Pub Date : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp472-482
Jacob Abraham, Kirthika Natarajan, Senthilkumar Andi, Jemin Vijayaselvan Mariyarose, Manjunathan Alagarsamy, K. Suriyan
Wireless communication technology is well-established, and several antennas have been developed and produced specifically for this purpose. However, antenna performance and communication system development need to be enhanced in order to adapt to the present era. The performance of the antenna is significantly influenced by its design. Thus, this work produced a novel wideband antenna design via the use of a frequency reconfigurable approach. In the recommended study, microstrip patch antennas (MPAs) were used in wideband applications to switch frequencies using shunt-series microelectromechanical systems (MEMS). The suggested antenna, which has two switches built into it, is tested in ON-ON, OFF-ON, and OFF-OFF switching scenarios. Radiation pattern, voltage standing wave ratio (VSWR), gain, bandwidth, and return loss are among the antenna performance metrics used to assess the suggested antenna's performance in each switching situation. The simulation findings suggest that the optimal antenna design for usage in wireless communication systems is one that works well with a shunt-series MEMS switch.
{"title":"Frequency reconfigurable microstrip patch antenna for multiband applications","authors":"Jacob Abraham, Kirthika Natarajan, Senthilkumar Andi, Jemin Vijayaselvan Mariyarose, Manjunathan Alagarsamy, K. Suriyan","doi":"10.11591/ijres.v13.i2.pp472-482","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp472-482","url":null,"abstract":"Wireless communication technology is well-established, and several antennas have been developed and produced specifically for this purpose. However, antenna performance and communication system development need to be enhanced in order to adapt to the present era. The performance of the antenna is significantly influenced by its design. Thus, this work produced a novel wideband antenna design via the use of a frequency reconfigurable approach. In the recommended study, microstrip patch antennas (MPAs) were used in wideband applications to switch frequencies using shunt-series microelectromechanical systems (MEMS). The suggested antenna, which has two switches built into it, is tested in ON-ON, OFF-ON, and OFF-OFF switching scenarios. Radiation pattern, voltage standing wave ratio (VSWR), gain, bandwidth, and return loss are among the antenna performance metrics used to assess the suggested antenna's performance in each switching situation. The simulation findings suggest that the optimal antenna design for usage in wireless communication systems is one that works well with a shunt-series MEMS switch.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"51 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141695223","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp458-471
Chandrakala Chandrakala, Mungamuri Sasikala
The technique of video copy-move forgery (CMF) is commonly employed in various industries; digital videography is regularly used as the foundation for vital graphic evidence that may be modified using the aforementioned method. Recently in the past few decades, forgery in digital images is detected via machine intellect. The second issue includes continuous allocation of parallel frames having relevant backgrounds erroneously results in false implications, detected as CMF regions third include as the CMF is divided into inter-frame or intra-frame forgeries to detect video copy is not possible by most of the existing methods. Thus, this research presents the dual deep network (DDN) for efficient and effective video copy-move forgery detection (VCMFD); DDN comprises two networks; the first detection network (DetNet1) extracts the general deep features and second detection network (DetNet2) extracts the custom deep features; both the network are interconnected as the output of DetNet1 is given to DetNet2. Furthermore, a novel algorithm is introduced for forged frame detection and optimization of the falsely detected frame. DDN is evaluated considering the two benchmark datasets REWIND and video tampering dataset (VTD) considering different metrics; furthermore, evaluation is carried through comparing the recent existing model. DDN outperforms the existing model in terms of various metrics.
