Search Results (24)

Move method refactoring (MMR) is one of the most commonly used software maintenance techniques to improve feature envy. Existing works focus on how to identify and recommend MMR. However, little is known about how MMR impacts program performance. There is a gap in knowledge regarding MMR and its performance impact. To address this gap, this paper proposes MovePerf, a novel approach to predicting performance for MMR based on deep learning and feature interaction. On the one hand, MovePerfselects 32 features based on observations from real-world projects. Furthermore, MovePerf obtains the execution time for each project after MMR as the performance label by employing a performance profiling tool, JMH. On the other hand, MovePerf builds a hybrid model to learn features from low-order and high-order interactions by composing a deep feedforward neural network and a factor machine. With this model, it predicts the performance for these projects after MMR. We evaluate MovePerf on real-world projects including JUnit, LC-problems, Kevin, and Concurrency. The experimental results show that MovePerf obtains an average MRE of 7.69%, illustrating that the predicted value is close to the real value. Furthermore, MovePerf improves the MRE from 1.83% to 8.61% compared to existing approaches, including a CNN, DeepFM, DeepPerf, and HINNPerf, demonstrating its effectiveness. Full article

Chlorophyll fluorescence is a useful indicator of a plant’s physiological status, particularly under stress conditions. Remote sensing is an increasingly adopted technology in modern agriculture, allowing the acquisition of crop information (e.g., chlorophyll fluorescence) without direct contact, reducing fieldwork. The objective of this study is to improve the monitoring of olive tree fluorescence (Fv′/Fm′) via remote sensing in a Mediterranean environment, where the frequency of stress factors, such as drought, is increasing. An advanced approach combining explainable artificial intelligence and multispectral Sentinel-2 satellite data was developed to predict olive tree fluorescence. Field measurements were conducted in southeastern Italy on two olive groves: one irrigated and the other one under rainfed conditions. Sentinel-2 reflectance bands and vegetation indices were used as predictors and different machine learning algorithms were tested and compared. Random Forest showed the highest predictive accuracy, particularly when Sentinel-2 reflectance bands were used as predictors. Using spectral bands preserves more information per observation, enabling models to detect variations that VIs might miss. Additionally, raw reflectance data minimizes potential bias that could arise from selecting specific indices. SHapley Additive exPlanations (SHAP) analysis was performed to explain the model. Random Forest showed the highest predictive accuracy, particularly when using Sentinel-2 reflectance bands as predictors. Key spectral regions associated with Fv′/Fm′, such as red-edge and NIR, were identified. The results highlight the potential of integrating remote sensing and machine learning to improve olive grove management, providing a useful tool for early stress detection and targeted interventions. Full article

Musculoskeletal injury (MSI) risk screening has gained significant attention in rehabilitation, sports, and fitness due to its ability to predict injuries and guide preventive interventions. This review analyzes the Functional Movement Screen (FMS) and the Y-Balance Test (YBT) landscape. Although these instruments are widely used because of their simplicity and ease of access, their accuracy in predicting injuries is inconsistent. Significant issues include reliance on broad scoring systems, varying contextual relevance, and neglecting individual characteristics such as age, gender, fitness levels, and past injuries. Meta-analyses reveal that the FMS and YBT overall scores often lack clinical relevance, exhibiting significant variability in sensitivity and specificity among different groups. Findings support the effectiveness of multifactorial models that consider modifiable and non-modifiable risk factors such as workload ratios, injury history, and fitness data for better prediction outcomes. Advances in machine learning (ML) and wearable technology, including inertial measurement units (IMUs) and intelligent monitoring systems, show promise by capturing dynamic and personalized high-dimensional data. Such approaches enhance our understanding of how biomechanical, physiological, and contextual injury aspects interact. This review discusses the problems of conventional movement screens, highlights the necessity for workload monitoring and personalized evaluations, and promotes the integration of technology-driven and data-centered techniques. Adopting tailored, multifactorial models could significantly improve injury prediction and prevention across varied populations. Future research should refine these models to enhance their practical use in clinical and field environments. Full article

China’s FengYun 3E (FY3E) meteorological satellite, launched in 2021, is equipped with advanced instruments for comprehensive Earth observations. In this study, we compared outgoing longwave radiation (OLR) measurements from the FY3E satellite (FY3E OLR) and from a series of satellites operated by the National Oceanic and Atmospheric Agency (NOAA, United States of America; hereafter NOAA OLR) and analyzed the spatiotemporal differences between the datasets. We designed a new correction model, “DeepFM”, implementing both a factorization machine algorithm and a deep artificial neural network to minimize daily mean differences between the datasets. Then, we evaluated the spatiotemporal consistency between the corrected FY3E OLR and NOAA OLR data. The DeepFM model effectively reduced daily mean differences: after correction, the daily mean absolute bias and root-mean-square error decreased from 7.4 W/m² to 4.2 W/m² and from 10.3 W/m² to 6.3 W/m², respectively, indicating a notably improved spatiotemporal consistency between the corrected FY3E OLR and NOAA OLR data. Subsequently, we merged these datasets to generate a long-term OLR dataset suitable for climate analyses. This study provides a robust technological basis and innovative methodology for the dedicated application of China meteorological satellites to climate science. Full article

