Pub Date : 2022-03-01DOI: 10.1109/CDMA54072.2022.00023
Amal Algefes, Nouf Aldossari, Fatma Masmoudi, Elham Kariri
Social networks have proven to be a massive hub for investigating contextual and individual behavior of people. Most recently micro-blogging sites like Twitter are indicating to researchers that their content can be aggregated and used to effectively predict forecast, and infer outcomes of real-world events. The crime-related tweets analysis research in Saudi Arabia set off with an ultimate goal of gathering a deeper understanding of what kinds of criminal weapons are people frequently talking about. In this paper, we aim at dealing with tweets mentioning different weapons, analyzing them to gather facts such as annual variation of percentage tweets mentioning different weapons, recognizing the impact of events such as the Covid-19 pandemic on crime social discussions. In the following step, we develop a number of classifiers to predict which weapon is mentioned in a tweet. In order to perform our tasks, the Python programming language is used in the majority of the cases.
{"title":"A Text-mining approach for crime tweets in Saudi Arabia: From analysis to prediction","authors":"Amal Algefes, Nouf Aldossari, Fatma Masmoudi, Elham Kariri","doi":"10.1109/CDMA54072.2022.00023","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00023","url":null,"abstract":"Social networks have proven to be a massive hub for investigating contextual and individual behavior of people. Most recently micro-blogging sites like Twitter are indicating to researchers that their content can be aggregated and used to effectively predict forecast, and infer outcomes of real-world events. The crime-related tweets analysis research in Saudi Arabia set off with an ultimate goal of gathering a deeper understanding of what kinds of criminal weapons are people frequently talking about. In this paper, we aim at dealing with tweets mentioning different weapons, analyzing them to gather facts such as annual variation of percentage tweets mentioning different weapons, recognizing the impact of events such as the Covid-19 pandemic on crime social discussions. In the following step, we develop a number of classifiers to predict which weapon is mentioned in a tweet. In order to perform our tasks, the Python programming language is used in the majority of the cases.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123799570","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00043
Asad Ullah, Tufail Muhammad
Automated classification of cells is an essential but challenging task for computer vision with significant biomedical advantages. Numerous studies have attempted to construct a cell classifier based on artificial intelligence using label-free cellular images obtained from an optical microscope in recent years. While these studies showed promising results, different cell types' biological complexity could not be represented by such classifiers. However, it is well-known that intracellular actin filaments are significantly modified in terms of the malignant cell. This is believed to be closely linked to tumor cells' distinctive growth characteristics, their tendency to invade tissues around them, and metastasize. It is also more beneficial to identify various cell types based on their biological activities using an automated technique. This paper shows the differentiation between normal White Blood Cells and cancer, which can provide new knowledge on malignant changes and be used as an additional diagnostic marker. Since human eyes can not observe the features, we proposed the application of a convolutional neural network (CNN) based on malignant and normal WBCs classification. The Inception- V3Cnn model was validated on various WBCs normal and malignant cell images on regular normal and blood cancer cell lines with differing aggression levels. The study showed that CNN performed better in accuracy and efficiency than a human expert in the cell classification system
{"title":"Deep Learning for Classifying of White Blood Cancer","authors":"Asad Ullah, Tufail Muhammad","doi":"10.1109/CDMA54072.2022.00043","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00043","url":null,"abstract":"Automated classification of cells is an essential but challenging task for computer vision with significant biomedical advantages. Numerous studies have attempted to construct a cell classifier based on artificial intelligence using label-free cellular images obtained from an optical microscope in recent years. While these studies showed promising results, different cell types' biological complexity could not be represented by such classifiers. However, it is well-known that intracellular actin filaments are significantly modified in terms of the malignant cell. This is believed to be closely linked to tumor cells' distinctive growth characteristics, their tendency to invade tissues around them, and metastasize. It is also more beneficial to identify various cell types based on their biological activities using an automated technique. This paper shows the differentiation between normal White Blood Cells and cancer, which can provide new knowledge on malignant changes and be used as an additional diagnostic marker. Since human eyes can not observe the features, we proposed the application of a convolutional neural network (CNN) based on malignant and normal WBCs classification. The Inception- V3Cnn model was validated on various WBCs normal and malignant cell images on regular normal and blood cancer cell lines with differing aggression levels. The study showed that CNN performed better in accuracy and efficiency than a human expert in the cell classification system","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115592210","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00042
