Multiple Heterogeneous Sensors Research Articles

Integration of multisensor hybrid reasoners to support personal autonomy in the smart home.

The deployment of the Ambient Intelligence (AmI) paradigm requires designing and integrating user-centered smart environments to assist people in their daily life activities. This research paper details an integration and validation of multiple heterogeneous sensors with hybrid reasoners that support decision making in order to monitor personal and environmental data at a smart home in a private way. The results innovate on knowledge-based platforms, distributed sensors, connected objects, accessibility and authentication methods to promote independent living for elderly people. TALISMAN+, the AmI framework deployed, integrates four subsystems in the smart home: (i) a mobile biomedical telemonitoring platform to provide elderly patients with continuous disease management; (ii) an integration middleware that allows context capture from heterogeneous sensors to program environment's reaction; (iii) a vision system for intelligent monitoring of daily activities in the home; and (iv) an ontologies-based integrated reasoning platform to trigger local actions and manage private information in the smart home. The framework was integrated in two real running environments, the UPM Accessible Digital Home and MetalTIC house, and successfully validated by five experts in home care, elderly people and personal autonomy.

A Dynamic Evidential Network for Fall Detection

This study is part of the development of a remote home healthcare monitoring application designed to detect distress situations through several types of sensors. The multisensor fusion can provide more accurate and reliable information compared to information provided by each sensor separately. Furthermore, data from multiple heterogeneous sensors present in the remote home healthcare monitoring systems have different degrees of imperfection and trust. Among the multisensor fusion methods, Dempster-Shafer theory (DST) is currently considered the most appropriate for representing and processing the imperfect information. Based on a graphical representation of the DST called evidential networks, a structure of heterogeneous data fusion from multiple sensors for fall detection has been proposed. The evidential networks, implemented on our remote medical monitoring platform, are also proposed in this paper to maximize the performance of automatic fall detection and thus make the system more reliable. However, the presence of noise, the variability of recorded signals by the sensors, and the failing or unreliable sensors may thwart the evidential networks performance. In addition, the sensors signals nonstationary nature may degrade the experimental conditions. To compensate the nonstationary effect, the time evolution is considered by introducing the dynamic evidential network which was evaluated by the simulated fall scenarios corresponding to various use cases.

Efficient allocation of resources in multiple heterogeneous Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are useful for a wide range of applications, from different domains. Recently, new features and design trends have emerged in the WSN field, making those networks appealing not only to the scientific community but also to the industry. One such trend is the running different applications on heterogeneous sensor nodes deployed in multiple WSNs in order to better exploit the expensive physical network infrastructure. Another trend deals with the capability of accessing sensor generated data from the Web, fitting WSNs in novel paradigms of Internet of Things (IoT) and Web of Things (WoT). Using well-known and broadly accepted Web standards and protocols enables the interoperation of heterogeneous WSNs and the integration of their data with other Web resources, in order to provide the final user with value-added information and applications. Such emergent scenarios where multiple networks and applications interoperate to meet high level requirements of the user will pose several changes in the design and execution of WSN systems. One of these challenges regards the fact that applications will probably compete for the resources offered by the underlying sensor nodes through the Web. Thus, it is crucial to design mechanisms that effectively and dynamically coordinate the sharing of the available resources to optimize resource utilization while meeting application requirements. However, it is likely that Quality of Service (QoS) requirements of different applications cannot be simultaneously met, while efficiently sharing the scarce networks resources, thus bringing the need of managing an inherent tradeoff. In this paper, we argue that a middleware platform is required to manage heterogeneous WSNs and efficiently share their resources while satisfying user needs in the emergent scenarios of WoT. Such middleware should provide several services to control running application as well as to distribute and coordinate nodes in the execution of submitted sensing tasks in an energy-efficient and QoS-enabled way. As part of the middleware provided services we present the Resource Allocation in Heterogeneous WSNs (SACHSEN) algorithm. SACHSEN is a new resource allocation heuristic for systems composed of heterogeneous WSNs that effectively deals with the tradeoff between possibly conflicting QoS requirements and exploits heterogeneity of multiple WSNs.

