Pub Date : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497139
Sadia Nazim, Syed Sajjad Hussain, M. Moinuddin, Muhammad Zubair, Rizwan Tanweer
Over the past few decades, the major debate regarding healthcare throughout the world is the analysis, and findings of diseases by investigating the medical images. Musculoskeletal disorder classification from a massive radiological image archive has always been a tedious task for radiologists. In recent literature, deep learning paves its way towards biomedical image classification with maximum accuracy and efficiency. Besides, deep learning models have already outperformed in various medical applications. Specifically, Convolution Neural Network (CNN) and LSTM architecture have been widely used. In this paper, new variants of conventional deep learning models have been proposed. Subsequently, an exhaustive parametric comparison from the existing pre-trained model has been established to validate the improved efficacy and productivity.
{"title":"Parametric Evaluation of Improved Deep Learning Networks for Musculoskeletal Disorder (MSD) Classification","authors":"Sadia Nazim, Syed Sajjad Hussain, M. Moinuddin, Muhammad Zubair, Rizwan Tanweer","doi":"10.1109/ICCOINS49721.2021.9497139","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497139","url":null,"abstract":"Over the past few decades, the major debate regarding healthcare throughout the world is the analysis, and findings of diseases by investigating the medical images. Musculoskeletal disorder classification from a massive radiological image archive has always been a tedious task for radiologists. In recent literature, deep learning paves its way towards biomedical image classification with maximum accuracy and efficiency. Besides, deep learning models have already outperformed in various medical applications. Specifically, Convolution Neural Network (CNN) and LSTM architecture have been widely used. In this paper, new variants of conventional deep learning models have been proposed. Subsequently, an exhaustive parametric comparison from the existing pre-trained model has been established to validate the improved efficacy and productivity.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124422259","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497235
Mogana Vadiveloo, Mishal Almazrooie, R. Abdullah
In this paper, the main idea is to investigate the hypothesis that superlinear speedup occurs when the concurrent threads on General Purposes Graphic Processing Units (GPGPU) carry heavy workloads. In order to evaluate this hypothesis, Laplacian image edge detection algorithm with convolution filtering is chosen as a case study. In this work, local memories of GPGPU are utilized in order to achieve the superlinear speedup. The convolution filtering kernels of the Laplacian edge detection algorithm are invoked in these local memories. By this, the low latency of the GPGPGU local memory are deployed efficiently and this subsequently leads to a higher speedup. The results obtained presented that the superlinear speedup is achieved when the size of the convolution kernel is large. In this study, when the convolution kernel size is 7×7, superlinear speedup is observed for image dataset of sizes between 1KB-2500KB.
{"title":"Superlinear Speedup on GPGPU Using Laplacian Algorithm with Convolution Filtering as A Case Study","authors":"Mogana Vadiveloo, Mishal Almazrooie, R. Abdullah","doi":"10.1109/ICCOINS49721.2021.9497235","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497235","url":null,"abstract":"In this paper, the main idea is to investigate the hypothesis that superlinear speedup occurs when the concurrent threads on General Purposes Graphic Processing Units (GPGPU) carry heavy workloads. In order to evaluate this hypothesis, Laplacian image edge detection algorithm with convolution filtering is chosen as a case study. In this work, local memories of GPGPU are utilized in order to achieve the superlinear speedup. The convolution filtering kernels of the Laplacian edge detection algorithm are invoked in these local memories. By this, the low latency of the GPGPGU local memory are deployed efficiently and this subsequently leads to a higher speedup. The results obtained presented that the superlinear speedup is achieved when the size of the convolution kernel is large. In this study, when the convolution kernel size is 7×7, superlinear speedup is observed for image dataset of sizes between 1KB-2500KB.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132008921","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497182
T. Hastuti, Ridwan Sanjaya, Freddy Koeswoyo
Financial statements as a tool for show the company financial performance and can be used as a basis for making economic decisions. Understanding of accounting standards specifically for SMEs can help SMEs in making business decisions. Information technology support and investment opportunity in SMEs are important factors that can help improve the financial performance of SMEs. Investment opportunity can be seen from the development of market tastes and reflection on the development of SMEs businesses. Investment opportunity is also obtained by innovating in production and marketing. The development of the SMEs business is in line with increasing business age. This shows the ability to survive batik business in facing the times and business competition. This study examines the factors that influence the financial performance of SMEs. using a sample of batik craftsmen. Data analysis was performed using multiple regression program which are currently widely used by researchers to test the research model that they formulate. The result of this research were (1) for small and medium-sized enterprises (SMEs), the company's age and investments opportunity greatly affect the company's financial performance. (2) IT support and good financial management in small and medium enterprises (SMEs) do not affect the company's financial performance.
