Significant Error Rate Reduction Research Articles

Myoelectric feature extraction using temporal-spatial descriptors for multifunction prosthetic hand control.

We tackle the challenging problem of myoelectric prosthesis control with an improved feature extraction algorithm. The proposed algorithm correlates a set of spectral moments and their nonlinearly mapped version across the temporal and spatial domains to form accurate descriptors of muscular activity. The main processing step involves the extraction of the Electromyogram (EMG) signal power spectrum characteristics directly from the time-domain for each analysis window, a step to preserve the computational power required for the construction of spectral features. The subsequent analyses involve computing 1) the correlation between the time-domain descriptors extracted from each analysis window and a nonlinearly mapped version of it across the same EMG channel; representing the temporal evolution of the EMG signals, and 2) the correlation between the descriptors extracted from differences of all possible combinations of channels and a nonlinearly mapped version of them, focusing on how the EMG signals from different channels correlates with each other. The proposed Temporal-Spatial Descriptors (TSDs) are validated on EMG data collected from six transradial amputees performing 11 classes of finger movements. Classification results showed significant reductions (at least 8%) in classification error rates compared to other methods.

Improving the Performance Against Force Variation of EMG Controlled Multifunctional Upper-Limb Prostheses for Transradial Amputees.

We investigate the problem of achieving robust control of hand prostheses by the electromyogram (EMG) of transradial amputees in the presence of variable force levels, as these variations can have a substantial impact on the robustness of the control of the prostheses. We also propose a novel set of features that aim at reducing the impact of force level variations on the prosthesis controlled by amputees. These features characterize the EMG activity by means of the orientation between a set of spectral moments descriptors extracted from the EMG signal and a nonlinearly mapped version of it. At the same time, our feature extraction method processes the EMG signals directly from the time-domain to reduce computational cost. The performance of the proposed features is tested on EMG data collected from nine transradial amputees performing six classes of movements each with three force levels. Our results indicate that the proposed features can achieve significant reductions in classification error rates in comparison to other well-known feature extraction methods, achieving improvements of ≈ 6% to 8% in the average classification performance across all subjects and force levels, when training with all forces.

Impact of Stewardship Interventions on Antiretroviral Medication Errors in an Urban Medical Center: A 3-Year, Multiphase Study.

There is a high prevalence of HIV infection in Newark, New Jersey, with University Hospital admitting approximately 600 HIV-infected patients per year. Medication errors involving antiretroviral therapy (ART) could significantly affect treatment outcomes. The goal of this study was to evaluate the effectiveness of various stewardship interventions in reducing the prevalence of prescribing errors involving ART. This was a retrospective review of all inpatients receiving ART for HIV treatment during three distinct 6-month intervals over a 3-year period. During the first year, the baseline prevalence of medication errors was determined. During the second year, physician and pharmacist education was provided, and a computerized order entry system with drug information resources and prescribing recommendations was implemented. Prospective audit of ART orders with feedback was conducted in the third year. Analyses and comparisons were made across the three phases of this study. Of the 334 patients with HIV admitted in the first year, 45% had at least one antiretroviral medication error and 38% had uncorrected errors at the time of discharge. After education and computerized order entry, significant reductions in medication error rates were observed compared to baseline rates; 36% of 315 admissions had at least one error and 31% had uncorrected errors at discharge. While the prevalence of antiretroviral errors in year 3 was similar to that of year 2 (37% of 276 admissions), there was a significant decrease in the prevalence of uncorrected errors at discharge (12%) with the use of prospective review and intervention. Interventions, such as education and guideline development, can aid in reducing ART medication errors, but a committed stewardship program is necessary to elicit the greatest impact.

