Pub Date : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009148
N. S, Manu S Rao, Sagar B M, P. T, Cauvery N K
Deep learning is a branch of Artificial Intelligence (AI) where neural networks are trained to learn patterns from large amounts of data. The primary issue raised by the growth in data volume and diversity of neural networks is selecting hardware accelerators that are effective and appropriate for the specified dataset and selected neural network. This paper studies the performance of CPU and GPU based on the input data size, size of data batches and type of neural network chosen. Four datasets were chosen for benchmark testing, these included a csv data file, a textual dataset and two image datasets. Suitable neural networks were chosen for given data sets. Tests were performed on Intel i5 9th gen CPU and NVIDIA GeForce GTX 1650 GPU. The results show that performance of CPU and GPU doesn't depend on the data format, but rather depends on the type of architecture of the neural network. Neural networks which support parallelization, provide performance boost in GPU s compared to CPUs. When ANN architecture was used, CPUs performed 1.2 times better than GPUs in terms of execution time. With deeper CNN models GPUs performed 8.8 times and with RNNs 4.90 times faster than CPU s. Linear relation between dataset size and training time was observed and GPUs outdid CPUs when batch size was increased irrespective of NN architecture.
{"title":"Performance of CPUs and GPUs on Deep Learning Models For Heterogeneous Datasets","authors":"N. S, Manu S Rao, Sagar B M, P. T, Cauvery N K","doi":"10.1109/ICECA55336.2022.10009148","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009148","url":null,"abstract":"Deep learning is a branch of Artificial Intelligence (AI) where neural networks are trained to learn patterns from large amounts of data. The primary issue raised by the growth in data volume and diversity of neural networks is selecting hardware accelerators that are effective and appropriate for the specified dataset and selected neural network. This paper studies the performance of CPU and GPU based on the input data size, size of data batches and type of neural network chosen. Four datasets were chosen for benchmark testing, these included a csv data file, a textual dataset and two image datasets. Suitable neural networks were chosen for given data sets. Tests were performed on Intel i5 9th gen CPU and NVIDIA GeForce GTX 1650 GPU. The results show that performance of CPU and GPU doesn't depend on the data format, but rather depends on the type of architecture of the neural network. Neural networks which support parallelization, provide performance boost in GPU s compared to CPUs. When ANN architecture was used, CPUs performed 1.2 times better than GPUs in terms of execution time. With deeper CNN models GPUs performed 8.8 times and with RNNs 4.90 times faster than CPU s. Linear relation between dataset size and training time was observed and GPUs outdid CPUs when batch size was increased irrespective of NN architecture.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127992453","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009394
Saravanan Alagarsamy, S. A. Reddy, V. V. Reddy, Varun S. Reddy, Y.V. Praneeth Reddy
Physically challenged people are feeling quite difficult to operate a mouse. The suggested method employs eye moments to direct the mouse pointer as a remedy for those who are physically unable to do so. The computer vision technique is useful for controlling the mouse on a computer using eye movements. It is an alternate way that enables a person to operate their computer using their eyes alone for those who are unable to use a mouse. For those with physical disabilities, eye moment might be seen as a crucial real-time input modality for human-computer communication. The suggested method explains how to utilize a webcam and Python to implement both eye moment and moment of cursor according to eye location, which may be used to control the cursor on the screen. Eye tracking is a sensor technology that can track what someone is looking at in real time while also detecting their presence. Eye motions are converted by the technology into a data stream that includes details like pupil position, gaze vectors for each eye, and gaze point.
