Statistical Characteristics Research Articles

Deep Learning‐Based Variational Autoencoder for Classification of Quantum and Classical States of Light

AbstractAdvancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements requires efficient detectors and longer measurement times to obtain high‐quality photon statistics. Here, a deep learning‐based variational autoencoder (VAE) method is introduced for classifying single photon added coherent state (SPACS), single photon added thermal state (SPATS), and mixed states between coherent and SPACS as well as between thermal and SPATS of light. The semi‐supervised learning‐based VAE efficiently maps the photon statistics features of light to a lower dimension, enabling quasi‐instantaneous classification with low average photon counts. The proposed VAE method is robust and maintains classification accuracy in the presence of losses inherent in an experiment, such as finite collection efficiency, non‐unity quantum efficiency, finite number of detectors, etc. Additionally, leveraging the transfer learning capabilities of VAE enables successful classification of data of any quality using a single trained model. It is envisioned that such a deep learning methodology will enable better classification of quantum light and light sources even in poor detection.

On the Definition of Velocity in Discrete-Time, Stochastic Langevin Simulations

We systematically develop beneficial and practical velocity measures for accurate and efficient statistical simulations of the Langevin equation with direct applications to computational statistical mechanics and molecular dynamics sampling. Recognizing that the existing velocity measures for the most statistically accurate discrete-time Verlet-type algorithms are inconsistent with the simulated configurational coordinate, we seek to create and analyze new velocity companions that both improve existing methods as well as offer practical options for implementation in existing computer codes. The work is based on the set of GJ methods that, of all methods, for any time step within the stability criteria correctly reproduces the most basic statistical features of a Langevin system; namely correct Boltzmann distribution for harmonic potentials and correct transport in the form of drift and diffusion for linear potentials. Several new and improved velocities exhibiting correct drift are identified, and we expand on an earlier conclusion that, generally, only half-step velocities can exhibit correct, time-step independent Maxwell–Boltzmann distributions. Specific practical and efficient algorithms are given in familiar forms, and these are used to numerically validate the analytically derived expectations. One especially simple algorithm is highlighted, and the ability of one of the new on-site velocities to produce statistically correct averages for a particular damping value is specified.

Models and applications of stochastic programming with decision‐dependent uncertainty in power systems: A review

AbstractStochastic programming is a competitive tool in power system uncertainty management. Traditionally, stochastic programming assumes uncertainties to be exogenous and independent of decisions. However, there are situations where statistical features of uncertain parameters are not constant but dependent on decisions, classifying such uncertainties as decision‐dependent uncertainty (DDU). This is particularly the case with future power systems highly penetrated by multi‐source uncertainties, where planning or operation decisions might exert unneglectable impacts on uncertainty features. This paper reviews the stochastic programming with DDU, especially those applied in the field of power systems. Mathematical properties of diversified types of DDU in stochastic programming are introduced, and a comprehensive review on sources and applications of DDU in power systems is presented. Then, focusing on a specific type of DDU, that is, decision‐dependent probability distributions, a taxonomy of available modelling techniques and solution approaches for stochastic programming with this type of DDU and different structural features are presented and discussed. Eventually, the outlook of two‐stage stochastic programming with DDU for future power system uncertainty management is explored, including both exploring the applications and developing efficient modelling and solution tools.

An integrated three-stream network model for discriminating fish feeding intensity using multi-feature analysis and deep learning.

