Skip to main content

Ammar Amjad

Followers

4

Following

1

Public Views

Noel B. Salazar

KU Leuven

University of Alicante / Universidad de Alicante

Armando Marques-Guedes

UNL - New University of Lisbon

The University of Queensland, Australia

SFS Qatar (Georgetown University)

Carmen Gonzalez

Loyola University Chicago

Polytechnic Institute of Leiria

Derek H Alderman

University of Tennessee Knoxville

University of Wisconsin-Madison

University of California, Los Angeles

Interests

Uploads

Papers by Ammar Amjad

Use of an Endobronchial Blocker Where a Double-Lumen Tube Failed to Ventilate: A Case Report of a Distorted Tracheobronchial Anatomy

Cureus, Nov 30, 2022

One-lung ventilation (OLV) during video-assisted thoracoscopic surgery (VATS) can be accomplished... more One-lung ventilation (OLV) during video-assisted thoracoscopic surgery (VATS) can be accomplished through several different techniques, including bronchial advancement of an endotracheal tube (ETT), use of a double-lumen tube (DLT), or placement of an endobronchial blocker. In most cases, a DLT is a mainstay of isolating and ventilating a single lung during cardiothoracic procedures. The reasons to deploy a DLT over other techniques include ease of placement, less chance of malposition, quick placement time, and quality of lung deflation. However, this case report highlights the importance of a bronchial blocker in a patient where a double-lumen tube failed to ventilate the lungs. Briefly, this young female patient had a right thoracic mass associated with ipsilateral lung collapse and moderate pleural effusion. CT-guided biopsy was planned but was deferred by the radiologist, as the patient was unable to lie in a prone position. The case was then referred to the cardiothoracic surgeon who planned a right VATS and biopsy of the lesion. In the operation theater, after induction of anesthesia, the patient could not be ventilated through a DLT, and high peak airway pressures were encountered. Initially, a size 37 left-sided DLT was used, and subsequently, sizes 35, 32, and 28 were also tried, but all these attempts to ventilate the patient remained futile. A bronchoscopy was done, which did not show any abnormality in the airway. The surgery was postponed due to an inability to ventilate the patient with a double-lumen tube. After a repeat CT scan and draining of 9.3 liters of pleural effusion over a week, the patient was again scheduled for the same procedure but with a changed anesthetic plan. This time around, the anesthetic plan was implemented successfully using a bronchial blocker to isolate the right lung. The surgery went ahead, and the patient had an uneventful postoperative period. The anesthetic management of this patient presented a unique set of challenges, which are shared in this case report.

Comparison of Recurrence of High Trans-Sphinteric Anal Fistula After Vaaft and Tight Setons in Military Hospital Rawalpindi

Pakistan Armed Forces Medical Journal

Objective: To compare the recurrence rate in patients undergoing fistulectomy using tight setons ... more Objective: To compare the recurrence rate in patients undergoing fistulectomy using tight setons with those using videoassisted anal fistula treatment (VAAFT). Study Design: Comparative prospective study. Place and Duration of Study: Department of General Surgery, MH Rawalpindi, Pakistan from May 2018 to Dec 2021. Methodology: We included 200 patients with high trans-sphincteric anal fistula (simple or complex) of age 18 to 60 years, having ASA I or II. Group- A comprised patients undergoing treatment with VAAFT, while Group- B included patients undergoing treatment with Tight Seton in conventional surgery. Patients were followed for three months after the procedure. Patients having a history of discharge around or in the vicinity of the previous external opening of the anal fistula were labelled as having a recurrence. Recurrence was confirmed on MRI Fistulogram. Results: The mean age of patients in Group-A was 42.10±8.26 years, and in Group-B was 42.17±7.91 years (p=0.95). There w...

Dynamic Fire and Smoke Detection Module with Enhanced Feature Integration and Attention Mechanisms

Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition

PeerJ Computer Science

Speech emotion recognition (SER) systems have evolved into an important method for recognizing a ... more Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to prov...