{"title":"Control the Movement of Mouse Using Computer Vision technique","authors":"Saravanan Alagarsamy, S. A. Reddy, V. V. Reddy, Varun S. Reddy, Y.V. Praneeth Reddy","doi":"10.1109/ICECA55336.2022.10009394","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009394","url":null,"abstract":"Physically challenged people are feeling quite difficult to operate a mouse. The suggested method employs eye moments to direct the mouse pointer as a remedy for those who are physically unable to do so. The computer vision technique is useful for controlling the mouse on a computer using eye movements. It is an alternate way that enables a person to operate their computer using their eyes alone for those who are unable to use a mouse. For those with physical disabilities, eye moment might be seen as a crucial real-time input modality for human-computer communication. The suggested method explains how to utilize a webcam and Python to implement both eye moment and moment of cursor according to eye location, which may be used to control the cursor on the screen. Eye tracking is a sensor technology that can track what someone is looking at in real time while also detecting their presence. Eye motions are converted by the technology into a data stream that includes details like pupil position, gaze vectors for each eye, and gaze point.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127530758","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009412
P. Srihari, J. Harikiran
Thermal image is formed by capturing of radiation emitted by object to its surroundings and the difference in radiation of object and its surroundings. The advantages of Thermal images over Normal RGB images is the ability to visible at night time irrespective of illumination conditions and weather conditions like rain, fog, mist, and dust. Thermal images can form images in typical situations like smoke, dust, and high intensity, where the normal RGB camera fails to capture image. Human Activity Recognition in Thermal Images is still a challenging task due to less availability of Thermal Human Activity Datasets. This research work has proposed a human activity recognition system using Siamese Networks of Gait Skeleton Thermal Images. The proposed approach can train a new human activity by extracting Gait Skeleton from existing RGB videos and can be compared to a gait skeleton extracted from a Thermal video in case of utilizing very less thermal videos for human activity recognition. Thermal videos are extracted from IITR- IAR dataset and the performance is analyzed with CNN+LSTM, LRCN, Inflated 3D CNN, Siamese using accuracy and the proposed model has achieved a better accuracy when compared to CNN+LSTM, LRCN, Inflated 3D CNN.
热图像是通过捕获物体对周围环境的辐射以及物体与周围环境的辐射差而形成的。与普通RGB图像相比，热图像的优点是能够在夜间看到，而不受照明条件和雨、雾、雾和灰尘等天气条件的影响。热成像可以在烟雾、灰尘和高强度等典型情况下形成图像，而普通RGB相机无法捕获图像。由于热人体活动数据集的可用性较低，热图像中的人体活动识别仍然是一项具有挑战性的任务。本研究提出了一种基于步态骨骼热图像连体网络的人体活动识别系统。该方法可以通过从现有的RGB视频中提取步态骨架来训练新的人体活动，并且可以在使用很少的热视频进行人体活动识别的情况下与从热视频中提取的步态骨架进行比较。从IITR- IAR数据集中提取热视频，并使用CNN+LSTM、LRCN、Inflated 3D CNN、Siamese进行准确率分析，与CNN+LSTM、LRCN、Inflated 3D CNN相比，本文提出的模型取得了更好的准确率。
{"title":"Skeleton Based Human Activity Prediction in Gait Thermal images using Siamese Networks","authors":"P. Srihari, J. Harikiran","doi":"10.1109/ICECA55336.2022.10009412","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009412","url":null,"abstract":"Thermal image is formed by capturing of radiation emitted by object to its surroundings and the difference in radiation of object and its surroundings. The advantages of Thermal images over Normal RGB images is the ability to visible at night time irrespective of illumination conditions and weather conditions like rain, fog, mist, and dust. Thermal images can form images in typical situations like smoke, dust, and high intensity, where the normal RGB camera fails to capture image. Human Activity Recognition in Thermal Images is still a challenging task due to less availability of Thermal Human Activity Datasets. This research work has proposed a human activity recognition system using Siamese Networks of Gait Skeleton Thermal Images. The proposed approach can train a new human activity by extracting Gait Skeleton from existing RGB videos and can be compared to a gait skeleton extracted from a Thermal video in case of utilizing very less thermal videos for human activity recognition. Thermal videos are extracted from IITR- IAR dataset and the performance is analyzed with CNN+LSTM, LRCN, Inflated 3D CNN, Siamese using accuracy and the proposed model has achieved a better accuracy when compared to CNN+LSTM, LRCN, Inflated 3D CNN.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127582971","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009174
P. Kumar, S. S. Harrsha, K. Abhiram, M. Kavitha, M. Kalyani
In today's culture the growing technology is promoting a lot of products and events in a very positive way. Technology usage in current generation has taken a new step in reaching great heights. But when a technology brings in so much positiveness it also has its own negative usage and one among them is the fake reviews. Fake reviews are weakening the actual worth of the product. To be more specific, the reviews can be divided into two categories: legitimate fake reviews and reviews written intentionally to decapitate the product or brand value. On the other hand, the machine learning algorithms are extensively used. The incorporation of machine learning techniques into the classification of the reviews is considered as an excellent combination. In this work, various datasets from different industries such as airline industry, movie industry and food industry are considered and fake reviews are classified using various algorithms including K-Nearest Neighbors, Naive Bayes, Random Forest, Decision tree, Support Vector Machine, Logistic Regression from Machine learning. There are reviews which can be decoded using the sentiment analysis from Natural Language Programming. Sentiment analysis is used to find the emotion in a text. The accuracy parameter result is analyzed for all the implemented models. The results demonstrate support vector machine technique giving high accuracy compared to other machine learning classification techniques.
