• Home
  • Sawsan M. Mahmoud
Sawsan M. Mahmoud

Sawsan M. Mahmoud
Mustansiriyah University · Computer Engineering

Ph.D

About

30
Publications
9,807
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
531
Citations
Citations since 2017
16 Research Items
381 Citations
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
Learn about citations on ResearchGate
Introduction
Skills and Expertise
Computational Intelligence
Neural Networks and Artificial Intelligence
Machine Learning
Applied Artificial Intelligence
Pattern Recognition
Advanced Machine Learning
Classification
Unsupervised Learning
Prediction
Supervised Learning

Publications

Publications (30)
Figure 1. A diagram of a framework
Figure 3. Block diagram of automatic X-ray segmentation (a) image...
Confusion matrices related to the COVID-19 class, for the evaluation...
Performance comparisons accuracy of DL networks for image...
+2 MAPs using GoogleNet, Resnet, AlexNet models with DF1 and DF2 for X-ray...
Chest Radiographs Images Retrieval Using Deep Learning Networks
Article
Full-text available
  • Jun 2022
Chest diseases are among the most common diseases today. More than one million people with pneumonia enter the hospital, and about 50,000 people die annually in the U.S. alone. Also, Coronavirus disease (COVID-19) is a risky disease that threatens the health by affecting the lungs of many people around the world. Chest X-ray and CT-scan images are...
Figure 1. Typical diagram of CBIR system
Figure 2. AlexNet Layout with its convolution and connected layers
Figure 4. GoogleNet architecture
Figure 5. ResNet architecture
+5 Figure 6. Framework of image classification and retrieval
A comparative analysis of automatic deep neural networks for image retrieval
Article
Full-text available
  • Jun 2021
Feature descriptor and similarity measures are the two core components in content-based image retrieval and crucial issues due to "semantic gap" between human conceptual meaning and a machine low-level feature. Recently, deep learning techniques have shown a great interest in image recognition especially in extracting features information about the...
Overlapped hierarchical clusters routing protocol for improving quality of service
Article
  • Jun 2021
The rapid development in communications and sensors technologies make wireless sensor networks (WSNs) as essential key in several advanced applications such as internet of things (IoT). The increasing demands on using WSNs required high quality of services (QoS) because most WSNs applications have critical requirements. This work aims to offer a ro...
Overlapped Hierarchical Clusters Routing Protocol for Improving Quality of Service -Final
Article
  • Nov 2020
The rapid development in communications and sensors technologies make Wireless Sensor Networks (WSNs) as essential key in several advanced applications such as Internet of Things (IoT). The increasing demands on using WSNs required high Quality of Services (QoS) because most WSNs applications have critical requirements. This work aims to offer a ro...
Figure 2. An illustration of the architecture of AlexNet
Figure 3. Architecture of ResNet-50 model
DIAGNOSING THORAX DISEASES USING DEEP LEARNING MODELS
Preprint
Full-text available
  • Sep 2020
Despite the availability of radiology devices in some health care centers, thorax diseases are considered as one of the most common health problems, especially in rural areas. In this paper, pre-trained AlexNet and ResNet-50 models are used and compared for diagnosing thorax diseases. Chest x-ray images has been used to diagnose thorax diseases and...
Figure 1. CBIR system
Figure 2. DCT-CT Feature from 8x8 block using YCbCr
Figure 4. Normalized Laplacian Spectral Algorithm
Figure 5. Frame work of Retrieval Method
SPECTRAL ALGORITHM FOR CONTENT-BASED IMAGE RETRIEVAL
Article
Full-text available
  • Sep 2020
Colour images are rich in visual information. The process of searching for the most similar images in large-scale database based on visual features of query image is still a challenge in Content-Based Image Retrieval (CBIR) due to a semantic gap issue. In this paper, we proposed a fusing retrieval method to diminish the gap between high-level and l...
Figure 1. Architecture of encoder-decoder convolutional neural network...
Figure 2: Architecture of Vgg16 and Vgg19 [31].
Figure 3. General structure of the proposed model.
Automatic Medical Images Segmentation Based on Deep Learning Networks
Article
Full-text available
  • Jul 2020
In recent years, radiography systems have become more used in medical fields, where they are used for diagnosing many diseases. The size of the radiographs differs, as well as the size of the body parts for each patient. So many researchers crop the radiographs manually to facilitate the diagnosis and make it more reliable. Currently, the trend tow...
Figure 3. Original Contourlet transform with two decomposition level
Figure 9. Contourlet coefficients
presents the performance of CT-OCSVM using different percentage of...
