Pub Date : 2022-03-28DOI: 10.15849/ijasca.220328.12
Yazan M. Alwaqfi, M. Mohamad, Ahmad T. Al-Taani
Abstract Currently, Arabic character recognition remains one of the most complicated challenges in image processing and character identification. Many algorithms exist in neural networks, and one of the most interesting algorithms is called generative adversarial networks (GANs), where 2 neural networks fight against one another. A generative adversarial network has been successfully implemented in unsupervised learning and it led to outstanding achievements. Furthermore, this discriminator is used as a classifier in most generative adversarial networks by employing the binary sigmoid cross-entropy loss function. This research proposes employing sigmoid cross-entropy to recognize Arabic handwritten characters using multi-class GANs training algorithms. The proposed approach is evaluated on a dataset of 16800 Arabic handwritten characters. When compared to other approaches, the experimental results indicate that the multi-class GANs approach performed well in terms of recognizing Arabic handwritten characters as it is 99.7% accurate. Keywords: Generative Adversarial Networks (GANs), Arabic Characters, Optical Character Recognition, Convolutional Neural Networks (CNNs).
{"title":"Generative Adversarial Network for an Improved Arabic Handwritten Characters Recognition","authors":"Yazan M. Alwaqfi, M. Mohamad, Ahmad T. Al-Taani","doi":"10.15849/ijasca.220328.12","DOIUrl":"https://doi.org/10.15849/ijasca.220328.12","url":null,"abstract":"Abstract Currently, Arabic character recognition remains one of the most complicated challenges in image processing and character identification. Many algorithms exist in neural networks, and one of the most interesting algorithms is called generative adversarial networks (GANs), where 2 neural networks fight against one another. A generative adversarial network has been successfully implemented in unsupervised learning and it led to outstanding achievements. Furthermore, this discriminator is used as a classifier in most generative adversarial networks by employing the binary sigmoid cross-entropy loss function. This research proposes employing sigmoid cross-entropy to recognize Arabic handwritten characters using multi-class GANs training algorithms. The proposed approach is evaluated on a dataset of 16800 Arabic handwritten characters. When compared to other approaches, the experimental results indicate that the multi-class GANs approach performed well in terms of recognizing Arabic handwritten characters as it is 99.7% accurate. Keywords: Generative Adversarial Networks (GANs), Arabic Characters, Optical Character Recognition, Convolutional Neural Networks (CNNs).","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41886432","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 : 2022-03-28DOI: 10.15849/ijasca.220328.09
Muhammad Halim, Muslihah Wook, N. Hasbullah, N. Razali, H. Hamid
Abstract Data mining techniques have recently drawn considerable attention from the research community for their ability to predict flash flood phenomena. These techniques can bring large-scale flood data into real practice and have become the necessary tools for impact assessment, societal resilience, and disaster control. Although numerous studies have been conducted on data mining techniques and flash flood predictions, domain-specific flash flood prediction models based on existing data mining techniques are still lacking. Notably, this study has focused on the performance of four data mining techniques, namely, logistic regression (LR), artificial neural networks (ANN), k-nearest neighbour (kNN), and support vector machine (SVM) in a comparative assessment as prediction models. The area under the curve (AUC) was utilised to validate these models. The value of AUC was higher than 0.9 for all models. Accordingly, the outcomes outlined in this study can contribute to Halim et al. the current literature by boosting the performance of data mining techniques for predicting flash floods through a comparison of the most recent data mining techniques. Keywords: Artificial neural networks (ANN), Flash flood, k-nearest neighbor (kNN), Logistic regression (LR), Support vector machine (SVM)
