Pub Date : 2019-05-06DOI: 10.19101/IJACR.2018.839045
N. Mduma, K. Kalegele, D. Machuve
School dropout is a widely recognized serious issue in developing countries. On the other hand, machine learning techniques have gained much attention on addressing this problem. This paper, presents a thorough analysis of four supervised learning classifiers that represent linear, ensemble, instance and neural networks on Uwezo Annual Learning Assessment datasets for Tanzania as a case study. The goal of the study is to provide data-driven algorithm recommendations to current researchers on the topic. Using three metrics: geometric mean, F-measure and adjusted geometric mean, we assessed and quantified the effect of different sampling techniques on the imbalanced dataset for model selection. We further indicate the significance of hyper parameter tuning in improving predictive performance. The results indicate that two classifiers: logistic regression and multilayer perceptron achieve the highest performance when over-sampling technique was employed. Furthermore, hyper parameter tuning improves each algorithm's performance compared to its baseline settings and stacking these classifiers improves the overall predictive performance.
{"title":"Machine learning approach for reducing students dropout rates","authors":"N. Mduma, K. Kalegele, D. Machuve","doi":"10.19101/IJACR.2018.839045","DOIUrl":"https://doi.org/10.19101/IJACR.2018.839045","url":null,"abstract":"School dropout is a widely recognized serious issue in developing countries. On the other hand, machine learning techniques have gained much attention on addressing this problem. This paper, presents a thorough analysis of four supervised learning classifiers that represent linear, ensemble, instance and neural networks on Uwezo Annual Learning Assessment datasets for Tanzania as a case study. The goal of the study is to provide data-driven algorithm recommendations to current researchers on the topic. Using three metrics: geometric mean, F-measure and adjusted geometric mean, we assessed and quantified the effect of different sampling techniques on the imbalanced dataset for model selection. We further indicate the significance of hyper parameter tuning in improving predictive performance. The results indicate that two classifiers: logistic regression and multilayer perceptron achieve the highest performance when over-sampling technique was employed. Furthermore, hyper parameter tuning improves each algorithm's performance compared to its baseline settings and stacking these classifiers improves the overall predictive performance.","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115626609","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: 10.19101/ijacr.2018.839032
Fareduddin Ahmed Js, R. Ujjinimatad
{"title":"Power allocation optimization for fading channels in cognitive radio networks","authors":"Fareduddin Ahmed Js, R. Ujjinimatad","doi":"10.19101/ijacr.2018.839032","DOIUrl":"https://doi.org/10.19101/ijacr.2018.839032","url":null,"abstract":"","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"154 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":"121876014","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: 10.19101/IJACR.2018.838015
M. Seneviratne, K. Fernando, D. Karunaratne
Classifying documents into predefined classes is a very necessary task, especially in extracting information from huge resources such as web. Although a considerable amount of work has been carried out to classify documents into groups according to the subject domain or according to the other attributes. It still prevails as a big challenge in large scale, high dimensional document space. A number of techniques have been presented and proceeded with suggested improvements in order to achieve a higher degree of success in the document class. In this paper, a novel rule-based method for document classification with a combination of relation extraction techniques have been proposed. It is possible to replace overwhelming text classification techniques which involve thousands of words, document features or numerous patterns of word combinations by a set of rules which involves a much smaller number of entities and relations. We further discuss the effectiveness of relation extraction rules in document classification with the use of Markov logic networks for learning the weights of rules efficiently. Our experimental results show that the use of relation extraction rules on document classification yields a very high precision in the selected domain. We also demonstrate the applicability of our method on a benchmark text corpus with good performance measures.
