Factorization Machines Leveraging Lightweight Linked Open Data-Enabled Features for Top-N Recommendations

There is currently a large amount of publicly accessible structured data available as RDF data sets. For example, the Linked Open Data (LOD) cloud now consists of thousands of RDF data sets with over 30 billion triples, and the number and size of the data sets is continuously growing. Many of the data sets in the LOD cloud provide public SPARQL endpoints to allow issuing queries over them. These end-points enable users to retrieve data using precise and highly expressive SPARQL queries. However, in order to do so, the user must have sufficient knowledge about the data sets that she wishes to query, that is, the structure of data, the vocabulary used within the data set, the exact values of literals, their data types, etc. Thus, while SPARQL is powerful, it is not easy to use. An alternative to SPARQL that does not require as much prior knowledge of the data is some form of keyword search over the structured data. Keyword search queries are easy to use, but inherently ambiguous in describing structured queries. This demonstration introduces Sapphire, a system for querying RDF data that strikes a middle ground between ambiguous keyword search and difficult-to-use SPARQL. Our system does not replace either, but utilizes both where they are most effective. Sapphire helps the user construct expressive SPARQL queries that represent her information needs without requiring detailed knowledge about the queried data sets. These queries are then executed over public SPARQL endpoints from the LOD cloud. Sapphire guides the user in the query writing process by showing suggestions of query terms based on the queried data, and by recommending changes to the query based on a predictive user model.

This paper proposes an ontology matching method for aligning a source ontology with target ontologies already published and linked on the Linked Open Data (LOD) cloud. This method relies on the refinement of a set of input alignments generated by existing ontology matching methods. Since the ontologies to be aligned can be expressed in several representation languages with different levels of expressiveness and the existing ontology matching methods can only be applied to some representation languages, the first step of our method consists in applying existing matching methods to as many ontology variants as possible. We then propose to apply two main strategies to refine the initial alignment set: the removal of different kinds of ambiguities between correspondences and the use of the links published on the LOD. We illustrate our proposal in the field of life sciences and environment.

Nowadays, Linked Open Data (LOD) has grown rapidly to become large open datasets defined by RDF standards. Thanks to development of Data Web, the information on LOD is increasingly deeper, larger and easier to link in multi-domains, constituting the Linked Open Data cloud. Recently end-users applications using linked data sources as background knowledge appeared [15]. Thus, the exploitation of information on LOD effectively brings tremendous values as well as challenges. Meanwhile, Exploratory Search (ES) describes information-seeking processes that are opportunistic, iterative, and multi-tactical [7]. Furthermore, systems based on ES capitalize on new technological capabilities and interface paradigms that facilitate an increased level of interaction with information. In this paper, we present a method on searching and recommending information to empower exploratory search with semantic technologies. Our aim is to use algorithms with incorporation of structured semantics in search to give users the best related-semantic results and enhance users' interactions. We have exploited the data within LinkedMDB1 to support users in finding some information in the movie domain.

This paper presents a Spatial Keyword Preference Query (SKPQ) enhanced by Linked Open Data. This query selects objects based on the textual description of features in their neighborhood. The spatial relationship between objects and features is explored by the SKPQ using a Spatial Inverted Index. In our approach, the spatial relationship is explored using SPARQL. However, the main benefit of using SPARQL is obtained by measuring the textual relevance between features’ description and user’s keywords. The object description in Linked Open Data is much richer than traditional spatial databases, which leads to a more precise similarity measure than the one employed in the traditional SKPQ. We present an enhanced SKPQ and two experimental evaluations of the proposed approach, comparing it with the traditional SKPQ. The first conducted experiment indicate a relative NDCG improvement of the proposed approach over the traditional SKPQ of 20% when using random query keywords. The second experiment shows that using real query keywords, our approach obtained a significant increase in the MAP score.

