Minimum Description Length Criterion Research Articles

Change point detection in INAR(p) models via likelihood ratio scanning method

In this paper, we consider an integer-valued autoregressive (INAR) model. Based on the likelihood ratio scanning method (LRSM), the numbers and locations of the piecewise stationary INAR process change points are discussed. The minimum description length (MDL) function of the INAR model is given. Moreover, we also study the case when the sum of coefficients in each segment of the model tends to 1 and make adjustments to the MDL criterion in the LRSM. In this way, the accuracy of change point detection is improved. In the end, simulation experiments and real data analysis are conducted to illustrate the efficiency of the LRSM.

Linking Frequentist and Bayesian Change-Point Methods

We show that the two-stage minimum description length (MDL) criterion widely used to estimate linear change-point (CP) models corresponds to the marginal likelihood of a Bayesian model with a specific class of prior distributions. This allows results from the frequentist and Bayesian paradigms to be bridged together. Thanks to this link, one can rely on the consistency of the number and locations of the estimated CPs and the computational efficiency of frequentist methods, and obtain a probability of observing a CP at a given time, compute model posterior probabilities, and select or combine CP methods via Bayesian posteriors. Furthermore, we adapt several CP methods to take advantage of the MDL probabilistic representation. Based on simulated data, we show that the adapted CP methods can improve structural break detection compared to state-of-the-art approaches. Finally, we empirically illustrate the usefulness of combining CP detection methods when dealing with long time series and forecasting.

A novel ship trajectory clustering analysis and anomaly detection method based on AIS data

The increasing volume of ship traffic has resulted in new challenges for the supervision of maritime safety administration. The conventional manual monitoring approach for maritime traffic is inefficient and lacks specifics, particularly for supervising ships with abnormal trajectories. To address this issue, this study proposes utilizing the minimum description length criterion to extract features from ship trajectory data provided by the automatic identification system (AIS). This approach simplifies the compression of ship trajectories. Additionally, the dynamic time warping trajectory similarity measurement algorithm is employed to optimize the density-based spatial clustering of applications with noise algorithm. This optimization enables the clustering of ship trajectories and the acquisition of normalized ship motion trajectories. Furthermore, a ship trajectory prediction method based on a transformer model is proposed, and the normalized motion trajectory is used as the training set for model training. The trained ship trajectory prediction model is subsequently utilized to predict the target ship trajectory. The AIS ship trajectory data in the vicinity of Yantai Port were used for experimental verification. The results demonstrate the effectiveness of the proposed approach in identifying abnormal ship trajectories.

Application of Wavelet Packet and S Transforms for Differential Protection of Power Transformer

The differential protection of power transformers appears to be more difficult than any type of protection for any other part or element in a power system. Such difficulties arise from the existence of the magnetizing inrush phenomenon. Therefore, it is necessary to recognize between inrush current and the current arise from internal faults. In this paper, two approaches based on wavelet packet transform (WPT) and S-transform (ST) are applied to recognize different types of currents following in the transformer. In WPT approach, the selection of optimal mother wavelet and the optimal number of resolution is carried out using minimum description length (MDL) criteria before taking the decision for the extraction features from the WPT tree. In ST approach,the spectral energy index and the standard deviation (STD) are calculated from the S-matrix obtained by discrete S-transform. The two approaches are tested for generating a trip signal and disconnecting the transformer supply experimentally using 1KVA, 220/110V, 50Hz, ∆ / Y threephase transformer. The experimental results show that the trip signal is initiated faster in WPT approach while the transformer is disconnected from the supply after a delay of 10-15msec in thetwo approaches due to computer interface and the relay circuit used.

A syntactic method for robot imitation learning of complex sequence task

PurposeAiming at the problems of weak generalization of robot imitation learning methods and higher accuracy requirements of low-level detectors, this study aims to propose an imitation learning method based on structural grammar.Design/methodology/approachThe paper proposes a hybrid training model based on artificial immune algorithm and the Baum–Welch algorithm to extract the action information of the demonstration activity to form the {action-object} sequence and extract the symbol description of the scene to form the symbol primitives sequence. Then, probabilistic context-free grammar is used to characterize and manipulate these sequences to form a grammar space. Minimum description length criteria are used to evaluate the quality of the grammar in the grammar space, and the improved beam search algorithm is used to find the optimal grammar.FindingsIt is found that the obtained general structure can parse the symbol primitive sequence containing noise and obtain the correct sequence, thereby guiding the robot to perform more complex and higher-order demonstration tasks.Practical implicationsUsing this strategy, the robot completes the fourth-order Hanoi tower task has been verified.Originality/valueAn imitation learning method for robots based on structural grammar is first proposed. The experimental results show that the method has strong generalization ability and good anti-interference performance.