Multi-class sentiment analysis of urdu text using multilingual BERT

Scientific Reports, 2022

Sentiment analysis (SA) is an important task because of its vital role in analyzing people’s opin... more Sentiment analysis (SA) is an important task because of its vital role in analyzing people’s opinions. However, existing research is solely based on the English language with limited work on low-resource languages. This study introduced a new multi-class Urdu dataset based on user reviews for sentiment analysis. This dataset is gathered from various domains such as food and beverages, movies and plays, software and apps, politics, and sports. Our proposed dataset contains 9312 reviews manually annotated by human experts into three classes: positive, negative and neutral. The main goal of this research study is to create a manually annotated dataset for Urdu sentiment analysis and to set baseline results using rule-based, machine learning (SVM, NB, Adabbost, MLP, LR and RF) and deep learning (CNN-1D, LSTM, Bi-LSTM, GRU and Bi-GRU) techniques. Additionally, we fine-tuned Multilingual BERT(mBERT) for Urdu sentiment analysis. We used four text representations: word n-grams, char n-grams...

Semi-Natural and Spontaneous Speech Recognition Using Deep Neural Networks with Hybrid Features Unification

Processes, 2021

Recently, identifying speech emotions in a spontaneous database has been a complex and demanding ... more Recently, identifying speech emotions in a spontaneous database has been a complex and demanding study area. This research presents an entirely new approach for recognizing semi-natural and spontaneous speech emotions with multiple feature fusion and deep neural networks (DNN). A proposed framework extracts the most discriminative features from hybrid acoustic feature sets. However, these feature sets may contain duplicate and irrelevant information, leading to inadequate emotional identification. Therefore, an support vector machine (SVM) algorithm is utilized to identify the most discriminative audio feature map after obtaining the relevant features learned by the fusion approach. We investigated our approach utilizing the eNTERFACE05 and BAUM-1s benchmark databases and observed a significant identification accuracy of 76% for a speaker-independent experiment with SVM and 59% accuracy with, respectively. Furthermore, experiments on the eNTERFACE05 and BAUM-1s dataset indicate that...

Deep Sentiment Analysis Using CNN-LSTM Architecture of English and Roman Urdu Text Shared in Social Media

Applied Sciences, 2022

Sentiment analysis (SA) has been an active research subject in the domain of natural language pro... more Sentiment analysis (SA) has been an active research subject in the domain of natural language processing due to its important functions in interpreting people’s perspectives and drawing successful opinion-based judgments. On social media, Roman Urdu is one of the most extensively utilized dialects. Sentiment analysis of Roman Urdu is difficult due to its morphological complexities and varied dialects. The purpose of this paper is to evaluate the performance of various word embeddings for Roman Urdu and English dialects using the CNN-LSTM architecture with traditional machine learning classifiers. We introduce a novel deep learning architecture for Roman Urdu and English dialect SA based on two layers: LSTM for long-term dependency preservation and a one-layer CNN model for local feature extraction. To obtain the final classification, the feature maps learned by CNN and LSTM are fed to several machine learning classifiers. Various word embedding models support this concept. Extensive...

Recognizing Semi-Natural and Spontaneous Speech Emotions Using Deep Neural Networks

IEEE Access

This work was supported by the Chang Gung Memorial Hospital under Grant CMRPD2J0023.

Resuscitation Council UK Guidelines 2021' -a short commentary

New Resuscitation guidelines have been published this year by Resuscitation Council UK (RCUK). It... more

Urdu Corpus Sentiment Analysis

DATASET STATISTICS

Eye in-painting using WGAN-GP for face images with mosaic

In order to protect personal privacy, news reports often use the mosaics upon the face of the pro... more In order to protect personal privacy, news reports often use the mosaics upon the face of the protagonist in the photo. However, readers will feel uncomfortable and awkward to this kind of photos. In this research, we detect the eye mosaic and try to use eye complementing which is not the same with original picture but matches the nearby texture. It can arouse readers' interest in reading. Traditional in-painting research is not suitable for filling special or large objects, such as eyes or boxes on the ground. They only can fill a small area of missing parts or a single background refer to nearby textures, such as landscape photos. We use WGAN-GP that can refer to nearby textures to generate special objects for in-painting eyes. We also divide the training set into male and female according to gender to avoid eye makeup appearing in all pictures. The experiment result shows our method get higher score in blind testing.

Effect on speech emotion classification of a feature selection approach using a convolutional neural network

PeerJ Computer Science

Speech emotion recognition (SER) is a challenging issue because it is not clear which features ar... more Speech emotion recognition (SER) is a challenging issue because it is not clear which features are effective for classification. Emotionally related features are always extracted from speech signals for emotional classification. Handcrafted features are mainly used for emotional identification from audio signals. However, these features are not sufficient to correctly identify the emotional state of the speaker. The advantages of a deep convolutional neural network (DCNN) are investigated in the proposed work. A pretrained framework is used to extract the features from speech emotion databases. In this work, we adopt the feature selection (FS) approach to find the discriminative and most important features for SER. Many algorithms are used for the emotion classification problem. We use the random forest (RF), decision tree (DT), support vector machine (SVM), multilayer perceptron classifier (MLP), and k-nearest neighbors (KNN) to classify seven emotions. All experiments are performe...