{"title":"Comparative Assessment of Data Mining Techniques for Flash Flood Prediction","authors":"Muhammad Halim, Muslihah Wook, N. Hasbullah, N. Razali, H. Hamid","doi":"10.15849/ijasca.220328.09","DOIUrl":"https://doi.org/10.15849/ijasca.220328.09","url":null,"abstract":"Abstract Data mining techniques have recently drawn considerable attention from the research community for their ability to predict flash flood phenomena. These techniques can bring large-scale flood data into real practice and have become the necessary tools for impact assessment, societal resilience, and disaster control. Although numerous studies have been conducted on data mining techniques and flash flood predictions, domain-specific flash flood prediction models based on existing data mining techniques are still lacking. Notably, this study has focused on the performance of four data mining techniques, namely, logistic regression (LR), artificial neural networks (ANN), k-nearest neighbour (kNN), and support vector machine (SVM) in a comparative assessment as prediction models. The area under the curve (AUC) was utilised to validate these models. The value of AUC was higher than 0.9 for all models. Accordingly, the outcomes outlined in this study can contribute to Halim et al. the current literature by boosting the performance of data mining techniques for predicting flash floods through a comparison of the most recent data mining techniques. Keywords: Artificial neural networks (ANN), Flash flood, k-nearest neighbor (kNN), Logistic regression (LR), Support vector machine (SVM)","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41497751","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 : 2022-03-28DOI: 10.15849/ijasca.220328.13
M. Elbes, Tarek Kanan, Mohammad Alia, Mohammad Ziad
Abstract Since the early days of 2020, COVID-19 has tragic effects on the lives of human beings all over the world. To combat this disease, it is important to survey the infected patients in an inexpensive and fast way. One of the most common ways of achieving this is by performing radiological testing using chest X-Rays and patient coughing sounds. In this work, we propose a Convolutional Neural Network-based solution which is able to identify the positive COVID-19 patients using chest XRay images. Multiple CNN models have been adopted in our work. Each of these models provides a decision whether the patient is affected with COVID-19 or not. Then, a weighted average selection technique is used to provide the final decision. To test the efficiency of our model we have used publicly available chest X-ray images of COVID positive and negative cases. Our approach provided a classification performance of 88.5%. Keywords: COVID-19, CT-Images, Deep Learning, CNN Algorithm.
{"title":"COVD-19 Detection Platform from X-ray Images using Deep Learning","authors":"M. Elbes, Tarek Kanan, Mohammad Alia, Mohammad Ziad","doi":"10.15849/ijasca.220328.13","DOIUrl":"https://doi.org/10.15849/ijasca.220328.13","url":null,"abstract":"Abstract Since the early days of 2020, COVID-19 has tragic effects on the lives of human beings all over the world. To combat this disease, it is important to survey the infected patients in an inexpensive and fast way. One of the most common ways of achieving this is by performing radiological testing using chest X-Rays and patient coughing sounds. In this work, we propose a Convolutional Neural Network-based solution which is able to identify the positive COVID-19 patients using chest XRay images. Multiple CNN models have been adopted in our work. Each of these models provides a decision whether the patient is affected with COVID-19 or not. Then, a weighted average selection technique is used to provide the final decision. To test the efficiency of our model we have used publicly available chest X-ray images of COVID positive and negative cases. Our approach provided a classification performance of 88.5%. Keywords: COVID-19, CT-Images, Deep Learning, CNN Algorithm.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42027101","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 : 2022-03-28DOI: 10.15849/ijasca.220328.05
S. Hansun
Abstract The real estate market is one of the most impacted sectors from the Corona Virus Disease 2019 (COVID-19) pandemic that happened in early 2020 globally. Here, we tried to apply an extension of the Long Short-Term Memory (LSTM) deep learning method, known as the Bidirectional LSTM (Bi-LSTM) networks for stock price prediction. Our focus is on six stocks that were included in the LiQuid45 (LQ45) property and real estate sectors. A simple three-layers Bi-LSTM network is proposed for predicting the stocks’ closing prices. We found that the prediction results fall in the reasonable prediction category, except for Pembangunan Perumahan Tbk (PTPP). Bumi Serpong Damai Tbk (BSDE) got the highest accuracy result with more than 90% score, while PTPP got the lowest score with less than 8% score. The proposed Bi-LSTM network could provide a baseline result for developing a good trading strategy. Keywords: Bi-LSTM networks, deep learning, LQ45, property and real estate, stock price prediction.
