Search

RGB-D salient object detection (SOD) has gained more and more research interest in recent years. Due to various imaging mechanisms of RGB and depth modalities, RGB-D images contain different information. Thus, how to effectively fuse multi-modality features and aggregate multi-scale features to generate accurate saliency prediction are still the problems. In this article, we present a Multi-Modality Information Refinement Fusion Network (MIRFNet) for RGB-D SOD to solve the problems. Specifically, a Feature-Enhancement and Cross-Refinement Module (FCM) is proposed to reduce redundant features and the gap between cross-modality data to achieve multi-modality feature fusion effectively. In FCM, the Feature-Enhancement step utilizes attention mechanisms to obtain enhanced features which contain less redundant information and more common salient information, and the Cross-Refinement step employs the enhanced features to reduce the gap between cross-modality features and achieve effective feature fusion. Then, we propose an Edge Guidance Module (EGM) to extract edge information from RGB features. Finally, to effectively aggregate multi-level features and achieve accurate saliency prediction, a Feature-Aggregation and Edge-Refinement Module (FEM) is designed, which introduces specific-modality information and edge information to conduct sufficient information interaction. In FEM, the Feature-Aggregation step aggregates multi-scale features with specific-modality information, and the Edge-Refinement step uses edge information to refine the aggregation features. Extensive experiments demonstrate that MIRFNet can achieve comparable performance against the other 12 SOTA methods on five datasets. [ABSTRACT FROM AUTHOR]

With the rapid advancement of sports analytics and fan engagement technologies, the volume and diversity of physique data generated by smart devices across various distributed sports platforms have grown significantly. Extracting insights and enhancing fan experiences from such data offer considerable benefits. Yet, this process unveils two primary challenges. Firstly, efficiently utilizing the vast datasets in sports analytics is daunting due to the complex nature of the sports industry. Secondly, the data collected from diverse sources and stored in distributed platforms contain sensitive information like fan preferences and athlete performance metrics, posing risks of privacy breaches. To address these challenges, we leverage an advanced Locality-Sensitive Hashing technique, known as PSDFP ALSH , tailored for the sports domain. This paper presents a new privacy-preserving method for sports data fusion and prediction in distributed environments, utilizing enhanced Locality-Sensitive Hashing to protect sensitive information while maintaining high data utility. Through extensive experimentation, our approach demonstrates superior performance over existing methods in terms of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and computational efficiency. [ABSTRACT FROM AUTHOR]

The devices deployed across diverse industrial scenarios have generated significant network traffic related to time. The system's irregular operation could result in substantial bad influence. Anomaly detection technologies utilized for identifying possible non-standard behaviours are paramount; furthermore, multivariate time series exhibit complex dependencies besides temporal correlation. However, most previous methods merely consider the temporal and variable correlation of time series data, neglecting the distance metrics among the sequences, leading to a deficiency in the model's anomaly detection ability. We propose a multivariate time series anomaly detection model based on the encoder–decoder architecture (CCER-ED). The model considers the similarity measure between temporal subsequences and designs a multi-scale feature embedding module for leveraging more interrelated properties. Moreover, the interrelations among sensors are explicitly learned using a manifold regularization graph structure. On this basis, an improved data fusion approach based on a multi-head self-attention mechanism is designed for capturing global feature representation, effectively integrating various aspects of information. Evaluations using the real-world datasets SWAT and WADI and performance analysis show that the proposed approach achieves improvement over the baselines in the recall and F1-score of anomaly detection performance at 9.3% and 8.5% (maximum), respectively, outperforming other existing methods. [ABSTRACT FROM AUTHOR]

Precipitation is a fundamental factor affecting many fields, including freshwater reservation, flood warning and prevention, agriculture, and hydropower planning. Observation-based precipitation data usually come from two primary sources, namely gauges and satellite images. The former provides high reliability but sparse coverage, while the latter offers fine-grained data but is still inaccurate. There have been several efforts to estimate precipitation, including mathematical and probabilistic models and machine learning-based techniques. All existing solutions consider the target problem as a satellite data calibration with gauge data as complementary information. However, this approach fails to provide accurate predictive results due to the sparsity of gauges and significant errors in satellite data. This paper presents a novel precipitation estimating method that highlights the importance of gauge data, the most trustworthy data source. To be more precise, we formulate the precipitation estimation issue as a spatial prediction task with the goal of predicting rainfall data for non-monitoring locations using gauge data at the monitored sites. To this end, we propose a data-driven approach that exploits the encoder–decoder architecture, graph neural network, and the multimodal data fusion strategy. Specifically, we design an encoder that leverages a graph neural network for capturing the spatial relationship among the gauges. Meanwhile, the decoder exploits the convolutional networks to learn the temporal correlation within the historical data. Finally, we integrate satellite images and meteorological information using a multimodal data fusion based on a multilayer perceptron to enhance prediction accuracy. The experimental results show that our proposed model increases the estimation accuracy from 24.3 to 65.2% compared to the state-of-the-art. [ABSTRACT FROM AUTHOR]

Intrusion detection in industrial control systems (ICS) is crucial for maintaining secu rity in modern industries. However, the rapid growth of data generated from various sources presents significant challenges, as complex and diverse attacks continue to threaten the integrity of these systems. Traditional intrusion detection systems face limitations in effectively detecting intrusions and suffer from processing delays. To address these issues, there is an urgent need for a real-time and efficient IDS. This study introduces a novel approach to real-time intrusion detection in ICS by leveraging Cloud Computing and Big Data techniques for data fusion. By fusing mul tiple streams of data, our approach enhances intrusion detection performance, reduces false alarm rates, and produces more consistent and accurate results. The contributions of this work are two-fold. Firstly, we propose a real-time IDS that overcomes the limitations of traditional systems through the efficient processing capabilities of Cloud Computing and Big Data techniques. Secondly, we employ data fusion to integrate diverse data sources, resulting in improved intrusion detection accuracy and efficiency. Our proposed IDS achieves higher accuracy rates and demonstrates superior efficiency in detecting intrusions compared to existing solutions. These findings underscore the potential of our approach in enhancing ICS security and mitigating risks posed by evolving attacks. [ABSTRACT FROM AUTHOR]

