𝑱𝒐𝒖𝒓𝒏𝒂𝒍 𝒐𝒇 𝑪𝒐𝒎𝒑𝒖𝒕𝒆𝒓 𝑺𝒄𝒊𝒆𝒏𝒄𝒆 𝑹𝒆𝒔𝒆𝒂𝒓𝒄𝒉 | 𝑽𝒐𝒍.4, 𝑰𝒔𝒔.1
Abstract
Machine learning algorithms have been deployed in numerous optimization, prediction and classification problems. This has endeared them for application in fields such as computer networks and medical diagnosis. Although these machine learning algorithms achieve convincing results in these fields, they face numerous challenges when deployed on imbalanced dataset. Consequently, these algorithms are often biased towards majority class, hence unable to generalize the learning process. In addition, they are unable to effectively deal with high-dimensional datasets. Moreover, the utilization of conventional feature selection techniques from a dataset based on attribute significance render them ineffective for majority of the diagnosis applications. In this paper, feature selection is executed using the more effective Neighbour Components Analysis (NCA). During the classification process, an ensemble classifier comprising of K-Nearest Neighbours (KNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) is built, trained and tested. Finally, cross validation is carried out to evaluate the developed ensemble model. The results shows that the proposed classifier has the best performance in terms of precision, recall, F-measure and classification accuracy.
Keywords
Full Text:
PDF
Abstract
The paper seeks to demonstrates the likelihood of embedding a 3D gaze point on a 3D visual field, the visual field is inform of a game console where the user has to play from one level to the other by overcoming obstacles that will lead them to the next level. Complex game interface is sometimes difficult for the player to progress to next level of the game and the developers also find it difficult to regulate the game for an average player. The model serves as an analytical tool for game adaptations and also players can track their response to the game. Custom eye tracking and 3D object tracking algorithms were developed to enhance the analysis of the procedure. This is a part of the contributions to user interface design in the aspect of visual transparency. The development and testing of human computer interaction uses and application is more easily investigated than ever, part of the contribution to this is the embedding of 3-D gaze point on a 3-D visual field. This could be used in a number of applications, for instance in medical applications that includes long and short sightedness diagnosis and treatment. Experiments and Test were conducted on five different episodes of user attributes, result show that fixation points and pupil changes are the two most likely user attributes that contributes most significantly in the performance of the custom eye tracking algorithm the study. As the advancement in development of eye movement algorithm continues user attributes that showed the least likely appearance will prove to be redundant.
Keywords
Full Text:
PDF
Abstract
Mobile devices are being deployed rapidly for both private and professional reasons. One area of that has been growing is in releasing healthcare applications into the mobile marketplaces for health management. These applications help individuals track their own biorhythms and contain sensitive information. This case study examines the source code of mobile applications released to GitHub for the Risk of Insufficient Cryptography in the Top Ten Mobile Open Web Application Security Project risks. We first develop and justify a mobile OWASP Cryptographic knowledgegraph for detecting security weaknesses specific to mobile applications which can be extended to other domains involving cryptography. We then analyze the source code of 203 open source healthcare mobile applications and report on their usage of cryptography in the applications. Our findings show that none of the open source healthcare applications correctly applied cryptography in all elements of their applications. As humans adopt healthcare applications for managing their health routines, it is essential that they consider the privacy and security risks they are accepting when sharing their data. Furthermore, many open source applications and developers have certain environmental parameters which do not mandate adherence to regulations. In addition to creating new free tools for security risk identifications during software development such as standalone or compiler-embedded, the article suggests awareness and training modules for developers prior to marketplace software release.
Keywords
Full Text:
PDF
Abstract
Keywords
Full Text:
PDF
Abstract
Keywords
Full Text:
PDF
Comments
Post a Comment