Prediction-based Approach Research Articles

Performance evaluation of CoAP proxy virtualisation in cloud‐assisted sensor networks

In this study, the authors have modelled the performance of a scalable proxy virtualisation framework to support an appropriate level of quality of service (QoS) for delay sensitive applications in cloud-based large-scale sensor networks. The proposed model leverages the functionalities of a constrained application protocol (CoAP) to expose a standard interface for transparently decoupling of the applications from servers and ensuring the implementation of the custom QoS metrics through virtualisation techniques. The model, combined with the prediction-based dynamic resource allocation approach, enables the computation of the number of requests that can be supported for a given service rate and required QoS. It also features the evaluation of different performance metrics, particularly, the probability distribution of the response time and the ability to identify the optimal balance between the resource cost and the service performance. The numerical results obtained from the proposed analytical model can be used to help design and optimise industrial cloud-based sensing systems.

Prediction-based approach to stabilization of 2-D continuous-time Roesser systems with directional input delays

In this paper, the problem of exponential stabilization of two-dimensional (2-D) continuous-time Roesser systems with directional input delays is studied. A predictor-based control strategy is applied to this type of systems for the first time. Based on an extended Lyapunov–Krasovskii functional method, stability analysis and synthesis conditions of a desired controller are derived in the form of linear matrix inequalities (LMIs). An extension to the case of directional input and output delays is also presented.

LocJury: An IBN-Based Location Privacy Preserving Scheme for IoCV

Stemming from the recent evolutionary progress of the 5G wireless communication and Internet of Things (IoT) relevant technologies, the vision of the Internet of Connected Vehicles (IoCV) has become more apparent. On the basis of the state-of-the-art IoCV conceptual implementations, the location of the vehicles is one of the essential driven data of IoCV, and the location privacy issue needs to be taken into account. However, when scrutinizing into IoCV, noticeable challenges of location-aware scenario has raised. For IoCV, location is more than just query criteria like in Location-based Services (LBSs) of mobile Internet. It is also the underpinning data of various types of IoCV underlying mechanisms and functions. This difference makes preserving location privacy in IoCV quite different from the traditional privacy scenarios. In this paper, an overall analysis of end-user location privacy in IoCV was performed. To solve the location privacy dilemma, we proposed an intent prediction-based approach named LocJury, which benefits from the emerging concept of Intent-based Networking (IBN). LocJury provides location privacy by learning and estimate the intent of location access and will penalize those malicious location accesses. By simulating the conceptual IBN-based IoCV application scenario, which relies on the location accesses, the performance of LocJury is evaluated under various circumstances. The simulation result verified the effectiveness of our proposed method.

Clustering-Based Self-Imputation of Unlabeled Fault Data in a Fleet of Photovoltaic Generation Systems

This work proposes a fault detection and imputation scheme for a fleet of small-scale photovoltaic (PV) systems, where the captured data includes unlabeled faults. On-site meteorological information, such as solar irradiance, is helpful for monitoring PV systems. However, collecting this type of weather data at every station is not feasible for a fleet owing to the limitation of installation costs. In this study, to monitor a PV fleet efficiently, neighboring PV generation profiles were utilized for fault detection and imputation, as well as solar irradiance. For fault detection from unlabeled raw PV data, K-means clustering was employed to detect abnormal patterns based on customized input features, which were extracted from the fleet PVs and weather data. When a profile was determined to have an abnormal pattern, imputation for the corresponding data was implemented using the subset of neighboring PV data clustered as normal. For evaluation, the effectiveness of neighboring PV information was investigated using the actual rooftop PV power generation data measured at several locations in the Gwangju Institute of Science and Technology (GIST) campus. The results indicate that neighboring PV profiles improve the fault detection capability and the imputation accuracy. For fault detection, clustering-based schemes provided error rates of 0.0126 and 0.0223, respectively, with and without neighboring PV data, whereas the conventional prediction-based approach showed an error rate of 0.0753. For imputation, estimation accuracy was significantly improved by leveraging the labels of fault detection in the proposed scheme, as much as 18.32% reduction in normalized root mean square error (NRMSE) compared with the conventional scheme without fault consideration.

