Pub Date : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296195
M. Dileep, A. Navaneeth, Savita Ullagaddi, A. Danti
Drones are considered to be the greatest invention of mankind. Drones can be used in many areas widely. Drones can also be used in agriculture and it is called as unnamed aerial vehicles (UAV). In the traditional agriculture methods land vehicles are used to monitor various activities of the agriculture, this was consuming lot of human effort and time. Using drones in agriculture is more beneficial than using traditional methods for the activities. Usage of drones in agriculture provides a huge benefit in terms of economy and time due to their most astonishing features. In recent years many surveys have proved that drones can cover almost 10 to 15 times of the area which can be covered with traditional land based techniques. Drones can be controlled by computers according to their capacities, that is drones can be automated over some range of area, locating remote area, and even can be semi-automated. Drones can be efficiently used in agriculture for performing certain activities such as, studying weather conditions and variations, infection for the crops, land fertility and many more. Because of the efficiency of the drones they can be used in various activities of agriculture. In this paper, a detailed study has been made on various types of agricultural drones based on the feature, capacity, range as well as cost and the area of agriculture where they suit the most, and a statistical analysis about the usage of the drones in the field of agriculture.
{"title":"A Study and Analysis on Various Types of Agricultural Drones and its Applications","authors":"M. Dileep, A. Navaneeth, Savita Ullagaddi, A. Danti","doi":"10.1109/ICRCICN50933.2020.9296195","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296195","url":null,"abstract":"Drones are considered to be the greatest invention of mankind. Drones can be used in many areas widely. Drones can also be used in agriculture and it is called as unnamed aerial vehicles (UAV). In the traditional agriculture methods land vehicles are used to monitor various activities of the agriculture, this was consuming lot of human effort and time. Using drones in agriculture is more beneficial than using traditional methods for the activities. Usage of drones in agriculture provides a huge benefit in terms of economy and time due to their most astonishing features. In recent years many surveys have proved that drones can cover almost 10 to 15 times of the area which can be covered with traditional land based techniques. Drones can be controlled by computers according to their capacities, that is drones can be automated over some range of area, locating remote area, and even can be semi-automated. Drones can be efficiently used in agriculture for performing certain activities such as, studying weather conditions and variations, infection for the crops, land fertility and many more. Because of the efficiency of the drones they can be used in various activities of agriculture. In this paper, a detailed study has been made on various types of agricultural drones based on the feature, capacity, range as well as cost and the area of agriculture where they suit the most, and a statistical analysis about the usage of the drones in the field of agriculture.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115413537","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296186
M. Dhar, S. M. Nahid Hasan, Tahsin Rahaman Otushi, Musharrat Khan
Clustering method splits a large dataset into smaller subsets, where each subset is called a cluster. Every cluster has the same characteristics and each cluster is different from all other clusters. The most common clustering algorithms are the k-Means clustering algorithm and the k-Medoids clustering algorithm. Clustering of high-dimensional dataset may become difficult. To overcome the problem, dimesion of the dataset is reduced. In the present work, we reduce dimension of a dataset by selecting suitable subset of features using entropy-based method. We calculate entropy using both Euclidean and Manhattan distances. We experiment with three widely used datasets from the Machine Learning Repository of the University of California, Irvine (UCI). From the results of experimentation, we can conclude that our approach produces higher clustering accuracies than those of previous $works$.
