Information Fusion Techniques Research Articles

Extending Appearance Based Gait Recognition with Depth Data

Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.

Fire Risk Assessment in Dense Urban Areas Using Information Fusion Techniques

A comprehensive fire risk assessment is very important in dense urban areas as it provides an estimation of people at risk and property. Fire policy and mitigation strategies in developing countries are constrained by inadequate information, which is mainly due to a lack of capacity and resources for data collection, analysis, and modeling. In this research, we calculated the fire risk considering two aspects, urban infrastructure and the characteristics of a high-rise building for a dense urban area in Zanjan city. Since the resources for this purpose were rather limited, a variety of information was gathered and information fusion techniques were conducted by employing spatial analyses to produce fire risk maps. For this purpose, the spatial information produced using unmanned aerial vehicles (UAVs) and then attribute data (about 150 characteristics of each high-rise building) were gathered for each building. Finally, considering high-risk urban infrastructures, like the position of oil and gas pipes and electricity lines and the fire safety analysis of high-rise buildings, the vulnerability map for the area was prepared. The fire risk of each building was assessed and its risk level was identified. Results can help decision-makers, urban planners, emergency managers, and community organizations to plan for providing facilities and minimizing fire hazards and solve some related problems to reduce the fire risk. Moreover, the results of sensitivity analysis (SA) indicate that the social training factor is the most effective causative factor in the fire risk.

Multivariate Analysis and Machine Learning for Ripeness Classification of Cape Gooseberry Fruits

This paper explores five multivariate techniques for information fusion on sorting the visual ripeness of Cape gooseberry fruits (principal component analysis, linear discriminant analysis, independent component analysis, eigenvector centrality feature selection, and multi-cluster feature selection.) These techniques are applied to the concatenated channels corresponding to red, green, and blue (RGB), hue, saturation, value (HSV), and lightness, red/green value, and blue/yellow value (L*a*b) color spaces (9 features in total). Machine learning techniques have been reported for sorting the Cape gooseberry fruits’ ripeness. Classifiers such as neural networks, support vector machines, and nearest neighbors discriminate on fruit samples using different color spaces. Despite the color spaces being equivalent up to a transformation, a few classifiers enable better performances due to differences in the pixel distribution of samples. Experimental results show that selection and combination of color channels allow classifiers to reach similar levels of accuracy; however, combination methods still require higher computational complexity. The highest level of accuracy was obtained using the seven-dimensional principal component analysis feature space.

A Review of Information Fusion Methods for Gas Turbine Diagnostics

The correct and early detection of incipient faults or severe degradation phenomena in gas turbine systems is essential for safe and cost-effective operations. A multitude of monitoring and diagnostic systems were developed and tested in the last few decades. The current computational capability of modern digital systems was exploited for both accurate physics-based methods and artificial intelligence or machine learning methods. However, progress is rather limited and none of the methods explored so far seem to be superior to others. One solution to enhance diagnostic systems exploiting the advantages of various techniques is to fuse the information coming from different tools, for example, through statistical methods. Information fusion techniques such as Bayesian networks, fuzzy logic, or probabilistic neural networks can be used to implement a decision support system. This paper presents a comprehensive review of information and decision fusion methods applied to gas turbine diagnostics and the use of probabilistic reasoning to enhance diagnostic accuracy. The different solutions presented in the literature are compared, and major challenges for practical implementation on an industrial gas turbine are discussed. Detecting and isolating faults in a system is a complex problem with many uncertainties, including the integrity of available information. The capability of different information fusion techniques to deal with uncertainty are also compared and discussed. Based on the lessons learned, new perspectives for diagnostics and a decision support system are proposed.