OUTLIER DETECTION TECHNIQUE USING CT-OCSVM AND FUZZY RULE-BASED SYSTEM IN WIRELESS SENSOR NETWORKS
Article
Full-text available
  • Mar 2020
The development of Wireless Sensor Networks (WSNs) has been attained in the past few years due to its important using in wide range of application. The readings of data derived from WSN nodes are not always accurate and may contain abnormal data. This paper proposed an anomaly detection and classification algorithm in WSNs. At first, an integration...
Figure 1. Illustration of chest image analysis with ResNet-50 model
Figure 2. Proposed model block diagram
Deep learning model for thorax diseases detection
Article
Full-text available
  • Feb 2020
Received Apr 25, 2019 Revised Jul 7, 2019 Accepted Jul 18, 2019 Despite the availability of radiology devices in some health care centers, thorax diseases are considered as one of the most common health problems, especially in rural areas. By exploiting the power of the Internet of things and specific platforms to analyze a large volume of medica...
Figure 1. Architecture of encoder-decoder convolutional neural network...
Figure 2: Architecture of Vgg16 and Vgg19 [31].
Figure 3. General structure of the proposed model.
Automatic Medical Images Segmentation Based on Deep Learning Networks
Conference Paper
Full-text available
  • Jan 2020
In recent years, radiography systems have become more used in medical fields, where they are used for diagnosing many diseases. The size of the radiographs differs, as well as the size of the body parts for each patient. So many researchers crop the radiographs manually to facilitate the diagnosis and make it more reliable. Currently, the trend tow...
Fig. 6. Feature Extraction Based on a MapReduce Framework
Fig. 7. Feature extraction of Image f0015-01r from the NIST-4 data set
Fig. 8. Total Processing Time of Images Using Mapreduce While Fig. 9...
CN Properties
Analysis of Large Set of Images Using MapReduce Framework
Article
Full-text available
  • Dec 2019
Due to the limitations of a physical memory, it is quite difficult to analyze and process big datasets. The Hadoop MapReduce algorithm has been widely used to process and mine such large sets of data using the Map and Reduce functions. The main contribution of this paper is to implement MapReduce programming algorithm to analyze large set of...
Fig.1. General Contourlet transform with two decomposition levels. In...
Fig.2. Block diagram of CT-OCSVM.
Fig.5. PSO with 15 in-bound outlier.
Fig.6. DE with 15 in-bound outlier.
+8 Fig.7. K-means clustering with 15 in-bound outlier and 3 clusters.
High Rate Outlier Detection in Wireless Sensor Networks: A Comparative Study
Article
Full-text available
  • Apr 2019
The rapid development of Smart Cities and the Internet of Thinks (IoT) is largely dependent on data obtained through Wireless Sensor Networks (WSNs). The quality of data gathered from sensor nodes is influenced by abnormalities that happen due to different reasons including, malicious attacks, sensor malfunction or noise related to communication ch...
Figure 3. Transmissibility functions TF(6,1) for different damage...
THE USE OF TRANSMISSIBILITY FUNCTIONS FOR DAMAGE IDENTIFICATION IN REINFORCED CONCRETE BEAMS
Article
Full-text available
  • May 2018
Nowadays, structural health monitoring is the area of a great interest of continuing research aiming at establishing a reliable condition monitoring strategy of civil engineering infrastructure. Such finding will allow moving from the schedule-based inspection policy to condition-based policy. This study is dedicated to identify the damage in reinf...
Figure 1: Architecture of the proposed outliers detection system.
Figure 2: A sample of two days of the back door entry point data...
Figure 3: Membership labels for input and output variables for the back...
Figure 6: Scattered plot for the first and second principal components...
+2 Figure 8: Scattered plot for the first and second principal components...
User activities outliers detection; Integration of statistical and computational intelligence techniques
Article
Full-text available
  • Jun 2014
In this article, a hybrid technique for user activities outliers detection is introduced. The hybrid technique consists of a two-stage integration of principal component analysis and fuzzy rule-based systems. In the first stage, the Hamming distance is used to measure the differences between different activities. Principal component analysis is the...
Figure 1: An overview of monitoring and interaction system architecture.  
Table 1: A sample of collected raw data from the environment 
Figure 2: Intermittent binary time series extracted from an occupancy...
Table 2: The prediction results of the lounge sensor for Elman and NARX...
+9 Figure 3: NARX Network with two input delays and three output delays.  
Behavioural Pattern Identification and Prediction in Intelligent Environments
Data
Full-text available
  • Apr 2013