{"title":"Role of Machine Learning in Fake Review Detection","authors":"P. Kumar, S. S. Harrsha, K. Abhiram, M. Kavitha, M. Kalyani","doi":"10.1109/ICECA55336.2022.10009174","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009174","url":null,"abstract":"In today's culture the growing technology is promoting a lot of products and events in a very positive way. Technology usage in current generation has taken a new step in reaching great heights. But when a technology brings in so much positiveness it also has its own negative usage and one among them is the fake reviews. Fake reviews are weakening the actual worth of the product. To be more specific, the reviews can be divided into two categories: legitimate fake reviews and reviews written intentionally to decapitate the product or brand value. On the other hand, the machine learning algorithms are extensively used. The incorporation of machine learning techniques into the classification of the reviews is considered as an excellent combination. In this work, various datasets from different industries such as airline industry, movie industry and food industry are considered and fake reviews are classified using various algorithms including K-Nearest Neighbors, Naive Bayes, Random Forest, Decision tree, Support Vector Machine, Logistic Regression from Machine learning. There are reviews which can be decoded using the sentiment analysis from Natural Language Programming. Sentiment analysis is used to find the emotion in a text. The accuracy parameter result is analyzed for all the implemented models. The results demonstrate support vector machine technique giving high accuracy compared to other machine learning classification techniques.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129187337","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009562
K. M. Kumar, M. Rashmi
Electric vehicles are the best way to avoid the pollution in the environment. Various types of motors are available for this application and the selection of motor is customized based on the speed-torque requirement of the vehicle. Permanent Magnet Synchronous Motors (PMSM) are more suitable for electric vehicles due to fast dynamic response, higher efficiency and ease of control at both low speed and high speeds. These motors are prone to mechanical and electrical faults. Open circuit fault and inter-turn short circuits are the electrical faults. 30 to 40% of the electrical faults are due to short circuiting of windings. Inter-turn short circuit fault is dangerous and prolonged faults leads lead to line to ground fault. To ensure the reliability and safety of the electric vehicles, these faults have to be taken care. Early estimation of winding faults is very essential. This paper focuses on modeling and analysis of PMSM motor during normal operation and inter-turn short circuit fault. A novel and simple model during inter-turn short circuit fault is proposed. The simulation results for various fault percentages in A-phase windings are presented in this paper.
{"title":"Modeling and Analysis of Interturn Short Circuit Fault in PMSM Motor for Electric Vehicle Applications","authors":"K. M. Kumar, M. Rashmi","doi":"10.1109/ICECA55336.2022.10009562","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009562","url":null,"abstract":"Electric vehicles are the best way to avoid the pollution in the environment. Various types of motors are available for this application and the selection of motor is customized based on the speed-torque requirement of the vehicle. Permanent Magnet Synchronous Motors (PMSM) are more suitable for electric vehicles due to fast dynamic response, higher efficiency and ease of control at both low speed and high speeds. These motors are prone to mechanical and electrical faults. Open circuit fault and inter-turn short circuits are the electrical faults. 30 to 40% of the electrical faults are due to short circuiting of windings. Inter-turn short circuit fault is dangerous and prolonged faults leads lead to line to ground fault. To ensure the reliability and safety of the electric vehicles, these faults have to be taken care. Early estimation of winding faults is very essential. This paper focuses on modeling and analysis of PMSM motor during normal operation and inter-turn short circuit fault. A novel and simple model during inter-turn short circuit fault is proposed. The simulation results for various fault percentages in A-phase windings are presented in this paper.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130825870","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009057
Sneha M S, B. Yamuna, Karthi Balasubramanian
Polar codes are highly channel efficient with minimum hardware complexity with increasing code length, making them one of the most favorable error-correcting codes. There exist many architectures for both encoding and decoding of polar codes. In this paper a modified partially parallel polar encoder architecture is proposed. The registers that are used for inducing the parallelism in the architecture are replaced with pulsed latches, making the whole architecture low power and area efficient. The synthesis and simulation of the proposed architecture is carried out in Xilinx ISE for (16,k), (32,k) and (64,k) polar codes. Results show that the proposed architecture leads to an average reduction of 50% and 45% in power and gate count respectively.
