Pub Date : 2019-03-29DOI: 10.1109/ICCMA.2019.00013
Francis M Mensah, A. Acakpovi, Futa Osumanu, R. Sowah, Francois-Xawier Nicolas Fifatin, Télesphore Cossi Nounangnonhou
This paper proposes the modelling and simulation of a special gap filler intended to cover grey areas in the DTT network of Accra. This has become necessary due to the numerous areas of low signal coverage in the Accra DTT and the incapability of previous methods to efficiently address the problem. The ADS simulation consists of arrangements of components from the DBV-T library which consists of filters, amplifiers and a power source. This setup mimics a gap filler system with a better noise reduction implementation, several frequency values are being used for the simulation process. A significant increase in the output signal as in comparison to the input means the shaded areas will be properly covered. The results derived from the simulation of the ADS setup highly improved upon the output signal values, when compared to the ITU standard. Three (3) out of five (5) simulation results show values beyond the minimum signal level requirement. Also using MATLAB, the RF propagation toolbox which has the map tool feature was able to implement the gap fillers into the Accra area and gave a visual representation of the signal strength. Modelling a gap filler system which has better noise cancellation and which propagates better with a dipole antenna was achieved in this paper. The outcome of the paper shows that the gap filler modelling increase signals in grey areas.
{"title":"Modelling an Efficient Gap Filler for DTT Network Using ADS Software","authors":"Francis M Mensah, A. Acakpovi, Futa Osumanu, R. Sowah, Francois-Xawier Nicolas Fifatin, Télesphore Cossi Nounangnonhou","doi":"10.1109/ICCMA.2019.00013","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00013","url":null,"abstract":"This paper proposes the modelling and simulation of a special gap filler intended to cover grey areas in the DTT network of Accra. This has become necessary due to the numerous areas of low signal coverage in the Accra DTT and the incapability of previous methods to efficiently address the problem. The ADS simulation consists of arrangements of components from the DBV-T library which consists of filters, amplifiers and a power source. This setup mimics a gap filler system with a better noise reduction implementation, several frequency values are being used for the simulation process. A significant increase in the output signal as in comparison to the input means the shaded areas will be properly covered. The results derived from the simulation of the ADS setup highly improved upon the output signal values, when compared to the ITU standard. Three (3) out of five (5) simulation results show values beyond the minimum signal level requirement. Also using MATLAB, the RF propagation toolbox which has the map tool feature was able to implement the gap fillers into the Accra area and gave a visual representation of the signal strength. Modelling a gap filler system which has better noise cancellation and which propagates better with a dipole antenna was achieved in this paper. The outcome of the paper shows that the gap filler modelling increase signals in grey areas.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133745393","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 : 2019-03-29DOI: 10.1109/ICCMA.2019.00011
A. Acakpovi, Isaiah Tefutor, Kester Quist-Aphetsi, N. Nwulu, R. Sowah, R. Abubakar
This paper investigates the effect of interference on Aeronautical Navigation systems by Frequency Modulation (FM) broadcasting signals. Precisely, the paper evaluated the impact of 3rd order intermodulation distortion on the VHF omnidirectional range and the instrument landing system (Localizer) used at the Ghana Civil Aviation Authority (GCAA). The necessity of this study stems from the fact that, electromagnetic compatibility (EMC) between FM audio broadcast and aeronautical radio communication services operating in the range of 85.7-108MHz and 108-117.975 MHz respectively is essential for safe flight operation. An analytical method of estimating the 3rd order intermodulation distortion has first been presented followed by simulation approach with the intermodulation analysis software v.10 and subsequent simulation with the Matlab software to determine and display the power spectral density of the output signals. All FM station frequencies in the Greater Accra region have been considered and paired to form dual tone signals that were considered input signal before assessing the impact of the 3rd order intermodulation harmonic. It was found that multiple 3rd order intermodulation harmonics distort and perturbate the aeronautical communication system in the Greater Accra region and these lead to severe safety implications for the operation of the aeronautical navigation system. It was recommended that broadcasting stations should implement cavity filters to reduce the effect of 3rd order intermodulation harmonics; they should respect the specification prescribed to them by the NCA and operate within limits allocated to them in order not to breach the international regulation of ITU that deems it an offense to interfere with the aeronautical communication system and to further ensure safety to the aviation navigation system.