Salma Kulsoom, Seemab Latif, T. Saba, R. Latif
Statement of Purpose (SOP) plays a vital role in the university admissions process as reviewers assess the personality of the students by reading their SOPs. In past, the Big Five personality traits of the students are assessed to predict their future academic performance. An exciting application of machine learning is the personality assessment using personality traits and behavior. In this paper, our focus is on developing a deep learning-based personality assessment model for the detection of Big Five Personality traits from SOP and mapping them to speculate a student's academic performance at the university. Our proposed model uses Long-Short Term Memory (LSTM), Convolutional Neural Network (CNN) and Bi-Directional LSTM (Bi- LSTM) architectures to extract features and predict ratios of Big Five traits in the SOP. The proposed model has been trained and tested on an essays' dataset and 400 students' SOP collected from computer science undergraduate students. Maximum accuracy achieved for essays dataset is 88.2 % and for student's personal statement is 67.0 % with FastText Embedding.
{"title":"Students Personality Assessment using Deep Learning from University Admission Statement of Purpose","authors":"Salma Kulsoom, Seemab Latif, T. Saba, R. Latif","doi":"10.1109/CDMA54072.2022.00042","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00042","url":null,"abstract":"Statement of Purpose (SOP) plays a vital role in the university admissions process as reviewers assess the personality of the students by reading their SOPs. In past, the Big Five personality traits of the students are assessed to predict their future academic performance. An exciting application of machine learning is the personality assessment using personality traits and behavior. In this paper, our focus is on developing a deep learning-based personality assessment model for the detection of Big Five Personality traits from SOP and mapping them to speculate a student's academic performance at the university. Our proposed model uses Long-Short Term Memory (LSTM), Convolutional Neural Network (CNN) and Bi-Directional LSTM (Bi- LSTM) architectures to extract features and predict ratios of Big Five traits in the SOP. The proposed model has been trained and tested on an essays' dataset and 400 students' SOP collected from computer science undergraduate students. Maximum accuracy achieved for essays dataset is 88.2 % and for student's personal statement is 67.0 % with FastText Embedding.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"16 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116851947","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00028
N. Mahmoodian, Harshita Thadesar, Marilena Georgiades, M. Pech, C. Hoeschen
Microwave ablation (MWA) therapy with image guidance by computed tomography (CT) is used for liver tumor destruction. However, because of the noise and therefore low contrast, CT images are not good enough for therapy control and need additional magnetic resonance imaging after the ther-apy. The ablation process itself is facing two significant chal-lenges: Firstly insufficient tumor ablation, which leads to tumor recurrence. Secondary, total ablated area was significantly larger than the tumor size which causes damaging of healthy tissue. To minimize the impact, it is crucial for the radiologist to perform the therapy well to prevent tumor recurrence. Therefore, it is essential to differentiate among healthy, tumor, and ablated tissue textures in the CT scan images. This research contributes to the understanding of tissue characterization for the reduction of the recurrence rate. In this regard, four machine-learning (ML) algorithms of Naive-Bayesian, Logistic-Regression, Decision-Tree, and Random-Forest were employed for liver tissues classification. In this paper, we propose higher order spectral particularly bispectrum analysis for extracting features from the CT images. Then classifiers were trained by ten new features extracted from the bispectrum analysis. For that, the images were divided into small patches, they were labeled as healthy, tumor, and ablated tissue. A maximum accuracy of 90.5% was obtained. The approach shows that the bispectral analysis provides valuable information that can be used during the MWA therapy for tissue characterization of CT scan even in the presence of noise.
