Tracking the states of a nonlinear system in the weight-space of a feed-forward neural network

Nonlinear, non-stationary signals are commonly found in a variety of disciplines such as biology, medicine, geology and financial modeling. The complexity (e.g. nonlinearity and non-stationarity) of such signals and their low signal to noise ratios often make it a challenging task to use them in critical applications. In this paper we propose a new neural network based technique to address those problems. We show that a feed forward, multi-layered neural network can conveniently capture the states of a nonlinear system in its connection weight-space, after a process of supervised training. The performance of the proposed method is investigated via computer simulations.

Balancing acts: Respiratory sensations, motor control and human posture

1. The present brief review covers some novel aspects of integration between respiration and movement of the body. 2. There are potent viscerosomatic reflexes in animals involving small-diameter pulmonary afferents that, when excited, would limit exercise. However, recent studies using lobeline injections to excite pulmonary afferents in awake humans suggest that there is no evoked reflex motoneuronal inhibition. Instead, the noxious respiratory sensations generated by the vagal afferents may be crucial in the decision to stop exercise. 3. While respiratory movements may affect limb movements, the control of the trunk and limbs can involve interaction (and even interference) with key respiratory muscles, such as the diaphragm. Recent studies have revealed that not only does the diaphragm receive feed-forward drive prior to some limb movements, but that it also contracts both phasically and tonically during repetitive limb movements. 4. Thus, challenges to posture can indirectly challenge ventilation, while coordinated diaphragm contraction may contribute to control of the trunk.

Delayed postural contraction of transversus abdominis in low back pain associated with movement of the lower limb

The temporal parameters of the response of the trunk muscles associated with movement of the lower limb were investigated in people with and without low back pain (LBP). The weight shift component of the task was completed voluntarily prior to a stimulus to move to allow investigation of the movement component of the response. In the control subjects the onset of electromyographic (EMG) activity of all trunk muscles preceded that of the muscle responsible for limb movement, thus contributing to the feed forward postural response. The EMG onset of transversus abdominis was delayed in the LBP subjects with movement in each direction, while the EMG onsets of rectus abdominis, erector spinae, and oblique abdominal muscles were delayed with specific movement directions. This result provides evidence of a change in the postural control of the trunk in people with LBP.

Experimental muscle pain changes feedforward postural responses of the trunk muscles

Many studies have identified changes in trunk muscle recruitment in clinical low back pain (LBP). However, due to the heterogeneity of the LBP population these changes have been variable and it has been impossible to identify a cause-effect relationship. Several studies have identified a consistent change in the feed-forward postural response of transversus abdominis (TrA), the deepest abdominal muscle, in association with arm movements in chronic LBP. This study aimed to determine whether the feedforward recruitment of the trunk muscles in a postural task could be altered by acute experimentally induced LBP. Electromyographic (EMG) recordings of the abdominal and paraspinal muscles were made during arm movements in a control trial, following the injection of isotonic (non-painful) and hypertonic (painful) saline into the longissimus muscle at L4, and during a 1-h follow-up. Movements included rapid arm flexion in response to a light and repetitive arm flexion-extension. Temporal and spatial EMG parameters were measured. The onset and amplitude of EMG of most muscles was changed in a variable manner during the period of experimentally induced pain. However, across movement trials and subjects the activation of TrA was consistently reduced in amplitude or delayed. Analyses in the time and frequency domain were used to confirm these findings. The results suggest that acute experimentally induced pain may affect feedforward postural activity of the trunk muscles. Although the response was variable, pain produced differential changes in the motor control of the trunk muscles, with consistent impairment of TrA activity.

Spatio-temporal evaluation of neck muscle activation during postural perturbations in healthy subjects

The purpose of this study was to examine the spatio-temporal activation of the sternocleidomastoid (SCM) and cervical extensor (CE) muscles with respect to the deltoid muscle onset during rapid voluntary upper limb movement in healthy volunteers. The repeatability and reliability of the spatio-temporal aspects of the myoelectric signals were also examined. Ten subjects performed bilateral and unilateral rapid upper limb flexion, abduction and extension in response to a visual stimulus. EMG onsets and normalised root mean square (nRMS) values were calculated for the SCM and CE muscles. Subjects attended three testing sessions over non-consecutive days allowing the repeatability and reliability of these measures to be assessed. The SCM and CE muscles demonstrated feed-forward activation (activation within 50 ms of deltoid onset) during rapid arm movements in all directions. The sequence and magnitude of neck muscle activation displayed directional specificity, however, the neck flexor and extensor muscles displayed co-activation during all perturbations. EMG onsets demonstrated high repeatability in terms of repeated measure precision (nSEM in the range 1.9-5.7%). This was less evident for the repeatability of nRMS values. The results of this study provide a greater understanding of cervical neuromotor control strategies. During bilateral and unilateral upper limb perturbations, the SCM and CE muscles demonstrate feed-forward co-activation. It seems apparent that feed-forward activation of neck muscles is a mechanism necessary to achieve stability for the visual and vestibular systems, whilst ensuring stabilisation and protection of the cervical spine. (C) 2004 Elsevier Ltd. All rights reserved.

