Pub Date : 2024-01-01DOI: 10.21608/mjeer.2023.232914.1079
Fatma elzahraa shehata, Mostafa Makkey, Shimaa A. Abdelrahman
— Alzheimer's disease (AD) is one illness that significantly impacts people’s lives. As AD worsens over time, it causes the death of brain cells. To assist a neurologist, a proposed classification method for AD progression is introduced in this paper. Pre-processing is applied to clean up artifacts from brain images. As biomarkers for AD diagnosis, three specific areas of the brain are utilized. Multiplicative intrinsic component optimization with an exemplar pyramid is employed for the three main biomarkers segmentation at a multi-scale. For feature extraction, the gray-level co-occurrence matrix is utilized. Finally, principal component analysis is incorporated for feature reduction, and based on the Euclidean distance the decision of the binary classifier is performed. The Alzheimer's Disease Neuroimaging Initiative baseline dataset is used with 311 subjects, 262 for training and 49 for testing. The proposed method achieved an accuracy of 96.296% for the classification between late mild cognitive impairment (LMCI) and cognitive normal (CN), 85.71% between early mild cognitive impairment (EMCI) and CN, 92% between AD and CN, 95.833% between EMCI and LMCI, 91.3% between AD and EMCI, and 84.21% between AD and LMCI. Evaluation results show that the proposed method enhanced the existing method's accuracy with less feature dimensionality.
- 阿尔茨海默病（AD）是一种严重影响人们生活的疾病。随着时间的推移，阿尔茨海默病逐渐恶化，导致脑细胞死亡。为了帮助神经科医生，本文介绍了一种针对阿兹海默症进展的分类方法。预处理用于清除大脑图像中的伪影。本文利用大脑的三个特定区域作为诊断渐冻症的生物标志物。在多尺度下对三个主要生物标志物进行分割时，采用了带有范例金字塔的乘法本征分量优化技术。在特征提取方面，采用了灰度共现矩阵。最后，采用主成分分析法进行特征还原，并根据欧氏距离对二元分类器进行判定。阿尔茨海默病神经影像计划基线数据集有 311 个受试者，其中 262 个用于训练，49 个用于测试。所提出的方法在晚期轻度认知障碍（LMCI）和认知正常（CN）之间的分类准确率达到 96.296%，在早期轻度认知障碍（EMCI）和认知正常之间的分类准确率达到 85.71%，在 AD 和 CN 之间的分类准确率达到 92%，在 EMCI 和 LMCI 之间的分类准确率达到 95.833%，在 AD 和 EMCI 之间的分类准确率达到 91.3%，在 AD 和 LMCI 之间的分类准确率达到 84.21%。评估结果表明，所提出的方法提高了现有方法的准确性，而且特征维数更少。
{"title":"Classification of Brain Neuroimaging for Alzheimer's Disease Employing Principal Component Analysis","authors":"Fatma elzahraa shehata, Mostafa Makkey, Shimaa A. Abdelrahman","doi":"10.21608/mjeer.2023.232914.1079","DOIUrl":"https://doi.org/10.21608/mjeer.2023.232914.1079","url":null,"abstract":"— Alzheimer's disease (AD) is one illness that significantly impacts people’s lives. As AD worsens over time, it causes the death of brain cells. To assist a neurologist, a proposed classification method for AD progression is introduced in this paper. Pre-processing is applied to clean up artifacts from brain images. As biomarkers for AD diagnosis, three specific areas of the brain are utilized. Multiplicative intrinsic component optimization with an exemplar pyramid is employed for the three main biomarkers segmentation at a multi-scale. For feature extraction, the gray-level co-occurrence matrix is utilized. Finally, principal component analysis is incorporated for feature reduction, and based on the Euclidean distance the decision of the binary classifier is performed. The Alzheimer's Disease Neuroimaging Initiative baseline dataset is used with 311 subjects, 262 for training and 49 for testing. The proposed method achieved an accuracy of 96.296% for the classification between late mild cognitive impairment (LMCI) and cognitive normal (CN), 85.71% between early mild cognitive impairment (EMCI) and CN, 92% between AD and CN, 95.833% between EMCI and LMCI, 91.3% between AD and EMCI, and 84.21% between AD and LMCI. Evaluation results show that the proposed method enhanced the existing method's accuracy with less feature dimensionality.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"7 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139631143","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 : 2024-01-01DOI: 10.21608/mjeer.2023.246301.1085
Ahmed Mohamed, Walid El-Shafa, Mona Shokair
: With the global proliferation of the Internet and digitalization transforming how information is shared, there has been exponential growth in the transmission of multimedia content fueled by advancing communication technologies. In recent times, Digital Imaging and Communications in Medicine (DICOM) medical imaging has become critical for disease diagnosis. Given that these images are often transmitted across networks, ensuring their robust protection has become imperative. Unauthorized access or misuse of the data within these images could potentially result in serious consequences. Various approaches exist for safeguarding such images, with encryption emerging as a highly effective method. Encryption algorithms typically involve two key phases: confusion and diffusion. This paper suggested proposed encryption technique designed specifically for encrypting both gray-scale and color DICOM medical images. Several assessment criteria, including the Number of Changing Pixel Rate (NPCR), Unified Averaged Changed Intensity (UACI), average entropy, correlation coefficients, Structural Similarity (SSIM), Feature Similarity (FSIM), and Peak Signal-to-Noise Ratio (PSNR), are employed to evaluate the suggested cryptosystem. These evaluations vividly underscore the robust security performance exhibited by the proposed approach.