Feed costs constitute a significant part of the expenses in the aquaculture industry. However, feeding practices in fish farming often rely on the breeder's experience, leading to feed wastage and environmental pollution. To achieve precision in feeding, it is crucial to adjust the feed according to the fish's feeding state. Existing computer vision-based methods for assessing feeding intensity are limited by their dependence on a single spatial feature and manual threshold setting for determining feeding status constraints. These models lack practicality due to their specificity to certain scenarios and objectives. To address these limitations, we propose an integrated approach that combines computer vision technology with a Convolutional Neural Net-work (CNN) to assess the feeding intensity of farmed fish. Our method incorporates temporal, spatial, and data statistical features to provide a comprehensive evaluation of feeding intensity. Using computer vision techniques, we preprocessed feeding images of pearl gentian grouper, extracting temporal features through optical flow, spatial features via binarization, and statistical features using the gray-level co-occurrence matrix. These features are input into their respective specific feature discrimination networks, and the classification results of the three networks are fused to construct a three-stream network for feeding intensity discrimination. The results of our proposed three-stream network achieved an impressive accuracy of 99.3% in distinguishing feeding intensity. The model accurately categorizes feeding states into none, weak, and strong, providing a scientific basis for intelligent fish feeding in aquaculture. This advancement holds promise for promoting sustainable industry development by minimizing feed wastage and optimizing environmental impact.

Extreme learning machine based on BDE feature selection to detect fault scenarios in grid-connected PV systems under MPPT mode

This paper considers real-time data-driven adaptive fault detection (FD) in grid-connected PV (GPV) systems under maximum power point tracking (MPPT) modes during large variations. Faults under MPPT modes remain undetected for longer periods, introducing new protection challenges and threats to the system. An intelligent FD algorithm is developed through real-time multi-sensor measurements and virtual Micro Phasor Measurement Unit (Micro-PMU) estimations. The high-dimensional and high-frequency multivariate features vary over time, and computational efficiency becomes crucial to realizing online adaptive FD. The goal of this study is to present an artificial intelligence (AI) technique for detecting seven faults: inverter fault, feedback sensor fault, grid anomaly, nonhomogeneous partial shading, open circuit in PV array, MPPT controller fault, and boost converter controller fault. In this work, it was found that the application of Extreme Learning Machine (ELM) plays an important role in fault detection and localization. Nine (9) statistical features and eight (8) wavelet packet parameters are extracted from the data based on multiple default values. These features were used as an input vector to train and test the ELM and determine whether the system is operating under normal conditions or is faulty. The BDE feature selection algorithm is adopted to optimize the seven-fault classification procedure to reduce the number of features. The results showed that the Extreme Learning Machine (ELM), based on statistical parameters followed by BDE, can detect faults with high accuracy (98.3%) compared to a case without optimization.

Enhancing machine learning multi-class fault detection in electric motors through entropy-based analysis

Abstract In the field of electric motor maintenance, this study introduces a transformative approach by inte-grating entropy-based algorithms with machine learning for enhanced multi-class fault detection. Employing Shannon, Renyi, and Tsallis entropy algorithms on standard fault detection measure-ments, the research significantly advances predictive maintenance strategies through a robust, ear-ly-indication, system-agnostic analysis. Detailed examination is conducted, comparing results de-rived from datasets that include statistical features (excluding entropy) against the proposed entro-py-based datasets, when applied to a Multi-Layer Perceptron Classifier. Optimization of the MLPC and all compared algorithms’ hyperparameters is done using the state-of-the-art Optuna tool to dynamically explore each search space, ensuring that each methodology performs adequately in a timely fashion while allowing for adaptation. The results showcase significant enhancement in clas-sification accuracy of diverse electric motor operational states, facilitating the differentiation be-tween healthy and various levels of fault conditions under assorted load scenarios. Computational analyses reveal favorable results related to execution time and memory overhead, thereby support-ing the practicality in operations constrained by memory resources. Validation of the approach is achieved through laboratory experiments on a purpose-built test bench. Versatility of entropy-based measures through their proposed utilization in diverse fault indications is achieved by a demonstration in the field of mechanical fault detection with a focus on bearing faults through well-respected datasets.

Automation of vegetable production analysis in the Russian Federation using a modern information system

The presented study is aimed at solving the problems of information support for making effective management decisions in the field of vegetable growing in Russia based on the use of technologies and tools that automate complex algorithms of statistical analysis, which expands the range of users of up-to-date, reliable and complete information on the factors that shape the volumes and efficiency of production in the vegetable growing industries. The information system proposed by the authors, developed on the basis of the PyCharm2023.1 programming environment using the Python programming language, allows the user to obtain statistical characteristics of the phenomenon under study, apply methods of correlation and regression analysis, ANOVA to identify cause-and-effect relationships, modeling processes and phenomena in order to predict their development. The web application was developed taking into account officially published information on the conditions and results of vegetable production, and its operation has been tested. At the same time, the information system has the potential for development and can be adapted to any data set.