{"title":"The Investment Opportunity, Information Technology and Financial Performance of SMEs","authors":"T. Hastuti, Ridwan Sanjaya, Freddy Koeswoyo","doi":"10.1109/ICCOINS49721.2021.9497182","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497182","url":null,"abstract":"Financial statements as a tool for show the company financial performance and can be used as a basis for making economic decisions. Understanding of accounting standards specifically for SMEs can help SMEs in making business decisions. Information technology support and investment opportunity in SMEs are important factors that can help improve the financial performance of SMEs. Investment opportunity can be seen from the development of market tastes and reflection on the development of SMEs businesses. Investment opportunity is also obtained by innovating in production and marketing. The development of the SMEs business is in line with increasing business age. This shows the ability to survive batik business in facing the times and business competition. This study examines the factors that influence the financial performance of SMEs. using a sample of batik craftsmen. Data analysis was performed using multiple regression program which are currently widely used by researchers to test the research model that they formulate. The result of this research were (1) for small and medium-sized enterprises (SMEs), the company's age and investments opportunity greatly affect the company's financial performance. (2) IT support and good financial management in small and medium enterprises (SMEs) do not affect the company's financial performance.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134395827","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497135
I. R. Ermawati, Meyta Dwi Kurniasih, Sri Astuti, Onny Fitriana, Wan Fatimah Wan Achmad, Mohd Hilmi Hasan
This study aims to determine the design stages of developing blended learning smartphone media learning products and to determine the feasibility of integral learning media using the developed flipbook. This study uses a small-scale trial on FHIP UHAMKA while for large-scale trials conducted by Malaysian UTP with 29 respondents including Physics Education FKIP UHAMKA, Mathematics Education FKIP UHAMKA and also Malaysian UTP. The method used is Research and Development (R&D) using the Brog and Gall development procedure. The results of the media interface test obtained a percentage of 77.18%. This shows that the products developed included in the category are very feasible to use while for the effectiveness of students as teaching material in the learning process, the average of the effectiveness of students is 83.26%, the value obtained can be said to be very well seen from the Likert scale index used, then from the assessment of the effectiveness of media students it is feasible to be used in integral learning. Blended learning media with character given to one class in FKIP UHAMKA, obtained an average post-test score of 48.04. The data obtained, the character development of the character questionnaire was 75.04.
