A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation

Vol. 6,  No. 6, 2019

Guest Editorial for Special Issue on Time Series Classification
Houshang Darabi, Georgiana Ifrim, Patrick Schäfer, Diego Furtado Silva
2019, 6(6): 1291-1292. doi: 10.1109/JAS.2019.1911741
Abstract(1390) HTML (680) PDF(122)
The UCR Time Series Archive
Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, Eamonn Keogh
2019, 6(6): 1293-1305. doi: 10.1109/JAS.2019.1911747
Abstract(4191) HTML (834) PDF(214)
The UCR time series archive – introduced in 2002, has become an important resource in the time series data mining community, with at least one thousand published papers making use of at least one data set from the archive. The original incarnation of the archive had sixteen data sets but since that time, it has gone through periodic expansions. The last expansion took place in the summer of 2015 when the archive grew from 45 to 85 data sets. This paper introduces and will focus on the new data expansion from 85 to 128 data sets. Beyond expanding this valuable resource, this paper offers pragmatic advice to anyone who may wish to evaluate a new algorithm on the archive. Finally, this paper makes a novel and yet actionable claim: of the hundreds of papers that show an improvement over the standard baseline (1-nearest neighbor classification), a fraction might be mis-attributing the reasons for their improvement. Moreover, the improvements claimed by these papers might have been achievable with a much simpler modification, requiring just a few lines of code.
Classification of Short Time Series in Early Parkinson’s Disease With Deep Learning of Fuzzy Recurrence Plots
Tuan D. Pham, Karin Wårdell, Anders Eklund, Göran Salerud
2019, 6(6): 1306-1317. doi: 10.1109/JAS.2019.1911774
Abstract(2399) HTML (1893) PDF(212)
There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson's disease (PD). A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease. Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long. With an attempt to avoid discomfort to participants in performing long physical tasks for data recording, this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory (LSTM) neural networks. Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture, fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.
Self-Learning of Multivariate Time Series Using Perceptually Important Points
Timo Lintonen, Tomi Räty
2019, 6(6): 1318-1331. doi: 10.1109/JAS.2019.1911777
Abstract(1952) HTML (732) PDF(168)
In machine learning, positive-unlabelled (PU) learning is a special case within semi-supervised learning. In positive-unlabelled learning, the training set contains some positive examples and a set of unlabelled examples from both the positive and negative classes. Positive-unlabelled learning has gained attention in many domains, especially in time-series data, in which the obtainment of labelled data is challenging. Examples which originate from the negative class are especially difficult to acquire. Self-learning is a semi-supervised method capable of PU learning in time-series data. In the self-learning approach, observations are individually added from the unlabelled data into the positive class until a stopping criterion is reached. The model is retrained after each addition with the existent labels. The main problem in self-learning is to know when to stop the learning. There are multiple, different stopping criteria in the literature, but they tend to be inaccurate or challenging to apply. This publication proposes a novel stopping criterion, which is called Peak evaluation using perceptually important points, to address this problem for time-series data. Peak evaluation using perceptually important points is exceptional, as it does not have tunable hyperparameters, which makes it easily applicable to an unsupervised setting. Simultaneously, it is flexible as it does not make any assumptions on the balance of the dataset between the positive and the negative class.
Clustering Structure Analysis in Time-Series Data With Density-Based Clusterability Measure
Juho Jokinen, Tomi Räty, Timo Lintonen
2019, 6(6): 1332-1343. doi: 10.1109/JAS.2019.1911744
Abstract(2032) HTML (786) PDF(138)
Clustering is used to gain an intuition of the structures in the data. Most of the current clustering algorithms produce a clustering structure even on data that do not possess such structure. In these cases, the algorithms force a structure in the data instead of discovering one. To avoid false structures in the relations of data, a novel clusterability assessment method called density-based clusterability measure is proposed in this paper. It measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningful insight to the relationships in the data. This is especially useful in time-series data since visualizing the structure in time-series data is hard. The performance of the clusterability measure is evaluated against several synthetic data sets and time-series data sets, which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.