{"title":"Impact Analysis of Induced FM Radio Interferences on Aeronautical Radio Navigation Systems: Case Study of Kotoka International Airport, Accra-Ghana","authors":"A. Acakpovi, Isaiah Tefutor, Kester Quist-Aphetsi, N. Nwulu, R. Sowah, R. Abubakar","doi":"10.1109/ICCMA.2019.00011","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00011","url":null,"abstract":"This paper investigates the effect of interference on Aeronautical Navigation systems by Frequency Modulation (FM) broadcasting signals. Precisely, the paper evaluated the impact of 3rd order intermodulation distortion on the VHF omnidirectional range and the instrument landing system (Localizer) used at the Ghana Civil Aviation Authority (GCAA). The necessity of this study stems from the fact that, electromagnetic compatibility (EMC) between FM audio broadcast and aeronautical radio communication services operating in the range of 85.7-108MHz and 108-117.975 MHz respectively is essential for safe flight operation. An analytical method of estimating the 3rd order intermodulation distortion has first been presented followed by simulation approach with the intermodulation analysis software v.10 and subsequent simulation with the Matlab software to determine and display the power spectral density of the output signals. All FM station frequencies in the Greater Accra region have been considered and paired to form dual tone signals that were considered input signal before assessing the impact of the 3rd order intermodulation harmonic. It was found that multiple 3rd order intermodulation harmonics distort and perturbate the aeronautical communication system in the Greater Accra region and these lead to severe safety implications for the operation of the aeronautical navigation system. It was recommended that broadcasting stations should implement cavity filters to reduce the effect of 3rd order intermodulation harmonics; they should respect the specification prescribed to them by the NCA and operate within limits allocated to them in order not to breach the international regulation of ITU that deems it an offense to interfere with the aeronautical communication system and to further ensure safety to the aviation navigation system.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"519 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123130497","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 : 2019-03-27DOI: 10.1109/ICCMA.2019.00022
Owusu Agyeman Antwi, A. Acakpovi
In this paper, a comprehensive evaluation of intercell interference and BER on the physical downlink channel of an LTE cellular network is undertaken. Because spectrum bandwidth is a scarce resource, operators are compelled to reassign frequency in a process called frequency reuse. However, the downlink channel of the currently deployed LTE network in Ghana, has low average throughput and data rate. This results from the fact that an interfering cell from adjacent eNodeB interrupts with the serving eNodeB. For cell-edge users (CEUs), the effect of inter-cell interference is especially severe. MATLAB was used to build models and to carry out simulations on the evaluation of this form of interference in LTE network. Simulation results were obtained for BER considering different adaptive modulation and also for simulation of the PDSCH transceiver which depicts the effect of inter-cell interference on the downlink throughput.
{"title":"Evaluation of Inter-Cell Interference and BER on a Downlink PDSCH of the LTE Network","authors":"Owusu Agyeman Antwi, A. Acakpovi","doi":"10.1109/ICCMA.2019.00022","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00022","url":null,"abstract":"In this paper, a comprehensive evaluation of intercell interference and BER on the physical downlink channel of an LTE cellular network is undertaken. Because spectrum bandwidth is a scarce resource, operators are compelled to reassign frequency in a process called frequency reuse. However, the downlink channel of the currently deployed LTE network in Ghana, has low average throughput and data rate. This results from the fact that an interfering cell from adjacent eNodeB interrupts with the serving eNodeB. For cell-edge users (CEUs), the effect of inter-cell interference is especially severe. MATLAB was used to build models and to carry out simulations on the evaluation of this form of interference in LTE network. Simulation results were obtained for BER considering different adaptive modulation and also for simulation of the PDSCH transceiver which depicts the effect of inter-cell interference on the downlink throughput.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130126615","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}
E-commerce and the financial services sector continue to rely hugely on the internet towards performing their activities. The need for a secured and protected environment to support the use of the internet has become critical in our time. A strong encryption system is required to protect data stored at a maximum level. The need for a strong and faster encryption algorithm to provide anenhanced network security has become relevant in recent time. This paper addresses the above issue by using a cryptographic method by applying the AES 256-bit algorithm (Rijndael) method of encryption and Non-Deterministic Algorithm (Monte- Carlo Simulation). An algorithm for encrypting and decrypting was built mainly for encrypting and decrypting documents coupled with non-deterministic approach for key generation. The system was designed, developed and the results obtained.