{"title":"Entropy-Based Feature Selection for Data Clustering Using k-Means and k-Medoids Algorithms","authors":"M. Dhar, S. M. Nahid Hasan, Tahsin Rahaman Otushi, Musharrat Khan","doi":"10.1109/ICRCICN50933.2020.9296186","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296186","url":null,"abstract":"Clustering method splits a large dataset into smaller subsets, where each subset is called a cluster. Every cluster has the same characteristics and each cluster is different from all other clusters. The most common clustering algorithms are the k-Means clustering algorithm and the k-Medoids clustering algorithm. Clustering of high-dimensional dataset may become difficult. To overcome the problem, dimesion of the dataset is reduced. In the present work, we reduce dimension of a dataset by selecting suitable subset of features using entropy-based method. We calculate entropy using both Euclidean and Manhattan distances. We experiment with three widely used datasets from the Machine Learning Repository of the University of California, Irvine (UCI). From the results of experimentation, we can conclude that our approach produces higher clustering accuracies than those of previous $works$.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124843335","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296201
S. Dhar, Hiranmoy Roy, A. Mukhopadhyay, Antu Kundu, A. Ghosh, Soham Roy
An underwater image suffers from degradation due to the physical attributes of water. The enhancement of degraded underwater images is an important area of research. Several researchers have been using machine learning-based models for enhancement. But, the network models are solely based on training data and the results are difficult to explain. Here, we present a novel enhancement technique for underwater image utilizing a set of enhancement functions and a Convolutional neural network(CNN). The four functions are blended to create the resultant enhancement function. The proposed network is interpretable in the sense that the work of the four functions are easily understandable and they can efficiently enhance different part of an underwater image. The CNNs are used to tune the parameters of the functions depending on the training data. The performance of the proposed method is quite efficient compared to the recently published methods on standard dataset.
{"title":"Interpretable Underwater Image Enhancement based on Convolutional Neural Network","authors":"S. Dhar, Hiranmoy Roy, A. Mukhopadhyay, Antu Kundu, A. Ghosh, Soham Roy","doi":"10.1109/ICRCICN50933.2020.9296201","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296201","url":null,"abstract":"An underwater image suffers from degradation due to the physical attributes of water. The enhancement of degraded underwater images is an important area of research. Several researchers have been using machine learning-based models for enhancement. But, the network models are solely based on training data and the results are difficult to explain. Here, we present a novel enhancement technique for underwater image utilizing a set of enhancement functions and a Convolutional neural network(CNN). The four functions are blended to create the resultant enhancement function. The proposed network is interpretable in the sense that the work of the four functions are easily understandable and they can efficiently enhance different part of an underwater image. The CNNs are used to tune the parameters of the functions depending on the training data. The performance of the proposed method is quite efficient compared to the recently published methods on standard dataset.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125553358","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296166
S. De, Sandip Dey, Soumyaratna Debnath, Abhirup Deb
This paper presents a modified evolution strategy based meta-heuristic, named Modified Red Deer Algorithm (MRDA), which can be effectively and methodically applied to solve single-objective optimization problems. Recently, the actions of red deers have been analysed during their breading time, that in turn inspired the researchers to develop a popular meta-heuristic, called Red Deer Algorithm (RDA). The RDA has been designed to deal with different combinatorial optimization problems in a variety of real-life applications. This paper introduces few adaptive approaches to modify the inherent operators and parameters of RDA to enhance its efficacy. As a comparative study, the performance of MRDA has been evaluated with RDA and Classical Genetic Algorithm (CGA) by utilizing some real-life gray-scale images. At the outset, the results of these competitive algorithms have been assessed with respect to optimum fitness, worst fitness, average fitness, standard deviation, convergence time at best case and average convergence time at three distinct level of thresholding for each test image. Finally, t-test and Friedman Test have been conducted among themselves to check out the superiority. This comparative analysis establishes that MRDA outperforms others in all facets and furnish exceedingly competitive results.
