Glioma grading is vital for therapeutic planning where the higher level of glioma is associated w... more Glioma grading is vital for therapeutic planning where the higher level of glioma is associated with high mortality. It is a challenging task as different glioma grades have mixed morphological characteristics of brain tumour. A computeraided diagnosis (CAD) system based on three-dimensional textural grey level co-occurrence matrix (GLCM) and machine learning is proposed for glioma grading. The purpose of this paper is to assess the usefulness of the 3D textural analysis in establishing a malignancy prediction model for glioma grades. Furthermore, this paper aims to find the best classification model based on textural analysis for glioma grading. The classification system was evaluated using leave-one-out cross-validation technique. The experimental design includes feature extraction, feature selection, and finally the classification that includes single and ensemble classification models in a comparative study. Experimental results illustrate that single and ensemble classification models, can achieve efficient prediction performance based on 3D textural analysis and the classification accuracy result has significantly improved after using feature selection methods. In this paper, we compare the proficiency of applying different angles of 3D textural analysis and different classification models to determine the malignant level of glioma. The obtained sensitivity, accuracy and specificity are 100%, 96.6%, 90% respectively. The prediction system presents an effective approach to assess the malignancy level of glioma with a non-invasive, reproducible and accurate CAD system for glioma grading.
Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rule... more Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rules and conditions set by banks and financial institutions. The plight yields to the growth in popularity of online peer-to-peer lending platforms which are an easier way to obtain loan as they have fewer rigid rules. However, high flexibility of loan funding in peer-to-peer lending comes with high default probability of loan funded to high-risk start-ups. An efficient model for evaluating credit risk of borrowers in peer-to-peer lending platforms is important to encourage investors to fund loans and justify the rejection of unsuccessful applications to satisfy financial regulators and increase transparency. This paper presents a supervised machine learning model with logistic regression to address this issue and predicts the probability of default of a loan funded to borrowers through peer-to-peer lending platforms. In addition, factors that affect the credit levels of borrowers are identified and discussed. The research shows that the most important features that affect probability of default are debt-to-income ratio, number of mortgage account, and Fair, Isaac and Company Score.
the preoperative diagnosis of brain Glioma grades is crucial for therapeutic planning as it impac... more the preoperative diagnosis of brain Glioma grades is crucial for therapeutic planning as it impacts on the tumour's prognosis. The development of machine learning methods that can accurately evaluate Glioma grades is of great interest since it is a repeatable and reliable diagnosis procedure. Moreover, the classification accuracy of a single classifier can be further improved by using the ensemble of different classifiers. In this paper, a new strategy has been developed, which uses a deep neural network incorporating an extensive iteration matrix based on the combination of eleven different machine learning algorithms. The classification system is evaluated using a crossvalidation technique, to add more generalization to the results of the classification system's reliability in unseen cases. Experimental results indicate that, when compared to both the single classification model, and the majority vote scheme, the grading accuracy has significantly improved using our proposed approach. The obtained sensitivity, specificity and accuracy are 100%, 90% and 93.3% respectively. The proposed approach has improved upon the highest accuracy of the single classification model by 13.3%. The proposed classification system presents an efficient method to evaluate the malignancy level of Glioma with more reliable and accurate clinical outcomes.
Even though the rise of the Neural Machine Translation (NMT) paradigm has brought a great deal of... more Even though the rise of the Neural Machine Translation (NMT) paradigm has brought a great deal of improvement to the machine translation field, the current translation results are still not perfect. One of the main reasons for this imperfection is the decoding task complexity. Indeed, the problem of finding the one best translation from the space of all possible translations was and still is a challenging problem. One of the most successful ways to address it is via n-best list re-ranking which attempts to reorder the n-best decoder translations according to some defined features. In this paper, we propose a set of new re-ranking features that can be extracted directly from the parallel corpus without needing any external tools. The features set that we propose takes into account lexical, syntactic, and even semantic aspects of the n-best list translations. We also present a method for feature weights optimization that uses a Quantum-behaved Particle Swarm Optimization (QPSO) algorithm. Our system has been evaluated on multiple English-to-Arabic and Arabic-to-English machine translation test sets, and the obtained re-ranking results yield noticeable improvements over the baseline NMT systems.
