Pub Date : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101527
Nur Mohammad Fahad, S. Sakib, Mohaimenul Azam Khan Raiaan, Md. Saddam Hossain Mukta
Skin cancer is a fatal disease that has become the leading cause of death worldwide in recent years, although it is curable if diagnosed early. Early skin cancer detection significantly improves patients' chances of survival and reduces mortality. In this research, we conduct experiments on a high imbalance dermoscopic ISIC 2020 dataset. The primary objective of this study is to develop a shallow CNN architecture to complete the classification task effectively, requiring fewer computational resources without compromising accuracy. We have used pre-processing techniques to remove image noise and truncation and augmentation techniques to balance the dataset before fitting it into the model. Multiple performance measurement metrics were utilized to establish the overall performance. Our proposed model yields a remarkable test accuracy of 98.81%. We compare our models' performance with different transfer learning (TL) models to assess the faster convergence rate. The proposed model demonstrated its robustness by outperforming the other TL models in terms of accuracy within a short processing time. It is reasonable to assume that our proposed system will reliably aid dermatologists in diagnosing skin cancer patients early and increasing survival rates.
{"title":"SkinNet-8: An Efficient CNN Architecture for Classifying Skin Cancer on an Imbalanced Dataset","authors":"Nur Mohammad Fahad, S. Sakib, Mohaimenul Azam Khan Raiaan, Md. Saddam Hossain Mukta","doi":"10.1109/ECCE57851.2023.10101527","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101527","url":null,"abstract":"Skin cancer is a fatal disease that has become the leading cause of death worldwide in recent years, although it is curable if diagnosed early. Early skin cancer detection significantly improves patients' chances of survival and reduces mortality. In this research, we conduct experiments on a high imbalance dermoscopic ISIC 2020 dataset. The primary objective of this study is to develop a shallow CNN architecture to complete the classification task effectively, requiring fewer computational resources without compromising accuracy. We have used pre-processing techniques to remove image noise and truncation and augmentation techniques to balance the dataset before fitting it into the model. Multiple performance measurement metrics were utilized to establish the overall performance. Our proposed model yields a remarkable test accuracy of 98.81%. We compare our models' performance with different transfer learning (TL) models to assess the faster convergence rate. The proposed model demonstrated its robustness by outperforming the other TL models in terms of accuracy within a short processing time. It is reasonable to assume that our proposed system will reliably aid dermatologists in diagnosing skin cancer patients early and increasing survival rates.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127158747","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101528
F. Chowdhury, Tania Noor, Md. Saiful Islam, Md Khorshed Alam
A brain tumor is an uncommon form of body cell proliferation. The most difficult tasks in the medical profession are to identify and categorize brain tumors. A person's life may be at risk if the brain tumor is not immediately identified or diagnosed. In this proposed method, an artificial neural network (ANN)-based technique can classify brain tumors accurately. Firstly, the images are normalized using the scaling process. Then the normalized images are segmented using the watershed algorithm. After that, the seven statistical features are extracted and then applied as input to the ANN classifier for the classification of the brain tumors. The experimental result of the proposed method provides an accuracy result of 95.8% which is better than modern state-of-the-art methods. Furthermore, compared to other contemporary techniques, the chosen seven statistical features are comparably few in illustrating this performance.
