Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548888
S. Sadkhan, B. S. Yaseen
In this paper, We propose DNA sticker model based algorithm, a computability model, which is a simulation of the parallel computations using the Molecular computing as in Adelman’s DNA computing experiment, it demonstrates how to use a sticker-based model to design a simple DNA-based algorithm for attacking a linear and a non-linear feedback shift register (FSR) based stream cipher. The algorithm first construct the TEST TUBE contains all overall solution space of memory complexes for the cipher and initials of registers via the sticker-based model. Then, with biological operations, separate and combine, we remove those which encode illegal plain and key stream from the TEST TUBE of memory complexes, the decision based on verifying a key stream bit this bit represented by output of LFSRs equation. The model anticipates two basic groups of single stranded DNA molecules in its representation one of a genetic bases and second of a bit string, It invests parallel search into the space of solutions through the possibilities of DNA computing and makes use of the method of cryptanalysis of algebraic code as a decision technique to accept the solution or not, and their operations are repeated until one solution or limited group of solutions is reached. The main advantages of the suggested algorithm are limited number of cipher characters, and finding one exact solution The present work concentrates on showing the applicability of DNA computing concepts as a powerful tool in breaking cryptographic systems.
{"title":"A DNA-Sticker Algorithm for Cryptanalysis LFSRs and NLFSRs Based Stream Cipher","authors":"S. Sadkhan, B. S. Yaseen","doi":"10.1109/ICOASE.2018.8548888","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548888","url":null,"abstract":"In this paper, We propose DNA sticker model based algorithm, a computability model, which is a simulation of the parallel computations using the Molecular computing as in Adelman’s DNA computing experiment, it demonstrates how to use a sticker-based model to design a simple DNA-based algorithm for attacking a linear and a non-linear feedback shift register (FSR) based stream cipher. The algorithm first construct the TEST TUBE contains all overall solution space of memory complexes for the cipher and initials of registers via the sticker-based model. Then, with biological operations, separate and combine, we remove those which encode illegal plain and key stream from the TEST TUBE of memory complexes, the decision based on verifying a key stream bit this bit represented by output of LFSRs equation. The model anticipates two basic groups of single stranded DNA molecules in its representation one of a genetic bases and second of a bit string, It invests parallel search into the space of solutions through the possibilities of DNA computing and makes use of the method of cryptanalysis of algebraic code as a decision technique to accept the solution or not, and their operations are repeated until one solution or limited group of solutions is reached. The main advantages of the suggested algorithm are limited number of cipher characters, and finding one exact solution The present work concentrates on showing the applicability of DNA computing concepts as a powerful tool in breaking cryptographic systems.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131144449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548920
Karam Hashim Mohammed, Omar Rafae Alomar, R. Mohammed
In this paper, the emissions characteristics and performance of a direct four-stroke diesel engine fueled by three different kinds of biodiesel oils and normal diesel oil (DF) has been experimentally investigated. Biodiesel fuels of Palm, Coconut and Sunflower have been separately used as an alternative fuel and the results obtained have been compared with that results obtained using DF at the same operating conditions. The results indicated that a higher Brake Thermal Efficiency (BTE) has been obtained when using the Coconut fuel. For moderate engine speed, the use of biodiesel produces high Brake Specific Fuel Consumption (BSFC) up to 22% in comparison with that obtained using normal DF. The BSFC of sunflower fuel at the maximum torque has been observed to be 10% higher than when using normal diesel oil. For moderate engine speed, the measured amount of carbon monoxide (CO) emissions when using either Sunflower, Palm or Coconut as a biodiesel fuel have been found to be lower than that obtained by using the DF. For low engine speed, the emissions of NOx for all three kinds of biodiesel fuels is lower than when using normal DF. Most importantly, the results indicated that the biodiesel fuels have significant impact on the emissions characteristics and performance of engine and hence biodiesel fuel can be directly used for normal engine system. Therefore, adequate care must be taken while selecting such a biodiesel fuel in order to meet the process requirement of the environment.