Ti t l e Ar a bi c m a c hi n e t r a n slit e r a tio n u si n g a n a t t e n tio n-b a s e d e... more Ti t l e Ar a bi c m a c hi n e t r a n slit e r a tio n u si n g a n a t t e n tio n-b a s e d e n c o d e r-d e c o d e r m o d el
International Journal of Intelligent Information Technologies, Oct 1, 2019
There is an abundance of existing biomedical ontologies such as the National Cancer Institute The... more There is an abundance of existing biomedical ontologies such as the National Cancer Institute Thesaurus and the Systematized Nomenclature of Medicine-Clinical Terms. Implementing these ontologiesinaparticularsystemhowever,maycauseunnecessaryhighusageofmemoryandslows downthesystems'performance.Ontheotherhand,buildinganewontologyfromscratchwillrequire additionaltimeandefforts.Therefore,thisresearchexplorestheontologyreuseapproachinorder to develop an Abdominal Ultrasound Ontology by extracting concepts from existing biomedical ontologies.Thisarticlepresentsthereaderwithastepbystepmethodinreusingontologiestogether withsuggestionsoftheoff-the-shelftoolsthatcanbeusedtoeasetheprocess.Theresultsshowthat ontologyreuseisbeneficialespeciallyinthebiomedicalfieldasitallowsfordevelopersfromthenontechnicalbackgroundtobuildandusedomainspecificontologywithease.Italsoallowsfordevelopers withtechnicalbackgroundtodevelopontologieswithminimalinvolvementsfromdomainexperts.
The work reported in this paper is part of a larger study comparing the online activities of Saud... more The work reported in this paper is part of a larger study comparing the online activities of Saudi citizens living in Saudi Arabia and those living in the United Kingdom. That study aims to answer the question of whether the environment plays a key role in influencing the activities of Saudis when purchasing goods and services online. This paper considers only that part of the research conducted in the United Kingdom. It attempts to understand the activities and perception of Business to Customer E-Commerce among Saudis living in the UK, and hence what impact being away from their home environment actually has on their online shopping behaviour. Quantitative data was collected from 169 Saudis living in the United Kingdom. Trust in both security and payment were tested, with the result that a high number of Saudis resident in the UK show trust in the security and payment systems associated with online transactions in the United Kingdom. These primary outcomes suggest that the environment plays an important role in changing the shopping behaviours of online customers.
The results reported in this paper are part of a study comparing the online behaviour of Saudis l... more The results reported in this paper are part of a study comparing the online behaviour of Saudis living in Saudi Arabia (SA) and those living in the United Kingdom (UK). It is acknowledged that culture and the environment play an important role to develop trust in E-Commerce and particularly when providing personal information. Previous studies have shown that this is particularly true for Saudis leaving in Saudi Arabia and this has affected the development of E-Commerce. The current study looks at the behaviour of Saudis living in a different environment and investigates on whether the new environment affects their behaviour. Quantitative data was gathered from 169 Saudi who live in the UK. The factor tested are related to "culture" and composed of 5 personal information and an aggregation of this information for male and females. The early results of this study show that there are some changes that have been noticed in the behaviour of Saudi living in the UK. However, some cultural aspects still remain within the community.