{"title":"Deep Learning Approach in Predicting Property and Real Estate Indices","authors":"S. Hansun","doi":"10.15849/ijasca.220328.05","DOIUrl":"https://doi.org/10.15849/ijasca.220328.05","url":null,"abstract":"Abstract The real estate market is one of the most impacted sectors from the Corona Virus Disease 2019 (COVID-19) pandemic that happened in early 2020 globally. Here, we tried to apply an extension of the Long Short-Term Memory (LSTM) deep learning method, known as the Bidirectional LSTM (Bi-LSTM) networks for stock price prediction. Our focus is on six stocks that were included in the LiQuid45 (LQ45) property and real estate sectors. A simple three-layers Bi-LSTM network is proposed for predicting the stocks’ closing prices. We found that the prediction results fall in the reasonable prediction category, except for Pembangunan Perumahan Tbk (PTPP). Bumi Serpong Damai Tbk (BSDE) got the highest accuracy result with more than 90% score, while PTPP got the lowest score with less than 8% score. The proposed Bi-LSTM network could provide a baseline result for developing a good trading strategy. Keywords: Bi-LSTM networks, deep learning, LQ45, property and real estate, stock price prediction.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42015887","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 : 2022-03-28DOI: 10.15849/ijasca.220328.02
M. Khder, Mohammad Sayf, S. Fujo
Abstract happiness is a dream goal to be achieved by governments and individuals and it can be considered as a proper measure of social development progress. The purpose of this paper is to conduct a study on World happiness report dataset, to classify the most critical variables regarding the life happiness score. The strong evidence of the identified main features classified from the outcomes of applying the supervised machine learning approaches using the Neural Network training model and the OneR models in classifications and feature selection. The trained model used in predictions revealed the insights derived from applying the data analysis, where the study found out that the GDP per capita is the critical indicator of life happiness score as well as the health life expectancy is the second primary feature. Findings from study evaluated using different performance metrics such as accuracy and confusion matrix to prove the insights gained from the data. Keywords: world happiness, machine learning, Neural Network.
{"title":"Analysis of World Happiness Report Dataset Using Machine Learning Approaches","authors":"M. Khder, Mohammad Sayf, S. Fujo","doi":"10.15849/ijasca.220328.02","DOIUrl":"https://doi.org/10.15849/ijasca.220328.02","url":null,"abstract":"Abstract happiness is a dream goal to be achieved by governments and individuals and it can be considered as a proper measure of social development progress. The purpose of this paper is to conduct a study on World happiness report dataset, to classify the most critical variables regarding the life happiness score. The strong evidence of the identified main features classified from the outcomes of applying the supervised machine learning approaches using the Neural Network training model and the OneR models in classifications and feature selection. The trained model used in predictions revealed the insights derived from applying the data analysis, where the study found out that the GDP per capita is the critical indicator of life happiness score as well as the health life expectancy is the second primary feature. Findings from study evaluated using different performance metrics such as accuracy and confusion matrix to prove the insights gained from the data. Keywords: world happiness, machine learning, Neural Network.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46515608","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 : 2022-03-28DOI: 10.15849/ijasca.220328.03
H. Hanaf, B. Hassani, M. Kbir
Abstract Prediction of gene-drug-disease interactions have talented new insights in biology. Discovering unknown interactions will provide new therapeutic approaches to explore gene expressions. Recent improvements in machine learning techniques have gotten considerable interest due to higher efficiency, accurate results, and their lower cost. However, most of the studies were ignoring relevant associations, by representing only drug-disease interactions on a network while public available data offers a large variety of interactions. Additionally, some computational techniques used in this domain are faced with new challenges, related to the organization of heterogeneous data which suffer from a high imbalance rate since there are extensively more non-interacting gene-drug-disease triplets than interacting ones. In this paper we present integration of heterogeneous biological data about genes, drugs, and diseases to build a model, and building a new graph representation relating genedrug-disease interactions. Using extreme gradient boosting (XGBoost) algorithm, we have been able to extract a list of valid interactions about gene-drug-disease triplets, and a list of gene-drug pairs related to lung cancer. Keywords: Biological heterogeneous data, Data integration, Gene-DrugDisease interactions, Machine learning.
{"title":"Predicting Gene-Drug-Disease Interactions by integrating Heterogeneous Biological Data Through a Network Model","authors":"H. Hanaf, B. Hassani, M. Kbir","doi":"10.15849/ijasca.220328.03","DOIUrl":"https://doi.org/10.15849/ijasca.220328.03","url":null,"abstract":"Abstract Prediction of gene-drug-disease interactions have talented new insights in biology. Discovering unknown interactions will provide new therapeutic approaches to explore gene expressions. Recent improvements in machine learning techniques have gotten considerable interest due to higher efficiency, accurate results, and their lower cost. However, most of the studies were ignoring relevant associations, by representing only drug-disease interactions on a network while public available data offers a large variety of interactions. Additionally, some computational techniques used in this domain are faced with new challenges, related to the organization of heterogeneous data which suffer from a high imbalance rate since there are extensively more non-interacting gene-drug-disease triplets than interacting ones. In this paper we present integration of heterogeneous biological data about genes, drugs, and diseases to build a model, and building a new graph representation relating genedrug-disease interactions. Using extreme gradient boosting (XGBoost) algorithm, we have been able to extract a list of valid interactions about gene-drug-disease triplets, and a list of gene-drug pairs related to lung cancer. Keywords: Biological heterogeneous data, Data integration, Gene-DrugDisease interactions, Machine learning.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47804632","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 : 2022-03-28DOI: 10.15849/ijasca.220328.07
Ali Mohammed Sahan, N. Jabr, Ahmed Bahaaulddin, Ali Al-Itb
Abstract Many studies refer that the figure knuckle comprises unique features. Therefore, it can be utilized in a biometric system to distinguishing between the peoples. In this paper, a combined global and local features technique has been proposed based on two descriptors, namely: Chebyshev Fourier moments (CHFMs) and Scale Invariant Feature Transform (SIFT) descriptors. The CHFMs descriptor is used to gaining the global features, while the scale invariant feature transform descriptor is utilized to extract local features. Each one of these descriptors has its advantages; therefore, combining them together leads to produce distinct features. Many experiments have been carried out using IIT-Delhi knuckle database to assess the accuracy of the proposed approach. The analysis of the results of these extensive experiments implies that the suggested technique has gained 98% accuracy rate. Furthermore, the robustness against the noise has been evaluated. The results of these experiments lead to concluding that the proposed technique is robust against the noise variation. Keywords: finger knuckle, biometric system, Chebyshev Fourier moments, scale invariant feature transform, IIT-Delhi knuckle database.