Urban traffic congestion is of utmost importance for modern societies due to population and economic growth. Thus, it contributes to environmental problems like increasing greenhouse gas emissions and noise pollution. Improved traffic flow in urban networks relies heavily on traffic signal control. Hence, optimizing cycle timing at many intersections is paramount to reducing congestion and increasing sustainability. This paper introduces an alternative to conventional traffic signal control, EcoLight+, which incorporates future noise predictions with the deep dueling Q-network reinforcement Learning algorithm to reduce noise levels, CO 2 emissions, and fuel consumption. An innovative data fusion approach is also proposed to improve our LSTM-based noise prediction model by integrating heterogeneous data from different sources. Our proposed solution allows the system to achieve higher efficiency than its competitors based on real-world data from Tallinn, Estonia. [ABSTRACT FROM AUTHOR]

Data fusion technology plays a pivotal role in aggregating, storing, and mining multi-source data to extract its joint value through the construction of a unified fusion representation model. However, we argue that mainstream methods are limited to precise data, which may not satisfy practical application requirements, as data collected from an information source often exhibits imprecision and uncertainty. In this paper, we develop a Multi-source Fuzzy Data-driven Dynamic Fusion Representation (MFD-DFR) model. This model effectively addresses the challenges related to heterogeneity, dynamics, and quality optimization that arise during the fusion of fuzzy data. To achieve this goal, we first adopt intervals as a means of description to capture the inherent uncertainty in single-source information. We then present a Dynamic Interval Standardization (DIS) algorithm, a novel approach that dynamically deals with the heterogeneity of multi-source fuzzy data without relying on the storage of historical sample data. We next propose a fusion representation model for standardized intervals that improves the quality of single-source fuzzy data through confidence interval estimation. The experimental results convincingly demonstrate that the MFD-DFR model outperforms alternative models in terms of data classification and clustering. We also show the effectiveness of our proposed DIS algorithm in expediting the convergence speed of gradient descent algorithms. [ABSTRACT FROM AUTHOR]

The roughness of the part surface is one of the most crucial standards for evaluating machining quality due to its relationship with service performance. For a preferable comprehension of the evolution of surface roughness, this study proposes a novel surface roughness prediction model on the basis of the unity of fuse d signal features and deep learning architecture. The force and vibration signals produced in the milling of P20 die steel are collected, and time and frequency domain feature from the acquired signals are extracted by variational modal decomposition. The GA-MI algorithm is taken to select the signal features that are relevant to the surface roughness of the workpiece. The optimal feature subset is analyzed and used as the input of the prediction model. DBN is adopted to estimate the surface roughness and the model parameters are optimized by ISSA. (Reviewer 1, Q1) The separate force, vibration and fusion signal information are brought into the DBN model and the ISSA-DBN model for the prediction of surface roughness, and the results show that the accuracy of the roughness prediction is as follows, respectively DBN: 78.1%, 68.8% and 84.4%, and ISSA-DBN: 93.8%, 87.5% and 100%. [ABSTRACT FROM AUTHOR]

Prior to further processing, completed questionnaires must be screened for the presence of careless respondents. Different people will respond to surveys in different ways. Some take the easy path and fill out the survey carelessly. The proportion of careless respondents determines the survey's quality. As a result, identifying careless respondents is critical for the quality of obtained results. This study aims to explore the characteristics of careless respondents in survey data and evaluate the predictive power and interpretability of different types of data and indices of careless responding. The research question focuses on understanding the behavior of careless respondents and determining the effectiveness of various data sources in predicting their responses. Data from a three-month web-based survey on participants' personality traits such as honesty-humility, emotionality, extraversion, agreeableness, conscientiousness and openness to experience was used in this study. Data for this study was taken from Schroeders et al.. The gradient boosting machine-based prediction model uses data from the answers, time spent for answering, demographic information on the respondents as well as some indices of careless responding from all three types of data. Prediction models were evaluated with tenfold cross-validation repeated a hundred times. Prediction models were compared based on balanced accuracy. Models' explanations were provided with Shapley values. Compared with existing work, data fusion from multiple types of information had no noticeable effect on the performance of the gradient boosting machine model. Variables such as "I would never take a bribe, even if it was a lot", average longstring, and total intra-individual response variability were found to be useful in distinguishing careless respondents. However, variables like "I would be tempted to use counterfeit money if I could get away with it" and intra-individual response variability of the first section of a survey showed limited effectiveness. Additionally, this study indicated that, whereas the psychometric synonym score has an immediate effect and is designed with the goal of identifying careless respondents when combined with other variables, it is not necessarily the optimal choice for fitting a gradient boosting machine model. [ABSTRACT FROM AUTHOR]

The relevance of data fusion in handling big data in blockchain-enabled healthcare systems is of utmost importance in today's data-driven healthcare landscape. As healthcare systems continue to generate vast amounts of data from various sources, the need to effectively manage and analyze this data becomes crucial for informed decision-making, improved patient outcomes, and efficient healthcare operations. The gaps for time complexity and inaccuracy of feature fusion in the existing algorithms have been identified by surveying the existing literature and this article is proposing a multi-attribute feature fusion algorithm blockchain communications based on ant colony neural networks (ACNN) to overcome the problems in the state-of-the-arts. This article applies the feature decomposition method for communication between blockchain-based healthcare transactions, and optimizes the information based on the data characteristics. The proposed algorithm identifies the properties and attributes of the data by making use of rough set theory. A genetic algorithm is also used to improve the ACNN which enhances the search ability by minimizing the space complexity of the solution space. The multi-attribute fusion mechanism extracts the information from the blockchain transactions and filters out the characteristics of data using the proposed method, and achieves better accuracy. The empirical results show that the fusion error of the blockchain communications based on multi-attribute feature fusion algorithm is relatively small and stable. The outcomes of the proposed fusion mechanism are promising and it has been found that the proposed mechanism produces accurate results with minimal errors. The average energy consumption rate during the transition of data is below 2% which reflects the viability of the proposed fusion mechanism for blockchain-based healthcare transactions. [ABSTRACT FROM AUTHOR]

Aiming to solve the problems of the inaccurate dimension reduction of high-dimensional data and insufficient information utilization in traditional manufacturing process monitoring methods—in which mostly only the distance information of pairwise points is used as the similarity index for the data dimension reduction—this paper proposes a data-manifold-based monitoring method that combines the distance information and angle information of pairwise points. First, the intrinsic dimension of manufacturing process data is estimated by combining multiple geometric features on the data manifold. Second, considering the angle information and distance information in the neighborhood of process data, the method to construct local features of the data manifold is given; further, a fusion method of local features and global–local features of manifold data based on the eigendimension is proposed, which constructs the data dimension-reduction mapping matrix to improve the integrity of data information extraction. Then, the data index of process monitoring is given and employed to monitor the manufacturing process. Finally, Tennessee Eastman (TE) process simulation data were used to verify the effectiveness of the proposed method. The results show that compared with other methods, the anomaly detection rate of the proposed method was increased by more than 50%, while the false alarm rate was decreased by 21.4%, which proves that the method can significantly improve the efficiency of manufacturing process anomaly monitoring. [ABSTRACT FROM AUTHOR]