Delayed onset of transversus abdominus in long-standing groin pain

Long-standing groin pain is a persistent problem that is commonly difficult to rehabilitate. Theoretical rationale indicates a relationship between the motor control of the pelvis and long-standing groin pain; however, this link has not been investigated. Purpose: The current experiment aimed to evaluate motor control of the abdominal muscles in a group of Australian football players with and without long-standing groin pain. Methods: Ten participants with long-standing groin pain and 12 asymptomatic controls were recruited for the study. Participants were elite or subelite Australian football players. Fine-wire and surface electromyography electrodes were used to record the activity of the selected abdominal and leg muscles during a visual choice reaction-time task (active straight leg raising). Results: When the asymptomatic controls completed the active straight leg raise (ASLR) task, the transversus abdominus contracted in a feed-forward manner. However, when individuals with long-standing groin pain completed the ASLR task, the onset of transversus abdominus was delayed (P < 0.05) compared with the control group. There were no differences between groups for the onset of activity of internal oblique, external oblique, and rectus abdominus (all P > 0.05). Conclusions: The finding that the onset of transversus abdominus is delayed in individuals with long-standing groin pain is important, as it demonstrates an association between long-standing groin pain and transversus abdominus activation.

Biologically inspired joint control for a humanoid robot

The GuRm is a 1.2m tall, 23 degree of freedom humanoid consuucted at the University of Queensland for research into humanoid robotics. The key challenge being addressed by the GuRw projcct is the development of appropriate learning strategies for control and coodinadon of the robot’s many joints. The development of learning strategies is Seen as a way to sidestep the inherent intricacy of modeling a multi-DOP biped robot. This paper outlines the approach taken to generate an appmpria*e control scheme for the joinis of the GuRoo. The paper demonsrrates the determination of local feedback control parameters using a genetic algorithm. The feedback loop is then augmented by a predictive modulator that learns a form of feed-fonward control to overcome the irregular loads experienced at each joint during the gait cycle. The predictive modulator is based on thc CMAC architecture. Results from tats on the GuRoo platform show that both systems provide improvements in stability and tracking of joint control.

Nonlinear quantum optical computing via measurement

We show how the measurement induced model of quantum computation proposed by Raussendorf and Briegel ( 2001, Phys. Rev. Letts., 86, 5188) can be adapted to a nonlinear optical interaction. This optical implementation requires a Kerr nonlinearity, a single photon source, a single photon detector and fast feed forward. Although nondeterministic optical quantum information proposals such as that suggested by KLM ( 2001, Nature, 409, 46) do not require a Kerr nonlinearity they do require complex reconfigurable optical networks. The proposal in this paper has the benefit of a single static optical layout with fixed device parameters, where the algorithm is defined by the final measurement procedure.

Optimal photons for quantum-information processing

Photonic quantum-information processing schemes, such as linear optics quantum computing, and other experiments relying on single-photon interference, inherently require complete photon indistinguishability to enable the desired photonic interactions to take place. Mode-mismatch is the dominant cause of photon distinguishability in optical circuits. Here we study the effects of photon wave-packet shape on tolerance against the effects of mode mismatch in linear optical circuits, and show that Gaussian distributed photons with large bandwidth are optimal. The result is general and holds for arbitrary linear optical circuits, including ones which allow for postselection and classical feed forward. Our findings indicate that some single photon sources, frequently cited for their potential application to quantum-information processing, may in fact be suboptimal for such applications.

Prediction of subcellular localization using sequence-biased recurrent networks

Motivation: Targeting peptides direct nascent proteins to their specific subcellular compartment. Knowledge of targeting signals enables informed drug design and reliable annotation of gene products. However, due to the low similarity of such sequences and the dynamical nature of the sorting process, the computational prediction of subcellular localization of proteins is challenging. Results: We contrast the use of feed forward models as employed by the popular TargetP/SignalP predictors with a sequence-biased recurrent network model. The models are evaluated in terms of performance at the residue level and at the sequence level, and demonstrate that recurrent networks improve the overall prediction performance. Compared to the original results reported for TargetP, an ensemble of the tested models increases the accuracy by 6 and 5% on non-plant and plant data, respectively.

