2022 3rd International Conference on Next Generation Computing Applications (NextComp)最新文献

{"title":"Classification of artefacts in endoscopic images using deep neural network","authors":"Muhammad Muzzammil Auzine, Preeti Bissoonauth-Daiboo, Maleika Heenaye-Mamode Khan, S. Baichoo, Xiaohong W. Gao, Nuzhah Gooda Sahib","doi":"10.1109/NextComp55567.2022.9932202","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932202","url":null,"abstract":"Early cancer diagnosis by endoscopy is a challenging and time challenging process in the medical field thus requiring endoscopists to first acquire substantial experience and good technique. In addition, the presence of artefacts like saturation, bubbles and blood among others during the endoscopic process, are often misinterpreted as lesions leading to the wrong diagnosis and treatment. Lately, we have witnessed how the intervention of medical imaging with convolution neural networks (CNN) have brought promising results in medical applications. Therefore, we have applied deep neural networks to detect and classify artefacts, which interfere with the diagnosis of gastric cancer. Training CNN models from scratch require considerable number of labelled dataset, which is not usually available in the medical field. Thus, we have performed data augmentation on the EAD 2019 and Kvasir-V2 dataset leading to a total of 9852 images for six classes of artefacts. We then applied transfer learning using three pretrained neural network architectures namely: InceptionV3, InceptionResNetV2 and VGG16. The weights of the models are updated accordingly. The models are enhanced using Adam Optimisation and by varying the learning rates. We achieved a testing accuracy of 68.15 % with the original dataset trained by the InceptionResnetV2 model and 77.65% with the augmented dataset trained by the InceptionV3 models. Our experiments show the effectiveness of using CNN to detect artifacts during endoscopic procedures.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124403074","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":"Cyber threat intelligence enabled automated attack incident response","authors":"F. Kaiser, Leon J. Andris, Tim F. Tennig, Jonas M. Iser, M. Wiens, F. Schultmann","doi":"10.1109/NextComp55567.2022.9932254","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932254","url":null,"abstract":"Cyber attacks keep states, companies and individuals at bay, draining precious resources including time, money, and reputation. Attackers thereby seem to have a first mover advantage leading to a dynamic defender attacker game. Automated approaches taking advantage of Cyber Threat Intelligence on past attacks bear the potential to empower security professionals and hence increase cyber security. Consistently, there has been a lot of research on automated approaches in cyber risk management including works on predictive attack algorithms and threat hunting. Combining data on countermeasures from “MITRE Detection, Denial, and Disruption Framework Empowering Network Defense” and adversarial data from “MITRE Adversarial Tactics, Techniques and Common Knowledge” this work aims at developing methods that enable highly precise and efficient automatic incident response. We introduce Attack Incident Responder, a methodology working with simple heuristics to find the most efficient sets of counter-measures for hypothesized attacks. By doing so, the work contributes to narrowing the attackers first mover advantage. Experimental results are promising high average precisions in predicting effiective defenses when using the methodology. In addition, we compare the proposed defense measures against a static set of defensive techniques offering robust security against observed attacks. Furthermore, we combine the approach of automated incidence response to an approach for threat hunting enabling full automation of security operation centers. By this means, we define a threshold in the precision of attack hypothesis generation that must be met for predictive defense algorithms to outperform the baseline. The calculated threshold can be used to evaluate attack hypothesis generation algorithms. The presented methodology for automated incident response may be a valuable support for information security professionals. Last, the work elaborates on the combination of static base defense with adaptive incidence response for generating a bio-inspired artificial immune system for computerized networks.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125311630","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":"Expert Views on Value Alignment for Stakeholders in Smart Cities","authors":"A. Hoogen, B. Scholtz, A. Calitz","doi":"10.1109/NextComp55567.2022.9932248","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932248","url":null,"abstract":"Smart City initiatives are critical in the digital information society. However, citizens and the value they receive from these initiatives are not being considered, particularly in developing countries where the digital divide is growing bigger in a post-Covid-19 society. The purpose of this paper is to report on an empirical validation of the Value Alignment Smart City Stakeholder (VASCS) model that was conducted using an expert review approach. The model was designed in a previous study using a systematic literature review and the conceptual framework analysis method. This paper presents the findings, which revealed interesting worldviews from the international experts about what makes cities smart. The expert review was conducted successfully and it validated the model with some minor recommendations suggested for improvement. The model can be used by practitioners and researchers to guide Smart City initiatives with the aim of improving the social lives of those living in these cities.