A Prediction-Based Approach to Distributed Filtering With Missing Measurements and Communication Delays Through Sensor Networks

This article addresses the prediction-based distributed filtering problem for a class of time-varying nonlinear stochastic systems with communication delays and missing measurements through the sensor networks. The phenomenon of the missing measurements is depicted by a set of Bernoulli distributed random variables, where each sensor node possesses its own missing probability. The communication delays are taken into account, which commonly occur during the estimation exchanges among the sensor nodes with communication links. A new prediction-based suboptimal distributed filter is designed by taking the missing probabilities and the prediction estimation into account, which has the advantages on the active compensation of the impacts caused by the missing measurements and communication delays. That is, a new compensation filtering method within the time-varying framework is presented based on the predictive estimation and the innovation measurements. A locally minimum upper bound matrix for the estimation error covariance is obtained by properly designing the distributed filter gain at every sampling step. Furthermore, the performance analysis problem of the prediction-based distributed filtering algorithm is discussed by providing the desirable theoretical derivations. Finally, some comparative simulations are used to show the advantages of the presented prediction-based distributed filtering strategy under delay compensation mechanism.

Operational Planning of a Residential Fuel Cell System for Minimizing Expected Operational Costs Based on a Surrogate Model

This study proposes a novel operational planning method for polymer electrolyte fuel cell cogeneration systems (PEFC-CGSs). PEFC-CGSs provide hot water by utilizing waste heat produced in the electricity generation process, and hot water is stored in an attached tank. Generating and storing hot water based on an optimal operational plan according to household demand leads to further energy saving; therefore, operational planning methods based on household demand prediction have received significant attention. However, the improvement in the demand prediction accuracy does not necessarily lead to efficient PEFC-CGS operation in terms of operational costs; in other words, the accuracy in the demand prediction does not directly indicate the resulting operational efficiency. In this study, the authors propose a novel approach based on a surrogate model for deriving an appropriate plan that minimizes the expected operational costs among the operational plan candidates. In the proposed scheme, the error between expected and actual operational costs explicitly represents the relevance of the operational plan, so that the optimal operational plan can be selected directly from the perspective of the resulting operational efficiency. The practicality of the proposed approach is evaluated with the existing demand prediction-based approach via numerical simulations using real-world measurements of multiple customers in Japan. The proposed method reveals 30% reduction of the excessive operational costs by avoiding the inefficient operation of the auxiliary gas-heater in the experiments and will further enhance the value of introducing highly efficient residential fuel cell system that contributes to a low-carbon society.

An interval-prediction based robust optimization approach for energy-hub operation scheduling considering flexible ramping products

The energy-hub (EH) technique provides a new-type conceptual framework for the interaction, coupling, conversion of different forms of energies to achieve the improvement of energy usage efficiency. In this paper, an optimal economic dispatching model for a residential-level EH in the energy market considering the flexible ramping product (FRP) is proposed. As distinct from existing studies, in this work, we assume that the EH not only involves bidding in the energy market but may also get profits by providing the FRP to the grid. The discussed problem is formulated as a two-stage robust optimization (RO) model, wherein the first-stage is dedicated to minimizing the operation cost of the EH by optimizing its bidding strategy (energy and flexible ramping trading quantities) in the DA market, while the second-stage aims to determine the optimal re-dispatch/corrective schedule of the EH (including adjusted output of EH components, bidding and flexible ramping amount) in the RT market to achieve the energy balancing with the least cost, considering the worst-case realization of uncertainties. In practice, since the selection of uncertainty interval has an important impact on the efficacy of the RO solution, we propose an interval prediction-based approach combining the long short-term memory (LSTM) recurrent neural network and bootstrapping technique to determine the uncertainty interval used in our RO formulation. Compared with the conventional empirical-based interval-setting, the proposed prediction-based technique is useful to reduce the conservative level of RO solutions by deep learning the value of historical data and reflecting the real error distribution of point forecast results in its estimation. The effectiveness of the proposed methodology is examined based on a residential EH case, and the obtained results confirm the validity of the proposed approach in actual implementations.

