{"title":"Skin Cancer Detection from Macroscopic Images","authors":"Verosha Pillay, Serestina Viriri","doi":"10.1109/ICTAS.2019.8703611","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703611","url":null,"abstract":"Automatic diagnosis of skin cancer images is especially difficult in medical image processing. Moreover, proper segmentation is crucial for the partitioning of growths from the skin, which can aid in the differentiation between melanoma and benign skin lesions. To address these issues, this research work investigates the widely used ABCD rule (Asymmetry, Border Irregularity, Colour and Diameter) on macroscopic images and the Graph-Cut segmentation technique as it demonstrates capabilities for handling extremely textured, noisy and colour images which are present in macroscopic images. The accuracy rates achieved by the proposed model with the use of the TDS (Total Dermoscopy Score) classifier is 73,529%, SVM is 75,294% and KNN classifier is 74,706%.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115700152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Agile UX: Integrating good UX development practices in Agile","authors":"Narendren Pillay, J. Wing","doi":"10.1109/ICTAS.2019.8703607","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703607","url":null,"abstract":"This paper explores a framework for the integration of User Experience (UX) in Agile within the South African context. For this study, grounded theory was applied as a suitable qualitative method to determine how the integration of UX into Agile is carried out in practice. The data was collected using semi-structured interviews with professionals working in an Agile/UX environment in South Africa. Further data was collected using questionnaires in order to promote validity and reliability with more information from more participants. The themes that emerged from the study shows that there is an increasing need for UX in software development amongst Agile teams. The findings were used to design a framework to facilitate the integration of UX into Agile.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130271220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Local Descriptors Parameter characterization with Fisher vectors for remote sensing images","authors":"Ronald Tombe, Serestina Viriri","doi":"10.1109/ICTAS.2019.8703623","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703623","url":null,"abstract":"Satellite technology yield huge quantities of high spatial resolution(HSR) images periodically. The HSR type of data is complex in its spatial arrangement with high intraclass and low interclass variability. Remote sensing images scene classification is a challenging task due high inter and intra class variations due to diverse scene contents, induced noise as a resultant of changes in illuminations, differing scales and rotations of images. Consequently, no one-specific image descriptor algorithm is effective to characterize scene image-semantics for accurate classification. This research employ Fisher vector to characterize parameters of local descriptors i.e. Local Ternary Patterns (LBPs) and Hu Moments to a high fisher-vector-feature-representation that is more discriminative for remote sensing image scene classification. Support Vector Machine Classifier is implemented to validate the result. Overall results of 52.29 is achieved using the proposed strategy show a significant improvement compared to individual image descriptor algorithms in literature.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124539049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Guidelines for Secure Cloud-Based Personal Health Records","authors":"Avuya Mxoli, N. Mostert, M. Gerber","doi":"10.1109/ICTAS.2019.8703524","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703524","url":null,"abstract":"Traditionally, health records have been stored in paper folders at the physician's consulting rooms – or at the patient's home. With the rise of technology there have been many offerings of ways to store health records in a safer and better way by using Personal Health Records (PHRs). Web-based PHRs are stored in various ways including the use of Cloud computing. This brings numerous benefits including accessibility and efficiency but there are also privacy and security concerns. This paper proposes guidelines that can assist PHR providers in choosing a Cloud Service Provider that will store PHRs in a secure manner.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123295875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reducing Zapping Delay in Internet Protocol Television Using a Hybrid Modular Method","authors":"Timothy T. Adeliyi, O. Olugbara","doi":"10.1109/ICTAS.2019.8703627","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703627","url":null,"abstract":"Internet protocol television (IPTV) has revolutionized the media and telecommunication industries by providing a platform for transmitting digitized television services across the internet protocol infrastructure. However, zapping delay is a critical hiccup that deters the switching intention of terrestrial subscribers and widespread adoption of IPTV services. Subscribers often experience this hiccup in IPTV when switching channels, which makes subscribers wait for several seconds before the desired channel is found and made available. An important information may elude a subscriber during the waiting time. This research develops a hybrid modular method that takes the advantages provided at the subscriber level and network level to help reduce zapping delay hiccup in IPTV. The validation of the method has proved that it is indeed possible to reduce zapping delay in IPTV to the barest minimum over a converged network.