电子商务和金融服务部门继续在很大程度上依赖互联网来开展活动。在我们这个时代，需要一个安全的、受保护的环境来支持互联网的使用已经变得至关重要。为了最大程度地保护存储的数据，需要一个强大的加密系统。近年来，需要一种强大而快速的加密算法来提供增强的网络安全性已经变得非常重要。本文采用AES 256位算法(Rijndael)和非确定性算法(Monte- Carlo Simulation)的加密方法解决了上述问题。建立了一种加密和解密算法，主要用于对文档进行加密和解密，并结合了非确定性的密钥生成方法。对系统进行了设计、开发并取得了效果。
{"title":"A Cryptographic Algorithm Based On Aes Cipher Andnondeterministic Algorithm Approach For Key Generation","authors":"Amoah Emmanuel Ofosu, Q. Kester, Attah Josephine Akosua Anyanewah","doi":"10.1109/ICCMA.2019.00024","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00024","url":null,"abstract":"E-commerce and the financial services sector continue to rely hugely on the internet towards performing their activities. The need for a secured and protected environment to support the use of the internet has become critical in our time. A strong encryption system is required to protect data stored at a maximum level. The need for a strong and faster encryption algorithm to provide anenhanced network security has become relevant in recent time. This paper addresses the above issue by using a cryptographic method by applying the AES 256-bit algorithm (Rijndael) method of encryption and Non-Deterministic Algorithm (Monte- Carlo Simulation). An algorithm for encrypting and decrypting was built mainly for encrypting and decrypting documents coupled with non-deterministic approach for key generation. The system was designed, developed and the results obtained.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117117574","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00018
R. Abubakar, E. Effah, S. Frimpong, A. Acakpovi, P. Acheampong, G. Kadambi, K. M. S. Kumar
Deployment of Smart Grid is neither a goal nor a destination, but rather an enabler to the provision of reliable, secured and clean electricity for the end- user or consumer. Overall Smart Grid vision is very well explained with the future of electricity systems, which largely depends on digitization and automation of the overall electricity value-chain, by enhancing electric power information to bi-directional flow and the provision of services that can support the operations of the generation, distribution and end-user usage of power can lead to improvement of electric power system efficiency. This work aims at analyzing factors and forecast effects on the adoption of Smart Grid in Ghana using Pattern Recognition Neural Net. The Primary data was collected using structured questionnaire and the questions were designed to test the perception of consumers on the deployment of Smart Grid. Also, the target group of respondents covered 80% of the regions in Ghana. Based on the collected data, the pattern recognition neural networks was employed in the analysis of data. Results indicated that education, government policy, cost and safety were the main drivers to the deployment of Smart Grid in Ghana. Other drivers like culture and societal perception recorded as insignificant variables to the deployment of distributed generation in Ghana. It is recommended that further research work should examine the extent of infrastructural preparedness of Ghana for the deployment of Smart Grid.
{"title":"Adoption of Smart Grid in Ghana Using Pattern Recognition Neural Networks","authors":"R. Abubakar, E. Effah, S. Frimpong, A. Acakpovi, P. Acheampong, G. Kadambi, K. M. S. Kumar","doi":"10.1109/ICCMA.2019.00018","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00018","url":null,"abstract":"Deployment of Smart Grid is neither a goal nor a destination, but rather an enabler to the provision of reliable, secured and clean electricity for the end- user or consumer. Overall Smart Grid vision is very well explained with the future of electricity systems, which largely depends on digitization and automation of the overall electricity value-chain, by enhancing electric power information to bi-directional flow and the provision of services that can support the operations of the generation, distribution and end-user usage of power can lead to improvement of electric power system efficiency. This work aims at analyzing factors and forecast effects on the adoption of Smart Grid in Ghana using Pattern Recognition Neural Net. The Primary data was collected using structured questionnaire and the questions were designed to test the perception of consumers on the deployment of Smart Grid. Also, the target group of respondents covered 80% of the regions in Ghana. Based on the collected data, the pattern recognition neural networks was employed in the analysis of data. Results indicated that education, government policy, cost and safety were the main drivers to the deployment of Smart Grid in Ghana. Other drivers like culture and societal perception recorded as insignificant variables to the deployment of distributed generation in Ghana. It is recommended that further research work should examine the extent of infrastructural preparedness of Ghana for the deployment of Smart Grid.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"37 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":"116822328","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00009
Shuo Pan, Lv Gang, Zhu Pei-yi
Considering sophisticated optical path system, low efficiency and accuracy in the traditional screening of food safety, some improvement methods are proposed for the traditional screening equipment of food safety. The equipment is took rear spectroscopic measuring technique and linear array Charge-coupled Device (CCD) which can realize real-time detection within visible range. Automatic liquid surface sensing and tracking technology in the process of sample injection are accepted for improving the test accuracy. Verification experiment through the equipment to accurately determine multicomponent pigment measurement, the results indicate that the equipment showed potential for the rapid testing of adulterated food.