{"title":"Effects of Different Biodiesel on Diesel-Engine Performance and Emissions","authors":"Karam Hashim Mohammed, Omar Rafae Alomar, R. Mohammed","doi":"10.1109/ICOASE.2018.8548920","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548920","url":null,"abstract":"In this paper, the emissions characteristics and performance of a direct four-stroke diesel engine fueled by three different kinds of biodiesel oils and normal diesel oil (DF) has been experimentally investigated. Biodiesel fuels of Palm, Coconut and Sunflower have been separately used as an alternative fuel and the results obtained have been compared with that results obtained using DF at the same operating conditions. The results indicated that a higher Brake Thermal Efficiency (BTE) has been obtained when using the Coconut fuel. For moderate engine speed, the use of biodiesel produces high Brake Specific Fuel Consumption (BSFC) up to 22% in comparison with that obtained using normal DF. The BSFC of sunflower fuel at the maximum torque has been observed to be 10% higher than when using normal diesel oil. For moderate engine speed, the measured amount of carbon monoxide (CO) emissions when using either Sunflower, Palm or Coconut as a biodiesel fuel have been found to be lower than that obtained by using the DF. For low engine speed, the emissions of NOx for all three kinds of biodiesel fuels is lower than when using normal DF. Most importantly, the results indicated that the biodiesel fuels have significant impact on the emissions characteristics and performance of engine and hence biodiesel fuel can be directly used for normal engine system. Therefore, adequate care must be taken while selecting such a biodiesel fuel in order to meet the process requirement of the environment.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130953378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548929
Husam Kareem, Hadi Jameel
Based on the wide variety of applications of wireless sensor networks (WSNs) in different aspects of life, research focusing on WSNs have rapidly increased in the recent few years. Different challenges shorten the operation of sensor nodes over the targeted area for different reasons such as danger, inhospitality, and limited energy resources of the surrounding area. One major issue is the energy required to operate the individual sensor nodes that definitely affect the operation of the entire sensor network. Accordingly, energy consumption must be minimized as possible which requires to compromise sensor network activities as well as network operation. One fundamental solution commonly used for minimizing the energy consumption in each sensor node is using an energy-efficient routing algorithm. In this study, a routing approach depends on the grid topology of the sensor network is presented to maximize the lifetime of WSNs via balancing a load of data traffic among sensor nodes as evenly as possible. The evaluation process is done using CFDASC routing protocol since it represents the most comparable and related algorithm among previous work. Simulation results prove that the presented approach outperformance CFDASC algorithm in terms of network stability and load balancing of the entire network.
{"title":"Maintain Load Balancing in Wireless Sensor Networks Using Virtual Grid Based Routing Protocol","authors":"Husam Kareem, Hadi Jameel","doi":"10.1109/ICOASE.2018.8548929","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548929","url":null,"abstract":"Based on the wide variety of applications of wireless sensor networks (WSNs) in different aspects of life, research focusing on WSNs have rapidly increased in the recent few years. Different challenges shorten the operation of sensor nodes over the targeted area for different reasons such as danger, inhospitality, and limited energy resources of the surrounding area. One major issue is the energy required to operate the individual sensor nodes that definitely affect the operation of the entire sensor network. Accordingly, energy consumption must be minimized as possible which requires to compromise sensor network activities as well as network operation. One fundamental solution commonly used for minimizing the energy consumption in each sensor node is using an energy-efficient routing algorithm. In this study, a routing approach depends on the grid topology of the sensor network is presented to maximize the lifetime of WSNs via balancing a load of data traffic among sensor nodes as evenly as possible. The evaluation process is done using CFDASC routing protocol since it represents the most comparable and related algorithm among previous work. Simulation results prove that the presented approach outperformance CFDASC algorithm in terms of network stability and load balancing of the entire network.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132085974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548890
S. Rasheed
The applications of pattern formation in nature attract a huge number of researchers and thus increase the production of researches in this field. In this paper, we introduce a new model of the reaction-diffusion system which satisfies Turing conditions and formulates complicate solutions such as pattern formation. We used for finding the numerical results and forming the patterns software COMSOL Multiphysics finite element package. We have discussed the condition of diffusion-driven instability theoretically and showed the region where these conditions can be satisfied. It was shown that the key fact for instability and the existence of pattern formation is the diffusion coefficient d. When d is large enough we can construct pattern formation with variants rings. The number of rings increases as the domain we use for study increases. Finally, we compared our results to real patterns in nature and we show how they matched together.