Localization of mixed coherently and incoherently distributed sources based on generalized array manifold

In practice, signals received by an array may be a mixture of coherently distributed (CD) and incoherently distributed (ID) sources, due to some complicated multipath/scattering effects. To localize mixed CD and ID sources, a method based on the generalized array manifold (GAM) is developed in this work. Firstly, source enumeration and source type classification are achieved by jointly employing the minimum description length (MDL) criterion, the covariance matrix difference technique and the second-order statistics of associated eigenvalues. Secondly, with the source enumeration result, the nominal direction of arrival (DOA) of ID sources is estimated by the rank-reduction principle based one-dimensional (1-D) spectral search, where shift invariance of the GAM associated with ID sources is considered. Thirdly, the oblique projection technique is adopted to separate the CD sources from ID ones, and then the nominal DOA of CD sources is estimated via the sparsity-cognizant total least-squares (S-TLS) method. Finally, with aid of the nominal DOA estimates, the corresponding angular spreads are calculated. An analysis of the proposed method is discussed and the approximate Cramér-Rao bound (CRB) is derived. Simulations are provided to demonstrate the performance of the proposed method.

Scalable and Fast Algorithm for Constructing Phylogenetic Trees With Application to IoT Malware Clustering

With the development of IoT devices, there is a rapid increase in new types of IoT malware and variants, causing social problems. The malware’s phylogenetic tree has been used in many studies for malware clustering or better understanding of malware evolution. However, when dealing with a large-scale malware set, conventional methods for constructing a phylogenetic tree is very time-consuming or even cannot be done in a realistic time. To solve this problem, we propose a high-speed, scalable phylogenetic tree construction algorithm with a clustering algorithm to cluster it. The proposed method involves the following steps: (1) Calculating the similarity of the specimen pairs using the normalized compression distance. (2) Creating a phylogenetic tree containing all specimens, instead of calculating the similarity of all pairs of a specimen, our algorithm only calculates a small part of the similarity matrix. (3) Dividing the phylogenetic tree into clusters by applying the minimum description length criterion. In addition, we propose a new online processing algorithm to add new malware specimens into the existing phylogenetic tree sequentially. Our goal is to reduce the computational cost of constructing the phylogenetic tree and improve the clustering accuracy of our previous research. We evaluated our method’s clustering accuracy and scalability with 65,494 IoT malware specimens. The results showed that our algorithm reduced the computation by 97.52% compared with the conventional method. Our clustering algorithm achieved accuracies of 95.5% and 99.3% for clustering family name and architecture name, respectively.

Nonlinear Model Order Selection: A GMM Clustering Approach Based on a Genetic Version of EM Algorithm

Choosing an accurate model order is one of the important sections in system identification. Traditionally, the model order selection of a nonlinear system depends on a predetermined model. However, it requires excess calculation and is impossible to get rid of the trouble of the structural design of the model, once the specific model was determined. A false nearest neighbor (FNN) algorithm that only relies on input-output data to estimate the model order is proposed here. Due to the FNN algorithm is sensitive to its own threshold which is a crucial constant for evaluating the model structure, Gaussian mixture model (GMM) clustering based on a genetic version of the expectation-maximization (EM) algorithm and minimum description length (MDL) criterion is developed in this paper, where the order can be determined without relying on a specific model. The GMM clustering is proposed to calculate the threshold of the FNN. Then, the genetic algorithm and MDL criteria are embedded to optimize the calculation of the EM algorithm as reduce the influence of initial values and not prone to fall into local extreme values as well. Three examples are given here to indicate the superiority of this technique: simulation of a strongly nonlinear system, isothermal polymerization process, and Van der Vusse reaction in relevant reference. Finally, some typical modeling methods are conducted to confirm the validity of this approach.

Application of minimum description length criterion to assess the complexity of models in mathematical immunology

AbstractMathematical models in immunology differ enormously in the dimensionality of the state space, the number of parameters and the parameterizations used to describe the immune processes. The ongoing diversification of the models needs to be complemented by rigorous ways to evaluate their complexity and select the parsimonious ones in relation to the data available/used for their calibration. A broadly applied metrics for ranking the models in mathematical immunology with respect to their complexity/parsimony is provided by the Akaike information criterion. In the present study, a computational framework is elaborated to characterize the complexity of mathematical models in immunology using a more general approach, namely, the Minimum Description Length criterion. It balances the model goodness-of-fit with the dimensionality and geometrical complexity of the model. Four representative models of the immune response to acute viral infection formulated with either ordinary or delay differential equations are studied. Essential numerical details enabling the assessment and ranking of the viral infection models include: (1) the optimization of the likelihood function, (2) the computation of the model sensitivity functions, (3) the evaluation of the Fisher information matrix and (4) the estimation of multidimensional integrals over the model parameter space.