{"title":"Development of Rapid-Testing Technology for the Screening of Food Safety","authors":"Shuo Pan, Lv Gang, Zhu Pei-yi","doi":"10.1109/ICCMA.2019.00009","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00009","url":null,"abstract":"Considering sophisticated optical path system, low efficiency and accuracy in the traditional screening of food safety, some improvement methods are proposed for the traditional screening equipment of food safety. The equipment is took rear spectroscopic measuring technique and linear array Charge-coupled Device (CCD) which can realize real-time detection within visible range. Automatic liquid surface sensing and tracking technology in the process of sample injection are accepted for improving the test accuracy. Verification experiment through the equipment to accurately determine multicomponent pigment measurement, the results indicate that the equipment showed potential for the rapid testing of adulterated food.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"29 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":"134155274","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00010
M. A. Boateng, F. Oduro-Gyimah, Daniel Kuyoli Ngala
Dependence between random variables is a phenomenon that cannot be over emphasized. This study considered the dependence between consumption and maximum demand for a bulk electricity customer when it comes to its electricity load. The study applied the Clayton, Frank, Gumbel, Joe and Tawn Type 1 copulas to the realizations of the random variables (consumption and maximum demand). Considering the AICs and BICs of the models under study, the Tawn Type 1 copula model best represented the dependence between consumption and maximum demand. Using the inverse marginal distributions of both consumption and maximum demand, actual values were obtained from the pseudoobservations provided by the Tawn Type 1 copula. All the models revealed the presence of lower tail dependence between the two variables, with the exception of the Frank copula. The selected model was used to forecast load consumption and maximum demand.
{"title":"Bivariate Copula Modeling of Electricity Load, Case Study of Kwame Nkrumah University of Science and Technology","authors":"M. A. Boateng, F. Oduro-Gyimah, Daniel Kuyoli Ngala","doi":"10.1109/ICCMA.2019.00010","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00010","url":null,"abstract":"Dependence between random variables is a phenomenon that cannot be over emphasized. This study considered the dependence between consumption and maximum demand for a bulk electricity customer when it comes to its electricity load. The study applied the Clayton, Frank, Gumbel, Joe and Tawn Type 1 copulas to the realizations of the random variables (consumption and maximum demand). Considering the AICs and BICs of the models under study, the Tawn Type 1 copula model best represented the dependence between consumption and maximum demand. Using the inverse marginal distributions of both consumption and maximum demand, actual values were obtained from the pseudoobservations provided by the Tawn Type 1 copula. All the models revealed the presence of lower tail dependence between the two variables, with the exception of the Frank copula. The selected model was used to forecast load consumption and maximum demand.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","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":"129369531","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00021
Nusrat-Jahan Abubakar, Emmanuel Freeman
The aim of this study is to model an appropriate Total Quality Management (TQM) framework for Higher Education Institutions (HEIs) in developed and developing countries particularly Ghana. The driving force for this study is the low-quality standards that most public universities in Ghana have compromised over the past years. However, they are known as the best standards for most private institutions. This situation called for the need for the researchers to embark on this study. Empirical studies of TQM and TQM frameworks in HEIs was conducted. The study employed both qualitative and quantitative analysis. The case study design was also used to describe and access the phenomenon. Purposive sampling technique was used to select fifteen (15) Quality Assurance Officials from three public HEIs in Ghana. A sample size of 400 respondents were used for the analysis of the quantitative data. The qualitative data collected were analyzed using thematic analysis. The findings from the study aided in a rigorous analysis to model an Academic Quality (ACQ) framework which was not done by prior studies. Key findings were verified and validated based on the ACQ model. Finally, the verification of the ACQ model indicated that it is workable and so HEIs can adopt for it usage.
