Real-time Input Research Articles

Real-Time Joint Angular-Acceleration Planning for Vision-Based Kinematically Redundant Manipulator in Dynamic Environment

This paper presents an angular acceleration planning for joint configuration spaces of vision-based kinematically redundant robot manipulators to achieve real-time tracking tasks in dynamic environment. In accordance with the proved proposition, the joint velocity formed by the inverse kinematics mapping of the defined pose error is regarded as the system error, and utilized to further deduce the planned joint angular acceleration and with kinematic redundancy for obstacle avoidance simultaneously. Highly-complex nonlinearities in the angular acceleration are equivalent to a system perturbation represented by a synthetic form, thereby simplifying the tedious calculations of the angular acceleration theoretically and converting the planning problem into a control problem. Hyperbolic tangent-based super twisting algorithm, as the control input of manipulator system, is designed to resist the synthetic perturbation. The collision-free movement of redundant manipulators for tracking tasks is thus achieved through the integration of the control input in real time. An error-based S-function is proposed as the internal parameter of the planned joint acceleration to prevent the integral saturation. Lyapunov theoretical analysis proves the stability of the proposed super twisting algorithm. Simulation and contrast experiments in dynamic-obstacles environments indicate that the proposed joint angular acceleration planning for kinematically redundant manipulators owns feasibility, smoothness and practicability.

London Heathrow Airport Uses Real-Time Analytics for Improving Operations

Improving airport collaborative decision making is at the heart of airport operations centers (APOCs), recently established in several major European airports. In this paper, we describe a project commissioned by Eurocontrol, the organization in charge of the safety and seamless flow of European air traffic. The project’s goal was to examine the opportunities offered by the co-location and real-time data sharing in the APOC at London’s Heathrow airport, arguably the most advanced of its type in Europe. We developed and implemented a pilot study of a real-time data sharing and collaborative decision-making process, selected to improve the effciency of Heathrow’s operations. In Guo et al. (2019), we describe the system that we developed for Heathrow to better estimate passenger connection times, which takes advantage of the integration and data sharing that Heathrow’s APOC offers. In this paper, we describe the process of how we chose the subject of the pilot, namely the improvement of transfer-passenger flows through the airport, and how we helped Heathrow move from its existing legacy system for managing passenger flows to an advanced machine learning-based approach using real-time inputs. The system, which is now in operation at Heathrow, can predict which passengers are likely to miss their connecting flights, reducing the likelihood that departures will incur delays while waiting for delayed passengers. This can be done by offloading passengers in advance, by expediting passengers through the airport, or by modifying the departure times of aircraft in advance. By aggregating estimated passenger arrival time at various points throughout the airport, the system also improves passenger experiences at immigration and security desks, by enabling modifications to staffing levels in advance of expected surges in arrivals. The nine-stage framework we present here can support the development and implementation of other real-time data-driven systems. To the best of our knowledge, the proposed system is the first to use machine learning to model passenger flows in an airport.

An Improved Divergence-Free Hatch Filter Algorithm Toward Sub-Meter Train Positioning With GNSS Single- Frequency Observations Only

Train positioning is the core function in the application of Global Navigation Satellite Systems (GNSS) in Railway Transportation. However, the use of the differential GPS (DGPS) along the Qinghai-Tibet Railway is expensive and difficult to maintain. Thus, a novel single-frequency algorithm based on the divergence-free Hatch filter is proposed, and no real-time augmentation correction input is required. The classical Hatch filter is severely affected by the divergence problem due to the ionospheric variation. In our algorithm, a novel decomposition-ensemble model is proposed for denoising and modeling the ionospheric variation, where the Variational Mode Decomposition (VMD) method is applied. With the aid of a sliding ionospheric variation fitting window, the divergence-free Hatch filter is constructed. The entire method is a so-called self-modeling method, but more efficient than recent studies. Besides, the Kalman filter is used for keeping continuous positioning accuracy. Finally, a static experiment in Tibet and a kinematic field test on the Qinghai-Tibet Railway is performed. In the ionospheric variation calculation-experiment, the experimental results show that the sliding window of our method can be shortened to 5 minutes with the data of 1s sampling rate, which basically meets the requirements of train positioning. In terms of train positioning accuracy, only the horizontal accuracy is concerned. In the static experiment, our method satisfies the accuracy requirements of the sub-meter level with a Root Mean Square Error (RMSE) value of better than 0.5m. In the kinematic test, the accuracy of our method is basically at the sub-meter level, with an RMSE value of approximately 0.6m.