In this paper, the application of soft computing techniques in prediction of an occupant's behaviour in an inhabited intelligent environment is ad-dressed. In this research, daily activities of elderly people who live in their own homes suffering from dementia are studied. Occupancy sensors are used to extract the movement patterns of the occupant....
Figure 1: An overview of monitoring and interaction system architecture. 
Figure 2: Intermittent binary time series extracted from an occupancy...
Figure 3: NARX Network with two input delays and three output delays. 
Figure 4: NARX network architecture.
+6 Figure 5: Elman network structure. 
Behavioural Pattern Identification and Prediction in Intelligent Environments
Article
Full-text available
  • Apr 2013
In this paper, the application of soft computing techniques in prediction of an occupant's behaviour in an inhabited intelligent environment is ad-dressed. In this research, daily activities of elderly people who live in their own homes suffering from dementia are studied. Occupancy sensors are used to extract the movement patterns of the occupant....
Fig. 1. An overview of the IIE architecture with the semantic decision...
Fig. 2. Concept Map for the Semantic-Driven Decision Support System  
Fig. 3. System Framework  
Utilising Semantic Technologies for Decision Support in Dementia Care
Conference Paper
Full-text available
  • Apr 2013
The main objective of this work is to discuss our experience in utilising semantic technologies for building decision support in Dementia care systems that are based on the non-intrusive on the non-intrusive monitoring of the patient's behaviour. Our approach adopts context-aware modelling of the patient's condition to facilitate the analysis of th...
Figure 1: Architecture of the proposed outlier detection system. 
Figure 2: Scree plot for determining significant number components for...
Figure 3: Scattered plot for the 1st and 2nd principal components of...
Figure 4: Principal component analysis statistic measures for the back...
Figure 5: Membership labels for input and output variables for the back...
Sawsan M. Mahmoud, Ahmad Lotfi and Caroline Langensiepen, User Activities Outlier Detection System Using Principal Component Analysis and Fuzzy Rule-Based System, Fifth International Conference on PErvasive Technologies Related to Assistive Environments, Crete, Greece, 2012.
Conference Paper
Full-text available
  • Jun 2012
In this paper, a user activities outlier detection system is introduced. The proposed system is implemented in a smart home environment equipped with appropriate sensory devices. An activity outlier detection system consist of a two-stage integration of Principal Component Analysis (PCA) and Fuzzy Rule-Based System (FRBS). In the first stage, the H...
Figure 1: Architecture of the proposed outlier detection system. 
Figure 2: Scree plot for determining significant number components for...
Figure 3: Scattered plot for the 1st and 2nd principal components of...
Figure 4: Principal component analysis statistic measures for the back...
+1 Figure 5: Membership labels for input and output variables for the back...
User activities outlier detection system using principal component analysis and fuzzy rule-based system
Conference Paper
Full-text available
  • Jun 2012
In this paper, a user activities outlier detection system is introduced. The proposed system is implemented in a smart home environment equipped with appropriate sensory devices. An activity outlier detection system consist of a two-stage integration of Principal Component Analysis (PCA) and Fuzzy Rule-Based System (FRBS). In the first stage, the H...
Modelling Decision Support Systems for Remote Dementia Care: A Semantic Web Approach
Conference Paper
  • May 2012
This paper reports on our investigation into the utilisation of semantic technologies to build a Dementia Care Decision Support System based on the non-intrusive monitoring of the patient’s behaviour. Our approach adopts context-aware modelling of the patient’s condition to enable the analysis of the dynamic behaviour observations (occupants mo...
Figure 2.1: A time-use representation for 24-hours [177].
Figure 3.1: Continues time series data.
Figure 3.2: Discrete time series data.
Figure 3.3: A graphical representation of Hidden Markov Model with...
+30 Figure 3.4: Neural networks for time series processing.
Identification and Prediction of Abnormal Behaviour Activities of Daily Living in Intelligent Environments
Thesis
Full-text available
  • May 2012
The aim of this research is to investigate efficient mining of useful information from a sensor network forming an Ambient Intelligence (AmI) environment. In this thesis, we investigate methods for sup- porting independent living of the elderly (and specifically patients who are suffering from dementia) by means of equipping their home with a simple se...
Fig. 1: An overview of the monitoring and interaction system architecture. 
Fig. 2: Phases in the data handling work flow. 
Fig. 3: Anomalies in a simple 2-dimensional data set. 
Fig. 4: A sample of activity of daily living data collected by sensory...
+15 Fig. 5: A sample of activity of daily living for a single user. 