{"title":"A Modified Partially Parallel Polar Encoder Architecture","authors":"Sneha M S, B. Yamuna, Karthi Balasubramanian","doi":"10.1109/ICECA55336.2022.10009057","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009057","url":null,"abstract":"Polar codes are highly channel efficient with minimum hardware complexity with increasing code length, making them one of the most favorable error-correcting codes. There exist many architectures for both encoding and decoding of polar codes. In this paper a modified partially parallel polar encoder architecture is proposed. The registers that are used for inducing the parallelism in the architecture are replaced with pulsed latches, making the whole architecture low power and area efficient. The synthesis and simulation of the proposed architecture is carried out in Xilinx ISE for (16,k), (32,k) and (64,k) polar codes. Results show that the proposed architecture leads to an average reduction of 50% and 45% in power and gate count respectively.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132675340","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009602
A. Elakkiya, K. Surya, Konduru Venkatesh, S. Aakash
Deep learning is revolutionary when used to transcribe spoken language into text that computers can read with the same intent as human readers. The fundamental idea is to give intelligent systems with human language as data that may be utilized in various domains. A speech-to-text synthesizer is a piece of software that can convert an audio file into text using Digital Signal Processing (DSP) algorithms that analyze and process the speech signal in the audio file. The objective of Speech To Text (STT) is to convert audio input from a user or computer into readable text. The STT is proposed to be transformed using the Hidden Markov Model (HMM) method. The development of a speech-to-text synthesizer will be a tremendous advantage for the visually handicapped and will make reading lengthy texts much easier.
{"title":"Implementation of Speech to Text Conversion Using Hidden Markov Model","authors":"A. Elakkiya, K. Surya, Konduru Venkatesh, S. Aakash","doi":"10.1109/ICECA55336.2022.10009602","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009602","url":null,"abstract":"Deep learning is revolutionary when used to transcribe spoken language into text that computers can read with the same intent as human readers. The fundamental idea is to give intelligent systems with human language as data that may be utilized in various domains. A speech-to-text synthesizer is a piece of software that can convert an audio file into text using Digital Signal Processing (DSP) algorithms that analyze and process the speech signal in the audio file. The objective of Speech To Text (STT) is to convert audio input from a user or computer into readable text. The STT is proposed to be transformed using the Hidden Markov Model (HMM) method. The development of a speech-to-text synthesizer will be a tremendous advantage for the visually handicapped and will make reading lengthy texts much easier.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128152899","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009285
S. S., T. Sheela, T. Muthumanickam
Now-a-davs Internet of Things (IoT) is used in various real-time applications, Including smart health monitoring. The existing health monitoring system can only collect the basic information about heat. heartbeat. and BP (Blood Pressure). This research study proposes an effective examination of patient's brain signals and detect the health status of the patient in real time. The main objective of the proposed study is to provide a proper optimized value about the mentally challenged patients by collecting the data information from brain signals with 24 channels and study the body parameters through each EEG (Electroencephalography) signal channel. Here, the collected data is pre-processed by using Machine Learninz (ML) tools and Neural Networks (NN) with Python programming language, By collecting the data information from brain signals with EEG sensors, an optimized value and solution can be provided to the patients suffering from Cerebral Palsy (CP). The collected data is then stored in a cloud storage platform and it can be accessed from any remote location. The stored data is then collected and filtered by using PCA techniques and further the Artifact siznals (Noise) are removed to diagnose seizures by Identifying brain signal parameters (Alpha, Beta, Delta and Theta). Further, a novel model has been designed by using python programming languaze for training the machine with a maximum number of datasets in order to check accuracy and predict the seizure levels of any CP patient. Neural Network (NN) algorithms were applied here by using python programming language in order to check the percentage error in the data processing mechanism. Once the data is analyzed with the proposed model it suggests the CP patient for Tentative Treatment.