Predicting art auction results presents a unique challenge due to the complexity and variability of factors influencing artwork prices. This study explores a range of machine learning architectures designed to forecast auction outcomes using tabular data, including historical auction records, artwork characteristics, artist profiles, and market indicators. We evaluate traditional models such as LinearModel, K-Nearest Neighbors, DecisionTree, RandomForest, XGBoost, CatBoost, LightGBM, MLP, VIME, ModelTree, DeepGBM, DeepFM, and SAINT. By comparing the performance of these models on a dataset comprising extensive auction results, we provide insights into their relative effectiveness across different scenarios. Additionally, we address the interpretability of models, which is crucial for understanding the influence of various features on predictions. The results suggest that while some models perform better than others, no single approach offers consistently high accuracy across all cases. This study provides guidance for auction houses, art investors, and market analysts in refining predictive approaches, identifying key challenges, and understanding where further improvements are needed for more accurate data-driven decisions in the art market. Full article

An accurate forecast of typhoon tracks is crucial for disaster warning and mitigation. However, existing numerical weather prediction models, such as the Weather Research and Forecasting (WRF) model, still exhibit significant errors in track forecasts. This study aims to improve forecast accuracy by correcting WRF-forecasted tracks using deep learning models, including Bidirectional Long Short-Term Memory (BiLSTM) + Convolutional Long Short-Term Memory (ConvLSTM) + Wide and Deep Learning (WDL), BiLSTM + Convolutional Gated Recurrent Unit (ConvGRU) + WDL, and BiLSTM + ConvLSTM + Extreme Deep Factorization Machine (xDeepFM), with a comparison to the Kalman Filter. The results demonstrate that the BiLSTM + ConvLSTM + WDL model reduces the 72 h track prediction error (TPE) from 255.18 km to 159.23 km, representing a 37.6% improvement over the original WRF model, and exhibits significant advantages across all evaluation metrics, particularly in key indicators such as Bias², Mean Squared Error (MSE), and Sequence. The decomposition of MSE further validates the importance of the BiLSTM, ConvLSTM, WDL, and Temporal Normalization (TN) layers in enhancing the model’s spatio-temporal feature-capturing ability. Full article

Personalized news recommendation can alleviate the information overload problem, and accurate modeling of user interests is the core of personalized news recommendation. Existing news recommendation methods integrate the titles and contents of news articles that users have historically browsed to construct user interest models. However, this method ignores the phenomenon of “title–content mismatching” in news articles, which leads to the lack of precision in user interest modeling. Therefore, a hybrid news recommendation method based on title–content matching is proposed in this paper: (1) An interactive attention network is employed to model the correlation between title and content contexts, thereby enhancing the feature representation of both; (2) The degree of title–content matching is computed using a Siamese neural network, constructing a user interest model based on title–content matching; and (3) neural collaborative filtering (NCF) based on factorization machines (FM) is integrated, taking into account the perspective of the potential relationships between users for recommendation, leveraging the insensitivity of neural collaboration to news content to alleviate the impact of title–content mismatching on user feature modeling. The proposed model was evaluated on a real-world dataset, achieving an nDCG of 83.03%, MRR of 81.88%, AUC of 85.22%, and F1 Score of 35.10%. Compared to state-of-the-art news recommendation methods, our model demonstrated an average improvement of 0.65% in nDCG and 3% in MRR. These experimental results indicate that our approach effectively enhances the performance of news recommendation systems. Full article

This study presents a data-driven model for identifying failure modes (FMs) and predicting the corresponding punching shear resistance of slab-column connections with shear reinforcement. An experimental database that contains 328 test results is used to determine nine input variables based on the punching shear mechanism. A comparison is conducted between three typical machine learning (ML) approaches: random forest (RF), light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost) and two hybrid optimized algorithms: grey wolf optimization (GWO) and whale optimization algorithm (WOA). It was found that the XGBoost classifier had the highest accuracy rate, precision, and recall values for FM identification. In testing, WOA-XGBoost has the best accuracy in predicting punching shear resistance, with R², MAE, and RMSE values of 0.9642, 0.087 MN, and 0.126 MN, respectively. However, a comparison between experimental values and calculated values derived from classical analytical methods clearly demonstrates that existing design codes need to be improved. Additionally, Shapley additive explanations (SHAP) were applied to explain the model’s predictions, with factors categorized according to their impact on failure modes and punching shear resistance. By modifying these parameters, punching resistance can be improved while reducing unpredictable failure. With the proposed hybrid algorithms, it is possible to determine the failure modes and the punching shear resistance of slabs during the preliminary stages of the construction. Full article