{"title":"Development of Blended Learning Media Using Character-Based Flipbook Smartphone","authors":"I. R. Ermawati, Meyta Dwi Kurniasih, Sri Astuti, Onny Fitriana, Wan Fatimah Wan Achmad, Mohd Hilmi Hasan","doi":"10.1109/ICCOINS49721.2021.9497135","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497135","url":null,"abstract":"This study aims to determine the design stages of developing blended learning smartphone media learning products and to determine the feasibility of integral learning media using the developed flipbook. This study uses a small-scale trial on FHIP UHAMKA while for large-scale trials conducted by Malaysian UTP with 29 respondents including Physics Education FKIP UHAMKA, Mathematics Education FKIP UHAMKA and also Malaysian UTP. The method used is Research and Development (R&D) using the Brog and Gall development procedure. The results of the media interface test obtained a percentage of 77.18%. This shows that the products developed included in the category are very feasible to use while for the effectiveness of students as teaching material in the learning process, the average of the effectiveness of students is 83.26%, the value obtained can be said to be very well seen from the Likert scale index used, then from the assessment of the effectiveness of media students it is feasible to be used in integral learning. Blended learning media with character given to one class in FKIP UHAMKA, obtained an average post-test score of 48.04. The data obtained, the character development of the character questionnaire was 75.04.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133581218","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497166
M. Faris, T. Javid, SS H. Rizvi, A. Aziz
Compressed Sensing theory promises to reconstruct the magnetic resonance images from partially sampled k-space data. Through this Compressed sensing - magnetic resonance imaging CS-MRI technique, we accelerate the reconstruction process but at the cost of high artifacts especially with the increase of high reduction factor and high reconstruction time. To minimize these artifacts, we proposed a segmented region based reconstruction technique to enhance the quality image without affecting much more the reconstruction time. In this algorithm, the partial k-space data segmented into two parts according to their frequencies. At central part which has lower frequency components selected and predicted by nuclear norm minimization. After that the part is fused with peripheral part of the k-space components and apply this recovery technique another time to reconstruct more accurate images in terms of conventional techniques. To analyze the performance of proposed algorithm, we compare the results for different data sets of brain with CS techniques. Better results in term of NMSE and time shows the effectiveness of proposed method with high reduction factor of data.
{"title":"Segmented Region Based Reconstruction of Magnetic Resonance Image","authors":"M. Faris, T. Javid, SS H. Rizvi, A. Aziz","doi":"10.1109/ICCOINS49721.2021.9497166","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497166","url":null,"abstract":"Compressed Sensing theory promises to reconstruct the magnetic resonance images from partially sampled k-space data. Through this Compressed sensing - magnetic resonance imaging CS-MRI technique, we accelerate the reconstruction process but at the cost of high artifacts especially with the increase of high reduction factor and high reconstruction time. To minimize these artifacts, we proposed a segmented region based reconstruction technique to enhance the quality image without affecting much more the reconstruction time. In this algorithm, the partial k-space data segmented into two parts according to their frequencies. At central part which has lower frequency components selected and predicted by nuclear norm minimization. After that the part is fused with peripheral part of the k-space components and apply this recovery technique another time to reconstruct more accurate images in terms of conventional techniques. To analyze the performance of proposed algorithm, we compare the results for different data sets of brain with CS techniques. Better results in term of NMSE and time shows the effectiveness of proposed method with high reduction factor of data.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123248577","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497212
Ahmed Sikander, Syed Sajjad Hussain Rizvi, R. Hussain, Jawwad Ahmed, Sheeraz Arif
In the World of Communication, digital transmission has its importance in sense of speed and accuracy which is the basic requirement of current time. Nowadays, successful as well as rapid communication is the main concern of the research. It can be achieved by using different technique and methods based on theories built upon the branches of applied sciences and engineering. In this research an algorithm is presented by sequentially combining two transforms, Wavelet and Krylov. The Algorithm was formerly developed by the same and was known as WK Algorithm. In this research the Algorithm is first studied for digital signal application and results are presented and concluded by applying also with other two methods in order to verify and validate the research.
