Applying Data Fusion Research Articles

A modified multiple-criteria decision-making approach based on a protein-protein interaction network to diagnose latent tuberculosis

BackgroundDNA microarrays provide informative data for transcriptional profiling and identifying gene expression signatures to help prevent progression of latent tuberculosis infection (LTBI) to active disease. However, constructing a prognostic model for distinguishing LTBI from active tuberculosis (ATB) is very challenging due to the noisy nature of data and lack of a generally stable analysis approach.MethodsIn the present study, we proposed an accurate predictive model with the help of data fusion at the decision level. In this regard, results of filter feature selection and wrapper feature selection techniques were combined with multiple-criteria decision-making (MCDM) methods to select 10 genes from six microarray datasets that can be the most discriminative genes for diagnosing tuberculosis cases. As the main contribution of this study, the final ranking function was constructed by combining protein-protein interaction (PPI) network with an MCDM method (called Decision-making Trial and Evaluation Laboratory or DEMATEL) to improve the feature ranking approach.ResultsBy applying data fusion at the decision level on the 10 introduced genes in terms of fusion of classifiers of random forests (RF) and k-nearest neighbors (KNN) regarding Yager’s theory, the proposed algorithm reached a sensitivity of 0.97, specificity of 0.90, and accuracy of 0.95. Finally, with the help of cumulative clustering, the genes involved in the diagnosis of latent and activated tuberculosis have been introduced.ConclusionsThe combination of MCDM methods and PPI networks can significantly improve the diagnosis different states of tuberculosis.Clinical trial numberNot applicable.

Applying data fusion procedures to evaluation of impact damage in carbon fiber reinforced plastic by using optical infrared thermography and laser vibrometry techniques

Applying data fusion procedures to evaluation of impact damage in carbon fiber reinforced plastic by using optical infrared thermography and laser vibrometry techniques

ENHANCING TRAFFIC SAFETY: A COMPREHENSIVE APPROACH THROUGH REAL-TIME DATA AND INTELLIGENT TRANSPORTATION SYSTEMS

Today, traffic accidents are still a difficult and urgent problem for many countries around the world. Traffic accidents on highways are often more serious than accidents on urban roads. Therefore, disseminating emergency information and creating immediate connections with road users is key to rescuing passengers and reducing congestion. Thus, this study applies data fusion and data mining techniques to analyze travel time and valuable information about traffic accidents based on the real-time data collected from On-Board Unit installed in vehicles. The results show that this important information is the vital database to analyze traffic conditions and safety factors, thereby developing a smart traffic information platform. This result enables traffic managers to provide real-time traffic information or forecasts of congestion and traffic accidents to road users. This helps limit congestion and serious accidents on the Highway.

Applying Data Fusion Procedures to Evaluation of Impact Damage in Carbon Fiber Reinforced Plastic by Using Optical Infrared Thermography and Laser Vibrometry Techniques

Applying Data Fusion Procedures to Evaluation of Impact Damage in Carbon Fiber Reinforced Plastic by Using Optical Infrared Thermography and Laser Vibrometry Techniques

Rapid Assessment of Fish Freshness for Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy and Fusion-Based Artificial Intelligence.

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.

Financial exposure to environmental liabilities in Lake Huron drainage area farmlands: a GIS and hedonic pricing approach