{"title":"Brain Tumor Classification Using Watershed Segmentation with ANN Classifier","authors":"F. Chowdhury, Tania Noor, Md. Saiful Islam, Md Khorshed Alam","doi":"10.1109/ECCE57851.2023.10101528","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101528","url":null,"abstract":"A brain tumor is an uncommon form of body cell proliferation. The most difficult tasks in the medical profession are to identify and categorize brain tumors. A person's life may be at risk if the brain tumor is not immediately identified or diagnosed. In this proposed method, an artificial neural network (ANN)-based technique can classify brain tumors accurately. Firstly, the images are normalized using the scaling process. Then the normalized images are segmented using the watershed algorithm. After that, the seven statistical features are extracted and then applied as input to the ANN classifier for the classification of the brain tumors. The experimental result of the proposed method provides an accuracy result of 95.8% which is better than modern state-of-the-art methods. Furthermore, compared to other contemporary techniques, the chosen seven statistical features are comparably few in illustrating this performance.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129381422","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101584
Md. Hasanul Bari, Tanver Ahmed, M. I. Afjal, A. M. Nitu, Md. Palash Uddin, Md Abu Marjan
The remote sensing hyperspectral image (HSI) consists of hundreds of narrow and adjoining spectral bands. It carries a lot of significant information about the earth's objects. However, the use of all HSI bands leads to higher misclassification. Band reduction is a potential solution to resolve this issue, where feature selection and feature extraction methods are commonly accomplished for the reduction of bands. One of the most commonly used unsupervised feature extraction techniques is the Principal Component Analysis (PCA). But it fails to bring out the local intrinsic information from the HSI as it ponders only the global variation of the data. This problem can be addressed by the Segmented PCA (SPCA) which exploits both the global and local variance of the data by partitioning it into highly correlated blocks. Beside, another unsupervised feature extraction technique named Nonnegative Matrix Factorization (NMF) is also applied for HSI by approximating the data in a low-dimensional subspace. In this paper, we propose a feature extraction method, named Segmented Nonnegative Matrix Factorization (SNMF), performing NMF on the segmented strongly correlated blocks of HSI data. The efficacy of the proposed method is compared with PCA, NMF, and SPCA on the Indian Pines dataset with a support vector machine classifier. The experimental result shows that SNMF (89.00%) outperforms PCA (84.33%), NMF (85.37%), and SPCA (87.59%) over all classes' samples.
{"title":"Segmented Nonnegative Matrix Factorization for Hyperspectral Image Classification","authors":"Md. Hasanul Bari, Tanver Ahmed, M. I. Afjal, A. M. Nitu, Md. Palash Uddin, Md Abu Marjan","doi":"10.1109/ECCE57851.2023.10101584","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101584","url":null,"abstract":"The remote sensing hyperspectral image (HSI) consists of hundreds of narrow and adjoining spectral bands. It carries a lot of significant information about the earth's objects. However, the use of all HSI bands leads to higher misclassification. Band reduction is a potential solution to resolve this issue, where feature selection and feature extraction methods are commonly accomplished for the reduction of bands. One of the most commonly used unsupervised feature extraction techniques is the Principal Component Analysis (PCA). But it fails to bring out the local intrinsic information from the HSI as it ponders only the global variation of the data. This problem can be addressed by the Segmented PCA (SPCA) which exploits both the global and local variance of the data by partitioning it into highly correlated blocks. Beside, another unsupervised feature extraction technique named Nonnegative Matrix Factorization (NMF) is also applied for HSI by approximating the data in a low-dimensional subspace. In this paper, we propose a feature extraction method, named Segmented Nonnegative Matrix Factorization (SNMF), performing NMF on the segmented strongly correlated blocks of HSI data. The efficacy of the proposed method is compared with PCA, NMF, and SPCA on the Indian Pines dataset with a support vector machine classifier. The experimental result shows that SNMF (89.00%) outperforms PCA (84.33%), NMF (85.37%), and SPCA (87.59%) over all classes' samples.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129425128","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101529
Md. Asiful Islam Sakib, Md. Tamzid Ahmed, Jitu Prakash Dhar
In this work, numerical modelling and simulation of CZTS solar cell has been performed using SCAPS-1D. The alternative of toxic CdS buffer layer with $text{Zn}_{mathrm{x}}text{Cd}_{1-mathrm{x}}mathrm{S}(mathrm{x}=0.1,0.2,0.3,0.6,0.8)$ buffer layer in CZTS solar cell. Here, the effect of zinc concentration in overall performance (open circuit voltage, short circuit current, fill factor, efficiency) of CZTS solar cell is experimented. In this work, the main attempt is to take the advantages of multiferroic properties of ferroelectric material BiMnO3 (BMO) in the back surface field (BSF) layer. The maximum performance is evaluated by varying the thickness and doping concentration of buffer layer, absorber layer and back surface field layer for the structure of $text{SnO}_{2}/text{Zn}_{2}text{SnO}_{4}/text{Zn}_{mathrm{x}}text{Cd}_{1-} {}_{mathrm{x}}mathrm{S}/text{CZTS}/text{BiMnO}_{3}/text{Cu}$ with and without BSF layer. With ferroelectric material in BSF layer, the J-V curves are investigated for cell structure and the optimal photovoltaic parameters have been achieved with efficiency of 24.18%, fill $text{factor}=87.15%, mathrm{J}_{text{sc}}=27.19$ mA/cm2 and $mathrm{V}_{text{oc}}=1.02mathrm{V}$. As compared to the high performance CZTS solar cell model presented in the reference model which had efficiency of 23.72% with CdS in buffer layer and Pt in BSF layer, the proposed solar cell model in this work with zinc doped CdS in buffer layer and ferroelectric BMO in BSF layer enhanced the solar cell efficiency upto 24.18%. Here, the optical properties layer by layer photon density is also observed for CZTS solar cell with zinc doped CdS in buffer layer and BMO in back surface field (BSF) layer.