A New Scene Sensing Model Based on Multi-Source Data from Smartphones

Smartphones with integrated sensors play an important role in people’s lives, and in advanced multi-sensor fusion navigation systems, the use of individual sensor information is crucial. Because of the different environments, the weights of the sensors will be different, which will also affect the method and results of multi-source fusion positioning. Based on the multi-source data from smartphone sensors, this study explores five types of information—Global Navigation Satellite System (GNSS), Inertial Measurement Units (IMUs), cellular networks, optical sensors, and Wi-Fi sensors—characterizing the temporal, spatial, and mathematical statistical features of the data, and it constructs a multi-scale, multi-window, and context-connected scene sensing model to accurately detect the environmental scene in indoor, semi-indoor, outdoor, and semi-outdoor spaces, thus providing a good basis for multi-sensor positioning in a multi-sensor navigation system. Detecting environmental scenes provides an environmental positioning basis for multi-sensor fusion localization. This model is divided into four main parts: multi-sensor-based data mining, a multi-scale convolutional neural network (CNN), a bidirectional long short-term memory (BiLSTM) network combined with contextual information, and a meta-heuristic optimization algorithm.

Inertial Measurement Unit-Based Frozen Shoulder Identification from Daily Shoulder Tasks Using Machine Learning Approaches.

Frozen shoulder (FS) is a common shoulder condition accompanied by shoulder pain and a loss of shoulder range of motion (ROM). The typical clinical assessment tools such as questionnaires and ROM measurement are susceptible to subjectivity and individual bias. To provide an objective evaluation for clinical assessment, this study proposes an inertial measurement unit (IMU)-based identification system to automatically identify shoulder tasks whether performed by healthy subjects or FS patients. Two groups of features (time-domain statistical features and kinematic features), seven machine learning (ML) techniques, and two deep learning (DL) models are applied in the proposed identification system. For the experiments, 24 FS patients and 20 healthy subjects were recruited to perform five daily shoulder tasks with two IMUs attached to the arm and the wrist. The results demonstrate that the proposed system using deep learning presented the best identification performance using all features. The convolutional neural network achieved the best identification accuracy of 88.26%, and the multilayer perceptron obtained the best F1 score of 89.23%. Further analysis revealed that the identification performance based on wrist features had a higher accuracy compared to that based on arm features. The system's performance using time-domain statistical features has better discriminability in terms of identifying FS compared to using kinematic features. We demonstrate that the implementation of the IMU-based identification system using ML is feasible for FS assessment in clinical practice.

A Comparative Study of Measurement Systems Using Machine Learning Techniques for Tool Fault Di-agnosis During Metal Removal in the Milling Process

Despite significant advancements in both measurement systems and machine learning techniques, the integration of these technologies for real-time tool fault diagnosis in milling processes remains under developed. Existing studies tend to focus on a comprehensive comparative analysis that bridges these two areas machine learning algorithms or the application of specific measurement sys-tems. There is also a gap in evaluating the cost-effectiveness and practicality of different measurement systems when integrated with machine learning models for industrial applications. This study addresses these gaps by conducting a detailed comparative analysis of multiple measurement sys-tems and their performance with machine learning techniques in a real-world milling context, aim-ing to provide practical recommendations for industry adoption. Using both traditional and Artificial Intelligence (AI) to define and exploit sensory systems in the milling process, as well as various (direct and indirect) monitoring approaches, are summarised in this study. Machine learning tech-niques SVM, KNN, DT performs better and provide higher accuracy and in feature extraction clas-sification techniques statistical features, wavelet transform with the Holder Exponent (HE) having higher accuracy for diagnosing the tool faults.