PurposeThis paper aims to quantify the impact of environmental contamination on farmland valuation. It applies data fusion and hedonic pricing approaches to quantify the contribution of nitrogen and phosphorus loading on farmland sales transactions. It further suggests approaches to improve internalization of environmental cost in valuation approaches using shadow pricing. The work informs the field of environmental, social and governance (ESG) investing by fusing environmental data with financial transactions.Design/methodology/approachThis paper is an empirical study implementing hedonic pricing of farmland in the Lake Huron major drainage area. Data sources and fusion were derived from AcreValue, the United States Department of Agriculture's Gridded Soil Survey Geographic database (gSSURGO) and the United States Geological Survey's Spatially Referenced Regression on Watershed Attributes database (SPARROW).FindingsThe results suggest that environmental contamination has statistically significant positive determination power on farmland prices such that prices increase with contamination. Conventional metrics such as percentage of cultivated land in the parcel, root zone depth, whether the parcel is designated by the Natural Resource Conservation Service as prime farmland, and the size of the farmland parcel contribution to farmland value as well. The results indicate that environmental impacts are not accurately accounted for in farmland transactions.Research limitations/implicationsThis paper points to inaccurate valuation of environmental contamination in farmland value. While geocoding allowed for positioning of farmland sales transactions relative to modeled areas of contaminant loading in the Lake Huron drainage area, the interpretation indicates that value is driven by cultivation. Hence, generalization to other areas needs a cautious approach. Empirical testing across locations and drainage areas with diverse farmland features will serve to verify the modeled data used in this study.Practical implicationsThe lack of integration of externalities in land valuation has implications on lending and disclosure practices, as financial service providers increasingly seek to account for ESG risk on their loan books and broader investment portfolios. The impact of farmland accounting practices for contamination such as shadow pricing may impact land valuation based on future cash flows, and may serve to inform sustainability-linked lending practices to farm operations.Originality/valueThis is the first paper to fuse data from AcreValue, gSSURGO and SPARROW to discover the explanatory power of nutrient contamination in farmland value in the Lake Huron major drainage area.

Deep Learning for Multifidelity Aerodynamic Distribution Modeling from Experimental and Simulation Data

Wind-tunnel experiment plays a critical role in the design and development phases of modern aircraft, which is always limited by prohibitive cost. In contrast, numerical simulation, as an important alternative research paradigm, mimics complex flow behaviors but is less accurate compared to experiments. This leads to the recent development and emerging interest in applying data fusion for aerodynamic prediction. In particular, the accurate prediction of aerodynamics with lower computational cost can be achieved by fusing experimental (high-fidelity) and computational (low-fidelity) aerodynamic data. Currently, existing works on aerodynamic models using data fusion mainly concern integrated data, like lift, drag, etc. In this paper, a multifidelity aerodynamic model based on deep neural network (DNN) is developed for aerodynamic distribution over the wing surface, where both numerical and experimental data are introduced in the loss function with a proper weighting factor to balance the overall accuracy. The proposed approach is illustrated by modeling the surface pressure distribution of the ONERA M6 wing in transonic flow, including different scenarios where the flow condition varies or a small number of high-fidelity data are available. The results demonstrate that the proposed model trained based on a decent number of low-fidelity data and a few high-fidelity data can accurately predict the surface pressure distribution on the transonic wing. The outperformance of the proposed model over other DNNs with a single fidelity has been reported.

Multi-source data fusion technique for parametric fault diagnosis in analog circuits

Input test signal plays important role in testing of analog circuits. Single type of input stimulus cannot maximally reveal the state of the circuit. To combat this shortcoming, this work proposes to integrate information from the output responses corresponding to different input stimuli and to use the combined information to improve the accuracy of fault diagnosis in analog circuits. The circuit under test is excited with different input signals and wavelet features are extracted from the output responses of the circuit. Ultimate fault features have been defined by applying data fusion algorithm to the sets of wavelet features obtained from individual output. Data fusion has been performed in two steps, data whitening and Principal component analysis (PCA). Fused features are used to train SVM (Support Vector Machine) classifier for fault diagnosis. The proposed approach is validated with three types of filter circuits, i.e. Sallen-Key band pass filter, four OPAMP high pass filter and elliptic low pass filter. The average accuracy of the proposed fault classification method has been found greater than 99.8% for all the test circuits. The proposed technique offers improved classification accuracy, lower computational burden and lesser implementation complexity.

