ORCID Profile
0000-0002-4745-6756
Current Organisation
University of Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: IEEE
Date: 09-2012
Publisher: IEEE
Date: 11-2014
Publisher: Wiley
Date: 30-10-2018
DOI: 10.1002/JMRS.251
Publisher: IGI Global
Date: 2011
DOI: 10.4018/978-1-60960-551-3.CH004
Abstract: The use of visual information for the navigation of unmanned ground vehicles in a cross-country environment recently received great attention. However, until now, the use of textural information has been somewhat less effective than color or laser range information. This chapter reviews the recent achievements in cross-country scene segmentation and addresses their shortcomings. It then describes a problem related to classification of high dimensional texture features. Finally, it compares three machine learning algorithms aimed at resolving this problem. The experimental results for each machine learning algorithm with the discussion of comparisons are given at the end of the chapter.
Publisher: IEEE
Date: 10-2010
Publisher: MDPI AG
Date: 30-12-2021
DOI: 10.3390/MATH10010112
Abstract: Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabeled datasets that could be leveraged as a proxy for out-of-distribution s les. In this paper we introduce the latent-insensitive autoencoder (LIS-AE) where unlabeled data from a similar domain are utilized as negative ex les to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. We provide theoretical justification for the proposed training process and loss functions along with an extensive ablation study highlighting important aspects of our model. We test our model in multiple anomaly detection settings presenting quantitative and qualitative analysis showcasing the significant performance improvement of our model for anomaly detection tasks.
Publisher: IGI Global
Date: 2012
DOI: 10.4018/978-1-4666-1833-6.CH015
Abstract: Volatile organic compounds (VOCs) belong to a new class of air pollutant that causes significant effect on human health and environment. Photocatalytic oxidation is an innovative, highly efficient, and promising option to decontaminate air polluted with VOCs, at faster elimination rates. This study pertains to the application of artificial neural networks to model the removal dynamics of an annular type photoreactor for gas – phase VOC removal. Relevant literature pertaining to the experimental work has been reported in this chapter. The different steps involved in developing a suitable neural model have been outlined by considering the influence of internal network parameters on the model architecture. Anew, the neural network modeling results were also subjected to sensitivity analysis in order to identify the most influential parameter affecting the VOC removal process in the photoreactor.
Publisher: Wiley
Date: 28-10-2018
DOI: 10.1002/JMRS.310
Publisher: IEEE
Date: 10-2010
Publisher: Wiley
Date: 20-01-2016
DOI: 10.1002/JMRS.154
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Elsevier BV
Date: 2023
Publisher: IEEE
Date: 08-2016
Publisher: IGI Global
Date: 2012
DOI: 10.4018/978-1-60960-818-7.CH418
Abstract: The use of visual information for the navigation of unmanned ground vehicles in a cross-country environment recently received great attention. However, until now, the use of textural information has been somewhat less effective than color or laser range information. This chapter reviews the recent achievements in cross-country scene segmentation and addresses their shortcomings. It then describes a problem related to classification of high dimensional texture features. Finally, it compares three machine learning algorithms aimed at resolving this problem. The experimental results for each machine learning algorithm with the discussion of comparisons are given at the end of the chapter.
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Wiley
Date: 28-06-2016
DOI: 10.1002/SONO.12068
Publisher: No publisher found
Date: 2018
Publisher: Wiley
Date: 25-04-2016
DOI: 10.1002/SONO.12058
Publisher: Wiley
Date: 25-04-2016
DOI: 10.1002/SONO.12059
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer Science and Business Media LLC
Date: 04-2012
Publisher: EJournal Publishing
Date: 06-2016
Publisher: IEEE
Date: 07-2016
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Hikari, Ltd.
Date: 2014
Publisher: EJournal Publishing
Date: 04-2016
Publisher: IGI Global
Date: 2012
DOI: 10.4018/978-1-61350-429-1.CH018
Abstract: In this chapter, the authors elaborate on the facial image segmentation and the detection of eyes and lips using two neural networks. The first neural network is applied to segment skin-colors and the second to detect facial features. As for input vectors, for the second network the authors apply speed-up robust features (SURF) that are not subject to scale and brightness variations. The authors carried out the detection of eyes and lips on two well-known facial feature databases, Caltech. and PICS. Caltech gave a success rate of 92.4% and 92.2% for left and right eyes and 85% for lips, whereas the PCIS database gave 96.9% and 95.3% for left and right eyes and 97.3% for lips. Using videos captured in real environment, among all videos, the authors achieved an average detection rate of 94.7% for the right eye and 95.5% for the left eye with a 86.9% rate for the lips
Publisher: EJournal Publishing
Date: 2014
Publisher: The Institute of Systems, Control and Information Engineers
Date: 05-05-2012
DOI: 10.5687/SSS.2012.333
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Korean Society of Ultrasound in Medicine
Date: 2019
DOI: 10.14366/USG.17062
Publisher: Wiley
Date: 16-12-2017
DOI: 10.1002/SONO.12098
Publisher: IEEE
Date: 07-2013
DOI: 10.1109/AMS.2013.31
Publisher: Medknow
Date: 2018
Publisher: Wiley
Date: 23-05-2017
DOI: 10.1002/SONO.12106
Publisher: SCITEPRESS - Science and Technology Publications
Date: 2020
Publisher: Frontiers Media SA
Date: 19-12-2017
Publisher: Springer Science and Business Media LLC
Date: 21-04-2017
Publisher: SAGE Publications
Date: 03-05-2020
Abstract: Leaving school for a period of time can have significant effects on students’ academic success. In this article, we analyze how taking an academic break for a different number of semesters affects students’ academic performance in terms of their Grade Point Average. This study is conducted at a university in Korea by analysing academic records of 653 undergraduate students who entered the university from 1998 to 2013. In addition, 101 currently enrolled students were surveyed to collect students’ opinions on the effects of academic breaks. We investigate changes in grades before and after a school leave and compare the final grades of students who had academic breaks to students who continued their studies without having any breaks during their undergraduate education.Our results indicate that students’ grades improve after coming back to the university from a four or more consecutive semesters break, however their final GPAs did not statistically differ from their peers who studied continuously, this suggests that students should not be afraid of taking longer academic breaks.
Location: Korea, Republic of
Location: No location found
No related grants have been discovered for Artem Lensky.