SATELLITE SELECTION ALGORITHMS FOR POSITIONING, NAVIGATION AND TIMING USERS

Проведен обзор методов и алгоритмов формирования рабочего созвездия навигационных космических аппаратов при решении задач определения местоположения потребителя ГНСС. Появление новых орбитальных группировок и развитие прошлых поколений глобальных навигационных спутниковых систем (ГНСС) способствует увеличению как количества навигационных аппаратов, так и навигационных радиосигналов, излучаемых каждым спутником, в связи с чем решение проблемы выбора навигационных аппаратов является важной составляющей навигационной задачи. Рассмотрены исследования, посвященные типовым алгоритмам формирования рабочего созвездия, а также современным алгоритмам, построенным с привлечением элементов теории машинного обучения. Представлена связь ошибок определения координат потребителя, погрешностей определения псевдодальностей и пространственного расположения навигационных аппаратов и потребителя. Среди рассмотренных алгоритмов выделены три направления исследований: 1) нацеленных на поиск оптимального рабочего созвездия, обеспечивающего минимальную оценку выбранного геометрического фактора снижения точности; 2) нацеленных на поиск квазиоптимальных рабочих созвездий с целью уменьшения вычислительной сложности алгоритма ввиду большого количества видимых спутников; 3) позволяющих одновременно работать в совмещенном режиме по нескольким ГНСС. Приводятся особенности реализаций алгоритмов, их преимущества и недостатки. В заключении приведены рекомендации по изменению подхода к оценке эффективности алгоритмов, а также делается вывод о необходимости учета как геометрического расположения космических аппаратов, так и погрешности определения псевдодальности при выборе космического аппарата в рабочее созвездие The article provides an overview of methods and algorithms for forming a satellite constellation as a part of the navigation problem for the positioning, navigation and timing service. The emergence of new orbital constellations and the development of past GNSS generations increase both the number of navigation satellites and radio signals emitted by every satellite, and therefore the proper solution of satellite selection problem is an important component of the positioning, navigation and timing service. We considered the works devoted to typical algorithms of working constellation formation, as well as to modern algorithms built with the use of machine-learning theory elements. We present the relationship between user coordinates errors, pseudorange errors and the influence of spatial location of satellites and the user. Three directions of researche among reviewed algorithms are outlined: 1) finding the best satellite constellation that provides the minimum geometric dilution of precision; 2) finding quasi-optimal satellite constellation in order to reduce the computational complexity of the algorithm due to the large number of visible satellites; 3) possibility to work in a combined mode using radio signals of multiple GNSS simultaneously. The article presents the features of the algorithms' implementations, their advantages and disadvantages. The conclusion presents the recommendations to change the approach to assessing the performance of the algorithms, and concludes that it is necessary to take into account both the satellite geometric configuration, and pseudorange errors when satellite constellation is being formed

Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor

This paper introduces a comparative analysis of the proficiencies of various textures and geometric features in the diagnosis of breast masses on mammograms. An improved machine learning-based framework was developed for this study. The proposed system was tested using 106 full field digital mammography images from the INbreast dataset, containing a total of 115 breast mass lesions. The proficiencies of individual and various combinations of computed textures and geometric features were investigated by evaluating their contributions towards attaining higher classification accuracies. Four state-of-the-art filter-based feature selection algorithms (Relief-F, Pearson correlation coefficient, neighborhood component analysis, and term variance) were employed to select the top 20 most discriminative features. The Relief-F algorithm outperformed other feature selection algorithms in terms of classification results by reporting 85.2% accuracy, 82.0% sensitivity, and 88.0% specificity. A set of nine most discriminative features were then selected, out of the earlier mentioned 20 features obtained using Relief-F, as a result of further simulations. The classification performances of six state-of-the-art machine learning classifiers, namely k-nearest neighbor (k-NN), support vector machine, decision tree, Naive Bayes, random forest, and ensemble tree, were investigated, and the obtained results revealed that the best classification results (accuracy = 90.4%, sensitivity = 92.0%, specificity = 88.0%) were obtained for the k-NN classifier with the number of neighbors having k = 5 and squared inverse distance weight. The key findings include the identification of the nine most discriminative features, that is, FD26 (Fourier Descriptor), Euler number, solidity, mean, FD14, FD13, periodicity, skewness, and contrast out of a pool of 125 texture and geometric features. The proposed results revealed that the selected nine features can be used for the classification of breast masses in mammograms.