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132517539","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":"Smart Irrigation System Using LoRaWAN","authors":"Rovishen Patten, A. Mungur","doi":"10.1109/NextComp55567.2022.9932251","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932251","url":null,"abstract":"The Internet of Things is now playing a crucial role in almost every field throughout the world. As far as the agricultural sector is concerned, for the future, more food would be needed with the same amount of land and water available. Therefore, there is a need for developing a smart irrigation system so as to cater for a better yield of the crops. Even though a large amount of time was spent on research for an effective smart irrigation system, the majority of them did not focus on the real-life issue which relates to connectivity problems due to agricultural lands being mostly found in rural areas where there is poor internet connection. This paper brings forward a smart irrigation system that makes use of LoRaWAN technologies. With the use of LoRaWAN, this problem is solved as connectivity will no longer be an issue with the smart irrigation system. This system uses a wireless sensor network using solar energy that is fully automated and that can be dispatched to different regions of the agricultural field. Backend management system handles all the incoming messages from the IoT system to integrate the information collected into a cloud database. The farmer will also be able to view his/her real time sensor data and irrigation status using his mobile application.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131948127","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":"Predictive Analysis of Fuel Prices Using Machine Learning","authors":"A. Calitz, M. Cullen, Simbarashe Mamombe","doi":"10.1109/NextComp55567.2022.9932204","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932204","url":null,"abstract":"Sales forecasting is seen as one of the most important indicators of the wellbeing of a business. The ability to accurately predict the sales figures can influence the success of a business. This can be tied to the stock levels of products, however businesses experience a number of problems, such as stock shortages that stem from not being able to accurately predict customer spending in advance. If there is understocking, there will be discouraged customers and overstocking will lead to unnecessary stock-holding costs. Several concepts have been introduced to help find useful insights from Big data to predict customer spending. Some of these are Predictive Analysis and Machine Learning. This paper focuses on the real-time prediction of fuel prices. The predictive analytics model implemented in this study takes into consideration the external factors such as time, the consumer price index, exchange rates, interest rates and oil prices. Relevant data, obtained from an agriculture organization and from various other sources were integrated into a single dataset. An exploratory analysis, using an Elman neural network was carried out to understand the relationships that exist between the datasets. Predictions were generated in two modes namely, daily and monthly fuel prices. The evaluation and validation of the model indicated accurate daily sales and spike predictions of diesel fuel.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132768005","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":"Trafik Moris: A Serious Game for Learning Traffic Behavior and Safety","authors":"Washeem Muhammad Jaunoo, L. Nagowah","doi":"10.1109/NextComp55567.2022.9932236","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932236","url":null,"abstract":"Driver and pedestrian education are as important as the engineering of roads and pathways. A number of people’s life can be at stake due to the lack of road safety knowledge. Moreover, the imprudence of drivers and/or pedestrians on the roads can prove to be fatal. The main reason behind those accidents are the violations of traffic rules from both parties. To ensure safety on the road, a good level of education on traffic safety is mandatory for all road users. However, the traditional delivery of traffic education can be monotonous and cannot hold the viewers for a long time. We are living in a digital world where most people have a smartphone. To avoid the hiccups of using the traditional approach to teaching and also delivering the traffic rules to all road users, a serious game, Traf$iota$k Moris, has been introduced for the people of Mauritius. The main functionalities of Trafik Moris includes the learning and recap of road signs and other traffic rules, a driving simulator, the control of a pedestrian in simulated settings and memorizing other materials that relate to traffic safety. Through this mobile serious game, road users, especially youngsters, who are often found guilty of causing many accidents on the road, will be more interested in learning and abiding by the traffic rules and therefore contribute to future safer roads.