Investigating machine learning techniques for detection of depression using structural MRI volumetric features

Structural MRI offers anatomical details and high sensitivity to pathological changes. It can demonstrate certain patterns of brain changes present at a structural level. Research to date has shown that volumetric analysis of brain regions has importance in depression detection. However, such analysis has had very minimal use in depression detection studies at individual level. Optimally combining various brain volumetric features/attributes, and summarizing the data into a distinctive set of variables remain difficult. This study investigates machine learning algorithms that automatically identify relevant data attributes for depression detection. Different machine learning techniques are studied for depression classification based on attributes extracted from structural MRI (sMRI) data. The attributes include volume calculated from whole brain, white matter, grey matter and hippocampus. Attributes subset selection is performed aiming to remove redundant attributes using three filtering methods and one hybrid method, in combination with ranker search algorithms. The highest average classification accuracy, obtained by using a combination of both SVM-EM and IG-Random Tree algorithms, is 85.23%. The classification approach implemented in this study can achieve higher accuracy than most reported studies using sMRI data, specifically for detection of depression.

Personal resilience in times of crisis : the implications of SWB homeostasis and set-points

Our companion paper (Cummins et al. in J Happiness Stud, 2013) describes the statistical process used to demonstrate set-points and set-point-ranges for subjective wellbeing. The implications of set-points and homeostasis are now considered in the context of resilience. This discussion leads with a brief overview of resilience definitions and is followed by a description of subjective wellbeing (SWB) homeostasis. This addresses, in particular, the issue of SWB malleability under homeostatic control. The link between resources and resilience is then considered, in terms of predictions made by homeostasis theory. Finally, discussion focuses on the implications of such understanding for future directions in SWB research. It is concluded that an understanding of set-points and homeostasis allows new insights into the resilience construct.

A demonstration of set-points for subjective wellbeing

This paper presents evidence for the existence of ‘set-points’ for subjective wellbeing. Our results derive from a 10-year longitudinal study in which subjective wellbeing has been measured using a single question of general life satisfaction. The process of data analysis is driven by logic based on the theory of subjective wellbeing homeostasis. This analysis involves the iterative elimination of raw data, from 7,356 individual respondents, based on confidence limits. All results are projected onto a 0–100 point scale. We demonstrate evidence for the existence of set-points lying between 71 and 90 points, with an average set-point-range of 18–20 points for each person. The implications and limitations of these findings are discussed.

Efficient mining of top-k breaker emerging subgraph patterns from graph datasets

This paper introduces a new type of discriminative subgraph pattern called breaker emerging subgraph pattern by introducing three constraints and two new concepts: base and breaker. A breaker emerging sub-graph pattern consists of three subpatterns: a con-strained emerging subgraph pattern, a set of bases and a set of breakers. An efficient approach is pro-posed for the discovery of top-k breaker emerging sub-graph patterns from graph datasets. Experimental re-sults show that the approach is capable of efficiently discovering top-k breaker emerging subgraph patterns from given datasets, is more efficient than two previ-ous methods for mining discriminative subgraph pat-terns. The discovered top-k breaker emerging sub-graph patterns are more informative, more discrim-inative, more accurate and more compact than the minimal distinguishing subgraph patterns. The top-k breaker emerging patterns are more useful for sub-structure analysis, such as molecular fragment analy-sis. © 2009, Australian Computer Society, Inc.

Partial state estimation for linear systems with output and input time delays.

This paper deals with the problem of partial state observer design for linear systems that are subject to time delays in the measured output as well as the control input. By choosing a set of appropriate augmented Lyapunov-Krasovskii functionals with a triple-integral term and using the information of both the delayed output and input, a novel approach to design a minimal-order observer is proposed to guarantee that the observer error is ε-convergent with an exponential rate. Existence conditions of such an observer are derived in terms of matrix inequalities for the cases with time delays in both the output and input and with output delay only. Constructive design algorithms are introduced. Numerical examples are provided to illustrate the design procedure, practicality and effectiveness of the proposed observer.

Reachable set bounding for nonlinear perturbed time-delay systems: the smallest bound

In this letter, we propose a new approach to obtain the smallest box which bounds all reachable sets of a class of nonlinear time-delay systems with bounded disturbances. A numerical example is studied to illustrate the obtained result.

