An Enhanced Fuzzy Clustering to Pattern Recognition for Cloud Computing, by using Model Aggregation and Model Selection
JUSPN, volume-16 , Issue 1 (2022), PP 49 - 53
Published: 26 Jan 2022
by Choukri Djellali, Mehdi adda , Mohamed Tarik Moutacalli from Department of Computer Science and Engineering University of Quebec At Rimouski Rimouski, Canada, G5L 3A1
Abstract: Numerical schemes research on clustering models has been quite intensive in the past decade. Many models have been proposed to address the clustering tasks. Most clustering models are influenced by presentation order, complex shapes, architecture configuration, and learning instability. Hence, in the present study, a novel clustering-based method for cloud computing that provides an improvement in recognition rate, is described. The evaluation, based on 10-fold Cross-validation, showed that the proposed model, which is named BaggingCluster, yielded good results and performed better than Self Organizing Map and fuzzy Adaptive Resonance Theory. Experimental studies demonstrate that our model provides an efficient model for cloud computing. read more... read less...
Keywords: Data Mining, Deep Learning, Clustering, Artificial Neural Network, Fuzzy Logic, Cross-Validation.
JUSPN, volume-16 , Issue 1 (2022), PP 37 - 47
Published: 24 Jan 2022
by Ruben Dobler Strand, Sindre Stokkenes, Lars Michael Kristensen, Torgrim Log from Department of Safety, Chemistry, and Biomedical laboratory sciences, Western Norway University of Applied Sciences, Haugesund, Norway, Department of Computer science, Electrical engineering and Mathematical sciences, Western Norway University of Applied Sciences, Bergen, Norway
Abstract: Dry and cold winter seasons result in very dry indoor conditions and have historically contributed to severe fires in the high and dense representation of wooden homes in Norway. The fire in Lærdalsøyri, January 2014, is a devastating reminder of town fires still posing a threat to a modern society. In order to reduce conflagration probability and consequences, it is necessary to have an accurate estimate of the current and near future fire risk to take proper planning precautions. Cloud computing services providing access to weather data in the form of measurements and forecasts, combined with recent developments in fire risk modelling, may enable smart and fine-grained fire risk prediction services. The main contribution of this study is implementation and experimental validation of a wooden home predictive fire risk indication model, as well as outlining a wooden home fire risk concept. The wooden home fire risk model focuses on the first house catching fire (indoors) in a potential conflagration event. Such a fire would be critical to intervene prior to the fire developing exterior flames and embers post flashover, and thus high likelihood of fire spread. The implemented model exploits cloud-provided weather measurements and forecasts, to predict the current- and near future fire risk at given geographical locations. It computes the indoor wooden fuel moisture content of houses that may catch fire, using measured and forecasted outdoor temperature and relative humidity, and estimates the time to flashover. The latter is found through an empirical relation with the fuel moisture content, and can be used as an indication of the fire risk, beyond the modelled single house. The model implementation was integrated into a micro-service based software system and experimentally validated at selected geographical locations, relying on weather data provided by the RESTful API’s of the Norwegian Meteorological Institute. The validation took place by applying the model to predefined cases, with an outcome known from observations or theory. The first part is a general evaluation of the outputs, considering three historical fires. Then, seasonal changes and natural climate variations were considered. Our evaluation demonstrates the ability to provide trustworthy and accurate fire risk indications using a combination of recorded weather data and forecasts. Further, our cloud- and micro-service based software system implementation is efficient with respect to data storage and computation time. Finally, the novel fire risk concept is demonstrated for a selected city, based on model output. It successfully depicts the implications following reduced indoor humidity by utilizing location specific fire risk contours. read more... read less...
Keywords: Smart city and cloud data services, Climate related fire risk, Mitigating urban fire risk
JUSPN, volume-16 , Issue 1 (2022), PP 29 - 35
Published: 20 Jan 2022
by Tariq Abu Hilal, Salam Hoshang, Hasan Abu Hilal from Higher Colleges of Technology, Abu Dhabi, United Arab Emirates, 4101
Abstract: Many higher education institutions are focusing on flipped classroom to gain the benefits that can be reaped for the institution, the students and teachers. The attractiveness of the flipped classroom is increasing, due to the Covid-19 situation and the promptly switch to the online teaching approach by many institutions. Based on the researchers' preliminary investigation, the utilization of flipped classrooms approach among educators is still not fully exploited. This initial and seed research aims to investigate students' and educators' point of view concerning the application of the flipped classroom concept. This qualitative research is based on interviews of focus groups, observations and mini structured surveys that aim to answer the main research question how the students and educator view flipped classroom. The researchers collected data from some 300 students and about ten educator form information systems and engineering disciplines. The research results reveal that students, as well as educators, are aware of flipped classrooms but more training in the tools and concepts of the flipped classroom is required. Flipped classrooms can bring enormous benefits to students, institutions and educators. The outcomes of this research work showed that students and educators prefer the flipped classroom approach in some aspects. In this paper, we provide and discuss the employment of the flipped classroom idea in a hybrid learning setting. We trust that this is an innovative learning strategy when the proper modern technology is utilized. Such as the utilization of smart gadgets to perform different tasks, like teaching, designing question bank, assessment of students, feedback…etc. We further focus on the use of information technology as well as the development of the course content. This paper provides a case study of hybrid learning flipped classroom at HCT. As the HCT is running completely hybrid in the last couple of years. As a result of this study in the United Arab Emirates, 62% of the teachers were comfortable with flipped classrooms read more... read less...
