Rytis Maskeliūnas

Smartphone User Identity Verification Using Gait Characteristics

Smartphone-based biometrics offers a wide range of possible solutions, which could be used to authenticate users and thus to provide an extra level of security and theft prevention. We propose a method for positive identification of smartphone user’s identity using user’s gait characteristics captured by embedded smartphone sensors (gyroscopes, accelerometers). The method is based on the application of the Random Projections method for feature dimensionality reduction to just two dimensions. Then, a probability distribution function (PDF) of derived features is calculated, which is compared against known user PDF. The Jaccard distance is used to evaluate distance between two distributions, and the decision is taken based on thresholding. The results for subject recognition are at an acceptable level: we have achieved a grand mean Equal Error Rate (ERR) for subject identification of 5.7% (using the USC-HAD dataset). Our findings represent a step towards improving the performance of gait-based user identity verification technologies.

Gender, Age, Colour, Position and Stress: How They Influence Attention at Workplace?

We explore the relationship between attention and action, and focus on human reaction to stress in the Supervisory Control and Data Acquisition (SCADA) based Human Computer Interface (HCI) environment aiming to measure the reaction time and warn against attention deficit. To provoke human reaction we simulate several provocative situations mimicking real-world accidents while working on the industrial production line. During the simulation of the industrial line control, the subjects are presented on screen with affective visual stimuli imitating the possible accident and the reaction of subjects is tracked with a gaze tracker. We measure a subjects’ response time from stimuli onset to the eye fixation (gaze time) and to the pressing of “line stop” button (press time). The reaction time patterns are analysed with respect to subject’s gender, age, colour and position of stop sign. The results confirm the significance of gender, age, sign colour and position factors.

User adaptive text predictor for mentally disabled Huntington's patients

This paper describes in detail the design of the specialized text predictor for patients with Huntingtons disease. The main aim of the specialized text predictor is to improve the text input rate by limiting the phrases that the user can type in. We show that such specialized predictor can significantly improve text input rate compared to a standard general purpose text predictor. Specialized text predictor, however, makes it more difficult for the user to express his own ideas. We further improved the text predictor by using the sematic database to extract synonym, hypernym, and hyponym terms for the words that are not present in the training data of the specialized text predictor. This data can then be used to compute reasonable predictions for words that are originally not known to the text predictor.

A Lightweight Protocol for Secure Video Streaming

The Internet of Things (IoT) introduces many new challenges which cannot be solved using traditional cloud and host computing models. A new architecture known as fog computing is emerging to address these technological and security gaps. Traditional security paradigms focused on providing perimeter-based protections and client/server point to point protocols (e.g., Transport Layer Security (TLS)) are no longer the best choices for addressing new security challenges in fog computing end devices, where energy and computational resources are limited. In this paper, we present a lightweight secure streaming protocol for the fog computing “Fog Node-End Device” layer. This protocol is lightweight, connectionless, supports broadcast and multicast operations, and is able to provide data source authentication, data integrity, and confidentiality. The protocol is based on simple and energy efficient cryptographic methods, such as Hash Message Authentication Codes (HMAC) and symmetrical ciphers, and uses modified User Datagram Protocol (UDP) packets to embed authentication data into streaming data. Data redundancy could be added to improve reliability in lossy networks. The experimental results summarized in this paper confirm that the proposed method efficiently uses energy and computational resources and at the same time provides security properties on par with the Datagram TLS (DTLS) standard.

Combining Cryptography with EEG Biometrics

Cryptographic frameworks depend on key sharing for ensuring security of data. While the keys in cryptographic frameworks must be correctly reproducible and not unequivocally connected to the identity of a user, in biometric frameworks this is different. Joining cryptography techniques with biometrics can solve these issues. We present a biometric authentication method based on the discrete logarithm problem and Bose-Chaudhuri-Hocquenghem (BCH) codes, perform its security analysis, and demonstrate its security characteristics. We evaluate a biometric cryptosystem using our own dataset of electroencephalography (EEG) data collected from 42 subjects. The experimental results show that the described biometric user authentication system is effective, achieving an Equal Error Rate (ERR) of 0.024.