Localized learning by emerging multinational enterprises in developed host countries: a fuzzy-set analysis of Chinese foreign direct investment in Australia

Firms learn general international management and foreign market specific knowledge in their internationalization process. Firms' strategic emphasis on generalized vs. localized learning is an important yet underexplored issue in the extant literature. Drawing on the theoretical framework of dynamic capability, and in the context of emerging multinational enterprises' FDI into developed host countries, this study examines the equifinal process-position-path configurations of firms that will motivate them to engage in localized learning (as opposed to generalized learning). Utilizing primary and secondary data of eleven Chinese foreign direct investments in Australia, collected at both headquarters and subsidiary levels, we conducted fuzzy-set qualitative comparative analysis (fsQCA) that provided substantial support to our propositions. This study contributes to the internationalization process model by identifying equifinal process-position-path configurations, as well as their core and peripheral conditions that motivate localized learning at both the headquarters and the subsidiary levels.

Functional range of movement of the hand : declination angles to reachable space

 The measurement of the range of hand joint movement is an essential part of clinical practice and rehabilitation. Current methods use three finger joint declination angles of the metacarpophalangeal, proximal interphalangeal and distal interphalangeal joints. In this paper we propose an alternate form of measurement for the finger movement. Using the notion of reachable space instead of declination angles has significant advantages. Firstly, it provides a visual and quantifiable method that therapists, insurance companies and patients can easily use to understand the functional capabilities of the hand. Secondly, it eliminates the redundant declination angle constraints. Finally, reachable space, defined by a set of reachable fingertip positions, can be measured and constructed by using a modern camera such as Creative Senz3D or built-in hand gesture sensors such as the Leap Motion Controller. Use of cameras or optical-type sensors for this purpose have considerable benefits such as eliminating and minimal involvement of therapist errors, non-contact measurement in addition to valuable time saving for the clinician. A comparison between using declination angles and reachable space were made based on Hume's experiment on functional range of movement to prove the efficiency of this new approach.

MicroRNA-23a has minimal effect on endurance exercise-induced adaptation of mouse skeletal muscle.

Skeletal muscles contain several subtypes of myofibers that differ in contractile and metabolic properties. Transcriptional control of fiber-type specification and adaptation has been intensively investigated over the past several decades. Recently, microRNA (miRNA)-mediated posttranscriptional gene regulation has attracted increasing attention. MiR-23a targets key molecules regulating contractile and metabolic properties of skeletal muscle, such as myosin heavy-chains and peroxisome proliferator-activated receptor gamma, coactivator 1 alpha (PGC-1α). In the present study, we analyzed the skeletal muscle phenotype of miR-23a transgenic (miR-23a Tg) mice to explore whether forced expression of miR-23a affects markers of mitochondrial content, muscle fiber composition, and muscle adaptations induced by 4 weeks of voluntary wheel running. When compared with wild-type mice, protein markers of mitochondrial content, including PGC-1α, and cytochrome c oxidase complex IV (COX IV), were significantly decreased in the slow soleus muscle, but not the fast plantaris muscle of miR-23a Tg mice. There was a decrease in type IId/x fibers only in the soleus muscle of the Tg mice. Following 4 weeks of voluntary wheel running, there was no difference in the endurance exercise capacity as well as in several muscle adaptive responses including an increase in muscle mass, capillary density, or the protein content of myosin heavy-chain IIa, PGC-1α, COX IV, and cytochrome c. These results show that miR-23a targets PGC-1α and regulates basal metabolic properties of slow but not fast twitch muscles. Elevated levels of miR-23a did not impact on whole body endurance capacity or exercise-induced muscle adaptations in the fast plantaris muscle.

Individualized arrhythmia detection with ECG signals from wearable devices

Low cost pervasive electrocardiogram (ECG) monitors is changing how sinus arrhythmia are diagnosed among patients with mild symptoms. With the large amount of data generated from long-term monitoring, come new data science and analytical challenges. Although traditional rule-based detection algorithms still work on relatively short clinical quality ECG, they are not optimal for pervasive signals collected from wearable devices - they don't adapt to individual difference and assume accurate identification of ECG fiducial points. To overcome these short-comings of the rule-based methods, this paper introduces an arrhythmia detection approach for low quality pervasive ECG signals. To achieve the robustness needed, two techniques were applied. First, a set of ECG features with minimal reliance on fiducial point identification were selected. Next, the features were normalized using robust statistics to factors out baseline individual differences and clinically irrelevant temporal drift that is common in pervasive ECG. The proposed method was evaluated using pervasive ECG signals we collected, in combination with clinician validated ECG signals from Physiobank. Empirical evaluation confirms accuracy improvements of the proposed approach over the traditional clinical rules.