{"title":"An efficient novel dual deep network architecture for video forgery detection","authors":"Chandrakala Chandrakala, Mungamuri Sasikala","doi":"10.11591/ijres.v13.i2.pp458-471","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp458-471","url":null,"abstract":"The technique of video copy-move forgery (CMF) is commonly employed in various industries; digital videography is regularly used as the foundation for vital graphic evidence that may be modified using the aforementioned method. Recently in the past few decades, forgery in digital images is detected via machine intellect. The second issue includes continuous allocation of parallel frames having relevant backgrounds erroneously results in false implications, detected as CMF regions third include as the CMF is divided into inter-frame or intra-frame forgeries to detect video copy is not possible by most of the existing methods. Thus, this research presents the dual deep network (DDN) for efficient and effective video copy-move forgery detection (VCMFD); DDN comprises two networks; the first detection network (DetNet1) extracts the general deep features and second detection network (DetNet2) extracts the custom deep features; both the network are interconnected as the output of DetNet1 is given to DetNet2. Furthermore, a novel algorithm is introduced for forged frame detection and optimization of the falsely detected frame. DDN is evaluated considering the two benchmark datasets REWIND and video tampering dataset (VTD) considering different metrics; furthermore, evaluation is carried through comparing the recent existing model. DDN outperforms the existing model in terms of various metrics.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"76 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141692944","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp234-243
S. Hadiyoso, Ahmad Zaky Ramdani, I. D. Irawati, I. Wijayanto
Statistical calculations on signals commonly used in feature extraction. In software processing, statistical computation is an easy task. However, providing a computer requires high costs for simple statistical processing. Another consideration is the need for implementation with real-time and portable processing. Therefore, an alternative device is needed, one of which is the field programmable gate array (FPGA). FPGA is a logic circuit board that can be reconfigured according to computing needs. FPGA can also be used as a prototyping of electronic chips. However, implementing statistical formulas in FPGA is interesting in developing its architecture. Therefore, this research proposes a logic circuit design that can be used for first-order statistical calculations. Statistical parameters include the mean, variance, standard deviation, skewness, and kurtosis. The validation test was performed on the electrocardiogram (ECG) signal series and compared with manual calculations. Validation shows that the mean and variance has very high accuracy with an average error of less than 0.06%.
{"title":"Implementation of first order statistical processor on FPGA for feature extraction","authors":"S. Hadiyoso, Ahmad Zaky Ramdani, I. D. Irawati, I. Wijayanto","doi":"10.11591/ijres.v13.i2.pp234-243","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp234-243","url":null,"abstract":"Statistical calculations on signals commonly used in feature extraction. In software processing, statistical computation is an easy task. However, providing a computer requires high costs for simple statistical processing. Another consideration is the need for implementation with real-time and portable processing. Therefore, an alternative device is needed, one of which is the field programmable gate array (FPGA). FPGA is a logic circuit board that can be reconfigured according to computing needs. FPGA can also be used as a prototyping of electronic chips. However, implementing statistical formulas in FPGA is interesting in developing its architecture. Therefore, this research proposes a logic circuit design that can be used for first-order statistical calculations. Statistical parameters include the mean, variance, standard deviation, skewness, and kurtosis. The validation test was performed on the electrocardiogram (ECG) signal series and compared with manual calculations. Validation shows that the mean and variance has very high accuracy with an average error of less than 0.06%.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141698269","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp372-382
Chaya T. Doddaiah, Mohamed Rafi
Cloud computing provides solutions for diverse commercial and academic applications which is the primary goal. Scientific workflows are used in the cloud-computing environment to analyses large-scale scientific applications. For scientific workflows, many data is required, and a single scientific workflow that includes hundreds of stages, depending on the application's time restrictions, task failures, money limits, incorrect task organization, and task management issues can all hinder the implementation of scientific methods. In light of this, a cloud-based scientific workflow management and scheduling system that is fault-tolerant and data-oriented method are proposed. This research designs a novel hybrid cost-aware fault tolerant (HCFT) mechanism for minimizing the cost. Moreover, HCFT integrates optimal clustering and efficient resource utilization through parallel and distributed execution. Novelty of HCFT lies in novel clustering of the similar task for improvisation, CyberShake, laser interferometer gravitational wave observatory (LIGO), Montage, and sRNA identification protocol using high throughput technology (SIPHT) processes are used in the simulations to evaluate the performance of the proposed approach.