Single molecule localization microscopy offers resolution nearly down to the molecular level with specific molecular labelling, and is thereby a promising tool for structural biology. In practice, however, the actual value to this field is limited primarily by incomplete fluorescent labelling of the structure. This missing information can be completed by merging information from many structurally identical particles in a particle fusion approach similar to cryo-EM single-particle analysis. In this paper, we present a data analysis of particle fusion results of fluorescently labelled Nup96 nucleoporins in the Nuclear Pore Complex to show that Nup96 occurs in a spatial arrangement of two rings of 8 units with two Nup96 copies per unit giving a total of 32 Nup96 copies per pore. We use Artificial Intelligence assisted modeling in Alphafold to extend the existing cryo-EM model of Nup96 to accurately pinpoint the positions of the fluorescent labels and show the accuracy of the match between fluorescent and cryo-EM data to be better than 3 nm in-plane and 5 nm out-of-plane. [ABSTRACT FROM AUTHOR]

In order to predict the thermal deformation of CNC machine tool spindle system more accurately, a method based on multi-source heterogeneous information fusion is proposed. Aiming at the problem that it is difficult to obtain the global information of thermal deformation with a single type of information source, the effective prediction of thermal deformation of spindle system in machining center is realized under the fusion of temperature and vibration signals. First, the combined denoising method of empirical mode decomposition (EMD) and wavelet threshold is used to preprocess the vibration data. Then, the time-domain, frequency-domain, and time-frequency features of vibration signals are extracted, and the feature dimension is reduced based on correlation analysis and kernel principal component analysis (KPCA). After dimensionality reduction, the vibration data and temperature information are fused in the eigenmatrix. The nonlinear prediction of thermal deformation is studied by support vector regression for grid search parameter optimization (GS-SVR) and support vector regression for particle swarm optimization (PSO-SVR) methods. In order to realize the information acquisition of multi-channel temperature, vibration, and verify the effectiveness of the prediction model in the case of information fusion, a specific machining center is taken as the research object and experiments are performed based on multi-channel and heterogeneous signal acquisition. Finally, the prediction results based on different information sources are compared and analyzed. The results show that the thermal deformation of the machine tool obtained by the multi-source heterogeneous information fusion method is consistent with the actual test results. As compared with the predicted performance using only temperature information, the mean square error (MSE) decreased by 0.1663 µm. Therefore, the temperature - vibration information fusion model has higher accuracy in terms of predicting the thermal deformation of the spindle system model. [ABSTRACT FROM AUTHOR]

Molecular properties prediction is an important task in the field of materials, especially in computational drug and materials discovery. Deep learning (DL) is one of the most popular methods for molecular properties prediction due to its ability to establish quantitative relationships between molecular representations and target properties. In order to improve the performance of DL algorithms, it is crucial to select appropriate representation of molecules. Molecular graph has become one of the choices as it can be easily input into graph neural network (GNN)-based DL models for learning. However, model performance is limited if molecular representation is only used because it only contains atomic information, bond information, and adjacency relationships between atoms. Therefore, we use molecular mass spectrum as another representation to provide supplement information which is not contained in the graph data. In this paper, a transformer-based model, named Mass Spectrum Transformer (MST), is proposed to perform quantitative analysis of molecular spectra, then it is combined with the graph neural network to form a multi-modal data fusion model TransG-Net for accurate molecular properties prediction. Several feature fusion methods are adopted and the best method is chosen to further enhance the performance of the model. A multi-modal dataset is collected in this paper which is composed of molecular graph data and spectra. Data augmentation is performed to simulate the experimentally measured molecular spectra for the generalizability of the model. Experimental results show that MST outperforms previous best mass spectrum-based methods for molecular properties prediction. In addition, TransG-Net combining MST and GNN achieves better performance than state-of-the-art well-designed message passing models, which proves the effectiveness of our multi-modal data fusion method. [ABSTRACT FROM AUTHOR]

The study of the prediction of stock market volatility is of great significance to rationally control financial market risks and increase excessive investment returns and has received extensive attention from academic and commercial circles. However, as a dynamic and complex system, the stock market is affected by multiple factors and has a comprehensive capability to include complex financial data. Given that the explanatory variables of influencing factors are diverse, heterogeneous and complex, the existing intelligent algorithms have great limitations for the analysis and processing of multi-source heterogeneous data in the stock market. Therefore, this study adopts the edge weight and information transmission mechanism suitable for subgraph data to complete node screening, the gate recurrent unit (GRU) and long short-term memory (LSTM) to aggregate subgraph nodes. The compiled data contain the metapaths of three types of index data, and the introduction of the association relationship attention dimension effectively mines the implicit meanings of multi-source heterogeneous data. The metapath attention mechanism is combined with a graph neural network to complete the classification of multi-source heterogeneous graph data, by which the prediction of stock market volatility is realized. The results show that the above method is feasible for the fusion of heterogeneous stock market data and the mining of implicit semantic information of association relations. The accuracy of the proposed method for the prediction of stock market volatility in this study is 16.64% higher than that of the dimensional reduction index and 14.48% higher than that of other methods for the fusion and prediction of heterogeneous data using the same model. [ABSTRACT FROM AUTHOR]

Special medical supplies such as blood and vaccines have strict temperature requirements in medical cold storage. In order to improve the stability of the temperature monitoring system in the medical cold storage and solve the problem of low measurement accuracy caused by node failure or abnormal data interference, we propose an algorithm based on classification adaptive estimation (CAEWF). The algorithm first monitors and classifies the data collected by the nodes, and uses the mutual support matrix between the data to filter out the validity abnormal data and transmit them to the cluster head. Then use the classification adaptive estimation weighted fusion algorithm to estimate the weighted fusion of the data. The simulation results show that the accuracy of the CAEWF algorithm is better than the arithmetic mean and batch estimation fusion algorithm, which can meet the temperature accuracy requirements of medical cold storage. [ABSTRACT FROM AUTHOR]