Urdu Sentiment Analysis With Deep Learning Methods

IEEE Access

Although over 169 million people in the world are familiar with the Urdu language and a large qua... more Although over 169 million people in the world are familiar with the Urdu language and a large quantity of Urdu data is being generated on different social websites daily, very few research studies and efforts have been completed to build language resources for the Urdu language and examine user sentiments. The primary objective of this study is twofold: (1) develop a benchmark dataset for resource-deprived Urdu language for sentiment analysis and (2) evaluate various machine and deep learning algorithms for sentiment. To find the best technique, we compare two modes of text representation: count-based, where the text is represented using word n-gram feature vectors and the second one is based on fastText pre-trained word embeddings for Urdu. We consider a set of machine learning classifiers (RF, NB, SVM, AdaBoost, MLP, LR) and deep leaning classifiers (1D-CNN and LSTM) to run the experiments for all the feature types. Our study shows that the combination of word n-gram features with LR outperformed other classifiers for sentiment analysis task, obtaining the highest F 1 score of 82.05% using combination of features. INDEX TERMS Urdu sentiment analysis, machine learning, deep learning, natural language processing.

Clicksafe: Providing Security against Clickjacking Attacks

2014 IEEE 15th International Symposium on High-Assurance Systems Engineering, 2014

ABSTRACT Click jacking is an act of hijacking user clicks in order to perform undesired actions w... more ABSTRACT Click jacking is an act of hijacking user clicks in order to perform undesired actions which are beneficial for the attacker. We propose Click safe, a browser-based tool to provide increased security and reliability against click jacking attacks. Click safe is based on three major components. The detection unit detects malicious components in a web page that redirect users to external links. The mitigation unit provides interception of user clicks and give educated warnings to users who can then choose to continue or not. Click safe also incorporate a feedback unit which records the user&#39;s actions, converts them into ratings and allows future interactions to be more informed. Click safe is predominant from other similar tools as the detection and mitigation is based on a comprehensive framework which utilizes detection of malicious web components and incorporating user feedback. We explain the mechanism of click safe, describes its performance, and highlights its potential in providing safety against click jacking to a large number of users

Use of an Endobronchial Blocker Where a Double-Lumen Tube Failed to Ventilate: A Case Report of a Distorted Tracheobronchial Anatomy

Cureus, Nov 30, 2022

One-lung ventilation (OLV) during video-assisted thoracoscopic surgery (VATS) can be accomplished... more One-lung ventilation (OLV) during video-assisted thoracoscopic surgery (VATS) can be accomplished through several different techniques, including bronchial advancement of an endotracheal tube (ETT), use of a double-lumen tube (DLT), or placement of an endobronchial blocker. In most cases, a DLT is a mainstay of isolating and ventilating a single lung during cardiothoracic procedures. The reasons to deploy a DLT over other techniques include ease of placement, less chance of malposition, quick placement time, and quality of lung deflation. However, this case report highlights the importance of a bronchial blocker in a patient where a double-lumen tube failed to ventilate the lungs. Briefly, this young female patient had a right thoracic mass associated with ipsilateral lung collapse and moderate pleural effusion. CT-guided biopsy was planned but was deferred by the radiologist, as the patient was unable to lie in a prone position. The case was then referred to the cardiothoracic surgeon who planned a right VATS and biopsy of the lesion. In the operation theater, after induction of anesthesia, the patient could not be ventilated through a DLT, and high peak airway pressures were encountered. Initially, a size 37 left-sided DLT was used, and subsequently, sizes 35, 32, and 28 were also tried, but all these attempts to ventilate the patient remained futile. A bronchoscopy was done, which did not show any abnormality in the airway. The surgery was postponed due to an inability to ventilate the patient with a double-lumen tube. After a repeat CT scan and draining of 9.3 liters of pleural effusion over a week, the patient was again scheduled for the same procedure but with a changed anesthetic plan. This time around, the anesthetic plan was implemented successfully using a bronchial blocker to isolate the right lung. The surgery went ahead, and the patient had an uneventful postoperative period. The anesthetic management of this patient presented a unique set of challenges, which are shared in this case report.