Evidential Network-Based Multimodal Fusion for Fall Detection

The multi-sensor fusion can provide more accurate and reliable information compared to information from each sensor separately taken. Moreover, the data from multiple heterogeneous sensors present in the medical surveillance systems have different degrees of uncertainty. Among multi-sensor data fusion techniques, Bayesian methods and Evidence theories such as Dempster-Shafer Theory (DST) are commonly used to handle the degree of uncertainty in the fusion processes. Based on a graphic representation of the DST called Evidential Networks, we propose a structure of heterogeneous multi-sensor fusion for falls detection. The proposed Evidential Network (EN) can handle the uncertainty present in a mobile and a fixed sensor-based remote monitoring systems (fall detection) by fusing them and therefore increasing the fall detection sensitivity compared to the a separated system alone.

Performance optimization of multiple interconnected heterogeneous sensor networks via collaborative information sharing

Interconnecting multiple sensor networks is a relatively new research field which has emerged in the Wireless Sensor Network domain. Wireless Sensor Networks WSNs have typically been seen as logically separate, and few works have considered interconnection and interaction between them. Interconnecting multiple heterogeneous sensor networks therefore opens up a new field besides more traditional research on, e.g., routing, self organization, or MAC layer development. Up to now, some approaches have been proposed for interconnecting multiple sensor networks with goals like information sharing or monitoring multiple sensor networks. In this paper, we propose to utilize inter-WSN communication to enable Collaborative Performance Optimization, i.e., our approach aims to optimize the performance of individual WSNs by taking into account measured information from others. The parameters to be optimized are energy consumption on the one hand and sensing quality on the other.

COSE: A Query-Centric Framework of Collaborative Heterogeneous Sensor Networks

Demands on better interacting with physical world require an effective and efficient collaboration mechanism of multiple heterogeneous sensor networks. Previous works mainly focus on each single and specific sensor network, thus failing to address issues in the newly emerging scenario. In this paper, we propose COSE, a query-centric framework of collaborative heterogeneous sensor networks, where sensor networks collaborate with each other for effective and efficient processing of queries. Finding an optimal strategy of query processing with respect to energy efficiency is a crucial issue in COSE, which we formulate into an optimization problem, called EE-QPS. We prove the NP-hardness of EE-QPS, and then design a heuristic approach named IAP by utilizing the correlation (called implication in this paper) among different sensor networks. The experimental results demonstrate that in the context of COSE, IAP achieves optimized energy efficiency under various settings.

Multifunctional optical MEMS sensor platform with heterogeneous fiber optic Fabry–Pérot sensors for wireless sensor networks

A multifunctional optical sensor platform based on the microelectromechanical systems (MEMS) technology is developed with the aim of miniaturizing conventional bulky optical measurement systems for application in future optical wireless sensor networks (WSNs). Low-coherence interferometry is used as the sensing principle, which allows for high performance sensing with multiple heterogeneous sensors. The entire platform with the associated electric circuit has a footprint of 2in.×1.8in.×0.75in., which are integrated with a conventional WSN module to form an optical WSN node. The multifunctionality of the platform is successfully demonstrated for simultaneous interrogation of a Fabry–Pérot (FP) pressure sensor and a FP temperature sensor. To prove the optical sensor platform's multifunctionality, chemical sensing is also demonstrated with a FP sensor. The multifunctional optical sensor platform and the optical WSN node will enable optical WSNs, which are expected to impact many fronts including those space-constrained applications and monitoring in harsh environments.

An Efficient Data Association Algorithm for Single Target Tracking with Multiple Centralized Heterogeneous Sensors

An efficient data association algorithm is presented to track a single target with multiple centralized heterogeneous sensors. The sharing parts of measurements from different sensors are used to accomplish the data association, which utilizes the 2 test match combined with Nearest Neighbor association strategy to depress the dummy measurements. Targetoriginated measurement matched pair will be retained and fused to update the target track. Unscented kalman filter is deployed to target state estimation for both the dynamic and measurement model are nonlinear. Simulations validate the algorithm and conclusions.