Fault prediction for distributed computing Hadoop clusters using real-time higher order differential inputs to SVM: Zedacross

Hadoop distributed computing clusters are used worldwide for high-performance computations. Often various hardware and software faults occur, leading to both data and computation time losses. This paper proposes the usage of a fault prediction software called 'Zedacross' which uses machine learning principles combined with cluster monitoring tools. Firstly, the paper suggests a model that uses the resource usage statistics of a normally functioning Hadoop cluster to create a machine learning model that can then be used to predict and detect faults in real time. Secondly, the paper explains the novel idea of using higher order differentials as inputs to SVM for highly accurate fault predictions. Predictions of system faults by observing system resource usage statistics in real-time with minimum delay will play a vital role in deciding the need for job rescheduling tasks or even dynamic up-scaling of the cluster. To demonstrate the effectiveness of the design a Java utility was built to perform cluster fault monitoring. The results obtained after running the system on various test cases demonstrate that the proposed method is accurate and effective.

Fault prediction for distributed computing Hadoop clusters using real-time higher order differential inputs to SVM: Zedacross

Hadoop distributed computing clusters are used worldwide for high-performance computations. Often various hardware and software faults occur, leading to both data and computation time losses. This paper proposes the usage of a fault prediction software called 'Zedacross' which uses machine learning principles combined with cluster monitoring tools. Firstly, the paper suggests a model that uses the resource usage statistics of a normally functioning Hadoop cluster to create a machine learning model that can then be used to predict and detect faults in real time. Secondly, the paper explains the novel idea of using higher order differentials as inputs to SVM for highly accurate fault predictions. Predictions of system faults by observing system resource usage statistics in real-time with minimum delay will play a vital role in deciding the need for job rescheduling tasks or even dynamic up-scaling of the cluster. To demonstrate the effectiveness of the design a Java utility was built to perform cluster fault monitoring. The results obtained after running the system on various test cases demonstrate that the proposed method is accurate and effective.

The Research of Gait Recognition Based on Deep Learning: A Case Study of the Missing Elderly

In our daily life, we often see some notices for the missing elderly. As we all know, the elderly people with Alzheimer’s disease or memory impairment are more likely and more often to get lost. Therefore, I hope that I can make some contribution to help solve this problem. For this reason, the author a detection and tracking system with interactive interface was designed by the author based on gait recognition for the elder people who are under the risk of getting lost. The walking characteristics of the elderly can be extracted from the gait image data of the elderly provided by their families. Combined with the video streaming information documented by the cameras of the public security organ, the detection and tracking system can identify the missing elderly at a long distance, in this way, it provides clues for searching the missing elderly. In this paper, all experiments were under the Windows 7 operating system. Python was used to invocate yolov3 model for character detection. The foreground images were obtained by applying background subtraction in the static background, and then gray processing, Gauss blurring, binarization and other image operations were done to extract the image features and obtain the GEI gait energy map with the help of gait feature extraction technology. The image data were stored in the database, and then pedestrian identity detection was carried out through an input video or by real-time cameras. In order to test conveniently, an interactive interface based on PyQt4 is designed, which can realize functions such as register pedestrian names on site, acquire pedestrian gait energy map and establish database, refresh background, detect and recognize pedestrians. Moreover, it supports arbitrary switching between real-time camera detection and input video detection.

Malaria predictions based on seasonal climate forecasts in South Africa: A time series distributed lag nonlinear model

Although there have been enormous demands and efforts to develop an early warning system for malaria, no sustainable system has remained. Well-organized malaria surveillance and high-quality climate forecasts are required to sustain a malaria early warning system in conjunction with an effective malaria prediction model. We aimed to develop a weather-based malaria prediction model using a weekly time-series data including temperature, precipitation, and malaria cases from 1998 to 2015 in Vhembe, Limpopo, South Africa and apply it to seasonal climate forecasts. The malaria prediction model performed well for short-term predictions (correlation coefficient, r > 0.8 for 1- and 2-week ahead forecasts). The prediction accuracy decreased as the lead time increased but retained fairly good performance (r > 0.7) up to the 16-week ahead prediction. The demonstration of the malaria prediction process based on the seasonal climate forecasts showed the short-term predictions coincided closely with the observed malaria cases. The weather-based malaria prediction model we developed could be applicable in practice together with skillful seasonal climate forecasts and existing malaria surveillance data. Establishing an automated operating system based on real-time data inputs will be beneficial for the malaria early warning system, and can be an instructive example for other malaria-endemic areas.