{"title":"Liver Texture Classification on CT Images of Microwave Ablation Therapy","authors":"N. Mahmoodian, Harshita Thadesar, Marilena Georgiades, M. Pech, C. Hoeschen","doi":"10.1109/CDMA54072.2022.00028","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00028","url":null,"abstract":"Microwave ablation (MWA) therapy with image guidance by computed tomography (CT) is used for liver tumor destruction. However, because of the noise and therefore low contrast, CT images are not good enough for therapy control and need additional magnetic resonance imaging after the ther-apy. The ablation process itself is facing two significant chal-lenges: Firstly insufficient tumor ablation, which leads to tumor recurrence. Secondary, total ablated area was significantly larger than the tumor size which causes damaging of healthy tissue. To minimize the impact, it is crucial for the radiologist to perform the therapy well to prevent tumor recurrence. Therefore, it is essential to differentiate among healthy, tumor, and ablated tissue textures in the CT scan images. This research contributes to the understanding of tissue characterization for the reduction of the recurrence rate. In this regard, four machine-learning (ML) algorithms of Naive-Bayesian, Logistic-Regression, Decision-Tree, and Random-Forest were employed for liver tissues classification. In this paper, we propose higher order spectral particularly bispectrum analysis for extracting features from the CT images. Then classifiers were trained by ten new features extracted from the bispectrum analysis. For that, the images were divided into small patches, they were labeled as healthy, tumor, and ablated tissue. A maximum accuracy of 90.5% was obtained. The approach shows that the bispectral analysis provides valuable information that can be used during the MWA therapy for tissue characterization of CT scan even in the presence of noise.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130110989","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00041
A. H. Syed, Tabrej Khan
Efficient screening of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) enables quick and efficient diagnosis of SARS-CoV-2 and can mitigate the burden on healthcare systems. The aim was to assist the medical team globally in triaging incoming patients, especially in countries with limited healthcare infrastructure. In this context, the features with imminent infection risk (Test Indication, Fever, and Headache) were obtained using a multi-tree XGBoost algorithm. Based on their feature importance, the top three clinically relevant earlier clinical symptoms (attributes) were employed to create a Multi-tree XGBoost-based model for an earlier prediction of SARS-CoV-2. Overall, our Multi-tree XGBoost model predicted SARS-CoV-2 infection status with a high F1-score (0.9920 $pm boldsymbol{0.008)}$ and AUC value (0. 9974 ± 0.0026) only by assessing the primary three clinical symptoms related to COVID-19 infection. Thus our multi-tree XGBoost - based model suggests a simple and accurate method for earlier detection of SARS-CoV-2 cases and initiating proper treatment protocol for SARS-CoV-2 positive patients. Therefore, we can conclude that our model will allow the health organizations to potentially reduce the infection rate and mortality in masses with COVID-19 infection and fatality due to SARS-CoV-2.