Signal Processing-image Communication, Feb 1, 2019
The digital medical workflow faces many circumstances in which the images can be manipulated duri... more The digital medical workflow faces many circumstances in which the images can be manipulated during viewing, extracting and exchanging. Reversible and imperceptible watermarking approaches have the potential to enhance trust within the medical imaging pipeline through ensuring the authenticity and integrity of the images to confirm that the changes can be detected and tracked. This study concentrates on the imperceptibility issue. Unlike reversibility, for which an objective assessment can be easily made, imperceptibility is a factor of human cognition that needs to be evaluated within the human context. By defining a perceptual boundary of detecting the modification, this study enables the formation of objective guidelines for the method of data encoding and level of image/pixel modification that translates to a specific watermark magnitude. This study implements a relative Visual Grading Analysis (VGA) evaluation of 117 brain MR images (8 original and 109 watermarked), modified by varying techniques and magnitude of image/pixel modification to determine where this perceptual boundary exists and relate the point at which change becomes noticeable to the objective measures of the image fidelity evaluation. The outcomes of the visual assessment were linked to the images Peak Signal to Noise Ratio (PSNR) values, thereby identifying the visual degradation threshold. The results suggest that, for watermarking applications, if a watermark is applied to the 512x512 pixel (16 bpp grayscale) images used in the study, a subsequent assessment of PSNR=82dB or greater would mean that there would be no reason to suspect that the watermark would be visually detectable.
Reversible and imperceptible watermarking is recognized as a robust approach to confirm the integ... more Reversible and imperceptible watermarking is recognized as a robust approach to confirm the integrity and authenticity of medical images and to verify that alterations can be detected and tracked back. In this paper, a novel blind reversible watermarking approach is presented to detect intentional and unintentional changes within brain Magnetic Resonance (MR) images. The scheme segments images into two parts; the Region of Interest (ROI) and the Region of Non Interest (RONI). Watermark data is encoded into the ROI using reversible watermarking based on the Difference Expansion (DE) technique. Experimental results show that the proposed method, whilst fully reversible, can also realize a watermarked image with low degradation for reasonable and controllable embedding capacity. This is fulfilled by concealing the data into 'smooth' regions inside the ROI and through the elimination of the large location map required for extracting the watermark and retrieving the original image. Our scheme delivers highly imperceptible watermarked images, at 92.18-99.94 dB Peak Signal to Noise Ratio (PSNR) evaluated through implementing a clinical trial based on relative Visual Grading Analysis (relative VGA). This trial defines the level of modification that can be applied to medical images without perceptual distortion. This compares favorably to outcomes reported under current state-of-art techniques. Integrity and authenticity of medical images are also ensured through detecting subsequent changes enacted on the watermarked images. This enhanced security measure, therefore, enables the detection of image manipulations, by an imperceptible approach, that may establish increased trust in the digital medical workflow.
Brain tumor segmentation in magnetic resonance imaging (MRI) is considered a complex procedure be... more Brain tumor segmentation in magnetic resonance imaging (MRI) is considered a complex procedure because of the variability of tumor shapes and the complexity of determining the tumor location, size, and texture. Manual tumor segmentation is a time-consuming task highly prone to human error. Hence, this study proposes an automated method that can identify tumor slices and segment the tumor across all image slices in volumetric MRI brain scans. First, a set of algorithms in the pre-processing stage is used to clean and standardize the collected data. A modified gray-level co-occurrence matrix and Analysis of Variance (ANOVA) are employed for feature extraction and feature selection, respectively. A multi-layer perceptron neural network is adopted as a classifier, and a bounding 3D-box-based genetic algorithm is used to identify the location of pathological tissues in the MRI slices. Finally, the 3D active contour without edge is applied to segment the brain tumors in volumetric MRI scans. The experimental dataset consists of 165 patient images collected from the MRI Unit of Al-Kadhimiya Teaching Hospital in Iraq. Results of the tumor segmentation achieved an accuracy of 89% ± 4.7% compared with manual processes.
Fake news are spread on online sites and social media at an alarming speed and in large quantitie... more Fake news are spread on online sites and social media at an alarming speed and in large quantities. Fake news aim to mislead and deceive readers with verifiable false information and they are published on untrusted websites and social media accounts. As they have a very big impact on readers, it is critical to develop efficient models for detecting fake news. This paper reviews the literature on fake news detection and categorizes detection approaches into Knowledge Based approaches and Machine Learning based approaches. Machine Learning based approaches that have been covered in this paper are divided into Conventional approaches and Neural Network approaches. It provides Support Vector Machines (SVMs) and Naïve Bayes for Conventional approaches. In addition to Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for Neural Network approaches. Also, the paper discusses the provided approaches.