Prognostics health management (PHM) is an emerging philosophy that aims to optimize maintenance processes. The first step in PHM after a system failure occurs, is to estimate the remaining useful life (RUL). This research is about predicting the RUL of rolling bearings using a hybrid fuzzy time series model based on granular computing and data fusion to estimate health index. It is not possible to obtain accurate information about the severity and location of defects during operation. Therefore, the major difficulties in prediction are the nonlinearity of the degradation process and high uncertainty. The novelty of this work is in the development and implement of a new fuzzy logic algorithm and fusion of the temperature signal with vibrations. Through using this algorithm, the average percentage of prediction error on bearings is 28.81% and the average prediction score is 0.43, which shows a significant improvement over findings of other researchers. [ABSTRACT FROM AUTHOR]

In condition monitoring, accurate fault identification is an essential task for designing a proper maintenance strategy. Misalignment is one of the main faults in rotary machinery, because 70% of the failure occurs due to misalignment. Conventionally, the diagnosis of misalignment is carried out through vibration measurements. Especially, the presence of strong 2x vibration peak is generally accepted. Both angular and parallel misalignment shows peak at 2x, therefore, distinguishing misalignment type by using vibration signals alone is a difficult activity. This paper discusses classification of misalignment i.e., angular and parallel by using a diagnostic medium such as the acoustic emission and the rotor vibration signal. Vibro-acoustic sensors are used to collect data from the misaligned rotor system at two different loading, three different speed and three defect severity conditions. Time domain features are extracted and graded according to their significance using t test (One-way ANOVA) technique. Extracted features are used to train different algorithms. The outcome obtained using support vector machine (SVM) is 100% accurate. Vibro-acoustic sensor data fusion technique is employed to classify various forms of misalignment under different operating conditions. This work also intended to explore using a small amount of training data using different algorithms. The proposed method outperforms fault classification using vibration signal and acoustic signal separately. [ABSTRACT FROM AUTHOR]

In cooperative mobile communications, spectrum sensing performance may encounter difficulties, which alert with many reporting errors, especially in dense network scenarios. In such networks, the decision fusion process for cooperating users becomes very complex, which requires sensing heavy traffic that needs a large bandwidth. To enhance the reliability of robust cooperative spectrum sensing, the paper proposed a new data fusion scheme based on clustering algorithm and distributed detection, in addition to an adapted threshold based on controlled false alarm probability. The proposed algorithm is dedicated to a highly Rayleigh faded environment to improves the channel errors. The results show that the use of two stages process of distribution clusters and selection fusion node (FN)s gives 0.42 error improvement. The results of the receiver operating characteristic (ROC) curve show an improvement in both false alarms and detection probabilities. Moreover, the sensitivity is also enhanced by 0.95. [ABSTRACT FROM AUTHOR]

In the era of big data, the field of enterprise risk is facing considerable challenges brought by massive multisource heterogeneous information sources. In view of the proliferation of multisource and heterogeneous enterprise risk information, insufficient knowledge fusion capabilities, and the low level of intelligence in risk management, this article explores the application process of enterprise knowledge service models for rapid responses to risk incidents from the perspective of semantic reasoning and data fusion and clarifies the elements of the knowledge service model in the field of risk management. Based on risk data, risk decision making as the standard, risk events as the driving force, and knowledge graph analysis methods as the power, the risk domain knowledge service process is decomposed into three stages: prewarning, in-event response, and postevent summary. These stages are combined with the empirical knowledge of risk event handling to construct a three-level knowledge service model of risk domain knowledge acquisition-organization-application. This model introduces the semantic reasoning and data fusion method to express, organize, and integrate the knowledge needs of different stages of risk events; provide enterprise managers with risk management knowledge service solutions; and provide new growth points for the innovation of interdisciplinary knowledge service theory. [ABSTRACT FROM AUTHOR]

With the complex landform and climate in the Sichuan region, the need for practical and scientific research production by only utilising the rainfall data derived from ground stations or satellites has not been satisfied. To overcome this difficulty, rainfall data from 161 meteorological stations in 2016 are used in this study. According to the distribution of stations, 146 rainfall data from 161 meteorological stations in 2016 are used for inverse distance weighted interpolation, and then, linear regression, weighted regression, and Kalman filter fusion and optimal interpolation method data fusion are performed with TRMM 3B42 satellite rainfall data, respectively. Then, 15 meteorological stations evenly distributed in the study area are selected for the accuracy test. The results show that compared with the measurement at ground stations, linear regression shows the best merging effect on rainfall data derived from ground stations and satellite rainfall estimates across the daily scale: the correlation coefficient is the most significantly improved (0.2–0.7) and the reduction in root-mean-square error (RMSE) is the largest. The method is applicable for use in Sichuan Province when merging rainfall data. At the monthly scale, the rainfall data processed by using the Kalman filter present the highest accuracy (0.72–0.84). At this scale, the Kalman filter is more suitable. [ABSTRACT FROM AUTHOR]

To realize the deep integration of complex product manufacturing and operation and maintenance processes, while eliminate the phenomenon of information islands generated in the manufacturing and operation and maintenance links, in the light of the lack of in-depth integration in the manufacturing and operation and maintenance process of complex products. With the help of digital twin technology, this paper puts forward the overall framework manufacturing and operation and maintenance integration of a complex product based on digital twin and the system integration mode of virtual and real integration. The solutions of complex product integration of manufacturing and operations and maintenance, data fusion, modeling and simulation, and manufacturing plant operation mode based on digital twin are analyzed. The key technologies based on digital twin deep integration of manufacturing and operation and maintenance, fault prediction, and knowledge base/case library construction are discussed. Finally, combined with the fault prediction case of a certain type of electric multiple units (EMU) bogie, the associated operation mode between the operation and maintenance process of the EMU and the manufacturer is demonstrated, which proves the feasibility and effectiveness of the integration method. [ABSTRACT FROM AUTHOR]

High shear wet granulation (HSWG) has been wildly used in manufacturing of oral solid dosage (OSD) forms, and process modeling is vital to understanding and controlling this complex process. In this paper, data fusion and multivariate modeling technique were applied to develop a formulation-process-quality model for HSWG process. The HSWG experimental data from both literature and the authors' laboratory were fused into a single and formatted representation. A material database and material matching method were used to compensate the incomplete physical characterization of literature formulation materials, and dimensionless parameters were utilized to reconstruct process variables at different granulator scales. The exploratory study on input materials properties by principal component analysis (PCA) revealed that the formulation data collected from different articles generated a formulation library which was full of diversity. In prediction of the median granule size, the partial least squares (PLS) regression models derived from literature data only and a combination of literature data and laboratory data were compared. The results demonstrated that incorporating a small number of laboratory data into the multivariate calibration model could help significantly reduce the prediction error, especially at low level of liquid to solid ratio. The proposed data fusion methodology was beneficial to scientific development of HSWG formulation and process, with potential advantages of saving both experimental time and cost. [ABSTRACT FROM AUTHOR]

