Real-time Information Processing Research Articles

Machine learning as a comparative tool to determine the relevance of signal features in laser welding

In laser welding, real-time process information is required for quality assurance and process control. The challenge on sensor technology and processing is determined by dynamic process behavior in the interaction zone. The dimensionality of spatial process information however can be used to determine different process conditions and quality faults. In this paper, a laser welding process is coaxially observed using a high-speed mid-infrared-camera in combination with near-infrared CMOS-camera. The signals are evaluated by extracting geometrical and statistical features. These features are subsequently used by machine learning techniques to predict quality-relevant process variables. The work identifies and compares the importance of the extracted features based on their prediction performance. This importance is used to reassess the sensors and underlying signal analyses in order to enhance the relevance of the acquired process information.

Generic Process Visualization Using Parametric t-SNE

In this work, a generic process visualization method is introduced using parametric t-SNE and used to visualize real-time process information and correlations among variables on a 2D map. A deep network is used to learn the Kullback-Leibler divergence between the original high-dimensional space and the latent space. In practice, it is observed that a model trained with historical data is not robust enough to visualize shifts into unknown states. Due to the effect of greedy learning, the response of the model is biased toward the most-contributing inputs. To relieve this effect, combinatorial variation creation is applied in the training stage to allow the model to respond to each input more evenly. The proposed method is tested on the Tennessee Eastman Process (TEP) data for four types of faults. The result indicates that the proposed method outperforms conventional methods such as PCA and Isomap, and is able to provide clear visual indication of process changes.

Optimization of distribution network operation based on data from smart metering systems

The paper is dealing with a current trend of development in distribution networks’ control, with the focus on a real-time data acquisition and processing of information providing an overview of the distribution system operation. Nowadays, the amount of information available for the control of the distribution network is very limited, making the use of new sophisticated control algorithms and strategies very difficult or even impossible. The installation of smart meters and intelligent monitoring systems on the low voltage side of distribution transformers opens new possibilities for using specific tools to improve different aspects of the distribution system operation, e.g., a voltage control, a reactive power control, a reduction in losses or a fault location. The use of such systems may lead to a higher utilization of renewable energy sources to the distribution networks.

Within Skyline Query Processing in Dynamic Road Networks

The continuous within skyline query is an important type of location-based query, which can provide useful skyline object information for the user. Previous studies on processing the continuous within skyline query focus exclusively on a static road network, where the object attributes and the conditions of roads remain unchanged. However, in real-world applications, object attributes and road conditions inevitably vary with time, which severely limits the applicability of previous studies in practice. Therefore, in this paper, we address the issue of efficiently processing the continuous within skyline query in dynamic road networks with time-varying information. We design three elaborate data structures, the object attribute dominating matrix (OADM), the road distance sorted list (RDSL) and the skyline object expansion tree (SOET), to maintain the information of objects and the road network. Combined with OADM, RDSL and SOET, we develop an efficient algorithm, namely the within skyline object updating algorithm, to provide real-time processing of the time-varying information. Finally, a thorough experimental evaluation is conducted to show the merits of the proposed approaches.

Blended Antenna Wearables for an Unconstrained Mobile Experience

We envision a world in which everyday life experiences can be augmented on-demand via the real-time cloud processing of information sourced at multiple wireless end points. While current wireless systems focus their effort on improving downlink capacity, these life-changing augmented experiences will only become a reality if the uplink capacity increases at the same or even higher rate. As a catalyzer for the capacity increase in both directions of the wireless communication link, we propose an innovative idea that brings the spectral and energy efficiency benefits of massive MIMO systems directly to the end user without compromising device size, weight, or power consumption. We propose a radio enhanced garment composed of blended textile antennas for seamless high data rate connectivity anytime, anywhere, addressing immediate and future needs. The real-world applications for such a solution are tremendous, including enhanced connectivity in crowded spaces and remote areas, as well as symmetric extremely high data rates for access to next generation real-time services (e.g., augmented reality and cognition, real-time computer vision, telepresence, 3D video sharing) from ever lighter end user devices (e.g., Google Glass).

Improving Patient Safety in Hospitals through Usage of Cloud Supported Video Surveillance.