{"title":"A New Modified Red Deer Algorithm for Multi-level Image Thresholding","authors":"S. De, Sandip Dey, Soumyaratna Debnath, Abhirup Deb","doi":"10.1109/ICRCICN50933.2020.9296166","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296166","url":null,"abstract":"This paper presents a modified evolution strategy based meta-heuristic, named Modified Red Deer Algorithm (MRDA), which can be effectively and methodically applied to solve single-objective optimization problems. Recently, the actions of red deers have been analysed during their breading time, that in turn inspired the researchers to develop a popular meta-heuristic, called Red Deer Algorithm (RDA). The RDA has been designed to deal with different combinatorial optimization problems in a variety of real-life applications. This paper introduces few adaptive approaches to modify the inherent operators and parameters of RDA to enhance its efficacy. As a comparative study, the performance of MRDA has been evaluated with RDA and Classical Genetic Algorithm (CGA) by utilizing some real-life gray-scale images. At the outset, the results of these competitive algorithms have been assessed with respect to optimum fitness, worst fitness, average fitness, standard deviation, convergence time at best case and average convergence time at three distinct level of thresholding for each test image. Finally, t-test and Friedman Test have been conducted among themselves to check out the superiority. This comparative analysis establishes that MRDA outperforms others in all facets and furnish exceedingly competitive results.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115987093","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296196
Yong Woon Kim, J. Innila Rose, Addapalli V. N. Krishna
Portrait segmentation is widely used as a preprocessing step in multiple applications. The accuracy of portrait segmentation models indicates its reliability. In recent times, portrait segmentation using deep learning models have achieved significant success in performance and accuracy. However, these portrait segmentation models are limited to a single model. In this paper, we propose ensemble approach using multiple portrait segmentation models to improve the segmentation accuracy. The result of experiment shows that the proposed ensemble approach produces better accuracy than individual models. Accuracy of single models and proposed ensemble approach were compared with Intersection over Union (IoU) metric and false prediction rate to evaluate the accuracy performance. The result shows reduced false negative rate and false discovery rate, this reduction in false prediction has enabled ensemble approach to produce segmented images with optimized error and improved result of segmentation in portrait area of human body than individual portrait segmentation models
在许多应用中，人像分割被广泛用作预处理步骤。图像分割模型的准确性表明了其可靠性。近年来，使用深度学习模型的人像分割在性能和准确性方面取得了显著的成功。然而，这些人像分割模型都局限于单个模型。在本文中，我们提出了使用多个肖像分割模型的集成方法来提高分割精度。实验结果表明，所提出的集成方法比单个模型具有更高的精度。将单一模型和集成方法的准确率与IoU (Intersection over Union)度量和错误预测率进行比较，以评估准确率性能。结果表明，该方法降低了假阴性率和假发现率，减少了错误预测，使得集成方法产生的分割图像误差优化，在人体肖像区域的分割效果优于单个肖像分割模型
{"title":"Accuracy Enhancement of Portrait Segmentation by Ensembling Deep Learning Models","authors":"Yong Woon Kim, J. Innila Rose, Addapalli V. N. Krishna","doi":"10.1109/ICRCICN50933.2020.9296196","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296196","url":null,"abstract":"Portrait segmentation is widely used as a preprocessing step in multiple applications. The accuracy of portrait segmentation models indicates its reliability. In recent times, portrait segmentation using deep learning models have achieved significant success in performance and accuracy. However, these portrait segmentation models are limited to a single model. In this paper, we propose ensemble approach using multiple portrait segmentation models to improve the segmentation accuracy. The result of experiment shows that the proposed ensemble approach produces better accuracy than individual models. Accuracy of single models and proposed ensemble approach were compared with Intersection over Union (IoU) metric and false prediction rate to evaluate the accuracy performance. The result shows reduced false negative rate and false discovery rate, this reduction in false prediction has enabled ensemble approach to produce segmented images with optimized error and improved result of segmentation in portrait area of human body than individual portrait segmentation models","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130449531","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9295965
S. Dhar, M. Kundu, Hiranmoy Roy
Industry uses nondestructive testing (NDT) to detect a fault in metal without damaging it. Image segmentation based technique for detecting the fault from an NDT image is a difficult task. The difficulty emerges due to uncertainties in the NDT image pattern. To segment an NDT image efficiently the uncertainties should be handled efficiently. In this paper, we present a novel technique to segment an NDT image by handling the uncertainties based on neutrosophic set(NS). The NS manages the uncertainties by representing an image into a true, false, and indeterminate subset. For proper NS value representation, two operations α – mean and β – enhancement are essential. For finding the proper values of α and β depending on the image statistics we utilize the bat algorithm(BA). The algorithm finds the optimal values of α and β for managing the uncertainties properly. We find that in terms of performance the proposed method is quite satisfying in comparison to the latest methods.