Optimizing feed automation: improving timer-feeders and on demand systems in semi-intensive pond culture of shrimp Litopenaeus vannamei

The continued success of shrimp farming will rely on improved feed management and reductions in labor costs. Shrimp are omnivorous, eating many small meals with limited stomach capacity for food storage. Hence, increased performance may be obtained by spreading feed through multiple meals. Initial work has demonstrated that moving from two feeding per day into multiple feeding systems increases growth rate and production. Further advances have been made with on-demand (satiation) feeding systems. The goal of this work was to continue the development of standard feeding protocol's (SFP) for automatic feeding systems to maximize growth rates in semi-intensive pond production of shrimp, Litopenaeus vannamei. For this work a 13-week pond production trial was performed in 16, 0.1 ha outdoors ponds, stocked at a 26 shrimp/m2, and fed 1.5-mm 40% crude protein for the first four weeks, and 2.4-mm protein soy optimized feed (35% crude protein) for last nine weeks, both produced by Zeigler Inc. Four treatments including: three fixed feeding treatments of 130, 145 and 160% of a SFP (SFP + 30%, SFP + 45%, SFP + 60%, respectively) were offered using automatic timer-feeders, and a fourth treatment utilized on-demand AQ1 acoustic feeding system. No statistical differences were found between treatments for survival (ranging 75.2–81.4%) and FCR (ranging 0.96–1.11). In general, increased feed inputs resulted in higher production. The best response was with the AQ1 system which adjusted feed inputs in real time and ended up offered higher feed inputs resulting in larger shrimp and yields. Based on results of this work and previous trials, standard feeding protocols for automated systems can be developed but to date, automated feedback systems which operate in real time out perform the standardized practices.

Optimization of Hybrid Renewable Energy System Using Homer

In this modern epoch Sustainable Energy Resources (SER) takes an upper hand in meeting the rise in power demand. Over the last few years, the increasing electrical power demand has prompted an incredible need for power from sustainable energy sources. The irradiation from solar, wind turbines are pondered as the main source of power generation since they supplement one another. For the general development of the economy, it is important that the agro-based economy would lead to the growth of the country. It is neither achievable nor affordable to dispatch power in the far away locales for a scarcely populated town. In this paper, the supplanting of energy sources with the sustainable power sources utilizing HOMER programming is performed. An independent sustainable power sources (ISPS) is used to meet the load and the cost is evaluated. The work is performed for real time data under different schemes like PV, wind and its combination. The optimization of operating cost under two scenario of using the ISPS (either PV or Wind) and using both PV & wind for real-time input taken from Sicud village in Philippines and Laboratory load data of SRMIST in India is performed. The comparison of the operating cost for the two region under two cases is executed and analyzed.

Design of Hardware Module for the Vehicle Condition Monitoring System Based on the Internet of Things

One problem in the development stage of driverless cars on public roads is how to monitor the condition of the vehicle that is affected by different weather and environment, including dry, snowy or heavy rain conditions, which are sometimes difficult to predict and require monitoring systems that should be real-time and accurate. For this reason, an internet of things-based car condition monitoring system is needed to be developed. The development covers three essential parts, which include the development of hardware and digital communication modules, web server development and data analysis and mobile application development for monitoring. The purpose of this study is to design a hardware module needed for car vehicle condition monitoring system; a prototype completed with the onboard diagnostic module and embedded system that will send data to the server in real time. The system was successfully designed and developed using ELM327 and ESP32 with SIM808 for communication module. The benefits of this research are as a tool for asset management of car vehicles both for personal and corporate needs. This study also supports the development of driverless cars that require real-time data input between the vehicle and the server.

Real-time nonlinear model predictive energy management system for a fuel-cell hybrid vehicle

Proton exchange membrane fuel cell is considered as one of the most efficient sources of renewable energy. Time-varying dynamic and nonlinear equations are two major factors that make control and power optimization of fuel-cell vehicles challenging. In this paper, by using a comprehensive PEMFC vehicle model and nonlinear model predictive controller, a novel energy management method is represented. By considering both of the regenerating brake power and fuel-cell output power as the controller inputs, the steady-state equations have been derived in a nonlinear form. Also, the NMPC contains a constrained quadratic cost function which has been minimized to make the controller inputs completely optimized. Moreover, the two controller references using in this article have been achieved based on experimental FTP drive-cycle data. Finally, the optimized cost-function weighting matrices will be calculated by genetic algorithm, and then, the real-time controller inputs are applied to the vehicle model to get better results on vehicle range during an online procedure, and the online results are compared with the experimental drive-cycle data.