A context management architecture for large-scale smart environments

Context-aware architecture collects various context data from heterogeneous sensors and provides an intelligent service by exploiting the collected data. In this article we explain the generalized context-aware software architecture for heterogeneous smart environments. The proposed architecture integrates large-scale contexts from multiple heterogeneous sensors, and makes a semantic decision by fusing and reasoning about the collected contexts. Moreover, we discuss a designed architecture that manages communities between large numbers of heterogeneous information entities and enhances intelligence abilities.

Testing Multilayer Flexible Wireless Multisensor Platforms

Smart wireless sensor systems that incorporate multiple sensors often cannot be implemented on a single chip. Advanced integration and assembly allows for a more complex conjugation and configuration of multiple system modules implemented under different technologies together in a small tiny package. In tiny sensor systems such as these, three common challenges seen across most platforms are: the difficult test access due to non-standard assembly and packaging, the testing of multiple heterogeneous sensor species, and the strict dimensional requirements limiting availability of any built-in hardware for testing. We discuss the method of testing by modules for testing a multilayer mechanically flexible wireless multisensor platform. A hierarchical test flow is presented for verifying the functionalities and assessing the performance of the various modules of the system. We also present an example of a design for testing feature, a built-in test point access bus that improves reliability for test point access, reduces the cost of testing and overall system bill-of-material, as well, increases test channel bandwidth allowing for full access to all critical subsystem nodes. Lastly, we provide examples of subsystem performance assessment and verification testing of selected sensor species on the multisensor platform as well as the system power consumption versus transmission range, to illustrate the usefulness of the test concepts, flow, and features introduced.

A Dynamic Channel Selection Strategy for Dense-Array ERP Classification

The goal of this paper is to introduce a new strategy to accurately classify event-related potentials (ERPs), recorded using dense electrode arrays, into predefined brain activity categories. The challenge is to exploit the enhanced spatial information offered by dense arrays while overcoming the significant increase in the dimensionality problem introduced by the large increase in the number of channels. These conflicting objectives are achieved by introducing a spatiotemporal-array model to observe the dense-array ERP amplitude variations across channels and time, simultaneously. To account for latency variations and EEG noise in the array elements, each spatiotemporal element in the array is initially modeled as a Gaussian random variable. A two-step process that uses the Kolmogrov-Smirnov test and the Lilliefors test is formulated to select the array elements that have different Gaussian densities across all ERP categories. Selecting spatiotemporal elements that fit the assumed model and also statistically differ across the ERP categories not only ensures high classification accuracies but also decreases the dimensionality significantly. The selection is dynamic in the sense that selecting spatiotemporal-array elements corresponds to selecting ERP samples of different channels at different time instants. Each selected array element is classified using a univariate Gaussian classifier, and the resulting decisions are fused into a decision fusion vector that is classified using a discrete Bayes classifier. By converting an inherently multivariate classification problem into a simpler problem involving only univariate classifications, the dimensionality problem that plagues the design of practical multivariate ERP classifiers is circumvented. Consequently, classifiers can be designed to classify the ERPs that are unique to an individual without having to collect a prohibitively large ERP dataset from him/her. The application of the resulting dynamic-channel-selection-based classification strategy is demonstrated by designing and testing classifiers for eight subjects using ERPs from a Stroop color test and it is shown that the strategy yields high classification accuracies. Finally, it is noted that because of the generalized formulation of the strategy, it can be applied to various other problems involving the classification of multivariate signals acquired from multiple identical or multiple heterogeneous sensors.

Multi-camera people tracking using evidential filters

This work proposes a novel filtering algorithm that constitutes an extension of Bayesian particle filters to the Dempster–Shafer theory. Our proposal solves the multi-target problem by combining evidences from multiple heterogeneous and unreliable sensors. The modelling of uncertainty and absence of knowledge in our approach is specially attractive since it does not require to specify prior nor conditionals that might be difficult to obtain in complex problems. The algorithm is employed to propose a novel solution to the multi-camera people tracking problem in indoor environments. For each particle, the evidence of finding the person being tracked at the particle location is calculated by each sensor. Sensors also provide a degree of evidence about their reliability. The reliability is calculated based on the visible portion of the targets and their occlusions. Evidences collected from the camera set are fused considering their reliability to calculate the best hypothesis. The experiments conducted in several environments show the validity of the proposal.

