Pub Date : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633949
A. Lakshna, K. Ramesh, B. Prabha, D. Sheema, K. Vijayakumar
Smart traffic congestion reduction is useful for reducing the traffic in a highly congested area. To prevent heavy traffic Internet of things is implemented through a small device called a sensor, this technology is called smart traffic. A small device is placed near the roadside street post to detect the vehicle count. Smart traffic works by collecting the various signals like WiFi, Bluetooth, ZigBee from various electronic gadgets like a smartphone, smartwatch, smart band, tablet. The MAC address from each vehicle is collected as input information and stored in a cloud platform. Analyze and calculate the collected data set and performed it under machine learning prediction algorithms to get a better accuracy result to avoid traffic congestion. The logistic regression algorithm gives a 91% of accuracy level in traffic. It gives the shortest route to reach the destination without any hurdles. Results are reduced the traveling time, noise pollution, carbon dioxide emission, reach the destination on correct time and also save the fuel.
{"title":"Machine learning Smart Traffic Prediction and Congestion Reduction","authors":"A. Lakshna, K. Ramesh, B. Prabha, D. Sheema, K. Vijayakumar","doi":"10.1109/ICSES52305.2021.9633949","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633949","url":null,"abstract":"Smart traffic congestion reduction is useful for reducing the traffic in a highly congested area. To prevent heavy traffic Internet of things is implemented through a small device called a sensor, this technology is called smart traffic. A small device is placed near the roadside street post to detect the vehicle count. Smart traffic works by collecting the various signals like WiFi, Bluetooth, ZigBee from various electronic gadgets like a smartphone, smartwatch, smart band, tablet. The MAC address from each vehicle is collected as input information and stored in a cloud platform. Analyze and calculate the collected data set and performed it under machine learning prediction algorithms to get a better accuracy result to avoid traffic congestion. The logistic regression algorithm gives a 91% of accuracy level in traffic. It gives the shortest route to reach the destination without any hurdles. Results are reduced the traveling time, noise pollution, carbon dioxide emission, reach the destination on correct time and also save the fuel.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"5 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74900994","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633844
A. Rameshbabu, G. Sundarrajan, Jebaseelan S D Sundarsingh, A. Dilleswararao, J. B. Paul Glady, J. V. Sunil Kumar
This paper shows a high gain idea for Industrial application to straight forwardly incorporate Boost LLC converter. Here the simulation was developedforFOPID for Boost LLC converter in DC loads system with Power Factor Correction (PFC). This work recommends FOPID to control and improve time domain response in voltage Regulation. The output of Boost LLC converter is measured by using closed loop arrangement. The locked PI & FOPID configured Boost LLC converter arrangements are simulated and outcomes are compared. The outcome of signifies of Boost LLC-FOPID provides a better answer than the Boost LLC-PI controller arrangement. The Boost LLC-FOPID controlled high gain arrangement has better result parameter like reduced steady-state error, rise time, peak time, settling time.
{"title":"Improved Dynamic Response of Boost LLC AC-DC Converter with Voltage Regulation","authors":"A. Rameshbabu, G. Sundarrajan, Jebaseelan S D Sundarsingh, A. Dilleswararao, J. B. Paul Glady, J. V. Sunil Kumar","doi":"10.1109/ICSES52305.2021.9633844","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633844","url":null,"abstract":"This paper shows a high gain idea for Industrial application to straight forwardly incorporate Boost LLC converter. Here the simulation was developedforFOPID for Boost LLC converter in DC loads system with Power Factor Correction (PFC). This work recommends FOPID to control and improve time domain response in voltage Regulation. The output of Boost LLC converter is measured by using closed loop arrangement. The locked PI & FOPID configured Boost LLC converter arrangements are simulated and outcomes are compared. The outcome of signifies of Boost LLC-FOPID provides a better answer than the Boost LLC-PI controller arrangement. The Boost LLC-FOPID controlled high gain arrangement has better result parameter like reduced steady-state error, rise time, peak time, settling time.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"219 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75548898","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633828
H. S. Govinda, Yogesh Chandrakant, D. Girish, S. Lokesh, Ravikiran, B. Jayasri
Online voting system the most suitable replacement for the older generations paper ballot system and the nowadays trending Electronic Voting Machines (EVM). Every year by year the technology tries to reach its peak with immense exploration by revolutionizing the technology which makes the human life with more coloring. Today's Internet gives us access to a wide range of resources, information easily in a second. Among other such experiments is Blockchain. With its special features such as consistency and architecture, many companies, applications are increasingly moving towards them. One major usage of blockchain can be found in electronic-voting system. We can ensure the transparency of the election by placing all messages or details in the Ethereum blockchain, which keeps the privacy of each voter protected with maximum security and provides an effective sign-up process. Blockchain advantages on online-voting systems includes nonchangeable feature called immutable ledger of votes casted using time stamp method, security of voting system, instant validation of votes and counting of votes and updating in public ledger which does not depending upon the number of nodes in the blockchain network.
