5 results
Search Results
Now showing 1 - 5 of 5
Article Citation - WoS: 23Citation - Scopus: 30Secure Ear Biometrics Using Circular Kernel Principal Component Analysis, Chebyshev Transform Hashing and Bose-Chaudhuri Error-Correcting Codes(Springer London Ltd, 2020) Olanrewaju, L.; Oyebiyi, Oyediran; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, RobertasEar biometrics has generated an increased interest in the domain of biometric identification systems due to its robustness and covert acquisition potential. The external structure of the human ear has a bilateral symmetry structure. Here, we analyse ear biometrics based on ear symmetry features. We apply iterative closest point and kernel principal component analysis with circular kernel for feature extraction while using a circular kernel function, combined with empirical mode decomposition into intrinsic mode functions perceptual hashing using and fast Chebyshev transform, and a secure authentication approach that exploits the discrete logarithm problem and Bose-Chaudhuri-Hocquenghem error-correcting codes to generate 128-bit crypto keys. We evaluate the proposed ear biometric cryptosecurity system using our data set of ear images acquired from 103 persons. Our results show that the ear biometric-based authentication achieved an equal error rate of 0.13 and true positive rate TPR of 0.85.Review Citation - WoS: 16Citation - Scopus: 28A Systematic Literature Review on Compliance Requirements Management of Business Processes(Springer india, 2020) Mustapha, A. M.; Arogundade, O. T.; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, RytisOne crucial aspect that had cost business organizations so much is management of compliance requirements from various regulatory sources. In a bid to avoid being penalized, some organizations have adopted various techniques to accomplish this task. However, literature revealed that few thorough reviews have been centered on this subject in a systematic way. This implies that a review that systematically captured the entire crucial elements such as implementation environment, constraints types addressed, main contributions and strengths of the existing techniques is missing. This has led to the lack of sufficiently good context of operation. A systematic review on existing literatures is presented in this paper, which focuses on the management of business process compliance requirements in order to present summarized evidences and provide a lead-up for appropriately positioning new research activities. The guideline for conducting systematic literature review in software engineering by Kitchenham was employed in carrying out the systematic review as well as a review planning template to execute the review. Results showed that control flow and data flow requirements have been addressed most in recent time. The temporal and resource allocation requirements have been under researched. The approaches that have been employed in business process compliance requirements management are model checking, patterns, semantic, formal, ontology, goal-based requirements analysis and network analysis. The traditional business environment has been put into consideration more than the cloud environment. The summary of research contributions revealed that the approaches have been more of formal techniques compared to model checking and semantics. This shows that there is a need for more research on business process compliance that will be centered on the cloud environment. Researchers will be able to suggest the technique to be adopted based on the combined importance of each criterion that was defined in this work.Article Citation - Scopus: 4Attitude of Mobile Telecommunication Subscribers Towards Sim Card Registration in Lagos State, Southwestern Nigeria(Springer india, 2019) Oyediran, O.; Omoshule, A.; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, RobertasDespite the concerted effort of the Nigeria Communication Commission (NCC) to ensure that Nigeria mobile phone subscribers register their SIM cards, there has been some level of apathy on the part of the mobile phone subscribers. This study investigated the attitude of mobile telecommunication subscribers towards SIM card registration in Lagos Metropolis, Nigeria. The theories of planned behaviour and reasoned action were adapted for the study because they provide the necessary constructs that help to investigate the attitudes of telecommunication subscribers. The purposive sampling technique was adopted in selecting five local government areas within Lagos. Random sampling method was used to select 300 mobile phone subscribers. In total, 290 responses were collected and were found usable. Data analysis was performed using statistical methods, and Spearman's correlation analysis was used to test relationship between the variables of interest. The results of the study revealed that SIM card users have positive attitude towards SIM card registration. Perceived usefulness and perceived ease of use significantly influenced subscribers attitude towards SIM card registration with both of them having negative significant relationship with attitude towards registration (r = -.116, r = -.132, p < 0.05) respectively.Article Citation - WoS: 17Citation - Scopus: 30Comparative Study of Real Time Machine Learning Models for Stock Prediction Through Streaming Data(Graz Univ Technolgoy, inst information Systems Computer Media-iicm, 2020) Behera, Ranjan Kumar; Das, Sushree; Rath, Santanu Kumar; Misra, Sanjay; Damasevicius, Robertas; Computer EngineeringStock prediction is one of the emerging applications in the field of data science which help the companies to make better decision strategy. Machine learning models play a vital role in the field of prediction. In this paper, we have proposed various machine learning models which predicts the stock price from the real-time streaming data. Streaming data has been a potential source for real-time prediction which deals with continuous flow of data having information from various sources like social networking websites, server logs, mobile phone applications, trading floors etc. We have adopted the distributed platform, Spark to analyze the streaming data collected from two different sources as represented in two case studies in this paper. The first case study is based on stock prediction from the historical data collected from Google finance websites through NodeJs and the second one is based on the sentiment analysis of Twitter collected through Twitter API available in Stanford NLP package. Several researches have been made in developing models for stock prediction based on static data. In this work, an effort has been made to develop scalable, fault tolerant models for stock prediction from the real-time streaming data. The Proposed model is based on a distributed architecture known as Lambda architecture. The extensive comparison is made between actual and predicted output for different machine learning models. Support vector regression is found to have better accuracy as compared to other models. The historical data is considered as a ground truth data for validation.Article Citation - WoS: 55Citation - Scopus: 105Windows Pe Malware Detection Using Ensemble Learning(Mdpi, 2021) Azeez, Nureni Ayofe; Odufuwa, Oluwanifise Ebunoluwa; Misra, Sanjay; Oluranti, Jonathan; Damasevicius, RobertasIn this Internet age, there are increasingly many threats to the security and safety of users daily. One of such threats is malicious software otherwise known as malware (ransomware, Trojans, viruses, etc.). The effect of this threat can lead to loss or malicious replacement of important information (such as bank account details, etc.). Malware creators have been able to bypass traditional methods of malware detection, which can be time-consuming and unreliable for unknown malware. This motivates the need for intelligent ways to detect malware, especially new malware which have not been evaluated or studied before. Machine learning provides an intelligent way to detect malware and comprises two stages: feature extraction and classification. This study suggests an ensemble learning-based method for malware detection. The base stage classification is done by a stacked ensemble of fully-connected and one-dimensional convolutional neural networks (CNNs), whereas the end-stage classification is done by a machine learning algorithm. For a meta-learner, we analyzed and compared 15 machine learning classifiers. For comparison, five machine learning algorithms were used: naive Bayes, decision tree, random forest, gradient boosting, and AdaBoosting. The results of experiments made on the Windows Portable Executable (PE) malware dataset are presented. The best results were obtained by an ensemble of seven neural networks and the ExtraTrees classifier as a final-stage classifier.
