Pub Date : 2018-10-01DOI: 10.1109/honet.2018.8551321
{"title":"HONET-ICT 2018 Index","authors":"","doi":"10.1109/honet.2018.8551321","DOIUrl":"https://doi.org/10.1109/honet.2018.8551321","url":null,"abstract":"","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115029728","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}
Pub Date : 2018-10-01DOI: 10.1109/HONET.2018.8551328
M. Nawaz, M. Hadzikadic
Predictive models using Support Vector Machines or Decision Tree Classifiers can be used in evaluating and advising students for the selection/placement process in the most suitable programs compatible with students’ aptitude. However, after the selection or placement process, one can go one step further by using predictive models in monitoring and evaluating the performance of trainees (students) through Machine Learning and Complex Adaptive Systems. In light of the monitoring and evaluation data, trainers can give corrective action, which may be necessary to ensure the optimal results during the ongoing training process. In the corporate sector, organizations can use the same methodology for training and evaluating their employees to meet their organizational objectives in the most effective way.
{"title":"Changing the Dynamics of Training by Predictive Modeling","authors":"M. Nawaz, M. Hadzikadic","doi":"10.1109/HONET.2018.8551328","DOIUrl":"https://doi.org/10.1109/HONET.2018.8551328","url":null,"abstract":"Predictive models using Support Vector Machines or Decision Tree Classifiers can be used in evaluating and advising students for the selection/placement process in the most suitable programs compatible with students’ aptitude. However, after the selection or placement process, one can go one step further by using predictive models in monitoring and evaluating the performance of trainees (students) through Machine Learning and Complex Adaptive Systems. In light of the monitoring and evaluation data, trainers can give corrective action, which may be necessary to ensure the optimal results during the ongoing training process. In the corporate sector, organizations can use the same methodology for training and evaluating their employees to meet their organizational objectives in the most effective way.","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126413831","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}
Pub Date : 2018-10-01DOI: 10.1109/HONET.2018.8551335
Uferah Shafi, M. Zeeshan, Naveed Iqbal, Nadia Kalsoom, R. Mumtaz
The ubiquitous use of IEEE 802.11 has aggravated the need to make efficient use of available bandwidth. Currently handoff decision in IEEE 802.11 is made based on the received signal strength but these results in poor connectivity specifically when an access point is overloaded. Overlapping regions where users can be connected to multiple access points, switching to less loaded access point can improve overall network capacity. In this article, we propose a decentralized approach for best access point selection which also prevents an access point to get overloaded. We propose an algorithm for handover strategy to improve network capacity via load balancing and it also minimizes switching overhead. We perform detail analysis on publically available dataset which consists of millions of Wi-Fi sessions with multiple access points.
{"title":"An Optimal Distributed Algorithm for Best AP Selection and Load Balancing in WiFi","authors":"Uferah Shafi, M. Zeeshan, Naveed Iqbal, Nadia Kalsoom, R. Mumtaz","doi":"10.1109/HONET.2018.8551335","DOIUrl":"https://doi.org/10.1109/HONET.2018.8551335","url":null,"abstract":"The ubiquitous use of IEEE 802.11 has aggravated the need to make efficient use of available bandwidth. Currently handoff decision in IEEE 802.11 is made based on the received signal strength but these results in poor connectivity specifically when an access point is overloaded. Overlapping regions where users can be connected to multiple access points, switching to less loaded access point can improve overall network capacity. In this article, we propose a decentralized approach for best access point selection which also prevents an access point to get overloaded. We propose an algorithm for handover strategy to improve network capacity via load balancing and it also minimizes switching overhead. We perform detail analysis on publically available dataset which consists of millions of Wi-Fi sessions with multiple access points.","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127933364","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}
Pub Date : 2018-10-01DOI: 10.1109/HONET.2018.8551339
Tajwar Mehmood, Seemab Latif, Sheheryaar Malik
Efficient resource utilization leads cloud provider to low cost and high performance. Cloud Computing is a dynamic environment that provides on-demand services over the internet on pay as you go model. Cloud platform has a dynamic resource usage as it is shared among large number of users. Resource allocator provisions resources to dynamic demands of user from finite set of resources. There should be no over and under provisioning of resources. Underutilized resources causes resource wastage and more cost whereas over utilized resource can lead to service degradation. If Resource allocators can presume future resource usage they can take resource provisioning decision efficiently. A resource utilization prediction mechanism is required to assist resource allocator for optimum resource provisioning.Accurate prediction is a challenge in such a dynamic resource usage. Machine learning techniques can help in creating a model that yields accurate prediction results. In machine learning, Ensemble mechanisms are renowned for improving the prediction accuracy which uses a combination of learners rather than a single learner. In this study, an “Ensemble based workload prediction mechanism” is proposed that is based on stack generalization. Experiments are conducted in order to compare the proposed model with the individual and baseline prediction models. For comparison with baseline model, we have used Root Mean Square Error(RMSE) as results of baseline model were given in RMSE. Proposed mechanism has shown 6% and 17% reduction in RMSE in CPU usage and in Memory usage prediction respectively. For comparing our proposed ensemble with independent learner(K Nearest Neighbor, Neural Network, Decision Tree, Support Vector Machine and Naïve Bayes), we have used accuracy as evaluation parameter. The proposed ensemble has improved the prediction accuracy by $approx 2$%.