The emergence of online social networks (OSNs) and linked open data (LOD) bring up opportunities to experiment on a new generation of cross-domain recommender systems in which the true benefit of LOD can be exploited, particularly to address the new user problems. In this article, the authors explore the feasibility of combining the two axes of comparison, similarity and relatedness, in LOD space, and introduce a new LOD-based similarity measure. The reason is to take benefit more from LOD to compare general resources, which can be useful in the context of cross-OSN recommendation. Experimental evaluation demonstrates the effectiveness of the proposed approach.

Faceted Search Over RDF-Based Knowledge Graphs

The sea surface temperature (SST) is an environmental indicator closely related to climate, weather, and atmospheric events worldwide. Its forecasting is essential for supporting the decision of governments and environmental organizations. Literature has shown that single machine learning (ML) models are generally more accurate than traditional statistical models for SST time series modeling. However, the parameters tuning of these ML models is a challenging task, mainly when complex phenomena, such as SST forecasting, are addressed. Issues related to misspecification, overfitting, or underfitting of the ML models can lead to underperforming forecasts. This work proposes using hybrid systems (HS) that combine (ML) models using residual forecasting as an alternative to enhance the performance of SST forecasting. In this context, two types of combinations are evaluated using two ML models: support vector regression (SVR) and long short-term memory (LSTM). The experimental evaluation was performed on three datasets from different regions of the Atlantic Ocean using three well-known measures: mean square error (MSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best HS based on SVR improved the MSE value for each analyzed series by 82.26%, 98.93%, and 65.03% compared to its respective single model. The HS employing the LSTM improved 92.15%, 98.69%, and 32.41% concerning the single LSTM model. Compared to literature approaches, at least one version of HS attained higher accuracy than statistical and ML models in all study cases. In particular, the nonlinear combination of the ML models obtained the best performance among the proposed HS versions.

Non-adherence to medication represents a significant concern in managing chronic conditions, resulting in poor health outcomes and increased mortality. Artificial Intelligence (AI) and Machine Learning (ML) models offer promising solutions by analyzing large datasets to improve the understanding and prediction of non-adherence. However, the dimensionality of data and associated computational costs, including environmental impact, remain a challenge in the application of AI systems. This study explores the influence of data dimensionality on the evaluation metrics and computational costs of ML models in predicting medication adherence. Utilizing adherence behaviour data collected in the BEAMER project, dimensionality reduction and Logistic Regression (LR) methods are performed. The results provide a comprehensive understanding of the models' performance after the application of Recursive Feature Elimination with Cross Validation (RFECV) and Principal Component Analysis (PCA), while also emphasizing the importance of evaluating the carbon footprint in ML models. The analysis indicates that pipelines including all variables and those incorporating RFECV present better evaluation metrics compared to those utilizing PCA, although this approach requires the least computational resources. These findings highlight the importance of tailoring project designs to their specific use cases and requirements.Clinical Relevance- This study highlights the importance of balancing accuracy, computational efficiency, interpretability and environmental impact in AI-based adherence to medication models, aiding clinicians in selecting optimal approaches for healthcare applications.

Factorization Machines (FMs) are widely used for the collaborative recommendation because of their effectiveness and flexibility in feature interaction modeling. Previous FM-based works have claimed the importance of selecting useful features since incorporating unnecessary features will introduce noise and reduce the recommendation performance. However, previous feature selection algorithms for FMs are proposed based on the i.i.d. hypothesis and select features according to their importance to the predictive accuracy on training data. However, the i.i.d. assumption is often violated in real-world applications, and shifts between training and testing sets may exist. In this paper, we consider achieving causal feature selection in FMs so as to enhance the robustness of recommendation when the distributions of training data and testing data are different. What's more, different from other machine learning tasks like image classification, which usually select a global set of causal features for a predictive model, we emphasize the importance of considering personalized causal feature selection in recommendation scenarios since the causal features for different users may be different. To achieve our goal, we propose a personalized feature selection method for FMs and refer to the confounder balancing approach to balance the confounders for every treatment feature. We conduct experiments on three real-world datasets and compare our method with both representative shallow and deep FM-based baselines to show the effectiveness of our method in enhancing the robustness of recommendations and improving the recommendation accuracy.