Scientific investigations of artworks are crucial in terms of preservation since they provide a measurable evaluation of the materials and the state of conservation. This is the case of Antonello da Messina's painting "Ecce Homo": its delicate state of conservation, with the need for constant monitoring, required a broad and in-depth diagnostic campaign to support the restorers. The project was carried out entirely in situ using non-invasive cutting-edge techniques and proposes a multimodal and data-centric approach, integrating 3D and 2D methodologies. The surface irregularities and the support were analysed with a structured-light 3D scanner and X-ray tomography. The painting materials were investigated with X-ray fluorescence scanning (MA-XRF) and reflectance hyperspectral imaging (HSI). Primarily, the data were jointly used for a scientific scope and provided new knowledge of the painting in terms of materials and painting techniques. In addition, two web-based interactive platforms were developed: one to provide restorers and experts with a new perspective of the hidden geometries of the painting, and the other targeted at the general public for dissemination purposes. The results of the Ecce Homo scientific analysis were exhibited, using a touch-screen interface, and developed for different user levels, from adults to kids. [ABSTRACT FROM AUTHOR]

Tremendous amounts of data are generated every day by different sources and stored in heterogeneous databases. Providing an integrated view by fusion of data is essential to enhance data utilization. An indispensable type of data is spatial data, with diverse application domains, including GIS, e-commerce, military, and tourism. The concept of location forms a key part of user-generated data with serious challenges, including uncertainty. A particular location may have different names, and conversely, various locations may have the same name. Furthermore, geographical coordinates of locations may not be expressed accurately in datasets. More challenges also exist that have received less attention. Various data sources might describe locations in different levels of detail. This increases data inconsistency and decreases the quality of data fusion. This paper focuses on spatial data granulation to deal with this variety. If these diversities are not taken into consideration, the different descriptions of a location may be interpreted differently and, in turn, not be fused. The contribution of this paper are: (a) Introducing a granular approach to measure the similarity between two place description for managing apparent differences. The proposed method improves the quality of the geocoding and data fusion phases, (b) Introducing a novel data blocking method to decrease pairwise comparisons based on geographical features. For result evaluation, we developed a dataset from two real aviation accident datasets. The evaluation shows that the quality of entity recognition and data fusion improved by using our proposed data granulation technique. [ABSTRACT FROM AUTHOR]

The development and progress of multi-sensor data fusion theory and methods have also laid the foundation for the research of human body posture tracking system based on inertial sensing. The main research in this paper is the simulation of gymnastics performance based on MEMS sensors. In the preprocessing to reduce noise interference, this paper mainly uses median filtering to remove signal glitches. This article uses virtual character models for gymnastics performances. The computer receives sensor data from the sink node of the motion capture device through a Bluetooth communication module. The unit calculates the quaternion output from the dynamic link library of sensor data processing, calculates the rotation amount and coordinate offset of each sensor node's limb, and uses the character model to realize the real-time rendering of the virtual character model. At the same time, it controls the storage of sensor data, the drive of the model, and the display of the graphical interface. When a gesture action is about to occur, a trigger signal is given to the system to mark the beginning of the action, so as to obtain the initial data of each axis signal of the MEMS sensor. When the gesture action is completed, give the system a signal to end the action. Mark the end of the action, so that you can capture the original signal data during the beginning and end of the gesture action. In order to ensure the normal communication between PS and PL, it is necessary to test the key interfaces involved. Because the data received by the SPI acquisition module is irregular, it is impossible to verify whether the data is wrong, so the SPI acquisition module is replaced with a module that automatically increments data, and the IP core is generated, and a test platform is built for testing. The data shows that the average measurement error of X-axis displacement of the space tracking system is 8.17%, the average measurement error of Y-axis displacement is 7.51%, the average measurement error of Z-axis displacement is 9.72%, and the average error of three-dimensional space measurement is 8.7%. The results show that the MEMS sensor can accurately recognize the action with high accuracy. [ABSTRACT FROM AUTHOR]

In order to establish the combined prediction model of milling noise based on force-thermal-vibration multi-feature fusion, a simultaneous milling noise-vibration-thermal-force test system was established. Based on the gray correlation theory and test data, the relationship between milling sound pressure and milling parameters, milling vibration, milling force, and milling thermal was analyzed. Based on the least square method, three single prediction models of milling sound pressure level for three-directional vibration, milling thermal, and three-directional milling force were established. Then, the weight coefficients of the combined model are determined by the standard errors of the three single models, and the linear combination model of the mean square root of milling sound pressure level expressed by the three single prediction models and the corresponding weight coefficients was established. The correlation coefficient of the combined prediction model of sound pressure is 0.95, which is larger than the correlation coefficient of three single prediction models. It shows that the combined prediction model of sound pressure level with multiple features can better predict milling noise and provide theoretical guidance for milling tool condition monitoring. [ABSTRACT FROM AUTHOR]

Economic data include data of various types and characteristics such as macro-data, meso-data, and micro-data. The source of economic data can be the data related to economy held by the National Bureau of statistics and a various software. These multi-source and heterogeneous data have important value for economic analysis and forecasting. Taking into account the limitations of existing methods such as low accuracy and complex calculations, this paper proposes an economic data analysis and prediction method based on machine learning. We use machine learning to solve the data fusion problem in the process of multi-source data analysis and prediction in the economic field. Specifically, we proposes an economic data analysis and forecasting method combining convolutional auto-encoder and extreme gradient boosting algorithms. This method uses a convolutional auto-encoder to extract the data characteristics of the normalized parameter sequence and uses it to train an extreme gradient boosting model to predict the level of economic development and evaluate the importance of each influencing factor. Finally, through a case study, this paper integrates the data of labor force, education and population to forecast GDP. Through the verification of this case, the prediction accuracy of the proposed method is higher than the AE-XGBoost method and CAE-1D-XGBoost method used in this experiment, and the error is kept below 11.7%. [ABSTRACT FROM AUTHOR]

With the promotion of the latest technologies and the new requirement of humanitarian, the wireless multi-sensor system is applied broadly. This paper studies the data fusion of the industrial wireless sensor networks (IWSNs), in order to acquire more thoughtful data for the prognosis and diagnosis of the monitored device. These authors propose a combination of back propagation neural network (BP NN) and Wavelet Packet algorithm for data fusion. This proposed algorithm is based on each cluster head, which is modelled with a three layers NN. A case study using the ball bearing test data, which is from the Bearing Data Center of the Case Western Reserve University, and to verify the effectiveness of the proposed algorithm. With MATLAB 2016b version, the raw data feature is extracted by the Wavelet Packet and the feature fusion is based on BP NN at sink node. The simulation results show that the proposed algorithm is effective in fault diagnosis of wind turbine. [ABSTRACT FROM AUTHOR]

