Parameter Analysis of Multiscale Two-Dimensional Fuzzy and Dispersion Entropy Measures Using Machine Learning Classification

Two-dimensional fuzzy entropy, dispersion entropy, and their multiscale extensions (MFuzzyEn2D and MDispEn2D, respectively) have shown promising results for image classifications. However, these results rely on the selection of key parameters that may largely influence the entropy values obtained. Yet, the optimal choice for these parameters has not been studied thoroughly. We propose a study on the impact of these parameters in image classification. For this purpose, the entropy-based algorithms are applied to a variety of images from different datasets, each containing multiple image classes. Several parameter combinations are used to obtain the entropy values. These entropy values are then applied to a range of machine learning classifiers and the algorithm parameters are analyzed based on the classification results. By using specific parameters, we show that both MFuzzyEn2D and MDispEn2D approach state-of-the-art in terms of image classification for multiple image types. They lead to an average maximum accuracy of more than 95% for all the datasets tested. Moreover, MFuzzyEn2D results in a better classification performance than that extracted by MDispEn2D as a majority. Furthermore, the choice of classifier does not have a significant impact on the classification of the extracted features by both entropy algorithms. The results open new perspectives for these entropy-based measures in textural analysis.     

Interventional Fairness with Indirect Knowledge of Unobserved Protected Attributes

The deployment of machine learning (ML) systems in applications with societal impact has motivated the study of fairness for marginalized groups. Often, the protected attribute is absent from the training dataset for legal reasons. However, datasets still contain proxy attributes that capture protected information and can inject unfairness in the ML model. Some deployed systems allow auditors, decision makers, or affected users to report issues or seek recourse by flagging individual samples. In this work, we examine such systems and consider a feedback-based framework where the protected attribute is unavailable and the flagged samples are indirect knowledge. The reported samples are used as guidance to identify the proxy attributes that are causally dependent on the (unknown) protected attribute. We work under the causal interventional fairness paradigm. Without requiring the underlying structural causal model a priori, we propose an approach that performs conditional independence tests on observed data to identify such proxy attributes. We theoretically prove the optimality of our algorithm, bound its complexity, and complement it with an empirical evaluation demonstrating its efficacy on various real-world and synthetic datasets.     

Statistics-Based Outlier Detection and Correction Method for Amazon Customer Reviews

People nowadays use the internet to project their assessments, impressions, ideas, and observations about various subjects or products on numerous social networking sites. These sites serve as a great source to gather data for data analytics, sentiment analysis, natural language processing, etc. Conventionally, the true sentiment of a customer review matches its corresponding star rating. There are exceptions when the star rating of a review is opposite to its true nature. These are labeled as the outliers in a dataset in this work. The state-of-the-art methods for anomaly detection involve manual searching, predefined rules, or traditional machine learning techniques to detect such instances. This paper conducts a sentiment analysis and outlier detection case study for Amazon customer reviews, and it proposes a statistics-based outlier detection and correction method (SODCM), which helps identify such reviews and rectify their star ratings to enhance the performance of a sentiment analysis algorithm without any data loss. This paper focuses on performing SODCM in datasets containing customer reviews of various products, which are (a) scraped from Amazon.com and (b) publicly available. The paper also studies the dataset and concludes the effect of SODCM on the performance of a sentiment analysis algorithm. The results exhibit that SODCM achieves higher accuracy and recall percentage than other state-of-the-art anomaly detection algorithms.     

Real-World Data Difficulty Estimation with the Use of Entropy

In the era of the Internet of Things and big data, we are faced with the management of a flood of information. The complexity and amount of data presented to the decision-maker are enormous, and existing methods often fail to derive nonredundant information quickly. Thus, the selection of the most satisfactory set of solutions is often a struggle. This article investigates the possibilities of using the entropy measure as an indicator of data difficulty. To do so, we focus on real-world data covering various fields related to markets (the real estate market and financial markets), sports data, fake news data, and more. The problem is twofold: First, since we deal with unprocessed, inconsistent data, it is necessary to perform additional preprocessing. Therefore, the second step of our research is using the entropy-based measure to capture the nonredundant, noncorrelated core information from the data. Research is conducted using well-known algorithms from the classification domain to investigate the quality of solutions derived based on initial preprocessing and the information indicated by the entropy measure. Eventually, the best 25% (in the sense of entropy measure) attributes are selected to perform the whole classification procedure once again, and the results are compared.     

Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images

Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.     