{"title":"Hybrid fault tolerant cost aware mechanism for scientific workflow in cloud computing","authors":"Chaya T. Doddaiah, Mohamed Rafi","doi":"10.11591/ijres.v13.i2.pp372-382","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp372-382","url":null,"abstract":"Cloud computing provides solutions for diverse commercial and academic applications which is the primary goal. Scientific workflows are used in the cloud-computing environment to analyses large-scale scientific applications. For scientific workflows, many data is required, and a single scientific workflow that includes hundreds of stages, depending on the application's time restrictions, task failures, money limits, incorrect task organization, and task management issues can all hinder the implementation of scientific methods. In light of this, a cloud-based scientific workflow management and scheduling system that is fault-tolerant and data-oriented method are proposed. This research designs a novel hybrid cost-aware fault tolerant (HCFT) mechanism for minimizing the cost. Moreover, HCFT integrates optimal clustering and efficient resource utilization through parallel and distributed execution. Novelty of HCFT lies in novel clustering of the similar task for improvisation, CyberShake, laser interferometer gravitational wave observatory (LIGO), Montage, and sRNA identification protocol using high throughput technology (SIPHT) processes are used in the simulations to evaluate the performance of the proposed approach.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141701519","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp441-449
Bharat Kumara, S. A. Padmanabhan
The fast expansion of wireless sensor network-internet of things (WSN-IoT) in recent years has led to the adoption of a vital infrastructure. Adversaries who work together to carry out privacy-related attacks and capture sensitive information from critical infrastructure for a range of personal, political, and commercial purposes, thus security and node preserving have been one of the key areas of research in WSN-IoT. Existing security and privacy research work focuses on cryptography, either which is less efficient, or it majorly focuses on securing the network, which further leads to exposing the nodes to the vulnerability in terms of privacy in the network. This research develops condition-based distributed privacy-preserving (CDPP) approach to preserve the sensor node privacy; the CDPP algorithm develops a condition based on which the nodes' vulnerable information is preserved and not accessed by the compromised nodes. CDPP architecture is evaluated considering the amount of misclassified nodes for safeguarding the node in the network. CDPP is evaluated by inducing the corrupt nodes and further comparing the model with existing low energy adaptive clustering hierarchy (LEACH) based on classification, misclassification and throughput. Furthermore, comparative analysis proves the marginal improvisation in terms of discussed parameter against existing protocol.
{"title":"A condition-based distributed approach for secured privacy preservation of nodes in wireless sensor networks IoT","authors":"Bharat Kumara, S. A. Padmanabhan","doi":"10.11591/ijres.v13.i2.pp441-449","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp441-449","url":null,"abstract":"The fast expansion of wireless sensor network-internet of things (WSN-IoT) in recent years has led to the adoption of a vital infrastructure. Adversaries who work together to carry out privacy-related attacks and capture sensitive information from critical infrastructure for a range of personal, political, and commercial purposes, thus security and node preserving have been one of the key areas of research in WSN-IoT. Existing security and privacy research work focuses on cryptography, either which is less efficient, or it majorly focuses on securing the network, which further leads to exposing the nodes to the vulnerability in terms of privacy in the network. This research develops condition-based distributed privacy-preserving (CDPP) approach to preserve the sensor node privacy; the CDPP algorithm develops a condition based on which the nodes' vulnerable information is preserved and not accessed by the compromised nodes. CDPP architecture is evaluated considering the amount of misclassified nodes for safeguarding the node in the network. CDPP is evaluated by inducing the corrupt nodes and further comparing the model with existing low energy adaptive clustering hierarchy (LEACH) based on classification, misclassification and throughput. Furthermore, comparative analysis proves the marginal improvisation in terms of discussed parameter against existing protocol.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"23 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141703047","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp278-285
O. O. Alabi, O. Adeaga, S. Ajagbe, Esther Oluwayemisi Adekunle, M. Adigun
A technology called an alcohol detection driver system is used to stop drunk driving by identifying alcohol in a motorist's breath or blood. This technology correctly measures the amount of alcohol a driver has in their system using sensors and algorithms, and it stops the car from starting if the amount is more than the legal limit. The number of fatal accidents and traffic fatalities caused by drinking could be greatly decreased thanks to this technology. The main focus of this project is to carry out the experiment in lowering the number of alcohol-related incidents on the road. Alcohol detection devices come in a variety of forms right now, including ignition interlocks, passive alcohol sensors, and in-car breathalyzers. Although these systems have reduced the number of drunk driving accidents, there remain questions about their efficiency, dependability, and cost. According to the sensor's specs, the output voltage of the MQ-3 sensor reduces by 69% during the sensor's recovery period of 30 seconds at 69% of baseline resistance. To assess the long-term viability and efficiency of these systems in lowering alcohol-related accidents and enhancing traffic safety, more research is required.