Generation of Homogeneous VHR Time Series by Nonparametric Regression of Multisensor Bitemporal Images

The availability of multitemporal images acquired by several very high geometrical resolution (VHR) optical sensors makes it possible to build VHR image time series (TS) of images acquired over the same geographical area with a temporal resolution better than the one achievable when considering a single VHR sensor. However, such TS include images showing different characteristics from the geometrical, radiometrical, and spectral viewpoint. Thus, there is a need of methods for building homogeneous VHR optical TS when using multispectral multisensor images. By focusing on the spectral domain, we propose a method to transform a VHR image into the spectral domain of another image in the same multisensor TS but acquired by a different sensor. To this end, a prediction-based approach relying on a nonparametric regression method is employed to mitigate sensor-dependent spectral differences. The impact of possible changes occurred on the ground is mitigated by training the prediction model on unchanged samples, only. Experimental results obtained on VHR optical multisensor images confirm the effectiveness of the proposed approach.

Prediction-based approach to finite-time stabilization of networked control systems with time delays and data packet dropouts

The problem of finite-time stabilization is investigated for a class of discrete-time networked control systems with network induced time delays and data packet dropouts in the feedback channel and the forward channel. By using predictive networked control methods, novel finite-time state-feedback and output-feedback stabilization controllers are proposed, and the time delays and data packet dropouts are compensated actively. For the given discrete-time networked control system, sufficient conditions of finite-time stabilization are given. Numerical examples are provided to illustrate the effectiveness of the proposed results in this paper.

Land cover change detection using focused time delay neural network

The development of improved satellite technology generates a huge amount of remote sensing data, these data play the crucial role in natural resource management. The land use and land cover (LULC) change intensely affects local environment, as well as the global environment. Therefore, the quantifiable knowledge about LULC changes occur in global scale is important to make effective planning for conservation and precise use of natural resources, that has motivated the scientists to develop the various land cover change detection techniques. In this paper, we have proposed neural network-based approach, i.e., focused time delay neural network (FTDNN)-based approach for land cover change detection, which is a time series prediction-based approach and detect the sudden change in the enhanced vegetation index (EVI) time series. The performance of the proposed method has been addressed by using quantitative and qualitative analysis techniques. For the quantitative evaluation, the proposed algorithm is applied to the standard synthetic data set, which are analogous to EVI time series data set. The performance result of the proposed method compares with the four previously existing data mining-based benchmark techniques. The analysis was shown that the FTDNN-based method significantly outperforms than other techniques. For qualitative analysis, the San Francisco Bay Area data set has been used, which comprises real EVI time series. The proposed FTDNN-based method is applied to the San Francisco Bay Area data set and observe the interesting land cover changes. These outcomes indicate the effectiveness of data mining techniques for the land cover change detection problem.

A prediction-based approach for features aggregation in Visual Sensor Networks

Visual Sensor Networks (VSNs) constitute a key technology for the implementation of several visual analysis tasks. Recent studies have demonstrated that such tasks can be efficiently performed following an operative paradigm where cameras transmit to a central controller local image features, rather than pixel-domain images. Furthermore, features from multiple camera views may be efficiently aggregated exploiting the spatial redundancy between overlapping views. In this paper we propose a routing protocol designed for supporting aggregation of image features in a VSN. First, we identify a predictor able to estimate the efficiency of local features aggregation between different cameras in a VSN. The proposed predictor is chosen so as to minimize the prediction error while keeping the network overhead cost low. Then, we harmonically integrate the proposed predictor in the Routing Protocol for Low-Power and Lossy Networks (RPL) in order to support the task of in-network feature aggregation. We propose a RPL objective function that takes into account the predicted aggregation efficiency and build the routes from the camera nodes to a central controller so that either energy consumption or used network bandwidth is minimized. Extensive experimental results confirm that the proposed approach can be used to increase the efficiency of VSNs.

