Pub Date : 2021-08-16DOI: 10.53409/mnaa/jcsit/2202
Jayamma R
Users of data-intensive implementation needs intelligent services and schedulers that will provide models and strategies to optimize their data transfer jobs. Normally sensor nodes are connected to consecutive sensor nodes depending on frequent transmission. To enhance end-to-end data flow parallelism for throughput optimization in high speed WSNs. The major objective is to maximize the WSNs throughput, minimizing the model overhead, avoiding disputation among users and using minimum number of end-system resources. Data packets are broadcasted from sender node to target node. Though, all nodes operate concurrently in various communications, the analysis shows that more packet latencies are occurred and priority-based transmission tasks are performed. Then the proposed Bearing parallelism-based Data Scheduler (BPDS) is used for data scheduling to enhance the end-to-end throughput input parameter. Sensor nodes are fast working node, it verifies each and every node before allocating packet transmission for that node. Busy resources are monitored to inform the nodes that are in processing, based on the schedule it allocates various paths to particular node and monitors the node capacity. Sampling algorithm supports for fixing threshold value, based on the values, they are further allocated to communicate between channels. It assigns the routing path with minimum resources and reduces end to end delay, to improve throughput, and network lifetime.
{"title":"Improving The Performances of WSN Using Data Scheduler and Hierarchical Tree","authors":"Jayamma R","doi":"10.53409/mnaa/jcsit/2202","DOIUrl":"https://doi.org/10.53409/mnaa/jcsit/2202","url":null,"abstract":"Users of data-intensive implementation needs intelligent services and schedulers that will provide models and strategies to optimize their data transfer jobs. Normally sensor nodes are connected to consecutive sensor nodes depending on frequent transmission. To enhance end-to-end data flow parallelism for throughput optimization in high speed WSNs. The major objective is to maximize the WSNs throughput, minimizing the model overhead, avoiding disputation among users and using minimum number of end-system resources. Data packets are broadcasted from sender node to target node. Though, all nodes operate concurrently in various communications, the analysis shows that more packet latencies are occurred and priority-based transmission tasks are performed. Then the proposed Bearing parallelism-based Data Scheduler (BPDS) is used for data scheduling to enhance the end-to-end throughput input parameter. Sensor nodes are fast working node, it verifies each and every node before allocating packet transmission for that node. Busy resources are monitored to inform the nodes that are in processing, based on the schedule it allocates various paths to particular node and monitors the node capacity. Sampling algorithm supports for fixing threshold value, based on the values, they are further allocated to communicate between channels. It assigns the routing path with minimum resources and reduces end to end delay, to improve throughput, and network lifetime.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122918476","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 : 2021-04-16DOI: 10.53409/mnaa/jcsit/2102
Narmatha C, Hayam Alatawi, H. Alatawi
Deep learning is a machine learning technique that has demonstrated better results and performance when compared to standard machine learning algorithms in relation to higher dimensional MRI brain imaging data. The applications of deep learning in the clinical domain are discussed in this study. A detailed analysis of several deep learning algorithms for the Alzheimer's disease diagnosis is analyzed, in which this disorder of brain that gradually spreads and destroys memory of the brain, and it is a typical disorder in elderly individuals due to dementia. When it comes to brain image processing, the most commonly used and represented method, according to most research publications, is Convolutional Neural Networks (CNN). Following a review of many relevant studies for the Alzheimer's disease diagnosis, it was shown that utilizing advanced deep learning algorithms in different datasets (OASIS and ADNI) combined to one can improve AD prediction at earlier stages.