The applicability of recurrent neural networks for biological sequence analysis

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Effect of supplementation with a by-product of molasses fermentation or a non-protein nitrogen/mineral mix on feed intake and microbial protein supply in sheep consuming chopped oat (Avena sativa) hay

Crossbred ewes, weighing 30-40 kg, were assigned to three groups of six animals. One group of sheep was fed chopped oat hay (control), the second group was fed the control diet plus 30 g per head per day spray dried residue from the fermentation of molasses and the third group was fed the control diet plus 30 g per head per day of a non-protein nitrogen/mineral mix. Voluntary feed intake, digestibility of DM, OM and nitrogen, nitrogen balance and microbial nitrogen flow to the intestines were significantly increased by supplementation but efficiency of microbial protein production was not affected. (C) 2001 Elsevier Science BN. All rights reserved,

Cleaner wrasse prefer client mucus: support for partner control mechanisms in cleaning interactions

Recent studies on cleaning behaviour suggest that there are conflicts between cleaners and their clients over what cleaners eat. The diet of cleaners usually contains ectoparasites and some client tissue. It is unclear, however, whether cleaners prefer client tissue over ectoparasites or whether they include client tissue in their diet only when searching for parasites alone is not profitable. To distinguish between these two hypotheses, we trained cleaner fish Labroides dimidiatus to feed from plates and offered them client mucus from the parrotfish Chlorurus sordidus, parasitic monogenean flat-worms, parasitic gnathiid isopods and boiled flour glue as a control. We found that cleaners ate more mucus and monogeneans than gnathiids, with gnathiids eaten slightly more often than the control substance. Because gnathiids are the most abundant ectoparasites, our results suggest a potential for conflict between cleaners and clients over what the cleaner should eat, and support studies emphasizing the importance of partner control in keeping cleaning interactions mutualistic.

Robust multivariable control of complex biological processes

This paper addresses advanced control of a biological nutrient removal (BNR) activated sludge process. Based on a previously validated distributed parameter model of the BNR activated sludge process, we present robust multivariable controller designs for the process, involving loop shaping of plant model, robust stability and performance analyses. Results from three design case studies showed that a multivariable controller with stability margins of 0.163, 0.492 and 1.062 measured by the normalised coprime factor, multiplicative and additive uncertainties respectively give the best results for meeting performance robustness specifications. The controller robustly stabilises effluent nutrients in the presence of uncertainties with the behaviour of phosphorus accumulating organisms as well as to effectively attenuate major disturbances introduced as step changes. This study also shows that, performance of the multivariable robust controller is superior to multi-loops SISO PI controllers for regulating the BNR activated sludge process in terms of robust stability and performance and controlling the process using inlet feed flowrate is infeasible. (C) 2003 Elsevier Ltd. All rights reserved.

Are the changes in postural control associated with low back pain caused by pain interference?

Background: Voluntary limb movements are associated with involuntary and automatic postural adjustments of the trunk muscles. These postural adjustments occur prior to movement and prevent unwanted perturbation of the trunk. In low back pain, postural adjustments of the trunk muscles are altered such that the deep trunk muscles are consistently delayed and the superficial trunk muscles are sometimes augmented. This alteration of postural adjustments may reflect disruption of normal postural control imparted by reduced central nervous system resources available during pain, so-called pain interference, or reflect adoption of an alternate postural adjustment strategy. Methods: We aimed to clarify this by recording electromyographic activity of the upper (obliquus extemus) and lower (transversus abdominis/obliquus internus) abdominal muscles during voluntary arm movements that were coupled with painful cutaneous stimulation at the low back. If the effect of pain on postural adjustments is caused by pain interference, it should be greatest at the onset of the stimulus, should habituate with repeated exposure, and be absent immediately when the threat of pain is removed. Sixteen patients performed 30 forward movements of the right arm in response to a visual cue (control). Seventy trials were then conducted in which arm movement was coupled with pain (pain trials) and then a further 70 trials were conducted without the pain stimulus (no pain trials). Results: There was a gradual and increasing delay of transversus abdominis/obliquus internus electromyograph and augmentation of obliquus externus during the pain trials, both of which gradually returned to control values during the no pain trials. Conclusion: The results suggest that altered postural adjustments of the trunk muscles during pain are not caused by pain interference but are likely to reflect development and adoption of an alternate postural adjustment strategy, which may serve to limit the amplitude and velocity of trunk excursion caused by arm movement.