Measurement data intrusion detection in industrial control systems based on unsupervised learning

<abstract><p>Anomaly detection strategies in industrial control systems mainly investigate the transmitting network traffic called network intrusion detection system. However, The measurement intrusion detection system inspects the sensors data integrated into the supervisory control and data acquisition center to find any abnormal behavior. An approach to detect anomalies in the measurement data is training supervised learning models that can learn to classify normal and abnormal data. But, a labeled dataset consisting of abnormal behavior, such as attacks, or malfunctions is extremely hard to achieve. Therefore, the unsupervised learning strategy that does not require labeled data for being trained can be helpful to tackle this problem. This study evaluates the performance of unsupervised learning strategies in anomaly detection using measurement data in control systems. The most accurate algorithms are selected to train unsupervised learning models, and the results show an accuracy of 98% in stealthy attack detection.</p></abstract>

A novel attention model for salient structure detection in seismic volumes

<abstract><p>A new approach to seismic interpretation is proposed to leverage visual perception and human visual system modeling. Specifically, a saliency detection algorithm based on a novel attention model is proposed for identifying subsurface structures within seismic data volumes. The algorithm employs 3D-FFT and a multi-dimensional spectral projection, which decomposes local spectra into three distinct components, each depicting variations along different dimensions of the data. Subsequently, a novel directional center-surround attention model is proposed to incorporate directional comparisons around each voxel for saliency detection within each projected dimension. Next, the resulting saliency maps along each dimension are combined adaptively to yield a consolidated saliency map, which highlights various structures characterized by subtle variations and relative motion with respect to their neighboring sections. A priori information about the seismic data can be either embedded into the proposed attention model in the directional comparisons, or incorporated into the algorithm by specifying a template when combining saliency maps adaptively. Experimental results on two real seismic datasets from the North Sea, Netherlands and Great South Basin, New Zealand demonstrate the effectiveness of the proposed algorithm for detecting salient seismic structures of different natures and appearances in one shot, which differs significantly from traditional seismic interpretation algorithms. The results further demonstrate that the proposed method outperforms comparable state-of-the-art saliency detection algorithms for natural images and videos, which are inadequate for seismic imaging data.</p></abstract>

Crop and weed classification based on AutoML

<abstract> <p>CNN models already play an important role in classification of crop and weed with high accuracy, more than 95% as reported in literature. However, to manually choose and fine-tune the deep learning models becomes laborious and indispensable in most traditional practices and research. Moreover, the classic objective functions are not thoroughly compatible with agricultural farming tasks as the corresponding models suffer from misclassifying crop to weed, often more likely than in other deep learning application domains. In this paper, we applied autonomous machine learning with a new objective function for crop and weed classification, achieving higher accuracy and lower crop killing rate (rate of identifying a crop as a weed). The experimental results show that our method outperforms state-of-the-art applications, for example, ResNet and VGG19.</p> </abstract>

Comparison of eleven measures for estimating difficulty of open-loop TSP instances

<abstract> <p>From the theory of algorithms, we know that the time complexity of finding the optimal solution for a traveling salesman problem (TSP) grows exponentially with the number of targets. However, the size of the problem instance is not the only factor that affects its difficulty. In this paper, we review existing measures to estimate the difficulty of a problem instance. We also introduce MST branches and two other measures called greedy path and greedy gap. The idea of MST branches is to generate minimum spanning tree (MST) and then calculate the number of branches in the tree. A branch is a target, which is connected to at least two other targets. We perform an extensive comparison of 11 measures to see how well they correlate to human and computer performance. We evaluate the measures based on time complexity, prediction capability, suitability, and practicality. The results show that while the MST branches measure is simple, fast to compute, and does not need to have the optimal solution as a reference unlike many other measures. It correlates equally good or even better than the best of the previous measures ‑ the number of targets, and the number of targets on the convex hull.</p> </abstract>

Adjustable mode ratio and focus boost search strategy for cat swarm optimization

<abstract><p>Evolutionary algorithm is one of the optimization techniques. Cat swarm optimization (CSO)-based algorithm is frequently used in many applications for solving challenging optimization problems. In this paper, the tracing mode in CSO is modified to reduce the number of user-defined parameters and weaken the sensitivity to the parameter values. In addition, a <italic>mode ratio</italic> control scheme for switching individuals between different movement modes and a search boosting strategy are proposed. The obtained results from our method are compared with the modified CSO without the proposed strategy, the original CSO, the particle swarm optimization (PSO) and differential evolution (DE) with three commonly-used DE search schemes. Six test functions from IEEE congress on evolutionary competition (CEC) are used to evaluate the proposed methods. The overall performance is evaluated by the average ranking over all test results. The ranking result indicates that our proposed method outperforms the other methods compared.</p></abstract>