotations such as place categories, tags, tips or user reviews which implies knowledge about the nature of the place as well as a visiting person's interests. This provides us with opportunities to better understand the patterns in users' interests and activities by exploiting the annotations which will continue to be useful even when a user moves to unfamiliar places. In this research, we proposed a location-aware POI recommendation system that models user preferences mainly based on user reviews, which shows the nature of activities that a user finds interesting. Using this information from users' location history, we predict user ratings by harnessing the information present in review text as well as consider social influence from similar user set formed based on matching category preferences and similar reviews. We use real data sets partitioned by city provided by Yelp, to compare the accuracy of our proposed method against some baseline POI recommendation algorithms. Experimental results show that our algorithm achieves a better accuracy.

RESUMEN

Recently, researchers have been increasingly focusing on microRNAs (miRNAs) with accumulating evidence indicating that miRNAs serve as a vital role in various biological processes and dysfunctions of miRNAs are closely related with human complex diseases. Predicting potential associations between miRNAs and diseases is attached considerable significance in the domains of biology, medicine, and bioinformatics. In this study, we developed a computational model of Personalized Recommendation-based MiRNA-Disease Association prediction (PRMDA) to predict potential related miRNA for all diseases by implementing personalized recommendation-based algorithm based on integrated similarity for diseases and miRNAs. PRMDA is a global method capable of prioritizing candidate miRNAs for all diseases simultaneously. Moreover, the model could be applied to diseases without any known associated miRNAs. PRMDA obtained AUC of 0.8315 based on leave-one-out cross validation, which demonstrated that PRMDA could be regarded as a reliable tool for miRNA-disease association prediction. Besides, we implemented PRMDA on the HMDD V1.0 and HMDD V2.0 databases for three kinds of case studies about five important human cancers in order to test the performance of the model from different perspectives. As a result, 92%, 94%, 88%, 96% and 88% out of the top 50 candidate miRNAs predicted by PRMDA for Colon Neoplasms, Esophageal Neoplasms, Lymphoma, Lung Neoplasms and Breast Neoplasms, respectively, were confirmed by experimental reports.