Adaptive Filtering Techniques using Cyclic Prefix in OFDM Systems for Multipath Fading Channel Prediction

This paper presents adaptive channel prediction techniques for wireless orthogonal frequency division multiplexing (OFDM) systems using cyclic prefix (CP). The CP not only combats intersymbol interference, but also precludes requirement of additional training symbols. The proposed adaptive algorithms exploit the channel state information contained in CP of received OFDM symbol, under the time-invariant and time-variant wireless multipath Rayleigh fading channels. For channel prediction, the convergence and tracking characteristics of conventional recursive least squares (RLS) algorithm, numeric variable forgetting factor RLS (NVFF-RLS) algorithm, Kalman filtering (KF) algorithm and reduced Kalman least mean squares (RK-LMS) algorithm are compared. The simulation results are presented to demonstrate that KF algorithm is the best available technique as compared to RK-LMS, RLS and NVFF-RLS algorithms by providing low mean square channel prediction error. But RK-LMS and NVFF-RLS algorithms exhibit lower computational complexity than KF algorithm. Under typical conditions, the tracking performance of RK-LMS is comparable to RLS algorithm. However, RK-LMS algorithm fails to perform well in convergence mode. For time-variant multipath fading channel prediction, the presented NVFF-RLS algorithm supersedes RLS algorithm in the channel tracking mode under moderately high fade rate conditions. However, under appropriate parameter setting in $$2\times 1$$2?1 space---time block-coded OFDM system, NVFF-RLS algorithm bestows enhanced channel tracking performance than RLS algorithm under static as well as dynamic environment, which leads to significant reduction in symbol error rate.

The Improved Amplify-and-Forward (IAF) Three Time Periods TDMA Fashioned Protocol with Inter-Relay Communication

The TDMA constructed protocols have been planned (i.e., proposed) by various researchers. These protocols are generally two time periods or three time periods based, and have shown significant reduction in Bit Error Rates (BER), because of low diversity order. Consequently, the Improved Amplify-and-Forward (IAF) protocol has been proposed. The IAF protocol uses three time periods, to transmit data from transmitter to receiver. Moreover, the transmitter is stimulated during the second as well as third time periods, to broadcast to receiver, and the diversity order is improved. It is shown from results that IAF demonstrated significant reduction in BER and rise in BER-Gain, over the previous proposed two time periods as well as three time periods protocols. The IAF protocol demonstrated substantial improvement in Global-Percentage-Error-Decrease (GPED) and Local-Percentage-Error (LPED) values, both at severe as well as at low fading conditions, over to previous proposed TDMA constructed protocols (i.e., two time periods as well as three time periods based).

Reflecting on past failures leads to increased perseverance and sustained attention

Psychology has struggled for years to define the traits and tendencies that make an individual successful. Past research has focused on intelligence. Recently, there has been a focus on perseverance or “grit”. We set out to examine the extent to which grit exhibits state-like facets and the relation between manipulations of grit and performance. Results from the first experiment provide evidence that reflecting on failures results in higher grit scores than reflecting on success. The second experiment extends the failure–grit relationship to explore how this relation might modify performance: Encouraging individuals to reflect on failures resulted in a significant reduction in error rates on a cognitive task requiring perseverance. Together, these results provide support for the idea that grit exhibits state-like tendencies, and that encouraging individuals to reflect on failures may result in improved behavioural outcomes.

A variant of gravitational classification

Summary In this article there is proposed a new two-parametrical variant of the gravitational classification method. We use the general idea of objects' behavior in a gravity field. Classification depends on a test object's motion in a gravity field of training points. To solve this motion problem, we use a simulation method. This classifier is compared to the 1NN method, because our method tends towards it for some parameter values. Experimental results on different data sets demonstrate an improvement in efficiency and that this approach outperforms the 1NN method by providing a significant reduction in the mean classification error rate.

Paraphrastic language models

Natural languages are known for their expressive richness. Many sentences can be used to represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage and generalization, for example, when using n-gram language models (LMs). This paper proposes a novel form of language model, the paraphrastic LM, that addresses these issues. A phrase level paraphrase model statistically learned from standard text data with no semantic annotation is used to generate multiple paraphrase variants. LM probabilities are then estimated by maximizing their marginal probability. Multi-level language models estimated at both the word level and the phrase level are combined. An efficient weighted finite state transducer (WFST) based paraphrase generation approach is also presented. Significant error rate reductions of 0.5–0.6% absolute were obtained over the baseline n-gram LMs on two state-of-the-art recognition tasks for English conversational telephone speech and Mandarin Chinese broadcast speech using a paraphrastic multi-level LM modelling both word and phrase sequences. When it is further combined with word and phrase level feed-forward neural network LMs, a significant error rate reduction of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and neural network LMs respectively.

Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features

Recent studies in Electromyogram (EMG) pattern recognition reveal a gap between research findings and a viable clinical implementation of myoelectric control strategies. One of the important factors contributing to the limited performance of such controllers in practice is the variation in the limb position associated with normal use as it results in different EMG patterns for the same movements when carried out at different positions. However, the end goal of the myoelectric control scheme is to allow amputees to control their prosthetics in an intuitive and accurate manner regardless of the limb position at which the movement is initiated. In an attempt to reduce the impact of limb position on EMG pattern recognition, this paper proposes a new feature extraction method that extracts a set of power spectrum characteristics directly from the time-domain. The end goal is to form a set of features invariant to limb position. Specifically, the proposed method estimates the spectral moments, spectral sparsity, spectral flux, irregularity factor, and signals power spectrum correlation. This is achieved through using Fourier transform properties to form invariants to amplification, translation and signal scaling, providing an efficient and accurate representation of the underlying EMG activity. Additionally, due to the inherent temporal structure of the EMG signal, the proposed method is applied on the global segments of EMG data as well as the sliced segments using multiple overlapped windows. The performance of the proposed features is tested on EMG data collected from eleven subjects, while implementing eight classes of movements, each at five different limb positions. Practical results indicate that the proposed feature set can achieve significant reduction in classification error rates, in comparison to other methods, with ≈8% error on average across all subjects and limb positions. A real-time implementation and demonstration is also provided and made available as a video supplement (see Appendix A).

A Family of Discriminative Manifold Learning Algorithms and Their Application to Speech Recognition

This paper presents a family of discriminative manifold learning approaches to feature space dimensionality reduction in noise robust automatic speech recognition (ASR). The specific goal of these techniques is to preserve local manifold structure in feature space while at the same time maximizing the separability between classes of feature vectors. In the manifold space, the relationships among the feature vectors are defined using nonlinear kernels. Two separate distance measures are used to characterize the kernels, namely the conventional Euclidean distance and a cosine-correlation based distance. The performance of the proposed techniques is evaluated on two task domains involving noise corrupted utterances of connected digits and read newspaper text. Performance is compared to existing approaches used for feature space transformations, including linear discriminant analysis (LDA) and locality preserving linear projections (LPP). The proposed approaches are found to provide a significant reduction in word error rate (WER) with respect to the more well-known techniques for a variety of noise conditions. Another contribution of the paper is to quantify the interaction between acoustic noise conditions and the shape and size of local neighborhoods which are used in manifold learning to define local relationships among feature vectors. Based on this analysis, a procedure for reducing the impact of varying acoustic conditions on manifold learning is proposed .

Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition

An important part of the acoustic modelling problem for automatic speech recognition (ASR) systems is to handle the mismatch against a target environment created by time-varying external factors such as ambient noise. One possible solution to this problem is to introduce controllability to the underlying acoustic model to allow an instantaneous adaptation to the underlying noise condition. Along this line, the continuous trajectory of optimal, well matched model parameters against the varying noise can be explicitly modelled using, for example, generalized variable parameter HMMs (GVP-HMM). In order to improve the generalization and computational efficiency of conventional GVP-HMMs, this paper investigates a novel model complexity control method for GVP-HMMs. The optimal polynomial degrees of Gaussian mean, variance and model space linear transform trajectories are automatically determined at local level. Significant error rate reductions of 20% and 28% relative were obtained over the multi-style training baseline systems on Aurora 2 and a medium vocabulary Mandarin Chinese speech recognition task respectively. Consistent performance improvements and model size compression of 60% relative were also obtained over the baseline GVP-HMM systems using a uniformly assigned polynomial degree.