Z *-Numbers, Data Structures, and Thinking in Machine-Mind Architecture

A generally intelligent cognitive machine is deliberative, reflective, adaptive, empathetic and rational; continually aiming for the best responses to complex real-world events. This article describes our efforts towards the realization of such a machine – an embodied machine-mind – endowed with abilities of multisensory processing, commonsense reasoning, reflection, consciousness, and empathy. A procedure for contemplation and comprehension by the machine-mind has been formalized. It uses: a) Z*-numbers for active-thought abstraction, b) multisensory data-structures to encapsulate objective and subjective real-time inputs, and transport these across framework-modules, and c) dynamic action-descriptor formulations for bespoke behavior, perception, and real-time attention modulation. The defined procedure acknowledges the machine-mind's interest in the subject being comprehended, and covers different levels of thinking (instinctive reactions to self-consciousness reasoning). This investigation contributes to the synthesis of ‘thinking machines’ for man-machine symbiosis.

The PanVax Tool to Improve Pandemic Influenza Emergency Vaccination Program Readiness and Partnership.

Objectives. To show how the Centers for Disease Control and Prevention's Pandemic Vaccine Campaign Planning Tool (PanVax Tool) can help state and local public health emergency planners demonstrate and quantify how partnerships with community vaccine providers can improve their overall pandemic vaccination program readiness.Methods. The PanVax Tool helps planners compare different strategies to vaccinate their jurisdiction's population in a severe pandemic by allowing users to customize the underlying model inputs in real time, including their jurisdiction's size, community vaccine provider types, and how they allocate vaccine to these providers. In this report, we used a case study with hypothetical data to illustrate how jurisdictions can utilize the PanVax Tool for preparedness planning.Results. By using the tool, planners are able to understand the impact of engaging with different vaccine providers in a vaccination campaign.Conclusions. The PanVax Tool is a useful tool to help demonstrate the impact of community vaccine provider partnerships on pandemic vaccination readiness and identify areas for improved partnerships for pandemic response.

Development of TracMyAir Smartphone Application for Modeling Exposures to Ambient PM2.5 and Ozone.

Air pollution epidemiology studies of ambient fine particulate matter (PM2.5) and ozone (O3) often use outdoor concentrations as exposure surrogates. Failure to account for the variability of the indoor infiltration of ambient PM2.5 and O3, and time indoors, can induce exposure errors. We developed an exposure model called TracMyAir, which is an iPhone application (“app”) that determines seven tiers of individual-level exposure metrics in real-time for ambient PM2.5 and O3 using outdoor concentrations, weather, home building characteristics, time-locations, and time-activities. We linked a mechanistic air exchange rate (AER) model, a mass-balance PM2.5 and O3 building infiltration model, and an inhaled ventilation model to determine outdoor concentrations (Tier 1), residential AER (Tier 2), infiltration factors (Tier 3), indoor concentrations (Tier 4), personal exposure factors (Tier 5), personal exposures (Tier 6), and inhaled doses (Tier 7). Using the application in central North Carolina, we demonstrated its ability to automatically obtain real-time input data from the nearest air monitors and weather stations, and predict the exposure metrics. A sensitivity analysis showed that the modeled exposure metrics can vary substantially with changes in seasonal indoor-outdoor temperature differences, daily home operating conditions (i.e., opening windows and operating air cleaners), and time spent outdoors. The capability of TracMyAir could help reduce uncertainty of ambient PM2.5 and O3 exposure metrics used in epidemiology studies.

Experimental validation of the proposed extended Kalman filter with unknown inputs algorithm based on data fusion

The extended Kalman filter is a useful tool in the research of structural health monitoring and vibration control. However, the traditional extended Kalman filter approach is only applicable when the information of external inputs to structures is available. In recent years, some improved extended Kalman filter methods applied with unknown inputs have been proposed. The authors have proposed an extended Kalman filter with unknown inputs based on data fusion of partially measured displacement and acceleration responses. Compared with previous approaches, the drifts in the estimated structural displacements and unknown external inputs can be avoided. The feasibility of proposed extended Kalman filter with unknown inputs has been demonstrated by some numerical simulation examples. However, experimental validation of the proposed extended Kalman filter with unknown inputs has not been conducted. In this paper, an experiment is conducted to validate the effectiveness of the proposed approach. A five-story shear building model subjected to an unknown external excitation of wide-band white noise is conducted. Moreover, the data fusion of partially measured strain and acceleration responses from the building is adopted as it is difficult to accurately measure structural displacement in practice. Identified results show that the recently proposed extended Kalman filter with unknown inputs can be applied to identify structural parameters, structural states, and the unknown inputs in real time.