{"title":"Pattern Formation for a New Model of Reaction-Diffusion System","authors":"S. Rasheed","doi":"10.1109/ICOASE.2018.8548890","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548890","url":null,"abstract":"The applications of pattern formation in nature attract a huge number of researchers and thus increase the production of researches in this field. In this paper, we introduce a new model of the reaction-diffusion system which satisfies Turing conditions and formulates complicate solutions such as pattern formation. We used for finding the numerical results and forming the patterns software COMSOL Multiphysics finite element package. We have discussed the condition of diffusion-driven instability theoretically and showed the region where these conditions can be satisfied. It was shown that the key fact for instability and the existence of pattern formation is the diffusion coefficient d. When d is large enough we can construct pattern formation with variants rings. The number of rings increases as the domain we use for study increases. Finally, we compared our results to real patterns in nature and we show how they matched together.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131792913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548845
M. Younis, E. Keedwell, D. Savić
This research evaluates pixel-based and object-based image classification techniques for extracting three land-use categories (buildings, roads, and vegetation areas) from six satellite images. The performance of eight supervised machine learning classifiers with 5-fold cross validation are also compared. Experimental validation found that using 'Bagged Tree' for object-based classification algorithms provides maximum overall accuracy when tested on 10,000 objects produced by the SLIC segmentation method, and improves upon an existing RGB-based approach. Our aforementioned proposed approach takes about 12 times less total runtime than the pixel-based method, demonstrating the power of the combined approach.
{"title":"An Investigation of Pixel-Based and Object-Based Image Classification in Remote Sensing","authors":"M. Younis, E. Keedwell, D. Savić","doi":"10.1109/ICOASE.2018.8548845","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548845","url":null,"abstract":"This research evaluates pixel-based and object-based image classification techniques for extracting three land-use categories (buildings, roads, and vegetation areas) from six satellite images. The performance of eight supervised machine learning classifiers with 5-fold cross validation are also compared. Experimental validation found that using 'Bagged Tree' for object-based classification algorithms provides maximum overall accuracy when tested on 10,000 objects produced by the SLIC segmentation method, and improves upon an existing RGB-based approach. Our aforementioned proposed approach takes about 12 times less total runtime than the pixel-based method, demonstrating the power of the combined approach.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115368366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548814
Majd S. Matti, Ahmed Khorsheed Al-Sulaifanie
This study is about using the genetic algorithm (GA) with wavelet transform (WT) for signal denoising purposes. The WT is a time-frequency signal analysis, and the GA is an optimization technique based on survival of the best solution using the maximized or minimized fitness value obtained from the fitness function. In this study, the parameters of WT are used as inputs for the GA for denoising the input signal that is corrupted by white Gaussian noise and gives an output of MSEo as fitness value. The input corrupted signal will pass through decomposition process to extract approximation and details coefficients, then thresholding the details coefficients using a threshold value in order to remove the noise, and finally reconstruction of the signal using the approximation and denoised details coefficients. Four standard benchmark signals are used to test this technique then a comparison is done with other studies in the same field, and the comparison showed that the results of this work is better.