{"title":"Implementation of Election System Using Blockchain Technology","authors":"H. S. Govinda, Yogesh Chandrakant, D. Girish, S. Lokesh, Ravikiran, B. Jayasri","doi":"10.1109/ICSES52305.2021.9633828","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633828","url":null,"abstract":"Online voting system the most suitable replacement for the older generations paper ballot system and the nowadays trending Electronic Voting Machines (EVM). Every year by year the technology tries to reach its peak with immense exploration by revolutionizing the technology which makes the human life with more coloring. Today's Internet gives us access to a wide range of resources, information easily in a second. Among other such experiments is Blockchain. With its special features such as consistency and architecture, many companies, applications are increasingly moving towards them. One major usage of blockchain can be found in electronic-voting system. We can ensure the transparency of the election by placing all messages or details in the Ethereum blockchain, which keeps the privacy of each voter protected with maximum security and provides an effective sign-up process. Blockchain advantages on online-voting systems includes nonchangeable feature called immutable ledger of votes casted using time stamp method, security of voting system, instant validation of votes and counting of votes and updating in public ledger which does not depending upon the number of nodes in the blockchain network.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"235 1","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73835505","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633953
Abhay Shreekant Shastry, B. Mervyn, Binish Zehra Rizvi, Varun G. Menon, G. Girisha
One of the major factors that determine the growth of a child is bone age. Traditionally, this is determined by using techniques like the TW (Tanner - Whitehouse method) or the GP (Greulich Pyle method) on X-rays of the left hand. The X-rays are examined for any abnormality based on a standard set of regions of interest by a trained medical professional. Therefore, susceptibility to human error is extremely high which causes inconsistencies and often outputs noticeably inaccurate test results. In addition, this process is time-consuming which furthermore affirms the impracticality of using the traditional method. To combat this, deep learning architectures like Convolution Neural Networks (CNN) and their modified counterparts are used to produce significantly more accurate results, in less time. In this paper, we use one such architecture called Xception. This architecture fundamentally replaces the standard Convolution operation with a much more efficient operation called Depthwise Separable Convolution, which in turn drastically reduces the time taken to build a model. Apart from being computationally quick, an exceptional deep learning model must also give accurate results, this is made possible by training a model on an enormous dataset. In this paper, we use a dataset of left-hand Radiographs provided by RSNA. The application of an efficient activation function also contributes to making a better model, in this paper we use two activation functions namely ReLU and Swish to demonstrate the significance activation functions play on the accuracy of the model. The results obtained by our paper indicate that the swish activation function outperforms ReLU in deeper convolution, providing us with 0.183 years MAE compared to the 0.2414 years MAE given by ReLU.