{"title":"Ferroelectric BiMnO3 in BSF layer and Zinc doped CdS in buffer layer: Boosting up the performance of CZTS solar cell","authors":"Md. Asiful Islam Sakib, Md. Tamzid Ahmed, Jitu Prakash Dhar","doi":"10.1109/ECCE57851.2023.10101529","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101529","url":null,"abstract":"In this work, numerical modelling and simulation of CZTS solar cell has been performed using SCAPS-1D. The alternative of toxic CdS buffer layer with $text{Zn}_{mathrm{x}}text{Cd}_{1-mathrm{x}}mathrm{S}(mathrm{x}=0.1,0.2,0.3,0.6,0.8)$ buffer layer in CZTS solar cell. Here, the effect of zinc concentration in overall performance (open circuit voltage, short circuit current, fill factor, efficiency) of CZTS solar cell is experimented. In this work, the main attempt is to take the advantages of multiferroic properties of ferroelectric material BiMnO3 (BMO) in the back surface field (BSF) layer. The maximum performance is evaluated by varying the thickness and doping concentration of buffer layer, absorber layer and back surface field layer for the structure of $text{SnO}_{2}/text{Zn}_{2}text{SnO}_{4}/text{Zn}_{mathrm{x}}text{Cd}_{1-} {}_{mathrm{x}}mathrm{S}/text{CZTS}/text{BiMnO}_{3}/text{Cu}$ with and without BSF layer. With ferroelectric material in BSF layer, the J-V curves are investigated for cell structure and the optimal photovoltaic parameters have been achieved with efficiency of 24.18%, fill $text{factor}=87.15%, mathrm{J}_{text{sc}}=27.19$ mA/cm2 and $mathrm{V}_{text{oc}}=1.02mathrm{V}$. As compared to the high performance CZTS solar cell model presented in the reference model which had efficiency of 23.72% with CdS in buffer layer and Pt in BSF layer, the proposed solar cell model in this work with zinc doped CdS in buffer layer and ferroelectric BMO in BSF layer enhanced the solar cell efficiency upto 24.18%. Here, the optical properties layer by layer photon density is also observed for CZTS solar cell with zinc doped CdS in buffer layer and BMO in back surface field (BSF) layer.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125064939","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101634
S. Haq, M. K. Hosain, S. P. Biswas
In this research work, a new modulation technique is proposed to control the switching of a 3-phase modular multilevel converter (MMC) based solar photovoltaic (PV) fed induction motor (IM) drive system. Multilevel inverters (MLIs) are gaining popularity in the industry as medium-voltage and high-power electronic power conversion solutions. Different multilevel inverter topologies have grown in prominence in recent years, owing to a variety of advantages, particularly in induction motor driving systems. Inverter switching strategies are critical for improving power quality. In this paper, a new switching method for a 5-level MMC is proposed that ensures high power quality, improves speed and torque performance, and reduces total harmonic distortion (THD) in the voltage and current waveforms of the stator of a PV-based IM. The practicality of this modulation method is demonstrated by comparing its performance to that of several existing popular switching strategies. The design, implementation, and comparisons are done by using MATLAB/Simulink simulation. A laboratory-scale prototype is developed and tested to evaluate the performance of the proposed switching technique.