BACKGROUND:Patient safety in hospitals is of equal importance as providing treatments and urgent healthcare. With the development of Cloud technologies and Big Data analytics, it is possible to employ VSaaS technology virtually anywhere, for any given security purpose.AIM:For the listed benefits, in this paper, we give an overview of the existing cloud surveillance technologies which can be implemented for improving patient safety.MATERIAL AND METHODS:Modern VSaaS systems provide higher elasticity and project scalability in dealing with real-time information processing. Modern surveillance technologies can prove to be an effective tool for prevention of patient falls, undesired movement and tempering with attached life supporting devices. Given a large number of patients who require constant supervision, a cloud-based monitoring system can dramatically reduce the occurring costs. It provides continuous real-time monitoring, increased overall security and safety, improved staff productivity, prevention of dishonest claims and long-term digital archiving.CONCLUSION:Patient safety is a growing issue which can be improved with the usage of high-end centralised surveillance systems allowing the staff to focus more on treating health issues rather that keeping a watchful eye on potential incidents.

Artemis Controls (a)

Avion Chemicals has approached Artemis Controls regarding the purchase of an Artemis smart valve to manage the highly volatile phenol in its production process. Although an existing valve could be used, discussions lead to the possibility of designing a new and potentially much improved valve. Time, engineering, and software constraints make the valve-redesign project a risky endeavor. The tension between delivering the old valve and developing the new valve is centered on the marketing opportunity and financial risk. The A case decision can be structured with a basic decision diagram, but the analysis cannot be completed because likelihood statements are presented as “weasel words.” In addition to the alternatives presented in the case, students might propose several risk-reducing possibilities: delivering the standard valve if the new valve is only moderately successful, delivering the standard valve if the software development is extended, reframing the price structure for the resultant new valve, and proposing a contingent contract with the software developer.The A case is a modification of “Orion Controls (A)” (UVA-QA-0480). The probability statements of Orion have been replaced by the weasel words of Artemis. This modification allows the discussion to be less “numbers” oriented, more structural, and more strategic. Excerpt UVA-QA-0756 Nov. 30, 2010 Artemis Controls (A) Even though the hiking trip to Shenandoah National Park was intended to be a restful interlude in his frenetic work pace, Nathan Armstrong, head of marketing at Artemis Controls (Artemis), found his mind wandering to his recent conversation with Andre Gide, executive vice president of Avion Chemicals (Avion). Contract discussions with Gide, who was responsible for worldwide corporate safety programs at Avion, had taken an interesting turn. Gide had initially contacted Artemis to place an order for 50 of Artemis's Model SV44A-10 smart-valve systems to manage the phenol flows at Avion's nine chemical plants worldwide. Their conversation, however, had led to the possibility that Artemis would develop an improved model for Avion at a substantially increased price. The new system that Gide wanted would require an improvement in the flow-sensing-and-control part of the existing valve system to allow for real-time information processing and dynamic responses to changes in process states. In addition, the new system would require substantial improvement in valve capability to enable quick changes in valve-gate positions. Because of the dynamic nature of the real-time information flow, these improved valve systems would need to respond to instruction changes far more rapidly than the existing model could. The Avion Contract . . .

A task-efficient sink node based on embedded multi-core SoC for Internet of Things

With the increase of collected information, the computing performance of single-core sink node for Internet of Things (IoTs) cannot satisfy with the demand of large data processing any more. Therefore, the sink node which based on embedded multi-core SoC for IoTs and maximizing its computing performance has brought into focus in recent years. In this paper, we design a multi-core Task-Efficient Sink Node (TESN) based on heterogeneous architecture and the Weighted-Least Connection (WLC) task schedule strategy has been proposed to improve its efficiency. There are two types of cores in the sink node, master core and slave cores. The master core deals with tasks allocation and the seven slave cores deal with data processing. All of the cores are communicating with each other through mailbox. By considering each core’s real-time processing information and computing performance, the proposed WLC can balance each core’s load and reduce network congestion. The XilinxV5 platform is used to evaluate the performance of WLC and Round-Robin (RR) algorithms for multi-core sink node. The experiment results show that the WLC strategy improves the processing speed obviously, achieves load balance and avoids large scale congestion of sink node in the sensor networks of IoTs.