{"title":"Nondestructive Testing Image Segmentation based on Neutrosophic Set and Bat Algorithm","authors":"S. Dhar, M. Kundu, Hiranmoy Roy","doi":"10.1109/ICRCICN50933.2020.9295965","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9295965","url":null,"abstract":"Industry uses nondestructive testing (NDT) to detect a fault in metal without damaging it. Image segmentation based technique for detecting the fault from an NDT image is a difficult task. The difficulty emerges due to uncertainties in the NDT image pattern. To segment an NDT image efficiently the uncertainties should be handled efficiently. In this paper, we present a novel technique to segment an NDT image by handling the uncertainties based on neutrosophic set(NS). The NS manages the uncertainties by representing an image into a true, false, and indeterminate subset. For proper NS value representation, two operations α – mean and β – enhancement are essential. For finding the proper values of α and β depending on the image statistics we utilize the bat algorithm(BA). The algorithm finds the optimal values of α and β for managing the uncertainties properly. We find that in terms of performance the proposed method is quite satisfying in comparison to the latest methods.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130860647","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296193
Arnab Dey, P. Chanda, S. Sarkar
Today rapid growth of communication and internet technologies has resulted in a significant enhancement of IoT devices. Even the best hospitals and doctors need to develop more in terms of patient care. In case of long waiting periods, a long term gap between doctor visits, inadequate data collection, and other challenges may create problems to healthcare professionals from giving the best care possible. The patients who are suffering from chronic diseases for them ehealthcare are a daily concern. They require disease management tools not only during their doctor visits but every day. In global pandemic situations like today’s, this automated software with the features of Machine Learning will help patients and doctors to maintain physical distance; doctors can monitor patients and prescribe medication to the respective patient from anywhere. Whenever Doctor is unable to monitor patient then this IoT based Machine Learning model will help patients to provide proper medicine through medical staff available based on the symptoms and reports from the IoT sensors with the Machine Learning (ML) trained data set. Here the results obtained for prediction of diabetes and heart diseases, through various machine learning approaches are shown. The obtained results show that for the Gradient Boost, KNN, Random Forest Based classification approaches classify the diseases with higher accuracy rates than the existing models.
{"title":"Patient Health Observation and Analysis With Machine Learning And IoT Based in Realtime Environment","authors":"Arnab Dey, P. Chanda, S. Sarkar","doi":"10.1109/ICRCICN50933.2020.9296193","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296193","url":null,"abstract":"Today rapid growth of communication and internet technologies has resulted in a significant enhancement of IoT devices. Even the best hospitals and doctors need to develop more in terms of patient care. In case of long waiting periods, a long term gap between doctor visits, inadequate data collection, and other challenges may create problems to healthcare professionals from giving the best care possible. The patients who are suffering from chronic diseases for them ehealthcare are a daily concern. They require disease management tools not only during their doctor visits but every day. In global pandemic situations like today’s, this automated software with the features of Machine Learning will help patients and doctors to maintain physical distance; doctors can monitor patients and prescribe medication to the respective patient from anywhere. Whenever Doctor is unable to monitor patient then this IoT based Machine Learning model will help patients to provide proper medicine through medical staff available based on the symptoms and reports from the IoT sensors with the Machine Learning (ML) trained data set. Here the results obtained for prediction of diabetes and heart diseases, through various machine learning approaches are shown. The obtained results show that for the Gradient Boost, KNN, Random Forest Based classification approaches classify the diseases with higher accuracy rates than the existing models.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116600460","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296175
A. Mandayam, Rakshith A.C, S. Siddesha, S. Niranjan
With the progression in the field of machine learning, predictive analysis has become a key component for future prediction. As we face the COVID-19 pandemic, it would be helpful to predict the future number of positive cases for better measures and control. We used two supervised learning models to predict the future using the time-series dataset of COVID-19. To study the performance of prediction, the comparison between Linear Regression and Support Vector Regression is carried out. We have used these two models as the data were almost linear.