{"title":"Application of a Wavelet based Krylov Subspace Algorithm on Digital Signal Convergence","authors":"Ahmed Sikander, Syed Sajjad Hussain Rizvi, R. Hussain, Jawwad Ahmed, Sheeraz Arif","doi":"10.1109/ICCOINS49721.2021.9497212","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497212","url":null,"abstract":"In the World of Communication, digital transmission has its importance in sense of speed and accuracy which is the basic requirement of current time. Nowadays, successful as well as rapid communication is the main concern of the research. It can be achieved by using different technique and methods based on theories built upon the branches of applied sciences and engineering. In this research an algorithm is presented by sequentially combining two transforms, Wavelet and Krylov. The Algorithm was formerly developed by the same and was known as WK Algorithm. In this research the Algorithm is first studied for digital signal application and results are presented and concluded by applying also with other two methods in order to verify and validate the research.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123973410","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497221
Shiladitya Bhattacharjee, Lukman A. B. Rahim
The importance of seismic big data exploration, especially in gas and oil industries, is indispensable. The processing of such complex data becomes more critical when its size is extremely large. These days the dispose of seismic big data over the network is notably common. Hence, the security of this huge complex data is equally important during its transportation over an insecure channel. Consequently, the application of any security algorithm on complex big seismic data makes it impractical for adopting it in any industry. Numerous researches have been conducted to resolve these issues. However, any unified solution has not been proclaimed by the exiting related studies. Therefore, this research work affirms a unique unified platform that uses the integration of Hadoop and Hive for parallel processing and advanced indexing for faster execution of large complex data. At the same time, it uses a low complex elliptic curve cryptography (ECC) to ensure data security in terms of data confidentiality and integrity. The result shows that the proposed integrated technique offers higher time efficiency in terms of producing higher Throughput than other security combinations. It further shows it produces a low percentage of Data Loss and higher Entropy Value as well as Avalanche Effect which justifies its ability to offer higher data confidentiality and integrity.
{"title":"A Hadoop Allied Security Platform for Seismic Big Data Processing","authors":"Shiladitya Bhattacharjee, Lukman A. B. Rahim","doi":"10.1109/ICCOINS49721.2021.9497221","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497221","url":null,"abstract":"The importance of seismic big data exploration, especially in gas and oil industries, is indispensable. The processing of such complex data becomes more critical when its size is extremely large. These days the dispose of seismic big data over the network is notably common. Hence, the security of this huge complex data is equally important during its transportation over an insecure channel. Consequently, the application of any security algorithm on complex big seismic data makes it impractical for adopting it in any industry. Numerous researches have been conducted to resolve these issues. However, any unified solution has not been proclaimed by the exiting related studies. Therefore, this research work affirms a unique unified platform that uses the integration of Hadoop and Hive for parallel processing and advanced indexing for faster execution of large complex data. At the same time, it uses a low complex elliptic curve cryptography (ECC) to ensure data security in terms of data confidentiality and integrity. The result shows that the proposed integrated technique offers higher time efficiency in terms of producing higher Throughput than other security combinations. It further shows it produces a low percentage of Data Loss and higher Entropy Value as well as Avalanche Effect which justifies its ability to offer higher data confidentiality and integrity.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122753737","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497159
Jin-Chuan See, Jing-Jing Chang, Hui-Fuang Ng, K. Mok, Wai-Kong Lee
As Internet of Things (IoT) continues to advance, the gap between IoT and Artificial Intelligence (AI) is getting smaller. IoT sensor node with "smart" capability has become a highly demanded infrastructure to realize Industrial 4.0. Typically, deep learning algorithms are implemented in Graphic Processing Unit (GPU) for high performance. But when it comes to adoption in IoT environment, integrating sensor node with a GPU may pose a major challenge due to high energy consumption. This paper discusses the basic idea on how to implement a deep learning core, specifically for Convolutional Neural Network (CNN) onto the Field Programmable Gate Array (FPGA). Optimization was proposed to reduce number of multiplications needed to address memory contents, hence reducing Digital Signal Processing (DSP) unit synthesized. Synthesis result shows a relatively low hardware area with reasonable performance on both Artix-7 and Virtex-7 FPGA.
