Unsupervised Rule Research Articles

Review of Cybersecurity Analysis in Smart Distribution Systems and Future Directions for Using Unsupervised Learning Methods for Cyber Detection

In a physical microgrid system, equipment failures, manual misbehavior of equipment, and power quality can be affected by intentional cyberattacks, made more dangerous by the widespread use of established communication networks via sensors. This paper comprehensively reviews smart grid challenges on cyber-physical and cyber security systems, standard protocols, communication, and sensor technology. Existing supervised learning-based Machine Learning (ML) methods for identifying cyberattacks in smart grids mostly rely on instances of both normal and attack events for training. Additionally, for supervised learning to be effective, the training dataset must contain representative examples of various attack situations having different patterns, which is challenging. Therefore, we reviewed a novel Data Mining (DM) approach based on unsupervised rules for identifying False Data Injection Cyber Attacks (FDIA) in smart grids using Phasor Measurement Unit (PMU) data. The unsupervised algorithm is excellent for discovering unidentified assault events since it only uses examples of typical events to train the detection models. The datasets used in our study, which looked at some well-known unsupervised detection methods, helped us assess the performances of different methods. The performance comparison with popular unsupervised algorithms is better at finding attack events if compared with supervised and Deep Learning (DL) algorithms.

(Invited) Enabling on-Device Learning with Deep Spiking Neural Networks for Video Classification

Spiking recurrent neural networks are gaining traction in solving complex temporal tasks. In general, spiking neural networks are resilient and computationally powerful. These intrinsic properties make them attractive for learning on the edge of the devices. In this work, we propose a semi-supervised deep spiking neural network that can be deployed on embedded devices. We present memristor synapse and neuron circuits integrated in a neuromemristive system to implement a deep spiking neural network. For optimal performance on-device, the synaptic crossbar array is trained using a modified gradient descent rule in conjunction with an unsupervised rule. The proposed deep spiking neural network is validated for on-device video classification tasks.

Pioneering topological methods for network-based drug-target prediction by exploiting a brain-network self-organization theory.

The bipartite network representation of the drug–target interactions (DTIs) in a biosystem enhances understanding of the drugs’ multifaceted action modes, suggests therapeutic switching for approved drugs and unveils possible side effects. As experimental testing of DTIs is costly and time-consuming, computational predictors are of great aid. Here, for the first time, state-of-the-art DTI supervised predictors custom-made in network biology were compared—using standard and innovative validation frameworks—with unsupervised pure topological-based models designed for general-purpose link prediction in bipartite networks. Surprisingly, our results show that the bipartite topology alone, if adequately exploited by means of the recently proposed local-community-paradigm (LCP) theory—initially detected in brain-network topological self-organization and afterwards generalized to any complex network—is able to suggest highly reliable predictions, with comparable performance with the state-of-the-art-supervised methods that exploit additional (non-topological, for instance biochemical) DTI knowledge. Furthermore, a detailed analysis of the novel predictions revealed that each class of methods prioritizes distinct true interactions; hence, combining methodologies based on diverse principles represents a promising strategy to improve drug–target discovery. To conclude, this study promotes the power of bio-inspired computing, demonstrating that simple unsupervised rules inspired by principles of topological self-organization and adaptiveness arising during learning in living intelligent systems (like the brain) can efficiently equal perform complicated algorithms based on advanced, supervised and knowledge-based engineering.

Data mining methods for knowledge discovery in multi-objective optimization: Part B - New developments and applications

The first part of this paper served as a comprehensive survey of data mining methods that have been used to extract knowledge from solutions generated during multi-objective optimization. The current paper addresses three major shortcomings of existing methods, namely, lack of interactiveness in the objective space, inability to handle discrete variables and inability to generate explicit knowledge. Four data mining methods are developed that can discover knowledge in the decision space and visualize it in the objective space. These methods are (i) sequential pattern mining, (ii) clustering-based classification trees, (iii) hybrid learning, and (iv) flexible pattern mining. Each method uses a unique learning strategy to generate explicit knowledge in the form of patterns, decision rules and unsupervised rules. The methods are also capable of taking the decision maker’s preferences into account to generate knowledge unique to preferred regions of the objective space. Three realistic production systems involving different types of discrete variables are chosen as application studies. A multi-objective optimization problem is formulated for each system and solved using NSGA-II to generate the optimization datasets. Next, all four methods are applied to each dataset. In each application, the methods discover similar knowledge for specified regions of the objective space. Overall, the unsupervised rules generated by flexible pattern mining are found to be the most consistent, whereas the supervised rules from classification trees are the most sensitive to user-preferences.

Fractional-Neuro-Optimizer: A Neural-Network-Based Optimization Method

Up to now, there have been many attempts in the use of artificial neural networks (ANNs) for solving optimization problems and some types of ANNs, such as Hopfield network and Boltzmann machine, have been applied for combinatorial optimization problems. However, there are some restrictions in the use of ANNs as optimizers. For example: (1) ANNs cannot optimize continuous variable problems; (2) discrete problems should be mapped into the neural networks' architecture; and (3) most of the existing neural networks are applicable only for a class of smooth optimization problems and global convexity conditions on the objective functions and constraints are required. In this paper, we introduce a new procedure for stochastic optimization by a recurrent ANN. The concept of fractional calculus is adopted to propose a novel weight updating rule. The introduced method is called fractional-neuro-optimizer (FNO). This method starts with an initial solution and adjusts the network's weights by a new heuristic and unsupervised rule to reach a good solution. The efficiency of FNO is compared to the genetic algorithm and particle swarm optimization techniques. Finally, the proposed FNO is used for determining the parameters of a proportional---integral---derivative controller for an automatic voltage regulator power system and is applied for designing the water distribution networks.