{"title":"Design and implementation of an alcohol detection driver system","authors":"O. O. Alabi, O. Adeaga, S. Ajagbe, Esther Oluwayemisi Adekunle, M. Adigun","doi":"10.11591/ijres.v13.i2.pp278-285","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp278-285","url":null,"abstract":"A technology called an alcohol detection driver system is used to stop drunk driving by identifying alcohol in a motorist's breath or blood. This technology correctly measures the amount of alcohol a driver has in their system using sensors and algorithms, and it stops the car from starting if the amount is more than the legal limit. The number of fatal accidents and traffic fatalities caused by drinking could be greatly decreased thanks to this technology. The main focus of this project is to carry out the experiment in lowering the number of alcohol-related incidents on the road. Alcohol detection devices come in a variety of forms right now, including ignition interlocks, passive alcohol sensors, and in-car breathalyzers. Although these systems have reduced the number of drunk driving accidents, there remain questions about their efficiency, dependability, and cost. According to the sensor's specs, the output voltage of the MQ-3 sensor reduces by 69% during the sensor's recovery period of 30 seconds at 69% of baseline resistance. To assess the long-term viability and efficiency of these systems in lowering alcohol-related accidents and enhancing traffic safety, more research is required.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141705083","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp483-490
Ricardo Yauri, Max Delgado, Enzo Flores, Oscar Llerena
Cardiovascular diseases increase due to factors such as obesity, an inadequate diet, and are a problem due to shortages of medical personnel and hospitals. In this case, the implementation of technological solutions is presented as a necessity to prevent heart diseases. Various approaches are used to design low-cost electrocardiogram (ECG) devices, from the use of Bluetooth technology to facilitate data transmission, to the development of wearable ECG devices that use artificial intelligence. The objective is to develop a monitoring system in LabVIEW to visualize the heart rhythms of older adults in the city of Lima (Peru), focusing on ease of use and adaptation to their needs, with the purpose of collaboration between health professionals. A development approach is used that encompasses design, implementation, and iterative testing, as well as practical evaluations and pilot testing. As a result, the correct functioning of the ECG device was validated. Electronic components and electrodes were integrated into the board to capture cardiac signals, energized with batteries and sending the information to an interface in LabVIEW. In conclusion, a portable ECG device has been developed that uses operational amplifiers (Op-amps) and analog filters to reduce noise in cardiac measurements and an intuitive interface in LabVIEW
{"title":"Low-cost electrocardiogram monitoring system for elderly people using LabVIEW","authors":"Ricardo Yauri, Max Delgado, Enzo Flores, Oscar Llerena","doi":"10.11591/ijres.v13.i2.pp483-490","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp483-490","url":null,"abstract":"Cardiovascular diseases increase due to factors such as obesity, an inadequate diet, and are a problem due to shortages of medical personnel and hospitals. In this case, the implementation of technological solutions is presented as a necessity to prevent heart diseases. Various approaches are used to design low-cost electrocardiogram (ECG) devices, from the use of Bluetooth technology to facilitate data transmission, to the development of wearable ECG devices that use artificial intelligence. The objective is to develop a monitoring system in LabVIEW to visualize the heart rhythms of older adults in the city of Lima (Peru), focusing on ease of use and adaptation to their needs, with the purpose of collaboration between health professionals. A development approach is used that encompasses design, implementation, and iterative testing, as well as practical evaluations and pilot testing. As a result, the correct functioning of the ECG device was validated. Electronic components and electrodes were integrated into the board to capture cardiac signals, energized with batteries and sending the information to an interface in LabVIEW. In conclusion, a portable ECG device has been developed that uses operational amplifiers (Op-amps) and analog filters to reduce noise in cardiac measurements and an intuitive interface in LabVIEW","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"37 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141715268","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 spectrum scarcity problem of wireless sensor networks (WSNs) is improved through amalgamation of cognitive radio networks (CRNs) into WSNs. However, spectrum allocation to secondary users (SUs) is challenging in cognitive radio wireless sensor networks (CR-WSNs) as channel is already crowded and at same time should not induce interference to primary users (PUs). In designing efficient spectrum access model for CR-WSNs recent work have adopted machine-learning game theory (GT) and statistical model. However, the major limitation of existing spectrum access model they fail to assure access fairness with maximal throughput with minimal collision. This work presents a maximizing channel access fairness model to handle the research challenges. To boost CR-WSN performance, the throughput maximization using channel access fairness (TMCAF) employs shared and non-shared channel access designs. Experiment outcome shows throughput is improved and collision in network is reduced in comparison with state-of-art channel access models.