Long-term Traffic Volume Prediction Based on K-means Gaussian Interval Type-2 Fuzzy Sets
Runmei Li, Yinfeng Huang, Jian Wang
2019, 6(6): 1344-1351. doi: 10.1109/JAS.2019.1911723
Abstract(1721) HTML (976) PDF(88)
This paper uses Gaussian interval type-2 fuzzy set theory on historical traffic volume data processing to obtain a 24- hour prediction of traffic volume with high precision. A K-means clustering method is used in this paper to get 5 minutes traffic volume variation as input data for the Gaussian interval type-2 fuzzy sets which can reflect the distribution of historical traffic volume in one statistical period. Moreover, the cluster with the largest collection of data obtained by K-means clustering method is calculated to get the key parameters of type-2 fuzzy sets, mean and standard deviation of the Gaussian membership function. Using the range of data as the input of Gaussian interval type-2 fuzzy sets leads to the range of traffic volume forecasting output with the ability of describing the possible range of the traffic volume as well as the traffic volume prediction data with high accuracy. The simulation results show that the average relative error is reduced to 8% based on the combined K-means Gaussian interval type-2 fuzzy sets forecasting method. The fluctuation range in terms of an upper and a lower forecasting traffic volume completely envelopes the actual traffic volume and reproduces the fluctuation range of traffic flow.
Efficient Deviation Detection Between a Process Model and Event Logs
Lu Wang, Yuyue Du, Liang Qi
2019, 6(6): 1352-1364. doi: 10.1109/JAS.2019.1911750
Abstract(1284) HTML (628) PDF(58)
Business processes described by formal or semi-formal models are realized via information systems. Event logs generated from these systems are probably not consistent with the existing models due to insufficient design of the information system or the system upgrade. By comparing an existing process model with event logs, we can detect inconsistencies called deviations, verify and extend the business process model, and accordingly improve the business process. In this paper, some abnormal activities in business processes are formally defined based on Petri nets. An efficient approach to detect deviations between the process model and event logs is proposed. Then, business process models are revised when abnormal activities exist. A clinical process in a healthcare information system is used as a case study to illustrate our work. Experimental results show the effectiveness and efficiency of the proposed approach.
Forecasting of Software Reliability Using Neighborhood Fuzzy Particle Swarm Optimization Based Novel Neural Network
Pratik Roy, Ghanshaym Singha Mahapatra, Kashi Nath Dey
2019, 6(6): 1365-1383. doi: 10.1109/JAS.2019.1911753
Abstract(1336) HTML (634) PDF(59)
This paper proposes an artificial neural network (ANN) based software reliability model trained by novel particle swarm optimization (PSO) algorithm for enhanced forecasting of the reliability of software. The proposed ANN is developed considering the fault generation phenomenon during software testing with the fault complexity of different levels. We demonstrate the proposed model considering three types of faults residing in the software. We propose a neighborhood based fuzzy PSO algorithm for competent learning of the proposed ANN using software failure data. Fitting and prediction performances of the neighborhood fuzzy PSO based proposed neural network model are compared with the standard PSO based proposed neural network model and existing ANN based software reliability models in the literature through three real software failure data sets. We also compare the performance of the proposed PSO algorithm with the standard PSO algorithm through learning of the proposed ANN. Statistical analysis shows that the neighborhood fuzzy PSO based proposed neural network model has comparatively better fitting and predictive ability than the standard PSO based proposed neural network model and other ANN based software reliability models. Faster release of software is achievable by applying the proposed PSO based neural network model during the testing period.