{"title":"Generation of relation-extraction-rules based on Markov logic network for document classification","authors":"M. Seneviratne, K. Fernando, D. Karunaratne","doi":"10.19101/IJACR.2018.838015","DOIUrl":"https://doi.org/10.19101/IJACR.2018.838015","url":null,"abstract":"Classifying documents into predefined classes is a very necessary task, especially in extracting information from huge resources such as web. Although a considerable amount of work has been carried out to classify documents into groups according to the subject domain or according to the other attributes. It still prevails as a big challenge in large scale, high dimensional document space. A number of techniques have been presented and proceeded with suggested improvements in order to achieve a higher degree of success in the document class. In this paper, a novel rule-based method for document classification with a combination of relation extraction techniques have been proposed. It is possible to replace overwhelming text classification techniques which involve thousands of words, document features or numerous patterns of word combinations by a set of rules which involves a much smaller number of entities and relations. We further discuss the effectiveness of relation extraction rules in document classification with the use of Markov logic networks for learning the weights of rules efficiently. Our experimental results show that the use of relation extraction rules on document classification yields a very high precision in the selected domain. We also demonstrate the applicability of our method on a benchmark text corpus with good performance measures.","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"171 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":"127425107","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: 10.19101/IJACR.2018.839057
Muktikanta Sahu, G. K. Nayak
{"title":"An efficient parallel framework for process discovery using OpenMP","authors":"Muktikanta Sahu, G. K. Nayak","doi":"10.19101/IJACR.2018.839057","DOIUrl":"https://doi.org/10.19101/IJACR.2018.839057","url":null,"abstract":"","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"1 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":"130569754","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: 10.19101/IJACR.2018.839001
C. Hlaing, A. Thida
1.Introduction Text to speech (TTS) conversion is a system that can convert the written text into their corresponding speech. It is a very useful application for the visual and speech impaired person. The optimal character recognition (OCR) -based TTS system to help such visually challenged people by OCR has been proposed [1]. The resulting text from the OCR is converted into speech. They used the blind deconvolution method and pre-processing operation to remove the effect of noise and blur so that they can achieve the efficient result of the framework for visually challenged. Nowadays, high quality TTS software can be commercially available for different languages. The most used speech synthesis approaches are articulatory synthesis, formant synthesis, concatenative synthesis and hidden Markov model (HMM)-based model approach. Each approach has their reasonable advantages and disadvantages based on the usage of languages.
{"title":"Phoneme concatenation method considering half vowel sound for the Myanmar speech synthesis system","authors":"C. Hlaing, A. Thida","doi":"10.19101/IJACR.2018.839001","DOIUrl":"https://doi.org/10.19101/IJACR.2018.839001","url":null,"abstract":"1.Introduction Text to speech (TTS) conversion is a system that can convert the written text into their corresponding speech. It is a very useful application for the visual and speech impaired person. The optimal character recognition (OCR) -based TTS system to help such visually challenged people by OCR has been proposed [1]. The resulting text from the OCR is converted into speech. They used the blind deconvolution method and pre-processing operation to remove the effect of noise and blur so that they can achieve the efficient result of the framework for visually challenged. Nowadays, high quality TTS software can be commercially available for different languages. The most used speech synthesis approaches are articulatory synthesis, formant synthesis, concatenative synthesis and hidden Markov model (HMM)-based model approach. Each approach has their reasonable advantages and disadvantages based on the usage of languages.","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"69 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":"126995097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A leading cyber warfare strategy according to the evolution of cyber technology after the fourth industrial revolution","authors":"Sin-Kon Kim, Sang-Pil Cheon, Jung-Ho Eom","doi":"10.19101/IJACR.SOC6","DOIUrl":"https://doi.org/10.19101/IJACR.SOC6","url":null,"abstract":"","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121043936","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}
Sung-Hwa Han, Ju-Hyung Kim, Won-Seok Song, Gwangyong Gim
{"title":"An empirical analysis on medical information sharing model based on blockchain","authors":"Sung-Hwa Han, Ju-Hyung Kim, Won-Seok Song, Gwangyong Gim","doi":"10.19101/IJACR.SRS16001","DOIUrl":"https://doi.org/10.19101/IJACR.SRS16001","url":null,"abstract":"","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116587587","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}
1.Introduction Developers of distributed applications can implement communication functionalities from the scratch, but it is more efficient for them to use services provided by communication middleware or framework. Although previous work [1, 2] of the proposed scheme, existing general communication middleware’s [3−7], middleware’s for online social networks [8−12], and other recent middleware’s [13−15] provide generic or application-specific communication services, they do not support both the synchronous and asynchronous communications. Communication between a client and a server that existing approaches use is not determined by application requirements, but by their internal ways of communication channel management or kinds of services. Thus, if an application selects a middleware or a service, it also uses a fixed communication method between the client and the server.