{"title":"Prediction of Covid-19 pandemic based on Regression","authors":"A. Mandayam, Rakshith A.C, S. Siddesha, S. Niranjan","doi":"10.1109/ICRCICN50933.2020.9296175","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296175","url":null,"abstract":"With the progression in the field of machine learning, predictive analysis has become a key component for future prediction. As we face the COVID-19 pandemic, it would be helpful to predict the future number of positive cases for better measures and control. We used two supervised learning models to predict the future using the time-series dataset of COVID-19. To study the performance of prediction, the comparison between Linear Regression and Support Vector Regression is carried out. We have used these two models as the data were almost linear.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123722171","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296176
J. Dutta, Yong Woon Kim, Dalia Dominic
Web page classification is an important task in various areas like web content filtering, contextual advertising and maintaining or expanding web directories etc. Machine Learning methods have been found to perform well to classify web pages, and ensemble models have been used to improve the results obtained from single classifiers. The Gradient Boosting and Extreme Boosting ensemble models are used in this work for binary classification. The dataset containing URLs of web pages have been collected manually. The comparison between the two boosting algorithms validated the improvement in accuracy and speed obtained through Extreme boosting. Extreme boosting has been found to be around ten times faster than Gradient boosting and also shows improvement in accuracy. The effect of three preprocessing techniques; lemmatization, stop words removal and regular expressions shows that these preprocessing techniques improves the accuracy of the results but not significantly.
{"title":"Comparison of Gradient Boosting and Extreme Boosting Ensemble Methods for Webpage Classification","authors":"J. Dutta, Yong Woon Kim, Dalia Dominic","doi":"10.1109/ICRCICN50933.2020.9296176","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296176","url":null,"abstract":"Web page classification is an important task in various areas like web content filtering, contextual advertising and maintaining or expanding web directories etc. Machine Learning methods have been found to perform well to classify web pages, and ensemble models have been used to improve the results obtained from single classifiers. The Gradient Boosting and Extreme Boosting ensemble models are used in this work for binary classification. The dataset containing URLs of web pages have been collected manually. The comparison between the two boosting algorithms validated the improvement in accuracy and speed obtained through Extreme boosting. Extreme boosting has been found to be around ten times faster than Gradient boosting and also shows improvement in accuracy. The effect of three preprocessing techniques; lemmatization, stop words removal and regular expressions shows that these preprocessing techniques improves the accuracy of the results but not significantly.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124301088","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 : 2020-11-26DOI: 10.1109/ICRCICN50933.2020.9296182
Ruchita Manohar, Ranjith Kumar Sreenilayam, V. Pandey
Communication networks have become integral part of our modern IoT systems. These networks are widely being used in industrial, commercial and residential applications. Reliability analysis plays a major role in identification of existing problems in network, and on improving communication based on node capabilities.To ensure error free communication in any network, usually BER/PER estimation is performed on bit or packet level. In case of WLAN networks, availability as matrix would be the best suit to measure the reliability of the communication network. The System Behavioral Test (SBT) approach is implemented to cover the effects of noise parameters on the communication reliability.This paper focuses on defining a standard approach for risk identification and testing strategy for WLAN type of networks. This work focusses on defining failure modes, factors impacting those failure modes, and standard test strategy based on SBT for any product in which WLAN communication is used.
{"title":"Functional Approach for Reliability Evaluation of WLAN Communication Networks","authors":"Ruchita Manohar, Ranjith Kumar Sreenilayam, V. Pandey","doi":"10.1109/ICRCICN50933.2020.9296182","DOIUrl":"https://doi.org/10.1109/ICRCICN50933.2020.9296182","url":null,"abstract":"Communication networks have become integral part of our modern IoT systems. These networks are widely being used in industrial, commercial and residential applications. Reliability analysis plays a major role in identification of existing problems in network, and on improving communication based on node capabilities.To ensure error free communication in any network, usually BER/PER estimation is performed on bit or packet level. In case of WLAN networks, availability as matrix would be the best suit to measure the reliability of the communication network. The System Behavioral Test (SBT) approach is implemented to cover the effects of noise parameters on the communication reliability.This paper focuses on defining a standard approach for risk identification and testing strategy for WLAN type of networks. This work focusses on defining failure modes, factors impacting those failure modes, and standard test strategy based on SBT for any product in which WLAN communication is used.","PeriodicalId":138966,"journal":{"name":"2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129924140","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：