Fischer Linear Discrimination and Quadratic Discrimination Analysis–Based Data Mining Technique for Internet of Things Framework for Healthcare

The internet of reality or augmented reality has been considered a breakthrough and an outstanding critical mutation with an emphasis on data mining leading to dismantling of some of its assumptions among several of its stakeholders. In this work, we study the pillars of these technologies connected to web usage as the Internet of things (IoT) system's healthcare infrastructure. We used several data mining techniques to evaluate the online advertisement data set, which can be categorized as high dimensional with 1,553 attributes, and the imbalanced data set, which automatically simulates an IoT discrimination problem. The proposed methodology applies Fischer linear discrimination analysis (FLDA) and quadratic discrimination analysis (QDA) within random projection (RP) filters to compare our runtime and accuracy with support vector machine (SVM), K-nearest neighbor (KNN), and Multilayer perceptron (MLP) in IoT-based systems. Finally, the impact on number of projections was practically experimented, and the sensitivity of both FLDA and QDA with regard to precision and runtime was found to be challenging. The modeling results show not only improved accuracy, but also runtime improvements. When compared with SVM, KNN, and MLP in QDA and FLDA, runtime shortens by 20 times in our chosen data set simulated for a healthcare framework. The RP filtering in the preprocessing stage of the attribute selection, fulfilling the model's runtime, is a standpoint in the IoT industry.Index Terms: Data Mining, Random Projection, Fischer Linear Discriminant Analysis, Online Advertisement Dataset, Quadratic Discriminant Analysis, Feature Selection, Internet of Things.

A comprehensive scheme for the objective upper body assessments of subjects with cerebellar ataxia

Background Cerebellar ataxia refers to the disturbance in movement resulting from cerebellar dysfunction. It manifests as inaccurate movements with delayed onset and overshoot, especially when movements are repetitive or rhythmic. Identification of ataxia is integral to the diagnosis and assessment of severity, and is important in monitoring progression and improvement. Ataxia is identified and assessed by clinicians observing subjects perform standardised movement tasks that emphasise ataxic movements. Our aim in this paper was to use data recorded from motion sensors worn while subjects performed these tasks, in order to make an objective assessment of ataxia that accurately modelled the clinical assessment. Methods Inertial measurement units and a Kinect© system were used to record motion data while control and ataxic subjects performed four instrumented version of upper extremities tests, i.e. finger chase test (FCT), finger tapping test (FTT), finger to nose test (FNT) and dysdiadochokinesia test (DDKT). Kinematic features were extracted from this data and correlated with clinical ratings of severity of ataxia using the Scale for the Assessment and Rating of Ataxia (SARA). These features were refined using Feed Backward feature Elimination (the best performing method of four). Using several different learning models, including Linear Discrimination, Quadratic Discrimination Analysis, Support Vector Machine and K-Nearest Neighbour these extracted features were used to accurately discriminate between ataxics and control subjects. Leave-One-Out cross validation estimated the generalised performance of the diagnostic model as well as the severity predicting regression model. Results The selected model accurately ($$96.4\%$$ 96.4 % ) predicted the clinical scores for ataxia and correlated well with clinical scores of the severity of ataxia ($$rho = 0.8$$ r h o = 0.8 , $$p < 0.001$$ p < 0.001 ). The severity estimation was also considered in a 4-level scale to provide a rating that is familiar to the current clinically-used rating of upper limb impairments. The combination of FCT and FTT performed as well as all four test combined in predicting the presence and severity of ataxia. Conclusion Individual bedside tests can be emulated using features derived from sensors worn while bedside tests of cerebellar ataxia were being performed. Each test emphasises different aspects of stability, timing, accuracy and rhythmicity of movements. Using the current models it is possible to model the clinician in identifying ataxia and assessing severity but also to identify those test which provide the optimum set of data. Trial registration Human Research and Ethics Committee, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia (HREC Reference Number: 11/994H/16).