Extropy and statistical features of dual generalized order statistics’ concomitants arising from the Sarmanov family

Abstract In this study, we disclose several statistical properties of concomitants of dual generalized order statistics (DGOSs) under a generic setting from the Sarmanov family of bivariate distributions. For this family, cross-moments and joint distributions of concomitants of DGOSs are explored. These results' implications for order statistics and record values are examined. Extropy and cumulative residual extropy (CRE), two well-known information measures, are also investigated. This study offers a few beautiful symmetrical relationships that these inaccuracy measurements satisfy. In addition, based on the concomitants of DGOSs, the issue of estimating the negative cumulative residual extropy (NCRE), empirical NCRE and NCE are investigated using the empirical technique. Lastly, a set of bivariate data from the real world is examined.

Enhancing the accuracy of blockage detection in centrifugal pump using the majority voting classifier on an unbalanced dataset

Blockage in a centrifugal pump can adversely impact its performance. In this study, an experimental facility is developed to simulate three types of blockages (suction, discharge, and simultaneous suction and discharge). To classify these faults and detect their severity, a methodology involving the application of majority voting classifier (MVC) to the pump’s discharge pressure signals is presented. An unbalanced dataset is constructed, where the number of samples for a specific blockage condition decreases with increasing fault severity. Statistical features, entropy features, and entropies meta features are extracted from the signal and ranked using XGBoost and minimum redundancy maximum relevance (MRMR). Subsequently, the optimal features are selected based on the best performing model (Linear Discriminant Analysis) among ten different models. Best four models are selected and ensembled to form MVC. Results show that MVC achieves an accuracy of 89.90% and 88.26% for features selected by XGBoost and MRMR, respectively. Finally, the unbalanced dataset is balanced using synthetic minority oversampling and it is shown that MVC achieves an accuracy of 100% on this balanced dataset for the features selected using both approaches.

On the linear response theory of vortex meandering and its statistical verification in experiments

Meandering designates the main manifestation of unsteady vortex dynamics observed in experiments. This study has the twofold objective to (i) develop a theoretical model describing vortex meandering and (ii) conduct a quantitative and objective evaluation of the model against experimental data. Based on an analogy with Brownian motion, we derive the theoretical model in the framework of linear response theory. Taking the form of a Langevin equation, our model explains meandering as the competition between external excitation by free-stream perturbations, counteracted by stabilising intrinsic vortex dynamics. As such, it contains the previous approaches to explaining the phenomenon as limiting cases, and clearly highlights their shortcomings. The statistical identification of characteristic regularities in experimental data as well as the assessment of their consistency with theoretical models are important problems in physics. For samples obtained from finite-length records of correlated data, these statistical characteristics are not unique and may show spurious behaviour merely induced by the finiteness of the sample. Statistical inference provides a systematic and quantitative methodology to objectively assess the reproducibility of statistical characteristics and to evaluate their consistency with theoretical models. Their systematic application to the analysis of vortex meandering has not been done before and provides statistical evidence for our proposed Brownian-motion-like model. That is, experimental vortex meandering constitutes the manifestation of a stationary Gauss–Markov random process, which implies that the dynamics admits an ergodic probability measure.

GeoGail: A Model-based Imitation Learning Framework for Human Trajectory Synthesizing

Synthesized human trajectories are crucial for a large number of applications. Existing solutions are mainly based on the generative adversarial network (GAN), which is limited due to the lack of modeling the human decision-making process. In this paper, we propose a novel imitation learning based method to synthesize human trajectories. This model utilizes a novel semantics-based interaction mechanism between the decision-making strategy and visitations to diverse geographical locations to model them in the semantic domain in a uniform manner. To augment the modeling ability to the real-world human decision-making policy, we propose a feature extraction model to extract the internal latent factors of variation of different individuals, and then propose a novel self-attention based policy net to capture the long-term correlation of mobility and decision-making patterns. Then, to better reward users’ mobility behavior, we propose a novel multi-scale reward net combined with mutual information to model the instant reward, long-term reward, and individual characteristics in a cohesive manner. Extensive experimental results on two real-world trajectory datasets show that our proposed model can synthesize the most high-quality trajectory data compared with six state-of-the-art baselines in terms of a number of key usability metrics, and can well support practical applications based on trajectory data, demonstrating its effectiveness. Furthermore, our proposed method can learn explainable knowledge automatically from data, including explainable statistical features of trajectories and statistical relation between decision-making policy and features.