{"title":"Channel access mechanism for maximizing throughput with fairness in wireless sensor networks","authors":"Shaik Humera Tauseef, Rukhsar Fatima, Rohina Khanam","doi":"10.11591/ijres.v13.i2.pp352-359","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp352-359","url":null,"abstract":"The spectrum scarcity problem of wireless sensor networks (WSNs) is improved through amalgamation of cognitive radio networks (CRNs) into WSNs. However, spectrum allocation to secondary users (SUs) is challenging in cognitive radio wireless sensor networks (CR-WSNs) as channel is already crowded and at same time should not induce interference to primary users (PUs). In designing efficient spectrum access model for CR-WSNs recent work have adopted machine-learning game theory (GT) and statistical model. However, the major limitation of existing spectrum access model they fail to assure access fairness with maximal throughput with minimal collision. This work presents a maximizing channel access fairness model to handle the research challenges. To boost CR-WSN performance, the throughput maximization using channel access fairness (TMCAF) employs shared and non-shared channel access designs. Experiment outcome shows throughput is improved and collision in network is reduced in comparison with state-of-art channel access models.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"65 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141696434","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp383-394
Shashirekha Hanumanthappa, Chetana Prakash
Recently, significant growth in using online-based learning stream (i.e., elearning systems) have been seen due to pandemic such as COVID-19. Forecasting student performance has become a major task as an institution is focusing on improving the quality of education and students' performance. Data mining (DM) employing machine learning (ML) techniques have been employed in the e-learning platform for analyzing student session streams and predicting academic performance with good effects. A recent, study shows ML-based methodologies exhibit when data is imbalanced. In addressing ensemble learning by combining multiple ML algorithms for choosing the best model according to data. However, the existing ensemblebased model does not incorporate feature importance into the student performance prediction model. Thus, exhibits poor performance, especially for multi-label classification. In addressing this, this paper presents an improved ensemble learning mechanism by modifying the XGBoost algorithm, namely modified XGBoost (MXGB). The MXGB incorporates an effective cross-validation scheme that learns correlation among features more efficiently. The experiment outcome shows the proposed MXGBabased student performance prediction model achieves much better prediction accuracy contrary to the state-of-art ensemble-based student performance prediction model.