{"title":"An Efficient Modulation Strategy for Modular Multilevel Cascaded Inverter Used in Solar PV Fed Induction Motor Drive Systems","authors":"S. Haq, M. K. Hosain, S. P. Biswas","doi":"10.1109/ECCE57851.2023.10101634","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101634","url":null,"abstract":"In this research work, a new modulation technique is proposed to control the switching of a 3-phase modular multilevel converter (MMC) based solar photovoltaic (PV) fed induction motor (IM) drive system. Multilevel inverters (MLIs) are gaining popularity in the industry as medium-voltage and high-power electronic power conversion solutions. Different multilevel inverter topologies have grown in prominence in recent years, owing to a variety of advantages, particularly in induction motor driving systems. Inverter switching strategies are critical for improving power quality. In this paper, a new switching method for a 5-level MMC is proposed that ensures high power quality, improves speed and torque performance, and reduces total harmonic distortion (THD) in the voltage and current waveforms of the stator of a PV-based IM. The practicality of this modulation method is demonstrated by comparing its performance to that of several existing popular switching strategies. The design, implementation, and comparisons are done by using MATLAB/Simulink simulation. A laboratory-scale prototype is developed and tested to evaluate the performance of the proposed switching technique.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123253484","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 : 2023-02-23DOI: 10.1109/ECCE57851.2023.10101560
Md Sakibul Islam, Afifa Hossain, A. Khatun, A. Kor
Rainfall is a major factor in our ecological and environmental balance for a variety of reasons, including economy, agriculture, and cleanliness. It supplies the planet with essential fresh water, especially in areas where groundwater resources are scarce. Hence, a dependable prediction model for rainfall is essential, as it can help predict flooding and monitor pollutant levels. Historically, weather predictions were made using meteorological satellites. But now, with advancements in technology and data analysis, machine learning has been utilized in weather forecasting. However, accurately predicting rainfall remains a complex task and existing methods depend on complex models that may incur high costs due to their extensive computational requirements. This research assesses the effectiveness of both conventional machine learning algorithms and deep learning techniques as potential options, by conducting a comprehensive comparison using a uniform case study that analyzed ten years of rainfall data collected from various regions in Australia. Through the comparisons and evaluations, we aim at finding the most feasible method for the detection of weather patterns. The models' performance is measured using metrics such as loss, Mean Absolute Error, Mean Squared Error and Mean Squared Logarithmic Error. The results show that the proposed CNN model is the most accurate among all the models.
{"title":"Evaluation of the Performance of Machine Learning and Deep Learning Techniques for Predicting Rainfall: An Illustrative Case Study from Australia","authors":"Md Sakibul Islam, Afifa Hossain, A. Khatun, A. Kor","doi":"10.1109/ECCE57851.2023.10101560","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101560","url":null,"abstract":"Rainfall is a major factor in our ecological and environmental balance for a variety of reasons, including economy, agriculture, and cleanliness. It supplies the planet with essential fresh water, especially in areas where groundwater resources are scarce. Hence, a dependable prediction model for rainfall is essential, as it can help predict flooding and monitor pollutant levels. Historically, weather predictions were made using meteorological satellites. But now, with advancements in technology and data analysis, machine learning has been utilized in weather forecasting. However, accurately predicting rainfall remains a complex task and existing methods depend on complex models that may incur high costs due to their extensive computational requirements. This research assesses the effectiveness of both conventional machine learning algorithms and deep learning techniques as potential options, by conducting a comprehensive comparison using a uniform case study that analyzed ten years of rainfall data collected from various regions in Australia. Through the comparisons and evaluations, we aim at finding the most feasible method for the detection of weather patterns. The models' performance is measured using metrics such as loss, Mean Absolute Error, Mean Squared Error and Mean Squared Logarithmic Error. The results show that the proposed CNN model is the most accurate among all the models.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124405227","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 : 2023-02-23DOI: 10.1109/ecce57851.2023.10101602