Smart homes for the elderly dementia sufferers: Identification and prediction of abnormal behaviour
Article
Full-text available
  • Sep 2011
In this paper, we have described a solution for supporting independent living of the elderly by means of equipping their home with a simple sensor network to monitor their behaviour. Standard home automation sensors including movement sensors and door entry point sensors are used. By monitoring the sensor data, important information regarding any a...
Figure 1: An overview of monitoring and interaction system architecture. 
Table 1 : A sample of collected raw data from the environment
Figure 2: Intermittent binary time series extracted from an occupancy...
Figure 3: NARX Network with two input delays and three output delays. 
+6 Figure 4: NARX network architecture.
Behavioural Pattern Identification in a Smart Home Using Binary Similarity and Dissimilarity Measures
Conference Paper
Full-text available
  • Jul 2011
The aim of this paper is to examine the suitability of binary similarity and dissimilarity measures in identifying frequent and abnormal human behavioural patterns in a smart home. There has been an increasing interest in this subject to help the elderly and disabled people to live alone in their own homes with little help and support from their ca...
Figure 3: Samples of front door sensor for Two days (a) AbNormal (b)...
Figure 5: A Comparison between fuzzy hamming distance and hamming...
Figure 2: Samples of lounge sensor for Two days (a) AbNormal (b) Normal.  
Abnormal behaviours identification for an elder's life activities using dissimilarity measurements
Conference Paper
Full-text available
  • May 2011
Identifying abnormal behaviour is an important factor in activity recognition. The aim of this paper is to design a system able to detect the abnormal behaviours of daily activity living in an intelligent environment. We approach this by applying dissimilarity (distance) measures on data collected from a single inhabitant environment. The data are...
Figure 1: An example of occupancy signal for a four-area environment...
Figure 3: A snapshot of the occupancy signal.
Figure 4: A sample of two days of occupancy signal simulation for a...
Figure 5: An occupant behaviour of an increasing trend in frequency of...
+1 Figure 6: An increasing trend in the occupant behaviour generated from...
Trend Modelling of Elderly Lifestyle within an Occupancy Simulator
Conference Paper
Full-text available
  • Mar 2011
In this paper, the trend as an important component in activities of daily living is modelled and integrated to a single-occupant occupancy simulator. Therefore, in the occupancy signal generated by the simulator, both seasonality and trend are included in occupant's movements. As the result of trends integrated to the simulator, occupancy signals w...
Fig. 1. 
Fig. 2. Converted intermittent binary time series extracted from an...
Fig. 3. 
Fig. 4. Three days sample of simulated data activities. Actual sensor...
Fig. 5. Two days sample of back and front door activities. Actual...
Occupancy Pattern Extraction and Prediction in an Inhabited Intelligent Environment Using NARX Networks
Conference Paper
Full-text available
  • Aug 2010
In this paper, occupancy pattern extraction and prediction in an intelligent inhabited environment is addressed. The results of this research will help elderly people to live independently in their own home longer and help them in case of an emergency. Using a wireless sensor network system, daily behavioral patterns of the occupant are extracted....
Figure 1. Discrete values of time series data collected from a door sensor 
Table 1 . Raw Sample of Sensor Data
Figure 2. Structure of an Echo State Network approach. Only the output...
Table 2 . Prediction results of all sensor datasets using ESN, RTRL and...
+3 Figure 3. The flat layout 
Echo State Network for Occupancy Prediction and Pattern Mining in Intelligent Environments
Conference Paper
Full-text available
  • Jan 2009
Pattern analysis and prediction of sensory data is becoming an increas- ing scientific challenge and a massive economical interest supports the need for better pattern mining techniques. The aim of this paper is to investigate efficient mining of useful information from a sensor network representing an ambient in- telligence environment. The goal i...

Network

Cited
View All
Cited By
View All

Projects

Projects (3)
Deep learning model for thorax diseases detection
Project
Clustering Algorithms for image retrieval
Project
"Improve Quality of Service in Wireless Sensor Networks"
Project
Quality of Service (QoS) in Wireless Sensor Networks(WSNs) can be defined as the optimum number of sensors that can perform their tasks and sending information at a given time. It can perform load balancing, power-aware sleep scheduling due to network density, and sending data. In this project, the factors that affect the QoS in different topologies of WSNs are studied, analyzed and evaluated. It also proposes and implements techniques that improve the QoS of WSNs.