Research on automatic physical testing method of relay protection equipment through data fusion technology

Intelligent substations can accomplish deeper and more complex substation information exchange and processing by virtue of their equipment intelligence and data integration. In this paper, a relay protection equipment test system for intelligent substations is investigated for intelligent relay protection equipment. By applying data fusion technology in the testing process, functions such as automatically obtaining the action information of secondary devices and judging the response status of secondary devices can be accomplished. Applying the test system proposed in this paper to high-voltage line protection devices, the results show that the relay protection equipment test system can optimize the relay protection equipment test process, which further improves the accuracy and efficiency of relay protection equipment testing.

Evolution and Quality Analysis Algorithm of Consumer Online Reviews Based on Data Fusion and Multiobjective Optimization

With the rise of network strategies, various businesses using the Internet as a platform have been vigorously developed, among which the scale of e‐commerce transactions has increased on a large scale. In order to deeply explore the role and advantages of data fusion and multiobjective optimization technology in consumer online reviews, this paper uses the new and old evaluation model comparison method, algorithm design method, and multiobject research method to collect samples, analyze the technical model, and streamline the algorithm. And it will create an analysis algorithm model that can improve and optimize the consumer’s current online reviews. First, we choose the electricity supplier on the platform of a total of four mobile phones grabbed 32,145 comments. Based on this research on the number of online comment fields of consumers, the results show that 78% of the comments are less than 55 words, indicating that most of the online comments left by consumers are short comments; at the same time, a small number of consumers have left detailed comments. Description, the longest of is reached 612 words. On this basis, further study the efficiency and function analysis of the algorithm proposed in this paper, and we can see that DCDG‐MOMA is used in 14‐7 and 28‐7 use cases as 1 and 2, respectively, which is the least, and at 40‐7 and 50‐7, the time used is 15 and 20 which is close to PBI, but it is also much less time than the MOMAD algorithm. This further shows that the algorithm really plays an effective role in the actual decision‐making process. It has basically realized a more efficient algorithm for consumer online reviews under the background of applying data fusion and multiobjective optimization technology.

Multi-source and multimodal data fusion for predicting academic performance in blended learning university courses

In this paper we apply data fusion approaches for predicting the final academic performance of university students using multiple-source, multimodal data from blended learning environments. We collect and preprocess data about first-year university students from different sources: theory classes, practical sessions, on-line Moodle sessions, and a final exam. Our objective is to discover which data fusion approach produces the best results using our data. We carry out experiments by applying four different data fusion approaches and six classification algorithms. The results show that the best predictions are produced using ensembles and selecting the best attributes approach with discretized data. The best prediction models show us that the level of attention in theory classes, scores in Moodle quizzes, and the level of activity in Moodle forums are the best set of attributes for predicting students’ final performance in our courses.

Time-Domain Data Fusion Using Weighted Evidence and Dempster-Shafer Combination Rule: Application in Object Classification.

To apply data fusion in time-domain based on Dempster–Shafer (DS) combination rule, an 8-step algorithm with novel entropy function is proposed. The 8-step algorithm is applied to time-domain to achieve the sequential combination of time-domain data. Simulation results showed that this method is successful in capturing the changes (dynamic behavior) in time-domain object classification. This method also showed better anti-disturbing ability and transition property compared to other methods available in the literature. As an example, a convolution neural network (CNN) is trained to classify three different types of weeds. Precision and recall from confusion matrix of the CNN are used to update basic probability assignment (BPA) which captures the classification uncertainty. Real data of classified weeds from a single sensor is used test time-domain data fusion. The proposed method is successful in filtering noise (reduce sudden changes—smoother curves) and fusing conflicting information from the video feed. Performance of the algorithm can be adjusted between robustness and fast-response using a tuning parameter which is number of time-steps().

Applying a fuzzy interval ordered weighted averaging aggregation fusion to nondestructive determination of retained austenite phase in D2 tool steel

In the present paper, application of data fusion coupled with three electromagnetic nondestructive technologies (magnetic hysteresis loop, Barkhausen noise, and eddy current) has been explored to achieve higher accuracy and reliability of measurements. The ability of the proposed methodology has been evaluated for determining microstructural changes of D2 cold work tool steel during tempering with focus on decomposition of retained austenite and determination of this phase, quantitatively. The proposed data fusion method takes advantage of ordered weighted averaging aggregation operator and fuzzy defined interval to fuse the data produced by different experiments to obtain more accurate and reliable results. The fusion process also uses redundant information produced by applying different mapping functions modeled by neural networks. The results of the experiments revealed that applying data fusion to the outputs obtained from different experiments produces more accurate results compared to the situation that only outputs of one experiment are used.