{"title":"DICOM Medical Image Security with DNA- Non-Uniform Cellular Automata and JSMP Map Based Encryption Technique","authors":"Ahmed Mohamed, Walid El-Shafa, Mona Shokair","doi":"10.21608/mjeer.2023.246301.1085","DOIUrl":"https://doi.org/10.21608/mjeer.2023.246301.1085","url":null,"abstract":": With the global proliferation of the Internet and digitalization transforming how information is shared, there has been exponential growth in the transmission of multimedia content fueled by advancing communication technologies. In recent times, Digital Imaging and Communications in Medicine (DICOM) medical imaging has become critical for disease diagnosis. Given that these images are often transmitted across networks, ensuring their robust protection has become imperative. Unauthorized access or misuse of the data within these images could potentially result in serious consequences. Various approaches exist for safeguarding such images, with encryption emerging as a highly effective method. Encryption algorithms typically involve two key phases: confusion and diffusion. This paper suggested proposed encryption technique designed specifically for encrypting both gray-scale and color DICOM medical images. Several assessment criteria, including the Number of Changing Pixel Rate (NPCR), Unified Averaged Changed Intensity (UACI), average entropy, correlation coefficients, Structural Similarity (SSIM), Feature Similarity (FSIM), and Peak Signal-to-Noise Ratio (PSNR), are employed to evaluate the suggested cryptosystem. These evaluations vividly underscore the robust security performance exhibited by the proposed approach.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"21 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139635571","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 : 2023-07-01DOI: 10.21608/mjeer.2023.203343.1076
naira salah, El-Sayed M. El-Rabie, Ashraf Khalaf
— This paper introduces an introduction to photonic crystals (PCs) and photonic crystal fiber (PCF) sensors along with their different applications. A comparative study of different types of PCF sensors including chemical, biomedical, and liquid sensors is presented. Many distinct factors, including the device structure, background material, operating wavelength, PCF's guiding mechanisms and the sample refractive indices to be detected, affect how PCF sensors behave. Different topologies such as hexagonal, hollow rectangle, decagonal, rectangular porous core, and mono rectangular are discussed. Sensing properties, and measurement methodologies for each of these sensors are discussed. Based on this comparative study, PCF sensors are categorized according to their properties, topologies, measurement techniques, and applications. The appropriate topology for the required application can be selected based on the required properties. The same PCF topology can be used for different sensing purposes. A comparative study of different types of PCF sensors in a form of table is presented followed by the challenges and some novel trends on Photonic Crystal Fiber. _______________________________________________________
{"title":"Photonic Crystal Fiber Sensors, Literature Review, Challenges, and Some Novel Trends","authors":"naira salah, El-Sayed M. El-Rabie, Ashraf Khalaf","doi":"10.21608/mjeer.2023.203343.1076","DOIUrl":"https://doi.org/10.21608/mjeer.2023.203343.1076","url":null,"abstract":"— This paper introduces an introduction to photonic crystals (PCs) and photonic crystal fiber (PCF) sensors along with their different applications. A comparative study of different types of PCF sensors including chemical, biomedical, and liquid sensors is presented. Many distinct factors, including the device structure, background material, operating wavelength, PCF's guiding mechanisms and the sample refractive indices to be detected, affect how PCF sensors behave. Different topologies such as hexagonal, hollow rectangle, decagonal, rectangular porous core, and mono rectangular are discussed. Sensing properties, and measurement methodologies for each of these sensors are discussed. Based on this comparative study, PCF sensors are categorized according to their properties, topologies, measurement techniques, and applications. The appropriate topology for the required application can be selected based on the required properties. The same PCF topology can be used for different sensing purposes. A comparative study of different types of PCF sensors in a form of table is presented followed by the challenges and some novel trends on Photonic Crystal Fiber. _______________________________________________________","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128171536","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 : 2023-05-25DOI: 10.21608/mjeer.2023.201037.1075
N. Saeed, O. Omara, M. Abd Elkader