Robust subgroup discovery

We introduce the problem of robust subgroup discovery, i.e., finding a set of interpretable descriptions of subsets that 1) stand out with respect to one or more target attributes, 2) are statistically robust, and 3) non-redundant. Many attempts have been made to mine either locally robust subgroups or to tackle the pattern explosion, but we are the first to address both challenges at the same time from a global modelling perspective. First, we formulate the broad model class of subgroup lists, i.e., ordered sets of subgroups, for univariate and multivariate targets that can consist of nominal or numeric variables, including traditional top-1 subgroup discovery in its definition. This novel model class allows us to formalise the problem of optimal robust subgroup discovery using the Minimum Description Length (MDL) principle, where we resort to optimal Normalised Maximum Likelihood and Bayesian encodings for nominal and numeric targets, respectively. Second, finding optimal subgroup lists is NP-hard. Therefore, we propose SSD++, a greedy heuristic that finds good subgroup lists and guarantees that the most significant subgroup found according to the MDL criterion is added in each iteration. In fact, the greedy gain is shown to be equivalent to a Bayesian one-sample proportion, multinomial, or t-test between the subgroup and dataset marginal target distributions plus a multiple hypothesis testing penalty. Furthermore, we empirically show on 54 datasets that SSD++ outperforms previous subgroup discovery methods in terms of quality, generalisation on unseen data, and subgroup list size.

Gaussian mixture modelling by exploiting competitive stop EM algorithm

To improve the robustness of order selection and parameter learning for Gaussian mixture model (GMM), this paper proposes a competitive stop expectation-maximization (EM) algorithm, which is based on two stop conditions. The first condition is a Lilliefors test based multivariate (MV) normality criterion, which is used to determine whether to split a component into two different components. The EM algorithm stops splitting when all components have MV normality. The minimum description length (MDL) criterion is used in the second condition, which competes with the first condition to prevent the EM algorithm from over-splitting. Simulation experiments verify the effectiveness of the proposed algorithm.

Gerschgorin disk estimator method for source number estimation based on peak-to-average power ratio

Gerschgorin disk estimator (GDE) method is difficult to detect the number of signal sources effectively under low signal-to-noise ratio (SNR). In view of this situation, we propose GDE method based on peak-to-average power ratio (GDE-PAR) by combining the peak-to-average power ratio (PAR) with the Gerschgorin disk radius. We extract the eigenvectors from the received data and use them as the weights of the data. The PAR is used to modify the corresponding Gerschgorin disk radius, and the number of signal sources is determined by GDE method. This paper adopts Matlab simulation on the Gerschgorin disk radius before and after correction under different SNR conditions. In the case of double target of equal intensity and double target of unequal intensity, three target of equal intensity and three target unequal intensity using Monte Carlo method, we use Akaike information theory criterion (AIC), minimum description length (MDL) criterion, PAR method and GDE-PAR method to estimate the number of signal sources respectively. The results show that under the conditions of low SNR and multi-target of unequal intensity, the probability of successful detection of source by GDE-PAR method is higher than that of AIC, MDL criterion and PAR method.

Resolution Enhancement of Spatial Parametric Methods via Regularization

The spatial spectral estimation problem has applications in a variety of fields, including radar, telecommunications, and biomedical engineering. Among the different approaches for estimating the spatial spectral pattern, there are several parametric methods, as the well-known multiple signal classification (MUSIC). Parametric methods like MUSIC are reduced to the problem of selecting an integer-valued parameter [so-called model order (MO)], which describes the number of signals impinging on the sensors array. Commonly, the best MO corresponds to the actual number of targets, nonetheless, relatively large model orders also retrieve good-fitted responses when the data generating mechanism is more complex than the models used to fit it. Most commonly employed MO selection (MOS) tools are based on information theoretic criteria (e.g., Akaike information criterion, minimum description length and efficient detection criterion). Normally, the implementation of these tools involves the eigenvalues decomposition of the data covariance matrix. A major drawback of such parametric methods (together with certain MOS tool) is the drastic accuracy decrease in adverse scenarios, particularly, with low signal-to-noise ratio, since the separation of the signal and noise subspaces becomes more difficult to achieve. Consequently, with the aim of refining the responses attained by parametric techniques like MUSIC, this article suggests utilizing regularization as a postprocessing step. Furthermore, as an alternative, this article also explores the possibility of selecting a single relatively large MO (rather than using MOS tools) and enhancing via regularization, the solutions retrieved by the treated parametric methods. In order to demonstrate the capabilities of this novel strategy, synthetic aperture radar tomography is considered as application.

