SEDRET—an intelligent system for the diagnosis and prediction of events in power plants

Artificial Intelligence applications in large-scale industry, such as fossil power plants, require the ability to manage uncertainty and time. In this paper, we present an intelligent system to assist an operator of a power plant. This system, called SEDRET, is based on a novel knowledge representation of uncertainty and time, called Temporal Nodes Bayesian Networks (TNBN), a type of Probabilistic Temporal Network. A set of temporal nodes and a set of edge define a TNBN, each temporal node is defined by a value of a variable and a time interval associate to the change of variable value. A TNBN generates a formal and systematic structure for modeling the temporal evolution of a process under uncertainty. The inference mechanism is based on probabilistic reasoning. A TNBN can be used to recognize events and state variables with respect to current plant conditions and predict the future propagation of disturbances. SEDRET was validated with the diagnosis and prediction of events in a steam generator with a power plant training simulator. The results performed in this work indicate that SEDRET can potentially improve plant availability through early diagnosis and prediction of disturbances that could lead to plant shutdown.     

Customer event history for churn prediction: How long is long enough?

The key question of this study is: How long should customer event history be for customer churn prediction? While most studies in predictive churn modeling aim to improve models by data augmentation or algorithm improvement, this study focuses on a another dimension: time window optimization with respect to predictive performance. This paper first presents a formalization of the time window selection strategy, along with a literature review. Next, using logistic regression, classification trees and bagging in combination with classification trees, this study analyzes the improvement in churn-model performance by extending customer event history from one to sixteen years. The results show that, after the fifth additional year, predictive performance is only marginally increased, meaning that the company in this study can discard 69% of its data with almost no decrease in predictive performance. The practical implication is that analysts can substantially decrease data-related burdens, such as data storage, preparation and analysis. This is particularly valuable in times of big data when decreasing computational complexity is paramount.     

How Sustainable is the Familial Support of Elderly in Asia?

This paper examines the extent of familial monetary support for the elderly in China, India, Indonesia, Japan, Korea, the Philippines, and Thailand, representing diverse public social security and assistance programs for the elderly across Asian countries. Using the National Transfer Accounts framework, Japan was found to experience the highest and China the lowest lifecycle deficit (LCD). Except Indonesia, the consumption of public and private goods and services at old ages is fast increasing in the Asian countries. In Japan public transfer supports 39.4% of the LCD of the 60 plus population and private asset-based reallocation, which includes liquidation and sale of assets, finances 33.7%. On the other in Indonesia and India LCD of elderly is largely 70.5 and 63.9% respectively are met by private asset-based reallocation. Public support for the 60 plus population in South Korea constitutes 22.9% of the LCD, whereas 52.6% is met by asset-based reallocation. The corresponding figures for China are 41.3 and 32.2% respectively.     

Future Trends in Computer Graphics: How Much is Enough?

Over the forty-year history of interactive computer graphics, there have been con-tinuous advances, but at some stage this progression must terminate with images being suifficently realistic for all practical purposes. How much detail do we really need? Polygon counts over a few million imply that on average each polygon paints less than a single pixel, making use of polygon shading hardware wasteful. We consider the problem of determining how much realism is required for a variety of applications. We discuss how current trends in computer graphics hardware, and in particular of graphics cards targeted at the computer games industry, will help or hinder achieve-ment of these requirements. With images now being so convincingly realistic in many cases, critical faculties are often suspended and the images are accepted as correct and truthful although they may well be incorrect and sometimes misleading or untruthful. Display resolution has remained largely constant in spatial terms for the last twenty yeaxs and in terms of the number of pixels has increased by less than an order of magnitude. If the long-promised breakthroughs in display technology are finally realised, how should we use the increased resolution?     

How hard is control in single-crossing elections?

Election control problems model situations where some entity (traditionally called the election chair) wants to ensure some candidate’s victory by either adding or deleting candidates or voters. The complexity of deciding if such control actions can be successful is well-studied for many typical voting rules and, usually, such control problems are \(\mathrm {NP}\)-complete. However, Faliszewski et al. (Inf Comput 209(2):89–107, 2011) have shown that many control problems become polynomial-time solvable when we consider single-peaked elections. In this paper we show that a similar phenomenon applies to the case of single-crossing elections. Specifically, we consider the complexity of control by adding/deleting candidates/voters under plurality, Condorcet, and approval voting. For each of these control types and each of the rules, we show that if the control type is \(\mathrm {NP}\)-complete in general, it becomes polynomial-time solvable for single-crossing elections.     

Learning the harmonic analysis: is visualization an effective approach?

Multimedia Tools and Applications - Understanding the structure of music compositions requires an ability built over time, through the study of the music theory and the application of countless...     

Grey is the new RGB: How good is GAN-based image colorization for image compression?

Multimedia Tools and Applications - GAN-based image colorization techniques are capable of producing highly realistic color in real-time. Subjective assessment of these approaches has demonstrated...     

Computer exhibitions — an overloaded market?: How to ge the most from an event

Computer trade exhibitions are held worldwide. Poor organization though has caused a number to fail. In order to have a successful show both visitors and exhibitors should understand their markets and the aims of the event.     

Trends in Labor Force Participation: How Much is Due to Changes in Pensions?

In the United States, beginning in the late 1980s there was a substantial increase in the labor force participation of men and women in their 60s. Over the same time period the type of pension plans offered by employers shifted strongly from defined benefit plans to defined contribution plans. Defined benefit plans typically have optimal retirement ages embedded in their structure which induce early retirement, whereas defined contribution plans do not favor any particular retirement age. Based on panel data, this paper quantifies the increase in participation due to the change in pension structure. The main result is that the pension changes account for a considerable part of the increase, but other factors also made a contribution.     