{"title":"Supporting synchronous and asynchronous communications in event-based communication framework for client-server applications","authors":"Mingyu Lim","doi":"10.19101/IJACR.COM16004","DOIUrl":"https://doi.org/10.19101/IJACR.COM16004","url":null,"abstract":"1.Introduction Developers of distributed applications can implement communication functionalities from the scratch, but it is more efficient for them to use services provided by communication middleware or framework. Although previous work [1, 2] of the proposed scheme, existing general communication middleware’s [3−7], middleware’s for online social networks [8−12], and other recent middleware’s [13−15] provide generic or application-specific communication services, they do not support both the synchronous and asynchronous communications. Communication between a client and a server that existing approaches use is not determined by application requirements, but by their internal ways of communication channel management or kinds of services. Thus, if an application selects a middleware or a service, it also uses a fixed communication method between the client and the server.","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133197335","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}
The purpose of this study is to design education program and computational thinking (CT) rubrics evaluation lists using physical computing tools to improve effective CT skills. To do this, we analyzed the elements of CT, rubrics evaluation lists, and physical computing tools, and presented 12 rubric evaluation lists for learners. The contents of the education program were designed based on the real-life problem solving (RPLS) model. The education program design set a one topic for artifacts to be consistent with are CT element. Based on the rubrics of Kim JK, designed by analyzing the CT framework, we devised a CT rubrics evaluation list used the physical computing tools. After, this study is expected to be used as an effective CT teach program using the physical computing tools through the verification of the empirical
{"title":"Design of the rubrics evaluation lists and the education contents for improve the computational thinking by using physical computing tool","authors":"Junhyeong Lee, Hyeong-Ok Lee","doi":"10.19101/ijacr.com16001","DOIUrl":"https://doi.org/10.19101/ijacr.com16001","url":null,"abstract":"The purpose of this study is to design education program and computational thinking (CT) rubrics evaluation lists using physical computing tools to improve effective CT skills. To do this, we analyzed the elements of CT, rubrics evaluation lists, and physical computing tools, and presented 12 rubric evaluation lists for learners. The contents of the education program were designed based on the real-life problem solving (RPLS) model. The education program design set a one topic for artifacts to be consistent with are CT element. Based on the rubrics of Kim JK, designed by analyzing the CT framework, we devised a CT rubrics evaluation list used the physical computing tools. After, this study is expected to be used as an effective CT teach program using the physical computing tools through the verification of the empirical","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127499680","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}
Due to the rapid development of information technology worldwide, the spread of information technology has made the use of information systems prominent throughout the industry. In particular, the public sector claiming electronic government, provided convenient services, prompt administrative processing, and utilizing various public data. As a result, the beneficiary, the citizens, can use more services conveniently and easily, thus the amount of information data has increased sharply. As the reliance on such information systems continues to increase, the demand for stable and continuous service of information resources is also increasing, and due to unexpected natural disasters or cyber-attacks, the operation of various information systems is stopped being unable to function properly. It should also be prepared at all times for damage situations where critical data may be destroyed or lost and recovery may not be possible. Therefore, a safety management system that prevents the loss of credibility and financial loss caused by various disasters and system damage is becoming a necessity, not an option. The safest and most reliable method of technical and administrative safeguards for establishing safety management systems to ensure continuity of information systems against disasters and disasters is to backup the data to remote locations. Backing up data to a remote location in preparation for disruption and restoration of the main information system requires large budgets, such as technical and administrative considerations, network dedicated lines, and construction of a physical remote center. Therefore, for small and medium enterprises, it is a burdensome reality to build as such. Thus, this study is going to propose the composition of the remote backup center model using a public virtual private network and de-duplication backup technology for low-cost and high efficiency remote backup center model that can utilize small and medium sized agencies.
{"title":"A technical study of remote backup center performance using public virtual private network","authors":"Hooki Lee, Sungtaek Lee, JongHyuk Seong, Hogun Rou, Gwangyong Gim","doi":"10.19101/ijacr.srs16002","DOIUrl":"https://doi.org/10.19101/ijacr.srs16002","url":null,"abstract":"Due to the rapid development of information technology worldwide, the spread of information technology has made the use of information systems prominent throughout the industry. In particular, the public sector claiming electronic government, provided convenient services, prompt administrative processing, and utilizing various public data. As a result, the beneficiary, the citizens, can use more services conveniently and easily, thus the amount of information data has increased sharply. As the reliance on such information systems continues to increase, the demand for stable and continuous service of information resources is also increasing, and due to unexpected natural disasters or cyber-attacks, the operation of various information systems is stopped being unable to function properly. It should also be prepared at all times for damage situations where critical data may be destroyed or lost and recovery may not be possible. Therefore, a safety management system that prevents the loss of credibility and financial loss caused by various disasters and system damage is becoming a necessity, not an option. The safest and most reliable method of technical and administrative safeguards for establishing safety management systems to ensure continuity of information systems against disasters and disasters is to backup the data to remote locations. Backing up data to a remote location in preparation for disruption and restoration of the main information system requires large budgets, such as technical and administrative considerations, network dedicated lines, and construction of a physical remote center. Therefore, for small and medium enterprises, it is a burdensome reality to build as such. Thus, this study is going to propose the composition of the remote backup center model using a public virtual private network and de-duplication backup technology for low-cost and high efficiency remote backup center model that can utilize small and medium sized agencies.","PeriodicalId":273530,"journal":{"name":"International Journal of Advanced Computer Research","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127141126","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：