Well logs reconstruction by DCT based IPRM and genetic algorithm

Hydrocarbon production from a particular layer requires careful identification of the stratigraphic boundaries and choosing the right perforation against the face of oil-bearing intervals.Excessive perforations may cause unwanted water production from adjacent layers. Nowadays, clustering of well log data through various methods such as self-organized maps (SOM) helps to find hydrocarbon intervals from other layers. SOM is a type of artificial neural network, which uses the non-monitored learning of the multi-dimensional logging observations to create a 2D clustering map. However, the noisy response data greatly reduces accuracy of the methods by increasing correlation of different data groups. Although spectral such as discrete wavelet transform (DWT) can reduce correlation and reconstruct the logs that no longer fluctuate as before, they have two major limitations. First, responses smooth the edge-shape behaviors in the log curve while preserving them is essential for recognizing the stratification changes. The second limitation is the generation of spurious oscillations in the reconstructed signals at the vicinity of the edges, known as the Gibbs phenomena. At the present study to overcome these problems, we use, for the first time, the inverse polynomial reconstruction method (IPRM) based on discrete cosine transform (DCT) to attenuate the random noise by projecting the data first on the orthogonal bases derived from Gegenbauer polynomials and then on cosine space. The de-noising level depends on the minimum description length (MDL) criterion that minimizes the distance of all the corresponding coefficients between the original and reconstructed signals during 100 iterations. However, in the proposed method, we use a genetic algorithm to decide quickly and optimally the coefficients of DCT and Gegenbauer required in real data reconstruction related to one of the oil fields in southwestern Iran. The results show that this preprocessing procedure compared to DCT and DWT, increases the success rate of the SOM method for oil-bearing zone detection based on evidence such as core drilling and perforation data. At the same time, the computational time is much shorter than the usual IPRM. The optimal perforation subsequent to this study may cut unwanted water production from adjacent layers. Such water with radioactive nature, in addition to causing environmental problems, greatly increases the cost of extraction operations due to the need to install surface-separating equipment.

Linear-shrinkage-based DOA estimation for coherently distributed sources considering mutual coupling in massive MIMO systems

In this paper, an approach of robust direction-of-arrival (DOA) estimation for coherently distributed (CD) sources considering the influence of array mutual coupling is proposed in a large-scale/massive multiple-input–multiple-output (MIMO) system. By exploiting the special structure of coupling matrix, the proposed approach first eliminates its influence through the inherent mechanism. Considering the realistic scenario that the number of available samples is of the same order of magnitude than the number of sensors in massive MIMO systems, the approach then improves the estimation of the sample covariance matrix (SCM) via the linear shrinkage operation, which is known as an efficient strategy to enhance the estimation of SCM in large-scale uniform linear arrays. Finally, according to the linear shrinkage based minimum description length (LS-MDL) criterion and the improved SCM, DOAs are obtained in closed-form expressions. Numerical results are included for illustrating the effectiveness of the proposed approach.

Adaptive DOA estimation with low complexity for wideband signals of massive MIMO systems

For massive multiple-input multiple-output (MIMO) communication systems, it is a major challenge to develop direction-of-arrival (DOA) estimation algorithm with low complexity and high accuracy for wideband signals. We propose a low-complexity adaptive multistage Wiener filter (MSWF)-based two-sided correlation transformation (AM-TCT) algorithm for wideband DOA estimation of two-dimensional (2D) massive MIMO systems. Unlike conventional TCT algorithms, the proposed AM-TCT algorithm uses the signal subspace that is obtained by forward recursion of the MSWF to construct the focusing matrix, which can reduce the computational complexity. To further reduce the computational complexity, the eigenvalue decomposition (EVD) of the covariance matrix is also replaced by the MSWF. Furthermore, to improve the precision, the Minimum Description Length (MDL) criterion uses the stage of MSWF to adaptively select the appropriate dimension of the noise subspace, and the backward recursion of the MSWF is employed to accurately estimate the noise subspace. Theoretical analysis demonstrates the complexity superiority of the proposed AM-TCT algorithm. Simulation results indicate that the proposed AM-TCT algorithm can effectively estimate the angle of wideband sources in massive MIMO systems and outperform some existing methods.

Coherent Noise Suppression Using Adaptive Homomorphic Filtering for Wideband Electromagnetic Imaging System.