{"title":"Organizing Advisory Committee","authors":"","doi":"10.1109/ecce57851.2023.10101602","DOIUrl":"https://doi.org/10.1109/ecce57851.2023.10101602","url":null,"abstract":"","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123030369","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}
As e-commerce has grown in recent years, so online shopping has increased with the number of product reviews posted online. The consumer's recommendations or complaints influence significantly customers and their decision to purchase. Sentiment polarity analysis is the interpretation and classification of text-based data. The main goal of our work is to categorize each customer's review into a class that represents its quality (positive or negative). Our sentiment polarity detection consists of the following steps: preprocessing, feature extraction, training, classification and generalization. First, the reviews were transformed into vector representation using different techniques of Tf-Idf and Tokenizer. Then, we trained with a machine learning model of SVM Linear, RBF, Sigmoid kernel and a deep learning model LSTM. After that, we evaluated the models using accuracy, f1-score, precision, recall. Our LSTM model predicts an accuracy of 86% for Amazon-based customer reviews and an accuracy of 85% for Yelp customer reviews.
{"title":"Sentiment Polarity Detection Using Machine Learning and Deep Learning","authors":"Ahasanur Rahman Mehul, Syed Montasir Mahmood, Tajri Tabassum, Puja Chakraborty","doi":"10.1109/ECCE57851.2023.10101494","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101494","url":null,"abstract":"As e-commerce has grown in recent years, so online shopping has increased with the number of product reviews posted online. The consumer's recommendations or complaints influence significantly customers and their decision to purchase. Sentiment polarity analysis is the interpretation and classification of text-based data. The main goal of our work is to categorize each customer's review into a class that represents its quality (positive or negative). Our sentiment polarity detection consists of the following steps: preprocessing, feature extraction, training, classification and generalization. First, the reviews were transformed into vector representation using different techniques of Tf-Idf and Tokenizer. Then, we trained with a machine learning model of SVM Linear, RBF, Sigmoid kernel and a deep learning model LSTM. After that, we evaluated the models using accuracy, f1-score, precision, recall. Our LSTM model predicts an accuracy of 86% for Amazon-based customer reviews and an accuracy of 85% for Yelp customer reviews.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114422810","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}
Digital modulation schemes determine how bits are mapped to the phase and amplitude of transmitted signals. This research comprehensively analyzes the necessity of studying various modulation schemes and a comparative investigation using appropriate simulations. The goal is to obtain the most effective modulation scheme for 5G technology. In the development phase of 5G technology, different candidates of modulation schemes like OFDM, F-OFDM, UFMC, FBMC, and others are being studied. For 5G communication, the modulation scheme that performs effectively across all dimensions will be evaluated. This research aims to compare several 4G and 5G modulation methods to determine the best modulation strategy for 5G technology. The comparative research for modulation schemes was carried out using modern technologies. Here, we transmit 5G data to evaluate the performance of several 4G and 5G modulation schemes to determine which Modulation Scheme is best for implementing 5G technology. Our research covered three modulation schemes: OFDM, F-OFDM, and UFMC. We employed PSD, PAPR, BER, and Constellation Diagrams to compare OFDM, which is currently used in 4G technology, with F-OFDM and UFMC, respectively. Following the comparative investigation, we discovered that F-OFDM significantly outperforms UFMC and OFDM, both modulation techniques. We also determined that F-OFDM promises enhanced efficiency in 5G technology by accurately proving all simulations for a potential application.