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125842196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reliable Internet of Things Network Architecture Based on High Altitude Platforms","authors":"S. Sibiya, O. Olugbara","doi":"10.1109/ICTAS.2019.8703519","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703519","url":null,"abstract":"Internet of Things (IoT) has become a hot topic of technical, social and economic significance in recent times. Projections on its impact are highly impressive, where over 100 billion of devices have been projected to be IoT connected with a global economic impact of more than $11 trillion by 2025. In this paper, we propose a reliable IoT network architecture based on high altitude platforms as an alternative standalone network that is well-positioned to provide seamless connectivity and coverage in remote areas. Potential applications of the proposed IoT network architecture are demonstrated in smart cities, healthcare, logistics, finance, agriculture and construction.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127192259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Implementation of Current Capacitance Resonant Circuit to Monitor Telecommunication and Utility Cable Tampering","authors":"Patrick Mabadie, M. Odhiambo","doi":"10.1109/ICTAS.2019.8703615","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703615","url":null,"abstract":"The telecommunication and utility cable tamper monitoring system was implemented to detect cable tampering. Cable tampering occurs although methods have been developed, to solve, mitigate and decrease cable tampering cases such as cable tampering prevention campaigns at the national and international levels. The objective of the research was to design and implement a cable monitoring system that would detect an anomaly, such as cable theft and report Global Positioning System (GPS) coordinates at which cable tampering took place. The system is an improvement on the traditional cable anti-theft monitoring system, based on tracking resonance signal frequency. The system incorporates a sensing circuit which detects a change in the capacitance value of the cable and converts it into an equivalent frequency value, Field-programable Gate Array (FPGA) board is utilized to convert the frequency into the distance from sensor of cable at which tampering took place. After detecting an anomaly on the cable, the system gives an output divided into two parts which are the display mode and the messaging mode. For display mode, the system uses a Crystal Display (LCD) to display the GPS coordinates of the location where the cable tampering took place and the distance from sensor of the cable where tampering took place. In the messaging mode, the FPGA activates the Global System for Mobile Communication (GSM) module and the module sends alert message to the user when the cable is tampered with.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126287616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Four I-s of E-skills","authors":"S. Soobramoney, D. Heukelman","doi":"10.1109/ICTAS.2019.8703618","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703618","url":null,"abstract":"Nationwide E-inclusion is yet to be realised in many countries, which could explain the E-skills diversities that exist in the workplace and amongst university students. Literature confirms the existence of E-skills diversity however fails to provide a comprehensive solution. Rapid E-learning adoption in South African universities make additional demands on first year students to use technology for learning, hence clear direction on how to address E-skill diversity is critical for university students' success. A longitudinal case study of sixteen undergraduate first year students with diverse E-skill levels was conducted to gather qualitative data needed to understand how using E-learning could contribute towards improving students' E-skills capabilities. Focus group interviews and course assessments were used to gather data from participants and Straussian-grounded-theory methods were employed to ensure rigorous, structured analysis of student experiences with technology and related E-skill development. Emerging categories show that diversity may be addressed by introducing carefully designed incrementally complex E-learning tasks, complemented by instructor interventions, beginning with instruction, then involvement, thereafter facilitating interaction and finally encouraging independence to stimulate E-skill development from fundamental to strategic levels.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123537285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Identifying Students At-Risk with an Ensemble of Machine Learning Algorithms","authors":"Ranjin Soobramoney, Alveen Singh","doi":"10.1109/ICTAS.2019.8703616","DOIUrl":"https://doi.org/10.1109/ICTAS.2019.8703616","url":null,"abstract":"Accurately predicting the academic performance of students is an important process for the long term sustainability of higher education institutions (HEIs). A reliable and timely identification of students at-risk will enable HEIs to take proactive measures to assist these students. Owing to large student numbers with varying backgrounds, identifying students at-risk is often primarily a manual process involving an analysis of students' prior academic results and little else. While prior academic results do play an important role in indentifying students at-risk, there could be several other factors that may be overlooked. The demographic and financial circumstances of the student for instance could play a key role in more accurately identifying students at-risk. It may be impractical to consider all of these factors when manually trying to identify students at-risk. We propose that classification models using an ensemble of machine learning algorithms (MLAs) have promising prospects to more effectively predict students at-risk by including several factors that may often not even be practical with manual methods.","PeriodicalId":386209,"journal":{"name":"2019 Conference on Information Communications Technology and Society (ICTAS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123745594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}