Personal computer system for ECG ST-segment recognition based on neural networks

A personal computer system for electrocardiogram (ECG) ST-segment recognition is developed based on neural networks. The system consists of a preprocessor, neural networks and a recogniser. The adaptive resonance theory (ART) is employed to implement the neural networks in the system, which self-organise in response to the input ECG. Competitive and co-operative interaction among neurons in the neural networks makes the system robust to noise. The preprocessor detects the R points and divides the ECG into cardiac cycles. Each cardiac cycle is fed into the neural networks. The neural networks then address the approximate locations of the J point and the onset of the T-wave (T_on). The recogniser determines the respective ranges in which the J and T_on points lie, based on the locations addressed. Within those ranges, the recogniser finds the exact locations of the J and T_on points either by a change in the sign of the slope of the ECG, a zero slope or a significant change in the slope. The ST-segment is thus recognised as the portion of the ECG between the J and T_on points. Finally, the appropriateness of the length of the ST-segment is evaluated by an evaluation rule. As the process goes on, the neural networks self-organise and learn the characteristics of the ECG patterns which vary with each patient. The experiment indicates that the system recognises ST-segments with an average of 95·7 per cent accuracy within a 15 ms error and with an average of 90·8 per cent accuracy within a 10 ms error, and that characteristics of the ECG patterns are stored in the long term memory of the neural networks.     

Extended horizon self-tuning control of a pulsed liquid-liquid extraction column

This paper describes the application of an extended horizon self-tuning control to a liquid-liquid extraction column. The work forms part of an industrial collaborative project. The control law is derived from plant output prediction over several steps with the assumption that beyond a certain horizon the control increments become constant. This technique is used to control the hydrodynamics of a liquid-liquid extraction column. The purpose of control is to maintain the column in its optimal behaviour zone, which corresponds to a specific hydrodynamic operation defined as a limit between two operating regimes. The measure of the conductivity gives information on the hydrodynamic behaviour of the column and has been selected as a control variable. The pulse frequency was also selected as a control variable. A single input-output linear discrete model with time-varying parameters was adopted to model the complex dynamics of the column. The model parameters are recursively estimated by a constant trace estimation algorithm. Some modifications have been introduced to improve the robustness of this estimation algorithm. Experiments carried out show that the presented algorithm has excellent control properties.     

Noninvasive beat-to-beat detection of ventricular late potentials

The detection of ventricular late potentials is a subject of some clinical interest. Most techniques currently being investigated rely on signal averaging to extract the microvolt signals from the considerable amounts of noise which are present. Although this approach produces useful results, it does remove any beat-to-beat variations from the signal, and also requires that the signal be present for a considerable number of beats. The paper describes a technique for detecting ventricular late potentials from the body surface, which preserves beat-to-beat variations. The most important aspect of this technique is the use of an adaptive signal enhancer to minimise random noise. Representative results for one normal and two pathological subjects are presented and discussed. A comparison with signal averaging is made and the effectiveness of adaptive signal enhancement is illustrated.     

On the number of auditory filter outputs needed to understand speech: Further evidence for auditory channel independence

The number of auditory filter outputs required to identify phonemes was estimated in two experiments. Stimuli were divided into 30 contiguous equivalent rectangular bandwidths (ERB_N) spanning 80–7563 Hz. Normal-hearing listeners were presented with limited numbers of bands having frequency locations determined randomly from trial to trial to provide a general view, i.e., irrespective of specific band location, of the number of 1-ERB_N-wide speech bands needed to identify phonemes. The first experiment demonstrated that 20 such bands are required to accurately identify vowels, and 16 are required to identify consonants. In the second experiment, speech-shaped noise or time-reversed speech was introduced to the non-speech bands at various signal-to-noise ratios. Considerably elevated noise levels were necessary to substantially affect phoneme recognition, confirming a high degree of channel independence in the auditory system. The independence observed between auditory filter outputs supports current views of speech recognition in noise in which listeners extract and combine pieces of information randomly distributed both in time and frequency. These findings also suggest that the ability to partition incoming sounds into a large number of narrow bands, an ability often lost in cases of hearing impairment or cochlear implantation, is critical for speech recognition in noise.     

