Shamaila Iram

Prediction of preterm deliveries from EHG signals using machine learning.

There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be

A Novel Method of Early Diagnosis of Alzheimer’s Disease Based on EEG Signals

26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.

Protecting critical infrastructures through behavioural observation

Studies have reported that electroencephalogram signals in Alzheimers disease patients usually have less synchronization than those of healthy subjects. Changes in electroencephalogram signals start at early stage but, clinically, these changes are not easily detected. To detect this perturbation, three neural synchrony measurement techniques: phase synchrony, magnitude squared coherence, and cross correlation are applied to three different databases of mild Alzheimers disease patients and healthy subjects. We have compared the right and left temporal lobes of the brain with the rest of the brain areas (frontal, central, and occipital) as temporal regions are relatively the first ones to be affected by Alzheimers disease. Moreover, electroencephalogram signals are further classified into five different frequency bands (delta, theta, alpha beta, and gamma) because each frequency band has its own physiological significance in terms of signal evaluation. A new approach using principal component analysis before applying neural synchrony measurement techniques has been presented and compared with Average technique. The simulation results indicated that applying principal component analysis before synchrony measurement techniques shows significantly better results as compared to the lateral one. At the end, all the aforementioned techniques are assessed by a statistical test (Mann-Whitney U test) to compare the results.

A classifier fusion strategy to improve the early detection of neurodegenerative diseases

The increase in the use of ICT in critical infrastructures has meant that dependence on automation and control systems has brought new risk in an increasingly digital age. The increase in digitisation and interconnectivity has meant that cyber-attacks have the potential to bring operations to a halt from a remote location with devastating consequences. In response to this, in our previous work to date, we have looked into the use of behavioural observation techniques to provide critical infrastructure support through pattern detection, in order to identify threats to the system. In this paper, a continuation of our research is presented including the use of mathematical classifications to analyse the critical infrastructure data, which has been constructed through simulation. In our approach, we develop a pattern of behaviour for the simulation and identify changes in patterns, which are the result of an attack on the system.

An Integrated Web-Based e-Assessment Tool

People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimers and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules voting, product, mean, median, maximum and minimum to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers a single classification algorithm using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.

E-Health: The Potential of Linked Data and Stream Reasoning for Personalised Healthcare

This research work aims to investigate and evaluate ways of enhancing the learning process by the use of technology. The technology offers a pedagogical strategy to assess the students (online) by describing an evaluating strategy of students assessment. The proposed system is being developed to provide an interactive web based learning environment. Three different types of assessment techniques have been introduced in this paper; Diagnostic Assessment, Self-Assessment and Summative Assessment which help the students and the teachers to improve teaching and learning capabilities. UML has been used to describe the proposed system specification while the whole system is implemented using .NET Framework. e-Learning and e-Assessment System with its web based features presents an equal opportunity of education for both the students in the classroom and the distant students. This is a student-centric system and the students progress depends upon his/her own learning efforts. The proposed assessment system presented in this paper is aimed at supporting students in their learning by providing them with instant feedback.

Early Detection Method of Alzheimer's Disease Using EEG Signals

Stream reasoning over rapidly changing data and its growing applications in real world environments has become a relatively new and challenging area of research in the field of computer science. This research work motivated further investigation into new tools and techniques in stream reasoning for its implementation regarding quick decision making processes, risk analysis, traffic jam, and so on. It has also addressed some significant challenges that needed to be tackled in order to develop a Personalized Health Care System to discover and understand life threatening and life limiting illnesses, such as cancer, Alzheimers and cystic fibrosis. Reasoning over streaming data has also helped to predict the spread of disease. This paper discusses these ideas further and describes some of the challenges and future work still required within this area. It also provides the basis for our own research and builds on advances made within the Semantic Web to develop a new and novel framework for personalised healthcare.

A novel method to analyze EEG synchrony for the early diagnosis of Alzheimer's disease in optimized frequency bands

Different studies have stated that electroencephalogram signals in Alzheimer’s disease patients usually have less synchronization as compare to healthy subjects. Changes in electroencephalogram signals start at early stage but clinically, these changes are not easily detected. To detect this perturbation, three neural synchrony measurement techniques have been examined with three different sets of data. This research work have successfully reported the experiment of comparing right and left temporal of brain with the rest of the brain area (frontal, central and occipital), as temporal regions are relatively the first ones to be affected by Alzheimer’s disease. A new approach using principal component analysis before applying neural synchrony measurement techniques has been presented and compared with to other existing techniques. The simulation results indicated that applying principal component analysis before synchrony measurement techniques show significantly improvement over the lateral one. The results of the experiments were analyzed using Mann-Whitney U test.

Home-Based Health Monitoring and Measurement for Personalised Healthcare

Studies have reported that electroencephalogram (EEG) signals in Alzheimers disease (AD) patients usually have less synchronization as compared to healthy subjects. To detect this perturbation, three neural synchrony measurement techniques; phase synchrony, magnitudes squared coherence, and cross correlation are applied on a dataset for mild Alzheimers disease (MiAD) patients and healthy subjects. This paper discusses the use of principle component analysis (PCA) before applying neural synchrony measurement techniques and assesses the approach with others using the Mann-Whitney U test. The results show that applying PCA before synchrony measurement techniques improvements are made compared to the use of traditional techniques.