{"title":"Vibration Control of Horizontally Supported Jeffcott-Rotor System Utilizing PIRC-controller","authors":"N. Saeed, O. Omara, M. Abd Elkader","doi":"10.21608/mjeer.2023.201037.1075","DOIUrl":"https://doi.org/10.21608/mjeer.2023.201037.1075","url":null,"abstract":"","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127255882","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 : 2023-05-25DOI: 10.21608/mjeer.2023.159995.1066
Hayam R. Seireg, Yasser M. K. Omar, F. El-Sayed, A. El-Fishawy, A. Elmahalawy
{"title":"Cascading ensemble machine learning algorithms for maize yield level prediction","authors":"Hayam R. Seireg, Yasser M. K. Omar, F. El-Sayed, A. El-Fishawy, A. Elmahalawy","doi":"10.21608/mjeer.2023.159995.1066","DOIUrl":"https://doi.org/10.21608/mjeer.2023.159995.1066","url":null,"abstract":"","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127227468","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 : 2023-01-01DOI: 10.21608/mjeer.2023.283902
Randa Ali, Taha E. Taha, Noha A. El-Hag, Moawad I.Dessoky, Walid El- Shafai, Fathi E. Abd El- samie
— This paper presents a framework for medical image diagnosis of brain tumors. This framework comprises image fusion, image interpolation and image segmentation. The objective of the fusion process is to integerate information from MR and CT images in a single image for better representation of tumors. The fusion is implemented with one of the Dual tree complex wavelet transform (DT-CWT), Discrete wavelet transform (DWT) and principal component analysis (PCA) algorithms to investigate the best one for the application of interest. Interpolation is implemented with one of both polynomial and inverse interpolation techniques. Inverse techniques including linear minimum mean square error (LMMSE) and regularized interpolation are preferred to polynomial technique. After that, threshold segmentation is implemented to isolate the tumor region. Different evolution metrics are used such as accuracy, sensitivity , precision , specifity ,…….. are used to assess the proposed framework. Simulation results prove that the frameworking depending on DWT fusion gives the best results over the existing published techniques
{"title":"Efficient Utilization of Image Fusion and Interpolation for Medical Image Diagnosis applications","authors":"Randa Ali, Taha E. Taha, Noha A. El-Hag, Moawad I.Dessoky, Walid El- Shafai, Fathi E. Abd El- samie","doi":"10.21608/mjeer.2023.283902","DOIUrl":"https://doi.org/10.21608/mjeer.2023.283902","url":null,"abstract":"— This paper presents a framework for medical image diagnosis of brain tumors. This framework comprises image fusion, image interpolation and image segmentation. The objective of the fusion process is to integerate information from MR and CT images in a single image for better representation of tumors. The fusion is implemented with one of the Dual tree complex wavelet transform (DT-CWT), Discrete wavelet transform (DWT) and principal component analysis (PCA) algorithms to investigate the best one for the application of interest. Interpolation is implemented with one of both polynomial and inverse interpolation techniques. Inverse techniques including linear minimum mean square error (LMMSE) and regularized interpolation are preferred to polynomial technique. After that, threshold segmentation is implemented to isolate the tumor region. Different evolution metrics are used such as accuracy, sensitivity , precision , specifity ,…….. are used to assess the proposed framework. Simulation results prove that the frameworking depending on DWT fusion gives the best results over the existing published techniques","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121584055","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 : 2023-01-01DOI: 10.21608/mjeer.2023.283913
Islam R.Kamal, Saied M. Abd El-atty, S. F. El-Zoghdy, Randa F. Soliman
—The authors propose a multi-compartmental model based on molecular communication (MC) technology for drug delivery to the malignant cell without affecting healthy cells in the patient's body. The medical personnel can transfer/control the required drug to the targeted cell with the help of a group of bio-nanomachines connected to the Internet of biological Nano Things (IoBNT) and a bio-cyber interface in both the forward and reverse directions. The proposed model consists of a set of multi-differential equations that are used to identify molecular communication among bio-nanomachines and quantify drug concentration to the targeted cell. Unlike conventional compartmental models, the proposed model can deliver the desired drug to the targeted cell by accounting for extracellular and intracellular tumor compartments, resulting in fewer therapeutic doses with improved efficacy. Simulations were also carried out to evaluate the performance of proposed multi-compartmental model with changing the physical parameters.