Ultrasound reporting plays an important role in diagnosis as images produced during an ultrasound... more Ultrasound reporting plays an important role in diagnosis as images produced during an ultrasound examination do not give the whole view of the medical conditions. However, in practice there are many issues that are inherent to ultrasound reporting and the most important was identified to be the lack of standardisation when producing these reports. There is a resistance to change from some radiologists preferring the free writing style, making any attempt to computerise the processing of these reports difficult. This paper explores the possibility of using Rhetorical Structure Theory (RST) together with a domain ontology to transform free-form ultrasound reports into a structured form. It discusses a new approach in segmenting and identifying rhetorical relations that are more applicable to ultrasound reports from classical RST relations. The approach was evaluated on a sample ultrasound reports where the system's parsing was compared to the manual parsing performed by experts. The results show that discourse parsing using RST in ultrasound reports can be performed effectively using the support of a domain ontology. The results also demonstrate that the transformation of free-form ultrasound reports into a structured form can be performed with the support of RST relations identified and the domain ontology.
Medical imaging technologies have an important role in the care of all human's organs and dis... more Medical imaging technologies have an important role in the care of all human's organs and disease entities, where they are used widely for the effective diagnosis, treatment and monitoring of the disease. The MRI has been among the most important of all these technologies in the care of patients with brain tumors, where the brain tumor is the one of the most common diseases that cause the death. Screening of brain tumors is an essential to significant improvements in the diagnose and reduce the incidence of death, it can only be as successful as the feature extraction techniques it relies on. Many of these techniques have been used, but it is still not exactly clear which of feature extraction techniques ought to be favored. In this paper, we present here the results of a study in which we compare the proficiency of utilizing grey level statistic method and Gabor wavelet method in detecting and recognizing MRI brain abnormality. The framework that serves as our testbed includes med-sagittal plane detection and correction, feature extraction, feature selection, and lastly classification and comparison.
Glioma grading is vital for therapeutic planning where the higher level of glioma is associated w... more Glioma grading is vital for therapeutic planning where the higher level of glioma is associated with high mortality. It is a challenging task as different glioma grades have mixed morphological characteristics of brain tumour. A computeraided diagnosis (CAD) system based on three-dimensional textural grey level co-occurrence matrix (GLCM) and machine learning is proposed for glioma grading. The purpose of this paper is to assess the usefulness of the 3D textural analysis in establishing a malignancy prediction model for glioma grades. Furthermore, this paper aims to find the best classification model based on textural analysis for glioma grading. The classification system was evaluated using leave-one-out cross-validation technique. The experimental design includes feature extraction, feature selection, and finally the classification that includes single and ensemble classification models in a comparative study. Experimental results illustrate that single and ensemble classification models, can achieve efficient prediction performance based on 3D textural analysis and the classification accuracy result has significantly improved after using feature selection methods. In this paper, we compare the proficiency of applying different angles of 3D textural analysis and different classification models to determine the malignant level of glioma. The obtained sensitivity, accuracy and specificity are 100%, 96.6%, 90% respectively. The prediction system presents an effective approach to assess the malignancy level of glioma with a non-invasive, reproducible and accurate CAD system for glioma grading.
Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rule... more Small and medium enterprises face the challenge of obtaining start-up fund due to the strict rules and conditions set by banks and financial institutions. The plight yields to the growth in popularity of online peer-to-peer lending platforms which are an easier way to obtain loan as they have fewer rigid rules. However, high flexibility of loan funding in peer-to-peer lending comes with high default probability of loan funded to high-risk start-ups. An efficient model for evaluating credit risk of borrowers in peer-to-peer lending platforms is important to encourage investors to fund loans and justify the rejection of unsuccessful applications to satisfy financial regulators and increase transparency. This paper presents a supervised machine learning model with logistic regression to address this issue and predicts the probability of default of a loan funded to borrowers through peer-to-peer lending platforms. In addition, factors that affect the credit levels of borrowers are identified and discussed. The research shows that the most important features that affect probability of default are debt-to-income ratio, number of mortgage account, and Fair, Isaac and Company Score.