How security fits in — a management view: Security is an essential for quality information

Today's businesses require quality information; that is, business operations management requires that information have qualities of reliability, integrity, and privacy. This fact makes selling the need for computer security easier, since security is one of the necessary elements for ensuring information quality. This report explains how quality information concepts were used as a basis for a presentation to the senior management people of a large business.     

This is Your Life: How secure is your CRM data?

If you bank, buy insurance, financial services or shop for groceries or consult a dealer about a new car, you may be surprised to learn that your data has found its way into CRM (Customer Relationship Management) systems. CRM solutions are used increasingly by household names: Direct Line, Safeway, Barclays, Delta Air Lines, Renault and Peugeot, to build knowledge about customer interactions and the customer’s buying behaviour while giving the customer access to the organization through multiple channels.     

Polite web-based intelligent tutors: Can they improve learning in classrooms?

Should an intelligent software tutor be polite, in an effort to motivate and cajole students to learn, or should it use more direct language? If it should be polite, under what conditions? In a series of studies in different contexts (e.g., lab versus classroom) with a variety of students (e.g., low prior knowledge versus high prior knowledge), the politeness effect was investigated in the context of web-based intelligent tutoring systems, software that runs on the Internet and employs artificial intelligence and learning science techniques to help students learn. The goal was to pinpoint the appropriate conditions for having the web-based tutors provide polite feedback and hints (e.g., “Let’s convert the units of the first item”) versus direct feedback and hints (e.g., “Convert the units of the first item now”). In the study presented in this paper, 132 high school students in a classroom setting, grouped as low and high prior knowledge learners according to a pre-intervention knowledge questionnaire, did not benefit more from polite feedback and hints than direct feedback and hints on either an immediate or delayed posttest, both of which contained near transfer and conceptual test items. Of particular interest and contrary to an earlier lab study, low prior knowledge students did not benefit more from using the polite version of a tutor. On the other hand, a politeness effect was observed for the students who made the most errors during the intervention, a different proxy for low prior knowledge, hinting that even in a classroom setting, politeness may be beneficial for more needy students. This article presents and discusses these results, as well as discussing the politeness effect more generally, its theoretical underpinnings, and future directions.     

How consistent is the satellite derived SST–LHF relationship in comparison with observed values?

Time series data for sea surface temperature (moored buoy), wind speed, air temperature, sea level pressure, relative humidity, short wave radiation and rainfall were collected close to the Lakshadweep islands for five months from July 2000 to cover two seasons, namely summer monsoon and autumn. Day and night passes of TMI data for the same period were analysed to compare with the observed values. Daily mean values were then generated from both satellite‐derived as well as observed parameters and daily latent heat flux (LHF) values computed using the advanced COARE‐3.0 version of the model. In concurrence with earlier studies, the observed LHF–SST relationship was inverse as the SST during this season seldom fell below 27°C. On the contrary, the satellite derived LHF–SST relationship exhibited a direct correlation. It is also observed that the satellite underestimation of SST increases linearly on either side of a threshold value of 28.5°C. Although the SST over the eastern Arabian Sea was generally above 27°C, the satellite underestimation often produced SSTs less than 27°C, thereby supporting a linear relationship with LHF, as suggested by Zhang and McPhaden. Similarly for SSTs higher than 28°C, the satellite underestimation prevented a further decrease of LHF (to sustain the linear relationship) by virtue of the inverse relationship for SSTs higher than 28°C. The overestimation of SST and wind speed in the satellite scenario generates a virtual enhancement of LHF values without cooling the sea surface. The linear relationship between SST and LHF is thus nothing but a virtual display of the observed inverse SST–LHF relationship.     

Authoring for English Literature in Hypercard: Where in the World is Blake's Tyger?

Many universities are applying computers to English literature, but find it difficult to integrate the machine into actual teaching. The difficulties of using hypertext in critical reading arc outlined in the article, and several examples of its use appraised, including Brown University's Intermedia. There are several dangers in the 'open field? approach, however, which the article outlines. The possibilities of hypertext for representing the foregrounded features of a literary text are then described, as well as its capacity to mimic or at least draw attention to the reading process itself. The author outlines in detail his own attempts to program in HyperCard: first, two Katherine Mansfield short stories; second, Blake's poem 'The Tyger?. He concludes that teacher-programmers in the Humanities should focus on solving the pedagogical issues involved in using hypertext by exploring its graphic resources to produce programs which can be genuinely useful adjuncts to classroom teaching.     

An analysis of students�� gaming behaviors in an intelligent tutoring system: predictors and impacts

Students who exploit properties of an instructional system to make progress while avoiding learning are said to be ??gaming?? the system. In order to investigate what causes gaming and how it impacts students, we analyzed log data from two Intelligent Tutoring Systems (ITS). The primary analyses focused on six college physics classes using the Andes ITS for homework and test preparation, starting with the research question: What is a better predictor of gaming, problem or student? To address this question, we developed a computational gaming detector for automatically labeling the Andes data, and applied several data mining techniques, including machine learning of Bayesian network parameters. Contrary to some prior findings, the analyses indicated that student was a better predictor of gaming than problem. This result was surprising, so we tested and confirmed it with log data from a second ITS (the Algebra Cognitive Tutor) and population (high school students). Given that student was more predictive of gaming than problem, subsequent analyses focused on how students gamed and in turn benefited (or not) from instructional features of the environment, as well as how gaming in general influenced problem solving and learning outcomes.