Brian 2, an intuitive and efficient neural simulator.

Brian 2 allows scientists to simply and efficiently simulate spiking neural network models. These models can feature novel dynamical equations, their interactions with the environment, and experimental protocols. To preserve high performance when defining new models, most simulators offer two options: low-level programming or description languages. The first option requires expertise, is prone to errors, and is problematic for reproducibility. The second option cannot describe all aspects of a computational experiment, such as the potentially complex logic of a stimulation protocol. Brian addresses these issues using runtime code generation. Scientists write code with simple and concise high-level descriptions, and Brian transforms them into efficient low-level code that can run interleaved with their code. We illustrate this with several challenging examples: a plastic model of the pyloric network, a closed-loop sensorimotor model, a programmatic exploration of a neuron model, and an auditory model with real-time input.

Method for Measurements of Terrestrial Ultraviolet Radiation on Inclined Surfaces in Personal Dosimetry Field Studies.

Understanding personal ultraviolet radiation (UVR) exposure is essential for the evaluation of the health risks and benefits; however, personal dosimetry could be challenging in large-scale or/and long-term population studies. Alternatively, personal exposure could be simulated using three-dimensional models and lifestyle surveys together with data on a body position with respect to the sun. These models require a real-time input on local environmental UVR. The main challenge in using this method is retrieval of the diffuse irradiance as it requires an often-expensive tracking of solar position. In this study, a hypothesis that UVR measured on a vertical plane in the north direction can be used in the UK as a proxy for diffuse radiation was tested against direct measurements and compared with models based on solar tracker data in Chilton, UK, (51.57°N) in June-July 2018. The statistical analysis over 17 days under all weather conditions showed that for 45° and 90° tilted surfaces the proposed method performed as well as the best of the models based on solar tracker data. A proposed system could offer a portable and low-cost alternative to measurements of diffuse radiation by solar tracking radiometers for spatial distribution of terrestrial erythema effective UVR in population field studies.

Reliable control of cyber-physical systems under sensor and actuator attacks: An identifier-critic based integral sliding-mode control approach

This study focuses on reliable control problems for cyber-physical systems (CPSs), described by linear continuous time-invariant systems, under a class of time-varying state-dependent sensor and actuator attacks. According to the state-dependent property of sensor attacks, the original reliable control problem is converted into a problem to stabilise a completely unknown time-varying system with the actuator attacks. Firstly, a dynamic neural network (NN) identifier with an indicator-function term is developed to model the unknown system dynamics. Due to the indicator term, the input distribution matrix of the identifier is guaranteed to be of full column rank. It provides a technical condition for designing an effective identifier-based integral sliding-mode (I-SM) attack compensator. It is shown that, under the proposed adaptive law, the identification errors and NN weight estimation errors are uniformly ultimately bounded. Furthermore, an identifier-critic based I-SM controller, which consists of an ADP-based controller and an adaptive I-SM attack compensator, is online learned using real-time control input and compromised sensor data, such that the unknown dynamics with the actuator attacks is stable with a nearly optimal performance. Meanwhile, it is shown that, the developed control approach ensures that the states in CPSs under sensor and actuator attacks converge to a compact set around zero. Finally, the effectiveness of the proposed one is verified by two illustrative examples.

Collecting reliable training data to extract tourism strolling behaviour from smartphone GPS logs during walking

Collecting reliable training data to extract tourism strolling behaviour from smartphone GPS logs during walking

SketTune: Real-time input assistance for novices to compose music for self-expression

When novice composers create a combination of melodies and accompaniments in the early stages of composition, they require a high easiness and good flexibility. We define music sketches as a “combination of an accompaniment and a melody. ” Novices need assistance in making music sketches, however, automation approach increases easiness but decreases flexibility. In this paper, we have developed a system that can input natural melodies in real-time based on the accompaniments so that novice composers can easily make music sketches. Moreover, the system provides rhythm assistance for novice composers who cannot provide inputs in real-time. Finally, we evaluated the proposed system using a comparison experiment having four systems that differed based on the note-flexibility, which is the flexibility of the pitches and the rhythms. As a result, we proved that the proposed system is the best for novice composers because of its easiness and note-flexibility.