{"title":"A Supervised Multi-tree XGBoost Model for an Earlier COVID-19 Diagnosis Based on Clinical Symptoms","authors":"A. H. Syed, Tabrej Khan","doi":"10.1109/CDMA54072.2022.00041","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00041","url":null,"abstract":"Efficient screening of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) enables quick and efficient diagnosis of SARS-CoV-2 and can mitigate the burden on healthcare systems. The aim was to assist the medical team globally in triaging incoming patients, especially in countries with limited healthcare infrastructure. In this context, the features with imminent infection risk (Test Indication, Fever, and Headache) were obtained using a multi-tree XGBoost algorithm. Based on their feature importance, the top three clinically relevant earlier clinical symptoms (attributes) were employed to create a Multi-tree XGBoost-based model for an earlier prediction of SARS-CoV-2. Overall, our Multi-tree XGBoost model predicted SARS-CoV-2 infection status with a high F1-score (0.9920 $pm boldsymbol{0.008)}$ and AUC value (0. 9974 ± 0.0026) only by assessing the primary three clinical symptoms related to COVID-19 infection. Thus our multi-tree XGBoost - based model suggests a simple and accurate method for earlier detection of SARS-CoV-2 cases and initiating proper treatment protocol for SARS-CoV-2 positive patients. Therefore, we can conclude that our model will allow the health organizations to potentially reduce the infection rate and mortality in masses with COVID-19 infection and fatality due to SARS-CoV-2.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127651403","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00024
S. Olatunji, Aisha Alansari, Heba Alkhorasani, Meelaf Alsubaii, Rasha Sakloua, Reem Alzahrani, Yasmeen Alsaleem, Reem A. Alassaf, Mehwash Farooqui, M. I. B. Ahmed
Lung cancer is a malignant disease that im-poses serious complications restricting patients from performing daily tasks in the early stages and eventu-ally cause their death. The prevalence of this disease has been highlighted by numerous statistics worldwide. The preemptive diagnosis of individuals with lung can-cer can enhance chances of prevention and treatment. Therefore, the purpose of this study is to predict lung cancer preemptively utilizing simple clinical and demo-graphical features obtained from the “data world” website. The experiment was conducted using Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Logistic Regression (LR) classifiers. To improve models' accuracy, SMOTETomek was employed along with GridsearchCV to tune hyperparameters. The Re-cursive Feature Elimination method was also utilized to find the best feature subset. Results indicated that SVM achieved the best performance with 98.33% recall, 96.72% precision, and an accuracy of 97.27% using 15 attributes.
{"title":"Machine Learning Based Preemptive Diagnosis of Lung Cancer Using Clinical Data","authors":"S. Olatunji, Aisha Alansari, Heba Alkhorasani, Meelaf Alsubaii, Rasha Sakloua, Reem Alzahrani, Yasmeen Alsaleem, Reem A. Alassaf, Mehwash Farooqui, M. I. B. Ahmed","doi":"10.1109/CDMA54072.2022.00024","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00024","url":null,"abstract":"Lung cancer is a malignant disease that im-poses serious complications restricting patients from performing daily tasks in the early stages and eventu-ally cause their death. The prevalence of this disease has been highlighted by numerous statistics worldwide. The preemptive diagnosis of individuals with lung can-cer can enhance chances of prevention and treatment. Therefore, the purpose of this study is to predict lung cancer preemptively utilizing simple clinical and demo-graphical features obtained from the “data world” website. The experiment was conducted using Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Logistic Regression (LR) classifiers. To improve models' accuracy, SMOTETomek was employed along with GridsearchCV to tune hyperparameters. The Re-cursive Feature Elimination method was also utilized to find the best feature subset. Results indicated that SVM achieved the best performance with 98.33% recall, 96.72% precision, and an accuracy of 97.27% using 15 attributes.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115997576","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00026
Basem Assiri, M. Bashraheel, Ala Alsuri
The advancement of technology contributes in the development of many field of life. One of the major fields to focus on is the field of higher education. Actually, Saudi's universities provide free education to the students, so large number of students apply to the universities. In response to that, universities usually maintain admission policies. Universities' admission policies and procedures focus on students Grade Point Average in high school (GPAH), General Aptitude Test (GAT) and Achievement Test (AT). In fact, guiding students to the suitable major improves students' achievements and success. This paper studies the admission criteria for universities in Saudi Arabia. This paper investigates the hidden details that lies behind students' GP AH, GAT and AT. Those details influence the process of students' major selection at universities. Indeed, this research uses machine learning models to include more features such as the grades of high school courses to predict the suitable majors for the students. We use K-Nearest Neighbor (KNN), Decision Tree (DT) and Support Vector Machine (SVM) to classify students into suitable majors. This process enhances the enrollments of applicants in appropriate majors. Furthermore, the experiments show that KNN gives the highest accuracy rate as it reaches 100%, while DT's accuracy rate is 81 % and SVM's accuracy rate is 75%.