{"title":"Design and Implementation of Deep Learning Core for FPGA Platform","authors":"Jin-Chuan See, Jing-Jing Chang, Hui-Fuang Ng, K. Mok, Wai-Kong Lee","doi":"10.1109/ICCOINS49721.2021.9497159","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497159","url":null,"abstract":"As Internet of Things (IoT) continues to advance, the gap between IoT and Artificial Intelligence (AI) is getting smaller. IoT sensor node with \"smart\" capability has become a highly demanded infrastructure to realize Industrial 4.0. Typically, deep learning algorithms are implemented in Graphic Processing Unit (GPU) for high performance. But when it comes to adoption in IoT environment, integrating sensor node with a GPU may pose a major challenge due to high energy consumption. This paper discusses the basic idea on how to implement a deep learning core, specifically for Convolutional Neural Network (CNN) onto the Field Programmable Gate Array (FPGA). Optimization was proposed to reduce number of multiplications needed to address memory contents, hence reducing Digital Signal Processing (DSP) unit synthesized. Synthesis result shows a relatively low hardware area with reasonable performance on both Artix-7 and Virtex-7 FPGA.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115613898","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497142
Sri Astuti, Aisyah Fitriana, W. F. Wan Ahmad, Imas Ratna Ermawati, M. Hasan
This research is concerned with the use of development applications using mobile devices as a tool for blended learning models. However, in developing learning applications, one important concern is the user interface (UI). Therefore, the purpose of this research is to find out which UI design components are easy to use according to the user to be more user friendly, so that the purpose of using mobile applications for education can be realized. This study covers design principles that are appropriate for applications developed for platforms. Based on research, user interface testing has been carried out from 5 user interface principles and analysis using the System Usage Scale (SUS) given to 32 respondents. The results showed that the majority of respondents agreed that the mobile application developed had met the requirements of the user interface element.
{"title":"Analysis User Interface: Mobile Application to Blended Learning Model","authors":"Sri Astuti, Aisyah Fitriana, W. F. Wan Ahmad, Imas Ratna Ermawati, M. Hasan","doi":"10.1109/ICCOINS49721.2021.9497142","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497142","url":null,"abstract":"This research is concerned with the use of development applications using mobile devices as a tool for blended learning models. However, in developing learning applications, one important concern is the user interface (UI). Therefore, the purpose of this research is to find out which UI design components are easy to use according to the user to be more user friendly, so that the purpose of using mobile applications for education can be realized. This study covers design principles that are appropriate for applications developed for platforms. Based on research, user interface testing has been carried out from 5 user interface principles and analysis using the System Usage Scale (SUS) given to 32 respondents. The results showed that the majority of respondents agreed that the mobile application developed had met the requirements of the user interface element.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115133963","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 : 2021-07-13DOI: 10.1109/ICCOINS49721.2021.9497204
Sumayema Kabir Ricky, L. Rahim
This project is the development of an analysis system for historical Metocean Data. It is a single page reactive web application with shiny web UI package of R containing forecasting model, ARIMA and two ML algorithms, Linear Regression and H2O AutoML developed with R for the variables of Metocean data stored in HDFS of a virtual Hadoop cluster and spark is integrated to make the computations happen in-memory. The predictions is compared to the actual data to see its correctness with RMSE. Performance difference of the application deployed on desktop and on the server is also discussed. The application performs better when running in the server than on desktop.
本项目是开发一个历史海洋气象数据分析系统。它是一个单页响应式web应用程序，具有闪亮的R web UI包，包含预测模型，ARIMA和两种ML算法，线性回归和H2O AutoML，用R开发，用于存储在虚拟Hadoop集群的HDFS中的Metocean数据的变量，并集成spark使计算发生在内存中。将预测与实际数据进行比较，以查看其与RMSE的正确性。还讨论了部署在桌面和服务器上的应用程序的性能差异。应用程序在服务器上运行时比在桌面上运行时性能更好。
{"title":"Metocean Prediction using Hadoop, Spark & R","authors":"Sumayema Kabir Ricky, L. Rahim","doi":"10.1109/ICCOINS49721.2021.9497204","DOIUrl":"https://doi.org/10.1109/ICCOINS49721.2021.9497204","url":null,"abstract":"This project is the development of an analysis system for historical Metocean Data. It is a single page reactive web application with shiny web UI package of R containing forecasting model, ARIMA and two ML algorithms, Linear Regression and H2O AutoML developed with R for the variables of Metocean data stored in HDFS of a virtual Hadoop cluster and spark is integrated to make the computations happen in-memory. The predictions is compared to the actual data to see its correctness with RMSE. Performance difference of the application deployed on desktop and on the server is also discussed. The application performs better when running in the server than on desktop.","PeriodicalId":245662,"journal":{"name":"2021 International Conference on Computer & Information Sciences (ICCOINS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121937948","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：