Sensor Data Streams Research Articles

Application Of Reinforcement Learning In Multisensor Fusion Problems With Conflicting Control Objectives

Abstract Smart agents are equipped with sensors that enable them to be sensitive to their surrounding environrnent. However, the mapping of multiple raw streams of sensory data to the appropriate actions is not an easy problem, especially when multiple conflicting objectives aze involved. This type of multi-sensor fusion problem through the domain of power management for smart mobile devices was investigated in this study. In this application domain, the objective is to keep the user’s mobile devices in an “on” state as long as possible such that just-in-time services (such as reminder announcements) can be provided. However, this conflicts with the mobile device’s inherent goal - to turn off to conserve power. Due to the stochastic nature of human behavior, ahand-coded fixed strategy may not be the best solution. A learning control approach to the problem is presented in this paper. The experimental results show that the approach learns the appropriate mapping from multiple streams of raw sensory data to...

Challenges for Event Queries over Markovian Streams

Building applications on top of sensor data streams is challenging because sensor data is noisy. A model-based view can reduce noise by transforming raw sensor streams into streams of probabilistic state estimates, which smooth out errors and gaps. The authors propose a novel model-based view, the Markovian stream, to represent correlated probabilistic sequences. Applications interested in evaluating event queries — extracting sophisticated state sequences — can improve robustness by querying a Markovian stream view instead of querying raw data directly. The primary challenge is to properly handle the Markovian stream's correlations.

Advances in information and knowledge management

Several research areas today overlap between the tracks of databases, information retrieval and knowledge management, such as natural language processing, semantic web, digital libraries, visualization, information quality and data mining. Inter-disciplinary research across these tracks encourages advances in the development of databases, the extraction of information and the discovery of knowledge. This is precisely the focus of our article. We explain the research issues addressed in a Ph.D. workshop recently held at the ACM Conference on Information and Knowledge Management. This workshop had presentations on novel ideas addressing challenges in information and knowledge management. It covered a broad range of topics such as XML architectures, sensor data streams, personal information managers and text pre-processing. In this article, we provide an overview of the research problems and solutions discussed in the Ph.D. workshop. Our article thus describes the latest technological developments in information and knowledge management as seen by academia. This cutting edge technology also finds practical applications in the corporate world.

유비쿼터스 환경에서 센서 데이터와 서비스의 연계를 표현하는 마크업 언어

유비쿼터스 시대에는 우리 주변에 산재하는 수많은 스마트 객체들이 끊임없이 방대한 양의 센서 데이터를 생성해 낸다. 인터넷이 널리 보급됨에 따라 인터넷으로 연결된 정보의 바다로부터 유용한 정보를 찾는데 도움을 주는 인터넷 정보 검색 엔진이 등장한 것처럼, 스마트 객체가 생성한 센서 데이터로부터 우리 삶을 윤택하게 하는데 활용될 정보를 추출하여 응용 서비스에 전달하는 일을 함으로써 유비쿼터스 서비스를 개발하는데 도움을 주는 센서 데이터 스트림 처리 미들웨어들이 등장하고 있다. 이러한 센서 데이터 스트림 처리 미들웨어를 이용하여 유비쿼터스 서비스를 사람들에게 제공하기 위해서는 제공될 서비스와 관련된 정보를 미들웨어에게 알려 주어야 한다. 이에 본 논문에서는 센서 데이터를 이용하는 유비쿼터스 서비스를 나타내는데 필요한 정보를 구분하고, 이를 효과적으로 표현하는 컨텍스트 드리븐 서비스 마크업 언어를 제안한다. 제안하는 컨텍스트 드리븐 서비스 마크업 언어를 이용하면 다양한 상황에서 제공되어야 하는 다양한 유비쿼터스 서비스를 쉽게 표현할 수 있다. In the ubiquitous environment, it is scattered all over our neighboring in many smart objects. These smart objects constantly produce the information and the amount of the generated information is massive. As the internet search engine came out to help us to find the useful data from the sea of the information connected to the internet, the sensor data stream processing middleware is appearing to make us to develop the ubiquitous service easily by extracting the meaningful information from the massive sensor data and delivering the extracted information to the application which makes our life convenient. We have to inform the information relating to the provided service to a middleware so that the ubiquitous service can be provided by using sensor data stream processing middleware. In this paper, we classify the information which is needed to express the ubiquitous service which uses sensor data for the service providing. And we propose a distinct markup language called Context-driven Service Markup Language (CSML) to effectively describe this information. We can easily express the various ubiquitous services which have to be provided in the various situations using proposed CSML.

