Nancy Moussa - Academia.edu (original) (raw)

Papers by Nancy Moussa

Research paper thumbnail of Environmental Noise Adaptable Hearing Aid using Deep Learning

The International Arab Journal of Information Technology

Speech de-nosing is one of the essential processes done inside hearing aids, and has recently sho... more Speech de-nosing is one of the essential processes done inside hearing aids, and has recently shown a great improvement when applied using deep learning. However, when performing the speech de-noising for hearing aids, adding noise frequency classification stage is of a great importance, because of the different hearing loss types. Patients who suffer from sensorineural hearing loss have lower ability to hear specific range of frequencies over the others, so treating all the noise environments similarly will result in unsatisfying performance. In this paper, the idea of environmental adaptable hearing aid will be introduced. A hearing aid that can be programmed to multiply the background noise by a weight based on its frequency and importance, to match the case and needs of each patient. Furthermore, a more generalized Deep Neural Network (DNN) for speech enhancement will be presented, by training the network on a diversity of languages, instead of only the target language. The resu...

Research paper thumbnail of A comparison between classical and new proposed feature selection methods for attention level recognition in disordered children

Alexandria Engineering Journal

Research paper thumbnail of Early prediction of hemodialysis complications employing ensemble techniques

BioMedical Engineering OnLine

Background and objectives Hemodialysis complications remain a critical threat among dialysis pati... more Background and objectives Hemodialysis complications remain a critical threat among dialysis patients. They result in sudden termination of the session which impacts the efficiency of dialysis. As intra-dialytic complications are the result of the interplay of multiple factors, artificial intelligence can aid in their early prediction. This research aims to compare different machine learning tools for the early prediction of the most frequent hemodialysis complications with high performance, using the fewest predictors for easier practical implementation. Methods Fifty different variables were recorded during 6000 hemodialysis sessions performed in a regional dialysis unit in Egypt. The filter technique was used to extract the most relevant features. Then, five individual classifiers and three ensemble approaches were implemented to predict the occurrence of intra-dialytic complications. Different subsets of 25, 12 and 6 from the 50 collected features were tested. Results Random for...

Research paper thumbnail of A step towards the application of an artificial intelligence model in the prediction of intradialytic complications

Research paper thumbnail of Classification Techniques for Diagnosing Respiratory Sounds in Infants and Children

2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), 2019

Recently, many studies were performed using several techniques to classify and diagnose lung soun... more Recently, many studies were performed using several techniques to classify and diagnose lung sound, but as a drawback the age category was limited, almost adult only, as well as the insufficient number of samples and this unfortunately leads to an unfair classification of lung sound. While this study deals with different methods to analyze lung sounds and extract distinctive features then classify them to diagnose lung sounds in infant and children to one of the three categories: Normal, Wheeze, or Stridor. Features were extracted using three different techniques in separate ways to compare the effectiveness; these techniques are Discrete Wavelet transform (DWT), Short Time Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficients (MFCCs). After that the sounds are categorized using four different classification techniques which include Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes (NB). The main aim of this research is to choose the best signal processing technique with the most suitable classifier to diagnose lung sounds by categorizing 300 lung sounds especially in infants and children to Normal, Wheeze, or Stridor. These sounds are collected from Alexandria University Children Hospital (AUCH) – Egypt as a particular environment which is considered one of the main advantages of this research. Moreover, extra 146 wheezes were used to validate the usefulness of the classifiers. The results were very promising.

Research paper thumbnail of Use of Area under the Expiratory Flow-volume Curve and Rectangular Area Ratio in Detecting Ventilatory Impairments in Spirometry: A Pilot Study

Purpose: This study aimed at demonstrating the reliability of surface area under the maximum expi... more Purpose: This study aimed at demonstrating the reliability of surface area under the maximum expiratory flow volume curve (Aex) and rectangular area ratio (RAR) to define the type of ventilatory impairment and assessing potential clinical value of Aex ratio (measured / predicted Aex) to indicate the severity of ventilatory obstruction. Methods: Spirometric data of 75 subjects were analyzed by qualified pulmonologists to distinguish between different spirometric patterns representing expert decision. Computerized graphic analysis methodology was used, Aex was used to calculate other parameters (area of concavity and RAR) and an algorithm for diagnosis was proposed. For validation of the proposed grading and cutoff values, we compared them with expert decision using classification and regression trees (CART). Results: According to calculated parameters, obstructive pattern is realized if area of concavity (Au) has positive value and RAR is less than 0.5. While convexity/linearity is i...