用信号处理技术及传播理论还原雷声频谱

以往关于雷声的研究都限于观测点雷声频域范围的探讨, 由于噪音和衰减因素的影响, 观测点的雷声频谱有很大失真. 针对在兰州地区观测的一次雷暴过程中的雷声信号, 利用数字信号处理技术,由观测点处的雷声音频信号得到频率谱,并对雷声频谱进行噪音分析; 然后结合声音在大气中传播的衰减理论, 分析了不同大气环境对声吸收的影响, 并推算出了声源附近的雷声频率谱. 关键词： 雷声频谱 信号处理 传播理论 峰值频率     

Propagation of sound waves through a spatially homogeneous but smoothly time-dependent medium

The propagation of sound through a spatially homogeneous but non-stationary medium is investigated within the framework of fluid dynamics. For a non-vortical fluid, especially, a generalized wave equation is derived for the (scalar) potential of the fluid velocity distribution in dependence of the equilibrium mass density of the fluid and the sound wave velocity. A solution of this equation for a finite   transition period τ$\tau$ is determined in terms of the hypergeometric function for a phenomenologically realistic, sigmoidal change of the mass density and sound wave velocity. Using this solution, it is shown that the energy flux of the sound wave is not conserved but increases always   for the propagation through a non-stationary medium, independent of whether the equilibrium mass density is increased or decreased. It is found, moreover, that this amplification of the transmitted wave arises from an energy exchange with the medium and that its flux is equal to the (total) flux of the incident and the reflected wave. An interpretation of the reflected wave as a propagation of sound backward in time is given in close analogy to Feynman and Stueckelberg for the propagation of anti-particles. The reflection and transmission coefficients of sound propagating through a non-stationary medium is analyzed in more detail for hypersonic waves with transition periods τ$\tau$ between 15 and 200 ps as well as the transformation of infrasound waves in non-stationary oceans.     

基于扩频码的单载波迭代频域均衡水声通信

单载波时域均衡在长时延扩展水声信道中计算量大,并对接收机参数的选择较为敏感,可靠性低,而正交频分复用信号峰均功率比高、对频率偏移敏感. 针对这些问题,提出基于扩频码的单载波块传输高速率水声通信方法和基于T/4分数间隔迭代频域均衡的接收机算法. 该接收机利用已知扩频码进行信道估计以及对由多普勒偏移引起的旋转相位进行估计,并通过一种低复杂度迭代频域均衡算法改善系统性能. 开展了湖上实验研究,结果表明在浅水1.8 km距离且复杂多径干扰条件下,利用BPSK/QPSK调制可实现10^-2–10^-4的误码率并达到1500–3000 bit/s的有效数据率. 关键词： 水声通信 单载波 频域均衡 迭代处理     

Establishment of an integrated data fusion method between the colorimeter and near-infrared spectroscopy to discriminate the stir-baked Gardenia jasminoides Ellis

Stir-heating is a common method to process Gardenia jasminoides Ellis. The processing of the G. jasminoides Ellis which do not meet the regulated requirements can result in the unqualified products, finally decreasing the efficacy of the drug. To guarantee the quality of the stir-baked G. jasminoides Ellis, a rapid and efficient method to discriminate the qualified stir-baked G. jasminoides Ellis from the unqualified was developed based on the middle level data fusion. 61 batches of qualified and unqualified stir-baked G. jasminoides Ellis were collected and analyzed using colorimeter and near-infrared spectroscopy, separately. L*, A*, and B* were apparent features that quantitatively described the characteristics of samples. The latent variables of partial least squares discriminant analysis model were extracted as the features of near-infrared spectroscopy. The extracted features from colorimeter and near-infrared spectroscopy were fused and a discriminant model was built using partial least squares discriminant analysis method. Accuracy, sensitivity, and specificity were used to evaluate the ability of classification. As a result, the accuracy, sensitivity, and specificity of the optimal partial least squares discriminant analysis model based on fused data were all equal to 1. It demonstrated that the developed method can be capable of discriminating the qualified stir-baked G. jasminoides Ellis from the unqualified. Compared with classification model results using color parameters or near infrared data alone, this data fusion strategy greatly improved the accuracy of classification.     

Informationen

Studies on the workability of precise seeders by means of labelling methods has been possible due to the solution of the following problems: labelling of seeds, radiation collimation of labelled seeds being sown, elaboration of measuring and registering systems as well as processing systems of a measuring signal. The developed method allows for precise, quick and fully objective evaluation of the studied seeders to be done under natural conditions.