Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications最新文献

{"title":"Implementing computer-based assessments in higher educational institutions: students' perceptions","authors":"Victor Faniran, Nurudeen Ajayi, Samuel T. Faloye","doi":"10.1145/3415088.3415111","DOIUrl":"https://doi.org/10.1145/3415088.3415111","url":null,"abstract":"Assessment refers to the measurement of the knowledge, capability, skill and understanding of a student. Over the years, assessments have been undertaken by students with paper, pen and pencil (paper-based assessment or PBA). However, the dynamic nature of technology has changed the way assessments are being implemented in higher educational institutions. Assessments are now implemented using computers (computer-based assessment or CBA). Higher educational institutions now implement CBA instead of PBA, and this implementation has stirred diverse reactions among researchers. It has been noted that, when an identical assessment is implemented as CBA and PBA, students get different assessment results. The literature shows that these differences arise from students' different perceptions of CBA. Therefore, this study aimed at investigating students' perceptions of CBA and how it affects their assessment performances and results. The study adopted a descriptive design and a quantitative methodology. Data was collected from 350 students using questionnaires and analysed using the Statistical Package for the Social Sciences (SPSS). Results showed that students prefer CBA to PBA, find it easy to take CBA and intend to frequently take CBA in the future. Furthermore, students indicated that the implementation of CBA improves their assessment performances.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"46 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132678076","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":"Design and implementation of a low-cost home automation and monitoring IoT system using message que telemetry transport protocol: south africa context","authors":"K. Ogudo, Periola Ayodele","doi":"10.1145/3415088.3415089","DOIUrl":"https://doi.org/10.1145/3415088.3415089","url":null,"abstract":"Home automation is a fast and growing industry in South Africa, because in recent years almost everything home and office electrical and electronics appliances are been connected to the internet and human mobile devices. There is an increase in demand of time from the working class and hence the busy time schedule. This necessitate the home automation and monitoring systems which enable homeowners to remotely monitor and control appliances in their houses and offices without being present in the device physical location. The designed system host the integrated intelligent unit functionalities that enable communication between the controller and remote end-user units of the system. It is important to ensure that home automation systems have a low cost to enable user adoption. Home automation systems should also incorporate latest technology, portability and also have internet connectivity capabilities. This paper proposes a design of low-cost home automation system that incorporates internet access and delivers internet of things (IoT) connectivity services in a smart home application. The designed system provides access to an internet connected home automation systems. The system is accessible via mobile devices and provides remote access to home appliances. In conclusion, during measurement and testing of the designed system, device full duplex connection for one round trip was less that 5seconds to relay a message packet between the transmitter subscriber device and the publisher receiver device. The performance of the designed device is satisfactory at first iteration prototype designed.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133566012","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":"Segmentation via principal component analysis for perceptron classification: a case study of kenyan mobile subscribers","authors":"Khamis Mwero Maneno, R. Rimiru, C. Otieno","doi":"10.1145/3415088.3415128","DOIUrl":"https://doi.org/10.1145/3415088.3415128","url":null,"abstract":"In today's competitive environment, companies must identify their most profitable customer groups and the groups that have the biggest potential to become as such. By identifying these critical groups, they can target their actions, such as launching tailored products and target one-to-one marketing to meet customer expectations. With the profound advancements in clustering algorithms, segmentation has emerged as the method of choice for isolating the various groups of interest. However, the quality of segments of the groups of interest is affected by the type of input data to the clustering algorithms and associated high dimensionality In this study, Principal Component Analysis has been used to solve the high dimensionality of data problem. Subscriber data from nine transactions were first tested for suitability for factor analysis. Principal component analysis was then used to reduce the nine variables to five inputs. The factored data was then to cluster the various customers into segments. The elbow criterion was used to determine the optimum number of clusters. The data was then clustered via several methods; K-means, FCM, PCM, and Hierarchal. Results showed that k-means was not just the simplest method but also performed best with dimensionally reduced data. By using real case data, the study was able to verify that dimensional reduction can be applied before clustering algorithms. The dimension reduction of telecom data can thus be solved via Principal Component Analysis. The study was extended to include the classification of new subscribers basing on the dimensionally reduced data. For that purpose, a perceptron neural network was created. Using the k-means clusters as targets, a perceptron capable of classifying was created and validated. The perceptron was able to classify new subscribers with acceptable accuracy. Dimension reduction via Principal Component Analysis can, therefore, be used to achieve the segmentation of existing customers and also be used to classify new customers. The use of a perceptron is also important for automating the process of customer classification. Companies can therefore easily identify profitable customers from both old and new customers.