Research paper thumbnail of Time-Frequency analysis versus cepstrum analysis for validating respiratory sounds in infants and children

Automatic sound recognition for human body acoustic signals has attracted wide interests in recen... more Automatic sound recognition for human body acoustic signals has attracted wide interests in recent years. However, the power of automatic sound recognition largely depends on the choice of features representing the acoustic signal. Recently, the time-frequency features and cepstral features are the most commonly utilized features in automatic recognition. The aim of this paper is to compare the time-frequency analysis versus cepstral analysis to find the best feature extraction technique. The one that has the greatest influence on the recognition and validation of diagnosed respiratory diseases in infants and children. This paper proves that the cepstral analysis of features result in better recognition accuracy, and the Mel-Frequency Cepstral Coefficients (MFCC) has the highest influence on recognition accuracy up to 94%, and more, versus the time-frequency features and linear cepstral technique. The used database was collected from infants and young children till the age of 12 yea...

Research paper thumbnail of Enhancing ECG Diagnosis Using Hybrid Automated Technique

Bulletin of Egyptian Society for Physiological Sciences

The electrocardiogram (ECG) is a test of electrical activities of the heart. To detect cardiac co... more The electrocardiogram (ECG) is a test of electrical activities of the heart. To detect cardiac conditions different detection techniques are used. In this paper, a novel hybrid system combining a modified scaling technique and Wavelet technique is implemented. It is applied to enhance the accuracy of filtration, denoising and diagnosis techniques. In previous computerized diagnosis techniques, either filtration or denoising is used. However, in this system, filtration and denoising are mixed in pre-processing to give a pure signal. This research deems as the premier work to utilize, in the diagnosis phase, the time feature of each wave and its location in the ECG signal. In contrast to previous automated techniques, the proposed hybrid system is based on three factors to detect and diagnose the ECG episodes; namely amplitude, frequency and time location scaling of the ECG signal. Mixing effectively these three factors in the diagnosis phase allows the detection of more episodes, gives more accurate and faster results. As the results demonstrate, the previous computerized techniques' average detection accuracy does not exceed 80 %, while the proposed hybrid technique average accuracy overtakes 97% with a good average time consumption equal to 0.05 seconds. Furthermore, the proposed system overcomes some of the previous challenges and detects more new episodes that have never been diagnosed before by any automated systems. This system can help the cardiologists to take more confident decisions in their diagnoses.

Research paper thumbnail of Enhanced smart hearing aid using deep neural networks

Alexandria Engineering Journal

Research paper thumbnail of A novel technique for validating diagnosed respiratory noises in infants and children

Alexandria Engineering Journal

Research paper thumbnail of What is initiative?

User Modeling and …, 1998

Abstract. This paper presents some alternate theories for explaining the term 'initiative&#x... more Abstract. This paper presents some alternate theories for explaining the term 'initiative', as it is used in the design of mixed-initiative AI systems. Although there is now active research in the area of mixed initiative interactive systems, there appears to be no true consensus in the ...

Research paper thumbnail of Environmental Noise Adaptable Hearing Aid using Deep Learning

The International Arab Journal of Information Technology

Speech de-nosing is one of the essential processes done inside hearing aids, and has recently sho... more Speech de-nosing is one of the essential processes done inside hearing aids, and has recently shown a great improvement when applied using deep learning. However, when performing the speech de-noising for hearing aids, adding noise frequency classification stage is of a great importance, because of the different hearing loss types. Patients who suffer from sensorineural hearing loss have lower ability to hear specific range of frequencies over the others, so treating all the noise environments similarly will result in unsatisfying performance. In this paper, the idea of environmental adaptable hearing aid will be introduced. A hearing aid that can be programmed to multiply the background noise by a weight based on its frequency and importance, to match the case and needs of each patient. Furthermore, a more generalized Deep Neural Network (DNN) for speech enhancement will be presented, by training the network on a diversity of languages, instead of only the target language. The resu...

Research paper thumbnail of A comparison between classical and new proposed feature selection methods for attention level recognition in disordered children

Alexandria Engineering Journal

Research paper thumbnail of Early prediction of hemodialysis complications employing ensemble techniques

BioMedical Engineering OnLine

Background and objectives Hemodialysis complications remain a critical threat among dialysis pati... more Background and objectives Hemodialysis complications remain a critical threat among dialysis patients. They result in sudden termination of the session which impacts the efficiency of dialysis. As intra-dialytic complications are the result of the interplay of multiple factors, artificial intelligence can aid in their early prediction. This research aims to compare different machine learning tools for the early prediction of the most frequent hemodialysis complications with high performance, using the fewest predictors for easier practical implementation. Methods Fifty different variables were recorded during 6000 hemodialysis sessions performed in a regional dialysis unit in Egypt. The filter technique was used to extract the most relevant features. Then, five individual classifiers and three ensemble approaches were implemented to predict the occurrence of intra-dialytic complications. Different subsets of 25, 12 and 6 from the 50 collected features were tested. Results Random for...