Hierarchical prediction-based motion vector refinement for video frame-rate up-conversion

Motion-compensated frame-rate up-conversion (MC-FRUC) often exploits either bilateral motion estimation (ME) or unidirectional ME with a fixed block size, which constrains the perceptual quality of up-converted video. In this paper, an advanced MC-FRUC approach is proposed by exploiting hierarchical prediction-based motion vector refinement. To reduce block mismatching in texture regions and color areas, an adaptive multi-layered block matching criterion is designed to extract color and edge information, which is integrated with motion information as constraint term. A hierarchical prediction-based motion vector refinement approach is proposed to obtain more accurate and dense motion vector fields (MVFs). To eliminate the outliers of MVFs, a robust dual-weighted motion vector smoothing scheme is adopted by using both spatial correlation and reliability of neighboring blocks. Experimental results show that the proposed approach has low computational complexity and outperforms state-of-the-art works in both objective and subjective qualities of interpolated frames.

Scheduling and Control Co-Design for Control Systems under Computational Constraints

A prediction-based approach is proposed for control systems with limited and time-varying computational resources. The limited and time-varying computational resources can make the control system run in an open-loop fashion which may severely degrade the system performance or even destabilize the system. This issue is dealt with by producing more than one forward control predictions when abundant computational resources are available, and then using these forward control predictions to close the system when the computational resources are insufficient to calculate real-time control signal. This achievement is made without additional requirement for the computational resources and can be regarded as a useful completion of the scheduling algorithms. With a controller designed using a modified model predictive control method, the effectiveness of the proposed approach is successfully illustrated by a numerical example.

Curtailing patient-specific IMRT QA procedures from 2D dose error distribution.

A patient-specific quality assurance (QA) test is conducted to verify the accuracy of dose delivery. It generally consists of three verification processes: the absolute point dose difference, the planar dose differences at each gantry angle, and the planar dose differences by 3D composite irradiation. However, this imposes a substantial workload on medical physicists. The objective of this study was to determine whether our novel method that predicts the 3D delivered dose allows certain patient-specific IMRT QAs to be curtailed. The object was IMRT QA for the pelvic region with regard to point dose and composite planar dose differences. We compared measured doses, doses calculated in the treatment planning system, and doses predicted by in-house software. The 3D predicted dose was reconstructed from the per-field measurement by incorporating the relative dose error distribution into the original dose grid of each beam. All point dose differences between the measured and the calculated dose were within ±3%, whereas 93.3% of them between the predicted and the calculated dose were within ±3%. As for planar dose differences, the gamma passing rates between the calculated and the predicted dose were higher than those between the calculated and the measured dose. Comparison and statistical analysis revealed a correlation between the predicted and the measured dose with regard to both point dose and planar dose differences. We concluded that the prediction-based approach is an accurate substitute for the conventional measurement-based approach in IMRT QA for the pelvic region. Our novel approach will help medical physicists save time on IMRT QA.

Fuzzy modeling, stabilization and synchronization of multi-scroll chaotic systems

A novel fuzzy control concept for stabilizing and synchronizing multi-scroll chaotic systems is presented in this paper. First, the multi-scroll chaotic systems are exactly derived using Takagi-Sugeno (T-S) fuzzy models. Then, the fuzzy controllers for stabilization and synchronization processes are designed via the prediction-based approach. Computer simulations on typical multi-scroll chaotic systems are provided to show the effectiveness of the proposed schemes.

PDC: Prediction-based data-aware clustering in wireless sensor networks

Minimizing energy consumption is the most important concern in wireless sensor networks (WSNs). To achieve this, clustering and prediction methods can enjoy the inherent redundancy of raw data and reduce transmissions more effectively. In this paper, we focus on designing a prediction-based approach, named PDC, to mainly contribute in data-aware clustering. It exploits both spatial and temporal correlations to form highly stable clusters of nodes sensing similar values. Here, the sink node uses only the local prediction models of cluster heads to forecast all readings in the network without direct communication. To the best of our knowledge, PDC is a novel energy efficient approach which provides a high precision of the approximate results with bounded error. Our simple prediction model presents high accuracy as well as low computation and communication costs. Extensive simulations have been conducted to evaluate the prediction model as well as our clustering approach. The results verify the superiority of our simple prediction model. Moreover, PDC implies a significant improvement on existing alternatives.