Predicting the Results of RNA Molecular Specific Hybridization Using Machine Learning
Weijun Zhu, Xiaokai Liu, Mingliang Xu, Huanmei Wu
2019, 6(6): 1384-1396. doi: 10.1109/JAS.2019.1911756
Abstract(1121) HTML (617) PDF(58)
Ribonucleic acid (RNA) hybridization is widely used in popular RNA simulation software in bioinformatics. However, limited by the exponential computational complexity of combinatorial problems, it is challenging to decide, within an acceptable time, whether a specific RNA hybridization is effective. We hereby introduce a machine learning based technique to address this problem. Sample machine learning (ML) models tested in the training phase include algorithms based on the boosted tree (BT), random forest (RF), decision tree (DT) and logistic regression (LR), and the corresponding models are obtained. Given the RNA molecular coding training and testing sets, the trained machine learning models are applied to predict the classification of RNA hybridization results. The experiment results show that the optimal predictive accuracies are 96.2%, 96.6%, 96.0% and 69.8% for the RF, BT, DT and LR-based approaches, respectively, under the strong constraint condition, compared with traditional representative methods. Furthermore, the average computation efficiency of the RF, BT, DT and LR-based approaches are 208 679, 269 756, 184 333 and 187 458 times higher than that of existing approach, respectively. Given an RNA design, the BT-based approach demonstrates high computational efficiency and better predictive accuracy in determining the biological effectiveness of molecular hybridization.
Posture Maintenance Control of 2-Link Object By Nonprehensile Two-Cooperative-Arm Robot Without Compensating Friction
Changan Jiang, Satoshi Ueno
2019, 6(6): 1397-1403. doi: 10.1109/JAS.2019.1911759
Abstract(1588) HTML (581) PDF(76)
In this paper, a method to posture maintenance control of 2-link object by nonprehensile two-cooperative-arm robot without compensating friction is proposed. In details, a mathematical model of the 2-link object is firstly built. Based on the model, stable regions for holding motion of nonprehensile two-cooperative-arm robot are obtained while the 2-link object is kept stable on the robot arms with static friction. Among the obtained stable regions, the robust pairs of orientation angles of the 2-link object are found. Under the robust orientation angles, a feedback control system is designed to control the arms to maintain the 2-link object’s posture while it is being held or lifted up. Finally, experimental results are shown to verify the effectiveness of the proposed method.
An Optimal Hybrid Learning Approach for Attack Detection in Linear Networked Control Systems
Haifeng Niu, Avimanyu Sahoo, Chandreyee Bhowmick, S. Jagannathan
2019, 6(6): 1404-1416. doi: 10.1109/JAS.2019.1911762
Abstract(1651) HTML (577) PDF(81)
A novel learning-based attack detection and estimation scheme is proposed for linear networked control systems (NCS), wherein the attacks on the communication network in the feedback loop are expected to increase network induced delays and packet losses, thus changing the physical system dynamics. First, the network traffic flow is modeled as a linear system with uncertain state matrix and an optimal Q-learning based control scheme over finite-horizon is utilized to stabilize the flow. Next, an adaptive observer is proposed to generate the detection residual, which is subsequently used to determine the onset of an attack when it exceeds a predefined threshold, followed by an estimation scheme for the signal injected by the attacker. A stochastic linear system after incorporating network-induced random delays and packet losses is considered as the uncertain physical system dynamics. The attack detection scheme at the physical system uses the magnitude of the state vector to detect attacks both on the sensor and the actuator. The maximum tolerable delay that the physical system can tolerate due to networked induced delays and packet losses is also derived. Simulations have been performed to demonstrate the effectiveness of the proposed schemes.
Finite-time Adaptive Fault-tolerant Control for Nonlinear Systems With Multiple Faults
Huanqing Wang, Wen Bai, Peter Xiaoping Liu
2019, 6(6): 1417-1427. doi: 10.1109/JAS.2019.1911765
Abstract(2042) HTML (555) PDF(137)
This paper focuses on the problem of adaptive finitetime fault-tolerant control for a class of non-lower-triangular nonlinear systems. The faults encountered in the control system include the actuator faults and the abrupt system fault. By applying backstepping design and neural networks approximation, an adaptive finite-time fault-tolerant control scheme is developed. It is shown that the proposed controller ensures that all signals in the closed-loop system are semi-globally practically finite-time stable and the track-ing error converges to a small neighborhood around the origin within finite time. The simulation is carried out to explain the validity of the developed strategy.