Comparison of Recurrence of High Trans-Sphinteric Anal Fistula After Vaaft and Tight Setons in Military Hospital Rawalpindi

Pakistan Armed Forces Medical Journal

Objective: To compare the recurrence rate in patients undergoing fistulectomy using tight setons ... more Objective: To compare the recurrence rate in patients undergoing fistulectomy using tight setons with those using videoassisted anal fistula treatment (VAAFT). Study Design: Comparative prospective study. Place and Duration of Study: Department of General Surgery, MH Rawalpindi, Pakistan from May 2018 to Dec 2021. Methodology: We included 200 patients with high trans-sphincteric anal fistula (simple or complex) of age 18 to 60 years, having ASA I or II. Group- A comprised patients undergoing treatment with VAAFT, while Group- B included patients undergoing treatment with Tight Seton in conventional surgery. Patients were followed for three months after the procedure. Patients having a history of discharge around or in the vicinity of the previous external opening of the anal fistula were labelled as having a recurrence. Recurrence was confirmed on MRI Fistulogram. Results: The mean age of patients in Group-A was 42.10±8.26 years, and in Group-B was 42.17±7.91 years (p=0.95). There w...

Dynamic Fire and Smoke Detection Module with Enhanced Feature Integration and Attention Mechanisms

Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition

PeerJ Computer Science

Speech emotion recognition (SER) systems have evolved into an important method for recognizing a ... more Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system’s efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to prov...

Multi-class sentiment analysis of urdu text using multilingual BERT

Scientific Reports, 2022

Sentiment analysis (SA) is an important task because of its vital role in analyzing people’s opin... more Sentiment analysis (SA) is an important task because of its vital role in analyzing people’s opinions. However, existing research is solely based on the English language with limited work on low-resource languages. This study introduced a new multi-class Urdu dataset based on user reviews for sentiment analysis. This dataset is gathered from various domains such as food and beverages, movies and plays, software and apps, politics, and sports. Our proposed dataset contains 9312 reviews manually annotated by human experts into three classes: positive, negative and neutral. The main goal of this research study is to create a manually annotated dataset for Urdu sentiment analysis and to set baseline results using rule-based, machine learning (SVM, NB, Adabbost, MLP, LR and RF) and deep learning (CNN-1D, LSTM, Bi-LSTM, GRU and Bi-GRU) techniques. Additionally, we fine-tuned Multilingual BERT(mBERT) for Urdu sentiment analysis. We used four text representations: word n-grams, char n-grams...

Semi-Natural and Spontaneous Speech Recognition Using Deep Neural Networks with Hybrid Features Unification

Processes, 2021

Recently, identifying speech emotions in a spontaneous database has been a complex and demanding ... more Recently, identifying speech emotions in a spontaneous database has been a complex and demanding study area. This research presents an entirely new approach for recognizing semi-natural and spontaneous speech emotions with multiple feature fusion and deep neural networks (DNN). A proposed framework extracts the most discriminative features from hybrid acoustic feature sets. However, these feature sets may contain duplicate and irrelevant information, leading to inadequate emotional identification. Therefore, an support vector machine (SVM) algorithm is utilized to identify the most discriminative audio feature map after obtaining the relevant features learned by the fusion approach. We investigated our approach utilizing the eNTERFACE05 and BAUM-1s benchmark databases and observed a significant identification accuracy of 76% for a speaker-independent experiment with SVM and 59% accuracy with, respectively. Furthermore, experiments on the eNTERFACE05 and BAUM-1s dataset indicate that...

Deep Sentiment Analysis Using CNN-LSTM Architecture of English and Roman Urdu Text Shared in Social Media

Applied Sciences, 2022

Sentiment analysis (SA) has been an active research subject in the domain of natural language pro... more Sentiment analysis (SA) has been an active research subject in the domain of natural language processing due to its important functions in interpreting people’s perspectives and drawing successful opinion-based judgments. On social media, Roman Urdu is one of the most extensively utilized dialects. Sentiment analysis of Roman Urdu is difficult due to its morphological complexities and varied dialects. The purpose of this paper is to evaluate the performance of various word embeddings for Roman Urdu and English dialects using the CNN-LSTM architecture with traditional machine learning classifiers. We introduce a novel deep learning architecture for Roman Urdu and English dialect SA based on two layers: LSTM for long-term dependency preservation and a one-layer CNN model for local feature extraction. To obtain the final classification, the feature maps learned by CNN and LSTM are fed to several machine learning classifiers. Various word embedding models support this concept. Extensive...