Staged suppression of main-lobe compound jamming using airborne distributed arrays

For the compound jamming scenario where noise suppression jamming and interrupted sampling repeater jamming simultaneously exist, we propose a method of staged suppression of them using distributed arrays. The basic principle is using the generalized inner product for the selection of non-uniform samples. By using the generalized inner product quadratically for the staged selection of the samples, we can obtain the statistical feature estimates of the noise suppression jamming and the interrupted sampling repeater jamming, respectively, and then complete the robust suppression of the compounded jamming using the distributed array spatial domain adaptive processing. With typical configuration of parameters, we validate and analyze the effectiveness and performance of the proposed method through numerical simulation experiments.

Construction of virtual test scenarios for intelligent car-pedestrian interaction

Aiming at the needs of intelligent car and pedestrian interaction testing under urban conditions, this paper proposes a scenario generation method that comprehensively considers the frequency of scenarios in the real world and the degree of challenge to human-vehicle interaction performance. First, according to the key features of intelligent car and pedestrian interaction, the original scene data of pedestrians crossing the road is extracted from the natural driving dataset; then, according to the needs of accelerated testing, a key scenario extraction method based on importance sampling theory is designed to extract and construct important scenarios for intelligent car-pedestrian interaction testing from the original scenes; finally, by comparing the data distribution of important scenarios with original scenarios, it is shown that this method can effectively screen out scenarios that may challenge safety performance during driving, thereby realizing accelerated testing, while taking into account the statistical characteristics of the test scenarios.

Distributed Consensus Filtering Over Sensor Networks With Asynchronous Measurements

ABSTRACTIn practical sensor networks, sensor nodes may operate with different sampling periods and initial sampling time instants, and their observations may also be nonuniform. Unfortunately, the research on distributed state estimation problems over such asynchronous sensor networks is very limited. Thus, this article focuses on the distributed consensus filtering problem over sensor networks with asynchronous measurements. First, the asynchronous measurement from each sensor is synchronized by the continuous‐time state evolution equation to a unified filtering fusion time instant within a given filtering period. After measurement synchronization, the statistical characteristics of measurement noise change. The cross‐correlations between the converted measurement noises are analyzed, as well as one‐step correlations between the converted measurement noises and the process noise. Second, an optimal asynchronous distributed consensus filter is designed based on synchronization measurements under the criterion of minimum mean‐square error with the above correlations between various types of noises taken into account. Meanwhile, a suboptimal distributed consensus filtering algorithm is further proposed to reduce computational complexity. Finally, based on the Lyapunov function method, the stability of the estimation error is theoretically demonstrated with an appropriate selection of consensus filtering gain and validated through simulations.

Statistical Characteristics of Snowfall on the Tibetan Plateau Affected by TCs Over the Bay of Bengal: An Observational Analysis

ABSTRACTIn this study, the characteristics of tropical cyclones (TCs) over the Bay of Bengal (BoB) that affect snowfall on the Tibetan Plateau (TP) and spatiotemporal distribution of snowfall related to BoB TCs are statistically analysed by using multi‐sources data from 1981 to 2020, with partitioning TC‐influenced snowfall by tracking cloud clusters. The results show that 141 TCs formed during the 40‐year period of 1981–2020, of which about 35% (50 TCs) impacted snowfall at 83% of meteorological stations on the TP during their northward or westward movement, and the average distance between the TC centre and the snowfall stations is 1277 km. The proportion of snowfall‐related TC frequency shows a significantly decreasing trend with a predominant cycle of 10a. The TC‐influenced snowfall frequency (SF), precipitation amount (PA) on a snowfall day and snow depth (SD) during 1981–2020 all show a non‐significant weak decreasing trend, while TC‐influenced snowfall is significantly increased in the eastern and southern edges of Xizang, western Sichuan and the southern margin of Qinghai. PA and SD in December account for more than 75% and 55% of the monthly total, respectively. The spatial pattern of PA could be objectively categorised into west‐type (24%) and southeast‐type (76%). The moisture transported by the BoB TC and a southerly jet stream formed between the trough and the western Pacific subtropical high (WPSH), the convergence of cold air and warm–moist airstream over the TP and the change in position of the south Asian high in the upper troposphere are significant factors causing the different spatial distribution. The results can provide reference for TC‐related snowfall, SD prediction and disaster assessment on the TP.