{"title":"Prediction Of Cloud Computing Resource Utilization","authors":"Tajwar Mehmood, Seemab Latif, Sheheryaar Malik","doi":"10.1109/HONET.2018.8551339","DOIUrl":"https://doi.org/10.1109/HONET.2018.8551339","url":null,"abstract":"Efficient resource utilization leads cloud provider to low cost and high performance. Cloud Computing is a dynamic environment that provides on-demand services over the internet on pay as you go model. Cloud platform has a dynamic resource usage as it is shared among large number of users. Resource allocator provisions resources to dynamic demands of user from finite set of resources. There should be no over and under provisioning of resources. Underutilized resources causes resource wastage and more cost whereas over utilized resource can lead to service degradation. If Resource allocators can presume future resource usage they can take resource provisioning decision efficiently. A resource utilization prediction mechanism is required to assist resource allocator for optimum resource provisioning.Accurate prediction is a challenge in such a dynamic resource usage. Machine learning techniques can help in creating a model that yields accurate prediction results. In machine learning, Ensemble mechanisms are renowned for improving the prediction accuracy which uses a combination of learners rather than a single learner. In this study, an “Ensemble based workload prediction mechanism” is proposed that is based on stack generalization. Experiments are conducted in order to compare the proposed model with the individual and baseline prediction models. For comparison with baseline model, we have used Root Mean Square Error(RMSE) as results of baseline model were given in RMSE. Proposed mechanism has shown 6% and 17% reduction in RMSE in CPU usage and in Memory usage prediction respectively. For comparing our proposed ensemble with independent learner(K Nearest Neighbor, Neural Network, Decision Tree, Support Vector Machine and Naïve Bayes), we have used accuracy as evaluation parameter. The proposed ensemble has improved the prediction accuracy by $approx 2$%.","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127567784","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}
Pub Date : 2018-10-01DOI: 10.1109/HONET.2018.8551333
Asad Khan, Shujaat Ali, Dilawar Shah, A. Farhad
IEEE 802.15.6 is primarily designed for the Wireless Body Area Networks (WBANs), which provides a base for the wearable and implantable sensors. These sensors are tiny nodes used to collect information and sent to a central controller called hub. In a star topology, the hub is responsible to transmit a key superframe bounded by the beacon. The superframe is an important attribute of the beacon-enabled mode of IEEE 802.15.6. The superframe structure is divided into exclusive access, random access, and managed access phases along with a contention access phase. However, currently, the superframe structure of IEEE 802.15.6 is static in nature and cannot adapt itself for emergency and regular traffic. Emergency traffic is the most important data which needs to be transmitted reliably and correctly in order to timely monitor the patient. Due to the fixed superframe structure, emergency traffic causes packet loss and delay. In order to alleviate packet loss and delay, we present a self-adaptive superframe (SAS) algorithm. The SAS algorithm adjusts the EAP phase for emergency traffic based on the network traffic, packet delivery, packet loss ratio, and the observed network delay to enhance the network performance. The results show that the SAS algorithm adapts itself based on the network conditions and adjusts the EAP phase efficiently and outperforms IEEE 802.15.6 in terms of delay, packet delivery ratio, and throughput.
{"title":"A Self-Adaptive Superframe Structure for Emergency Traffic Based IEEE 802.15.6","authors":"Asad Khan, Shujaat Ali, Dilawar Shah, A. Farhad","doi":"10.1109/HONET.2018.8551333","DOIUrl":"https://doi.org/10.1109/HONET.2018.8551333","url":null,"abstract":"IEEE 802.15.6 is primarily designed for the Wireless Body Area Networks (WBANs), which provides a base for the wearable and implantable sensors. These sensors are tiny nodes used to collect information and sent to a central controller called hub. In a star topology, the hub is responsible to transmit a key superframe bounded by the beacon. The superframe is an important attribute of the beacon-enabled mode of IEEE 802.15.6. The superframe structure is divided into exclusive access, random access, and managed access phases along with a contention access phase. However, currently, the superframe structure of IEEE 802.15.6 is static in nature and cannot adapt itself for emergency and regular traffic. Emergency traffic is the most important data which needs to be transmitted reliably and correctly in order to timely monitor the patient. Due to the fixed superframe structure, emergency traffic causes packet loss and delay. In order to alleviate packet loss and delay, we present a self-adaptive superframe (SAS) algorithm. The SAS algorithm adjusts the EAP phase for emergency traffic based on the network traffic, packet delivery, packet loss ratio, and the observed network delay to enhance the network performance. The results show that the SAS algorithm adapts itself based on the network conditions and adjusts the EAP phase efficiently and outperforms IEEE 802.15.6 in terms of delay, packet delivery ratio, and throughput.","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127584847","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}
Pub Date : 2018-10-01DOI: 10.1109/HONET.2018.8551323
Abdul Hafeez Abid, Ammar Hasan
We propose an optimization mechanism for non-flexible load demand management in smart grid for academic buildings using a fuzzy controller and integer linear programming (ILP) technique. The proposed mechanism is able to make decisions on human like thinking to control the operation of non-flexible appliances on the basis of convenience level affected by individual appliances. Simulation results based on academic area scenarios have been presented to validate effectiveness of the proposed mechanism.
{"title":"An approach for demand side management of non-flexible load in academic buildings","authors":"Abdul Hafeez Abid, Ammar Hasan","doi":"10.1109/HONET.2018.8551323","DOIUrl":"https://doi.org/10.1109/HONET.2018.8551323","url":null,"abstract":"We propose an optimization mechanism for non-flexible load demand management in smart grid for academic buildings using a fuzzy controller and integer linear programming (ILP) technique. The proposed mechanism is able to make decisions on human like thinking to control the operation of non-flexible appliances on the basis of convenience level affected by individual appliances. Simulation results based on academic area scenarios have been presented to validate effectiveness of the proposed mechanism.","PeriodicalId":161800,"journal":{"name":"2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT & IoT (HONET-ICT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125297715","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：