{"title":"Automatic Bone Age Assessment of Radiographs using Deep Learning","authors":"Abhay Shreekant Shastry, B. Mervyn, Binish Zehra Rizvi, Varun G. Menon, G. Girisha","doi":"10.1109/ICSES52305.2021.9633953","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633953","url":null,"abstract":"One of the major factors that determine the growth of a child is bone age. Traditionally, this is determined by using techniques like the TW (Tanner - Whitehouse method) or the GP (Greulich Pyle method) on X-rays of the left hand. The X-rays are examined for any abnormality based on a standard set of regions of interest by a trained medical professional. Therefore, susceptibility to human error is extremely high which causes inconsistencies and often outputs noticeably inaccurate test results. In addition, this process is time-consuming which furthermore affirms the impracticality of using the traditional method. To combat this, deep learning architectures like Convolution Neural Networks (CNN) and their modified counterparts are used to produce significantly more accurate results, in less time. In this paper, we use one such architecture called Xception. This architecture fundamentally replaces the standard Convolution operation with a much more efficient operation called Depthwise Separable Convolution, which in turn drastically reduces the time taken to build a model. Apart from being computationally quick, an exceptional deep learning model must also give accurate results, this is made possible by training a model on an enormous dataset. In this paper, we use a dataset of left-hand Radiographs provided by RSNA. The application of an efficient activation function also contributes to making a better model, in this paper we use two activation functions namely ReLU and Swish to demonstrate the significance activation functions play on the accuracy of the model. The results obtained by our paper indicate that the swish activation function outperforms ReLU in deeper convolution, providing us with 0.183 years MAE compared to the 0.2414 years MAE given by ReLU.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"14 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84905350","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633871
G. Sundarrajan, V. Sivachidambaranathan, J. B. Paul Glady, R. Babu, S. Jebaseelan, Ganesan Subramanian
KY converter a boost converter which consists of power switches, one energy transferring elements and inductor. The circuit involves of two stages inter leaved KY converter to acquire a high voltage conversion ratio. This converter normally has greater voltage gain than the conventional interleaved converters. Voltage strain of the power switches and diode are slow. Efficiency can also be increased to a greater level. It can be used in photo voltaic where input current ripple is a significant concern.
{"title":"A Novel Design on Non-Isolated High-Gain Interleaved KY - Converter with Enhanced Dynamic Performance","authors":"G. Sundarrajan, V. Sivachidambaranathan, J. B. Paul Glady, R. Babu, S. Jebaseelan, Ganesan Subramanian","doi":"10.1109/ICSES52305.2021.9633871","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633871","url":null,"abstract":"KY converter a boost converter which consists of power switches, one energy transferring elements and inductor. The circuit involves of two stages inter leaved KY converter to acquire a high voltage conversion ratio. This converter normally has greater voltage gain than the conventional interleaved converters. Voltage strain of the power switches and diode are slow. Efficiency can also be increased to a greater level. It can be used in photo voltaic where input current ripple is a significant concern.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"5 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75606514","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633832
A. Rameshbabu, G. Sundarrajan, Godwin Immanuel, Barnabas Paul Glady, Sundar Singh S D Jeebaseelan, C. Muthukumar
In this work the PV (Photo Voltaic) panel is used for primary energy supply of the complete arrangement. However, class IV power supply is proposed as a backup power source. The PV output power is fed to zeta converter and class IV source is fed to boost converter with the same input power. In this proposed system the P&O algorithmic method of MPPT is implemented. The P&O algorithm regulates the duty cycles given to zeta converter, that will continue DC link voltage. The motor speed is regulated by correcting the voltage of the DC link in the inverter which is given to motor. When the PV power absent, class IV power and boost converter maintain the voltage constant across DC link. The effectiveness of proposed work can be verified using MATLAB simulation and developed prototype model.
{"title":"MPPT Based Solar PV and Class IV Powered Brushless DC Motor for Water Pump System","authors":"A. Rameshbabu, G. Sundarrajan, Godwin Immanuel, Barnabas Paul Glady, Sundar Singh S D Jeebaseelan, C. Muthukumar","doi":"10.1109/ICSES52305.2021.9633832","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633832","url":null,"abstract":"In this work the PV (Photo Voltaic) panel is used for primary energy supply of the complete arrangement. However, class IV power supply is proposed as a backup power source. The PV output power is fed to zeta converter and class IV source is fed to boost converter with the same input power. In this proposed system the P&O algorithmic method of MPPT is implemented. The P&O algorithm regulates the duty cycles given to zeta converter, that will continue DC link voltage. The motor speed is regulated by correcting the voltage of the DC link in the inverter which is given to motor. When the PV power absent, class IV power and boost converter maintain the voltage constant across DC link. The effectiveness of proposed work can be verified using MATLAB simulation and developed prototype model.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"212 2 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73027751","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633783
CH.V. Krishna Rasagnya, C. R. Kumar
Medical image fusion is a popular subject in the medical imaging industry because it improves clinical diagnostic accuracy by combining complimentary information from several pictures. The existing study involves a multimodal picture fusion technique. This paper presents, including the Convolution Neural Network (CNN), to develop the network for images. With the help of network, feature maps can be developed for images. Finally, by usage of an improved feature maps along merging scheme the fusion of image is produced. MATLAB environment used for simulation for proposed algorithm.
