Feature selection is used in many application areas relevant to expert and intelligent systems, such as data mining and machine learning, image processing, anomaly detection, bioinformatics and natural language processing. Feature selection based on information theory is a popular approach due its computational efficiency, scalability in terms of the dataset dimensionality, and independence from the classifier. Common drawbacks of this approach are the lack of information about the interaction between the features and the classifier, and the selection of redundant and irrelevant features. The latter is due to the limitations of the employed goal functions leading to overestimation of the feature significance.To address this problem, this article introduces two new nonlinear feature selection methods, namely Joint Mutual Information Maximisation (JMIM) and Normalised Joint Mutual Information Maximisation (NJMIM); both these methods use mutual information and the ‘maximum of the minimum’ criterion, which alleviates the problem of overestimation of the feature significance as demonstrated both theoretically and experimentally. The proposed methods are compared using eleven publically available datasets with five competing methods. The results demonstrate that the JMIM method outperforms the other methods on most tested public datasets, reducing the relative average classification error by almost 6% in comparison to the next best performing method. The statistical significance of the results is confirmed by the ANOVA test. Moreover, this method produces the best trade-off between accuracy and stability

Activity recognition using wearable sensors has become essential for a variety of applications. Tri-axial accelerometers are the most widely used sensor for activity recognition. Although various features have been used to capture patterns and classify the accelerometer signals to recognise activities, there is no consensus on the best features to choose. Reducing the number of features can reduce the computational cost and complexity and enhance the performance of the classifiers. This paper identifies the signal features that have significant discriminative power between different human activities. It also investigates the effect of sensor placement location, the sampling frequency, and activity complexity on the selected features. A comprehensive list of 193 signal features has been extracted from accelerometer signals of four publicly available datasets, including features that have never been used before for activity recognition. Feature significance was measured using the Joint Mutual Information Maximisation (JMIM) method. Common significant features among all the datasets were identified. The results show that the sensor placement location does not significantly affect recognition performance, nor does it affect the significant sub-set of features. The results also showed that with high sampling frequency, features related to signal repeatability and regularity show high discriminative power.

Quantitative assessment of movement impairment in Huntington's disease (HD) is essential to monitoring of disease progression. This paper aimed to develop and validate a novel low cost, objective automated system for the evaluation of upper limb movement impairment in HD in order to eliminate the inconsistency of the assessor and offer a more sensitive, continuous assessment scale. Patients with genetically confirmed HD and healthy controls were recruited to this observational study. Demographic data, including age (years), gender, and unified HD rating scale total motor score (UHDRS-TMS), were recorded. For the purposes of this paper, a modified upper limb motor impairment score (mULMS) was generated from the UHDRS-TMS. All participants completed a brief, standardized clinical assessment of upper limb dexterity while wearing a tri-axial accelerometer on each wrist and on the sternum. The captured acceleration data were used to develop an automatic classification system for discriminating between healthy and HD participants and to automatically generate a continuous movement impairment score (MIS) that reflected the degree of the movement impairment. Data from 48 healthy and 44 HD participants was used to validate the developed system, which achieved 98.78% accuracy in discriminating between healthy and HD participants. The Pearson correlation coefficient between the automatic MIS and the clinician rated mULMS was 0.77 with a p-value <; 0.01. The approach presented in this paper demonstrates the possibility of an automated objective, consistent, and sensitive assessment of the HD movement impairment.

Huntington's disease (HD) is a progressive inherited neurodegenerative disorder, causing involuntary movement and cognitive problems, severely affecting the quality of life. Controlling upper limb function is a core feature of daily activity and can prove problematic for people with HD. The Money Box Test (MBT) has been developed with a purpose of quantifying the involuntary movement frequently seen in people with HD. In this research, wearable and highly sensitive accelerometers are used to collect the acceleration of the hands and chest during the performance of the MBT. Using this data, a new approach is proposed to automatically classify the participants into two classes, healthy and HD, on the basis of the time series accelerometer data. A set of 90 time domain features is extracted from the accelerometer data, a feature selection technique is used to analyse the feature significance and to reduce the dimensionality of the dataset, and finally an SVM classifier is used to classify subjects into healthy and HD classes. The data of seven healthy controls and 15 HD patients are used in this study. The highest accuracy with the most significant eight features is 86.36% with the sensitivity and the specificity values being 87.50%, and 83.33% respectively

Dementia is a syndrome caused by a chronic or progressive disease of the brain, which affects memory, orientation, thinking, calculation, learning ability and language. The Clock Drawing Test (CDT) and Mini Mental State Examination (MMSE) are well-known cognitive assessment tests. A known obstacle to the wider usage of the CDT assessments is the scoring and interpretation of the results. This paper introduces a novel cascade CDT classifier, which can help in the diagnosis of three stages of dementia. The data used in this research are 604 clock drawings produced by patients and healthy individuals. The study employs 47 visual features, which are selected following a comprehensive analysis of the available data and the most common CDT scoring systems reported in the medical literature. These features are used to build a new digitized dataset needed to train and validate the proposed classifier. The results show significant improvement of 6.8% in differentiating between three levels of dementia (normal/functional, mild cognitive impairment/mild dementia, and moderate/severe dementia) when compared to a single stage classifier. In particular, the results show classification accuracy of over 89% when discriminating between normal and abnormal conditions only.