the preoperative diagnosis of brain Glioma grades is crucial for therapeutic planning as it impac... more the preoperative diagnosis of brain Glioma grades is crucial for therapeutic planning as it impacts on the tumour's prognosis. The development of machine learning methods that can accurately evaluate Glioma grades is of great interest since it is a repeatable and reliable diagnosis procedure. Moreover, the classification accuracy of a single classifier can be further improved by using the ensemble of different classifiers. In this paper, a new strategy has been developed, which uses a deep neural network incorporating an extensive iteration matrix based on the combination of eleven different machine learning algorithms. The classification system is evaluated using a crossvalidation technique, to add more generalization to the results of the classification system's reliability in unseen cases. Experimental results indicate that, when compared to both the single classification model, and the majority vote scheme, the grading accuracy has significantly improved using our proposed approach. The obtained sensitivity, specificity and accuracy are 100%, 90% and 93.3% respectively. The proposed approach has improved upon the highest accuracy of the single classification model by 13.3%. The proposed classification system presents an efficient method to evaluate the malignancy level of Glioma with more reliable and accurate clinical outcomes.
Even though the rise of the Neural Machine Translation (NMT) paradigm has brought a great deal of... more Even though the rise of the Neural Machine Translation (NMT) paradigm has brought a great deal of improvement to the machine translation field, the current translation results are still not perfect. One of the main reasons for this imperfection is the decoding task complexity. Indeed, the problem of finding the one best translation from the space of all possible translations was and still is a challenging problem. One of the most successful ways to address it is via n-best list re-ranking which attempts to reorder the n-best decoder translations according to some defined features. In this paper, we propose a set of new re-ranking features that can be extracted directly from the parallel corpus without needing any external tools. The features set that we propose takes into account lexical, syntactic, and even semantic aspects of the n-best list translations. We also present a method for feature weights optimization that uses a Quantum-behaved Particle Swarm Optimization (QPSO) algorithm. Our system has been evaluated on multiple English-to-Arabic and Arabic-to-English machine translation test sets, and the obtained re-ranking results yield noticeable improvements over the baseline NMT systems.
Ti t l e Ar a bi c m a c hi n e t r a n slit e r a tio n u si n g a n a t t e n tio n-b a s e d e... more Ti t l e Ar a bi c m a c hi n e t r a n slit e r a tio n u si n g a n a t t e n tio n-b a s e d e n c o d e r-d e c o d e r m o d el
International Journal of Intelligent Information Technologies, Oct 1, 2019
There is an abundance of existing biomedical ontologies such as the National Cancer Institute The... more There is an abundance of existing biomedical ontologies such as the National Cancer Institute Thesaurus and the Systematized Nomenclature of Medicine-Clinical Terms. Implementing these ontologiesinaparticularsystemhowever,maycauseunnecessaryhighusageofmemoryandslows downthesystems'performance.Ontheotherhand,buildinganewontologyfromscratchwillrequire additionaltimeandefforts.Therefore,thisresearchexplorestheontologyreuseapproachinorder to develop an Abdominal Ultrasound Ontology by extracting concepts from existing biomedical ontologies.Thisarticlepresentsthereaderwithastepbystepmethodinreusingontologiestogether withsuggestionsoftheoff-the-shelftoolsthatcanbeusedtoeasetheprocess.Theresultsshowthat ontologyreuseisbeneficialespeciallyinthebiomedicalfieldasitallowsfordevelopersfromthenontechnicalbackgroundtobuildandusedomainspecificontologywithease.Italsoallowsfordevelopers withtechnicalbackgroundtodevelopontologieswithminimalinvolvementsfromdomainexperts.