As an emerging research field of brain science, multimodal data fusion analysis has attracted broader attention in the study of complex brain diseases such as Parkinson's disease (PD). However, current studies primarily lie with detecting the association among different modal data and reducing data attributes. The data mining method after fusion and the overall analysis framework are neglected. In this study, we propose a weighted random forest (WRF) model as the feature screening classifier. The interactions between genes and brain regions are detected as input multimodal fusion features by the correlation analysis method. We implement sample classification and optimal feature selection based on WRF, and construct a multimodal analysis framework for exploring the pathogenic factors of PD. The experimental results in Parkinson's Progression Markers Initiative (PPMI) database show that WRF performs better compared with some advanced methods, and the brain regions and genes related to PD are detected. The fusion of multi-modal data can improve the classification of PD patients and detect the pathogenic factors more comprehensively, which provides a novel perspective for the diagnosis and research of PD. We also show the great potential of WRF to perform the multimodal data fusion analysis of other brain diseases. [ABSTRACT FROM AUTHOR]

Image fusion is a challenging research area which is useful in various image processing applications. Image fusion integrates information from multiple source images into a single composite image for better visual quality and information content than any of its source images. In the present paper, we have proposed a new median based image fusion algorithm using nonsubsampled shearlet transform. Nonsubsampled shearlet transform is a powerful multiscale geometrical analysis (MGA) tool having rich mathematical structure, high directionality, anisotropy and shift-invariance features. Due to these features nonsubsampled shearlet transform can efficiently capture information of the source images in its coefficient sets. The coefficient sets of the source images are fused by using a new median based fusion rule. Median is an important statistical measurement, which is enriched with two outstanding properties that are edge preserving and robustness against noise. Hence, median based fusion rule increases the quality of fused image. The proposed fusion rule is simple and easy to understand. Strength of the proposed fusion method is verified visually as well as quantitatively by comparing it with different state of the art methods. We have performed experiments on three different types of images (medical, remote sensing and multifocus). Results of the experiments confirm that the proposed method outperform in comparison with other state-of-the-art fusion methods visually as well as quantitatively in terms of different quantitative performance measures such as entropy, standard deviation, edge strength, fusion factor, and running time. [ABSTRACT FROM AUTHOR]

The existing building surface data fusion algorithms do not extract the segmented data features, resulting in inaccurate fusion results. In heterogeneous environment, a Clustering Fusion Algorithm Based on mutual information and fractal dimension is proposed. The regression coefficient is used to express the sequence, and the data feature representation and data dimension reduction are realized. The dynamic data series are processed by similarity measure function method. For the long dynamic data series, the piecewise aggregation approximation method is used to segment the data and then extract the features. Through the incremental clustering processing data based on fractal dimension clustering algorithm, the research of data fusion algorithm is realized. The experimental results show that the accuracy of building surface data fusion is greatly improved by using the dynamic data fusion algorithm, the highest is 0.98, the sum of square error is reduced, and the lowest is only 90.44. [ABSTRACT FROM AUTHOR]

Dempster-Shafer evidence theory (D-S theory) is applied to process uncertain information in different scenarios. However, traditional Dempster combination rule may produce counterintuitive results while dealing with highly conflicting data. Inspired by a perspective of constructing base belief function for conflicting data processing in D-S theory, a new base basic probability assignment (bBPA) method is proposed to process the potential conflict before data fusion. Instead of assigning initial belief on the whole power set space, the new method assigns the base belief to basic events in the frame of discernment. Consequently, the bBPA is consistent with the classical probability theory. Several numerical examples are adopted to verify the reliability and accuracy of the method in processing highly conflicting data. The data sets in the University of California Irvine (UCI) Machine Learning Repository are used to verity the availability of the new method in classification problem. Experimental result shows that the new method has some superiority in dealing with highly conflicting data. [ABSTRACT FROM AUTHOR]

Wireless body sensor network (WBSN) is also known as wearable sensors with transmission capabilities, computation, storage and sensing. In this paper, a supervised learning based decision support system for multi sensor (MS) healthcare data from wireless body sensor networks (WBSN) is proposed. Here, data fusion ensemble scheme is developed along with medical data which is obtained from body sensor networks. Ensemble classifier is taken the fusion data as an input for heart disease prediction. Feature selection is done by the squirrel search algorithm which is used to remove the irrelevant features. From the sensor activity data, we utilized the modified deep belief network (M-DBN) for the prediction of heart diseases. This work is implemented by Python platform and the performance is carried out of both proposed and existing methods. Our proposed M-DBN technique is compared with various existing techniques such as Deep Belief Network, Artificial Neural Network and Conventional Neural Network. The performance of accuracy, recall, precision, F1 score, false positive rate, false negative and true negative are taken for both proposed and existing methods. Our proposed performance values for accuracy (95%), precision (98%), and recall (90%), F1 score (93%), false positive (72%), false negative (98%) and true negative (98%). [ABSTRACT FROM AUTHOR]

In the discrete manufacturing workshop, an unreasonable workshop layout has a significant impact on the production efficiency, which can result in a large distance between operations, low utilization of tooling, and the backlog of products in production process. However, the existing optimization algorithms for workshop layout rarely take into account the real-time feedback of physical information from the workshop such that the layout cannot be self-adjusted to realize the optimum during manufacturing. Thus, this paper focuses on a discrete manufacturing workshop layout optimization based on digital twin, in which the workshop layout problem is solved by twin data fusion, information and physical interaction fusion, and data analysis and optimization. First, a sub-framework of digital twin-based workshop partitioning is established and the workshop partitioning is optimized via simulation analysis. Second, a sub-framework of digital twin-based equipment layout optimization is presented, in which equipment layout decisions are made by real-time data collection and value-added processing of twin data. Then, a sub-framework of digital twin-based distribution route optimization is developed for the workshop. Finally, the proposed method is applied to a welding production workshop and increased the production capacity o by 29.4%. [ABSTRACT FROM AUTHOR]