Tradeoff between leakage and dephasing errors in the fluxonium qubit

We present a tradeoff between anharmonicity (related to leakage) and pure dephasing errors for the fluxonium circuit. We show that in the insulating regime, i.e., when the persistent current flowing across the circuit is suppressed, the pure dephasing rate induced by a Markovian environment decreases exponentially as the impedance of the circuit is increased. In contrast to this exponential decrease, the qubit remains sufficiently anharmonic so that gate times can still be short, allowing for significant reduction in the computational error rates. A transition from the insulating to the superconducting phases establishes an upper bound on the Josephson energy below which this tradeoff exists.

Session variability modelling for face authentication

This study examines session variability modelling for face authentication using Gaussian mixture models. Session variability modelling aims to explicitly model and suppress detrimental within-class (inter-session) variation. The authors examine two techniques to do this, inter-session variability modelling (ISV) and joint factor analysis (JFA), which were initially developed for speaker authentication. We present a self-contained description of these two techniques and demonstrate that they can be successfully applied to face authentication. In particular, they show that using ISV leads to significant error rate reductions of, on average, 26% on the challenging and publicly available databases SCface, BANCA, MOBIO and multi-PIE. Finally, the authors show that a limitation of both ISV and JFA for face authentication is that the session variability model captures and suppresses a significant portion of between-class variation.

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

In this contribution we extend a previously proposed Bayesian approach for the enhancement of reverberant logarithmic mel power spectral coefficients for robust automatic speech recognition to the additional compensation of background noise. A recently proposed observation model is employed whose time-variant observation error statistics are obtained as a side product of the inference of the a posteriori probability density function of the clean speech feature vectors. Further a reduction of the computational effort and the memory requirements are achieved by using a recursive formulation of the observation model. The performance of the proposed algorithms is first experimentally studied on a connected digits recognition task with artificially created noisy reverberant data. It is shown that the use of the time-variant observation error model leads to a significant error rate reduction at low signal-to-noise ratios compared to a time-invariant model. Further experiments were conducted on a 5000 word task recorded in a reverberant and noisy environment. A significant word error rate reduction was obtained demonstrating the effectiveness of the approach on real-world data.

Response to Introduction of an N‐acetylcysteine weight‐based dosing chart reduces prescription errors in the treatment of paracetamol poisoning: Reply

Objective Under- or overdosing of N-acetylcysteine (NAC), when used to treat paracetamol toxicity, is associated with significant morbidity and mortality. This study evaluated the effect of a weight-based dosing chart (WBDC) introduced to decrease NAC prescription errors. Methods We undertook a pre- and post-intervention trial in a single ED. The intervention (the NAC WBDC) was introduced in January 2011 and publicised by posters and presentations at medical handovers and education sessions. ED staff were not aware that use of the WBDC was to be evaluated. Data were collected using a retrospective explicit medical record review by a single investigator. The study end-point was the proportion of NAC prescriptions with errors. Results The 81 and 42 patients enrolled in the pre- and post-intervention periods, respectively, did not differ in age, sex or weight (P > 0.05). Post-intervention, there were significant reductions in prescription errors of fluid type/volume (50.6% vs 4.8%, P < 0.001), NAC dosage (13.6% vs 0.0%, P = 0.01) and infusion rate (11.1% vs 0.0%, P = 0.03). The proportion of prescriptions with any errors also decreased (56.8% vs 14.3%, P < 0.001). However, there were no improvements in the documentation of patient weight (65.4% vs 64.3%, respectively, P = 0.90) or the proportion of incomplete prescriptions (4.9% vs 11.9%, P = 0.16). Conclusion The introduction of a WBDC did not produce a clinically significant reduction in major NAC prescription error rates (as pre-defined in this study); however, there was a clear trend towards a reduction. The WBDC significantly reduced total and minor NAC prescription error rates.