The work reported in this paper is part of a larger study comparing the online activities of Saud... more The work reported in this paper is part of a larger study comparing the online activities of Saudi citizens living in Saudi Arabia and those living in the United Kingdom. That study aims to answer the question of whether the environment plays a key role in influencing the activities of Saudis when purchasing goods and services online. This paper considers only that part of the research conducted in the United Kingdom. It attempts to understand the activities and perception of Business to Customer E-Commerce among Saudis living in the UK, and hence what impact being away from their home environment actually has on their online shopping behaviour. Quantitative data was collected from 169 Saudis living in the United Kingdom. Trust in both security and payment were tested, with the result that a high number of Saudis resident in the UK show trust in the security and payment systems associated with online transactions in the United Kingdom. These primary outcomes suggest that the environment plays an important role in changing the shopping behaviours of online customers.
The results reported in this paper are part of a study comparing the online behaviour of Saudis l... more The results reported in this paper are part of a study comparing the online behaviour of Saudis living in Saudi Arabia (SA) and those living in the United Kingdom (UK). It is acknowledged that culture and the environment play an important role to develop trust in E-Commerce and particularly when providing personal information. Previous studies have shown that this is particularly true for Saudis leaving in Saudi Arabia and this has affected the development of E-Commerce. The current study looks at the behaviour of Saudis living in a different environment and investigates on whether the new environment affects their behaviour. Quantitative data was gathered from 169 Saudi who live in the UK. The factor tested are related to "culture" and composed of 5 personal information and an aggregation of this information for male and females. The early results of this study show that there are some changes that have been noticed in the behaviour of Saudi living in the UK. However, some cultural aspects still remain within the community.
Signal Processing-image Communication, Feb 1, 2019
The digital medical workflow faces many circumstances in which the images can be manipulated duri... more The digital medical workflow faces many circumstances in which the images can be manipulated during viewing, extracting and exchanging. Reversible and imperceptible watermarking approaches have the potential to enhance trust within the medical imaging pipeline through ensuring the authenticity and integrity of the images to confirm that the changes can be detected and tracked. This study concentrates on the imperceptibility issue. Unlike reversibility, for which an objective assessment can be easily made, imperceptibility is a factor of human cognition that needs to be evaluated within the human context. By defining a perceptual boundary of detecting the modification, this study enables the formation of objective guidelines for the method of data encoding and level of image/pixel modification that translates to a specific watermark magnitude. This study implements a relative Visual Grading Analysis (VGA) evaluation of 117 brain MR images (8 original and 109 watermarked), modified by varying techniques and magnitude of image/pixel modification to determine where this perceptual boundary exists and relate the point at which change becomes noticeable to the objective measures of the image fidelity evaluation. The outcomes of the visual assessment were linked to the images Peak Signal to Noise Ratio (PSNR) values, thereby identifying the visual degradation threshold. The results suggest that, for watermarking applications, if a watermark is applied to the 512x512 pixel (16 bpp grayscale) images used in the study, a subsequent assessment of PSNR=82dB or greater would mean that there would be no reason to suspect that the watermark would be visually detectable.
Reversible and imperceptible watermarking is recognized as a robust approach to confirm the integ... more Reversible and imperceptible watermarking is recognized as a robust approach to confirm the integrity and authenticity of medical images and to verify that alterations can be detected and tracked back. In this paper, a novel blind reversible watermarking approach is presented to detect intentional and unintentional changes within brain Magnetic Resonance (MR) images. The scheme segments images into two parts; the Region of Interest (ROI) and the Region of Non Interest (RONI). Watermark data is encoded into the ROI using reversible watermarking based on the Difference Expansion (DE) technique. Experimental results show that the proposed method, whilst fully reversible, can also realize a watermarked image with low degradation for reasonable and controllable embedding capacity. This is fulfilled by concealing the data into 'smooth' regions inside the ROI and through the elimination of the large location map required for extracting the watermark and retrieving the original image. Our scheme delivers highly imperceptible watermarked images, at 92.18-99.94 dB Peak Signal to Noise Ratio (PSNR) evaluated through implementing a clinical trial based on relative Visual Grading Analysis (relative VGA). This trial defines the level of modification that can be applied to medical images without perceptual distortion. This compares favorably to outcomes reported under current state-of-art techniques. Integrity and authenticity of medical images are also ensured through detecting subsequent changes enacted on the watermarked images. This enhanced security measure, therefore, enables the detection of image manipulations, by an imperceptible approach, that may establish increased trust in the digital medical workflow.