Observability Analysis and Adaptive Information Fusion for Integrated Navigation of Unmanned Ground Vehicles

Integrated navigation of unmanned ground vehicles (UGV) is significant for many advanced intelligent transportation system applications. Adaptive information fusion technique based on observability analysis has a great potential to enhance UGV integrated navigation systems for the capability of high-precision positioning and navigation. In an integrated navigation system, the tolerance against unknown and time-varying observation conditions is a key factor to satisfy the specific requirements of high-precision, self-adaption, and high reliability. Thus, a novel adaptive federated Kalman filter (FKF) is proposed with time-varying information sharing factors based on the criteria for the degree of observability. In addition, an error-state cascaded integration architecture is designed for UGV integrated navigation. Simulation with real datasets gathered from road tests in urban areas showed that the new adaptive integrated navigation system can autonomously update FKF information sharing factors according to the measurement quality and the observability of each navigation error-state. Therefore, the accuracy, robustness, and fault-tolerance ability of the whole system can be effectively improved in a high dynamic environment.

A combined fuzzy multicriteria decision‐making approach for evaluating hospital website quality

AbstractDevelopments in the health care industry in the last decade have forced companies to improve their website quality with the goal of attaining a sustainable competitive advantage through e‐business models. Here, we evaluate and measure the website quality of hospitals while considering the interactions among evaluation criteria. For this purpose, the fuzzy decision making trial and evaluation laboratory (DEMATEL) method, which copes with the interactions among the evaluation criteria, is presented. In addition, the generalized Choquet fuzzy integral (GCFI), non‐additive information fusion technique, is proposed to aggregate the experts' preferences and to calculate the overall website quality of hospitals. Finally, a sensitivity analysis is used to observe the changes in evaluation results of hospitals when assigning different weight combinations to the evaluation criteria. The proposed model is the first to evaluate the website quality of hospitals operating in Turkey.

Linking Gaussian process regression with data-driven manifold embeddings for nonlinear data fusion.

In statistical modelling with Gaussian process regression, it has been shown that combining (few) high-fidelity data with (many) low-fidelity data can enhance prediction accuracy, compared to prediction based on the few high-fidelity data only. Such information fusion techniques for multi-fidelity data commonly approach the high-fidelity model f h(t) as a function of two variables (t, s), and then use f l(t) as the s data. More generally, the high-fidelity model can be written as a function of several variables (t, s 1, s 2….); the low-fidelity model f l and, say, some of its derivatives can then be substituted for these variables. In this paper, we will explore mathematical algorithms for multi-fidelity information fusion that use such an approach towards improving the representation of the high-fidelity function with only a few training data points. Given that f h may not be a simple function-and sometimes not even a function-of f l, we demonstrate that using additional functions of t, such as derivatives or shifts of f l, can drastically improve the approximation of f h through Gaussian processes. We also point out a connection with 'embedology' techniques from topology and dynamical systems. Our illustrative examples range from instructive caricatures to computational biology models, such as Hodgkin-Huxley neural oscillations.

Constructing the geometric Bonferroni mean from the generalized Bonferroni mean with several extensions to linguistic 2-tuples for decision-making

The geometric Bonferroni mean (GeoBM), which was designed as a primitive attempt to extend the Bonferroni mean (BM), has enriched the family of BM-type aggregation functions in a variety of decision-making contexts to model homogeneous relations among certain attributes. Although it is difficult to dispute the versatility of GeoBM-based information fusion techniques, a key disadvantage of existing GeoBM developments is that they provide no specification regarding how the GeoBM should be designed, constructed, and applied, which has led to the existence of disparate GeoBM definitions and non-unified and unsound generalizations. This has resulted in some confusion within the GeoBM field and has thus presented significant barriers to researchers hoping to apply the latest developments in their specific areas of interest. In this study, we propose a novel GeoBM construction based on the generalized BM (GenBM) by selecting suitable components of the GenBM to provide a decomposable descriptive formulation that is easy to understand and interpret. A modified GeoBM (MGeoBM) is also proposed to enhance the capacity for modeling real-life situations. Furthermore, we demonstrate that the concept of generating the GeoBM from the GenBM can be readily adopted in a generalized extended BM (EBM) framework to construct an extended GeoBM (EGeoBM) that can model heterogeneous relations among certain attributes. The proposed calibrated EBM is an accurate update to the standard EBM, as can be seen on noting that independent attributes can be modeled by the arithmetic mean rather than by the power mean. Several natural extensions of the EGeoBM, e.g., the extended MGeoBM (EMGeoBM) and its weighted form, together with their degenerate forms under various assumptions, are discussed and finally applied to a linguistic 2-tuple environment. Comparisons among several existing linguistic 2-tuple aggregation functions demonstrate that the proposed EMGeoBM performs more robustly than the EBM, providing relatively stable alternative rankings.