Use of Real-Time Rig-Sensor Data To Improve Daily Drilling Reporting, Benchmarking, and Planning—A Case Study

Summary State-of-the-art drilling-operations analysis is mostly dependent on existing daily-activity reporting. However, these activity reports are based on human observations and judgment. This fact implies a number of limitations such as the coarse level of detail and subjective coding systems. To overcome these problems, a rule-based system has been applied to analyze real-time surface-sensor data autonomously. The system evaluates the sensor data stream and acquires crucial process information as a basis for further analysis. The scope of the system is the recognition of drilling operations, such as tripping, making connections, reaming, and washing, to extend and enhance standard reporting. In this way, a standardized and objective categorization of the drilling process can be achieved at a level of accuracy and detail yet to be reached. Another benefit is the automated reporting feature. Through the recognition of the rigs, current state, the system is able to propose an impartial process description. This leads to a reduction of the time spent on reporting and leaves more time to focus on unexpected events and lessons learned. Analysis of field data allowed the introduction of new key performance indicators (e.g., wellbore treatment time per depth interval) for benchmarking, which are determined automatically during the evaluation process. This type of benchmarking does not rely on company-specific activity coding systems. In this way, costly and time-consuming data management effort (e.g., to compare operated and nonoperated wells) is eliminated. The new system was applied to wells drilled in the Vienna basin during the past year. The Vienna basin covers large parts of eastern Austria (lower Austria, Vienna, and Burgenland) and reaches into the territories of the Czech Republic in the north and the Slovak Republic in the east. It is approximately 200 km long and 55 km wide, striking roughly southwest to northeast from Gloggnitz (lower Austria) in the south to southwest to Napajedla (Czech Republic) in the north to northeast. As a conclusion, it can be stated that the application of this system significantly improves the accuracy and resolution of the drilling-process description, reducing data-management efforts. The objective categorization of process information is a key enabler for benchmarking, specifically when identifying hidden lost time.

Routing Correlated Data in Wireless Sensor Networks: A Survey

Sensory data gathered from sensor nodes in physical proximity tend to exhibit strong correlation. To minimize such redundancy and hence curtail the load in wireless sensor networks with a goal to conserve energy, effective in-network fusion schemes have been extensively proposed in the literature. To this end, routing schemes supporting data fusion are extremely important as they dictate where and when sensory data streams shall intersect with each other and thus fusion will be performed. In this article we briefly articulate this problem and classify recently proposed routing schemes supporting data fusion in wireless sensor networks into three categories: routing-driven, coding-driven, and fusion-driven. We also give an overview of various algorithms in each category by summarizing their design approaches, benefits, and drawbacks.

A word from the editor

A word from the editor

A fast multistream scattering-based Jacobian for microwave radiance assimilation

The full utilization of satellite-based passive microwave imagery for weather forecasting rests on the ability to assimilate radiances into numerical weather prediction (NWP) models for highly scattering and absorbing hydrometeor states. State vector updates need to be performed rapidly enough to maintain pace with the sensor data stream and require, in particular, rapid calculation of the tangent linear relationship (Jacobian) between the observed antenna temperatures and the NWP prognostic hydrometeor parameters. To facilitate the use of both spaceborne and airborne passive microwave data in numerical forecasting, we present a new rapid multiple-stream discrete-ordinate algorithm for calculating the Jacobian under arbitrary scattering and absorbing conditions. The algorithm is based on the layer-adding method for a plane-parallel atmosphere for which the number of operations required to compute the solution is proportional to the number of layers. A nontrivial aspect of the problem is the stable calculation of the reflectance and transmittance operators in highly scattering layers for which a diagonalization technique and analytical factorization of specific matrices are used to ensure stability. Scaling calculations suggest that the new algorithm will be suitable for use in real-time all-weather microwave radiance assimilation.

A Dependency Model-Based Approach for Identifying and Evaluating Power Quality Problems

The purpose of this paper is to present a diagnostic system that will not only monitor sensor data streams, but also classify power conditions, and diagnose power quality problems both in real-time and off-line. Signal processing techniques are applied to extract features from monitored data for event detection and classification. A cause-effect relationship model is used to trace the power quality related events to particular equipment of a system under consideration. The methodology has been implemented in a software tool. Results obtained from the application of this tool on monitored data collected from a facility validate the utility of this approach.