{"title":"An Analysis of Deep Learning Techniques in Neuroimaging","authors":"Narmatha C, Hayam Alatawi, H. Alatawi","doi":"10.53409/mnaa/jcsit/2102","DOIUrl":"https://doi.org/10.53409/mnaa/jcsit/2102","url":null,"abstract":"Deep learning is a machine learning technique that has demonstrated better results and performance when compared to standard machine learning algorithms in relation to higher dimensional MRI brain imaging data. The applications of deep learning in the clinical domain are discussed in this study. A detailed analysis of several deep learning algorithms for the Alzheimer's disease diagnosis is analyzed, in which this disorder of brain that gradually spreads and destroys memory of the brain, and it is a typical disorder in elderly individuals due to dementia. When it comes to brain image processing, the most commonly used and represented method, according to most research publications, is Convolutional Neural Networks (CNN). Following a review of many relevant studies for the Alzheimer's disease diagnosis, it was shown that utilizing advanced deep learning algorithms in different datasets (OASIS and ADNI) combined to one can improve AD prediction at earlier stages.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121601680","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 : 2021-04-16DOI: 10.53409/mnaa/jcsit/2103
Chettiyar Vani Vivekanand
As the central processing unit of the human body, the human brain is in charge of several activities, including cognition, perception, emotion, attention, action, and memory. Emotions have a significant impact on human well-being in their life. Methodologies for accessing emotions of human could be essential for good user-machine interactions. Comprehending BCI (Brain-Computer Interface) strategies for identifying emotions can also help people connect with the world more naturally. Many approaches for identifying human emotions have been developed using signals of EEG for classifying happy, neutral, sad, and angry emotions, discovered to be effective. The emotions are elicited by various methods, including displaying participants visuals of happy and sad facial expressions, listening to emotionally linked music, visuals, and, sometimes, both of these. In this research, a multi-model fusion approach for emotion classification utilizing BCI and EEG data with various classifiers was proposed. The 10-20 electrode setup was used to gather the EEG data. The emotions were classified using the sentimental analysis technique based on user ratings. Simultaneously, Natural Language Processing (NLP) is implemented for increasing accuracy. This analysis classified the assessment parameters as happy, neutral, sad, and angry emotions. Based on these emotions, the proposed model’s performance was assessed in terms of accuracy and overall accuracy. The proposed model has a 93.33 percent overall accuracy and increased performance in all emotions identified.
{"title":"Performance Analysis of Emotion Classification Using Multimodal Fusion Technique","authors":"Chettiyar Vani Vivekanand","doi":"10.53409/mnaa/jcsit/2103","DOIUrl":"https://doi.org/10.53409/mnaa/jcsit/2103","url":null,"abstract":"As the central processing unit of the human body, the human brain is in charge of several activities, including cognition, perception, emotion, attention, action, and memory. Emotions have a significant impact on human well-being in their life. Methodologies for accessing emotions of human could be essential for good user-machine interactions. Comprehending BCI (Brain-Computer Interface) strategies for identifying emotions can also help people connect with the world more naturally. Many approaches for identifying human emotions have been developed using signals of EEG for classifying happy, neutral, sad, and angry emotions, discovered to be effective. The emotions are elicited by various methods, including displaying participants visuals of happy and sad facial expressions, listening to emotionally linked music, visuals, and, sometimes, both of these. In this research, a multi-model fusion approach for emotion classification utilizing BCI and EEG data with various classifiers was proposed. The 10-20 electrode setup was used to gather the EEG data. The emotions were classified using the sentimental analysis technique based on user ratings. Simultaneously, Natural Language Processing (NLP) is implemented for increasing accuracy. This analysis classified the assessment parameters as happy, neutral, sad, and angry emotions. Based on these emotions, the proposed model’s performance was assessed in terms of accuracy and overall accuracy. The proposed model has a 93.33 percent overall accuracy and increased performance in all emotions identified.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127636573","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}
Sarah Salaheldin Lutfi, Evans Ga Usa. Aysik Consulting Services, Mahmoud Lutfi Ahmed
With the wide application of wireless sensor networks in military and environmental monitoring, security issues have become increasingly prominent. Data exchanged over wireless sensor networks is vulnerable to malicious attacks due to the lack of physical defense equipment. Therefore, corresponding schemes of intrusion detection are urgently needed to defend against such attacks. A new method of intrusion detection using Hybrid Neuro-Fuzzy Filter with Ant Colony Algorithm (HNF-ACA) is proposed in this study, which has been able to map the network status directly into the sensor monitoring data received by base station, accordingly that base station can sense the abnormal changes in network.The hybridized Sugeno-Mamdani based fuzzy interference system is implemented in both the NF filters to obtain more efficient noise removal system. The Modified Mutation Based Ant Colony Algorithm technique improves the accuracy of determining the membership values of input trust values of each node in fuzzy filters. To end, the proposed method was tested on the WSN simulation and the results showed that the intrusion detection method in this work can effectively recognise whether the abnormal data came from a network attack or just a noise than the existing methods.