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130069117","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":"A survey of contend-based filtering technique for personalized recommendations","authors":"Lefats’e Manamolela, M. Appiah, T. Zuva","doi":"10.1145/3415088.3415101","DOIUrl":"https://doi.org/10.1145/3415088.3415101","url":null,"abstract":"The number of choices on the internet is devastating. In recent years, internet services have grown exponentially and it is unavoidable that a number of services suffer from information overload, which makes it difficult for users to find the information they are in need of. This is where recommender systems or RSs come in handy by delivering personalized suggestions from a set of choices that is presented to users to pinpoint items or services of interest. Recommender systems among other practices are mostly used for music, movies, jokes, restaurants, financial services, life insurance, Instagram Facebook and twitter followers. This makes recommender systems a fundamental part of websites and e-commerce applications. In this paper, we present a survey of content-based filtering recommender systems. We further provide the landscape of different recommendation methods and their basic approaches.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"252 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134498049","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":"Educational data mining in higher education in sub-saharan africa: a systematic literature review and research agenda","authors":"Mfowabo Maphosa, V. Maphosa","doi":"10.1145/3415088.3415096","DOIUrl":"https://doi.org/10.1145/3415088.3415096","url":null,"abstract":"The impact of the coronavirus disease (COVTD-19) will see an increase in data generated by higher education institutions (HEIs) in Sub-Saharan Africa as more institutions introduce online learning. HEIs are storing huge volumes of data since data collection has become an affordable activity in the data economy. This data can be mined to reveal hidden knowledge that can be used for informed decision-making. Educational data mining (EDM) within higher education has been gaining traction in the past two decades. This paper aims to explore and analyse existing research on EDM in institutions of higher learning in Sub-Saharan Africa and to offer recommendations for future EDM research in higher education in the fourth industrial revolution (4IR) era. The paper provides a systematic literature review (SLR) on EDM in institutions of higher learning in the Sub-Saharan Africa region that covers a decade (2010--2019). Search terms used in the SLR identified 811 research articles on EDM with a focus on higher education, but only 24 were conducted in Sub-Saharan Africa. These articles were critically reviewed and analysed by applying an SLR approach. Analysis of these research articles reveals that EDM research in higher education in Sub-Saharan Africa is still in its infancy even though a notable increase in research output was observed in the years 2015--2019. The main finding of this paper is that very few Sub-Saharan African countries have embraced EDM to maximise on better educational management and the returns of the increased enrollment rates. The paper proposes a research agenda for HEIs in Sub-Saharan Africa based on current trends in EDM.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"3 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123682907","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":"Developing an effective regulatory framework for virtual currencies in mauritius","authors":"Priya Balgobin, A. Seeam","doi":"10.1145/3415088.3415126","DOIUrl":"https://doi.org/10.1145/3415088.3415126","url":null,"abstract":"It is widely accepted that virtual currencies have the potential of revolutionising the global finance sector. The potential of bitcoin has been recognised by corporate organisations and governments. With the continuing growth of bitcoin as a cryptocurrency, its regulatory regime has become crucial in determining the fate of this novel system of exchange. The global economic crisis and pandemic situation of 2020 is turning industries towards adoption of digital and virtual currencies. Although bitcoins have been regarded as the pioneer of decentralized peer to peer virtual currencies, there remains uncertainties in various countries as to whether they should embrace, devise new regulations or completely outlaw the digital currency. It has been recognised that Mauritius has the potential of acting as a Financial Technology (Fintech) hub for the African and surrounding regions through the rapid development and adoption of technology.For this to become possible, the current regulatory framework of Mauritius must be updated to reflect the continuing innovating changes in this area. So far, Mauritius has not yet implemented any specific regulations to address the use of Blockchain, bitcoins and cryptocurrencies in its jurisdiction. The only related legal framework currently being used in this area is the Regulatory Sandbox Licensing Scheme implemented by the Board of Investment Mauritius (\"BOI\"). It offers the possibility for investors to conduct their businesses in an area where there exists no legal framework or inadequate provisions under existing Mauritian legislation. In this research paper, the different regulatory frameworks of United States,Canada and China will be assessed to serve as a comparative analysis to examine the nature of their regulatory regimes.These jurisdictions have been chosen as they have been in the forefront of bringing significant regulatory changes, which has not been the case in any countries in Africa or Indian Ocean. These will be used to address the question as to whether there are any existing legal frameworks from other jurisdictions that can be customised or adapted for incorporation into the jurisdiction of Mauritius.