低剂量X射线全身照射诱导小鼠胸腺细胞CD_3分子表达的适应性反应

采用免疫荧光流式细胞术（ＦＣＭ）观察了昆明种小鼠胸腺细胞ＣＤ３分子表达的变化。首次报道了０．０７５ＧｙＸ射线单次全身照射可诱导小鼠胸腺细胞ＣＤ３分子表达对其后１．５Ｇｙ攻击剂量照射的适应性反应。证实，１．５Ｇｙ全身照射后胸腺ＣＤ３阳性细胞明显减少，照后１８小时仅为假照射组的３３．７４％。当１．５Ｇｙ照射前６小时预先照射０．０７５Ｇｙ时，可明显减轻其后攻击剂量对ＣＤ３分子表达的抑制作用，此时，ＣＤ３阳性细胞数显著高于单纯攻击剂量对照组（Ｐ＜０．０１）。对其机理进行了讨论。     

Adaptive critic designs: A case study for neurocontrol

For the first time, different adaptive critic designs (ACDs), a conventional proportional integral derivative (PID) regulator and backpropagation of utility are compared for the same control problem—automatic aircraft landing. The original problem proved to contain little challenge since various conventional and neural network techniques had solved it very well. After the problem had been made much more difficult by a change of parameters, increasingly better performance was observed by going from the simplest ACD to more sophisticated designs, dual heuristic programming having been ranked best of all. This case study is of use in general intelligent control problems for it provides an example of the capabilities of different adaptive critic designs.     

莪术体外抑制成纤维细胞生长的初步研究

应用体外培养的人发结膜成纤维细胞，观察中药莪术在休外对细胞增殖的影响。结果：１０％莪术液对细胞生长有极显著的抑制作用（Ｐ〈０．０１），而５％莪术液和对照组则对细胞生长无抑制作用（Ｐ〉０．０５），提示莪术可作为抗青光眼滤过性手术的辅助用药，预防成纤维细胞增殖导致的手术失败。     

Influence of Filtering Techniques on the Time-Domain Analysis of Signal-Averaged P Wave Electrocardiogram

Differences in P Wave Filtering Techniques. introduction : The advent of signal-averaged ECG (SAECG) systems for P wave analysis has made it important to determine if the use of different filtering techniques in these systems is diagnostically equivalent.
Methods and Results : Three different high-pass filtering techniques and two cutoff frequency values were used: 29- and 40-Hz Butterworth bidirectional filter (BB29, BB40), 29-and 40-Hz Butterworth unidirectional filter (UB29, UB40), and 29- and 40-Hz least mean square filter (LIV1S29, LMS40). Normal healthy volunteers (n = 36) and patients with documented paroxysmal atrial fibrillation (n = 23) were analyzed. A custom-built SAECG system and standard bipolar orthogonal leads were used. Noise was reduced to < 0.3 μV. P wave total duration, root mean square voltage of the terminal 20, 30, and 40 msec of the filtered vector magnitude, and the area under the curve between the onset and offset of averaged unfiltered and filtered P wave vector magnitude were analyzed. Only the duration of the P wave showed statistically significant differences between groups, being longer in the PAF group for all filters and cutoff frequencies studied. A bias increment of -20 msec was detected in unidirectional and least mean square filters as compared to the bidirectional filter. Sensitivity, specificity, and predictive accuracy were > 70% for all filters; the BB40 filter yielded the best performance.
Conclusion : The normality limits derived from one filter cannot be applied directly to recordings obtained from the other filters. Critical limits must be established individually for different software settings.     

Real-time adaptive sampling with the fan algorithm

Adaptive sampling of cardiac waveforms can produce higher quality measurements than uniform sampling at the same average rates. The paper presents the design of a device for real-time adaptive sampling with the fan algorithm. Design equations define the relationships between system parameters, allowing choices among hardware complexity, speed or accuracy to be evaluated. The design incorporates a parallel architecture, which can be expanded to achieve any desired peak sampling rate. Examples show the system to be flexible and realistic. A major feature of the design is that fan samples are provided to the user at a fixed rate that the user specifies, although they are selected internally at variable rates. Because of this feature, complications in receiving and storing samples at widely varying intervals are entirely avoided, and simple computers such as PCs can be used to collect samples at a rate far below the peak sampling rate. To accomplish fixed-rate transmission, the system itself selects the fan tolerance ε based on characteristics of the incoming signal. As the signal changes, ε is varied dynamically to ensure that the fixed rate is never exceeded. Furthermore, the design guarantees that measurements will never be worse than those from uniform sampling at the given fixed rate.