Geoinformation support of cartographic-space monitoring of Siberia’s Arctic zone

A rationale is provided for the need and current importance of establishing a cartographic-space monitoring of Siberia’s Arctic zone in conditions of an increased interest in the exploitation of the region’s natural resource wealth and an aggravation of the geopolitical situation. We examine the principles of cartographic-space monitoring as a system for real-time acquisition, processing, visual display and supply (to users) of geospace information on natural and anthropogenic processes and phenomena. The primary goal of monitoring is defined as well as its particular objectives, such as the promotion of geoinformation services, training and professional improvement of specialists in remotely sensed data processing, digital cartography and geoinformation technologies, etc. We developed a conceptual model for geoinformation support of cartographic-space monitoring, based on the methodology of system analysis. We determined the sources and the composition of geospace information as well as the main requirements on it. The composition, purpose, structure and characteristic features of the main monitoring units and subsystems are presented and discussed, on the basis of the geoinformation portal that provides the users with the systems of base servers intended for acquisition, generation, updating and visualization of geospace information and metadata as well as for data control: loading, search, interactive editing, and unloading. We singled out three units of the system for geoinformation support of cartographic-space monitoring: the information unit, the geospace data processing unit, and the unit of access to information resources.

Detection over sensor networks: a tutorial

The applications of sensor networks (SNs) are increasing since they facilitate real-time remote information monitoring and processing. Detection of an event is one of the main tasks of SNs in many applications. Sensors may transmit either raw or processed data to a fusion center (FC), where a final decision is taken. The problems and challenges that exist in detection over SNs and the previously proposed methods to deal with them are reviewed and described in this tutorial.

Virtual multi-beamforming for distributed satellite clusters in space information networks

This article introduces some basic theories of space information networking (SIN), which is a novel research field. A SIN is a network that is able to achieve real-time acquisition, transmission, and processing of space information. The article first investigates the basic satellite-terrestrial architecture of SINs, and then three key technologies of SINs are presented, specifically more details on the high data rate transmission theory. The DSC is the foundation of high data rate transmission; thus, the core technology of DSC, which is beam/beamforming theory, is discussed in detail. Compared to the traditional spot beam theory, this article proposes a novel VBF concept, which is capable of increasing the channel capacity. Some key technologies are also investigated for VBF; they are channel capacity theoretical analysis, opportunistic beamforming, virtual multi-beamforming, and resource management.

Multilingual financial news retrieval and smart recommendation based on big data

In view of the study of finance and economics information, we research on the real-time financial news posted on the authority sites in the world’s major advanced economies. Analyzing the massive financial news of different information sources and language origins, we come up with a basic theory model and its algorithm on financial news, which is capable of intelligent collection, quick access, deduplication, correction and integration with financial news’ backgrounds. Furthermore, we can find out connections between financial news and readers’ interest. So we can achieve a real-time and on-demand financial news feed, as well as provide a theoretical basis and verification of the scientific problems on real-time processing of massive information. Finally, the simulation experiment shows that the multilingual financial news matching technology can give more help to distinguish the similar financial news in different languages than the traditional method.

Review of the Book Vehicular Networking [Book Review

This book describes clearly the many opportunities and challenges in the emerging area of network communications applied in vehicles, as well as traffic infrastructures. Specific topics in the area include internet access and vehicle to vehicle (V2V) communication or vehicle to infrastructure (V2I) communication. The main objective is the enhancement of the driving experience, the efficient management of the traffic incidents, the information dissemination and the improvement of the safety levels for drivers, motorists and pedestrians. Nowadays, the computing power has substantially increased, enabling vehicles to receive and process real time information, incorporating devices like radar, LIDAR, infrared sensors, camera and communication systems. However, the path between objectives and successful application has numerous challenges that need to be addressed.

A data pipeline for PHM data-driven analytics in large-scale smart manufacturing facilities


 
 
 The term smart manufacturing refers to a future-state of manufacturing, where the real-time transmission and processing of information across the factory will be used to produce advanced manufacturing intelligence that can optimize every aspect of its operation. In recent years, initiatives and groups such as the Smart Manufacturing Leadership Coalition (SMLC), Industry 4.0, and the Industrial Internet Consortium (IIC), have led the way by bringing together industry, academia and government to establish policies, roadmaps and platforms to support smart manufacturing. Although there are many characteristics that can be associated with smart manufacturing across these initiatives, a common theme is the emphasis on transitioning operations from reactive and responsive, to predictive and preventative. The research presented in this paper focuses on the development of a data pipeline that supports the development of data-driven Prognostics and Health Management (PHM) applications. In the context of smart manufacturing, PHM enables facilities to transition from preventative and reactive maintenance strategies, to predictive, preventative and condition-based strategies. The benefits that can be derived by PHM are aligned with those of smart manufacturing, which include the opportunity to decrease costs, increase machine availability, reduce energy consumption, and improve production yield.
 However, the process of ingesting, cleaning and transforming real-time data streams for data-driven PHM is a difficult, complex and time-consuming task, with estimates from business intelligence projects ranging from 80% to 90% of total project effort. This effort may only be exacerbated further in manufacturing environments due to additional technology challenges, such as low levels of standardization, disparate protocols and interfaces, and ad hoc data management. While emerging technologies such as Cyber Physical Systems (CPS) and Internet of Things (IoT) can overcome many of these challenges and provide an open platform for transmitting data, existing large-scale manufacturing facilities that are subject to compliance, regulation, and stringent quality
 