Developing a Calorie Counter Fitness App for Smartphones

A number of mobile fitness devices as well as smart watches have emerged on the technology landscape. However, the rate of adoption of these devices is still low especially in developing countries with a teeming population. On the other hand, smart phones are becoming ubiquitous given their steady price decline. To this end, the present study aims to leverage the smartphone platform by developing a smart phone fitness app that tracks the calories burnt by individuals who go about their daily activities while carrying their smart phones with them. In order to achieve this, the design specification for the application was done using Unified Modeling Language diagrams such as use case diagrams and sequence diagrams. This was then implemented using the following tools: Angular - a JavaScript framework and Ionic - a hybrid framework that was hosted via the Heroku Cloud Application Platform. The initial results show that the app can gain traction in terms of its adoption given the fact that it is cheaper to download the app than buy a new smart watch for the same purpose.

Investigation of Predicting Functional Capacity Level for Huntington Disease Patients

This paper introduces a model to forecast functional capacity level for people having disorders such as hand tremors, disturbed balance, involuntary movements, chorea etc. These motor features are very closely related the symptoms occurring for Huntington or Parkinson patients in various stages of the disease. Proposed model is designed by applying one of supervised learning artificial neural network models for data collected with smart phones or tablets. Feed-forward backpropagation (FFBP), feed-forward time delay neural network (FFTDNN), cascade forward backpropagation (CFBP), nonlinear autoregressive exogenous model (NARX), Elman, layer recurrent neural network (RNN) and generalized regression neural network (GRNN) were used in investigation. Moreover, the processes of preparing and labeling data, choosing a learning algorithm, training particular neural network, evaluating and comparing each model performance, making predictions on new data, are described in the paper.

Comparative Evaluation of Mobile Forensic Tools

The rapid rise in the technology today has brought to limelight mobile devices which are now being used as a tool to commit crime. Therefore, proper steps need to be ensured for Confidentiality, Integrity, Authenticity and legal acquisition of any form of digital evidence from the mobile devices. This study evaluates some mobile forensic tools that were developed mainly for mobile devices memory and SIM cards. An experiment was designed with five android phones with different Operating System. Four tools were used to find out the capability and efficiency of the tools when used on the sampled phones. This would help the forensic investigator to know the type of tools that will be suitable for each phone to be investigated for acquiring digital evidence. The evaluation result showed that AccessData FTK imager and Paraben device seizure performs better than Encase and Mobiledit. The experimental result shows that, Encase could detect the unallocated space on the mobile deice but could retrieve an deleted data.

A Fuzzy Classifier-Based Penetration Testing for Web Applications

The biggest challenge of Web application is the inestimable losses arising from security flaws. Two approaches were advanced by a number of scholars to provide security to Web space. One of such approach is vulnerability assessment, which is a conscious effort to isolate, identify and recognize potentials vulnerabilities exploited by attackers. The second being the estimation and determination of level of risks/threats posed to Web applications by vulnerabilities obvious to the developer (or tester); this is generally referred to as penetration testing. Recently, there is Vulnerability Assessment and Penetration Testing (VAPT) that combined these two schemes to improve safety and effectively combat the menace of attackers on Web applications. This paper proposed Fuzzy Classifier-based Vulnerability and Assessment Testing (FCVAPT) model to provide security for sensitive data/information in Web applications. Cross Site Scripting (XSS) and Structured Query Language (SQL) injections were selected for evaluation of proposed FCVAPT model. FCVAPT model’s classification performance for MSE, MAPE and RMSE were 33.33, 14.81% and 5.77% respectively. FCVAPT is considerably effective for detecting vulnerability and ascertaining the nature of threats/risks available to Web applications.

Cloud Based Simple Employee Management Information System: A Model for African Small and Medium Enterprises

Cloud computing is gradually becoming accepted in different sectors and businesses are beginning to adopt the concept’s shared infrastructure and applications. The aim of this paper is to design and implement a simple prototype of a cloud based application for SMEs to manage their human resources challenges. The choice of an Employee Information Management System (EIMS) is due to the fact that one of the basic challenges of SMEs is human resource management and how to effectively manage employee information. The prototype developed in this study is targeted at the Software as a Service (SaaS) layer of the cloud framework. It leverages on existing cloud platform providers to deliver four core modules, which include: payroll management, record management, leave management and staff appraisal. Among the things this study seeks to achieve is a cheaper and cost effective solution to some basic issues affecting human resource management in SMEs.