Single Image Rain Removal Using Image Decomposition and a Dense Network
Qiusheng Lian, Wenfeng Yan, Xiaohua Zhang, Shuzhen Chen
2019, 6(6): 1428-1437. doi: 10.1109/JAS.2019.1911441
Abstract(1525) HTML (619) PDF(128)
Removing rain from a single image is a challenging task due to the absence of temporal information. Considering that a rainy image can be decomposed into the low-frequency (LF) and high-frequency (HF) components, where the coarse scale information is retained in the LF component and the rain streaks and texture correspond to the HF component, we propose a single image rain removal algorithm using image decomposition and a dense network. We design two task-driven sub-networks to estimate the LF and non-rain HF components of a rainy image. The high-frequency estimation sub-network employs a densely connected network structure, while the low-frequency sub-network uses a simple convolutional neural network (CNN). We add total variation (TV) regularization and LF-channel fidelity terms to the loss function to optimize the two subnetworks jointly. The method then obtains de-rained output by combining the estimated LF and non-rain HF components. Extensive experiments on synthetic and real-world rainy images demonstrate that our method removes rain streaks while preserving non-rain details, and achieves superior de-raining performance both perceptually and quantitatively.
A Novel Cascaded PID Controller for Automatic Generation Control Analysis With Renewable Sources
Aurobindo Behera, Tapas Kumar Panigrahi, Prakash K. Ray, Arun Kumar Sahoo
2019, 6(6): 1438-1451. doi: 10.1109/JAS.2019.1911666
Abstract(1831) HTML (634) PDF(89)
Present day power scenarios demand a high quality uninterrupted power supply and needs environmental issues to be addressed. Both concerns can be dealt with by the introduction of the renewable sources to the existing power system. Thus, automatic generation control (AGC) with diverse renewable sources and a modified-cascaded controller are presented in the paper. Also, a new hybrid scheme of the improved teaching learning based optimization-differential evolution (hITLBO-DE) algorithm is applied for providing optimization of controller parameters. A study of the system with a technique such as TLBO applied to a proportional integral derivative (PID), integral double derivative (IDD) and PIDD is compared to hITLBO-DE tuned cascaded controller with dynamic load change.The suggested methodology has been extensively applied to a 2-area system with a diverse source power system with various operation time non-linearities such as dead-band of, generation rate constraint and reheat thermal units. The multi-area system with reheat thermal plants, hydel plants and a unit of a wind-diesel combination is tested with the cascaded controller scheme with a different controller setting for each area. The variation of the load is taken within 1% to 5% of the connected load and robustness analysis is shown by modifying essential factors simultaneously by ± 30%. Finally, the proposed scheme of controller and optimization technique is also tested with a 5-equal area thermal system with non-linearities. The simulation results demonstrate the superiority of the proposed controller and algorithm under a dynamically changing load.
Parallel Building: A Complex System Approach for Smart Building Energy Management
Abdulaziz Almalaq, Jun Hao, Jun Jason Zhang, Fei-Yue Wang
2019, 6(6): 1452-1461. doi: 10.1109/JAS.2019.1911768
Abstract(1824) HTML (580) PDF(59)
These days’ smart buildings have high intensive information and massive operational parameters, not only extensive power consumption. With the development of computation capability and future 5G, the ACP theory (i.e., artificial systems, computational experiments, and parallel computing) will play a much more crucial role in modeling and control of complex systems like commercial and academic buildings. The necessity of making accurate predictions of energy consumption out of a large number of operational parameters has become a crucial problem in smart buildings. Previous attempts have been made to seek energy consumption predictions based on historical data in buildings. However, there are still questions about parallel building consumption prediction mechanism using a large number of operational parameters. This article proposes a novel hybrid deep learning prediction approach that utilizes long short-term memory as an encoder and gated recurrent unit as a decoder in conjunction with ACP theory. The proposed approach is tested and validated by real-world dataset, and the results outperformed traditional predictive models compared in this paper.
