Graph Embedding Using Frequency Filtering.

The target of graph embedding is to embed graphs in vector space such that the embedded feature vectors follow the differences and similarities of the source graphs. In this paper, a novel method named Frequency Filtering Embedding (FFE) is proposed which uses graph Fourier transform and Frequency filtering as a graph Fourier domain operator for graph feature extraction. Frequency filtering amplifies or attenuates selected frequencies using appropriate filter functions. Here, heat, anti-heat, part-sine and identity filter sets are proposed as the filter functions. A generalized version of FFE named GeFFE is also proposed by defining pseudo-Fourier operators. This method can be considered as a general framework for formulating some previously defined invariants in other works by choosing a suitable filter bank and defining suitable pseudo-Fourier operators. This flexibility empowers GeFFE to adapt itself to the properties of each graph dataset unlike the previous spectral embedding methods and leads to superior classification accuracy relative to the others. Utilizing the proposed part-sine filter set, which its members filter different parts of the spectrum in turn, improves the classification accuracy of GeFFE method. Additionally, GeFFE resolves the cospectrality problem entirely in tested datasets.

Machine learning algorithms, bull genetic information, and imbalanced datasets used in abortion incidence prediction models for Iranian Holstein dairy cattle.

The ability to predict abortion incidence, especially in regions with high abortion rates (e.g., Iran), helps improve reproductive performance and, thereby, dairy farm profitability. The objective of this study was to predict pregnancy loss in Iranian dairy herds. For this purpose, the cow history records and bull genetic information available at 6 large commercial dairy farms with cows calved between 2005 and 2014 were extracted from an on-farm record-keeping software. Using WEKA, 12 commonly used machine learning (ML) algorithms were applied to the dataset. The algorithms belonged to 5 classifier groups which were Bayes, meta, functions, rules, and trees. The original dataset including herd-cow factors was randomly divided into 2 subsets: a training dataset and a test one (at a ratio of 60:40). The original dataset was combined with the bull genetic information to create a full dataset. The average abortion rate was 15.4 %, which represented an imbalanced dataset. Therefore, 2 down- and up-sampling techniques were additionally implemented on the original dataset (more specifically on the training one) to create 2 balanced datasets. This ultimately yielded 4 datasets; original, full, down-sampling, and up-sampling. Different algorithms and models were evaluated based on F-measure and area under the curve (AUC). Based on the results obtained, ML algorithms exhibited a high performance in predicting abortion when applied to the balanced dataset. However, their performance varied from 32.3 % (poor) to 69.2 % (medium upward) when applied to the imbalanced original dataset. In addition to the imbalance in the original dataset, the reason for these poor results were attributed to the high proportion of unknown risk factors underlying abortion incidence. Even when including the bull genetic information, it did not lead to any significant improvements in the prediction model. From among the datasets used, the Bayes algorithms outperformed the others in predicting pregnancy losses while rules had the worst performance. Furthermore, while the Bayes algorithms were not affected by the type of dataset (balanced or imbalanced), substantial increases in F-measure and AUC were observed for rules, trees, and functions with balanced datasets. Overall, the balanced models outperformed the others, with the down-sampling method exhibiting the highest performance. Despite the fact that the prediction models used in this study did not perform as expected, it was shown that they can be beneficially used to predict and reduce pregnancy losses, despite their moderate accuracy, especially when used for herds with high abortion rates and low reproductive performances.

Creating Discriminative Models for Time Series Classification and Clustering by HMM Ensembles.

Classification of temporal data sequences is a fundamental branch of machine learning with a broad range of real world applications. Since the dimensionality of temporal data is significantly larger than static data, and its modeling and interpreting is more complicated, performing classification and clustering on temporal data is more complex as well. Hidden Markov models (HMMs) are well-known statistical models for modeling and analysis of sequence data. Besides, ensemble methods, which employ multiple models to obtain the target model, revealed good performances in the conducted experiments. All these facts are a high level of motivation to employ HMM ensembles in the task of classification and clustering of time series data. So far, no effective classification and clustering method based on HMM ensembles has been proposed. Moreover, employing the limited existing HMM ensemble methods has trouble separating models of distinct classes as a vital task. In this paper, according to previous points a new framework based on HMM ensembles for classification and clustering is proposed. In addition to its strong theoretical background by employing the Rényi entropy for ensemble learning procedure, the main contribution of the proposed method is addressing HMM-based methods problem in separating models of distinct classes by considering the inverse emission matrix of the opposite class to build an opposite model. The proposed algorithms perform more effectively compared to other methods especially other HMM ensemble-based methods. Moreover, the proposed clustering framework, which derives benefits from both similarity-based and model-based methods, together with the Rényi-based ensemble method revealed its superiority in several measurements.