The wideband electromagnetic imaging system using a parabolic reflector is a device for detecting and locating electromagnetic interference sources (EMIS). When multiple coherent interference sources are detected, the confusion will occur due to the coherent noise that is caused by interference phenomenons. Previous works have removed the coherent noise by using iterative techniques, but they face a limitation in removing noise in that the coherent noise pattern changes with frequency in a wideband. In this paper, an adaptive homomorphic filtering is proposed to overcome the limitations of conventional methods from 1 GHz–6 GHz. The coherent noise existing in the several electromagnetic images is studied, and it is confirmed that the variation of the coherent noise pattern is related to the position, the number, and the frequency of EMIS. Then, by analyzing the probability density of coherent noise intensity, an adaptive Gaussian filter is carefully designed to remove coherent noise. The filter parameters are selected by the minimum description length criterion (MDL) to apply to compute directly the local amount of Gaussian smoothing at each pixel of each image. The results of the experiments and simulations demonstrate that the proposed method can significantly improve the quality of electromagnetic images in terms of maximum sidelobe level (MSL) by 15 dB and dynamic range (DR) of the system over 20 dB, compared with conventional narrowband denoising methods.

An Improved Denoising Method for Partial Discharge Signals Contaminated by White Noise Based on Adaptive Short-Time Singular Value Decomposition

To extract partial discharge (PD) signals from white noise efficiently, this paper proposes a denoising method for PD signals, named adaptive short-time singular value decomposition (ASTSVD). First, a sliding window was moved along the time axis of a PD signal to cut a whole signal into segments with overlaps. The singular value decomposition (SVD) method was then applied to each segment to obtain its singular value sequence. The minimum description length (MDL) criterion was used to determine the number of effective singular values automatically. Then, the selected singular values of each signal segment were used to reconstruct the noise-free signal segment, from which the denoised PD signal was obtained. To evaluate ASTSVD, we applied ASTSVD and two other methods on simulated, laboratory-measured, and field-detected noisy PD signals, respectively. Compared to the other two methods, the denoised PD signals of ASTSVD contain less residual noise and exhibit smaller waveform distortion.

Two‐dimensional DOA estimation for multi‐path environments by accurate separation of signals using k ‐medoids clustering

The authors propose a two-dimensional direction-of-arrival (DOA) estimation for multi-path environments, in which there are uncorrelated, partially correlated and coherent signals. The inability to identify non-coherent signals from coherent ones results in a considerable waste of sensors. In this work, an adaptive and automated threshold is considered for the efficient separation of noise, non-coherent signals, and coherent groups. First, non-coherent signals, coherent groups, and noise subspace are separated using k-medoids clustering. After determining the number of sources, non-coherent signals and coherent groups, non-coherent DOAs are estimated separately. The number of coherent signals in each coherence group is determined by the minimum descriptive length criterion. Finally, coherent DOAs are estimated in each group by constructing a coherent estimation matrix. The proposed method does not require any prior information such as knowing the number of signals or the covariance matrix of uncorrelated signals. The simulation results show that the proposed method is able to distinguish between the non-coherent and coherent signals, even at low signal-to-noise ratios and a small number of snapshots. Also, in terms of detection probability and estimation accuracy, it shows an improvement of over 1.2 and 83%, respectively, compared with the conventional forward−backward spatial smoothing scheme.

CULTURAL HERITAGE MONITORING BY LOW-COST GNSS RECEIVERS: A FEASIBILITY STUDY FOR SAN GAUDENZIO’S CUPOLA, NOVARA

Abstract. In this study the cupola of San Gaudenzio’s Basilica in Novara, Italy, has been monitored by using two low-cost GNSS receivers located on the East and West side of the spire. Time series of daily solutions for an observation period of about one year have been collected and interpolated by cubic splines. The minimum description length criterion has been used to optimize this interpolation. The results show that the building had an uplift with a maximum amplitude of about 2 cm during summer. Moreover, from a joint analysis of the two points, one can realize that the uplift is not homogeneous, but the structure made some oscillations (with an amplitude at most of 4 mm) when rising up. As for the planimetric coordinates, the two antennas had a slightly different behaviour. The West point showed displacements at most of 1 cm and solutions with a very high repeatability of the order of few millimeters. The East point had a similar repeatability until a sudden jump occurred, followed by more noisy solutions in all the three directions. This noise degradation slowly dampened, till almost disappearing at the end of the recorded time series. This anomalous behaviour could be attributed to some structural movements. The test was successful in the sense that (1) it was proved that the millimeter accuracy can be reached by using GNSS low-cost receivers installed at San Gaudenzio’s cupola, even with a non-perfect sky visibility; (2) such an accuracy is able to show interesting movements of the cupola that can provide information about its stability.