{"title":"A Novel Intrusion Detection System in WSN using Hybrid Neuro-Fuzzy Filter with Ant Colony Algorithm","authors":"Sarah Salaheldin Lutfi, Evans Ga Usa. Aysik Consulting Services, Mahmoud Lutfi Ahmed","doi":"10.53409/mnaa.jcsit1101","DOIUrl":"https://doi.org/10.53409/mnaa.jcsit1101","url":null,"abstract":"With the wide application of wireless sensor networks in military and environmental monitoring, security issues have become increasingly prominent. Data exchanged over wireless sensor networks is vulnerable to malicious attacks due to the lack of physical defense equipment. Therefore, corresponding schemes of intrusion detection are urgently needed to defend against such attacks. A new method of intrusion detection using Hybrid Neuro-Fuzzy Filter with Ant Colony Algorithm (HNF-ACA) is proposed in this study, which has been able to map the network status directly into the sensor monitoring data received by base station, accordingly that base station can sense the abnormal changes in network.The hybridized Sugeno-Mamdani based fuzzy interference system is implemented in both the NF filters to obtain more efficient noise removal system. The Modified Mutation Based Ant Colony Algorithm technique improves the accuracy of determining the membership values of input trust values of each node in fuzzy filters. To end, the proposed method was tested on the WSN simulation and the results showed that the intrusion detection method in this work can effectively recognise whether the abnormal data came from a network attack or just a noise than the existing methods.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125323171","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 : 1900-01-01DOI: 10.53409/mnaa.jcsit20201302
A. T, C. G, S. M
Determining the size of the tumor is a significant obstacle in brain tumour preparation and objective assessment. Magnetic Resonance Imaging (MRI) is one of the non-invasive methods that has emanated without ionizing radiation as a front-line diagnostic method for brain tumour. Several approaches have been applied in modern years to segment MRI brain tumours automatically. These methods can be divided into two groups based on conventional learning, such as support vector machine (SVM) and random forest, respectively hand-crafted features and classifier method. However, after deciding hand-crafted features, it uses manually separated features and is given to classifiers as input. These are the time consuming activity, and their output is heavily dependent upon the experience of the operator. This research proposes fully automated detection of brain tumor using Convolutional Neural Network (CNN) to avoid this problem. It also uses brain image of high grade gilomas from the BRATS 2015 database. The suggested research performs brain tumor segmentation using clustering of k-means and patient survival rates are increased with this proposed early diagnosis of brain tumour using CNN.
{"title":"A Proficient Adaptive K-means based Brain Tumor Segmentation and Detection Using Deep Learning Scheme with PSO","authors":"A. T, C. G, S. M","doi":"10.53409/mnaa.jcsit20201302","DOIUrl":"https://doi.org/10.53409/mnaa.jcsit20201302","url":null,"abstract":"Determining the size of the tumor is a significant obstacle in brain tumour preparation and objective assessment. Magnetic Resonance Imaging (MRI) is one of the non-invasive methods that has emanated without ionizing radiation as a front-line diagnostic method for brain tumour. Several approaches have been applied in modern years to segment MRI brain tumours automatically. These methods can be divided into two groups based on conventional learning, such as support vector machine (SVM) and random forest, respectively hand-crafted features and classifier method. However, after deciding hand-crafted features, it uses manually separated features and is given to classifiers as input. These are the time consuming activity, and their output is heavily dependent upon the experience of the operator. This research proposes fully automated detection of brain tumor using Convolutional Neural Network (CNN) to avoid this problem. It also uses brain image of high grade gilomas from the BRATS 2015 database. The suggested research performs brain tumor segmentation using clustering of k-means and patient survival rates are increased with this proposed early diagnosis of brain tumour using CNN.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124314519","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}
Dengue is one of the most significant diseases transmitted by arthropods in the world. Dengue phenotypes are focused on documented inaccuracies in the laboratory and clinical studies. In countries with a high incidence of this disease, early diagnosis of dengue is still a concern for public health. Deep learning has been developed as a highly versatile and accurate methodology for classification and regression, which requires small adjustment, interpretable results, and the prediction of risk for complex diseases. This work is motivated by the inclusion of the Particle Swarm Optimization (PSO) algorithm for the fine-tuning of the model's parameters in the convolutional neural network (CNN). The use of this PSO was used to forecast patients with extreme dengue, and to refine the input weight vector and CNN parameters to achieve anticipated precision, and to prevent premature convergence towards local optimum conditions.
