Multi-source Information Fusion Research Articles

MIFAM-DTI: a drug-target interactions predicting model based on multi-source information fusion and attention mechanism

MIFAM-DTI: a drug-target interactions predicting model based on multi-source information fusion and attention mechanism

A Real-time Assessment System for Cognitive Performances of Armored Vehicle Crews Based upon the Multi-source Information Fusion

In the human-machine system of armored vehicles, the cognitive performance state of crews is crucial for the personnel security and combat efficiency. The purpose of this research was to establish a real-time assessment system for cognitive performances of armored vehicle crews, consisting of the data input module, data processing module, data visualization module, and scheduling module. Forty subjects were recruited to cooperate and execute the cross-platform strike task in a virtual simulation platform. The physiological data and operation behavior data was collected during the experiment process. To realize the accurate classification of different cognitive performance states, a multi-source information fusion algorithm was developed based on linear discriminant analysis (LDA) and D-S evidence theory, which included the information collection module, the feature extraction module, and the information fusion module. The results indicated that there existed a significant correlation between the extractive feature indicators (i.e., EOG, ECG, and task performance indicators) and the cognitive performance. The recognition accuracy and the data efficiency of the proposed assessment system were 91.25% and 96.69% respectively by using the complementarity of different evidences, which were higher than the others using partial information sources. This study can provide a reference for the comprehensive assessment of cognitive performance of human operators in military and industrial domains.

Damage effect evaluation of CCD irradiated by laser based on multi-source information fusion

This study introduces an advanced approach for assessing the damage state of charge-coupled devices (CCDs) caused by laser interactions, leveraging a multi-source and multi-feature information fusion technique. We established an experimental system that simulates laser damage on CCDs and collects diverse data types including echo information from active laser detection based on the ‘cat's eye’ effect, plasma flash data, and surface image characteristics of the CCD. A probabilistic neural network (PNN) was utilized to integrate these data sources effectively. Our analysis demonstrated that using multiple features from single sources significantly improves the accuracy of the damage assessment compared to single-feature evaluations. The error rates using dual features from each information type were 10.65% for cat's eye echo, 7.3% for plasma flash, and 7.17% for surface image analysis. By combining all three information sources and six features, we successfully reduced the error rate to 0.85%, with the evaluation time under 60 milliseconds. These findings confirm that our multi-source, multi-feature fusion method is highly effective for the online and real-time evaluation of CCD damage, offering significant improvements in the operational reliability and safety of devices in high-energy environments.

Multisource information fusion model for deformation safety monitoring of earth and rock dams based on deep graph feature fusion

Constructing a long-term deformation monitoring model for earth–rock dams that integrates multisource monitoring information is highly important for enhancing the safety state evaluation and monitoring effectiveness of such dams. In this paper, we propose a new health monitoring model named the deformation–seepage–water level multimeasurement point health monitoring (DSW-MPHM) model for earth–rock dams based on deep graph feature fusion. This model fuses coupled seepage, deformation, and water level features from different monitoring sites of the dam body, base, and shoulder. To achieve this goal, we first establish a new module to fuse spatial and temporal features using graph convolutional networks and long short-term memory. Seepage features and water level features are then extracted using graph attention mechanisms. Subsequently, we employ the feature fusion technique, which incorporates principal component analysis and gated fusers, to construct the DSW-MPHM model, which effectively fuses information from multiple sources. This novel approach successfully addresses the issues of information redundancy and the limited reliability of monitoring models. To verify the validity of the model, it is applied to an endoscopic deformation monitoring program of a panel rockfill dam with a height of 185.5 m. The results demonstrate the superior stability and effectiveness of the proposed method compared to those of 10 baseline prediction models. Additionally, the characterization of the seepage and water level features extracted from the model is verified for its reasonableness. Thus, our proposed model is well suited for practical engineering applications.

Investigation on the fusion reliability and cluster consistency of multivariable entropy method

Recent researches have shown that the multivariable entropy based feature extraction method can obtain better diagnosis results for fault diagnosis of planetary gearbox. However, the nature properties of multivariable entropy have still not been deeply explored: the reliability of multi-source information fusion and cluster consistency for the same fault signal. These two properties will affect the accuracy of fault diagnosis based on multivariate entropy. This paper aims to reveal the nature properties of multivariate entropy. Firstly, a rigid-flexible coupling dynamic model of a planetary gearbox is conducted to establish a pure test environment. Then the generated vibration signals are used to evaluate the fusion reliability and cluster consistency of multivariable entropy. Additionally, a new multivariable entropy feature extraction method called variational embedding refined composite multiscale diversity entropy (veRCMDE) is proposed. Finally, the simulation and experiment results show that high fusion reliability and high cluster consistency enable multivariate entropy to extract more valuable features, and the proposed veRCMDE performs the best in all experiments.

