Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts

Clinical gait analysis has proven to reduce uncertainties in selecting the appropriate quantity and type of treatment for patients with neuromuscular disorders. However, gait analysis as a clinical tool is under-utilised due to the limitations and cost of acquiring and managing data. To overcome these obstacles, inertial motion capture (IMC) recently emerged to counter the limitations attributed to other methods. This paper investigates the use of IMC for training and testing a back-propagation artificial neural network (ANN) for the purpose of distinguishing between hemiparetic stroke and able-bodied ambulation. Routine gait analysis was performed on 30 able-bodied control subjects and 28 hemiparetic stroke patients using an IMC system. An ANN was optimised to classify the two groups, achieving a repeatable network accuracy of 99.4%. It is concluded that an IMC system and appropriate computer methods may be useful for the planning and monitoring of gait rehabilitation therapy of stroke victims.     

Predicting final extent of ischemic infarction using artificial neural network analysis of multi-parametric MRI in patients with stroke

In hemispheric ischemic stroke, the final size of the ischemic lesion is the most important correlate of clinical functional outcome. Using a set of acute-phase MR images (Diffusion-weighted - DWI, T₁-weighted – T1WI, T₂-weighted-T2WI, and proton density weighted - PDWI) for inputs, and the chronic T2WI at 3 months as an outcome measure, an Artificial Neural Network (ANN) was trained to predict the 3-month outcome in the form of a voxel-by-voxel forecast of the chronic T2WI. The ANN was trained and tested using 12 subjects (with 83 slices and 140218 voxels) using a leave-one-out cross-validation method with calculation of the Area Under the Receiver Operator Characteristic Curve (AUROC) for training, testing and optimization of the ANN. After training and optimization, the ANN produced maps of predicted outcome that were well correlated (r = 0.80, p<0.0001) with the T2WI at 3 months for all 12 patients. This result implies that the trained ANN can provide an estimate of 3-month ischemic lesion on T2WI in a stable and accurate manner (AUROC = 0.89).     

Recognition of culture state using two-dimensional gel electrophoresis with an artificial neural network

Proteomic technologies were applied to the examination of nutrient components in culture broth. In bioprocesses, many types of media have been proposed and used on the commercial scale. Natural nutrients, the chemical components of which cannot be identified completely, are often used in fermentation processes such as in the production of baker's yeast, alcoholic beverages, amino acids, and pharmaceuticals. The catabolic activities of the microorganisms in these processes vary with the species used. We used an artificial neural network (ANN) to recognize the sufficiency of chemical elements based on the protein spots resolved in 2-DE, and we evaluated this technique using the leave-one-out method. We also attempted to reduce the number of input data for spot selection based on sensitivity analysis of the ANN, and the selected data were used to improve accuracy.     

Emergence of gamma motor activity in an artificial neural network model of the corticospinal system

Muscle spindle discharge during active movement is a function of mechanical and neural parameters. Muscle length changes (and their derivatives) represent its primary mechanical, fusimotor drive its neural component. However, neither the action nor the function of fusimotor and in particular of γ-drive, have been clearly established, since γ-motor activity during voluntary, non-locomotor movements remains largely unknown. Here, using a computational approach, we explored whether γ-drive emerges in an artificial neural network model of the corticospinal system linked to a biomechanical antagonist wrist simulator. The wrist simulator included length-sensitive and γ-drive-dependent type Ia and type II muscle spindle activity. Network activity and connectivity were derived by a gradient descent algorithm to generate reciprocal, known target α-motor unit activity during wrist flexion-extension (F/E) movements. Two tasks were simulated: an alternating F/E task and a slow F/E tracking task. Emergence of γ-motor activity in the alternating F/E network was a function of α-motor unit drive: if muscle afferent (together with supraspinal) input was required for driving α-motor units, then γ-drive emerged in the form of α-γ coactivation, as predicted by empirical studies. In the slow F/E tracking network, γ-drive emerged in the form of α-γ dissociation and provided critical, bidirectional muscle afferent activity to the cortical network, containing known bidirectional target units. The model thus demonstrates the complementary aspects of spindle output and hence γ-drive: i) muscle spindle activity as a driving force of α-motor unit activity, and ii) afferent activity providing continuous sensory information, both of which crucially depend on γ-drive.     