{"title":"Modeling Total Quality Management Framework for Higher Education Institutions in Ghana","authors":"Nusrat-Jahan Abubakar, Emmanuel Freeman","doi":"10.1109/ICCMA.2019.00021","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00021","url":null,"abstract":"The aim of this study is to model an appropriate Total Quality Management (TQM) framework for Higher Education Institutions (HEIs) in developed and developing countries particularly Ghana. The driving force for this study is the low-quality standards that most public universities in Ghana have compromised over the past years. However, they are known as the best standards for most private institutions. This situation called for the need for the researchers to embark on this study. Empirical studies of TQM and TQM frameworks in HEIs was conducted. The study employed both qualitative and quantitative analysis. The case study design was also used to describe and access the phenomenon. Purposive sampling technique was used to select fifteen (15) Quality Assurance Officials from three public HEIs in Ghana. A sample size of 400 respondents were used for the analysis of the quantitative data. The qualitative data collected were analyzed using thematic analysis. The findings from the study aided in a rigorous analysis to model an Academic Quality (ACQ) framework which was not done by prior studies. Key findings were verified and validated based on the ACQ model. Finally, the verification of the ACQ model indicated that it is workable and so HEIs can adopt for it usage.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"334 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":"115966418","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00020
F. Oduro-Gyimah, K. Boateng
The study compared the forecasting performance of two multiple-input and multiple-output (MIMO) and two single-input and single-output (SISO) neural networks using 4G network traffic data aggregated into daily, weekly and monthly time spans. To explore the best configuration of SISO and MIMO neural networks, the empirical traffic data of 1-input, 2- input and 3-input were used together with varying the parameters of the models. The study concluded that for 2-input, MIMO Radial basis function neural (RBFN) network performed better than the 2-input MIMO Multilayer perceptron (MLP) neural network in predicting the traffic data. In the case of 3-input, MLP network was found to be more efficient than RBFN network. In the scenario of SISO architecture, the MLP network outperformed the RBFN network for 4G daily, weekly and monthly traffic data.
{"title":"Forecasting Abilities of MIMO and SISO Neural Networks: A Comparative Study using Telecommunication Traffic Data","authors":"F. Oduro-Gyimah, K. Boateng","doi":"10.1109/ICCMA.2019.00020","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00020","url":null,"abstract":"The study compared the forecasting performance of two multiple-input and multiple-output (MIMO) and two single-input and single-output (SISO) neural networks using 4G network traffic data aggregated into daily, weekly and monthly time spans. To explore the best configuration of SISO and MIMO neural networks, the empirical traffic data of 1-input, 2- input and 3-input were used together with varying the parameters of the models. The study concluded that for 2-input, MIMO Radial basis function neural (RBFN) network performed better than the 2-input MIMO Multilayer perceptron (MLP) neural network in predicting the traffic data. In the case of 3-input, MLP network was found to be more efficient than RBFN network. In the scenario of SISO architecture, the MLP network outperformed the RBFN network for 4G daily, weekly and monthly traffic data.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"29 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":"125316441","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 : 2019-03-01DOI: 10.1109/ICCMA.2019.00023
Paul A. Agbodza
In this paper the fundamental solution to CMSVJD is implemented to simulate USD/GHS forward exchange rates under the condition of jumps. CMSVJD was generalized in this study to include conditions of ‘no jump’ and ‘reduced parameters’. The model captures both stochastic volatility and jumps. Stochastic calculus modeling and machine learning interface is the answer to speculators and chartists driving prices in the Ghana interbank market (a frontier market). Codes written in R were used for simulation and plot of results. A 5-fold cross validation was used to create the test sample data, as proxy for forward rates required to validate the performance of the model. The resultant machine yields a predictive result of forward USD/GHS rates with a mean squared error of 0.169% and 0.5%.
{"title":"Ito Calculus-Machine Learning Projection of Forward US Dollar-Ghana Cedi Rates","authors":"Paul A. Agbodza","doi":"10.1109/ICCMA.2019.00023","DOIUrl":"https://doi.org/10.1109/ICCMA.2019.00023","url":null,"abstract":"In this paper the fundamental solution to CMSVJD is implemented to simulate USD/GHS forward exchange rates under the condition of jumps. CMSVJD was generalized in this study to include conditions of ‘no jump’ and ‘reduced parameters’. The model captures both stochastic volatility and jumps. Stochastic calculus modeling and machine learning interface is the answer to speculators and chartists driving prices in the Ghana interbank market (a frontier market). Codes written in R were used for simulation and plot of results. A 5-fold cross validation was used to create the test sample data, as proxy for forward rates required to validate the performance of the model. The resultant machine yields a predictive result of forward USD/GHS rates with a mean squared error of 0.169% and 0.5%.","PeriodicalId":413965,"journal":{"name":"2019 International Conference on Computing, Computational Modelling and Applications (ICCMA)","volume":"95 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":"130415230","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：