Search

Highlights: [•] Soft sensors are widely used to predict process variables in chemical plants. [•] Our goal is to achieve high prediction accuracy of soft sensors for new data. [•] We employ the online support vector regression (OSVR) and time variable. [•] The hyperparameters and the window size of the OSVR model were discussed. [•] The performance was confirmed with simulation data and real industrial data. [Copyright &y& Elsevier]

Abstract: Soft sensors are used in chemical plants to estimate process variables that are difficult to measure online. However, the predictive accuracy of adaptive soft sensor models decreases when sudden process changes occur. An online support vector regression (OSVR) model with a time variable can adapt to rapid changes among process variables. One problem faced by the proposed model is finding appropriate hyperparameters for the OSVR model; we discussed three methods to select parameters based on predictive accuracy and computation time. The proposed method was applied to simulation data and industrial data, and achieved high predictive accuracy when time-varying changes occurred. [Copyright &y& Elsevier]

Abstract: A number of scholars have questioned the practice of assessing academic writing in the context of a one-off language test, claiming that the time restrictions imposed in the test environment, when compared to the writing conditions typical at university, may prevent learners from displaying the kinds of writing skills required in academic contexts. Studies which have explored this issue have thus far produced conflicting findings. This paper investigates the impact of an efficiency driven policy decision to reduce the time allowed for performance on a post-entry diagnostic test of academic writing from 55 to 30min. It does so by comparing the performance of 30 test takers under both old and new time conditions. A fully counter-balanced design was chosen to establish whether the different time limits had an effect on (a) the writing scores, (b) the inter-rater reliability and (c) the quality of the discourse. Test takers’ perceptions were also canvassed via a post-task questionnaire. Findings showed that the test takers’ scores on the analytic rating criteria were not significantly different under the two time conditions, although high proficiency candidates profited more from the extended time allowance than did the others. Ratings were equally reliable in the “short” and “long” condition. The detailed discourse analysis illustrated that the longer writing condition yielded, as predicted, a better quality performance on a number of variables; however the performance on the majority of the variables was unaffected by the time factor. The questionnaire data nevertheless showed that students in general preferred having more time for planning and revising. The study considers the implications of these findings for the validity and fairness of diagnostic writing tests. [Copyright &y& Elsevier]

Abstract: Computer Forensics is mainly about investigating crime where computers have been involved. There are many tools available to aid the investigator with this task. We have created a prototype of a new type of tool called CyberForensic TimeLab where all evidence is indexed by their time variables and plotted on a timeline. We believed that this way of visualizing the evidence allows the investigators to find coherent evidence faster and more intuitively. We have performed a user test where a group of people has evaluated our prototype tool against a modern commercial computer forensic tool and the results of this preliminary test are very promising. The results show that users completed the task in shorter time, with greater accuracy and with less errors using CyberForensic TimeLab. The subjects also experienced that the prototype were more intuitive to use and that it allowed them to easier locate evidence that was coherent in time. [Copyright &y& Elsevier]