Saturated Adaptive Output-Constrained Control of Cooperative Spacecraft Rendezvous and Docking
Liang Sun
2019, 6(6): 1462-1470. doi: 10.1109/JAS.2019.1911621
Abstract(1183) HTML (583) PDF(60)
This paper investigates the robust relative pose control for spacecraft rendezvous and docking with constrained relative pose and saturated control inputs. A barrier Lyapunov function is used to ensure the constraints of states, so that the computational singularity of the inverse matrix in control command can be avoided, while a linear auxiliary system is introduced to handle with the adverse effect of actuator saturation. The tuning rules for designing parameters in control command and auxiliary system are derived based on the stability analysis of the closed-loop system. It is proved that all closed-loop signals always keep bounded, the prescribed constraints of relative pose tracking errors are never violated, and the pose tracking errors ultimately converge to small neighborhoods of zero. Simulation experiments validate the performance of the proposed robust saturated control strategy.
A Context Sensitive Multilevel Thresholding Using Swarm Based Algorithms
Shreya Pare, Anil Kumar, Varun Bajaj, Girish Kumar Singh
2019, 6(6): 1471-1486. doi: 10.1109/JAS.2017.7510697
Abstract(1219) HTML (576) PDF(47)
In this paper, a comprehensive energy function is used to formulate the three most popular objective functions: Kapur's, Otsu and Tsalli's functions for performing effective multilevel color image thresholding. These new energy based objective criterions are further combined with the proficient search capability of swarm based algorithms to improve the efficiency and robustness. The proposed multilevel thresholding approach accurately determines the optimal threshold values by using generated energy curve, and acutely distinguishes different objects within the multi-channel complex images. The performance evaluation indices and experiments on different test images illustrate that Kapur's entropy aided with differential evolution and bacterial foraging optimization algorithm generates the most accurate and visually pleasing segmented images.
A Hybrid Learning Method for the Data-Driven Design of Linguistic Dynamic Systems
Chengdong Li, Jianqiang Yi, Yisheng Lv, Peiyong Duan
2019, 6(6): 1487-1498. doi: 10.1109/JAS.2019.1911543
Abstract(978) HTML (500) PDF(32)
In lots of data based prediction or modeling applications, uncertainties and/or noises in the observed data cannot be avoided. In such cases, it is more preferable and reasonable to provide linguistic (fuzzy) predicted results described by fuzzy memberships or fuzzy sets instead of the crisp estimates depicted by numbers. Linguistic dynamic system (LDS) provides a powerful tool for yielding linguistic (fuzzy) results. However, it is still difficult to construct LDS models from observed data. To solve this issue, this paper first presents a simplified LDS whose inputoutput mapping can be determined by closed-form formulas. Then, a hybrid learning method is proposed to construct the data-driven LDS model. The proposed hybrid learning method firstly generates fuzzy rules by the subtractive clustering method, then carries out further optimization of centers of the consequent triangular fuzzy sets in the fuzzy rules, and finally adopts multiobjective optimization algorithm to determine the left and right end-points of the consequent triangular fuzzy sets. The proposed approach is successfully applied to three real-world prediction applications which are: prediction of energy consumption of a building, forecasting of the traffic flow, and prediction of the wind speed. Simulation results show that the uncertainties in the data can be effectively captured by the linguistic (fuzzy) estimates. It can also be extended to some other prediction or modeling problems, in which observed data have high levels of uncertainties.
New Result on Delay-dependent Stability for Markovian Jump Time-delay Systems With Partial Information on Transition Probabilities
Yan Zhang, Ke Lou, Yuan Ge
2019, 6(6): 1499-1505. doi: 10.1109/JAS.2016.7510229
Abstract(989) HTML (490) PDF(43)
This paper focuses on the delay-dependent stability for a kind of Markovian jump time-delay systems (MJTDSs), whose transition rates are incompletely known. In order to reduce the computational complexity and achieve better performance, auxiliary function-based double integral inequality is combined with extended Wirtinger's inequality and Jensen inequality to deal with the double integral and the triple integral in augmented Lyapunov-Krasovskii function (ALKF) and their weak infinitesimal generator respectively, the more accurate approximation bounds with a fewer variables are derived. As a result, less conservative stability criteria are proposed in this paper. Finally, numerical examples are given to show the effectiveness and the merits of the proposed method.