A Comprehensive Scheme for the Objective Upper Body Assessments of Subjects with Cerebellar Ataxia

BackgroundCerebellar Ataxia refers to the disturbance in movement resulting from cerebellar dysfunction. It manifests as inaccurate movements with delayed onset and overshoot, especially when movements are repetitive or rhythmic. Identification of ataxia is integral to the diagnosis and assessment of severity, and is important in monitoring progression and improvement. Ataxia is identified and assessed by clinicians observing subjects perform standardised movement tasks that emphasise ataxic movements. Our aim in this paper was to use data recorded from motion sensors worn while subjects performed these tasks, in order to make an objective assessment of ataxia that accurately modelled the clinical assessment.MethodsInertial measurement units and a Kinect system were used to record motion data while control and ataxic subjects performed four instrumented version of upper extremities tests, i.e. Finger Chase Test (FCT), Finger Tapping Test (FTT), Finger to Nose Test (FNT) and Dysdiadochokinesia Test (DDKT). Kinematic features were extracted from this data and correlated with clinical ratings of severity of ataxia using the Scale for the Assessment and Rating of Ataxia (SARA). These features were refined using Feed Backward feature Elimination (the best performing method of four). Using several different learning models, including Linear Discrimination, Quadratic Discrimination Analysis, Support Vector Machine and K-Nearest Neighbour these extracted features were used to accurately discriminate between ataxics and control subjects. Leave-One-Out cross validation estimated the generalised performance of the diagnostic model as well as the severity predicting regression model.ResultsThe selected model accurately (96.4%) predicted the clinical scores for ataxia and correlated well with clinical scores of the severity of ataxia (rho = 0.8, p < 0.001). The severity estimation was also considered in a 4-level scale to provide a rating that is familiar to the current clinically-used rating of upper limb impairments. The combination of FCT and FTT performed as well as all four test combined in predicting the presence and severity of ataxia.ConclusionIndividual bedside tests can be emulated using features derived from sensors worn while bedside tests of cerebellar ataxia were being performed. Each test emphasises different aspects of stability, timing, accuracy and rhythmicity of movements. Using the current models it is possible to model the clinician in identifying ataxia and assessing severity but also to identify those test which provide the optimum set of data.Trial registrationHuman Research and Ethics Committee, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia (HREC Reference Number: 11/994H/16).

A Comprehensive Scheme for the Objective Upper Body Assessments of Subjects with Cerebellar Ataxia

Background Cerebellar ataxia (CA) is a complex motor disorder that exhibits various symptoms such as lack of movement accuracy, delayed motion and ataxic movements associated with gait, extremity and eye. Accurate assessment of ataxic movements forms an integral part, not only in the process of diagnosis, but also to monitor the severity of the neurodegenerative progression, particularly in a rehabilitation context. However, the current assessment schemes are mostly based on the subjective observation of experienced clinicians. Capturing the movement during standard upper limb tests using readily available motion sensors, this paper is intended to amalgamate the sensory information to obtain a more accurate and objective form of assessment. Methods An assessment scheme involving an inertial measurement system and a Kinect system was considered to quantify the degree of ataxia in four instrumented version of upper extremities tests, i.e. Finger Chase (FCT), Finger Tapping (FTT), Finger to Nose (FNT) and Dysdiadochokinesia (DDKT). Kinematic features from these tests were extracted to quantitatively define ataxic signs such as dysmetria, delay in timing, irregularity and instability. Using Feed backward feature elimination (FBE) and Quadratic discrimination analysis (QDA) and Ridge regression (RR), the features were selectively combined to improve the diagnosis and verify the association with clinical assessments by means of Leave-One-Out cross validation. Clinical ratings of the disease status were recorded using the Scale for the Assessment and Rating of Ataxia (SARA). Results We report statistical significance in identifying ataxia from movement features of the four tests. The combined information from the features provided a high accuracy in diagnosing CA subjects (96.4%) in addition to a promising result in predicting the severity of ataxia due to CA (rho=0.8, p<0.001). The severity estimation was also considered in a 4-level scale to provide a rating that is familiar to the current clinically-used rating of upper limb impairments. The combination of FCT and FTT achieve the most acceptable outcome among the considered subsets of the 4 tests. Conclusion The analysis of ataxia can be decomposed primarily into four affected dimensions, i.e. stability, timing, accuracy and rhythmicity. In the context of upper limb tests, the results of accurate classification and prediction of severity attributed mostly to the timing. Furthermore, the underlying approach uncovers the appropriate combination with a reduced number of tests for the assessment of CA utilising the clinical resources more effectively. Trial registration Human Research and Ethics Committee, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia (HREC Reference Number: 11/994H/16).