A Simple Indoor Localization Methodology for Fast Building Classification Models Based on Fingerprints

Indoor localization has received tremendous attention in the last two decades due to location-aware services being highly demanded. Wireless networks have been suggested to solve this problem in many research works, and efficient algorithms have been developed with precise location and high accuracy. Nevertheless, those approaches often have high computational and high energy consumption. Hence, in temporary environments, such as emergency situations, where a fast deployment of an indoor localization system is required, those methods are not appropriate. In this manuscript, a methodology for fast building of an indoor localization system is proposed. For that purpose, a reduction of the data dimensionality is achieved by applying data fusion and feature transformation, which allow us to reduce the computational cost of the classifier training phase. In order to validate the methodology, three different datasets were used: two of them are public datasets based mainly on Received Signal Strength (RSS) from different Wi-Fi access point, and the third is a set of RSS values gathered from the LED lamps in a Visible Light Communication (VLC) network. The simulation results show that the proposed methodology considerably amends the overall computational performance and provides an acceptable location estimation error.

An optimized data fusion method and its application to improve lateral boundary conditions in winter for Pearl River Delta regional PM2.5 modeling, China

Lateral boundary conditions (LBCs) are essential for chemical transport models to simulate regional transport; however they often contain large uncertainties. This study proposes an optimized data fusion approach to reduce the bias of LBCs by fusing gridded model outputs, from which the daughter domain's LBCs are derived, with ground-level measurements. The optimized data fusion approach follows the framework of a previous interpolation-based fusion method but improves it by using a bias kriging method to correct the spatial bias in gridded model outputs. Cross-validation shows that the optimized approach better estimates fused fields in areas with a large number of observations compared to the previous interpolation-based method. The optimized approach was applied to correct LBCs of PM2.5 concentrations for simulations in the Pearl River Delta (PRD) region as a case study. Evaluations show that the LBCs corrected by data fusion improve in-domain PM2.5 simulations in terms of the magnitude and temporal variance. Correlation increases by 0.13–0.18 and fractional bias (FB) decreases by approximately 3%–15%. This study demonstrates the feasibility of applying data fusion to improve regional air quality modeling.

Event-based sensor data exchange and fusion in the Internet of Things environments

Internet of Things (IoT) is a promising technology for improving our lives and society by integrating smart devices in our environment and paving the way for novel ICT application, spanning from smart cities to energy efficiency and home automation. However, such a vision encompasses the availability of thousands of smart devices, or even more, that continuously exchange a huge volume of data among each other and with cloud-based services, raising a big data problem. Such a problem can be approached by properly applying data fusion practices within an IoT infrastructure. Due to the characteristics and peculiarities of the communications among smart devices within the IoT, an event-based data fusion is needed, where devices exchange notifications of events among each others. Such data fusion should be focused on special devices where notification heterogeneity, and data source trust issues have to be faced with. Accordingly, the contribution of this work is proposing (i) a novel broker-less event-based communication protocol specifically tailored to sensors with constrained resources, (ii) a solution for flexible event-based communications among heterogeneous data sources, and (iii) an approach based on the theory of evidence for data fusion processes that depend on the matching and trust degree of the data to be fused.