{"title":"Fusion of Medical Images for Better Quality","authors":"CH.V. Krishna Rasagnya, C. R. Kumar","doi":"10.1109/ICSES52305.2021.9633783","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633783","url":null,"abstract":"Medical image fusion is a popular subject in the medical imaging industry because it improves clinical diagnostic accuracy by combining complimentary information from several pictures. The existing study involves a multimodal picture fusion technique. This paper presents, including the Convolution Neural Network (CNN), to develop the network for images. With the help of network, feature maps can be developed for images. Finally, by usage of an improved feature maps along merging scheme the fusion of image is produced. MATLAB environment used for simulation for proposed algorithm.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"119 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76196729","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633843
M. Mahima, Nidhi C. Patel, Srividhya Ravichandran, N. Aishwarya, Sumana Maradithaya
With the growing importance of textual data processing, sentiment analysis which is a field of text mining, has been widely researched. But it is insufficient for the detection of human emotions. Emotion detection, an extension of sentiment analysis, has proven to be one of the most important areas in text mining, especially in the field of human-computer interactions. The recent works on emotion detection primarily focus on facial expressions, voice, audio and gestures. However, the content on the web is mostly text-based and it becomes difficult to capture the human emotions in the absence of facial and audio aspects in the data. Therefore, there is a need to design efficient mining techniques for processing textual data. Traditional approaches overlook disambiguation and ignore the presence of multiple emotions in text. In this paper, we propose a hybrid model which uses rules, sentiments and context for the disambiguation of words by using sentence transformers which recognize the various emotions involved by using natural language processing, sentence embeddings, BERT and similarity techniques so as to overcome such shortcomings. Our work ensures that Ekman's emotions along with neutral emotion are identified such that multiple emotions are tagged precisely based on the context. This hybrid method has proven to be far superior than existing approaches for the detection of multiple emotions.
{"title":"A Text-Based Hybrid Approach for Multiple Emotion Detection Using Contextual and Semantic Analysis","authors":"M. Mahima, Nidhi C. Patel, Srividhya Ravichandran, N. Aishwarya, Sumana Maradithaya","doi":"10.1109/ICSES52305.2021.9633843","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633843","url":null,"abstract":"With the growing importance of textual data processing, sentiment analysis which is a field of text mining, has been widely researched. But it is insufficient for the detection of human emotions. Emotion detection, an extension of sentiment analysis, has proven to be one of the most important areas in text mining, especially in the field of human-computer interactions. The recent works on emotion detection primarily focus on facial expressions, voice, audio and gestures. However, the content on the web is mostly text-based and it becomes difficult to capture the human emotions in the absence of facial and audio aspects in the data. Therefore, there is a need to design efficient mining techniques for processing textual data. Traditional approaches overlook disambiguation and ignore the presence of multiple emotions in text. In this paper, we propose a hybrid model which uses rules, sentiments and context for the disambiguation of words by using sentence transformers which recognize the various emotions involved by using natural language processing, sentence embeddings, BERT and similarity techniques so as to overcome such shortcomings. Our work ensures that Ekman's emotions along with neutral emotion are identified such that multiple emotions are tagged precisely based on the context. This hybrid method has proven to be far superior than existing approaches for the detection of multiple emotions.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"23 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86892805","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633816
Narasimha Reddy Soora, Kumar Dorthi, Sai Vythik Mankala
In ordered to identify an object in an image it is considered a single unit and this process is known as image processing. So, In this paper, we have proposed a novel feature extraction (FE) technique for character/digit recognition (CR) by applying perpendicular distance onto a sweep line from borders of the input character. Proposing a robust FE technique is crucial for any CR system for better performance. CR plays crucial role in many Image Processing (IP) applications. Before extracting the features of the image, process it by converting into grey scale and subsequently to binary image. A scan line is generated in the binary image and traversed perpendicularly from each point on the scan line to both directions to get the extreme end points which is taken as perpendicular distance. The extracted features are in a DB/text file for recognition of input characters. A data set containing 10, 000 images have been used for performance analysis and separated them into 2 different categories as training, testing sets and stored the extracted features in the DB/text file along with the label which it specifies while training and test the efficiency of the model. Chi-square statistic is used as classifier in this paper. We have achieved encouraging results using the proposed CR FE technique when compared with the other CR FE techniques from the literature.