Presence and The Sixth Sense

This paper discusses the notion that presence may be considered as a selection mechanism that organizes the stream of sensory data into an environmental gestalt or perceptual hypothesis about current environment. A par ticular environmental gestalt results in scan-sensing of the world in a particular pattern reminiscent of saccades and fixations in eye scan paths. The environment hypothesis is continually reverified or else a break in presence oc curs. Presence is therefore compared to visual hypothe sis selection in the work of Richard Gregory and Law rence Stark. The implications for measurement are discussed, and it is concluded that physiological measures indicating breaks in presence are worthy of study, and that the study of presence is also the study of what maintains an environmental gestalt.

A state-based approach to the representation and recognition of gesture

A state-based technique for the representation and recognition of gesture is presented. We define a gesture to be a sequence of states in a measurement or configuration space. For a given gesture, these states are used to capture both the repeatability and variability evidenced in a training set of example trajectories. Using techniques for computing a prototype trajectory of an ensemble of trajectories, we develop methods for defining configuration states along the prototype and for recognizing gestures from an unsegmented, continuous stream of sensor data. The approach is illustrated by application to a range of gesture-related sensory data: the two-dimensional movements of a mouse input device, the movement of the hand measured by a magnetic spatial position and orientation sensor, and, lastly, the changing eigenvector projection coefficients computed from an image sequence.

Advances in polarization diversity lidar for cloud remote sensing

As soon as high-energy pulsed lasers became available in the mid-1960s, atmospheric scientists began assessing the information contents of various light detection and ranging (lidar) techniques in the field and laboratory. A particularly promising approach, which has recently gained increased stature as a result of growing interests in previously overlooked cloud types important to climate research (e.g. high-altitude cirrus), involves the polarization analysis of the backscattered laser return. Polarization diversity lidars collect data simultaneously in two or more channels to remotely determine the thermodynamic cloud phase, structure, and boundaries, and infer a variety of other climatically important cloud microphysical properties. As illustrated by the description of the mobile University of Utah Polarization Diversity Lidar system, commercially available dual-wavelength transmitters and improved electronic technologies to process high-resolution multichannel lidar signals represent significant advantages over earlier devices used in cloud studies. Polarization diversity can be added rather economically to more specialized lidars employing spectroscopic techniques, for other forms of atmospheric probing, such as Raman, differential absorption, and high spectral resolution lidars, in order to enhance instrument accuracy and versatility for cloud an aerosol research. Future engineering challenges remain in the hardening of compact lidar systems for extraterrestrial deployment, the achievement of unattended eye-safe operations, and in the improved integration of multiple remote sensor data streams and supporting in situ measurements to more fully characterize cloud systems and their effects on the Earth's radiation balance. >

Dynamic sensing in a ping-pong playing robot

The application of sensing technologies to an environment that changes at rates comparable to the sensing and actuation rates of a robot system is considered. In such dynamic environments, the temporal characteristics of the sensor must be taken into account. Additionally, the processing system must be able to integrate the stream of sensor data into its task plan, compensating for changed sensor data and continuously optimizing the plan. The author examines these issues in the context of a functioning robot system that plays ping-pong.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Clifford multiplication tables

The objective of this work is the development of a learning system for the automatic assessment of balance abilities in elderly people. The system is based on estimating the Berg Balance Scale (BBS) score from the stream of sensor data gathered by a Wii Balance Board. The scientific challenge tackled by our investigation is to assess the feasibility of exploiting the richness of the temporal signals gathered by the balance board for inferring the complete BBS score based on data from a single BBS exercise.The relation between the data collected by the balance board and the BBS score is inferred by neural networks for temporal data, modeled in particular as Echo State Networks within the Reservoir Computing (RC) paradigm, as a result of a comprehensive comparison among different learning models. The proposed system results to be able to estimate the complete BBS score directly from temporal data on exercise #10 of the BBS test, with ≈10 s of duration. Experimental results on real-world data show an absolute error below 4 BBS score points (i.e. below the 7% of the whole BBS range), resulting in a favorable trade-off between predictive performance and user’s required time with respect to previous works in literature. Results achieved by RC models compare well also with respect to different related learning models.Overall, the proposed system puts forward as an effective tool for an accurate automated assessment of balance abilities in the elderly and it is characterized by being unobtrusive, easy to use and suitable for autonomous usage.