{"title":"Hybrid Convolutional Neural Network with PSO Based Severe Dengue Prognosis Method in Human Genome Data","authors":"Mohammed Mustafa, R. E. Ahmed, S. Eljack","doi":"10.53409/mnaa.jcsit1104","DOIUrl":"https://doi.org/10.53409/mnaa.jcsit1104","url":null,"abstract":"Dengue is one of the most significant diseases transmitted by arthropods in the world. Dengue phenotypes are focused on documented inaccuracies in the laboratory and clinical studies. In countries with a high incidence of this disease, early diagnosis of dengue is still a concern for public health. Deep learning has been developed as a highly versatile and accurate methodology for classification and regression, which requires small adjustment, interpretable results, and the prediction of risk for complex diseases. This work is motivated by the inclusion of the Particle Swarm Optimization (PSO) algorithm for the fine-tuning of the model's parameters in the convolutional neural network (CNN). The use of this PSO was used to forecast patients with extreme dengue, and to refine the input weight vector and CNN parameters to achieve anticipated precision, and to prevent premature convergence towards local optimum conditions.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115322796","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}
There are an increasing number of security threats to the Internet and computer networks. For new kinds of attacks constantly emerging, a major challenge is the development of versatile and innovative security-oriented approaches. Anomaly-based network intrusion detection techniques are in this sense a valuable tool for defending target devices and networks from malicious activities. With testing dataset, this work was able to use the NSL-KDD data collection, the binary and multiclass problems. With that inspiration, data mining techniques are used to offer an automated platform for network attack detection. The system is based on the Hybrid Genetic Neuro-Weighted Algorithm (HNWGA).In this weighted genetic algorithm is used for the selection of features and in this work a neuro-genetic fuzzy classification algorithm has been proposed which is used to identify malicious users by classifying user behaviors. The main benefit of this proposed framework is that it reduces the attacks by highly accurate detection of intruders and minimizes false positives. The evaluation of the performance is performed in NSL-KDD dataset. The experimental result shows of that the proposed work attains better accuracy when compared to previous methods. Such type of IDS systems are used in the identification and response to malicious traffic / activities to improve extremely accuracy.
{"title":"A New Framework for Anomaly Detection in NSL-KDD Dataset using Hybrid Neuro-Weighted Genetic Algorithm","authors":"P. Muneeshwari, M. Kishanthini","doi":"10.53409/mnaa.jcsit1105","DOIUrl":"https://doi.org/10.53409/mnaa.jcsit1105","url":null,"abstract":"There are an increasing number of security threats to the Internet and computer networks. For new kinds of attacks constantly emerging, a major challenge is the development of versatile and innovative security-oriented approaches. Anomaly-based network intrusion detection techniques are in this sense a valuable tool for defending target devices and networks from malicious activities. With testing dataset, this work was able to use the NSL-KDD data collection, the binary and multiclass problems. With that inspiration, data mining techniques are used to offer an automated platform for network attack detection. The system is based on the Hybrid Genetic Neuro-Weighted Algorithm (HNWGA).In this weighted genetic algorithm is used for the selection of features and in this work a neuro-genetic fuzzy classification algorithm has been proposed which is used to identify malicious users by classifying user behaviors. The main benefit of this proposed framework is that it reduces the attacks by highly accurate detection of intruders and minimizes false positives. The evaluation of the performance is performed in NSL-KDD dataset. The experimental result shows of that the proposed work attains better accuracy when compared to previous methods. Such type of IDS systems are used in the identification and response to malicious traffic / activities to improve extremely accuracy.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116774869","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 : 1900-01-01DOI: 10.53409/mnaa/jcsit/2105
Rajesh M N, Chandrasekar B S
Prostate cancer (PCa) is reported as utmost common malignancy, causing substantial morbidity and mortality in men globally. PCa screening happens by digital rectal examination (DRE) along with usage of prostate specific antigen (PSA) examination. Rapid developments in imaging modalities in Ultrasound with multiparametric ultrasound (mpUS) and in Magnetic Resonance imaging with multiparametric magnetic resonance imaging (mpMRI) and also with nuclear imaging with positron emission tomography (PET) are adopted as well as utilized in PCa diagnosis and localizing also in staging as well as for active cancer surveillance and for monitoring cancer recurrence The paper is focused on understanding the recent imaging modalities advocated for PCa imaging.