A Multisensor Decision Fusion System for Terrain Safety Assessment

This paper describes an onboard automated hybrid reasoning system for terrain safety assessment using multiple heterogeneous sensors onboard a spacecraft. An innovative feature of this system is integration of multiple sensing modalities and different reasoning engines into a unified approach. Three different frameworks for representation of data uncertainty are considered: fuzzy set theory, Bayesian probability theory, and Dempster-Shafer belief theory. The hybrid reasoning system is composed of three subsystems, namely, multisensor fusion, multidecision fusion, and tier-based fusion selection, where each tier represents a range of spacecraft altitudes. Simulation results are presented to illustrate the multisensor decision fusion methodology described in this paper. The developed capabilities will enable future spacecraft to land safely in more challenging planetary regions with scientifically interesting terrain features.

Combined person tracking and classification in a network of chemical sensors

Transportation infrastructures play a crucial role in the way of life and the economic vitality of a modern society. Access points like stations, airports or harbors are among the most critical elements in these infrastructures because they offer the possibility to bring in hazardous materials that can be used for attacks against people and the transportation network itself. A timely recognition of such threats is essential and can be significantly supported by systems that monitor critical areas continuously and call the security personnel in case of anomalies. We are describing the concept and the realization of an indoor security assistance system for real-time decision support. The system is specifically designed for the surveillance of entrance areas in transportation access facilities and consists of multiple heterogeneous sensors: Chemical sensors detecting hazardous materials provide data for the classification of persons. But due to their limited spatio-temporal resolution, a single chemical sensor cannot localize a substance and assign it to a person. We compensate for this deficiency by fusing the output of multiple, distributed chemical sensors with kinematical data from laser range-scanners. Both tracking and fusion of tracks with chemical attributes can be processed within a single framework called Probabilistic Multi-Hypothesis Tracking (PMHT). An extension of PMHT for dealing with classification measurements (PMHT-c) already exists. We show how PMHT-c can be applied to assign chemical attributes to person tracks. This affords the localization of threats and a timely notification of the security personnel.

COSMOS: A Middleware for Integrated Data Processing over Heterogeneous Sensor Networks

With the increasing need for intelligent environment monitoring applications and the decreasing cost of manufacturing sensor devices, it is likely that a wide variety of sensor networks will be deployed in the near future. In this environment, the way to access heterogeneous sensor networks and the way to integrate various sensor data are very important. This paper proposes the common system for middleware of sensor networks (COSMOS), which provides integrated data processing over multiple heterogeneous sensor networks based on sensor network abstraction called the sensor network common interface. Specifically, this paper introduces the sensor network common interface which defines a standardized communication protocol and message formats used between the COSMOS and sensor networks.

대규모 다중 센서 네트워크에서 효과적인 경로 관리 기법

다수의 이종 센서 네트워크가 넓은 지역에 포설된 경우 각 센서 네트워크에서 수집된 데이터를 싱크 (sink)에서 게이트웨이 (GW)로 전송하기 위해 릴레이 포인트 (relay point: RP)들로 구성된 전달망이 이용된다. 전달망 내에서 RP의 위치는 전달망의 에너지 효율을 결정하는 중요한 요인이지만 전달망 내의 싱크의 수가 동적으로 변하고 특히 싱크가 이동하는 경우 이들의 경로를 미리 알지 못한다면 각 RP의 최적 위치를 전달망 포설시에 결정할 수 없게 된다. 이를 해결하기 위해 본 논문에서는 RP를 격자 모양으로 포설한 트리 기반 전달망에서 RP의 운용 비용과 경로 관리 부하 측면에서 효율적인 싱크와 GW 사이의 경로 관리 기법을 제안한다. 제안 기법의 성능은 단일 경로 설정 비용에 대한 수학적 분석과 ns-2를 이용한 모의 실험을 통해 검증되었다. 분석 결과 제안 기법은 싱크과 GW 사이의 데이터 전송 시간, 전달망의 서비스 지속 시간 및 경로 관리 부하 측면에서 AODV보다 우수하였다. In the environment with multiple heterogeneous wireless sensor networks with a single point of sensed data collection or a gateway (GW), relay points (RPs) may be required for the energy efficient delivery of sensed data from static or mobile sinks to the GW. The optimal placement of RPs becomes an even more difficult problem if static sinks are dynamically added or the trajectory of mobile sinks can not be known in advance. In order to resolve this problem, we propose a mechanism to deploy RPs in a grid pattern and to use the tree-based relaying network for reducing the cost of the RP and for reducing the control overhead incurred by the route setup from sinks to the GW. For the performance evaluation of our proposed mechanism, we have carried out a numerical analysis on a single route setup from a sink to the GW and, for more general performance evaluations, ns-2 based simulations have been carried out. According to the performance evaluation results, our tree-based relaying network mechanism outperforms that based on AODV in terms of the data delivery time, the network service time and the control overhead.