{"title":"Human identification using finger knuckle features","authors":"Ali Mohammed Sahan, N. Jabr, Ahmed Bahaaulddin, Ali Al-Itb","doi":"10.15849/ijasca.220328.07","DOIUrl":"https://doi.org/10.15849/ijasca.220328.07","url":null,"abstract":"Abstract Many studies refer that the figure knuckle comprises unique features. Therefore, it can be utilized in a biometric system to distinguishing between the peoples. In this paper, a combined global and local features technique has been proposed based on two descriptors, namely: Chebyshev Fourier moments (CHFMs) and Scale Invariant Feature Transform (SIFT) descriptors. The CHFMs descriptor is used to gaining the global features, while the scale invariant feature transform descriptor is utilized to extract local features. Each one of these descriptors has its advantages; therefore, combining them together leads to produce distinct features. Many experiments have been carried out using IIT-Delhi knuckle database to assess the accuracy of the proposed approach. The analysis of the results of these extensive experiments implies that the suggested technique has gained 98% accuracy rate. Furthermore, the robustness against the noise has been evaluated. The results of these experiments lead to concluding that the proposed technique is robust against the noise variation. Keywords: finger knuckle, biometric system, Chebyshev Fourier moments, scale invariant feature transform, IIT-Delhi knuckle database.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47948194","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 : 2022-03-28DOI: 10.15849/ijasca.220328.08
Deepshikha Bhatia
Abstract Cyber security, an application that protects and controls the systems, programs, networks, data and devices from cyber-attacks. This cyber security practice used by individuals and small or large organizations for protecting against unusual data access. A powerful cyber security system provides a great security against malware attacks, viruses, ransom ware, cloud attacks, IoT attacks etc. and it designed for accessing, destroying, deleting and altering these attacks and secure the retrieving data from the server and user’s systems. This paper discuss about the importance of cyber security in organizations of India. Surveys of Indian organization’s cyber security measures are taken for the evaluation of the methods and challenges of cyber security. This comprehensive review provides insights about securing the data by employing cyber security frame works, risk assessment models and educating cyber security knowledge among public with help of government public programs. With these information this paper helps for overcoming the cyber threats and attacks and created a pre cautionary thought and also made a pre vision for diminishing theft of data among employees and tracking hacker’s activities before attacking the organizations. Keywords: cyber security, Indian organization, cyber-attacks, cyber security methods, DDoS attack.
