Skip to main content

2018 | Buch

Transactions on Computational Science XXXII

Special Issue on Cybersecurity and Biometrics

herausgegeben von: Prof. Marina L. Gavrilova, C.J. Kenneth Tan, Prof. Alexei Sourin

Verlag: Springer Berlin Heidelberg

Buchreihe : Lecture Notes in Computer Science


Über dieses Buch

This, the 32nd issue of the Transactions on Computational Science, focusses on cybersecurity and biometrics. The eight detailed papers cover the following topics: Multimodal Warnings for Distracted Smartphone Users on the Move; EEG-Based Mental Workload and Stress Monitoring of Crew Members in a Maritime Virtual Simulator; Detecting Web Defacement and Enabling Web-Content Regeneration; Software as a Weapon in the Context of (Inter)national Security; Multi-user Architecture and Multi-player Games; An Adaptive Discrete Wavelet Transform Based Face Recognition Approach; Synthesizing Images of Imagined Faces Based on Relevance Feedback; and Neurofeedback Training to Enhance the Focused Attention of Elite Rifle Shooters.


Investigating Multimodal Warnings for Distracted Smartphone Users on the Move in Potentially Dangerous Situations
The use of smart devices has become an integrated part of our everyday life. Communication is now possible any place and any time. The distraction caused by these devices, however, can lead to potentially dangerous situations. To mitigate these situations, various researchers have proposed and developed solutions to analyze the environment and to alert the user if a situation is evaluated dangerous. While seeking technical solutions, the concerns of the users are usually not addressed. With our studies we put the needs of the user into focus and investigated the acceptance, potential dangers, events to be warned about, type of warning, reaction time and legal regulations.
Melinda C. Braun, Sandra Beuck, Matthias Wölfel, Alexander Scheurer
EEG-Based Mental Workload and Stress Monitoring of Crew Members in Maritime Virtual Simulator

Many studies have shown that most maritime accidents are attributed to human error as the initiating cause, resulting in a need for study of human factors to improve safety in maritime transportation. Among the various techniques, Electroencephalography (EEG) has the key advantage of high time resolution, with the possibility to continuously monitor brain states including human mental workload, emotions, stress levels, etc. In this paper, we proposed a novel mental workload recognition algorithm using deep learning techniques that outperformed the state-of art algorithms and successfully applied it to monitor crew members’ brain states in a maritime simulator. We designed and carried out an experiment to collect the EEG data, which was used to study stress and distribution of mental workload among crew members during collaborative tasks in the ship’s bridge simulator. The experiment consisted of two parts. In part 1, 3 maritime trainees fulfilled the tasks with and without an experienced captain. The results of EEG analyses showed that 2 out of 3 trainees had less workload and stress when the experienced captain was present. In part 2, 4 maritime trainees collaborated with each other in the simulator. Our findings showed that the trainee who acted as the captain had the highest stress and workload levels while the other three trainees experienced low workload and stress due to the shared work and responsibility. These results suggest that EEG is a promising evaluation tool applicable in human factors study for the maritime domain.

Wei Lun Lim, Yisi Liu, Salem Chandrasekaran Harihara Subramaniam, Serene Hui Ping Liew, Gopala Krishnan, Olga Sourina, Dimitrios Konovessis, Hock Eng Ang, Lipo Wang
An Approach for Detecting Web Defacement with Self-healing Capabilities
Websites have become a form of information distribution; usage of websites has seen a significant rise in the amount of information circulated on the Internet. Some businesses have created websites that display services the business renders or information about that particular product; businesses make use of the Internet to expand business opportunities or advertise the services they render on a global scale. This does not only apply to businesses. Other entities such as celebrities, socialites, bloggers and vloggers are using the Internet to expand personal or business opportunities too. These entities make use of websites that are hosted by a web host. The contents of the website is stored on a web server. However, not all websites undergo penetration testing which leads to them being vulnerable. Penetration testing is a costly exercise that most companies or website owners find they cannot afford. With web defacement still one of the most common attacks on websites, these attacks aim at altering the content of the web pages or to make the website inactive. This paper proposes a Web Defacement and Intrusion Monitoring Tool that could be a possible solution to the rapid identification of altered or deleted web pages. The proposed tool has web defacement detection capabilities that may be used for intrusion detection as well. The proposed solution will also be used to regenerate the original content of a website, after the website has been defaced.
Mfundo Masango, Francois Mouton, Palesa Antony, Bokang Mangoale
Assessing Opinions on Software as a Weapon in the Context of (Inter)national Security
Modern life is permeated by software which provides a large attack surface, ranging from generic, low impact malware attacks, to sophistically created and targeted code touted as a next generation of weapons. Although some research on this broad area of cyber weapons exists, the solicitation of public opinion through surveys is lacking. A questionnaire was conducted on the attitudes towards Software as a Weapon (SaaW), with this article presenting further results, linking traditional aspects of weapons to the understanding of, and differences between, software and malware in context of international security. The results suggest that there is a statistically significant difference between respondents in the Military, Academia, or Other professions concerning questions of capabilities, and the demise of the state-centric model. Furthermore, factor analyses identified eight dimensions in our questionnaire. Comparison of these across the three groups revealed significant differences in how peoples’ background influenced their perception concerning the nature, intent, and potential of software and malware to be used as a weapon. Finally, using text-mining, we present the words frequently used to describe malware, software, and weapons, and provide an interpretation for overlap between constructs.
Jantje A. M. Silomon, Mark Patrick Roeling
OpenGL|D - An Alternative Approach to Multi-user Architecture