Multisensory processing for speech enhancement and magnitude-normalized spectra for speech modeling

In this paper, we tackle the problem of speech enhancement from two fronts: speech modeling and multisensory input. We present a new speech model based on statistics of magnitude-normalized complex spectra of speech signals. By performing magnitude normalization, we are able to get rid of huge intra- and inter-speaker variation in speech energy and to build a better speech model with a smaller number of Gaussian components. To deal with real-world problems with multiple noise sources, we propose to use multiple heterogeneous sensors, and in particular, we have developed microphone headsets that combine a conventional air microphone and a bone sensor. The bone sensor makes direct contact with the speaker’s temple (area behind the ear), and captures the vibrations of the bones and skin during the process of vocalization. The signals captured by the bone microphone, though distorted, contain useful audio information, especially in the low frequency range, and more importantly, they are very robust to external noise sources (stationary or not). By fusing the bone channel signals with the air microphone signals, much improved speech signals have been obtained.

Diagnosability study for quality improvement based on distributed sensing and information technology

With rapid innovations in information technology and sensing technology, increasingly less expensive and smart devices with multiple heterogeneous on-board sensors, networked through wireless links and deployable in large numbers, are distributed throughout complex Multistage Manufacturing Systems (MMSs). These technologies provide unprecedented opportunities for quality improvement. If product-sensing data are obtained via certain distributed sensing and information system, the problem of whether the faults of a manufacturing system are diagnosable is of great interest to both academia and industry. In this study, the diagnosability of the process faults in a MMS is defined in a general way using a linear input-output model, which does not depend on specific diagnosis algorithms. The condition of faults diagnosability, the diagnosability matrix and indices are defined and derived. Finally, the methodology is illustrated by a machining process and a hot deformation process.

Distributed sensor system for fault detection and isolation in multistage manufacturing systems

With rapid innovations in sensing technology and the rising complexity in manufacturing processes, increasingly less expensive and smart devices with multiple heterogeneous on-board sensors, networked through wired or wireless links and deployable in large numbers, are distributed throughout complex Multistage Manufacturing Systems (MMSs). The Distributed Sensor System (DSS) provides unprecedented opportunities for fault detection and isolation. The related issues of the state-of-the-art practice, research challenges and future directions related to software infrastructure of a distributed sensor network are discussed, which include optimal design of DSSs, design criteria, data management, information processing and decision-making. Applications based on the authors' research experiences are also given.

Combination of Localization Techniques for Mobile Sensor Network for Precise Localization

A precise localization is required in order to maximize the usage of Mobile Sensor Network. As well, mobile robots also need a precise localization mechanism for the same reason. In this paper, we showed a combination of various localization mechanisms for precise localization in three different levels. Localization can be classified in three big categories: wide area and long distance localization with low accuracy, medium area and distance localization with medium accuracy, and small area short distance localization with high accuracy. In order to present localization methods, traditional map building technologies such as grid maps or topological maps can be used. We implemented mobile sensor vehicles and composed mobile sensor network with three levels of localization techniques. Each mobile sensor vehicles act as a mobile sensor node with the facilities such as autonomous driving, obstacle detection and avoidance, map building, communication via wireless network, image processing, extensibility of multiple heterogeneous sensors, and so on. For localization, each mobile sensor vehicle has abilities of the location awareness by mobility trajectory based localization, RSSI based localization and computer vision based localization. With this set of mobile sensor network, we have the possibility to demonstrate various localization mechanisms and their effectiveness. In this paper, the result of computer vision based localization, sensor mobility trail based localization and RSSI based localization will be presented.