Recognizing Semi-Natural and Spontaneous Speech Emotions Using Deep Neural Networks

IEEE Access

This work was supported by the Chang Gung Memorial Hospital under Grant CMRPD2J0023.

Resuscitation Council UK Guidelines 2021' -a short commentary

New Resuscitation guidelines have been published this year by Resuscitation Council UK (RCUK). It... more

Urdu Corpus Sentiment Analysis

DATASET STATISTICS

Eye in-painting using WGAN-GP for face images with mosaic

In order to protect personal privacy, news reports often use the mosaics upon the face of the pro... more In order to protect personal privacy, news reports often use the mosaics upon the face of the protagonist in the photo. However, readers will feel uncomfortable and awkward to this kind of photos. In this research, we detect the eye mosaic and try to use eye complementing which is not the same with original picture but matches the nearby texture. It can arouse readers' interest in reading. Traditional in-painting research is not suitable for filling special or large objects, such as eyes or boxes on the ground. They only can fill a small area of missing parts or a single background refer to nearby textures, such as landscape photos. We use WGAN-GP that can refer to nearby textures to generate special objects for in-painting eyes. We also divide the training set into male and female according to gender to avoid eye makeup appearing in all pictures. The experiment result shows our method get higher score in blind testing.

Effect on speech emotion classification of a feature selection approach using a convolutional neural network

PeerJ Computer Science

Speech emotion recognition (SER) is a challenging issue because it is not clear which features ar... more Speech emotion recognition (SER) is a challenging issue because it is not clear which features are effective for classification. Emotionally related features are always extracted from speech signals for emotional classification. Handcrafted features are mainly used for emotional identification from audio signals. However, these features are not sufficient to correctly identify the emotional state of the speaker. The advantages of a deep convolutional neural network (DCNN) are investigated in the proposed work. A pretrained framework is used to extract the features from speech emotion databases. In this work, we adopt the feature selection (FS) approach to find the discriminative and most important features for SER. Many algorithms are used for the emotion classification problem. We use the random forest (RF), decision tree (DT), support vector machine (SVM), multilayer perceptron classifier (MLP), and k-nearest neighbors (KNN) to classify seven emotions. All experiments are performe...

Urdu Sentiment Analysis With Deep Learning Methods

IEEE Access

Although over 169 million people in the world are familiar with the Urdu language and a large qua... more Although over 169 million people in the world are familiar with the Urdu language and a large quantity of Urdu data is being generated on different social websites daily, very few research studies and efforts have been completed to build language resources for the Urdu language and examine user sentiments. The primary objective of this study is twofold: (1) develop a benchmark dataset for resource-deprived Urdu language for sentiment analysis and (2) evaluate various machine and deep learning algorithms for sentiment. To find the best technique, we compare two modes of text representation: count-based, where the text is represented using word n-gram feature vectors and the second one is based on fastText pre-trained word embeddings for Urdu. We consider a set of machine learning classifiers (RF, NB, SVM, AdaBoost, MLP, LR) and deep leaning classifiers (1D-CNN and LSTM) to run the experiments for all the feature types. Our study shows that the combination of word n-gram features with LR outperformed other classifiers for sentiment analysis task, obtaining the highest F 1 score of 82.05% using combination of features. INDEX TERMS Urdu sentiment analysis, machine learning, deep learning, natural language processing.

Clicksafe: Providing Security against Clickjacking Attacks

2014 IEEE 15th International Symposium on High-Assurance Systems Engineering, 2014

ABSTRACT Click jacking is an act of hijacking user clicks in order to perform undesired actions w... more ABSTRACT Click jacking is an act of hijacking user clicks in order to perform undesired actions which are beneficial for the attacker. We propose Click safe, a browser-based tool to provide increased security and reliability against click jacking attacks. Click safe is based on three major components. The detection unit detects malicious components in a web page that redirect users to external links. The mitigation unit provides interception of user clicks and give educated warnings to users who can then choose to continue or not. Click safe also incorporate a feedback unit which records the user&#39;s actions, converts them into ratings and allows future interactions to be more informed. Click safe is predominant from other similar tools as the detection and mitigation is based on a comprehensive framework which utilizes detection of malicious web components and incorporating user feedback. We explain the mechanism of click safe, describes its performance, and highlights its potential in providing safety against click jacking to a large number of users