{"title":"Character Recognition using Perpendicular Distance on Sweep Line and Chi-Square Statistic as classifier","authors":"Narasimha Reddy Soora, Kumar Dorthi, Sai Vythik Mankala","doi":"10.1109/ICSES52305.2021.9633816","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633816","url":null,"abstract":"In ordered to identify an object in an image it is considered a single unit and this process is known as image processing. So, In this paper, we have proposed a novel feature extraction (FE) technique for character/digit recognition (CR) by applying perpendicular distance onto a sweep line from borders of the input character. Proposing a robust FE technique is crucial for any CR system for better performance. CR plays crucial role in many Image Processing (IP) applications. Before extracting the features of the image, process it by converting into grey scale and subsequently to binary image. A scan line is generated in the binary image and traversed perpendicularly from each point on the scan line to both directions to get the extreme end points which is taken as perpendicular distance. The extracted features are in a DB/text file for recognition of input characters. A data set containing 10, 000 images have been used for performance analysis and separated them into 2 different categories as training, testing sets and stored the extracted features in the DB/text file along with the label which it specifies while training and test the efficiency of the model. Chi-square statistic is used as classifier in this paper. We have achieved encouraging results using the proposed CR FE technique when compared with the other CR FE techniques from the literature.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"05 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90208983","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 : 2021-09-24DOI: 10.1109/ICSES52305.2021.9633795
B. Markapudi, Kunchaparthi Jyothsna Latha, Kavitha Chaduvula
Decision trees, support vector machine and gradient boosting are very popular algorithms for predicting the customer churn with good comprehensibility and strong predictive performance. In spite ofall strengths, the decision trees be likely have some problems forholding linear-relations amongthe variables, support vector machine performs marginally better than logistic regression, and gradient boosting givesgreater results when compared with logistic regression, with less development effort. Hencenew hybrid-algorithm, aboosting leaf model (BLM), was proposed forclassifying the data in better way. The basic idea behind this BLM is diverse models was constructed among the segments of data instead of entire dataset thusleads to improved predictive performances how ever observance comprehensibility among those models which constructed on leaves. ThisBLM resides two stages they are one is segmentation and the other one is prediction stages. Inthe first stageby using decision tree segments of customers are identified and second stagemodel wasappliedon each leaf of the tree. This new hybrid-approach was bench-marked compared with decision trees, support leaf model, andlogit leaf model (LLM)regards predictive performance and comprehensibility. The top decile lift (TDL), area under Receiver Operating Characteristics curve (AUC) which used to measure theirpredictive performancesof which BLM marksknowinglyimprovedtheirblocks support vectormachine, decision trees which performs howeverwith advanced ensemble methods logit leaf model.
{"title":"A New hybrid classification algorithm for predicting customer churn","authors":"B. Markapudi, Kunchaparthi Jyothsna Latha, Kavitha Chaduvula","doi":"10.1109/ICSES52305.2021.9633795","DOIUrl":"https://doi.org/10.1109/ICSES52305.2021.9633795","url":null,"abstract":"Decision trees, support vector machine and gradient boosting are very popular algorithms for predicting the customer churn with good comprehensibility and strong predictive performance. In spite ofall strengths, the decision trees be likely have some problems forholding linear-relations amongthe variables, support vector machine performs marginally better than logistic regression, and gradient boosting givesgreater results when compared with logistic regression, with less development effort. Hencenew hybrid-algorithm, aboosting leaf model (BLM), was proposed forclassifying the data in better way. The basic idea behind this BLM is diverse models was constructed among the segments of data instead of entire dataset thusleads to improved predictive performances how ever observance comprehensibility among those models which constructed on leaves. ThisBLM resides two stages they are one is segmentation and the other one is prediction stages. Inthe first stageby using decision tree segments of customers are identified and second stagemodel wasappliedon each leaf of the tree. This new hybrid-approach was bench-marked compared with decision trees, support leaf model, andlogit leaf model (LLM)regards predictive performance and comprehensibility. The top decile lift (TDL), area under Receiver Operating Characteristics curve (AUC) which used to measure theirpredictive performancesof which BLM marksknowinglyimprovedtheirblocks support vectormachine, decision trees which performs howeverwith advanced ensemble methods logit leaf model.","PeriodicalId":6777,"journal":{"name":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","volume":"15 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86238614","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：