Extracting viewer interests for automated bookmarking in video-on-demand services

Video-on-demand (VoD) services have become popular on the Internet in recent years. In VoD, it is challenging to support the VCR functionality, especially the jumps, while maintaining a smooth streaming quality. Previous studies propose to solve this problem by predicting the jump target locations and prefetching the contents. However, through our analysis on traces from a real-world VoD service, we find that it would be fundamentally difficult to improve a viewer’s VCR experience by simply predicting his future jumps, while ignoring the intentions behind these jumps.Instead of the prediction-based approach, in this paper, we seek to support the VCR functionality by bookmarking the videos. There are two key techniques in our proposed methodology. First, we infer and differentiate viewers’ intentions in VCR jumps by decomposing the interseek times, using an expectation-maximization (EM) algorithm, and combine the decomposed inter-seek times with the VCR jumps to compute a numerical interest score for each video segment. Second, based on the interest scores, we propose an automated video bookmarking algorithm. The algorithm employs the time-series change detection techniques of CUSUMandMB-GT, and bookmarks videos by detecting the abrupt changes on their interest score sequences.We evaluate our proposed techniques using real-world VoD traces from dozens of videos. Experimental results suggest that with our methods, viewers’ interests within a video can be precisely extracted, and we can position bookmarks on the video’s highlight events accurately. Our proposed video bookmarking methodology does not require any knowledge on video type, contents, and semantics, and can be applied on various types of videos.

Fast orientation prediction-based discrete wavelet transform for remote sensing image compression

In this letter, a fast orientation prediction-based discrete wavelet transform (DWT) is introduced for high-spatial-resolution remote sensing image compression. The proposed fast orientation prediction-based approach is designed to improve coding performance and reduce computational complexity of the previous adaptive directional lifting method. The main contribution of the proposed approach consists of three parts: a new orientation map is designed to achieve a better transform coding performance; an orientation prediction model is presented to fast obtain the optimal transform orientation; the new fast orientation prediction-based DWT is introduced. Experimental results show that the proposed fast orientation prediction-based high-spatial-resolution remote sensing image coding technique outperforms the traditional lifting wavelet and the method based on adaptive directional lifting in coding performance, and the computational complexity of the proposed transform is far lower than that of adaptive directional lifting method.

Model prediction-based approach to fault-tolerant control with applications

Abstract— Fault-tolerant control (FTC) is an integral component in industrial processes as it enables the system to continue robust operation under some conditions. In this paper, an FTC scheme is proposed for interconnected systems within an integrated design framework to yield a timely monitoring and detection of fault and reconfiguring the controller according to those faults. The unscented Kalman filter (UKF)-based fault detection and diagnosis system is initially run on the main plant and parameter estimation is being done for the local faults. This critical information is shared through information fusion to the main system where the whole system is being decentralized using the overlapping decomposition technique. Using this parameter estimates of decentralized subsystems, a model predictive control (MPC) adjusts its parameters according to the fault scenarios thereby striving to maintain the stability of the system. Experimental results on interconnected continuous time stirred tank reactors (CSTR) with recycle and quadruple tank system indicate that the proposed method is capable to correctly identify various faults, and then controlling the system under some conditions.

Forward Prediction-Based Approach to the Out-of-Sequence Measurement Problem with Correlated Noise

In target tracking systems, measurements from the same target can arrive out-of-sequence. Such OOSM arrivals can induce negative-time measurement update problem. In order to solve the l-step-lag OOSM problem with correlated process noise and measurement noise, a new algorithm based on forward prediction is proposed. A modified information filter is adopted so as to eliminate the correlated noise. By defining an equivalent measurement the l-step-lag OOSM problem is transformed into 1-step-lag problem. The new algorithm is independent with the discrete time model of the process noise. The storage requirements and calculations are reduced. The simulation results show its effectiveness.