Automatic Epilepsy Detection Based on Wavelets Constructed From Data

Epileptic seizures are caused by excessive, synchronized activity of large groups of neurons. In human electroencephalograph (EEG), they are reflected by multiple epileptic characteristic waves. Based on the idea of template matching, this paper presents a patient-specific approach for the automatic detection of epileptic seizures. In our method, a set of wavelets are constructed based on the epileptic characteristic waves extracted from training EEG signals, and then continuous wavelet transform (CWT) is performed on the recorded EEG. The coefficients of CWT reflect the similarity of the recorded EEG and the epileptic characteristic waveforms and thus can be used to detect if the epileptic characteristic waveforms exist in the EEG. After applying data fusion to the CWT coefficient matrices corresponding to the multiple constructed wavelets, the boundaries of seizures can be determined. In the experiment, our constructed wavelets performed better in the detection of epileptic characteristic waves compared to the Daubechies wavelet. We analyzed the EEG of 10 patients and our method detected 32 out of 34 seizures and declared five false detections. Therefore, our method is promising for the automatic detection of epileptic seizures and the real-time monitoring of patients’ EEG signal.

In-silico cardiac aging regulatory model including microRNA post-transcriptional regulation

In most developed countries, cardiovascular diseases are among the top causes of death and their development has been shown closely related to aging. In this context, because of their ability to pervasively influence gene networks, miRs have been found as possible key players in the development of cardiac pathologies, suggesting their potential role as therapeutic targets or diagnostic markers. Based on these assumptions, we hereby present a computational study that applies data fusion techniques coupled with network analysis theory to identify a regulatory model able to represent the relationship between key genes and miRs involved in cardiac senescence processes. The proposed model has been validated through an extensive literature analysis, which confirmed that 94% of the identified genes and miRs are related with cardiac senescence. Furthermore, two relevant genes of the model have been also validated by Western blot experiments on heart samples from young and old mice, confirming in vitro their ectopic expression in aged hearts. The pure computationally inferred model presented in the paper is therefore a good candidate to represent the relationship between key genes and miRs involved in cardiac senescence processes, and represents a reliable selection of genes and miRs for further studies, in order to elucidate and better detail their involvement in cardiac aging.

A Location Technique Based on Hybrid Data Fusion used to Increase the Indoor Location Accuracy

Systems based on wireless sensor have been presented as an alternative to location and navigation for visually impaired in environments where GPS is not effective. However, dealing with the information obtained from these sensors may present some challenges. The difficulties described by several authors are related mainly to the oscillation of the signals, which are susceptible to numerous interfering agents such as the scene itself, the presence of people, etc. It is necessary to increase the accuracy of the location in all the techniques observed. Therefore, this paper proposes to apply data fusion of wi-fi sensors with inertial sensors to allow visually impaired to location and navigation in indoor places using aspects of healthcare like sensor based systems embedded in wearable devices. The methodology adopted was associate redundant fusion and complementary fusion to construct a database obtained from several readings of the wi-fi sensors and an inertial sensor to construct a reference position to compare the data of the test readings to this reference and indicate the reliability in an indoor location. The results show that RSSI with SNR and magnetometer with gyroscope provide high error rates with raw and isolated data, but when fused, they show a more efficient location, decreasing the error rates observed in isolated mode. The error margins between the real position and the position indicated by the system were 0,386 m, 0,336 m and 0,148 m to RSSI with SNR, inertial and fusion application, respectively.

Investigating Potential Transit Ridership by Fusing Smartcard and Global System for Mobile Communications Data

The public transport industry faces challenges in catering to the variety of mobility patterns and corresponding needs and preferences of passengers. Travel habit surveys provide information on overall travel demand as well as its spatial variation. However, that information often does not include information on temporal variations. By applying data fusion to smartcard and Global System for Mobile Communications (GSM) data, researchers were able to examine spatial and temporal patterns of public transport usage versus overall travel demand. The analysis was performed by contrasting different spatial and temporal levels of smartcard and GSM data. The methodology was applied to a case study in Rotterdam, Netherlands, to analyze whether the current service span is adequate. The results suggested that there is potential demand for extending public transport service on both ends. In the early mornings, right before transit operations are resumed, an hourly increase in visitor occupancy of 33% to 88% was observed in several zones, showing potential demand for additional public transport services. The proposed data fusion method was shown to be valuable in supporting tactical transit planning and decision making and can easily be applied to other origin-destination transport data.