QSAR study of the enantiomeric excess in asymmetric catalytic reactions with topological indices and an artificial neural network

The relationships between the enantiomer excess of product in catalytic asymmetric reactions and the structures of the catalysts or reagents in several asymmetric reactions were studied using a backpropagation (BP) neural network with topological indices and their chiral expansions. The trained network can be used to screen new asymmetric catalysts, estimate catalytic effects, design reaction environments, and prove or improve the proposed reaction mechanism.     

Calculation of the Volterra kernels of non-linear dynamic systems using an artificial neural network

The Volterra series is a well-known method of describing non-linear dynamic systems. A major limitation of this technique is the difficulty involved in the calculation of the kernels. More recently, artificial neural networks have been used to produce black box models of non-linear dynamic systems. In this paper we show how a certain class of artificial neural networks are equivalent to Volterra series and give the equation for the nth order Volterra kernel in terms of the internal parameters of the network. The technique is then illustrated using a specific non-linear system. The kernels obtained by the method described in the paper are compared with those obtained by a Toeplitz matrix inversion technique. Received: 4 June 1993/Accepted in revised form: 2 March 1994     

Character displacement and the evolution of mate choice: an artificial neural network approach

Interactions with heterospecifics can promote the evolution of divergent mating behaviours between populations that do and do not occur with heterospecifics. This process--reproductive character displacement--potentially results from selection to minimize the risk of mating with heterospecifics. We sought to determine whether heterospecific interactions lead to divergence of female preferences for aspects of conspecific male signals. We used artificial neural network models to simulate a mate recognition system in which females co-occur with different heterospecifics in different populations. Populations that evolved conspecific recognition in the presence of different heterospecifics varied in their preferences for aspects of conspecific male signals. When we tested networks for their preferences of conspecific versus heterospecific signals, however, we found that networks from allopatric populations were usually able to select against heterospecifics. We suggest that female preferences for aspects of conspecific male signals can result in a concomitant reduction in the likelihood that females will mate with heterospecifics. Consequently, even females in allopatry may discriminate against heterospecific mates depending on the nature of their preferences for conspecifics. Such a pattern could potentially explain cases where reproductive character displacement is expected, but not observed.     

Multi-sensor assessment of dynamic balance during gait in patients with subacute stroke

The capacity to maintain upright balance by minimising upper body oscillations during walking, also referred to as gait stability, has been associated with a decreased risk of fall. Although it is well known that fall is a common complication after stroke, no study considered the role of both trunk and head when assessing gait stability in this population. The primary aim of this study was to propose a multi-sensor protocol to quantify gait stability in patients with subacute stroke using gait quality indices derived from pelvis, sternum, and head accelerations. Second, the association of these indices with the level of walking ability, with traditional clinical scale scores, and with fall events occurring within the six months after patients’ dismissal was investigated. The accelerations corresponding to the three abovementioned body levels were measured using inertial sensors during a 10-Meter Walk Test performed by 45 inpatients and 25 control healthy subjects. A set of indices related to gait stability were estimated and clinical performance scales were administered to each patient. The amplitude of the accelerations, the way it is attenuated/amplified from lower to upper body levels, and the gait symmetry provide valuable information about subject-specific motor strategies, discriminate between different levels of walking ability, and correlate with clinical scales. In conclusion, the proposed multi-sensor protocol could represent a useful tool to quantify gait stability, support clinicians in the identification of patients potentially exposed to a high risk of falling, and assess the effectiveness of rehabilitation protocols in the clinical routine.     

The application of an artificial neural network in the identification of medicinal rhubarbs by near-infrared spectroscopy

This paper describes a method to combine near-infrared spectroscopy and a three layer back-propagation artificial neural network in order to identify official and unofficial rhubarbs. Thirty-three samples were taken as the training set, and 62 samples as the test set. The effects of input node number, learning rate and momentum on the final error and recognition accuracy for the training set, and on prediction accuracy for the test set were determined. A neural network with eight input nodes, a 0.5 learning rate, and a momentum of 0.3 can achieve a recognition accuracy of 100% for the training set and a prediction accuracy of 96.8% for the test set. The method described offers a quick and efficient means of identifying rhubarbs.     