MF-DAT: a stock trend prediction of the double-graph attention network based on multisource information fusion

Stock forecasting research, which aims to predict the future price movement of stocks, has been the focus of investors and scholars. This is important for practical applications related to human-centric computing and information sciences. Previous research has generally only considered market information other than the relationship between stocks, and it is challenging to learn a better representation of stock characteristics by considering the relationship between stocks. In the existing methods of combining market information with stock relationship modeling, most of them use predefined industry relationships to construct stock relationship diagrams, which inevitably ignores the potential interactions between stocks, especially the hidden relationships between stock groups. To this end, a new dual-graph attention model (MF-DAT) based on multisource information fusion is designed. Specifically, first, multiple features are fused by the LMF module, then the long-term and short-term state characteristics of stocks are learned through the first layer of the graph attention layer, and finally the node representation of the stock relationship network constructed by the mining stock cluster structure through community detection is updated. Our model takes into account both stock time-series information and potential relationships between stocks. Experiments on the S &P 500 and NASDAQ datasets show that our MF-DAT has better performance than the 8 SOTA methods that are now more popular.

Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals

Currently, surface EMG signals have a wide range of applications in human–computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model’s capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.

LogMS: a multi-stage log anomaly detection method based on multi-source information fusion and probability label estimation

Introduction: Log anomaly detection is essential for monitoring and maintaining the normal operation of systems. With the rapid development and maturation of deep learning technologies, deep learning-based log anomaly detection has become a prominent research area. However, existing methods primarily concentrate on directly detecting log data in a single stage using specific anomaly information, such as log sequential information or log semantic information. This leads to a limited understanding of log data, resulting in low detection accuracy and poor model robustness.Methods: To tackle this challenge, we propose LogMS, a multi-stage log anomaly detection method based on multi-source information fusion and probability label estimation. Before anomaly detection, the logs undergo parsing and vectorization to capture semantic information. Subsequently, we propose a multi-source information fusion-based long short-term memory (MSIF-LSTM) network for the initial stage of anomaly log detection. By fusing semantic information, sequential information, and quantitative information, MSIF-LSTM enhances the anomaly detection capability. Furthermore, we introduce a probability label estimation-based gate recurrent unit (PLE-GRU) network, which leverages easily obtainable normal log labels to construct pseudo-labeled data and train a GRU for further detection. PLE-GRU enhances the detection capability from the perspective of label information. To ensure the overall efficiency of the LogMS, the second-stage will only be activated when anomalies are not detected in the first stage.Results and Discussion: Experimental results demonstrate that LogMS outperforms baseline models across various log anomaly detection datasets, exhibiting superior performance in robustness testing.

A novel quantum Dempster's rule of combination for pattern classification

Dempster's rule of combination (DRC) is widely used for uncertainty reasoning in intelligent information system, which is generalized to complex domain recently. However, as the increase of identification framework elements, the computational complexity of Dempster's rule of combination increases exponentially. To address this issue, we propose a novel quantum Dempster's rule of combination (QDRC) by means of Toffoli gate. The QDRC combination process is completely implemented using quantum circuits. To validate the efficiency of the proposed QDRC, we conduct simulation experiments on IBM and IonQ quantum cloud platforms. Besides, we implement the QDRC algorithm to the real quantum computer of IonQ Harmony. The experiment results show that the result of QDRC is getting more and more accurate as the number of measurements increases. In addition, we propose a quantum multisource information fusion method on the basis of QDRC. Finally, we demonstrate its effectiveness to solve pattern classification problem under several diverse real UCI datasets.