Brain tumor segmentation in magnetic resonance imaging (MRI) is considered a complex procedure be... more Brain tumor segmentation in magnetic resonance imaging (MRI) is considered a complex procedure because of the variability of tumor shapes and the complexity of determining the tumor location, size, and texture. Manual tumor segmentation is a time-consuming task highly prone to human error. Hence, this study proposes an automated method that can identify tumor slices and segment the tumor across all image slices in volumetric MRI brain scans. First, a set of algorithms in the pre-processing stage is used to clean and standardize the collected data. A modified gray-level co-occurrence matrix and Analysis of Variance (ANOVA) are employed for feature extraction and feature selection, respectively. A multi-layer perceptron neural network is adopted as a classifier, and a bounding 3D-box-based genetic algorithm is used to identify the location of pathological tissues in the MRI slices. Finally, the 3D active contour without edge is applied to segment the brain tumors in volumetric MRI scans. The experimental dataset consists of 165 patient images collected from the MRI Unit of Al-Kadhimiya Teaching Hospital in Iraq. Results of the tumor segmentation achieved an accuracy of 89% ± 4.7% compared with manual processes.
Fake news are spread on online sites and social media at an alarming speed and in large quantitie... more Fake news are spread on online sites and social media at an alarming speed and in large quantities. Fake news aim to mislead and deceive readers with verifiable false information and they are published on untrusted websites and social media accounts. As they have a very big impact on readers, it is critical to develop efficient models for detecting fake news. This paper reviews the literature on fake news detection and categorizes detection approaches into Knowledge Based approaches and Machine Learning based approaches. Machine Learning based approaches that have been covered in this paper are divided into Conventional approaches and Neural Network approaches. It provides Support Vector Machines (SVMs) and Naïve Bayes for Conventional approaches. In addition to Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for Neural Network approaches. Also, the paper discusses the provided approaches.
Ultrasound reporting plays an important role in diagnosis as images produced during an ultrasound... more Ultrasound reporting plays an important role in diagnosis as images produced during an ultrasound examination do not give the whole view of the medical conditions. However, in practice there are many issues that are inherent to ultrasound reporting and the most important was identified to be the lack of standardisation when producing these reports. There is a resistance to change from some radiologists preferring the free writing style, making any attempt to computerise the processing of these reports difficult. This paper explores the possibility of using Rhetorical Structure Theory (RST) together with a domain ontology to transform free-form ultrasound reports into a structured form. It discusses a new approach in segmenting and identifying rhetorical relations that are more applicable to ultrasound reports from classical RST relations. The approach was evaluated on a sample ultrasound reports where the system's parsing was compared to the manual parsing performed by experts. The results show that discourse parsing using RST in ultrasound reports can be performed effectively using the support of a domain ontology. The results also demonstrate that the transformation of free-form ultrasound reports into a structured form can be performed with the support of RST relations identified and the domain ontology.
Medical imaging technologies have an important role in the care of all human's organs and dis... more Medical imaging technologies have an important role in the care of all human's organs and disease entities, where they are used widely for the effective diagnosis, treatment and monitoring of the disease. The MRI has been among the most important of all these technologies in the care of patients with brain tumors, where the brain tumor is the one of the most common diseases that cause the death. Screening of brain tumors is an essential to significant improvements in the diagnose and reduce the incidence of death, it can only be as successful as the feature extraction techniques it relies on. Many of these techniques have been used, but it is still not exactly clear which of feature extraction techniques ought to be favored. In this paper, we present here the results of a study in which we compare the proficiency of utilizing grey level statistic method and Gabor wavelet method in detecting and recognizing MRI brain abnormality. The framework that serves as our testbed includes med-sagittal plane detection and correction, feature extraction, feature selection, and lastly classification and comparison.
Uploads
Papers by Farid Meziane