 
 assurance policies may not be able to adopt these technologies in the short-term due to the associated cost, risk and effort. Therefore, PHM applications that need to access data streams in large-scale manufacturing facilities must do so using transparent data integration that does not discriminate between emerging and legacy technologies in the factory. To this end, this research presents a real- time, scalable, robust, and fault tolerant data pipeline for ingesting, cleaning, transforming, processing and contextualizing time-series data from a wide-range of sources in the factory.
 
 

The Economic Man

This paper questions how economic systems are using knowledge to support economic decision making. Scientific knowledge collected by centralized planners is not the right type of information to base economic decisions on since it does not have the capacity to consider local opportunity factors. These concerns, originally espoused by Frederick Hayek when analyzing the economy as a whole, can be decomposed to focus on individual businesses. A large corporation, encumbered with a traditional vertical organizational structure, typically has an executive management team taking on the role of the centralized planners in Hayek’s model, and is forced to make decisions without the local opportunity knowledge that may be available in their low-level business units. Economic decisions must fundamentally be based on accurate information that considers local opportunities, and must be made rapidly in today’s dynamic market place. To get access to local knowledge from their low-level business units, executive management teams should consider implementing learning organizations with horizontal management structures that encourage collaboration. Companies with centralized organizational structures simply move too slowly to be competitive. The “Economic Man” is an economist’s creation designed by Mr. Hayek to show how unlikely it is that economic decision makers could ever accurately predict future economic conditions. A hypothetical “Economic Man” with “perfect foresight” was described, in essence, to allow readers to visualize the futility of the assumptions underlying our current economic theories. Yet in today’s competitive business environment, perfect foresight is precisely the standard we impose on our executive managers. The perfect knowledge assumption is said to mislead these economic decision makers into a false believe the problem is simpler, from the perspective of the information needed to support such decisions, than it actually is. This results in poor investment decisions by managers that collect the wrong economic data. The division of labor concept notices that complex jobs can be more efficiently completed by a number of workers performing specialized tasks, than by one worker trying to complete the entire job. By dividing up the required skills on complex tasks across multiple workers, they can become specialists and work their assigned area more efficiently. The level of knowledge required to make workers skilled specialists is essential for the division of labor concept to be effective. Further knowledge is required to quantify economic input variables to the extent that decision makers in executive management can accurately predict how the marketplace will unfold and, in so doing, achieve an "economic man" like stature. No matter how we materialize or describe the problem; it seems the effective acquisition and use of knowledge is the correct answer. Peter Drucker relates the economic successes a corporation has with their ability to create “core competencies” that lead to market leadership positions. He begins to abstractly define the type of data that should be collected to help managers of these corporations monitor the strength and relative position of their core competencies. This relates to Mr. Hayek’s concern that managers need accurate, but relevant, information to base their decisions on. Just when things were looking bleak for our hypothetical “Economic Man,” these important steps define feasible types of real time information processing that can support economic decision makers monitoring the strength and position of core competencies. While it’s not quite as good as the perfect foresight imposed on our “Economic Man,” relevant, near real time economic data is a giant leap forward.