Group-aware graph neural networks for sequential recommendation

Sequential recommendations play a crucial role in recommender systems. Existing methods commonly focus on extracting sequential patterns within individual item sequences to make personalized recommendations. However, this paper argues that such a closure strategy has limitations. Firstly, the inherent uncertainty and sparsity within these sequences pose considerable challenges in accurately capturing sequential patterns. Secondly, ignoring group behaviors beyond the sequence hinders the modeling of user similarities, which are essential for recommendations. To address these limitations, this paper proposes a novel collaborative sequential recommendation approach, called Group-aware Graph Neural Networks (GaGNN). GaGNN seeks to incorporate group behaviors within sequential recommendations, thereby enhancing the modeling of user preferences through the assimilation of collective wisdom. GaGNN constructs two transition graphs, each offering a distinct behavioral perspective. The group transition graph is designed to capture the collaborative effects and learn collaborative information, whereas the individual transition graph aims to articulate individual behaviors, thereby extracting sequential information. Additionally, a multi-source information fusion module is designed to bridge semantic gaps between the two types of information and yield a holistic understanding of user preferences. Through rigorous experimental comparisons and ablation studies, the superiority of GaGNN and the beneficial integration of collaborative information are emphatically validated.

Identification of the surface heat flux of charring ablative materials using dynamic Bayesian network based on multisource information fusion

In order to solve the dual uncertainty problem between heat flux and thermophysical properties in the identification of the heat flux of charring ablative materials, a dynamic Bayesian network (DBN) based on multisource information fusion is proposed. The method is divided into two stages, with thermophysical properties identified in the former stage and the heat flux identified in the latter stage. A one-dimensional pyrolysis layer model is adopted to characterize the ablation process of materials. In the DBN, the multisource information of surface recession and temperature history data are considered as observation nodes. Sensitivity analysis is used to determine the key parameters in each time step in the DBN, and only key parameters are identified in the corresponding time step. Thus, with the increase of types of information and the decrease of the number of simultaneous identification parameters, the identification accuracy can be improved. The method was verified by numerical and experimental cases. In the numerical cases with noise and experimental cases, the maximum error of using the proposed method was 3.27% and 2.55%, respectively. Compared with only considering the temperature information, the relative errors of the identification results considering multisource information fusion were reduced by 83.95% and 47.53%, respectively.

A review of object tracking methods: From general field to autonomous vehicles

Object tracking is a key technology in the field of intelligent vehicle environmental perception. Accurate and efficient object tracking technologies provide autonomous vehicles with real-time information of moving objects, helping judge the behavioral intention of the objects and predict the trajectories. With the rapid development of artificial intelligence and vehicular sensors, object tracking algorithms have made great progress. Recently however, only a few studies focus on object tracking technology for autonomous vehicles, especially involving multi-source sensors and information fusion algorithms. This study systematically and comprehensively reviews over 230 studies, therein noting the recent research achievements in object tracking are generalized. First, the single object tracking (SOT) and multiple object tracking (MOT) algorithms based on vision sensor are introduced respectively, including 2D, 3D, and intelligent vehicle object tracking algorithms, while the pros and cons of the classical algorithms and latest algorithms are summarized. Then, the object tracking methods based on point cloud and multimodal fusion are discussed and analyzed, and a variety of object tracking datasets are displayed. Finally, on the basis of the research status of intelligent vehicle object tracking algorithms, the challenges and opportunities of future research are presented.

Inconsistency elimination of multi-source information fusion in smart home using the Dempster-Shafer evidence theory

In the smart home, inconsistencies in multi-source information often occur due to the vast quantities and diverse varieties of context information, and the Dempster-Shafer (D-S) evidence theory exhibits remarkable efficacy in addressing this issue. However, the use of basic possibility assignment (BPA) to quantify the credibility of information may introduce the uncertainty contained in the original data. In order to obtain a more reliable BPA and improve the accuracy of multi-source information fusion, an index that combines the relationships of sources and the information volume of context (RSIVC) is defined to comprehensively calculate the uncertainty of context information. In addition, interval distance is introduced to calculate the credibility of the proposition (CoP), which quantifies the correspondence among uncertain context information and all propositions in the frame of discernment (FoD). Finally, based on the d-S evidence theory, a multi-discount context information inconsistency elimination (MDCIE) algorithm using RSIVC and CoP is proposed, which is specifically applied to address the problem of inconsistency in multi-source light intensity information in smart homes. In the experimental part, we compare the traditional and state-of-the-art inconsistency elimination algorithms to verify the effectiveness of the proposed algorithm. Besides, we also test the efficiency of various components of the MDCIE algorithm as well as several RSIVC indicator-building strategies to ensure that the proposed algorithm is optimal. Under the conditions of high precision, medium precision, and low precision of sensors, the context-judge rate reaches 99.24 %, 98.58 %, and 98.09 %, respectively, which corroborates that the MDCIE algorithm is highly effective.