Bivariate BMM-based hybrid domain image watermark detector

Robustness, imperceptibility, and watermark capacity are three indispensable and contradictory properties for any image watermarking systems. It is a challenging work to achieve the balance among the three important properties. In this paper, by using the bivariate Beta mixture model (Bivariate BMM), we present a statistical image watermark scheme in nonsubsampled Contourlet transform (NSCT)-fractional order Jacobi Fourier moments (FJFMs) amplitude hybrid domain. The whole watermarking algorithm includes two parts: watermark embedding and detection. NSCT is firstly performed on host image to obtain the frequency subbands, and the NSCT subbands are divided into non overlapping blocks. Then, the significant NSCT domain blocks are selected using local binary patterns (LBP). Meanwhile, for each selected NSCT coefficient block, FJFMs are calculated to obtain the NSCT-FJFMs amplitude. Finally, watermark signals are inserted into the amplitude hybrid domain of NSCT-FJFMs. In order to detect accurately watermark signal, the statistical characteristics of NSCT-FJFMs magnitudes are analyzed in detail. Then, NSCT-FJFMs magnitudes are described statistically by Bivariate BMM, which can simultaneously capture the marginal distribution and strong dependencies of NSCT-FJFMs magnitudes. Also, Bivariate BMM parameters are estimated accurately by the rough-enhanced-Bayes mixture estimation & expectation–maximization (REBMIX&EM) approach. Finally, a statistical watermark detector based on the locally optimum (LO) decision rule and Bivariate BMM is developed in NSCT-FJFMs magnitude hybrid domain. Also, the closed-form expressions on the LO statistic is derived and the receiver operating characteristic (ROC) about our detector is analyzed. Extensive experimental results show the superiority of the proposed image watermark detector over some state-of-the-art statistical watermarking methods.

Feature selection based on game theory optimization to achieve desired performance metrics in seizure onset detection

Background and Objective: Epilepsy is one of the common diseases of the nervous system, which affects almost 1% of the world’s population. The unpredictable nature of epileptic seizures has caused people suffering from it to be deprived of their normal life, and making a device that can detect a seizure onset can help them. Methods:Game theory is a branch of mathematical science that, after proving its ability in economics, has entered into the field of signal processing and is trying to solve complex problems with a new approach. In this paper, we use game theory and coalitional game concepts to provide a novel way of feature selection in the analysis of Electroencephalography (EEG) signals. We have used a variety of statistical, morphological, and frequency features, and with the proposed feature selection algorithm we have attempted to select the smallest coalition which discriminates between two brain states while appropriately allocating resources to satisfy our desired sensitivity, delay, and false alarm. A modified change point detection algorithm has also been introduced to be used to detect epileptic seizures. Results:The results of the test on the CHB-MIT dataset show that using the proposed algorithm, we can achieve improved performance in terms of sensitivity, delay, and false alarm with a few number of features. Our framework also provides a means to focus on desired criteria for different applications. In scenario which the focus was on sensitivity, the proposed framework achieved 99% average sensitivity, 0.4/h average false alarm, and 2.4 s average delay with only using about 2 features for each patient. Conclusion:By applying the proposed framework on the CHB-MIT dataset we observe that we can achieve better performance compared to recent studies with fewer features in terms of sensitivity, delay, and false alarm metrics. Such an algorithm can be used for the purpose of real-time detection and in wearable devices.