In geographic data analysis, it is often the case that multiple aspects of a single phenomenon are captured by different sources of data. For instance, a storm can be identified based on its precipitation, as well as windspeed, and changes in barometric pressure. It proves beneficial in specific domains to be able to use all available sources of data, and some method must be used to integrate all of these sources of data into a singular decision, often in the form of a classification. This paper proposes the general form of what has been termed the Class Label Conflation Problem – the problem of taking a number of distinct and possibly conflicting sources in the form of spatially-located time series, and using this historical dataset to determine a class label at a new location. In addition to this formalization, this paper details an algorithm (called ACCL) to solve the general case of the problem. This algorithm has its foundations in information theory (specifically Dempster-Shafer Theory), supervised classification, and data fusion. An analysis of the algorithm demonstrates its effectiveness using synthetic datasets as well as the US Drought Monitor as a case study. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of the stock closing price forecasting for the stock market. Based on existing two-stage fusion models in the literature, two new prediction models based on clustering have been proposed, where k-means clustering method is adopted to cluster several common technical indicators. In addition, ensemble learning has also been applied to improve the prediction accuracy. Finally, a hybrid prediction model, which combines both the k-means clustering and ensemble learning, has been proposed. The experimental results on a number of Chinese stocks demonstrate that the hybrid prediction model obtains the best predicting accuracy of the stock price. The k-means clustering on the stock technical indicators can further enhance the prediction accuracy of the ensemble learning. [ABSTRACT FROM AUTHOR]

In today's increasingly international economy, return and volatility spillover effects across international equity markets are major macroeconomic drivers of stock dynamics. Thus, information regarding foreign markets is one of the most important factors in forecasting domestic stock prices. However, the cross-correlation between domestic and foreign markets is highly complex. Hence, it is extremely difficult to explicitly express this cross-correlation with a dynamical equation. In this study, we develop stock return prediction models that can jointly consider international markets, using multimodal deep learning. Our contributions are threefold: (1) we visualize the transfer information between South Korea and US stock markets by using scatter plots; (2) we incorporate the information into the stock prediction models with the help of multimodal deep learning; (3) we conclusively demonstrate that the early and intermediate fusion models achieve a significant performance boost in comparison with the late fusion and single-modality models. Our study indicates that jointly considering international stock markets can improve the prediction accuracy and deep neural networks are highly effective for such tasks. [ABSTRACT FROM AUTHOR]

Healthcare predictive analytics using electronic health records (EHR) offers a promising direction to address the challenging tasks of health assessment. It is highly important to precisely predict the potential disease progression based on the knowledge in the EHR data for chronic disease care. In this paper, we utilize a novel longitudinal data fusion approach to model the disease progression for chronic disease care. Different from the conventional method using only initial or static clinical data to model the disease progression for current time prediction, we design a temporal regularization term to maintain the temporal successivity of data from different time points and simultaneously analyze data from data source level and feature level based on a sparse regularization regression approach. We examine our approach through extensive experiments on the medical data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). The results show that the proposed approach is more useful to simulate and predict the disease progression compared with the existing methods. [ABSTRACT FROM AUTHOR]

In 2015, the European Commission has drafted a framework regulation for integrated European social statistics. This integration covers the Labour Force Survey, the Statistics on Income and Living conditions, and others. In order to avoid an inappropriate response burden, administrative and other sources shall be considered to achieve accurate survey estimates. Combining information from different data sources has become a field of growing research interest among statistical offices and other institutions. In the statistical literature this problem is known as data fusion or statistical matching, and is widely considered as a particular missing-data pattern. Assuming that budgets are limited, and that only some additional information can be obtained to improve the quality of the data fusion, we investigate different scenarios of using these limited resources within an integrated system of household surveys. Our main objective is to develop a framework that fosters on the one hand the estimation of statistical models using several surveys, and on the other hand classical totals for different sub-classes and areas which are of special interest for official statistics. [ABSTRACT FROM AUTHOR]

Fusion effect of SVM in the Spark architecture for speech data mining in cluster structure is studied in this manuscript. Based on the information entropy of nodes, the data in clusters are fused to eliminate redundant data and improve the efficiency of information fusion. Information entropy is a statistical form based on the characteristics of information representation, which reflects the average amount of information in information. Based on the Spark platform SVM algorithm, the frequent items with the highest support after each sort are directly recursively obtained, and the transaction data set is allocated to each computing node. The structure of the item head table directly affects the efficiency of the algorithm, so optimizing the structure of the item head table can improve the efficiency of the algorithm in constructing FP-Tree, and then improve the efficiency of the whole algorithm. The proposed speech data mining algorithm can cluster, analyze, and comprehensively detection the saliency information, the detection accuracy is much higher than the state-of-the-art models. The experimental results compared with the latest research have reflected that fact that the proposed model has the better performance and robustness. [ABSTRACT FROM AUTHOR]

The early hepatic fibrosis staging is very important for timely diagnosis, prognosis, and treatment of all chronic liver diseases. Diffraction-enhanced imaging, which can provide much more information on soft tissue morphology than conventional absorption radiography, might be a potential noninvasive technique to diagnose and stage hepatic fibrosis. This paper presents different feature extraction strategies and classification methods to automatically classify hepatic fibrosis using diffraction-enhanced imaging images. Texture features are obtained using a total of three methods including first order feature, gray level co-occurrence matrix, and grayscale gradient co-occurrence matrix. The fusion of these texture features is also studied. The principal component analysis is used to reduce the dimension of the features and redundant information among data. The features are classified using two popular classification techniques, namely, K-nearest neighbors and support vector machines. On the basis of the comparison of different feature strategies and classification methods, we can identify the suitable methods for grading hepatic fibrosis. The proposed approach efficiently classifies the hepatic fibrosis DEI images into four classes with the highest classification accuracy of 99.99%. We further demonstrate the potential of the DEI images in staging hepatic fibrosis. [ABSTRACT FROM AUTHOR]

Categorical attributes are ubiquitous in real-world collected data. However, such attributes lack a well-defined distance metric and cannot be directly manipulated per algebraic operations, so many data mining algorithms are unable to work directly on them. Learning an appropriate metric or an effective numerical embedding is very vital yet challenging, for categorical attributes with multi-view heterogeneous data characteristics. This paper proposes a novel multi-view heterogeneous fusion model (MVHF), which first captures basic coupling information for each view and then fuses these heterogeneous information from different views by multi-kernel metric learning, to measure the intrinsic distances between this type of categorical attributes; based on these measured distances, further, we use the manifold learning method to learn a high-quality numerical embedding for each categorical value. Experiments on 33 mixed data sets demonstrate that MVHF-enabled classification significantly enhances the performance, compared with state-of-the-art distance metrics or embedding competitors. [ABSTRACT FROM AUTHOR]