{"title":"Wavelet Denoising Based on Genetic Algorithm","authors":"Majd S. Matti, Ahmed Khorsheed Al-Sulaifanie","doi":"10.1109/ICOASE.2018.8548814","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548814","url":null,"abstract":"This study is about using the genetic algorithm (GA) with wavelet transform (WT) for signal denoising purposes. The WT is a time-frequency signal analysis, and the GA is an optimization technique based on survival of the best solution using the maximized or minimized fitness value obtained from the fitness function. In this study, the parameters of WT are used as inputs for the GA for denoising the input signal that is corrupted by white Gaussian noise and gives an output of MSEo as fitness value. The input corrupted signal will pass through decomposition process to extract approximation and details coefficients, then thresholding the details coefficients using a threshold value in order to remove the noise, and finally reconstruction of the signal using the approximation and denoised details coefficients. Four standard benchmark signals are used to test this technique then a comparison is done with other studies in the same field, and the comparison showed that the results of this work is better.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115139133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548869
Saba Fouad Hassan, Rana Fareed
The most prevalent media on the Internet is Video streaming which has the greatest bandwidth expended. The massive quantity of internet usage goes for video streaming that expends nearly 70% of the internet today. However, there are constraints for Interactive media represented by increased bandwidth usage and lateness. Cloud computing not suitable for interactive application because the data transmissions between cloud centers and end users have a high response time. Fog computing is extending of cloud service, it’s an intermediary layer between cloud and end user, it aims to provide services close to the user onto the network edge. This study proposes an architecture to reduce the limitation in video outflowing by employing fog computing to deliver very lower response time and real-time communication, and weighted round robin algorithm for scheduling streaming task in fog environment. The experiment results display that in the suggested architecture the latency is minimum and good quality of video with bandwidth changes
{"title":"Video streaming processing using fog computing","authors":"Saba Fouad Hassan, Rana Fareed","doi":"10.1109/ICOASE.2018.8548869","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548869","url":null,"abstract":"The most prevalent media on the Internet is Video streaming which has the greatest bandwidth expended. The massive quantity of internet usage goes for video streaming that expends nearly 70% of the internet today. However, there are constraints for Interactive media represented by increased bandwidth usage and lateness. Cloud computing not suitable for interactive application because the data transmissions between cloud centers and end users have a high response time. Fog computing is extending of cloud service, it’s an intermediary layer between cloud and end user, it aims to provide services close to the user onto the network edge. This study proposes an architecture to reduce the limitation in video outflowing by employing fog computing to deliver very lower response time and real-time communication, and weighted round robin algorithm for scheduling streaming task in fog environment. The experiment results display that in the suggested architecture the latency is minimum and good quality of video with bandwidth changes","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126393664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548915
S. Refish
Password authentication code (PAC) is a very important issue in many applications such as web-sites and data base systems etc. In this paper, PAC between two users to confirm authentication between them has presented. This research presents a novel solution to the era long problem password authentication at incoming level. A legitimate user typing his password only and press enter to propagate it to another user which he wants to be authenticated. My solution does not require the password (input code) to be hidden from anyone for security reasons. PAC-RMPN uses routing in message passing networks method (RMPN) which determines the positions of bits which sent to reach the destination. My method regenerates a new code each authentication process based RMPN that is convincingly more secure against both online and offline attacks. This scheme has some advantages such as secrecy of session key, and password privacy. This method proves the users authenticated does not need to hide passwords.
{"title":"PAC-RMPN: Password Authentication Code Based RMPN","authors":"S. Refish","doi":"10.1109/ICOASE.2018.8548915","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548915","url":null,"abstract":"Password authentication code (PAC) is a very important issue in many applications such as web-sites and data base systems etc. In this paper, PAC between two users to confirm authentication between them has presented. This research presents a novel solution to the era long problem password authentication at incoming level. A legitimate user typing his password only and press enter to propagate it to another user which he wants to be authenticated. My solution does not require the password (input code) to be hidden from anyone for security reasons. PAC-RMPN uses routing in message passing networks method (RMPN) which determines the positions of bits which sent to reach the destination. My method regenerates a new code each authentication process based RMPN that is convincingly more secure against both online and offline attacks. This scheme has some advantages such as secrecy of session key, and password privacy. This method proves the users authenticated does not need to hide passwords.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116967978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548840
M. R. Mahmood, Adnan Mohsin Abdulazeez, Zeynep Orman
Hand gesture recognition forms a great difficulty for computer vision especially in dynamics. Sign language has been significant and an interesting application field of dynamic hand gesture recognition system. The recognition of human hands formed an- extremely complicated mission. The solution for such a difficulty requires a robust hand tracking method which depends on an effective feature and classifier. This paper presents a novel, fast and simple method for dynamic hand gesture recognition based on two lines (hundred) of features extracted from two rows of a Real-Time video. Feature selections have been used for hand shape representation to recognize the dynamic word for Kurdish Sign Language. The features extracted in real time from pre-processed hand object were represented through the optimization values of binary captured frame. Finally, an Artificial Neural Network classifier is used to recognize the performed hand gestures by 80% for training and 20% for testing with success 98%.