Multi-Model Based PSO Method for Burden Distribution Matrix Optimization With Expected Burden Distribution Output Behaviors
Yong Zhang, Ping Zhou, Guimei Cui
2019, 6(6): 1506-1512. doi: 10.1109/JAS.2018.7511090
Abstract(945) HTML (502) PDF(37)
Burden distribution is one of the most important operations, and also an important upper regulation in blast furnace (BF) iron-making process. Burden distribution output behaviors (BDOB) at the throat of BF is a 3-dimensional spatial distribution produced by burden distribution matrix (BDM), including burden surface output shape (BSOS) and material layer initial thickness distribution (MLITD). Due to the lack of effective model to describe the complex input-output relations, BDM optimization and adjustment is carried out by experienced foremen. Focusing on this practical challenge, this work studies complex burden distribution input-output relations, and gives a description of expected MLITD under specific integral constraint on the basis of engineering practice. Furthermore, according to the decision variables in different number fields, this work studies optimization of BDM with expected MLITD, and proposes a multi-mode based particle swarm optimization (PSO) procedure for optimization of decision variables. Finally, experiments using industrial data show that the proposed model is effective, and optimized BDM calculated by this multi-model based PSO method can be used for expected distribution tracking.
A Novel Statistical Manifold Algorithm for Position Estimation
Bin Xia, Wenhao Yuan, Nan Xie, Caihong Li
2019, 6(6): 1513-1518. doi: 10.1109/JAS.2019.1911771
Abstract(1346) HTML (773) PDF(163)
In this paper, a novel statistical manifold algorithm is proposed for position estimation of sensor nodes in a wireless network, making full use of distance information available among unknown nodes and simultaneous localization of multiple unknown nodes. To begin, a ranging model including the distance information among unknown nodes is established. With the reparameterization of the natural parameter and natural statistic, the solution problem of the ranging model is transformed into a parameter estimation problem of the curved exponential family. Then, a natural gradient method is adopted to deal with the parameter estimation problem of the curved exponential family. To ensure the convergence of the proposed algorithm, a particle swarm optimization method is utilized to obtain initial values of the unknown nodes. Experimental results indicate that the proposed algorithm can improve the positioning accuracy, compared with the traditional algorithm.
Stability of Nonlinear Systems Using Optimal Fuzzy Controllers and Its Simulation by Java Programming
Mohammad Javad Mahmoodabadi, Saideh Arabani Mostaghim
2019, 6(6): 1519-1527. doi: 10.1109/JAS.2017.7510388
Abstract(969) HTML (578) PDF(48)
In this paper, at first, the single input rule modules (SIRMs) dynamically connected fuzzy inference model is used to stabilize a double inverted pendulum system. Then, a multi-objective particle swarm optimization (MOPSO) is implemented to optimize the fuzzy controller parameters in order to decrease the distance error of the cart and summation of the angle errors of the pendulums, simultaneously. The feasibility and efficiency of the proposed Pareto front is assessed in comparison with results reported in literature and obtained from other algorithms. Finally, the Java programming with applets is utilized to simulate the stability of the nonlinear system and explain the internet-based control.
A User Requirement Oriented Web Service Discovery Approach Based on Logic and Threshold Petri Net
Jing Sha, Yuyue Du, Liang Qi
2019, 6(6): 1528-1542. doi: 10.1109/JAS.2019.1911657
Abstract(1138) HTML (596) PDF(41)
In recent years, the number of Web services has increased significantly. Web service discovery has drawn much attention with the development of Web service applications and big data analysis. Under this circumstance, traditional Web service discovery strategies cannot adequately meet high user requirements due to the efficiency and precision of service discovery is low. In order to improve the accuracy and efficiency of service discovery, a user requirement oriented Web service discovery approach based on Petri nets is proposed in this study. A data preprocessing strategy of Web service is first designed. Then, a service clustering method is proposed based on Petri nets, which can conduct service cluster head generation, service cluster composition, and service discovery. The proposed method utilizes a superior data preprocessing method. Using simulation experiments, the efficiency and precision of Web service discovery are illustrated. Finally, the application value of the approach on real Web service is discussed.