{"title":"Study of Different Candidates of Modulation Schemes for 5G Communication Systems","authors":"Tamanna Sultana, Rahela Akhter Akhi, Jubayed Hossain Turag, Suhail Najeeb","doi":"10.1109/ECCE57851.2023.10101611","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101611","url":null,"abstract":"Digital modulation schemes determine how bits are mapped to the phase and amplitude of transmitted signals. This research comprehensively analyzes the necessity of studying various modulation schemes and a comparative investigation using appropriate simulations. The goal is to obtain the most effective modulation scheme for 5G technology. In the development phase of 5G technology, different candidates of modulation schemes like OFDM, F-OFDM, UFMC, FBMC, and others are being studied. For 5G communication, the modulation scheme that performs effectively across all dimensions will be evaluated. This research aims to compare several 4G and 5G modulation methods to determine the best modulation strategy for 5G technology. The comparative research for modulation schemes was carried out using modern technologies. Here, we transmit 5G data to evaluate the performance of several 4G and 5G modulation schemes to determine which Modulation Scheme is best for implementing 5G technology. Our research covered three modulation schemes: OFDM, F-OFDM, and UFMC. We employed PSD, PAPR, BER, and Constellation Diagrams to compare OFDM, which is currently used in 4G technology, with F-OFDM and UFMC, respectively. Following the comparative investigation, we discovered that F-OFDM significantly outperforms UFMC and OFDM, both modulation techniques. We also determined that F-OFDM promises enhanced efficiency in 5G technology by accurately proving all simulations for a potential application.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115680785","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}
The mother's mode of delivery greatly impacts the relationship between the newborn baby and the mother, as well as the mother's and baby's health. Currently, the cesarean rate is increasing at an alarming rate. The inability to predict the mother's health status and mode of delivery are mainly responsible for this situation. Support Vector Machine (SVM), Decision Tree, Random Forest (RF), Gradient Boosting Classifier(GBC), Logistic Regression, Gaussian Naive Bayes, Stochastic Gradient Descent, CatBoost (CB), Adaptive Boosting (AB), Gaussian Naïve Bayes, Extreme Gradient Boosting(XGB) are used to predict the mother's mode of delivery. This study also proposed an ensemble machine learning algorithm that stacked the SVC, XGB, and RF together and named the ensemble SVXGBRF. To preprocess the dataset, we use a pipeline that basic preprocessing techniques, data balancing and feature selection. Our proposed SVXGBRF classifiers show 95.52% accuracy, 96% precision, recall, f1 score, and 99% AUC score. SVXGBRF shows its superiority, where most models show an accuracy of less than 90% except RF, GBC, CB, and AB. Eventually, this research could be utilized to develop a decision-support system for reducing the number of cesarean sections by trying to extract insights from complex data patterns.
{"title":"Ensemble Based Machine Learning Model for Early Detection of Mother's Delivery Mode","authors":"M. Hasan, Md Jakaria Zobair, Sumya Akter, Mahir Ashef, Nazrin Akter, Nahid Binte Sadia","doi":"10.1109/ECCE57851.2023.10101558","DOIUrl":"https://doi.org/10.1109/ECCE57851.2023.10101558","url":null,"abstract":"The mother's mode of delivery greatly impacts the relationship between the newborn baby and the mother, as well as the mother's and baby's health. Currently, the cesarean rate is increasing at an alarming rate. The inability to predict the mother's health status and mode of delivery are mainly responsible for this situation. Support Vector Machine (SVM), Decision Tree, Random Forest (RF), Gradient Boosting Classifier(GBC), Logistic Regression, Gaussian Naive Bayes, Stochastic Gradient Descent, CatBoost (CB), Adaptive Boosting (AB), Gaussian Naïve Bayes, Extreme Gradient Boosting(XGB) are used to predict the mother's mode of delivery. This study also proposed an ensemble machine learning algorithm that stacked the SVC, XGB, and RF together and named the ensemble SVXGBRF. To preprocess the dataset, we use a pipeline that basic preprocessing techniques, data balancing and feature selection. Our proposed SVXGBRF classifiers show 95.52% accuracy, 96% precision, recall, f1 score, and 99% AUC score. SVXGBRF shows its superiority, where most models show an accuracy of less than 90% except RF, GBC, CB, and AB. Eventually, this research could be utilized to develop a decision-support system for reducing the number of cesarean sections by trying to extract insights from complex data patterns.","PeriodicalId":131537,"journal":{"name":"2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117066897","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：