The integration of graph embedding technology and collaborative filtering algorithms has shown promise in enhancing the performance of recommendation systems. However, existing integrated recommendation algorithms often suffer from feature bias and lack effectiveness in personalized user recommendation. For instance, users’ historical interactions with a certain class of items may inaccurately lead to recommendations of all items within that class, resulting in feature bias. Moreover, accommodating changes in user interests over time poses a significant challenge. This study introduces a novel recommendation model, RCKFM, which addresses these shortcomings by leveraging the CoFM model, TransR graph embedding model, backdoor tuning of causal inference, KL divergence, and the factorization machine model. RCKFM focuses on improving graph embedding technology, adjusting feature bias in embedding models, and achieving personalized recommendations. Specifically, it employs the TransR graph embedding model to handle various relationship types effectively, mitigates feature bias using causal inference techniques, and predicts changes in user interests through KL divergence, thereby enhancing the accuracy of personalized recommendations. Experimental evaluations conducted on publicly available datasets, including “MovieLens-1M” and “Douban dataset” from Kaggle, demonstrate the superior performance of the RCKFM model. The results indicate a significant improvement of between 3.17% and 6.81% in key indicators such as precision, recall, normalized discount cumulative gain, and hit rate in the top-10 recommendation tasks. These findings underscore the efficacy and potential impact of the proposed RCKFM model in advancing recommendation systems. Full article

As the world’s energy demand continues to expand, shale oil has a substantial influence on the global energy reserves. The third submember of the Mbr 3 of the Shahejie Fm, characterized by complicated mudrock lithofacies, is one of the significant shale oil enrichment intervals of the Bohai Bay Basin. The classification and identification of lithofacies are key to shale oil exploration and development. However, the efficiency and reliability of lithofacies identification results can be compromised by qualitative classification resulting from an incomplete workflow. To address this issue, a comprehensive technical workflow for mudrock lithofacies classification and logging prediction was designed based on machine learning. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) were conducted to realize the automatic classification of lithofacies, which can classify according to the internal relationship of the data without the disturbance of human factors and provide an accurate lithofacies result in a much shorter time. The PCA and HCA results showed that the third submember can be split into five lithofacies: massive argillaceous limestone lithofacies (MAL), laminated calcareous claystone lithofacies (LCC), intermittent lamellar argillaceous limestone lithofacies (ILAL), continuous lamellar argillaceous limestone lithofacies (CLAL), and laminated mixed shale lithofacies (LMS). Then, random forest (RF) was performed to establish the identification model for each of the lithofacies and the obtained model is optimized by grid search (GS) and K-fold cross validation (KCV), which could then be used to predict the lithofacies of the non-coring section, and the three validation methods showed that the accuracy of the GS–KCV–RF model were all above 93%. It is possible to further enhance the performance of the models by resampling, incorporating domain knowledge, and utilizing the mechanism of attention. Our method solves the problems of the subjective and time-consuming manual interpretation of lithofacies classification and the insufficient generalization ability of machine-learning methods in the previous works on lithofacies prediction research, and the accuracy of the model for mudrocks lithofacies prediction is also greatly improved. The lithofacies machine-learning workflow introduced in this study has the potential to be applied in the Bohai Bay Basin and comparable reservoirs to enhance exploration efficiency and reduce economic costs. Full article

High efficiency and safety are critical factors in ensuring the optimal performance and reliability of systems and equipment across various industries. Fault monitoring (FM) techniques play a pivotal role in this regard by continuously monitoring system performance and identifying the presence of faults or abnormalities. However, traditional FM methods face limitations in fully capturing the complex interactions within a system and providing real-time monitoring capabilities. To overcome these challenges, Digital Twin (DT) technology has emerged as a promising solution to enhance existing FM practices. By creating a virtual replica or digital copy of a physical equipment or system, DT offers the potential to revolutionize fault monitoring approaches. This paper aims to explore and discuss the diverse range of predictive methods utilized in DT and their implementations in FM across industries. Furthermore, it will showcase successful implementations of DT in FM across a wide array of industries, including manufacturing, energy, transportation, and healthcare. The utilization of DT in FM enables a comprehensive understanding of system behavior and performance by leveraging real-time data, advanced analytics, and machine learning algorithms. By integrating physical and virtual components, DT facilitates the monitoring and prediction of faults, providing valuable insights into the system’s health and enabling proactive maintenance and decision making. Full article