Research paper thumbnail of A step towards the application of an artificial intelligence model in the prediction of intradialytic complications

Research paper thumbnail of Classification Techniques for Diagnosing Respiratory Sounds in Infants and Children

2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), 2019

Recently, many studies were performed using several techniques to classify and diagnose lung soun... more Recently, many studies were performed using several techniques to classify and diagnose lung sound, but as a drawback the age category was limited, almost adult only, as well as the insufficient number of samples and this unfortunately leads to an unfair classification of lung sound. While this study deals with different methods to analyze lung sounds and extract distinctive features then classify them to diagnose lung sounds in infant and children to one of the three categories: Normal, Wheeze, or Stridor. Features were extracted using three different techniques in separate ways to compare the effectiveness; these techniques are Discrete Wavelet transform (DWT), Short Time Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficients (MFCCs). After that the sounds are categorized using four different classification techniques which include Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes (NB). The main aim of this research is to choose the best signal processing technique with the most suitable classifier to diagnose lung sounds by categorizing 300 lung sounds especially in infants and children to Normal, Wheeze, or Stridor. These sounds are collected from Alexandria University Children Hospital (AUCH) – Egypt as a particular environment which is considered one of the main advantages of this research. Moreover, extra 146 wheezes were used to validate the usefulness of the classifiers. The results were very promising.

Research paper thumbnail of Use of Area under the Expiratory Flow-volume Curve and Rectangular Area Ratio in Detecting Ventilatory Impairments in Spirometry: A Pilot Study

Purpose: This study aimed at demonstrating the reliability of surface area under the maximum expi... more Purpose: This study aimed at demonstrating the reliability of surface area under the maximum expiratory flow volume curve (Aex) and rectangular area ratio (RAR) to define the type of ventilatory impairment and assessing potential clinical value of Aex ratio (measured / predicted Aex) to indicate the severity of ventilatory obstruction. Methods: Spirometric data of 75 subjects were analyzed by qualified pulmonologists to distinguish between different spirometric patterns representing expert decision. Computerized graphic analysis methodology was used, Aex was used to calculate other parameters (area of concavity and RAR) and an algorithm for diagnosis was proposed. For validation of the proposed grading and cutoff values, we compared them with expert decision using classification and regression trees (CART). Results: According to calculated parameters, obstructive pattern is realized if area of concavity (Au) has positive value and RAR is less than 0.5. While convexity/linearity is i...

Research paper thumbnail of Time-Frequency analysis versus cepstrum analysis for validating respiratory sounds in infants and children

Automatic sound recognition for human body acoustic signals has attracted wide interests in recen... more Automatic sound recognition for human body acoustic signals has attracted wide interests in recent years. However, the power of automatic sound recognition largely depends on the choice of features representing the acoustic signal. Recently, the time-frequency features and cepstral features are the most commonly utilized features in automatic recognition. The aim of this paper is to compare the time-frequency analysis versus cepstral analysis to find the best feature extraction technique. The one that has the greatest influence on the recognition and validation of diagnosed respiratory diseases in infants and children. This paper proves that the cepstral analysis of features result in better recognition accuracy, and the Mel-Frequency Cepstral Coefficients (MFCC) has the highest influence on recognition accuracy up to 94%, and more, versus the time-frequency features and linear cepstral technique. The used database was collected from infants and young children till the age of 12 yea...

Research paper thumbnail of Enhancing ECG Diagnosis Using Hybrid Automated Technique

Bulletin of Egyptian Society for Physiological Sciences

The electrocardiogram (ECG) is a test of electrical activities of the heart. To detect cardiac co... more The electrocardiogram (ECG) is a test of electrical activities of the heart. To detect cardiac conditions different detection techniques are used. In this paper, a novel hybrid system combining a modified scaling technique and Wavelet technique is implemented. It is applied to enhance the accuracy of filtration, denoising and diagnosis techniques. In previous computerized diagnosis techniques, either filtration or denoising is used. However, in this system, filtration and denoising are mixed in pre-processing to give a pure signal. This research deems as the premier work to utilize, in the diagnosis phase, the time feature of each wave and its location in the ECG signal. In contrast to previous automated techniques, the proposed hybrid system is based on three factors to detect and diagnose the ECG episodes; namely amplitude, frequency and time location scaling of the ECG signal. Mixing effectively these three factors in the diagnosis phase allows the detection of more episodes, gives more accurate and faster results. As the results demonstrate, the previous computerized techniques' average detection accuracy does not exceed 80 %, while the proposed hybrid technique average accuracy overtakes 97% with a good average time consumption equal to 0.05 seconds. Furthermore, the proposed system overcomes some of the previous challenges and detects more new episodes that have never been diagnosed before by any automated systems. This system can help the cardiologists to take more confident decisions in their diagnoses.

Research paper thumbnail of Enhanced smart hearing aid using deep neural networks

Alexandria Engineering Journal

Research paper thumbnail of A novel technique for validating diagnosed respiratory noises in infants and children

Alexandria Engineering Journal

Research paper thumbnail of What is initiative?

User Modeling and …, 1998

Abstract. This paper presents some alternate theories for explaining the term 'initiative&#x... more Abstract. This paper presents some alternate theories for explaining the term 'initiative', as it is used in the design of mixed-initiative AI systems. Although there is now active research in the area of mixed initiative interactive systems, there appears to be no true consensus in the ...