Keywords: Flipped classroom, Online Education, Undergraduate Studies, Hybrid Learning.
JUSPN, volume-16 , Issue 1 (2022), PP 23 - 27
Published: 19 Jan 2022
by Krish Bhanushali, Viren Sureja , Vidhan Patel , Tanmay Thaker , Nishant Doshi from Pandit Deendayal Energy University, Gandhinagar, India, Gujarat-382426
Abstract: Currently, in a modern world where people are getting busier, it is hard for them to take time to work-out or exercise regularly by themselves. People have been using the gym as a place to make their body fit and it is right as Health and Immunity are an important part of a person’s life and everyone would always like to be fit and healthy. To achieve that level requires motivation and discipline. And lack of motivation results in quitting the gym in a very short span. Now Generally in Gym, there are only a few that keep track of everything, others we have a huge marketplace for the people who joined but quit soon since doing exercise doesn’t give you short-term results. The changes in your body start appearing after months. The slightest changes and every other important aspect can be hard to keep track of them altogether, now using smart gym approach, the slightest change can be measured, using IoT and later one can curate all the training regiments, diets and exercises properly according to it. We propose an overall IoT-based-system to monitor the user's Health and Fitness Records in an effective way of using a database management system. It plans to collect data from the machines when the user uses it, keep track of its workouts and diet intake, with a gym social media that would help to maintain a competitive environment, also including management of membership, payment, trainers, and employees. This would result in a whole new way of looking towards the gym. read more... read less...
Keywords: Smart Gym; database; IoT; Health and Fitness monitoring
JUSPN, volume-16 , Issue 1 (2022), PP 07 - 22
Published: 10 Jan 2022
by Mohammed Alabbad , Ridha Khedri from Communications and IT Research Institute, King Abdulaziz City for Science and Technology (KACST), Riyadh, 11442, Saudi Arabia, Dept. of Computing and Software, McMaster University, Hamilton, Ontario, Canada
Abstract: Software Defined Networks (SDN) is a networking paradigm that helps transform networks by breaking away from the restrictive constraints put by networking hardware used in traditional non-SDN networks. They bring improved agility, scalability, and programmability of the control and the switching of the traffic. The challenges of structuring the SDN data plane for security still necessitate further investigation especially to deal with dynamic SDN networks. The use of the Robust Network and Segmentation (RNS) algorithm, which is based on Product Family Algebra, is essential for implementing layered defence and segmentation strategies to compartmentalize the networks and attain an access-control secure network. In this paper, we present an additional plane in charge of the configuration and governance of SDN data planes that we call Dynamic Configuration and Governance (DCG) plane. It is intended to give agility to dynamic networks. It implements the RNS algorithm in the SDN environment. Moreover, we propose and assess three architectures that use the DCG plane. The assessment results identify an architecture that is suitable for dynamic networks and another for networks that are more stable regarding changes to policies and network topology. read more... read less...
Keywords: Dynamic SDN, SDN Architecture, Secure SDN, SDN Segmentation, Formal Methods for Network Segmentation
JUSPN, volume-16 , Issue 1 (2022), PP 01 - 06
Published: 04 Jan 2022
by Oluwasegun O. Aluko, Astrid Gühnemann, Paul Timms from Civil Engineering Department, Ekiti State University, Ado Ekiti, Nigeria, University of Natural Resources and Life Sciences, Vienna, Department of Landscape, Spatial and Infrastructure Sciences, Institute for Transport Studies, Austria, Institute for Transport Studies, University of Leeds, UK
Abstract: Road safety is a subject of concern the world over and many studies have looked into how to improve safe travel. Motorcycles, including motorcycle taxis, are particularly vulnerable. This paper reports the outcome of a study conducted on motorcycle taxi safety problems using a system dynamics method. Qualitative data was obtained from the field and analysed using qualitative analysis methods. The outcome of the qualitative analysis led to the formulation of a dynamic hypothesis for a system dynamics approach, whose first step was to develop and analyse a causal loop diagram [CLD]. This CLD demonstrates how deterrence, a behavioural pattern that can be produced by the appropriate application of sanctions, is both strengthened and weakened within the system. The paper uses this analysis to provide insights about the behavioural patterns of motorcycle taxi operation in Nigeria. These insights include the possibility of maintaining the system at equilibrium for a desired level of deterrence as well as the possibility of breaking undesirable cycles of bribery and jumping arrest loops. These insights can also be useful in other countries of the world where motorcycle taxis operate. read more... read less...
Keywords: System Dynamics, Causal Loop Diagram, Safety Culture, Motorcycle Taxi.