An improved memetic approach for protein structure prediction incorporating maximal hydrophobic core estimation concept
- Authors: Nazmul, Rumana , Chetty, Madhu , Chowdhury, Ahsan
- Date: 2021
- Type: Text , Journal article
- Relation: Knowledge-Based Systems Vol. 219, no. (2021), p. 104395
- Full Text: false
- Reviewed:
- Description: Protein Structure Prediction (PSP) from the primary amino acid sequence, even using a simplified Hydrophobic-Polar (HP) lattice model, continues to be extremely challenging. Finding an optimal conformation, even for a small sequence, by any of the currently known evolutionary approaches is computationally extensive and time consuming. Although Memetic Algorithms (MAs) have shown success in finding the optimal solution for PSP, no significant work on the incorporation of domain or problem specific knowledge into the search process to significantly improve their performance is reported. In this paper, we present an approach to incorporate such knowledge into the initial population to enhance the effectiveness of MA for PSP. The domain knowledge we propose to use is based on the concept of maximal ‘core’ formation by exploiting the fundamental property of the H residues to be at the core of the minimum energy optimal protein structure. A generic technique is proposed for estimating the maximal Hydrophobic core (H-core) in a protein sequence for 2D Square, 3D Cubic and a more complex and realistic 3D FCC (Face Centered Cubic) lattice models. Subsequently, the knowledge of this estimated core is incorporated in an MA. The experiments conducted using HP benchmark sequences for 2D Square, 3D Cubic and 3D FCC lattice models show that the proposed MA with the new core-based population initialization technique has superior performance to the existing methods in terms of convergence speed as well as minimal energy. © 2018 Elsevier B.V.
Associations between comorbid stress and internet gaming disorder symptoms : are there cultural and gender variations?
- Authors: Andreetta, Jesse , Teh Msc, Justin , Burleigh, Tyrone , Gomez, Rapson , Stavropoulos, Vasileios
- Date: 2020
- Type: Text , Journal article
- Relation: Asia-Pacific Psychiatry Vol. 12, no. 2 (2020), p.
- Full Text: false
- Reviewed:
- Description: Introduction: The American Psychiatric Association has requested additional studies examine risk, protective, and cultural factors in relation to Internet Gaming Disorder (IGD). The present study aimed to explore the association between stress as a potential IGD risk effect, the possible exacerbating role of cultural orientation (vertical individualism [VI]), and how this may vary between genders. Methods: The sample included adult gamers from the USA, UK, and Australia. Analyses were conducted via linear regression, moderation, and moderated moderation. Results: The results suggested that higher stress symptoms act to increase IGD risk. Gender and VI also influenced this association. Discussion: Males presenting with higher levels of stress and VI were at greater risk of IGD compared to females who exhibited a reduction in IGD-related behaviors. This demonstrates a need for more research to determine how culture and gender can act to mitigate or worsen the risks associated with excessive gaming. © 2020 John Wiley & Sons Australia, Ltd
Cyberattack triage using incremental clustering for intrusion detection systems
- Authors: Taheri, Sona , Bagirov, Adil , Gondal, Iqbal , Brown, Simon
- Date: 2020
- Type: Text , Journal article
- Relation: International Journal of Information Security Vol. 19, no. 5 (2020), p. 597-607
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text:
- Reviewed:
- Description: Intrusion detection systems (IDSs) are devices or software applications that monitor networks or systems for malicious activities and signals alerts/alarms when such activity is discovered. However, an IDS may generate many false alerts which affect its accuracy. In this paper, we develop a cyberattack triage algorithm to detect these alerts (so-called outliers). The proposed algorithm is designed using the clustering, optimization and distance-based approaches. An optimization-based incremental clustering algorithm is proposed to find clusters of different types of cyberattacks. Using a special procedure, a set of clusters is divided into two subsets: normal and stable clusters. Then, outliers are found among stable clusters using an average distance between centroids of normal clusters. The proposed algorithm is evaluated using the well-known IDS data sets—Knowledge Discovery and Data mining Cup 1999 and UNSW-NB15—and compared with some other existing algorithms. Results show that the proposed algorithm has a high detection accuracy and its false negative rate is very low. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.
- Description: This research was conducted in Internet Commerce Security Laboratory (ICSL) funded by Westpac Banking Corporation Australia. In addition, the research by Dr. Sona Taheri and A/Prof. Adil Bagirov was supported by the Australian Government through the Australian Research Council’s Discovery Projects funding scheme (DP190100580).
The knowledge management functions of corporate university and their evolution: case studies of two Chinese corporate universities
- Authors: Chen, Yunqi , Xu, Yusen , Zhai, Qingguo
- Date: 2019
- Type: Text , Journal article
- Relation: Journal of Knowledge Management Vol. 23, no. 10 (Dec 2019), p. 2086-2112
- Full Text: false
- Reviewed:
- Description: Purpose The purpose of this paper is to investigate the knowledge management functions of corporate universities and their evolution. Design/methodology/approach Two Chinese corporate universities in the ICT industry were selected for the case studies. Data were collected by interviews and consulting the documents of the two corporate universities. Grounded theory was used for data analysis. Findings The research found that the knowledge management functions of the corporate universities encompass knowledge transfer, knowledge creation and knowledge services for intrapreneurship. The knowledge management functions of the corporate universities are enhancing with the development of the corporate universities. The knowledge management functions mutually reinforce each other. The knowledge network of the corporate universities is expanding and the scope of knowledge managed is broadening. Originality/value Analyzing the knowledge management functions of corporate universities and their evolution from the perspective of knowledge network enriches research on knowledge management of corporate universities.
A quasisecant method for solving a system of nonsmooth equations
- Authors: Long, Qiang , Wu, Changzhi
- Date: 2013
- Type: Text , Journal article
- Relation: Computers and Mathematics with Applications Vol. 66, no. 4 (2013), p. 419-431
- Full Text: false
- Reviewed:
- Description: In this paper, the solution of nonsmooth equations is studied. We first transform the problem into an equivalent nonsmooth optimization problem and then the quasisecant method is introduced to solve it. Some nonsmooth equations that have arisen from bilevel programming problems are solved by our proposed method. The numerical results show the effectiveness and efficiency of our proposed method. © 2013 Elsevier Ltd. All rights reserved.
- Description: 2003011208
Novel weighting in single hidden layer feedforward neural networks for data classification
- Authors: Seifollahi, Sattar , Yearwood, John , Ofoghi, Bahadorreza
- Date: 2012
- Type: Text , Journal article
- Relation: Computers and Mathematics with Applications Vol. 64, no. 2 (2012), p. 128-136
- Full Text: false
- Reviewed:
- Description: We propose a binary classifier based on the single hidden layer feedforward neural network (SLFN) using radial basis functions (RBFs) and sigmoid functions in the hidden layer. We use a modified attribute-class correlation measure to determine the weights of attributes in the networks. Moreover, we propose new weights called as influence weights to utilize in the weights connecting the input layer and the hidden layer nodes (hidden weights) of the network with sigmoid hidden nodes. These weights are calculated as the sum of conditional probabilities of attribute values given class labels. Our learning procedure of the networks is based on the extreme learning machines; in which the parameters of the hidden nodes are first calculated and then the weights connecting the hidden nodes and output nodes (output weights) are found. The results of the networks with the proposed weights on some benchmark data sets show improvements over those of the conventional networks. © 2012 Elsevier Ltd. All rights reserved.