The Recognition of Motion Intention of Knee Joint Based on Piezoelectric Signals

Aiming at the human body exoskeleton motion intention recognition process, based on the pressure signals of muscle groups of control, building joint motion information acquisition system, the application of multi-sensor information fusion technique based on neural network, based on the piezoelectric signal muscle as input and output of the joint angle trajectory motion intention model, calculate the joint exercise intention and angle track. Finally, the knee flexion and extension movement as the main object of study, through calculation and practical test, the ideal results are obtained. It shows that the motion signals of the knee joint can be reflected by the piezoelectric signals collected during the motion of the knee joint.

Modeling Antibacterial Activity with Machine Learning and Fusion of Chemical Structure Information with Microorganism Metabolic Networks.

Predicting the activity of new chemical compounds over pathogenic microorganisms with different metabolic reaction networks (MRN s) is an important goal due to the different susceptibility to antibiotics. The ChEMBL database contains >160 000 outcomes of preclinical assays of antimicrobial activity for 55 931 compounds with >365 parameters of activity (MIC, IC50, etc.) and >90 bacteria strains of >25 bacterial species. In addition, the Leong and Barabàsi data set includes >40 MRNs of microorganisms. However, there are no models able to predict antibacterial activity for multiple assays considering both drug and MRN structures at the same time. In this work, we combined perturbation theory, machine learning, and information fusion techniques to develop the first PTMLIF model. The best linear model found presented values of specificity = 90.31/90.40 and sensitivity = 88.14/88.07 in training/validation series. We carried out a comparison to nonlinear artificial neural network (ANN) techniques and previous models from the literature. Next, we illustrated the practical use of the model with an experimental case of study. We reported for the first time the isolation and characterization of terpenes from the plant Cissus incisa. The antibacterial activity of the terpenes was experimentally determined. The more active compounds were phytol and α-amyrin, with MIC = 100 μg/mL for Vancomycin-resistant Enterococcus faecium and Acinetobacter baumannii resistant to carbapenems. These compounds are already known from other sources. However, they have been isolated and evaluated for the first time here against several strains of multidrug-resistant bacteria including World Health Organization (WHO) priority pathogens. Last, we used the model to predict the activity of these compounds versus other microorganisms with different MRNs in order to find other potential targets.

A Sustainable Approach for Assessing Safety Management in Subterranean Infrastructure excavation Using Multi-Criteria Decision-Making

Subterranean infrastructure excavation necessitates stringent safety assessment methodologies due to its complex nature. This study addresses this imperative by presenting an integrated framework based on the Decision-Making Trial and Evaluation Laboratory (DEMATEL) technique. This methodology amalgamates multi-source information fusion and DEMATEL-driven multi-criteria decision-making techniques. The approach evaluates safety parameters within subterranean infrastructure excavation by synthesizing expert insights, on-site measured data, and predefined criteria. Through a systematic construction of judgment matrices, our approach offers a standardized means to assess observed values against established safety benchmarks. The collaborative synthesis of expert assessments and empirical data not only informs the comprehensive relation matrix, highlighting intricate interdependencies among key factors but also fosters a structured pathway for evaluating safety. This integrated methodology, adaptable across diverse excavation scenarios, equips stakeholders with a holistic understanding of safety factors within subterranean construction. Facilitating informed decision-making, enables the optimization of safety protocols and interventions, thereby enhancing overall safety standards within such critical infrastructure projects.

