Cross-domain data fusion is becoming a key driver in the growth of numerous and diverse applications in the Internet of Things (IoT) era. We have proposed the concept of a new information platform, Geo-Centric Information Platform (GCIP), that enables IoT data fusion based on geolocation, i.e., produces spatio-temporal content (STC), and then provides the STC to users. In this environment, users cannot know in advance “when,” “where,” or “what type” of STC is being generated because the type and timing of STC generation vary dynamically with the diversity of IoT data generated in each geographical area. This makes it difficult to directly search for a specific STC requested by the user using the content identifier (domain name of URI or content name). To solve this problem, a new content discovery method that does not directly specify content identifiers is needed while taking into account (1) spatial and (2) temporal constraints. In our previous study, we proposed a content discovery method that considers only spatial constraints and did not consider temporal constraints. This paper proposes a new content discovery method that matches user requests with content metadata (topic) characteristics while taking into account spatial and temporal constraints. Simulation results show that the proposed method successfully discovers appropriate STC in response to a user request.

In view of the different spatial and temporal resolutions of observed multi-source heterogeneous carbon dioxide data and the uncertain quality of observations, a data fusion prediction model for observed multi-scale carbon dioxide concentration data is studied. First, a wireless carbon sensor network is created, the gross error data in the original dataset are eliminated, and remaining valid data are combined with kriging method to generate a series of continuous surfaces for expressing specific features and providing unified spatio-temporally normalized data for subsequent prediction models. Then, the long short-term memory network is used to process these continuous time- and space-normalized data to obtain the carbon dioxide concentration prediction model at any scales. Finally, the experimental results illustrate that the proposed method with spatio-temporal features is more accurate than the single sensor monitoring method without spatio-temporal features.

In IoT era, the growth of data variety is driven by cross-domain data fusion. In this paper, we advocate that “local production for local consumption (LPLC) paradigm” can be an innovative approach in cross-domain data fusion, and propose a new framework, geolocation-centric information platform (GCIP) that can produce and deliver diverse spatio-temporal content (STC). In the GCIP, (1) infrastructure-based geographic hierarchy edge network and (2) adhoc-based STC retention system are interplayed to provide both of geolocation-awareness and resiliency. Then, we discussed the concepts and the technical challenges of the GCIP. Finally, we implemented a proof-of-concepts of GCIP and demonstrated its efficacy through practical experiments on campus IPv6 network and simulation experiments.

The triaxial accelerometer is one of the most important sensors for human activity recognition (HAR). It has been observed that the relations between the axes of a triaxial accelerometer plays a significant role in improving the accuracy of activity recognition. However, the existing research rarely focuses on these relations, but rather on the fusion of multiple sensors. In this paper, we propose a data fusion-based convolutional neural network (CNN) approach to effectively use the relations between the axes. We design a single-channel data fusion method and multichannel data fusion method in consideration of the diversified formats of sensor data. After obtaining the fused data, a CNN is used to extract the features and perform classification. The experiments show that the proposed approach has an advantage over the CNN in accuracy. Moreover, the single-channel model achieves an accuracy of 98.83% with the WISDM dataset, which is higher than that of state-of-the-art methods.

To prevent constraints or defects of a single sensor from malfunctions, this paper proposes a fire detection system based on the Dempster-Shafer theory with multi-sensor technology. The proposed system operates in three stages: measurement, data reception and alarm activation, where an Arduino is tasked with measuring and interpreting the readings from three types of sensors. Sensors under consideration involve smoke, light and temperature detection. All the measured data are wirelessly transmitted to the backend Raspberry Pi for subsequent processing. Within the system, the Raspberry Pi is used to determine the probability of fire events using the Dempster-Shafer theory. We investigate moderate settings of the conflict coefficient and how it plays an essential role in ensuring the plausibility of the system's deduced results. Furthermore, a MySQL database with a web server is deployed on the Raspberry Pi for backlog and data analysis purposes. In addition, the system provides three notification services, including web browsing, smartphone APP, and short message service. For validation, we collected the statistics from field tests conducted in a controllable and safe environment by emulating fire events happening during both daytime and nighttime. Each experiment undergoes the No-fire, On-fire and Post-fire phases. Experimental results show an accuracy of up to 98% in both the No-fire and On-fire phases during the daytime and an accuracy of 97% during the nighttime under reasonable conditions. When we take the three phases into account, the accuracy in the daytime and nighttime increase to 97% and 89%, respectively. Field tests validate the efficiency and accuracy of the proposed system.

With the huge influx of various data nowadays, extracting knowledge from them has become an interesting but tedious task among data scientists, particularly when the data come in heterogeneous form and have missing information. Many data completion techniques had been introduced, especially in the advent of kernel methods — a way in which one can represent heterogeneous data sets into a single form: as kernel matrices. However, among the many data completion techniques available in the literature, studies about mutually completing several incomplete kernel matrices have not been given much attention yet. In this paper, we present a new method, called Mutual Kernel Matrix Completion (MKMC) algorithm, that tackles this problem of mutually inferring the missing entries of multiple kernel matrices by combining the notions of data fusion and kernel matrix completion, applied on biological data sets to be used for classification task. We first introduced an objective function that will be minimized by exploiting the EM algorithm, which in turn results to an estimate of the missing entries of the kernel matrices involved. The completed kernel matrices are then combined to produce a model matrix that can be used to further improve the obtained estimates. An interesting result of our study is that the E-step and the M-step are given in closed form, which makes our algorithm efficient in terms of time and memory. After completion, the (completed) kernel matrices are then used to train an SVM classifier to test how well the relationships among the entries are preserved. Our empirical results show that the proposed algorithm bested the traditional completion techniques in preserving the relationships among the data points, and in accurately recovering the missing kernel matrix entries. By far, MKMC offers a promising solution to the problem of mutual estimation of a number of relevant incomplete kernel matrices.