Synchronising state between multiple connected clients can be a challenging task. However, the need to carry this out is becoming much greater as a larger number of software packages are becoming collaborative across a network. Online multiplayer games in particular are already extremely popular but the synchronisation methods and architecture have largely remained the same. OpenGL|Distributed, presented here, aims to provide not only an alternative to this architecture allowing for a greatly simplified development pipeline, but also the opportunity for a number of additional features and design patterns. The architecture provided by OpenGL|D is such that no state information needs to be transferred between clients. Instead, the OpenGL API has been utilised as a platform agnostic protocol. This means that graphical calls can be streamed to each client rather than relying on manual synchronisation of application domain specific data. Initial test results are discussed, including performance evaluation using data from a number of small prototypes developed within a constrained 48-h timeframe. These results are compared and evaluated against a more traditional approach to network multiplayer by id Software’s QuakeWorld client. It should be noted that this article is an extended version of the work we published in the proceedings of the Cyberworlds 2017 conference [1].

Karsten Pedersen, Christos Gatzidis, Wen Tang
Image Quality-Based Illumination-Invariant Face Recognition
Quality of biometric samples has a significant impact on the accuracy of a biometric recognition system. Various quality factors, such as different lighting conditions, occlusion, and variations in pose and expression may affect an automated face recognition system. One of the most challenging issues in automated face recognition is intra-class variations introduced by the varied facial quality due to the variation in illumination conditions. In this paper, we proposed an adaptive discrete wavelet transform (DWT) based face recognition approach which will normalize the illumination distortion using quality-based normalization approaches. The DWT based approach is used to extract the low and high frequency sub-bands for representing the facial features. In the proposed method, a weighted fusion of the low and high frequency sub-bands is computed to improve the identification accuracy under varying lighting conditions. The selection of fusion parameters is made using fuzzy membership functions. The performance of the proposed method was validated on the Extended Yale Database B. Experimental result shows that the proposed method outperforms some well-known face recognition approaches.
Fatema Tuz Zohra, Marina Gavrilova
Synthesizing Imagined Faces Based on Relevance Feedback
In this paper, we propose a user-friendly system that can create a facial image from a corresponding image in the user’s mind. Unlike most of the existing methods, which require a sketch as input or the tedious work of selecting similar facial components from an example database, our method can synthesise a satisfying result without questioning the user on the explicit features of the face in his or her mind. Through a dialogic approach based on a relevance feedback strategy to translate facial features into input, the user only needs to look at several candidate face images and judge whether each image resembles the face that he or she is imagining. A set of sample face images that are based on users’ feedbacks are used to dynamically train an Optimum-Path Forest algorithm to classify the relevance of face images. Based on the trained Optimum-Path Forest classifier, candidate face images that best reflect the user’s feedback are retrieved and interpolated to synthesise new face images that are similar to those the user had imagined. The experimental results show that the proposed technique succeeded in generating images resembling a face a user had imagined or memorised.
Caie Xu, Shota Fushimi, Masahiro Toyoura, Jiayi Xu, Xiaoyang Mao
NeuroFeedback Training for Enhancement of the Focused Attention Related to Athletic Performance in Elite Rifle Shooters
NeuroFeedback Training (NFT) is a type of biofeedback training using Electroencephalogram (EEG) that allows the subjects to do self-regulation during the training according to their real-time brain activities. The purpose of this study is to optimize focused attention in expert rifle shooters with the use of NFT tools and to enhance shooting performance. We designed and implemented an experiment, conducted NFT sessions, and confirmed that NFT can boost performance of the shooters. The efficiency of the NFT was examined by comparing the shooters’ performance, their results of standardized tests of general cognitive abilities on the Vienna Test System (VTS), and the brain patterns in before and after NFT sessions. According to the results, we confirmed that NFT can be used to boost the shooters’ performance. EEG data were recorded during the shooting tasks. We extracted different types of EEG-based indexes and identified the emotion and mental workload levels of the shooters right before they pulled the trigger. These indexes and emotion/workload levels were then correlated with the shooting scores to understand what are the optimal brain states for “good” shots. According to the results, we confirmed that (1) mental workload level is negatively correlated with the shooting performance; (2) the correlations analyses results between EEG-based power features and shooting performance are consistent with the literature review results; (3) the difference of brain states in the before and after NFT shooting session could be because of NFT.
Yisi Liu, Salem Chandrasekaran Harihara Subramaniam, Olga Sourina, Eesha Shah, Joshua Chua, Kirill Ivanov
Transactions on Computational Science XXXII
herausgegeben von
Prof. Marina L. Gavrilova
C.J. Kenneth Tan
Prof. Alexei Sourin
Springer Berlin Heidelberg
Electronic ISBN
Print ISBN

Premium Partner