N-terminal pro-brain natriuretic peptide (NT-proBNP) and uric acid are elevated in pregnancies with preeclampsia (PE). Short-term prediction of PE using angiogenic factors has many false-positive results. Our objective was to validate a machine-learning model (MLM) to predict PE in patients with clinical suspicion, and evaluate if the model performed better than the sFlt-1/PlGF ratio alone. A multicentric cohort study of pregnancies with suspected PE between 24⁺⁰ and 36⁺⁶ weeks was used. The MLM included six predictors: gestational age, chronic hypertension, sFlt-1, PlGF, NT-proBNP, and uric acid. A total of 936 serum samples from 597 women were included. The PPV of the MLM for PE following 6 weeks was 83.1% (95% CI 78.5–88.2) compared to 72.8% (95% CI 67.4–78.4) for the sFlt-1/PlGF ratio. The specificity of the model was better; 94.9% vs. 91%, respectively. The AUC was significantly improved compared to the ratio alone [0.941 (95% CI 0.926–0.956) vs. 0.901 (95% CI 0.880–0.921), p < 0.05]. For prediction of preterm PE within 1 week, the AUC of the MLM was 0.954 (95% CI 0.937–0.968); significantly greater than the ratio alone [0.914 (95% CI 0.890–0.934), p < 0.01]. To conclude, an MLM combining the sFlt-1/PlGF ratio, NT-proBNP, and uric acid performs better to predict preterm PE compared to the sFlt-1/PlGF ratio alone, potentially increasing clinical precision. Full article

In recent years, deep learning has been applied to the field of recommendation, which can learn complex user interaction features and make better recommendations. However, deep learning only focuses on the interaction of high-order features and neglects the low-order features. The DeepFM model combines the linear FM (Factorization Machines) model and the deep DNN (Deep Neural Network) model to realize the interactive learning of low-order and high-order features, but it does not take into account that user interests will change dynamically with time. When the data sparsity is high, it cannot be effectively recommended. Based on this, an improved DeepFM recommendation algorithm that combines depth feature extraction was proposed, named fDeepFM. Firstly, the word features are transformed into low-dimensional dense vectors through the Embedding layer. Then Doc2Vec is combined to mine item features with context, and the two are stitched together as the input to the FM model and DNN model. Subsequently, user features are input to the GRU (Gated Cyclic Unit) model according to different cycles to mine user features. Finally, the results of the FM model, DNN model, and GRU model are combined by linear stitching as the overall output of the fDeepFM model. Experiments were carried out on Movielens-20M and Amazon data sets. The experimental results showed that MAE, RMSE, F1-score, and AUC on the Movielens-20M data set were optimized by 1.69%, 2.4%, 1.67%, and 2.28%, respectively; On the Amazon dataset, MAE, RMSE, F1-score, and AUC are optimized by 3.2%, 3.86%, 1.63%, and 2.2% respectively compared with DeepFM. Full article

Accurate sales forecasting can provide a scientific basis for the management decisions of enterprises. We proposed the xDeepFM-LSTM combined forecasting model for the characteristics of sales data of apparel retail enterprises. We first used the Extreme Deep Factorization Machine (xDeepFM) model to explore the correlation between the sales influencing features as much as possible, and then modeled the sales prediction. Next, we used the Long Short-Term Memory (LSTM) model for residual correction to improve the accuracy of the prediction model. We then designed and implemented comparison experiments between the combined xDeepFM-LSTM forecasting model and other forecasting models. The experimental results show that the forecasting performance of xDeepFM-LSTM is significantly better than other forecasting models. Compared with the xDeepFM forecasting model, the combined forecasting model has a higher optimization rate, which provides a scientific basis for apparel companies to make adjustments to adjust their demand plans. Full article

Under variable working conditions, the tool status signal is affected by changing machine processing parameters, resulting in a decreased prediction accuracy of the remaining useful life (RUL). Aiming at this problem, a method based on multi-sensor fusion for tool RUL prediction was proposed. Firstly, the factorization machine (FM) was used to extract the nonlinear processing features in the low-frequency condition signal, and the one-dimensional separable convolution was applied to extract tool life state features from multi-channel high-frequency sensor signals. Secondly, the residual attention mechanism was introduced to weight the low-frequency condition characteristics and high-frequency state characteristics, respectively. Finally, the features extracted in the low-frequency and high-frequency parts were input into the full connection layer to integrate working condition information and state information to suppress the influence of variable conditions and improve prediction accuracy. The experimental results demonstrated that the method could predict the remaining life of the tool effectively, and the accuracy and stability of the model are better than several other methods. Full article