Multi-Source Information Fusion Based DLaaS for Traffic Flow Prediction

Traffic flow prediction is the key to transportation safety and efficiency. The advance in machine learning and deep learning has promoted the development of intelligent transportation systems. For example, the emergence of Deep Learning as a Service (DLaaS) has benefitted researchers a lot in dealing with large scale dataset and complex deep learning algorithms. In traffic forecasting, despite the success of deep learning-based models, there are still shortcomings, such as inadequate use of temporal and spatial traffic information, and indirect modeling of dependencies in traffic data. To address these challenges, we learn the transportation network in the form of a graph, and use graph wavelet as a key component to extract well-positioned features from the graph based on the transportation network. Compared with graph convolution, graph wavelets are very flexible and do not need to specify adjacent regions in the topological graph structure for feature extraction. At the same time, we propose to combine the multi-information fusion traffic control and guidance collaborative neural network and the results obtained are better than the benchmark algorithms. The results by comparison with several baseline methods show that our proposed method can outperform all the baseline methods.

An efficient multi-source information fusion approach for dynamic interval-valued data via fuzzy approximate conditional entropy

An efficient multi-source information fusion approach for dynamic interval-valued data via fuzzy approximate conditional entropy

The impact of virtual technology on students’ creativity: A meta-analysis

As an interactive simulation technology with multi-source information fusion, virtual technology can be used to create learning scenarios, enhance the learning experience, and promote teaching innovation. However, there is no unanimous answer whether virtual technology can effectively improve students' creativity. Therefore, this study adopted a meta-analysis method to analyze 62 experimental (quasi) studies published in international journals between 2014 and 2023 to examine the Impact of Virtual Technology-Based Teaching on Student Creativity. The results found that: 1) Virtual technology has a moderately positive impact on students' creativity (the combined effect size is 0.596), and there is no significant difference in innovative thinking, innovative practical ability, innovative personality quality, and other aspects; 2) Compared with other learning levels, teaching based on virtual technology had the best effect on the creativity of school-age children; 3) Virtual technology could stimulate students' creativity more when applied to the teaching of declarative knowledge than the teaching of procedural knowledge; 4) The use of virtual technology combined with inquiry-discovery and task-driven methods had a more positive impact on creativity; 5) Compared with observational learning and social learning, operational learning had a more improving effect on students' creativity; 6) The use of detailed explanations and true-false feedback in teaching based on virtual technology was more optimistic for the development of students' creativity; 7) Distributed virtual reality and augmented reality had a higher degree of impact on student creativity than other virtual technologies. These analyses provide a reference for future research and practice of using virtual technology to enhance students' creativity.

Garlic Origin Traceability and Identification Based on Fusion of Multi-Source Heterogeneous Spectral Information.

The chemical composition and nutritional content of garlic are greatly impacted by its production location, leading to distinct flavor profiles and functional properties among garlic varieties from diverse origins. Consequently, these variations determine the preference and acceptance among diverse consumer groups. In this study, purple-skinned garlic samples were collected from five regions in China: Yunnan, Shandong, Henan, Anhui, and Jiangsu Provinces. Mid-infrared spectroscopy and ultraviolet spectroscopy were utilized to analyze the components of garlic cells. Three preprocessing methods, including Multiple Scattering Correction (MSC), Savitzky-Golay Smoothing (SG Smoothing), and Standard Normalized Variate (SNV), were applied to reduce the background noise of spectroscopy data. Following variable feature extraction by Genetic Algorithm (GA), a variety of machine learning algorithms, including XGboost, Support Vector Classification (SVC), Random Forest (RF), and Artificial Neural Network (ANN), were used according to the fusion of spectral data to obtain the best processing results. The results showed that the best-performing model for ultraviolet spectroscopy data was SNV-GA-ANN, with an accuracy of 99.73%. The best-performing model for mid-infrared spectroscopy data was SNV-GA-RF, with an accuracy of 97.34%. After the fusion of ultraviolet and mid-infrared spectroscopy data, the SNV-GA-SVC, SNV-GA-RF, SNV-GA-ANN, and SNV-GA-XGboost models achieved 100% accuracy in both training and test sets. Although there were some differences in the accuracy of the four models under different preprocessing methods, the fusion of ultraviolet and mid-infrared spectroscopy data yielded the best outcomes, with an accuracy of 100%. Overall, the combination of ultraviolet and mid-infrared spectroscopy data fusion and chemometrics established in this study provides a theoretical foundation for identifying the origin of garlic, as well as that of other agricultural products.