Multi-resource collaborative optimization for adaptive virtual machine placement

The unbalanced resource utilization of physical machines (PMs) in cloud data centers could cause resource wasting, workload imbalance and even negatively impact quality of service (QoS). To address this problem, this paper proposes a multi-resource collaborative optimization control (MCOC) mechanism for virtual machine (VM) migration. It uses Gaussian model to adaptively estimate the probability that the running PMs are in the multi-resource utilization balance status. Given the estimated probability of the multi-resource utilization balance state, we propose effective selection algorithms for live VM migration between the source hosts and destination hosts, including adaptive Gaussian model-based VMs placement (AGM-VMP) algorithm and VMs consolidation (AGM-VMC) method. Experimental results show that the AGM-VMC method can effectively achieve load balance and significantly improve resource utilization, reduce data center energy consumption while guaranteeing QoS.

A Feature Selection Algorithm Integrating Maximum Classification Information and Minimum Interaction Feature Dependency Information

Feature selection is the key step in the analysis of high-dimensional small sample data. The core of feature selection is to analyse and quantify the correlation between features and class labels and the redundancy between features. However, most of the existing feature selection algorithms only consider the classification contribution of individual features and ignore the influence of interfeature redundancy and correlation. Therefore, this paper proposes a feature selection algorithm for nonlinear dynamic conditional relevance (NDCRFS) through the study and analysis of the existing feature selection algorithm ideas and method. Firstly, redundancy and relevance between features and between features and class labels are discriminated by mutual information, conditional mutual information, and interactive mutual information. Secondly, the selected features and candidate features are dynamically weighted utilizing information gain factors. Finally, to evaluate the performance of this feature selection algorithm, NDCRFS was validated against 6 other feature selection algorithms on three classifiers, using 12 different data sets, for variability and classification metrics between the different algorithms. The experimental results show that the NDCRFS method can improve the quality of the feature subsets and obtain better classification results.

Machine Learning for Diagnosis of Alzheimer’s Disease and Early Stages

According to the WHO, approximately 50 million people worldwide have dementia and there are nearly 10 million new cases every year. Alzheimer’s disease is the most common form of dementia and may contribute to 60–70% of cases. It has been proved that early diagnosis is key to promoting early and optimal management. However, the early stage of dementia is often overlooked and patients are typically diagnosed when the disease progresses to a more advanced stage. The objective of this contribution is to predict Alzheimer’s early stages, not only dementia itself. To carry out this objective, different types of SVM and CNN machine learning classifiers will be used, as well as two different feature selection algorithms: PCA and mRMR. The different experiments and their performance are compared when classifying patients from MRI images. The newness of the experiments conducted in this research includes the wide range of stages that we aim to predict, the processing of all the available information simultaneously and the Segmentation routine implemented in SPM12 for preprocessing. We will make use of multiple slices and consider different parts of the brain to give a more accurate response. Overall, excellent results have been obtained, reaching a maximum F1 score of 0.9979 from the SVM and PCA classifier.

Analyzing Tuberculosis Reactivation in Patients with Rheumatoid Arthritis and Ankylosing Spondylitis Treated with Biological Therapy Using Machine Learning Methods

This study is based on the consideration that the patients with rheumatoid arthritis and ankylosing spondylitis undergoing biological therapy have a higher risk of developing tuberculosis. The QuantiFERON-TB Gold test result was the output of the models and a series of features related to the patients and their treatments were chosen as inputs. A distribution of patients by gender and biological therapy, followed at the time of inclusion in the study, and at the end of the study, is made for both rheumatoid arthritis and ankylosing spondylitis. A series of classification algorithms (random forest, nearest neighbor, k-nearest neighbors, C4.5 decision trees, non-nested generalized exemplars, and support vector machines) and attribute selection algorithms (ReliefF, InfoGain, and correlation-based feature selection) were successfully applied. Useful information was obtained regarding the influence of biological and classical treatments on tuberculosis risk, and most of them agreed with medical studies.

Zoo: Selecting Transcriptomic and Methylomic Biomarkers by Ensembling Animal-Inspired Swarm Intelligence Feature Selection Algorithms

Biological omics data such as transcriptomes and methylomes have the inherent “large p small n” paradigm, i.e., the number of features is much larger than that of the samples. A feature selection (FS) algorithm selects a subset of the transcriptomic or methylomic biomarkers in order to build a better prediction model. The hidden patterns in the FS solution space make it challenging to achieve a feature subset with satisfying prediction performances. Swarm intelligence (SI) algorithms mimic the target searching behaviors of various animals and have demonstrated promising capabilities in selecting features with good machine learning performances. Our study revealed that different SI-based feature selection algorithms contributed complementary searching capabilities in the FS solution space, and their collaboration generated a better feature subset than the individual SI feature selection algorithms. Nine SI-based feature selection algorithms were integrated to vote for the selected features, which were further refined by the dynamic recursive feature elimination framework. In most cases, the proposed Zoo algorithm outperformed the existing feature selection algorithms on transcriptomics and methylomics datasets.