最近，由于 COVID-19 等流行病的影响，使用在线学习流（即电子学习系统）的人数大幅增加。随着教育机构对提高教育质量和学生成绩的重视，预测学生成绩已成为一项重要任务。采用机器学习（ML）技术的数据挖掘（DM）已被应用于电子学习平台，用于分析学生课程流和预测学习成绩，并取得了良好的效果。最近的一项研究表明，当数据不平衡时，基于 ML 的方法就会出现问题。在解决集合学习问题时，结合多种 ML 算法，根据数据选择最佳模型。然而，现有的基于集合的模型并没有将特征重要性纳入学生成绩预测模型。因此，表现出了较差的性能，尤其是在多标签分类方面。针对这一问题，本文通过修改 XGBoost 算法，提出了一种改进的集合学习机制，即改进的 XGBoost（MXGB）。MXGB 采用了有效的交叉验证方案，能更有效地学习特征之间的相关性。实验结果表明，与目前基于集合的学生成绩预测模型相比，基于 MXGB 的学生成绩预测模型获得了更高的预测精度。
{"title":"Machine learning based education data mining through student session streams","authors":"Shashirekha Hanumanthappa, Chetana Prakash","doi":"10.11591/ijres.v13.i2.pp383-394","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp383-394","url":null,"abstract":"Recently, significant growth in using online-based learning stream (i.e., elearning systems) have been seen due to pandemic such as COVID-19. Forecasting student performance has become a major task as an institution is focusing on improving the quality of education and students' performance. Data mining (DM) employing machine learning (ML) techniques have been employed in the e-learning platform for analyzing student session streams and predicting academic performance with good effects. A recent, study shows ML-based methodologies exhibit when data is imbalanced. In addressing ensemble learning by combining multiple ML algorithms for choosing the best model according to data. However, the existing ensemblebased model does not incorporate feature importance into the student performance prediction model. Thus, exhibits poor performance, especially for multi-label classification. In addressing this, this paper presents an improved ensemble learning mechanism by modifying the XGBoost algorithm, namely modified XGBoost (MXGB). The MXGB incorporates an effective cross-validation scheme that learns correlation among features more efficiently. The experiment outcome shows the proposed MXGBabased student performance prediction model achieves much better prediction accuracy contrary to the state-of-art ensemble-based student performance prediction model.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"49 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141711154","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 : 2024-07-01DOI: 10.11591/ijres.v13.i2.pp431-440
Sharada P. Narasimha, Sanjeev C. Lingareddy
Video saliency has a profound effect on our lives with its compression efficiency and precision. There have been several types of research done on image saliency but not on video saliency. This paper proposes a modified high efficiency video coding (HEVC) algorithm with background modelling and the implication of classification into coding blocks. This solution first employs the G-picture in the fourth frame as a long-term reference and then it is quantized based on the algorithm that segregates using the background features of the image. Then coding blocks are introduced to decrease the complexity of the HEVC code, reduce time consumption and overall speed up the process of saliency. The solution is experimented upon with the dynamic human fixation 1K (DHF1K) dataset and compared with several other state-of-the-art saliency methods to showcase the reliability and efficiency of the proposed solution.
视频显著性的压缩效率和精确度对我们的生活影响深远。关于图像显著性的研究有多种类型，但关于视频显著性的研究却不多。本文提出了一种改进的高效视频编码（HEVC）算法，该算法具有背景建模和编码块分类的含义。该解决方案首先采用第四帧中的 G 图像作为长期参考，然后根据利用图像背景特征进行分离的算法对其进行量化。然后引入编码块，以降低 HEVC 代码的复杂性，减少时间消耗，并从整体上加快显著性处理过程。我们利用动态人类固定 1K (DHF1K) 数据集对该解决方案进行了实验，并与其他几种最先进的显著性方法进行了比较，以展示所提解决方案的可靠性和效率。
{"title":"Video saliency detection using modified high efficiency video coding and background modelling","authors":"Sharada P. Narasimha, Sanjeev C. Lingareddy","doi":"10.11591/ijres.v13.i2.pp431-440","DOIUrl":"https://doi.org/10.11591/ijres.v13.i2.pp431-440","url":null,"abstract":"Video saliency has a profound effect on our lives with its compression efficiency and precision. There have been several types of research done on image saliency but not on video saliency. This paper proposes a modified high efficiency video coding (HEVC) algorithm with background modelling and the implication of classification into coding blocks. This solution first employs the G-picture in the fourth frame as a long-term reference and then it is quantized based on the algorithm that segregates using the background features of the image. Then coding blocks are introduced to decrease the complexity of the HEVC code, reduce time consumption and overall speed up the process of saliency. The solution is experimented upon with the dynamic human fixation 1K (DHF1K) dataset and compared with several other state-of-the-art saliency methods to showcase the reliability and efficiency of the proposed solution.","PeriodicalId":158991,"journal":{"name":"International Journal of Reconfigurable and Embedded Systems (IJRES)","volume":"115 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141693048","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：