{"title":"A Multi Compartmental model for Targeted Drug Delivery Based on Internet of Biological NanoThings","authors":"Islam R.Kamal, Saied M. Abd El-atty, S. F. El-Zoghdy, Randa F. Soliman","doi":"10.21608/mjeer.2023.283913","DOIUrl":"https://doi.org/10.21608/mjeer.2023.283913","url":null,"abstract":"—The authors propose a multi-compartmental model based on molecular communication (MC) technology for drug delivery to the malignant cell without affecting healthy cells in the patient's body. The medical personnel can transfer/control the required drug to the targeted cell with the help of a group of bio-nanomachines connected to the Internet of biological Nano Things (IoBNT) and a bio-cyber interface in both the forward and reverse directions. The proposed model consists of a set of multi-differential equations that are used to identify molecular communication among bio-nanomachines and quantify drug concentration to the targeted cell. Unlike conventional compartmental models, the proposed model can deliver the desired drug to the targeted cell by accounting for extracellular and intracellular tumor compartments, resulting in fewer therapeutic doses with improved efficacy. Simulations were also carried out to evaluate the performance of proposed multi-compartmental model with changing the physical parameters.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115097975","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 : 2023-01-01DOI: 10.21608/mjeer.2023.283915
Eman sayed ward, Nasr Gad, M. Lotfy Rabeh, A. Yahia
— The electrical performance of photovoltaic (PV) cells or arrays is greatly influenced by the ambient temperature and the solar radiation intensity (irradiation) as well. The effect of temperature and solar irradiance on the main characteristics of solar panels and photovoltaic modules is investigated in this paper. The primary parameters are identified and extracted using the capacitive load approach. These parameters are Short Circuit Current (I sc ), Maximum Power Point Current (I mpp ), Open Circuit Voltage (V oc ), Maximum Power Point Voltage (V mpp ), Maximum Power Point (P max ), Fill factor (FF) and Efficiency (η). The PV cell used in this study is poly-crystal silicon. Its commercial name is Kyocera solar KC130GT. MATLAB Simulink is used to assess the capacitive load method in the investigation of I-V and P-V curves. These two curves are derived based on the effects of varying temperatures (30, 35, 40, and 45 o C) at a constant irradiance (1000 W/m 2 ) on the PV cell performance and the effect of varying irradiance (250, 500, 750, and 1000 W/m 2 ) at constant temperature (25 o C) as well. It is concluded that by increasing the irradiance at constant temperature, I sc and V oc are increasing. As a result, η increases from 13.9% at 250 W/m 2 to reach 14.7% at 1000 W/m 2 . In the case of increasing temperature at constant irradiance, η decreases from 13.5% at 30 o C to reach 12.8% at 45 o C. This is due to the large drop in V oc compared to the small increment in I sc .