{"title":"Improve the Accuracy of Students Admission at Universities Using Machine Learning Techniques","authors":"Basem Assiri, M. Bashraheel, Ala Alsuri","doi":"10.1109/CDMA54072.2022.00026","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00026","url":null,"abstract":"The advancement of technology contributes in the development of many field of life. One of the major fields to focus on is the field of higher education. Actually, Saudi's universities provide free education to the students, so large number of students apply to the universities. In response to that, universities usually maintain admission policies. Universities' admission policies and procedures focus on students Grade Point Average in high school (GPAH), General Aptitude Test (GAT) and Achievement Test (AT). In fact, guiding students to the suitable major improves students' achievements and success. This paper studies the admission criteria for universities in Saudi Arabia. This paper investigates the hidden details that lies behind students' GP AH, GAT and AT. Those details influence the process of students' major selection at universities. Indeed, this research uses machine learning models to include more features such as the grades of high school courses to predict the suitable majors for the students. We use K-Nearest Neighbor (KNN), Decision Tree (DT) and Support Vector Machine (SVM) to classify students into suitable majors. This process enhances the enrollments of applicants in appropriate majors. Furthermore, the experiments show that KNN gives the highest accuracy rate as it reaches 100%, while DT's accuracy rate is 81 % and SVM's accuracy rate is 75%.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128002484","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00036
J. G, A. Azar, B. Qureshi, Nashwa Ahmad Kamal
For visually impaired persons, it is quite difficult to read printed text. Non-visual forms of reading materials, such as Braille, are available as Blind Aiding Technology amoung many others. In recent times, many devices and assistive equipment have been developed and technologies made available to assist visually impaired persons with reading. Most of these research works and products support reading from printed text-based manuscripts only. Due to this limitation, it may not be possible for a visually impaired person to describe and comprehend a printed image. In this paper, we develop iReader, an Intelligent Reader system that not only helps a visually impaired reader to read but also vocally describes an image available in the printed text. The Convolution Neural Network (CNN) is employed to collect features from the printed image and its caption. The Long Short- Term Memory (LSTM) network is used to train the model for describing the image data. The resulting data is sent as a voice message using Text- To-Speech to be read out loud to the user. The efficiency of the LSTM model is examined using the ResNet50 and VGG16. The experimental results show that the LSTM-based training model delivers the best prediction of a picture's description with an accuracy of 83
{"title":"iReader: An Intelligent Reader System for the Visually Impaired","authors":"J. G, A. Azar, B. Qureshi, Nashwa Ahmad Kamal","doi":"10.1109/CDMA54072.2022.00036","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00036","url":null,"abstract":"For visually impaired persons, it is quite difficult to read printed text. Non-visual forms of reading materials, such as Braille, are available as Blind Aiding Technology amoung many others. In recent times, many devices and assistive equipment have been developed and technologies made available to assist visually impaired persons with reading. Most of these research works and products support reading from printed text-based manuscripts only. Due to this limitation, it may not be possible for a visually impaired person to describe and comprehend a printed image. In this paper, we develop iReader, an Intelligent Reader system that not only helps a visually impaired reader to read but also vocally describes an image available in the printed text. The Convolution Neural Network (CNN) is employed to collect features from the printed image and its caption. The Long Short- Term Memory (LSTM) network is used to train the model for describing the image data. The resulting data is sent as a voice message using Text- To-Speech to be read out loud to the user. The efficiency of the LSTM model is examined using the ResNet50 and VGG16. The experimental results show that the LSTM-based training model delivers the best prediction of a picture's description with an accuracy of 83","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"25 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133650869","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00027
Wajdi Aljedaani, Mohamed Wiem Mkaouer, S. Ludi, Yasir Javed
In recent years, mobile applications have gained popularity for providing information, digital services, and content to users including users with disabilities. However, recent studies have shown that even popular mobile apps are facing issues related to accessibility, which hinders their usability experience for people with disabilities. For discovering these issues in the new app releases, developers consider user reviews published on the official app stores. However, it is a challenging and time-consuming task to identify the type of accessibility-related reviews manually. Therefore, in this study, we have used super-vised learning techniques, namely, Extra Tree Classifier (ETC), Random Forest, Support Vector Classification, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression for automated classification of 2,663 Android app reviews based on four types of accessibility guidelines, i.e., Principles, Audio/Images, Design and Focus. Results have shown that the ETC classifier produces the best results in the automated classification of accessibility app reviews with 93% accuracy.