Simple network motifs can capture key characteristics of the floral transition in Arabidopsis

The floral transition is a key decision during plant development. While different species have evolved diverse pathways to respond to different environmental cues to flower in the correct season, key properties such as irreversibility and robustness to fluctuating signals appear to be conserved. We have used mathematical modeling to demonstrate how minimal regulatory networks of core components are sufficient to capture these behaviors. Simplified models inevitably miss finer details of the biological system, yet they provide a tractable route to understanding the overall system behavior. We combined models with experimental data to qualitatively reproduce characteristics of the floral transition and to quantitatively scale the network to fit with available leaf numbers. Our study highlights the value of pursuing an iterative approach combining modeling with experimental work to capture key features of complex systems.     

Systematic perturbation of an artificial neural network: A step towards quantifying causal contributions in the brain

Lesion inference analysis is a fundamental approach for characterizing the causal contributions of neural elements to brain function. This approach has gained new prominence through the arrival of modern perturbation techniques with unprecedented levels of spatiotemporal precision. While inferences drawn from brain perturbations are conceptually powerful, they face methodological difficulties. Particularly, they are challenged to disentangle the true causal contributions of the involved elements, since often functions arise from coalitions of distributed, interacting elements, and localized perturbations have unknown global consequences. To elucidate these limitations, we systematically and exhaustively lesioned a small artificial neural network (ANN) playing a classic arcade game. We determined the functional contributions of all nodes and links, contrasting results from sequential single-element perturbations with simultaneous perturbations of multiple elements. We found that lesioning individual elements, one at a time, produced biased results. By contrast, multi-site lesion analysis captured crucial details that were missed by single-site lesions. We conclude that even small and seemingly simple ANNs show surprising complexity that needs to be addressed by multi-lesioning for a coherent causal characterization.     

上海市景观格局的人工神经网络(ANN)模型

定量分析城市景观的空间格局,深入研究景观格局的形成机制,将有助于理解城市景观的格局与过程,分析城市化的社会、经济和生态学后果以及制定更有效的景观管理策略。研究以城市景观生态学途径,应用基于GIS的景观格局分析与人工神经网络(ANN)相结合的方法定量分析上海市城市景观格局(1994年)及其变化规律,建立了能够较好地模拟上海市景观格局对居住区用地、道路密度、人口密度、城市发展历史与黄浦江等自然、社会、经济因素响应的人工神经网络。结果表明,人工神经网络方法适于研究城市化驱动因素与城市景观格局的非线性对应关系,为景观格局形成机制和景观空间结构与生态学过程相互关系的深入研究提供了一条有效、实用的研究途径。     

Application of an artificial neural network (ANN) model for predicting mosquito abundances in urban areas

The mosquito species is one of most important insect vectors of several diseases, namely, malaria, filariasis, Japanese encephalitis, dengue, and so on. In particular, in recent years, as the number of people who enjoy outdoor activities in urban areas continues to increase, information about mosquito activity is in demand. Furthermore, mosquito activity prediction is crucial for managing the safety and the health of humans. However, the estimation of mosquito abundances frequently involves uncertainty because of high spatial and temporal variations, which hinders the accuracy of general mechanistic models of mosquito abundances. For this reason, it is necessary to develop a simpler and lighter mosquito abundance prediction model. In this study, we tested the efficacy of the artificial neural network (ANN), which is a popular empirical model, for mosquito abundance prediction. For comparison, we also developed a multiple linear regression (MLR) model. Both the ANN and the MLR models were applied to estimate mosquito abundances in 2-year observations in Yeongdeungpo-gu, Seoul, conducted using the Digital Mosquito Monitoring System (DMS). As input variables, we used meteorological data, including temperature, wind speed, humidity, and precipitation. The results showed that performances of the ANN model and the MLR model are almost same in terms of R and root mean square error (RMSE). The ANN model was able to predict the high variability as compared to MLR. A sensitivity analysis of the ANN model showed that the relationships between input variables and mosquito abundances were well explained. In conclusion, ANNs have the potential to predict fluctuations in mosquito numbers (especially the extreme values), and can do so better than traditional statistical techniques. But, much more work needs to be conducted to assess meaningful time delays in environmental variables and mosquito numbers.     