{"title":"A Comprehensive Review on the Cyber Security Methods in Indian Organisation","authors":"Deepshikha Bhatia","doi":"10.15849/ijasca.220328.08","DOIUrl":"https://doi.org/10.15849/ijasca.220328.08","url":null,"abstract":"Abstract Cyber security, an application that protects and controls the systems, programs, networks, data and devices from cyber-attacks. This cyber security practice used by individuals and small or large organizations for protecting against unusual data access. A powerful cyber security system provides a great security against malware attacks, viruses, ransom ware, cloud attacks, IoT attacks etc. and it designed for accessing, destroying, deleting and altering these attacks and secure the retrieving data from the server and user’s systems. This paper discuss about the importance of cyber security in organizations of India. Surveys of Indian organization’s cyber security measures are taken for the evaluation of the methods and challenges of cyber security. This comprehensive review provides insights about securing the data by employing cyber security frame works, risk assessment models and educating cyber security knowledge among public with help of government public programs. With these information this paper helps for overcoming the cyber threats and attacks and created a pre cautionary thought and also made a pre vision for diminishing theft of data among employees and tracking hacker’s activities before attacking the organizations. Keywords: cyber security, Indian organization, cyber-attacks, cyber security methods, DDoS attack.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47185928","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 : 2022-03-28DOI: 10.15849/ijasca.220328.04
Hiba Alsaidi, W. Etaiwi
Abstract Humans have been fighting the Covid19 pandemic since it started, not just to protect their wellbeing but also to counteract the news and rumors that have been spreading about it. Rumors and false allegations can be almost as dangerous as the virus, as they affect people's mental health and increase their stress levels. To address this problem, several machine learning techniques could be used to detect fake news. In this paper, four different machine learning algorithms are compared according to their ability to detect fake news, including Naive Bayes, Decision Tree, Support Vector Machines, and Logistic Regression. A dataset of annotated news is used in the experiments. The experimental results show that Naïve Bayes outperforms other algorithms in terms of accuracy, precision, recall, and F1 score. Keywords: COVID-19, Machine Learning, Fake news detection.
{"title":"Empirical Evaluation of Machine Learning Classification Algorithms for Detecting COVID19 Fake News","authors":"Hiba Alsaidi, W. Etaiwi","doi":"10.15849/ijasca.220328.04","DOIUrl":"https://doi.org/10.15849/ijasca.220328.04","url":null,"abstract":"Abstract Humans have been fighting the Covid19 pandemic since it started, not just to protect their wellbeing but also to counteract the news and rumors that have been spreading about it. Rumors and false allegations can be almost as dangerous as the virus, as they affect people's mental health and increase their stress levels. To address this problem, several machine learning techniques could be used to detect fake news. In this paper, four different machine learning algorithms are compared according to their ability to detect fake news, including Naive Bayes, Decision Tree, Support Vector Machines, and Logistic Regression. A dataset of annotated news is used in the experiments. The experimental results show that Naïve Bayes outperforms other algorithms in terms of accuracy, precision, recall, and F1 score. Keywords: COVID-19, Machine Learning, Fake news detection.","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43009283","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 : 2022-03-28DOI: 10.15849/zujijasaca.220328.01
W. Alzyadat, Mohammad I. Muhairat, Aysh Alhroob, Thamer Rawashdeh
Abstract The various model that has been used to predict, datamining, and information retrieval are useful to use through the traditional database, due to big data the prediction should derive in a different role that conduct the hidden structure data based on a stability scale to allow discovering accrue unsupervised drug data. Especially, the drug data must be understandable to analysts. Following this approach, conduct the stability drug data through computation methods are quality measurements, preprocess data, k-mean cluster, and decision tree. This approach seeks to identify the data by two dimensions (vertically and horizontally), which extrapolations, compilation, and interpretation values of the dataset while considering individual attributes. A comparison with clusters defines the set for features using balance value by K-mean algorithm to determine the k clusters that consider the set of features based on two values 0 and 1, which given the discernible between dependent and independent class target, and pinpoint the relationship among them. Keywords: Big Data, Discretize, k-mean cluster Stability, Target drug
{"title":"A Recruitment Big Data Approach to interplay of the Target Drugs","authors":"W. Alzyadat, Mohammad I. Muhairat, Aysh Alhroob, Thamer Rawashdeh","doi":"10.15849/zujijasaca.220328.01","DOIUrl":"https://doi.org/10.15849/zujijasaca.220328.01","url":null,"abstract":"Abstract The various model that has been used to predict, datamining, and information retrieval are useful to use through the traditional database, due to big data the prediction should derive in a different role that conduct the hidden structure data based on a stability scale to allow discovering accrue unsupervised drug data. Especially, the drug data must be understandable to analysts. Following this approach, conduct the stability drug data through computation methods are quality measurements, preprocess data, k-mean cluster, and decision tree. This approach seeks to identify the data by two dimensions (vertically and horizontally), which extrapolations, compilation, and interpretation values of the dataset while considering individual attributes. A comparison with clusters defines the set for features using balance value by K-mean algorithm to determine the k clusters that consider the set of features based on two values 0 and 1, which given the discernible between dependent and independent class target, and pinpoint the relationship among them. Keywords: Big Data, Discretize, k-mean cluster Stability, Target drug","PeriodicalId":38638,"journal":{"name":"International Journal of Advances in Soft Computing and its Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46877002","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：