For online video service providers, the accurate prediction of video popularity directly impacts their advertisement revenue, bandwidth provisioning policy and copyright procurement decision. Most of previous approaches only utilize data from a single platform (e.g., view history) for prediction. However, such approaches cannot provide satisfactory prediction accuracy, as video popularity may be affected by many influential features dispersed over multiple platforms. In this paper, we focus on the popularity prediction of online movies and propose a prediction framework called DeepFusion to fuse salient features from multiple platforms so as to boost the accuracy of popularity prediction of online movies. For this purpose, we extract influential factors from Douban, which is a leading movie rating website in China, and Youku, which is one of the largest online video service providers in China. Considering the complexity incurred by numerous parameters, we choose to feed these influential factors into deep neural networks for prediction and thus avoid the limitation of traditional predictive models. Compared with previous approaches, our solution can significantly improve the prediction accuracy over 40%. Moreover, even for movies without any historical views, our approach can also well capture their popular trends and overcome the cold-start problem. [ABSTRACT FROM AUTHOR]

Seeing that the light in the water is affected by absorption and scattering, underwater image will suffer degradation including low contrast, low visibility and color deviation. Therefore, the key issue of underwater image enhancement is to improve the visibility and the contrast of underwater images. In this paper, we proposed an underwater image dehazing algorithm combining three main steps of homomorphic filtering, double transmission map and dual-image wavelet fusion. First at all, we removed the color deviation in the underwater image by homomorphic filtering. Then, we obtained the enhanced image by depth map which calculate the difference between the light and dark channels. Finally, the dual-image wavelet fusion technique is used to combine the enhanced image obtained by the depth map with the enhanced image obtained by the dark channel. In addition, we obtained the contrast enhanced image which use Contrast-Limited Adaptive Histogram Equalization (CLAHE) method. Through simulation experiments, the proposed method has better visual effects and better effect on entropy, average gradient and underwater color image quality evaluation (UCIQE) compared with other popular methods. [ABSTRACT FROM AUTHOR]

Advances in species recognition technologies can contribute to the conservation and protection of flora species, especially those threatened with extinction. The aim of this research was to compare the early fusion approaches of operators known as Local Binary Patterns (LBP) and late fusion, carried out at the level of the decision classifiers, in the construction of an automatic recognition system of forest species. 1901 macroscopic images of wood from 46 Brazilian species were used. The extraction of image characteristics was done using two variants of the LBP descriptor, covering different aspects of spatial and angular resolution. The repeated stratified k-fold cross-validation method was used to estimate the performance of the classifiers. The cross-validation folds were created using stratified random sampling, whose strata were the prediction classes. An automatic recognition system based on the concatenation of rotation-invariant LBP histograms and the SVM classifier showed an F1-score of 97.67%. The fusion of classifiers, through majority voting, improved the F1-score of this system by 0.33% point. This experiment revealed that more than 50% of the species showed no misclassification or occurred only once or twice. It was identified that some groups of species generally confused by wood anatomists were perfectly differentiated by this classification system. The recognition system showed good ability to identify species, and if this technology is combined with traditional identification tools and empirical knowledge, it is possible to minimize errors in the identification of Brazilian flora, especially endangered species, for which the proposed classification system showed high accuracy. [ABSTRACT FROM AUTHOR]

A reasonable clustering structure can make data aggregation methods run efficiently in most wireless sensor networks (WSNs). However, compared with other WSNs, the energy imbalance problem of long and linear WSNs is more serious, and the delay is higher. It is still impossible to achieve efficient data aggregation by optimizing the clustering structure. Therefore, this letter proposes a novel data aggregation tree based on a clustering structure. First, through the optimization of cluster head selection and multihop path selection, this letter proposes a long and linear nonuniform clustering structure to improve the energy balance. Furthermore, taking the minimum delay as the objective function and the number of fusion nodes and energy balance as the constraint, an aggregation node selection mechanism based on a swarm optimization algorithm is proposed to build a data aggregation tree based on a long and linear nonuniform clustering structure. The simulation results show that the proposed method can effectively reduce the delay and energy consumption and that it is suitable for long and linear WSNs. [ABSTRACT FROM AUTHOR]

Facial image analysis has been an important subject of study in the communities of pattern recognition and computer vision. Facial images contain much information about the person they belong to like identity, age, gender, ethnicity, and expression. This paper introduces a new framework that exploits facial deep features for kinship verification. The framework integrates efficient feature selection and kinship-oriented discriminant data projection. The resulting framework incorporates three levels of fusion: (1) an early fusion of descriptors where the filter selection selects the most relevant deep features, (2) a middle-stage fusion which exploits a kinship-based multi-view metric learning method, and (3) a late-stage fusion that merges classifiers responses. In our study, face features are provided by the pre-trained deep convolutional neural networks VGG-F and VGG-Face that were originally proposed for discriminating categories of objects and identities, respectively. Experimental results on two benchmarked datasets for kinship verification in the wild (KinFaceW-I and KinFaceW-II) show that the proposed framework outperforms state-of-the-art techniques without the use of external data or data augmentation that are tailored for the kinship verification problem. These experiments show that the proposed scheme can outperform feature fusion obtained by deep multi-metric learning. [ABSTRACT FROM AUTHOR]

Chronic Obstructive Pulmonary Disease (COPD) is a chronic lung disease that causes a progressive decline in respiratory function. COPD has become the fourth most lethal disease in the world, and worldwide deaths continue to become more common as a result of COPD. Therefore, it is important to help doctors diagnose COPD more accurately using big data analytics and effective algorithms. In the past, COPD was mainly studied as follows: applying data to determine the impact of a single feature on the disease, such as the effect of FEV1/FVC (forced expiratory volume in the first second/forced vital capacity), and analyzing a case with simple models, such as logistic regression or a support vector machine. Therefore, there are obviously deficiencies in previous studies. First, the impacts of multi-dimensional features on COPD have not been considered comprehensively. Second, there is no fusion of multiple study methods on the diagnosis and prognosis of COPD. Thus, this paper presents a feature-maximum-dependency-based fusion diagnosis method for COPD. First, the MDF-RS (feature maximum dependency-rough set) algorithm is proposed to extract the optimal combination of multi-dimensional features. Second, the integrated model DSA-SVM (direct search simulated annealing-support vector machine) is presented to classify the disease. Finally, the proposed method is experimentally tested. The results show that the algorithms outperform other classic methods. [ABSTRACT FROM AUTHOR]