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122232801","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":"Chronic Kidney Disease Prediction using Deep Neural Network","authors":"Khadiime Jhumka, Muhammad Muzzammil Auzine, Mohammad Shoaib Casseem, Maleika Heenaye-Mamode Khan, Zahra Mungloo-Dilmohamud","doi":"10.1109/NextComp55567.2022.9932200","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932200","url":null,"abstract":"Chronic Kidney Disease (CKD) is a global health issue and symptoms are not always visible at the early stage. Deep learning techniques can be developed to determine the factors that potentially cause CKD at an early stage to enable patients to receive timely treatment. This paper attempts to forecast Chronic Kidney Disease (CKD) by analysing a set of attributes. A publicly available dataset with information collected in India was used for carrying out the research. Data was first preprocessed using different techniques to deal with missing values and outliers in the dataset. Next, classification between CKD and notCKD was performed using both Random Forest and Deep Neural network. The results of both methods were compared, and it was found that the proposed DNN model yielded a superior accuracy of 98.8% for the binary classification.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116211992","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":"Internet Management Practices at Higher Education Institutions in South Africa","authors":"A. Calitz, M. Cullen, Ryno Boshoff","doi":"10.1109/NextComp55567.2022.9932183","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932183","url":null,"abstract":"The COVID-19 pandemic the past years has forced Higher Education Institutions (HEIs) to fast-track digital transformation, specifically moving to an online environment. The online environment requires students to have access to the Internet, mobile technologies and data. The past years, a number of HEIs have become a smart campus, using networked technologies to facilitate teaching and learning, communication, campus security and advanced information technology (IT). HEIs constantly need to monitor and improve Internet management practices and relevant IT resources for their users. The Internet has become the foundation on which most IT resources rely and thus Internet management is a distinctive competency for a HEI. South African HEIs have limited Internet resources and are expected to use these resources optimally to ensure efficient and effective Internet connectivity on all campuses for all users and applications. The aim of this study was to determine the present Internet management practices at South African HEIs and to determine which elements may require change to optimize South African HEIs’ Internet provision to their users. A best practices HEIs Internet management business model is presented.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":" 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120827349","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 Contribution of Telework to Resilience: Covid-19 Analysis","authors":"Chantal Fuhrer","doi":"10.1109/NextComp55567.2022.9932201","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932201","url":null,"abstract":"Our aim is to study the contribution of telework to resilience during the pandemic. The research question is: how does telework affect individual and collective resilience during this crisis? We analyse the results from five online surveys from March 2020 to February 2021. The corpus results from the compilation of five different sources: written reports, two narrative surveys, a quantitative survey, and three focus groups. Thus, the transcription of 1,299 managers and specialists is studied following the textual data analysis methods. Our findings indicate that the contribution of telework differs whether the resilience is individual or collective. The process of resilience is also dynamic and we propose to distinguish three phases: preventive resilience (before the disaster), reactive resilience (during the disaster) and curative resilience (after the disaster). We use the results of the resilience study to discuss implications for the development of telework as a digital tool and practice.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123518351","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":"User Modelling to support Behavioural Modelling in Smart Environments","authors":"Oluwande Adewoyin, J. Wesson, Dieter Vogts","doi":"10.1109/NextComp55567.2022.9932209","DOIUrl":"https://doi.org/10.1109/NextComp55567.2022.9932209","url":null,"abstract":"Behavioural modelling in smart environments has the capability to allow the adequate provision of services to users of smart environments with inputs from user modelling. Although promising behavioural models developed for users in smart and normal environments already exist, the effectiveness of these behavioural models in terms of user-specific preferences is unclear. This study aims to investigate ways in which user models can be constructed for behavioural modelling purposes in smart environments. To achieve this aim, the Generic User Model was developed to cater for the limitations of existing user models by ensuring that behavioural modelling and monitoring are conducted by using inputs from the user model. The Generic User Model comprises five sub models, namely, static, dynamic, internal activity and external context models.","PeriodicalId":422085,"journal":{"name":"2022 3rd International Conference on Next Generation Computing Applications (NextComp)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123951632","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}