Advanced Technologies and Communication Solutions for Internet of Things

Internet of Things (IoT) is one of the important issues to describe several technologies and research disciplines that enable the IoT to reach out into the real world of physical objects. IoT is also a novel paradigm that is rapidly gaining in the scenario of Wireless Sensor Networks (WSN) and Wireless Telecommunications. The basic idea of this concept is the pervasive presence around our lifestyle of a variety of things or objects [1–3]. Tremendous advances in processing, wireless sensor networks, mobile communication, and systems/middleware technologies are leading to new paradigms and platforms for computing environment. There might be many issues to realize and provide intelligent services and much effort and enormous attention have been focused on the IoT. The research area poses challenges such as the advanced technologies for sensors and actuators, identifications with objects in IoT, interoperable serviceoriented technologies to share real-world data among heterogeneous devices, interoperable middleware, networking technologies for wired and wireless networking to interconnect things, application services that store, integrate, and process in real-time variable data streams from devices, infrastructure for storage and computing capabilities for IoT application services and for processing big data, quality of service assurance for efficient resource management to allocate, track, and resource utilization, scalablemanagement of network, computing, and storage capacity across multiple objects, advanced security, privacy, authentication, trust and verification with the IoT applications, and numerical analysis and simulation technologies for IoT application with wireless sensor networks. The topics have been more aggressively covered by journals in the advanced technologies and application of the related wireless sensor networks and wireless telecommunications with the IoT [1–3]. This special issue discusses the following: advanced technologies for sensors and actuators; interoperable service-oriented technologies; interoperablemiddleware; networking technologies forwired and wireless networking to interconnect things; application services to store, integrate, and process real-time information; infrastructure for IoT application and services and big data processing; quality of service for efficient resource management; scalable management of network, computing, and storage capacity across multiple objects; advanced security, privacy, authentication, trust, and verification with the IoT applications; software defined networking and the opportunities in the development of IoT applications; numerical analysis and simulation technologies for IoT application with wireless sensor networks.

Real-Time Information Processing Method and its Application in Optical Target Tracking System

Optical information processing systems have been widely applied, this paper studies the calculation of the amount of a reduction in the use of genetic algorithms to increase the diversity of the sample algorithm to reduce problems caused by the sample dilution with a resampling method, combined with the finite field resampling, resampling constitute a finite field of genetic algorithms. We using surface to capture the dynamics of template update, to prevent inappropriate tracking results into the template set, pending the outcome of the tracking template is added to the first test for cover. Detect occlusion control template updates. Prevent tracking results of drift.

Crowd Modelling for Quasi-real-time Feedback during Evacuation in a Situational Awareness System

Evacuation modelling has traditionally been limited to prior analysis of the geometrical design of spaces. This approach is limited by the number of scenarios that can be tested. A scenario-independent evacuation model would rely on real-time information processing. This approach allows the generation of an optimum evacuation strategy that minimises evacuation time and crowd density, and is tailored to the current situation at hand. This paper describes the requirements and development of such a crowd model. Graph theory and network flow heuristics are combined with agent movement, based on the individual determination of speed by meso-scale density assessment.

Visually guided grasping of common objects: Effects of priming

Priming effects were tested on the planning of the grasping of common objects under full vision during action performance. Healthy participants took part in four experiments which manipulated the nature of the prime (objects, circular block, rectangular bar) and priming context (blocked vs. mixed). Each experiment relied on four priming conditions: (1) congruent orientation, (2) incongruent orientation, (3) neutral prime, and (4) no prime. Priming was observed to have a facilitating effect on visually guided grasping when the object to be grasped was primed by a congruently oriented identical object. This effect was rather independent of the priming context (experimental set-up). Our data suggest an object's functional identity may contribute to the priming effect, as well as its intrinsic (e.g., shape, size) and extrinsic (orientation) visual characteristics. We showed that the planning of visually guided grasping is influenced by prior visual experience, and thus that grasping is not based exclusively on real-time processing of visual information.

It's All About MeE: Using Structured Experiential Learning ('e') to Crawl the Design Space

There is an inherent tension between implementing organizations — which have specific objectives and narrow missions and mandates — and executive organizations — which provide resources to multiple implementing organizations. Ministries of finance/planning/budgeting allocate across ministries and projects/programs within ministries, development organizations allocate across sectors (and countries), foundations or philanthropies allocate across programs/grantees. Implementing organizations typically try to do the best they can with the funds they have and attract more resources, while executive organizations have to decide what and who to fund. Monitoring and Evaluation (M&E) has always been an element of the accountability of implementing organizations to their funders. There has been a recent trend towards much greater rigor in evaluations to isolate causal impacts of projects and programs and more ‘evidence-based’ approaches to accountability and budget allocations. Here we extend the basic idea of rigorous impact evaluation — the use of a valid counterfactual to make judgments about causality — to emphasize that the techniques of impact evaluation can be directly useful to implementing organizations (as opposed to impact evaluation being seen by implementing organizations as only an external threat to their funding). We introduce structured experiential learning (which we add to M&E to get MeE) which allows implementing agencies to actively and rigorously search across alternative project designs using the monitoring data that provides real-time performance information with direct feedback into the decision loops of project design and implementation. Our argument is that within-project variations in design can serve as their own counterfactual and this dramatically reduces the incremental cost of evaluation and increases the direct usefulness of evaluation to implementing agencies. The right combination of M, e, and E provides the right space for innovation and organizational capability building while at the same time providing accountability and an evidence base for funding agencies.