{"title":"Dynamic Hand Gesture Recognition System for Kurdish Sign Language Using Two Lines of Features","authors":"M. R. Mahmood, Adnan Mohsin Abdulazeez, Zeynep Orman","doi":"10.1109/ICOASE.2018.8548840","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548840","url":null,"abstract":"Hand gesture recognition forms a great difficulty for computer vision especially in dynamics. Sign language has been significant and an interesting application field of dynamic hand gesture recognition system. The recognition of human hands formed an- extremely complicated mission. The solution for such a difficulty requires a robust hand tracking method which depends on an effective feature and classifier. This paper presents a novel, fast and simple method for dynamic hand gesture recognition based on two lines (hundred) of features extracted from two rows of a Real-Time video. Feature selections have been used for hand shape representation to recognize the dynamic word for Kurdish Sign Language. The features extracted in real time from pre-processed hand object were represented through the optimization values of binary captured frame. Finally, an Artificial Neural Network classifier is used to recognize the performed hand gestures by 80% for training and 20% for testing with success 98%.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117186782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICOASE.2018.8548804
N. S. Ahmed, Mohammed Hikmat Sadiq
Many supportive decision systems using classification algorithms have been built as a black box in the last years. Such systems were hiding its inner operations to users. Lack of explanation of these algorithms leads to a practical problem. The education field is one of the areas that needs more clarification in such systems to help users in order to get more information for a right decision. In this paper, the Random Forest algorithm has been clarified and used in analyzing the students’ performance, as a dataset. The result showed that the clarified method of the aforementioned algorithm can give an accuracy of 83.56%. On the other hand, WEKA tool gives an accuracy of 80.82% for the same algorithm and dataset. Also, the proposed method of the Random Forest algorithm has been tested using another previous study’s dataset. The comparison results showed that the proposed method can give an accuracy of 92.65%, which is in turn better than the accuracy of 91.2% that obtained by another study done. Furthermore, to make the Random Forest algorithm work as a white box, Rules have been extracted from the Random Forest black box algorithm in order to make it more interpretable and helpful in predicting student’s performance.
{"title":"Clarify of the Random Forest Algorithm in an Educational Field","authors":"N. S. Ahmed, Mohammed Hikmat Sadiq","doi":"10.1109/ICOASE.2018.8548804","DOIUrl":"https://doi.org/10.1109/ICOASE.2018.8548804","url":null,"abstract":"Many supportive decision systems using classification algorithms have been built as a black box in the last years. Such systems were hiding its inner operations to users. Lack of explanation of these algorithms leads to a practical problem. The education field is one of the areas that needs more clarification in such systems to help users in order to get more information for a right decision. In this paper, the Random Forest algorithm has been clarified and used in analyzing the students’ performance, as a dataset. The result showed that the clarified method of the aforementioned algorithm can give an accuracy of 83.56%. On the other hand, WEKA tool gives an accuracy of 80.82% for the same algorithm and dataset. Also, the proposed method of the Random Forest algorithm has been tested using another previous study’s dataset. The comparison results showed that the proposed method can give an accuracy of 92.65%, which is in turn better than the accuracy of 91.2% that obtained by another study done. Furthermore, to make the Random Forest algorithm work as a white box, Rules have been extracted from the Random Forest black box algorithm in order to make it more interpretable and helpful in predicting student’s performance.","PeriodicalId":144020,"journal":{"name":"2018 International Conference on Advanced Science and Engineering (ICOASE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125546802","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：