Extreme Learning Machines for VISualization+R: Mastering Visualization with Target Variables

The current paper presents an improvement of the Extreme Learning Machines for VISualization (ELMVIS+) nonlinear dimensionality reduction method. In this improved method, called ELMVIS+R, it is proposed to apply the originally unsupervised ELMVIS+ method for the regression problems, using target values to improve visualization results. It has been shown in previous work that the approach of adding supervised component for classification problems indeed allows to obtain better visualization results. To verify this assumption for regression problems, a set of experiments on several different datasets was performed. The newly proposed method was compared to the ELMVIS+ method and, in most cases, outperformed the original algorithm. Results, presented in this article, prove the general idea that using supervised components (target values) with nonlinear dimensionality reduction method like ELMVIS+ can improve both visual properties and overall accuracy.     

Low Amplitude Characterization Tests Conducted at Regular Intervals Can Affect Tendon Mechanobiological Response

In bioreactor studies of tissue mechanobiology, characterizing changes in tissue quality is essential for understanding and predicting the response to mechanical stimuli. Unfortunately, current methods are often destructive and cannot be used at regular intervals on the same sample to characterize progression over time. Non-destructive methods such as low amplitude stress relaxation tests could be used, but then, the following dilemma comes into play: how can we accurately measure live tissue progression over time if the tissue is reacting to our measurement methods? In this study, we investigated the hypothesis that stress relaxation tests at physiological amplitudes conducted at regular intervals between stimulation periods do not modify tissue progression over time. Live, healthy tendons were subjected to mechanical stimuli inside a bioreactor for 3 days. The tendons were grouped based on the daily characterization protocol (24 or 0 stress relaxation tests) and their progression over time were compared. Stress relaxation tests at physiological amplitudes modified the tendon response to mechanical stimulation as observed through mechanical and histologic analyses. Possible solutions to eliminate or minimize the effect of stress relaxation tests are to use the mechanical stimuli to characterize tissue progression or to limit the number of stress relaxation tests.     

Anomaly-Based Intrusion Detection Using Extreme Learning Machine and Aggregation of Network Traffic Statistics in Probability Space

Recently, with the increased use of network communication, the risk of compromising the information has grown immensely. Intrusions have become more sophisticated and few methods can achieve efficient results while the network behavior constantly changes. This paper proposes an intrusion detection system based on modeling distributions of network statistics and Extreme Learning Machine (ELM) to achieve high detection rates of intrusions. The proposed model aggregates the network traffic at the IP subnetwork level and the distribution of statistics are collected for the most frequent IPv4 addresses encountered as destination. The obtained probability distributions are learned by ELM. This model is evaluated on the ISCX-IDS 2012 dataset, which is collected using a real-time testbed. The model is compared against leading approaches using the same dataset. Experimental results show that the presented method achieves an average detection rate of 91% and a misclassification rate of 9%. The experimental results show that our methods significantly improve the performance of the simple ELM despite a trade-off between performance and time complexity. Furthermore, our methods achieve good performance in comparison with the other few state-of-the-art approaches evaluated on the ISCX-IDS 2012 dataset.