Multifocus Image Fusion Based on Fast Guided Filter and Focus Pixels Detection

As an effective technique of information fusion, multifocus image fusion has attracted increasing attention for image processing and computer vision. The goal of multifocus image fusion method is integrating all focus information from source images into fused result. In this paper, we propose a novel simple and effective multifocus image fusion technique based on fast guided filter and focus pixels detection. In order to detect the focused pixels correctly from source images, we develop a new multi-scale sum modified Laplacian technique. For the decision maps learning stage, based on the block consistency verification and faster guided filter techniques, we generate a series of binary focus decision maps to express the focus property of each pixel. In the fusion stage, we employ neighbor distance filter to extract detail pixels of source images, then the informative highpass images and the energetic lowpass images can be generated. The fused results are developed by constructing the corresponding decision maps and the neighbor distance filtered images. Compared with some state-of-the-art fusion methods, experimental results clearly demonstrate the superiority of the proposed method in terms of both comprehensive subjective assessment and some well-known quantitative evaluations.

Enhancing multiple attribute group decision making flexibility based on information fusion technique and hesitant Pythagorean fuzzy sets

Abstract The aim of this paper is to develop some novel hesitant Pythagorean fuzzy sets (HPFSs) based methods in enhancing fuzzy related problems flexibility. In view of the effectiveness of hesitant fuzzy sets (HFSs) for expressing the hesitant situation, and the powerfulness of Pythagorean fuzzy sets (PFSs) in handling vagueness and uncertainty, we combine the best aspects of HFSs and PFSs and consider a new concept called the HPFSs. Firstly, some existing basic properties and operators are extended and improved in detail. For the sake of application, considering the deficiencies of pessimistic-optimistic normalization principles in dealing with hesitant fuzzy related sets, on the basis of lowest common multiple principle in number theory, an improved normalization algorithm is proposed to reserve the fidelity of original information. Then, a flexible and multipurpose generalized distance measure for HPFSs is presented. Further, under the HPFSs environment, a multiple attribute group decision making method based on the extended hesitant Pythagorean fuzzy VIKOR is presented. Three numerical examples, one from the bidirectional approximate reasoning system and other from the medical diagnosis and selection model of health management center, are presented to elaborate on the performance of our approach and compared their results with the several existing approaches results.

Multi-Sensor Fusion-Based Permanent Magnet Demagnetization Detection in Permanent Magnet Synchronous Machines

When permanent magnet (PM) demagnetization in a PM synchronous machine (PMSM) occurs, the demagnetization characteristic information is usually coupled with other characteristics of the PMSM which may demonstrate similar features. Therefore, it is difficult to accurately detect the demagnetization by monitoring only one parameter. This paper explores the use of multi-sensor information, namely, acoustic noise and torque, for demagnetization detection through the information fusion technique. The acoustic noise and torque information are processed and analyzed using wavelet transforms for filtering and extracting features. Bayesian network-based multi-sensor information fusion is then proposed to detect the demagnetization ratio from the extracted features. The proposed approach is experimentally verified on a laboratory PMSM and compared with single-sensor dection methods.

WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming

The ability to automatically monitor agricultural fields is an important capability in precision farming, enabling steps towards more sustainable agriculture. Precise, high-resolution monitoring is a key prerequisite for targeted intervention and the selective application of agro-chemicals. The main goal of this paper is developing a novel crop/weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Although a map can be generated by processing single segmented images incrementally, this requires additional complex information fusion techniques which struggle to handle high fidelity maps due to their computational costs and problems in ensuring global consistency. Moreover, computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB (red, green, and blue) inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics.

Identifying people at risk of developing type 2 diabetes: A comparison of predictive analytics techniques and predictor variables

BackgroundThe present study aims to identify the patients at risk of type 2 diabetes (T2D). There is a body of literature that uses machine learning classification algorithms to predict development of T2D among patients. The current study compares the performance of these classification algorithms to identify patients who are at risk of developing T2D in short, medium and long terms. In addition, the list of predictor variables important for prediction for T2D progression is provided. MethodsThis study uses 10,911 records generated in 36 clinics from the 15th of November 2008–15th of November 2016. Syntactic minority oversampling and random under sampling were used to create a balanced dataset. The performance of Neural Networks, Support Vector Machines, Decision Tress and Logistic Regression to identify patients developing T2D in short, medium and long terms was compared. The measures were Area Under Curve, Sensitivity, Specificity, Matthew correlation coefficient and Mean Calibration Error. Through importance analysis and information fusion techniques the predictors of developing T2D were identified for short, medium and long-term risk analysis. ResultsThe findings show that the performance of analytics techniques depends on both period and purpose of prediction whether the prediction is to identify people who will not develop T2D or to determine at risk patients. Oversampling as opposed to under sampling improved performance. 16 predictors and their importance to determine patients at risk of T2D in short, medium and long terms were identified. ConclusionsThis study provides guidelines for an automated system to prompt patients for screening. Several predictors are reportable by patients, others can be examined by physicians or ordered for further lab examination, which offers a potential reduction of the burden placed upon the clinical settings.