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127374461","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":"Effects of membership functions for fuzzy logic controlled autonomous mobile robot","authors":"A. Shitsukane, C. Otieno","doi":"10.1145/3415088.3415098","DOIUrl":"https://doi.org/10.1145/3415088.3415098","url":null,"abstract":"There is a growing trend in autonomous robotics research. A consistent collision avoidance and path following method is needed for an intelligent and operative mobile robot navigation. Usually robots are fitted with sensors for detecting the surrounding. Nevertheless, they still are unreliable due to ambiguity in the surroundings. Fuzzy logic has been long-established as an suitable tool for handling ambiguity that arises from vague data. Many Studies have presented Fuzzy logic models for obstacle avoidance wheeled robots frequently leading to a dead zone and inability to avoid obstacles. We presented a model with 8 inputs, 2 outputs and 27 rules for the robot movement. The research investigates the possibility of upholding uncertainty by changing controller membership functions to achieve optimum results. The study was implemented and tested through simulation by V-REP and MATLAB software. The outcomes reveal that tuning of membership functions enhance controller performance.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130991753","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":"Intelligent traffic management algorithm for wireless sensor networks","authors":"T. M. Tshilongamulenzhe, Topside E. Mathonsi, M. Mphahlele, Deon P. DuPlessis","doi":"10.1145/3415088.3415115","DOIUrl":"https://doi.org/10.1145/3415088.3415115","url":null,"abstract":"Wireless Sensor Networks (WSNs) are used to simplify various real-time applications which include traffic management, humidity, monitoring of the temperature, and pressure by using a wide range of sensor nodes. Sensor nodes are assigned through various resource restrictions such as allocated bandwidth, available memory, and battery power. This research paper demonstrated the packet congestion issue that happens during packet distribution from the source node to destination node. The packet congestion in WSNs is normally caused by Buffer overflow. This leads to the decrement of network throughput, packet drop, and high end-to-end delay during packet transmission from and to different nodes. Therefore, in order to avoid packet congestion in WSNs, an Intelligent Traffic Management (ITM) algorithm is proposed. The proposed ITM algorithm was developed by integrating different algorithms namely: Modified Neural Network Wavelet Congestion Control (MNNWCC) algorithm and Tree-based Congestion Control (TACC) algorithm. The simulation is performed using the Network Simulator 2 (NS-2) simulation platform. The simulation results showed that the proposed ITM algorithm improves the network throughput by 97.1 %, reduce packet drop by 32%, and end-to-end delay minimized by 27% when compared with MNNWCC algorithm and TACC algorithm.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"45 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114323886","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":"Application of augmented reality in aviation: improving engagement of cabin crew during emergency procedures training","authors":"Tanveer Gangabissoon, Girish Bekaroo, Waseemah Moedeen","doi":"10.1145/3415088.3415120","DOIUrl":"https://doi.org/10.1145/3415088.3415120","url":null,"abstract":"The main duty of the cabin crew is to ensure the safety of all passengers onboard and are crucial during emergency situations. It is mandatory for cabin crew to attend the annual Emergency Procedures Training (EPT) to be able to operate as cabin crew regardless of the seniority. Despite the high importance, this training can be long and bulky leading to boredom and lack of engagement, hence jeopardizing the importance of in-flight safety procedures. Although Augmented Reality (AR) can potentially address this issue while enhancing engagement and learning retention, limited work has been undertaken to apply this technology to EPT. As such, this paper investigates whether augmented reality can effectively improve user engagement during emergency procedures training in the context of aviation. In this endeavor, an AR-based application was developed and is presented in this paper. The Positive Engagement Evaluation Method (PEEM) was then used to assess engagement among the 45 cabin-crew of the national carrier. From the PEEM matrix, the positive engagement score obtained was 10.58 and mean scores from the questionnaire ranged from 3 to 4.7. This highlights that Augmented Reality has the potential to enhance the motivation and engagement of users during the emergency procedures training, although a few limitations were identified.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129848781","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 development of a sepedi text generation model using long-short term memory","authors":"Mercy M. Moila, T. Modipa","doi":"10.1145/3415088.3415114","DOIUrl":"https://doi.org/10.1145/3415088.3415114","url":null,"abstract":"Recurrent Neural Network (RNN) is a type of deep neural network that is developed to generate a set of text given the features to produce the output based on features provided to the model. RNN is difficult to train when dealing with long memory dependencies. Long-short term memory (LSTM) is a recurrent neural network technique that works with memory cells which were developed to deal with the difficulties that were experienced by RNN. The system for word generation in text messages deduce the words based on statistical analysis from a large corpus. Moreover, the word in a sentence depends on its context which requires the use of machine learning algorithms to generate word sequences. The system to generate Sepedi text has not been developed especially using RNN techniques. The aim of the study is to use the LSTM RNN technique to generate Sepedi language text sequences. The data used for the experiments is a version of the NCHLT Sepedi text corpus. We obtained the accuracy of 50.3% with limited data and only 20 epochs.","PeriodicalId":274948,"journal":{"name":"Proceedings of the 2nd International Conference on Intelligent and Innovative Computing Applications","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124650818","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}