{"title":"Effects of Solar Irradiance and Temperature on Photovoltaic Module Characteristics using a capacitive load method","authors":"Eman sayed ward, Nasr Gad, M. Lotfy Rabeh, A. Yahia","doi":"10.21608/mjeer.2023.283915","DOIUrl":"https://doi.org/10.21608/mjeer.2023.283915","url":null,"abstract":"— The electrical performance of photovoltaic (PV) cells or arrays is greatly influenced by the ambient temperature and the solar radiation intensity (irradiation) as well. The effect of temperature and solar irradiance on the main characteristics of solar panels and photovoltaic modules is investigated in this paper. The primary parameters are identified and extracted using the capacitive load approach. These parameters are Short Circuit Current (I sc ), Maximum Power Point Current (I mpp ), Open Circuit Voltage (V oc ), Maximum Power Point Voltage (V mpp ), Maximum Power Point (P max ), Fill factor (FF) and Efficiency (η). The PV cell used in this study is poly-crystal silicon. Its commercial name is Kyocera solar KC130GT. MATLAB Simulink is used to assess the capacitive load method in the investigation of I-V and P-V curves. These two curves are derived based on the effects of varying temperatures (30, 35, 40, and 45 o C) at a constant irradiance (1000 W/m 2 ) on the PV cell performance and the effect of varying irradiance (250, 500, 750, and 1000 W/m 2 ) at constant temperature (25 o C) as well. It is concluded that by increasing the irradiance at constant temperature, I sc and V oc are increasing. As a result, η increases from 13.9% at 250 W/m 2 to reach 14.7% at 1000 W/m 2 . In the case of increasing temperature at constant irradiance, η decreases from 13.5% at 30 o C to reach 12.8% at 45 o C. This is due to the large drop in V oc compared to the small increment in I sc .","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129116864","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 : 2023-01-01DOI: 10.21608/mjeer.2023.283911
Ahmed A. Hassan, El-Sayed M. El-Rabie, R. Elsharkawy, Demyana A. Saleeb, Ahmed S. Elkorany
{"title":"Terahertz Reflectarray Antenna with a Square Patch Surrounded by Two Concentric Square Rings as a Unit Cell","authors":"Ahmed A. Hassan, El-Sayed M. El-Rabie, R. Elsharkawy, Demyana A. Saleeb, Ahmed S. Elkorany","doi":"10.21608/mjeer.2023.283911","DOIUrl":"https://doi.org/10.21608/mjeer.2023.283911","url":null,"abstract":"","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129065026","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 : 2022-07-05DOI: 10.21608/mjeer.2022.79630.1037
Ibrahim sayed, M. Nour, Mohammed Badawy, E. Abed
— In this research work, four classifiers are adopted, analyzed, and discussed. The classifiers are Naïve Bayes (NB), Support Vector Machine (SVM), Stochastic Gradient Descent (SGD), and Logistic Regression (LR). The classifiers are operated on a dataset with more than eight-thousands of instances. The dataset contains the users' reviews and their opinions about the quality of service of restaurants. The reviews are collected from the Arabic Facebook posts. Several experiments are done to evaluate the performance of the adopted classifiers. Moreover, some features selection methods are also applied to improve the classification process. The feature selected methods are based on term-weights with N-grams, correlation, chi-square, and mutual information. Some criteria are considered to evaluate the performance of the classification process mainly: precision, recall, F-measure, and learning time. From the experimental results, the SVM classifier outperforms the other adopted ones. Also, the feature selection method based on the correlation between the individual features and the target class outperforms the other chosen methods. The same concluding remarks are expected to take place for other datasets containing comments or reviews from social media.
{"title":"Classification of Users' Opinions and Posts on Facebook Using Machine Learning Approaches","authors":"Ibrahim sayed, M. Nour, Mohammed Badawy, E. Abed","doi":"10.21608/mjeer.2022.79630.1037","DOIUrl":"https://doi.org/10.21608/mjeer.2022.79630.1037","url":null,"abstract":"— In this research work, four classifiers are adopted, analyzed, and discussed. The classifiers are Naïve Bayes (NB), Support Vector Machine (SVM), Stochastic Gradient Descent (SGD), and Logistic Regression (LR). The classifiers are operated on a dataset with more than eight-thousands of instances. The dataset contains the users' reviews and their opinions about the quality of service of restaurants. The reviews are collected from the Arabic Facebook posts. Several experiments are done to evaluate the performance of the adopted classifiers. Moreover, some features selection methods are also applied to improve the classification process. The feature selected methods are based on term-weights with N-grams, correlation, chi-square, and mutual information. Some criteria are considered to evaluate the performance of the classification process mainly: precision, recall, F-measure, and learning time. From the experimental results, the SVM classifier outperforms the other adopted ones. Also, the feature selection method based on the correlation between the individual features and the target class outperforms the other chosen methods. The same concluding remarks are expected to take place for other datasets containing comments or reviews from social media.","PeriodicalId":218019,"journal":{"name":"Menoufia Journal of Electronic Engineering Research","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127162884","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：