In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.

Misbehaving nodes intrinsic to the physical vulnerabilities of ad-hoc sensor networks pose a challenging constraint on the designing of data fusion. To address this issue, a statistics-based reputation method for reliable data fusion is proposed in this study. Different from traditional reputation methods that only compute the general reputation of a node, the proposed method modeled by negative binomial reputation consists of two separated reputation metrics: fusion reputation and sensing reputation. Fusion reputation aims to select data fusion points and sensing reputation is used to weigh the data reported by sensor nodes to the fusion point. So, this method can prevent a compromised node from covering its misbehavior in the process of sensing or fusion by behaving well in the fusion or sensing. To tackle the unexpected facts such as packet loss, a discounting factor is introduced into the proposed method. Additionally, Local Outlier Factor (LOF) based outlier detection is applied to evaluate the behavior result of sensor nodes. Simulations show that the proposed method can enhance the reliability of data fusion and is more accurate than the general reputation method when applied in reputation evaluation.

This paper addresses the sensing-throughput tradeoff problem by using cluster-based cooperative spectrum sensing (CSS) schemes in two-layer hierarchical cognitive radio networks (CRNs) with soft data fusion. The problem is formulated as a combinatorial optimization problem involving both discrete and continuous variables. To simplify the solution, a reasonable weight fusion rule (WFR) is first optimized. Thus, the problem devolves into a constrained discrete optimization problem. In order to efficiently and effectively resolve this problem, a lexicographical approach is presented that solving two optimal subproblems consecutively. Moreover, for the first optimal subproblem, a closed-form solution is deduced, and an optimal clustering scheme (CS) is also presented for the second optimal subproblem. Numerical results show that the proposed approach achieves a satisfying performance and low complexity.

In this paper, we propose a robust registration method, named Bounded-Variables Least Median of Squares (BVLMS). It overcomes both the misassociations and the ill-conditioning due to the interactions between Bounded-Variables Least Squares (BVLS) and Least Median of Squares (LMS). Simulation results demonstrate the feasibility of this new registration method.

Cognitive radio is a wireless technology aimed at improving the efficient use of the radio-electric spectrum, thus facilitating a reduction in the load on the free frequency bands. Cognitive radio networks can scan the spectrum and adapt their parameters to operate in the unoccupied bands. To avoid interfering with licensed users operating on a given channel, the networks need to be highly sensitive, which is achieved by using cooperative sensing methods. Current cooperative sensing methods are not robust enough against occasional or continuous attacks. This article outlines a Group Fusion method that takes into account the behaviour of users over the short and long term. On fusing the data, the method is based on giving more weight to user groups that are more unanimous in their decisions. Simulations of a dynamic environment with interference are performed. Results prove that when attackers are present (both reiterative or sporadic), the proposed Group Fusion method has superior sensing capability than other methods.

Spectrum sensing is a fundamental function for cognitive radio network to protect transmission of primary system. Cooperative spectrum sensing, which can help increasing sensing performance, is regarded as one of the most promising methods in realizing a reliable cognitive network. In such cooperation system, however the communication resources such as sensing time delay, control channel bandwidth and consumption energy for reporting the cognitive radio node's sensing results to the fusion center may become extremely huge when the number of cognitive users is large. In this paper, we propose an ordered sequential cooperative spectrum sensing scheme in which the local sensing data will be sent according to its reliability order to the fusion center. In proposed scheme, the sequential fusion process is sequentially conducted based on Dempster Shafer theory of evidence's combination of the reported sensing results. Above all, the proposed scheme is highly feasible due to the proposed two ordered sequential reporting methods. From simulation results, it is shown that the proposed technique not only keeps the same sensing performance of non-sequential fusion scheme but also extremely reduces the reporting resource requirements.

This letter proposes a novel censor-based scheme for cooperative spectrum sensing on Cognitive Radio Sensor Networks. A Takagi-Sugeno's fuzzy system is proposed to make the decision on the presence of the licensed user's signal based on the observed energy at each cognitive sensor node. The local spectrum sensing results are aggregated to make the final sensing decision at the fusion center after being censored to reduce transmission energy and reporting time. Simulation results show that significant improvement of the spectrum sensing accuracy, and saving energy as well as reporting time are achieved by our scheme.

A new adaptive model based on fuzzy integrals has been presented and used for combining three well-known methods, Eigenface, Fisherface and SOMface, for face classification. After training the competence estimation functions, the adaptive mechanism enables our system the filtering of unsure judgments of classifiers for a specific input. Comparison with classical and non-adaptive approaches proves the superiority of this model. Also we examined how these features contribute to the combined result and whether they can together establish a more robust feature.

In this paper, proactive data filtering (PDF) algorithm is proposed for data aggregation (or data fusion) in wireless sensor networks. The objective of the algorithm is to further reduce the energy consumption when sensor nodes perform data aggregation. In many applications, the sensor field will be overwhelmed by unnecessary and redundant sensory information when the sink node disseminates a query throughout the sensor field. In order to reduce the energy consumption, our scheme employs intelligent decision logic in the sensor node which delays or deactivates the transmission of its response. A performance evaluation shows that data aggregation with the PDF significantly improves energy-efficiency.

Recent progress in neural network research has demonstrated the usefulness of neural networks in a variety of areas. In this work, its application in the spatial resolution improvement of a remotely sensed low resolution thermal infrared image using high spatial resolution of visible and near-infrared images from Landsat TM sensor is described. The same work is done by an algebraic method. The tests developed are explained and examples of the results obtained in each test are shown and compared with each other. The error analysis is also carried out. Future improvements of these methods are evaluated.