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

BackgroundWhile machine learning (ML) models are increasingly used to predict outcomes in health care, their practical effect on health care operations, such as bed capacity management, remains underexplored. There is a variety of traditionally used evaluation metrics to analyze ML models; however, decision makers in health care settings require a deeper understanding of their implications for resource management. Traditional performance measures often fail to provide this practical insight.MethodsIn this work, we conduct a simulation study to evaluate the impact of ML-driven length-of-stay (LOS) predictions on intensive care unit (ICU) bed capacity management. Two classification models differing in terms of explainability and interpretability, logistic regression (LR) and extreme gradient boosting (XGB), are applied to predict ICU-LOS. We use the HiRID dataset containing high-frequency data of more than 33,000 patients. The predictions of the ML models are integrated into a simulation framework that replicates real-world ICU bed management, allowing for the assessment of the practical implications of using these algorithms in a clinical setting.ResultsThe application of both classification models results in improved capacity control regarding the key performance indicators in the simulation study, with XGB outperforming LR. While LR leads to slight overoccupancy in the ICU, slight underoccupancy can be observed when XGB is applied.ConclusionOur study bridges the gap between predictive accuracy and practical application by emphasizing the importance of evaluating ML models within the context of ICU capacity management. The simulation-based approach offers a more relevant assessment for health care practitioners, providing actionable insights that go beyond classical performance measures and directly address the needs of decision makers in clinical practice.HighlightsWe apply multiple classification models for ICU-LOS prediction using time-series data. This approach enables an update of the initial prediction resulting in the possibility of efficiently managing intensive care capacities.We present a simulation-based approach to evaluate ML algorithms and their impact on bed capacity management in real-world clinical settings.Our work provides in-depth insights into the impact of using ML techniques as decision support systems in the ICU and can lead to increased acceptance in practice.

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

The Recommender System (RS) has obtained a pivotal role in e-commerce. To improve the performance of RS, review text information has been extensively utilized. However, it is still a challenge for RS to extract the most informative feature from a tremendous amount of reviews. Another significant issue is the modeling of user–item interaction, which is rarely considered to capture high- and low-order interactions simultaneously. In this paper, we design a multi-level attention mechanism to learn the usefulness of reviews and the significance of words by Deep Neural Networks (DNN). In addition, we develop a hybrid prediction structure that integrates Factorization Machine (FM) and DNN to model low-order user–item interactions as in FM and capture the high-order interactions as in DNN. Based on these two designs, we build a Multi-level Attentional and Hybrid-prediction-based Recommender (MAHR) model for recommendation. Extensive experiments on Amazon and Yelp datasets showed that our approach provides more accurate recommendations than the state-of-the-art recommendation approaches. Furthermore, the verification experiments and explainability study, including the visualization of attention modules and the review-usefulness prediction test, also validated the reasonability of our multi-level attention mechanism and hybrid prediction.

Assessing the performance of machine learning (ML) models requires careful consideration of the evaluation metrics used. It is often necessary to utilize multiple metrics to gain a comprehensive understanding of a trained model's performance, as each metric focuses on a specific aspect. However, comparing the scores of these individual metrics for each model to determine the best-performing model can be time-consuming and susceptible to subjective user preferences, potentially introducing bias. We propose the Machine Learning Cumulative Performance Score (MLcps), a novel evaluation metric for classification problems. MLcps integrates several precomputed evaluation metrics into a unified score, enabling a comprehensive assessment of the trained model's strengths and weaknesses. We tested MLcps on 4 publicly available datasets, and the results demonstrate that MLcps provides a holistic evaluation of the model's robustness, ensuring a thorough understanding of its overall performance. By utilizing MLcps, researchers and practitioners no longer need to individually examine and compare multiple metrics to identify the best-performing models. Instead, they can rely on a single MLcps value to assess the overall performance of their ML models. This streamlined evaluation process saves valuable time and effort, enhancing the efficiency of model evaluation. MLcps is available as a Python package at https://pypi.org/project/MLcps/.

Memory-aware gated factorization machine for top-N recommendation