Finding fossils in new ways: an artificial neural network approach to predicting the location of productive fossil localities

Chance and serendipity have long played a role in the location of productive fossil localities by vertebrate paleontologists and paleoanthropologists. We offer an alternative approach, informed by methods borrowed from the geographic information sciences and using recent advances in computer science, to more efficiently predict where fossil localities might be found. Our model uses an artificial neural network (ANN) that is trained to recognize the spectral characteristics of known productive localities and other land cover classes, such as forest, wetlands, and scrubland, within a study area based on the analysis of remotely sensed (RS) imagery. Using these spectral signatures, the model then classifies other pixels throughout the study area. The results of the neural network classification can be examined and further manipulated within a geographic information systems (GIS) software package. While we have developed and tested this model on fossil mammal localities in deposits of Paleocene and Eocene age in the Great Divide Basin of southwestern Wyoming, a similar analytical approach can be easily applied to fossil-bearing sedimentary deposits of any age in any part of the world. We suggest that new analytical tools and methods of the geographic sciences, including remote sensing and geographic information systems, are poised to greatly enrich paleoanthropological investigations, and that these new methods should be embraced by field workers in the search for, and geospatial analysis of, fossil primates and hominins.     

Artificial neural network properties associated with wiring patterns in the visual projections of vertebrates and arthropods

We model the functioning of different wiring schemes in visual projections using artificial neural networks and so speculate on selective factors underlying taxonomic variation in neural architecture. We model the high connective overlap of vertebrates (where networks have a dense mesh of connections) and the less overlapping, more modular architecture of arthropods. We also consider natural variation in these basic wiring schemes. Generally, arthropod networks are as efficient or more efficient in functioning compared to vertebrate networks. They do not show the confusion effect (decreasing targeting accuracy with increasing input group size), and they train as well or better. Arthropod networks are, however, generally poorer at reconstructing novel inputs. The ability of vertebrate networks to effectively process novel stimuli could promote behavioral sophistication and drive the evolution of vertebrate wiring schemes. Vertebrate networks with less connective overlap have, surprisingly, similar or superior properties compared to those with high connective overlap. Thus, the partial connective overlap seen in real vertebrate visual projections may be an optimal, evolved solution. Arthropod networks with and without whole-cell neural connections within neural layers have similar properties. This indicates that neural connections mediated by offshoots of single cells (dendrites) may be fundamental to generating the confusion effect.     

Kinematic parameters of throwing performance in patients with schizophrenia using a markerless motion capture system

Abstract

Motor dysfunction is consistently reported but understudied in schizophrenia. It has been hypothesized that this abnormality may reflect a neuro-developmental disorder underlying this illness. The main goal of this study was to analyze movement patterns used by participants with schizophrenia and healthy controls during overarm throwing performance, using a markerless motion capture system. Thirteen schizophrenia patients and 16 healthy control patients performed the overarm throwing task in a markerless motion capture system. Participants were also examined for the presence of motor neurological soft signs (mNSS) using the Brief Motor Scale. Schizophrenia patients demonstrated a less developed movement pattern with low individualization of components compared to healthy controls. The schizophrenia group also displayed a higher incidence of mNSS. The presence of a less mature movement pattern can be an indicator of neuro-immaturity and a marker for atypical neurological development in schizophrenia. Our findings support the understanding of motor dysfunction as an intrinsic part of the disorder of schizophrenia.     

Modelling of glucoamylase thermal inactivation in the presence of starch by artificial neural network

Thermal inactivation is suspected to be a limiting factor for use of glucoamylase in starch saccharification at elevated temperatures. Thus, inactivation of the enzyme has been studied in the presence of reagents (enzyme, substrate and product in wide range of concentrations, and moderate stirring). The influence of substrate and glucose as stability modulators showed the complexity of the studied system. Hence, one might expect multilateral correlations that could depreciate some efforts for phenomenological modelling. These obstacles forced to apply artificial neural network (ANN) modelling to map the enzyme activity decays. For this purpose, a dynamic network with four hidden neurons was selected. The database containing 42 data vectors was used for neural model training and verification process. The standard error of calculations and correlation coefficient (0.997-0.999) for dynamic simulations has proved correctness of the developed ANN.     

Neuropathological findings processed by artificial neural networks (ANNs) can perfectly distinguish Alzheimer's patients from controls in the Nun Study

Background  

Many reports have described that there are fewer differences in AD brain neuropathologic lesions between AD patients and control subjects aged 80 years and older, as compared with the considerable differences between younger persons with AD and controls. In fact some investigators have suggested that since neurofibrillary tangles (NFT) can be identified in the brains of non-demented elderly subjects they should be considered as a consequence of the aging process. At present, there are no universally accepted neuropathological criteria which can mathematically differentiate AD from healthy brain in the oldest old.