{"title":"IoT Enabled Health Monitoring System using Machine Learning Algorithm","authors":"S. S., T. Sheela, T. Muthumanickam","doi":"10.1109/ICECA55336.2022.10009285","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009285","url":null,"abstract":"Now-a-davs Internet of Things (IoT) is used in various real-time applications, Including smart health monitoring. The existing health monitoring system can only collect the basic information about heat. heartbeat. and BP (Blood Pressure). This research study proposes an effective examination of patient's brain signals and detect the health status of the patient in real time. The main objective of the proposed study is to provide a proper optimized value about the mentally challenged patients by collecting the data information from brain signals with 24 channels and study the body parameters through each EEG (Electroencephalography) signal channel. Here, the collected data is pre-processed by using Machine Learninz (ML) tools and Neural Networks (NN) with Python programming language, By collecting the data information from brain signals with EEG sensors, an optimized value and solution can be provided to the patients suffering from Cerebral Palsy (CP). The collected data is then stored in a cloud storage platform and it can be accessed from any remote location. The stored data is then collected and filtered by using PCA techniques and further the Artifact siznals (Noise) are removed to diagnose seizures by Identifying brain signal parameters (Alpha, Beta, Delta and Theta). Further, a novel model has been designed by using python programming languaze for training the machine with a maximum number of datasets in order to check accuracy and predict the seizure levels of any CP patient. Neural Network (NN) algorithms were applied here by using python programming language in order to check the percentage error in the data processing mechanism. Once the data is analyzed with the proposed model it suggests the CP patient for Tentative Treatment.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131680226","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009093
Rama Krishna Peddarapu, Sofia Ameena, S. Yashaswini, Nadipelli Shreshta, Muppidi PurnaSahithi
The varying customer requirements and interests often result in subscription cancellation. Hence, running a subscription business necessitates an accurate churn forecasting model as even a minor change will result in a significant impact. If the seller is not informed that the customer is about to cancel the subscription, no action will be taken to retain them. As a result, this research study attempts to design and develop a churn prediction model to predict a subscription cancellation and provide incentives for that particular subscriber to stay back. This results in significant cost savings and generate an additional revenue source for any online business. The primary goal of this research work is to analyze different models for predicting the active churners with high accuracy. In existing systems, the service providers track down the clients before they leave in order to solve this problem. This study has compared the well-known machine learning techniques to solve the problem and also predict the results in a more accurate way.
{"title":"Customer Churn Prediction using Machine Learning","authors":"Rama Krishna Peddarapu, Sofia Ameena, S. Yashaswini, Nadipelli Shreshta, Muppidi PurnaSahithi","doi":"10.1109/ICECA55336.2022.10009093","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009093","url":null,"abstract":"The varying customer requirements and interests often result in subscription cancellation. Hence, running a subscription business necessitates an accurate churn forecasting model as even a minor change will result in a significant impact. If the seller is not informed that the customer is about to cancel the subscription, no action will be taken to retain them. As a result, this research study attempts to design and develop a churn prediction model to predict a subscription cancellation and provide incentives for that particular subscriber to stay back. This results in significant cost savings and generate an additional revenue source for any online business. The primary goal of this research work is to analyze different models for predicting the active churners with high accuracy. In existing systems, the service providers track down the clients before they leave in order to solve this problem. This study has compared the well-known machine learning techniques to solve the problem and also predict the results in a more accurate way.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132258786","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009434
Sindhuja R, S. K, P. E., P. S
In recent years, classical inverters such as the H-bridged cascaded multilevel inverter, flying capacitor, and flying capacitor multilevel inverter have contributed in electric vehicle and non-conventional energy applications. Due to higher switching and conduction losses, as well as a greater number of power switches and driver circuits, conventional multilevel inverters do not achieve the highest performance. To obtain higher performance while reducing power losses and total harmonic distortion, individual switches are controlled by logic gates. In this proposed work, one of the inverters is considered symmetrical voltage another is asymmetrical voltage for implementing these effective topologies. The proposed single-phase seven-level voltage output and current for both symmetric and asymmetric multilevel inverters are employed to test the intended computation. The MATLAB/Simulink tool is used to implement and investigate the various parameters of proposed topologies.
{"title":"A Reconfigurable Multilevel Inverters with Minimal Switches for Battery Charging and Renewable Energy Applications","authors":"Sindhuja R, S. K, P. E., P. S","doi":"10.1109/ICECA55336.2022.10009434","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009434","url":null,"abstract":"In recent years, classical inverters such as the H-bridged cascaded multilevel inverter, flying capacitor, and flying capacitor multilevel inverter have contributed in electric vehicle and non-conventional energy applications. Due to higher switching and conduction losses, as well as a greater number of power switches and driver circuits, conventional multilevel inverters do not achieve the highest performance. To obtain higher performance while reducing power losses and total harmonic distortion, individual switches are controlled by logic gates. In this proposed work, one of the inverters is considered symmetrical voltage another is asymmetrical voltage for implementing these effective topologies. The proposed single-phase seven-level voltage output and current for both symmetric and asymmetric multilevel inverters are employed to test the intended computation. The MATLAB/Simulink tool is used to implement and investigate the various parameters of proposed topologies.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134305801","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：