{"title":"Automatic Classification of Accessibility User Reviews in Android Apps","authors":"Wajdi Aljedaani, Mohamed Wiem Mkaouer, S. Ludi, Yasir Javed","doi":"10.1109/CDMA54072.2022.00027","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00027","url":null,"abstract":"In recent years, mobile applications have gained popularity for providing information, digital services, and content to users including users with disabilities. However, recent studies have shown that even popular mobile apps are facing issues related to accessibility, which hinders their usability experience for people with disabilities. For discovering these issues in the new app releases, developers consider user reviews published on the official app stores. However, it is a challenging and time-consuming task to identify the type of accessibility-related reviews manually. Therefore, in this study, we have used super-vised learning techniques, namely, Extra Tree Classifier (ETC), Random Forest, Support Vector Classification, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression for automated classification of 2,663 Android app reviews based on four types of accessibility guidelines, i.e., Principles, Audio/Images, Design and Focus. Results have shown that the ETC classifier produces the best results in the automated classification of accessibility app reviews with 93% accuracy.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132274150","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00034
M. Aljabri, Samiha Mirza
Because of the fast expansion of internet users, phishing attacks have become a significant menace where the attacker poses as a trusted entity in order to steal sensitive data, causing reputational damage, loss of money, ransomware, or other malware infections. Intelligent techniques mainly Machine Learning (ML) and Deep Learning (D L) are increasingly applied in the field of cybersecurity due to their ability to learn from available data in order to extract useful insight and predict future events. The effectiveness of applying such intelligent approaches in detecting phishing web sites is investigated in this paper. We used two separate datasets and selected the highest correlated features which comprised of a combination of content-based, URL lexical-based, and domain-based features. A set of ML models were then applied, and a comparative performance evaluation was conducted. Results proved the importance of features selection in improving the models' performance. Furthermore, the results also aimed to identify the best features that influence the model in identifying phishing websites. For classification performance, Random Forest (RF) algorithm achieved the highest accuracy for both datasets.
{"title":"Phishing Attacks Detection using Machine Learning and Deep Learning Models","authors":"M. Aljabri, Samiha Mirza","doi":"10.1109/CDMA54072.2022.00034","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00034","url":null,"abstract":"Because of the fast expansion of internet users, phishing attacks have become a significant menace where the attacker poses as a trusted entity in order to steal sensitive data, causing reputational damage, loss of money, ransomware, or other malware infections. Intelligent techniques mainly Machine Learning (ML) and Deep Learning (D L) are increasingly applied in the field of cybersecurity due to their ability to learn from available data in order to extract useful insight and predict future events. The effectiveness of applying such intelligent approaches in detecting phishing web sites is investigated in this paper. We used two separate datasets and selected the highest correlated features which comprised of a combination of content-based, URL lexical-based, and domain-based features. A set of ML models were then applied, and a comparative performance evaluation was conducted. Results proved the importance of features selection in improving the models' performance. Furthermore, the results also aimed to identify the best features that influence the model in identifying phishing websites. For classification performance, Random Forest (RF) algorithm achieved the highest accuracy for both datasets.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116640498","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：