A Bayesian Network (BN) is a graphical model which can be used to represent conditional dependency between random variables, such as diseases and symptoms. A Bayesian Network Classifier (BNC) uses BN to characterize t...
详细信息
A Bayesian Network (BN) is a graphical model which can be used to represent conditional dependency between random variables, such as diseases and symptoms. A Bayesian Network Classifier (BNC) uses BN to characterize the relation-ships between attributes and the class labels, where a simplified approach is to employ a conditional independence assumption between attributes and the corresponding class labels, i.e., the Naive Bayes (NB) classification model. One major approach to mitigate NB's primary weakness (the conditional independence assumption) is the attribute weighting, and this type of approach has been proved to be effective for NB with simple structure. However, for weighted BNCs involving complex structures, in which attribute weighting is embedded into the model, there is no existing study on whether the weighting will work for complex BNCs and how effective it will impact on the learning of a given task. In this paper, we first survey several complex structure models for BNCs, and then carry out experimental studies to investigate the effectiveness of the attribute weighting strategies for complex BNCs, with a focus on Hidden Naive Bayes (HNB) and Averaged One-Dependence Estimation (AODE). Our studies use classification accuracy (ACC), area under the ROC curve ranking (AUC), and conditional log likelihood (CLL), as the performance metrics. Experiments and comparisons on 36 benchmark data sets demonstrate that attribute weighting technologies just slightly outperforms unweighted complex BNCs with respect to the ACC and AUC, but significant improvement can be observed using CLL.
The foundation of a country's critical infrastructures (CI), which provide crucial services, is its security, healthcare, and economic systems. By lowering CI's operational costs and associated expenses and en...
详细信息
The foundation of a country's critical infrastructures (CI), which provide crucial services, is its security, healthcare, and economic systems. By lowering CI's operational costs and associated expenses and enhancing its effectiveness and safety, appropriately functional CI infrastructure plays an essential role in the prosperity of the nations. To do so, businesses that manage CIs frequently combine the Internet of Things (IoT) with Cyber-Physical systems (CPS), such as SCADA systems. SCADA systems were not initially built with web security in mind, exposing CIs open to security risks. National security issues can arise when these technologies are connected to power plants and water treatment facilities. This study aims to demonstrate how security features can be implemented in DNP3-based SCADA infrastructures. By creating a functional configuration and consensus amongst the communicating devices, the DNP3 protocol will support digital signatures. The team proposed a SCADA architecture to accomplish this, making it possible for these systems more secure manner.
In this paper, we describe the design journey of a smart clothing system, SoPhy from the research laboratory to finally being evaluated in the hospital setting. SoPhy is a smart socks-based system, designed to make ph...
详细信息
Context-aware Recommender systems aim to provide users with the most adequate recommendations for their current situation. However, an exact context obtained from a user could be too specific and may not have enough d...
详细信息
Context-aware Recommender systems aim to provide users with the most adequate recommendations for their current situation. However, an exact context obtained from a user could be too specific and may not have enough data for accurate rating prediction. This is known as the data sparsity problem. Moreover, often user preference representation depends on the domain or the specific recommendation approach used. Therefore, a big effort is required to change the method used. In this paper we present a new approach for contextual pre-filtering (i.e. using the current context to select a relevant subset of data). Our approach can be used with existing recommendation algorithms. It is based on two ontologies: Recommender System Context ontology, which represents the context, and Contextual Ontological User Profile ontology, which represents user preferences. We evaluated our approach through an offline study which showed that when used with well-known recommendation algorithms it can significantly improve the accuracy of prediction.
Order tracking is a widely used tool for analysis of vibrations generated in engines, drive lines, and other components, since many vibration components are related to RPM. In recent years off-line order tracking has ...
详细信息
ISBN:
(纸本)0912053895
Order tracking is a widely used tool for analysis of vibrations generated in engines, drive lines, and other components, since many vibration components are related to RPM. In recent years off-line order tracking has become suitable due to enhanced computer speeds. Many methods, some patented, for on-line as well as off-line order tracking have been presented over the years. In this paper we review some basic ideas behind current methods and compare their main advantages and limitations. Some basic time-frequency concepts and time window effects are reviewed. Questions on suitable tachometers and their number of pulses per revolution are also addressed. The possibility of processing RPM dependent data without tachometers is also discussed.
The objective of the paper is to present some results of experiments for structural health monitoring by utilizing a wireless sensor network technology based on GPS. Sensor nodes equipped with GPS are installed on the...
详细信息
ISBN:
(纸本)9781479904051
The objective of the paper is to present some results of experiments for structural health monitoring by utilizing a wireless sensor network technology based on GPS. Sensor nodes equipped with GPS are installed on the top of the roof of a building and allow to detect the position of this sensor nodes during several instants of time. This information is collected through wireless communication. At first, the description of the system is presented. Then, an application of the wireless sensor network technology based on GPS to one building is discussed.
In this paper we develop communication strategies with the concept of parallel processing to enhance performance of the Ant Colony System algorithm. In these strategies we choose one particular scheme of adapting the ...
详细信息
In this paper we develop communication strategies with the concept of parallel processing to enhance performance of the Ant Colony System algorithm. In these strategies we choose one particular scheme of adapting the amount of pheromone based on the quality of solutions found by several colonies and the state of convergence. We investigate and compare the search behavior and the performance of these strategies with other existing strategies using the Traveling Salesman Problem (TSP). The results demonstrate the potential of applying the multiple version over the sequential version of the Ant Colony System with some variations in the performance of the multiple version employing different strategies. The study indicates that the weighting scheme that is incorporated in the proposed strategies improves performance, particularly in strategies that share information among all colonies.
A variety of output regulation problems can be addressed via sliding mode control when system's relative degree is known. The difficulties in the implementation of sliding mode controllers emerge when the relative...
详细信息
A variety of output regulation problems can be addressed via sliding mode control when system's relative degree is known. The difficulties in the implementation of sliding mode controllers emerge when the relative degree is unknown. On the other hand, practical systemscontrolled by sliding mode algorithms always work under tolerance limits, which are frequently known. This behavior is called real sliding motion. In this work, the concept of practical relative degree in single-input-single-output systemscontrolled by sliding mode controllers is revisited from the view point of frequency analysis. Practical relative degree is understood as the smallest order of the sliding mode controller that satisfies the tolerance limits. Also, the notion of practical relative degree is analyzed in terms of the definitions of performance margins. The usefulness of the proposed concept is the way to design sliding mode controllers for systems that can be considered a black-box. The practical relative degree is studied and illustrated via examples and simulations.
In this paper, we present and validate an analytical expression for the induced current on a long terminated line, under the thin wire approximation. The coefficients of the analytical expression are determined using ...
暂无评论