Use of a Fast Information Extraction Method as a Decision Support Tool

INTRODUCTION Most electronic documents are available in the free-text format. Analyzability of the free-text information can play a crucial role in decision making through pattern discovery (Lo & Hsieh, 2003). The enormous volume of available documents can be processed semi-automatically by a closed or an open system (Banko & Etzioni, 2008). Important applications such as electronic governance (Zhang, Lin, Lin, & Hsieh, 2008) may entail the use of extracted information from these documents to gain competitiveness and public trust by enforcing transparency. An effectively designed Information Extraction (IE) system can be useful in this regard. An IE system is designed to extract the user-specified items or pre-defined events (Srihari, Li, Niu, & Cornell, 2008) from the text documents of a specific domain. The items to be extracted are specific word(s) of sentences of the input documents. An IE system can be used to fill the fields of a table of a relational database from text documents. Examples of the fields may include the name of a company or type of business. In order to interpret the extracted information, these items can be saved into a relational database. The extracted items can also be used to fill-out forms specified by a user. The information saved in the database can be further processed to identify the relevant correlations. Compared to the extraction of structured data performed by, for example, an ERP system (Wu, Hsieh, Shin, & Wu, 2005), extracting information from a free-text domain is a challenging problem. The reason is that only the contextually relevant target words or phrases have to be extracted. Because statistics does not consider the contexts of the words, the methods such as Naive Bayes Classifier or Average Mutual Information (Carven et al., 2000) are not effective in extracting information. Most of the state of the art IE systems use a combination of statistical and machine learning methods (Freitag, 2000). Jose Iria and Fabio Ciravegna (2006) developed an ontology learning (Suchanek, Sozio, & Weikum, 2009) and document classification method that represents language resources, such as syntactic and semantic parsers, in a way that is independent of the extraction process. Yildiz and Miksch (2007) proposed an unsupervised rule learning method (Downey, Schoenmackers, & Etzioni, 2007; Sekine & Oda, 2007) based on ontological structures. Syntactic and semantic analyses have been found to improve precision (Feldman, Aumann, Finkelstein-Landau, Hurvitz, Regev, & Yaroshevich, 2002). Xu, Uszkoreit, Li, and Felger (2008) designed a system that extracts linguistic grammar rules from a semantic seed. An alignment based pattern matching technique was developed by (Kim, Jeong, Lee, Ko, & Lee, 2008) that can extract relationships between two arguments. Jain, Ipeirotis, and Gravano (2008) developed a technique to process structured queries from the relations extracted from unstructured texts. Stevenson and Greenwood (2009) found that the IE models that use the relevant portions of a dependency tree (Wu & Weld, 2008) perform better. A rule-based decision tree was found effective in extracting information from online resumes (Bhargavi, Jyothi, Jyothi, & Sekar, 2008). The use of deep level ontology structure (Welty & Murdock, 2006) and the use of multiple ontologies from the same domain (Wimalasuriya & Dou, 2009) have been found effective in performance enhancement. Assigning weights to the syntactic features according to their co-occurrences in the related class has been found effective in determining ontologies about person-names and their geographic locations (Tanev & Magnini, 2008). Enterprise applications of IE systems require higher accuracy and scalability (Chiticariu, Li, Raghavan, & Reiss, 2010). Similar to many other systems, Pennacchiotti and Pantel (2009) used a combination of a pattern match method with a distributional method. …

Power analysis of principal components regression in genetic association studies

Association analysis provides an opportunity to find genetic variants underlying complex traits. A principal components regression (PCR)-based approach was shown to outperform some competing approaches. However, a limitation of this method is that the principal components (PCs) selected from single nucleotide polymorphisms (SNPs) may be unrelated to the phenotype. In this article, we investigate the theoretical properties of such a method in more detail. We first derive the exact power function of the test based on PCR, and hence clarify the relationship between the test power and the degrees of freedom (DF). Next, we extend the PCR test to a general weighted PCs test, which provides a unified framework for understanding the properties of some related statistics. We then compare the performance of these tests. We also introduce several data-driven adaptive alternatives to overcome difficulties in the PCR approach. Finally, we illustrate our results using simulations based on real genotype data. Simulation study shows the risk of using the unsupervised rule to determine the number of PCs, and demonstrates that there is no single uniformly powerful method for detecting genetic variants.

Unsupervised and auto-adaptive neural architecture for on-line monitoring. Application to a hydraulic process

Generally, the functioning of a monitored system is characterized by some parameters. Each evolution of these parameters may be assimilated with a drift or a fault. Therefore it may be considered to estimate the functioning state of the system by analyzing the drifts of these critical parameters evolving with time. So, this paper presents a new architecture, based on a new neural network classifier, for on-line monitoring of complex industrial systems. The first stage consists in the choice and the extraction of the significant parameters. The second stage extracts some parameter characteristics to be used in order to discriminate the different kinds of evolution. Then, in the third stage, a specialized neural network is used to classify, on-line, the evolutions for each significant parameter. The neural network is initialized with a set of synthetic and experimental data and a copy of this classifier is used to achieve the trend detection for each monitored parameter. Due to unsupervised rules and auto-adaptive abilities, each copy is adapted according to the specific evolutions of its monitored parameter in order to take account of new kinds of evolutions in situ and on-line. In the fourth stage, a decision tree is used to establish the diagnostic by analyzing the results of the trend detection stage for all the monitored parameters. The application to the monitoring of an industrial hydraulic process shows the ability of the classifier to learn and detect the different drifts.