The research of multi-information fusion in electrostatic monitoring for rolling bearing

The monitoring of rolling bearing with electrostatic method is a novel technology at present. Few experiments have been investigated with information fusion technique to improve the efficient of monitoring. This paper introduced a new method called moving window local outlier factor (MWLOF) to process electrostatic monitoring signals of rolling bearing under variable operating conditions. In the load and accelerated life tests, the extracted features can reduce the impact and accurately reflect the wear condition of the bearings compared with traditional features. It can detect weak faults earlier and has a better sensitivity and performance degradation trend than conventional techniques, which has a bright future in industrial application.

Information Fusion for Human Action Recognition via Biset/Multiset Globality Locality Preserving Canonical Correlation Analysis.

In this paper, we study the problem of human action recognition, in which each action is captured by multiple sensors and represented by multisets. We propose two novel information fusion techniques for fusing the information from multisets. The first technique is biset globality locality preserving canonical correlation analysis (BGLPCCA), which aims to learn the common feature subspace between two sets. The second technique is multiset globality locality preserving canonical correlation analysis (MGLPCCA), which aims to deal with three or more sets. The proposed BGLPCCA and MGLPCCA are able to learn a low-dimensional common subspace that preserves the local and global structures of data samples. Moreover, two novel descriptors are presented for both depth and skeleton. We then propose a new human action recognition framework employing the proposed BGLPCCA or MGLPCCA to learn the shared subspace from multiple sets of features including skeleton, depth, and optical flow. Extensive experiments on five publicly available datasets (MSR Action3D, UTD multimodal human action dataset, multimodal action database, Kinect activity recognition dataset, and SBU Kinect interaction dataset) demonstrate the effectiveness of the proposed framework.

A Reliability Game for Source Factors and Situational Awareness Experimentation

Systems to support Situational Awareness take increasingly advantage of data and information fusion techniques. Due to the rise in the variety of information sources (e.g., sensors, open-source, intelligence, historical databases) and their possible lack of veracity those techniques should account for source reliability. Although the appropriate mathematical instruments exist, it still needs to be fully understood what are the factors that contribute to source reliability and what is their relative and total impact on Situation Assessment, which is the process that builds up Situational Awareness. In order to characterise source factors impact on human belief assessment the Reliability Game has been developed. This is a data exchange game in which the players are requested to perform Situational Assessment tasks by mentally processing incoming information and meta-information, abstracted and provided through cards. This paper presents the method, the design choices and shows through a qualitative analysis that the proposed approach is indeed able to capture elements of source factors impact on players’ belief changes. Data collected through the game will be further analysed to inform and improve the design of information correction methods in multi-source information fusion systems.

Innovative assessment scheme of navigation risk based on improved multi-source information fusion techniques

To deal with highly time complexity and unstable assessments for conflicting evidences from various navigation factors, we put forward an innovative assessment scheme of navigation risk based on the improved multi-source information fusion techniques. Different from the existing studies, we first deduce the nonlinear support vector machine classification model for the general scenario. The slack variable is adaptively computed based on the Euclidean distance ratio. Considering the unsatisfactory characteristics of the standard Dempster–Shafer evidence theory, the optimal combination rule is derived step by step. What"s more, the lowly dimensional Kalman filter is applied to forecast the navigation risk. Simultaneously, the time complexity of each technique is analyzed. With respect to the vessel navigation risk, the assessment results are provided to indicate the reliability and efficiency of the proposed scheme.