Quantitative Method to Assess Acute Stress Related Behavior in Dogs by Using Motion Capture Technology

Animal therapy is a form of healthcare intervention conducted with the aid of therapy animals, most commonly dogs. For a therapy dog to play an active role in animal therapy, an animal therapist must design a therapy program, which does not place the dog under stress. Generally, a dogs stress can be evaluated by observing its behavior. However, existing ethological evaluation indices of stress behavior are subjective and obscure, and discrimination between dogs stress behaviors is difficult for observers with insufficient experience. Thus, we propose to quantitatively evaluate behaviors associated with acute stress in dogs. We quantified dog behavior by using a motion capture system. Specifically, body and ear postures such as the opening degree of left and right ears, anteroposterior tilt of left and right ears, height of the vertex above the floor, height of the center of gravity above the floor, and angle between the lateral axis of the body and the floor were recorded using nine motion capture markers. During the experiments, a canine subject was acutely stressed using a tail clamp, and the dogs posture while under stress was quantitatively distinguished from non-stress postures via quadratic discrimination analysis (QDA). From the results, we distinguished the dogs body and ears postures while under acute stress from those under non-stressed conditions with 81% sensitivity and 93% specificity, and a quantitative evaluation of the dogs acute stress behavior was carried out.

Developing a New Computer-Aided Clinical Decision Support System for Prediction of Successful Postcardioversion Patients with Persistent Atrial Fibrillation

We propose a new algorithm to predict the outcome of direct-current electric (DCE) cardioversion for atrial fibrillation (AF) patients. AF is the most common cardiac arrhythmia and DCE cardioversion is a noninvasive treatment to end AF and return the patient to sinus rhythm (SR). Unfortunately, there is a high risk of AF recurrence in persistent AF patients; hence clinically it is important to predict the DCE outcome in order to avoid the procedure’s side effects. This study develops a feature extraction and classification framework to predict AF recurrence patients from the underlying structure of atrial activity (AA). A multiresolution signal decomposition technique, based on matching pursuit (MP), was used to project the AA over a dictionary of wavelets. Seven novel features were derived from the decompositions and were employed in a quadratic discrimination analysis classification to predict the success of post-DCE cardioversion in 40 patients with persistent AF. The proposed algorithm achieved 100% sensitivity and 95% specificity, indicating that the proposed computational approach captures detailed structural information about the underlying AA and could provide reliable information for effective management of AF.

Viabilities of seismic ray impedance and elastic impedance for hydrocarbon-sand discrimination

Theoretical evaluation of the elastic impedance (EI) and the ray impedance (RI) reveals that RI has a more reliable value range and is less sensitive to noise than EI. We devised a new measurement [Formula: see text] to estimate the ray impedance from elastic impedance derived by existing techniques. The recovered [Formula: see text] was expressed in the form of a normalization of EI. It solved the range variability problem of EI and had the same interpretation capability as RI. In addition, reflection coefficients represented by [Formula: see text] showed good agreement with the Zeoppritz equation even at postcritical angle of incidence. Tests of these three attributes (RI, [Formula: see text], and EI) were performed on the log data of three different types of reservoir: a typical Class III marine gas-sand, a Class I tight gas-sand, and a Class II oil-bearing sand in thin sand-mud interbedded layers. Although the crossplots of EI against acoustic impedance (AI) showed visually similar characteristics for a gas-sand as that of RI, based on the linear/quadratic discrimination analysis, RI appeared to be more applicable than EI for characterizing gas sands, especially tight gas sands. [Formula: see text], estimated from EI, had a comparable value range to the AI, and retained the interpretation ability of the original RI. Application on real seismic data showed that existing EI inversion results could be improved straightforwardly by means of the introduced transformation.