{"title":"Imaging Modalities used in Prostate Cancer Detection","authors":"Rajesh M N, Chandrasekar B S","doi":"10.53409/mnaa/jcsit/2105","DOIUrl":"https://doi.org/10.53409/mnaa/jcsit/2105","url":null,"abstract":"Prostate cancer (PCa) is reported as utmost common malignancy, causing substantial morbidity and mortality in men globally. PCa screening happens by digital rectal examination (DRE) along with usage of prostate specific antigen (PSA) examination. Rapid developments in imaging modalities in Ultrasound with multiparametric ultrasound (mpUS) and in Magnetic Resonance imaging with multiparametric magnetic resonance imaging (mpMRI) and also with nuclear imaging with positron emission tomography (PET) are adopted as well as utilized in PCa diagnosis and localizing also in staging as well as for active cancer surveillance and for monitoring cancer recurrence The paper is focused on understanding the recent imaging modalities advocated for PCa imaging.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132194469","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 : 1900-01-01DOI: 10.53409/mnaa/jcsit/e202203013342
Salar Faisal Noori, Bazeer Ahamed B
The solutions for the data extraction problem are based on an analysis of the HTML DOM trees and the response page tags. These techniques rely highly on HTML specifications, even though they can produce good results. To effectively disclose in-depth online data, this research provides a methodology with two stages to address the problem. To find the user’s text query, the suggested system first performs “normal crawling.” A method is suggested based on the crawler’s received moved forward weighting work (ITF-IDF) to choose important websites. “data region extraction” is carried out in the second stage to gather data records. The suggested data extractor extracts visual blocks using the blocks’ visual characteristics. According to the suggested technique, the visual blocks should be grouped into similar formats based on format trees and appearance similarity. The visual blocks that will be extracted as information records from the cluster with the highest weight are those that are selected. The test reveals that the system’s suggested outline is superior to earlier information extraction efforts.
{"title":"A Deep Web Data Extraction Framework Enhancement Method","authors":"Salar Faisal Noori, Bazeer Ahamed B","doi":"10.53409/mnaa/jcsit/e202203013342","DOIUrl":"https://doi.org/10.53409/mnaa/jcsit/e202203013342","url":null,"abstract":"The solutions for the data extraction problem are based on an analysis of the HTML DOM trees and the response page tags. These techniques rely highly on HTML specifications, even though they can produce good results. To effectively disclose in-depth online data, this research provides a methodology with two stages to address the problem. To find the user’s text query, the suggested system first performs “normal crawling.” A method is suggested based on the crawler’s received moved forward weighting work (ITF-IDF) to choose important websites. “data region extraction” is carried out in the second stage to gather data records. The suggested data extractor extracts visual blocks using the blocks’ visual characteristics. According to the suggested technique, the visual blocks should be grouped into similar formats based on format trees and appearance similarity. The visual blocks that will be extracted as information records from the cluster with the highest weight are those that are selected. The test reveals that the system’s suggested outline is superior to earlier information extraction efforts.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133003251","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 : 1900-01-01DOI: 10.53409/mnaa.jcsit20201205
Manimurugan S
Determining the size of the tumor is a significant obstacle in brain tumour preparation and objective assessment. Magnetic Resonance Imaging (MRI) is one of the non-invasive methods that has emanated without ionizing radiation as a front-line diagnostic method for brain tumour. Several approaches have been applied in modern years to segment MRI brain tumours automatically. These methods can be divided into two groups based on conventional learning, such as support vectormachine (SVM) and random forest, respectively hand-crafted features and classifier method. However, after deciding hand-crafted features, it uses manually separated features and is given to classifiers as input. These are the time consuming activity, and their output is heavily dependent upon the experience of the operator. This research proposes fully automated detection of brain tumor using Convolutional Neural Network (CNN) to avoid this problem. It also uses brain image of high grade gilomas from the BRATS 2015 database. The suggested research performs brain tumor segmentation using clustering of k-means and patient survival rates are increased with this proposed early diagnosis of brain tumour using CNN.
{"title":"Classification of Alzheimer's disease from MRI Images using CNN based Pre-trained VGG-19 Model","authors":"Manimurugan S","doi":"10.53409/mnaa.jcsit20201205","DOIUrl":"https://doi.org/10.53409/mnaa.jcsit20201205","url":null,"abstract":"Determining the size of the tumor is a significant obstacle in brain tumour preparation and objective assessment. Magnetic Resonance Imaging (MRI) is one of the non-invasive methods that has emanated without ionizing radiation as a front-line diagnostic method for brain tumour. Several approaches have been applied in modern years to segment MRI brain tumours automatically. These methods can be divided into two groups based on conventional learning, such as support vectormachine (SVM) and random forest, respectively hand-crafted features and classifier method. However, after deciding hand-crafted features, it uses manually separated features and is given to classifiers as input. These are the time consuming activity, and their output is heavily dependent upon the experience of the operator. This research proposes fully automated detection of brain tumor using Convolutional Neural Network (CNN) to avoid this problem. It also uses brain image of high grade gilomas from the BRATS 2015 database. The suggested research performs brain tumor segmentation using clustering of k-means and patient survival rates are increased with this proposed early diagnosis of brain tumour using CNN.","PeriodicalId":125707,"journal":{"name":"Journal of Computational Science and Intelligent Technologies","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127975589","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：