MHIF-MSEA: a novel model of miRNA set enrichment analysis based on multi-source heterogeneous information fusion.

Introduction: MicroRNAs (miRNAs) are a class of non-coding RNA molecules that play a crucial role in the regulation of diverse biological processes across various organisms. Despite not encoding proteins, miRNAs have been found to have significant implications in the onset and progression of complex human diseases. Methods: Conventional methods for miRNA functional enrichment analysis have certain limitations, and we proposed a novel method called MiRNA Set Enrichment Analysis based on Multi-source Heterogeneous Information Fusion (MHIF-MSEA). Three miRNA similarity networks (miRSN-DA, miRSN-GOA, and miRSN-PPI) were constructed in MHIF-MSEA. These networks were built based on miRNA-disease association, gene ontology (GO) annotation of target genes, and protein-protein interaction of target genes, respectively. These miRNA similarity networks were fused into a single similarity network with the averaging method. This fused network served as the input for the random walk with restart algorithm, which expanded the original miRNA list. Finally, MHIF-MSEA performed enrichment analysis on the expanded list. Results and Discussion: To determine the optimal network fusion approach, three case studies were introduced: colon cancer, breast cancer, and hepatocellular carcinoma. The experimental results revealed that the miRNA-miRNA association network constructed using miRSN-DA and miRSN-GOA exhibited superior performance as the input network. Furthermore, the MHIF-MSEA model performed enrichment analysis on differentially expressed miRNAs in breast cancer and hepatocellular carcinoma. The achieved p-values were 2.17e(-75) and 1.50e(-77), and the hit rates improved by 39.01% and 44.68% compared to traditional enrichment analysis methods, respectively. These results confirm that the MHIF-MSEA method enhances the identification of enriched miRNA sets by leveraging multiple sources of heterogeneous information, leading to improved insights into the functional implications of miRNAs in complex diseases.

Key technologies of earthquake early warning system for China’s high-speed railway

PurposeThe purpose of this study is to introduce the top-level design ideas and the overall architecture of earthquake early-warning system for high speed railways in China, which is based on P-wave earthquake early-warning and multiple ways of rapid treatment.Design/methodology/approachThe paper describes the key technologies that are involved in the development of the system, such as P-wave identification and earthquake early-warning, multi-source seismic information fusion and earthquake emergency treatment technologies. The paper also presents the test results of the system, which show that it has complete functions and its major performance indicators meet the design requirements.FindingsThe study demonstrates that the high speed railways earthquake early-warning system serves as an important technical tool for high speed railways to cope with the threat of earthquake to the operation safety. The key technical indicators of the system have excellent performance: The first report time of the P-wave is less than three seconds. From the first arrival of P-wave to the beginning of train braking, the total delay of onboard emergency treatment is 3.63 seconds under 95% probability. The average total delay for power failures triggered by substations is 3.3 seconds.Originality/valueThe paper provides a valuable reference for the research and development of earthquake early-warning system for high speed railways in other countries and regions. It also contributes to the earthquake prevention and disaster reduction efforts.

Predicting lncRNA–protein interactions through deep learning framework employing multiple features and random forest algorithm

RNA-protein interaction (RPI) is crucial to the life processes of diverse organisms. Various researchers have identified RPI through long-term and high-cost biological experiments. Although numerous machine learning and deep learning-based methods for predicting RPI currently exist, their robustness and generalizability have significant room for improvement. This study proposes LPI-MFF, an RPI prediction model based on multi-source information fusion, to address these issues. The LPI-MFF employed protein–protein interactions features, sequence features, secondary structure features, and physical and chemical properties as the information sources with the corresponding coding scheme, followed by the random forest algorithm for feature screening. Finally, all information was combined and a classification method based on convolutional neural networks is used. The experimental results of fivefold cross-validation demonstrated that the accuracy of LPI-MFF on RPI1807 and NPInter was 97.60% and 97.67%, respectively. In addition, the accuracy rate on the independent test set RPI1168 was 84.9%, and the accuracy rate on the Mus musculus dataset was 90.91%. Accordingly, LPI-MFF demonstrated greater robustness and generalization than other prevalent RPI prediction methods.