Oversampled perfect reconstruction DFT modulated filter banks for multi-carrier transceiver systems

In this work, we propose a novel method for the design of oversampled perfect reconstruction (PR) discrete Fourier transform (DFT) modulated filter banks (FB) for application to multi-carrier modulation (MCM). The PR property is enforced by employing a parametric class of paraunitary matrices to form the transmit/receive polyphase filters of the transceiver system. Specifically, the polyphase filters are formed by cascading special types of paraunitary matrices characterized by a limited set of design parameters. To reduce the number of these parameters, three different factorization methods are employed and compared. Through the optimization of these design parameters, the stop-band energy of the subband filters can be minimized which leads to improved spectral containment. The performance of the proposed system is investigated in a multi-carrier transceiver application, where it is compared with OFDM and other recently proposed FB structures. Numerical results show that the proposed scheme leads to a clear advantage not only in additive white Gaussian noise (AWGN) and frequency selective channels, but also in the presence of channel impairments such as narrow band interference or carrier frequency offset. In particular, it is found that a significant reduction in the bit error rate can be achieved by employing the proposed scheme.

Sequential correction of linear classifiers

In this article, a sequential correction of two linear methods: linear discriminant analysis (LDA) and perceptron is proposed. This correction relies on sequential joining of additional features on which the classifier is trained. These new features are posterior probabilities determined by a basic classification method such as LDA and perceptron. In each step, we add the probabilities obtained on a slightly different data set, because the vector of added probabilities varies at each step. We therefore have many classifiers of the same type trained on slightly different data sets. Four different sequential correction methods are presented based on different combining schemas (e.g. mean rule and product rule). Experimental results on different data sets demonstrate that the improvements are efficient, and that this approach outperforms classical linear methods, providing a significant reduction in the mean classification error rate.

ANALYSIS OF BAYESIAN CLASSIFIER ACCURACY

The naive Bayes classifier is considered one of the most effective classification algorithms today, competing with more modern and sophisticated classifiers. Despite being based on unrealistic (naive) assumption that all variables are independent, given the output class, the classifier provides proper results. However, depending on the scenario utilized (network structure, number of samples or training cases, number of variables), the network may not provide appropriate results. This study uses a process variable selection, using the chi-squared test to verify the existence of dependence between variables in the data model in order to identify the reasons which prevent a Bayesian network to provide good performance. A detailed analysis of the data is also proposed, unlike other existing work, as well as adjustments in case of limit values between two adjacent classes. Furthermore, variable weights are used in the calculation of a posteriori probabilities, calculated with mutual information function. Tests were applied in both a naive Bayesian network and a hierarchical Bayesian network. After testing, a significant reduction in error rate has been observed. The naive Bayesian network presented a drop in error rates from twenty five percent to five percent, considering the initial results of the classification process. In the hierarchical network, there was not only a drop in fifteen percent error rate, but also the final result came to zero.

Syllable language models for Mandarin speech recognition: Exploiting character language models

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

Introduction of an N‐acetylcysteine weight‐based dosing chart reduces prescription errors in the treatment of paracetamol poisoning

Under- or overdosing of N-acetylcysteine (NAC), when used to treat paracetamol toxicity, is associated with significant morbidity and mortality. This study evaluated the effect of a weight-based dosing chart (WBDC) introduced to decrease NAC prescription errors. We undertook a pre- and post-intervention trial in a single ED. The intervention (the NAC WBDC) was introduced in January 2011 and publicised by posters and presentations at medical handovers and education sessions. ED staff were not aware that use of the WBDC was to be evaluated. Data were collected using a retrospective explicit medical record review by a single investigator. The study end-point was the proportion of NAC prescriptions with errors. The 81 and 42 patients enrolled in the pre- and post-intervention periods, respectively, did not differ in age, sex or weight (P > 0.05). Post-intervention, there were significant reductions in prescription errors of fluid type/volume (50.6% vs 4.8%, P < 0.001), NAC dosage (13.6% vs 0.0%, P = 0.01) and infusion rate (11.1% vs 0.0%, P = 0.03). The proportion of prescriptions with any errors also decreased (56.8% vs 14.3%, P < 0.001). However, there were no improvements in the documentation of patient weight (65.4% vs 64.3%, respectively, P = 0.90) or the proportion of incomplete prescriptions (4.9% vs 11.9%, P = 0.16). The introduction of a WBDC did not produce a clinically significant reduction in major NAC prescription error rates (as pre-defined in this study); however, there was a clear trend towards a reduction. The WBDC significantly reduced total and minor NAC prescription error rates.