An adaptive human–machine control system based on multiple fuzzy predictive models of operator functional state

Under the framework of adaptive Human–Machine (HM) systems, it has been proposed that human operators’ task level should be dynamically adjusted according to his/her functional state. The construction of models that can reliably predict the operator functional state (OFS) becomes critical to accomplish such adjustments. However, most of the existing models that evaluate the current OFS by using operators’ current physiological data are static and are of no real predictive capability. Thus, when they are used in adaptive HM systems, the resultant task allocation between operators and machines would be time-delayed. To overcome this problem, a one-step-ahead predictive model concept for OFS computation is proposed. Meanwhile, multiple fuzzy models are developed by using the Wang–Mendel method. These models are able to increase the accuracy of the OFS breakdown prediction, as well as to reduce the model training time. In addition, an adaptive task allocation strategy is designed to validate the proposed models. The results demonstrate that, compared to the conventional HM systems, a 6.7% OFS increment and a 57.1% OFS breakdown decrement can be obtained in the multiple models based adaptive HM systems. The multiple predictive models and the adaptive task allocation strategy would pave the way for future implementations of real-time adaptive HM systems.     

Classifying human operator functional state based on electrophysiological and performance measures and fuzzy clustering method

The human operator’s ability to perform their tasks can fluctuate over time. Because the cognitive demands of the task can also vary it is possible that the capabilities of the operator are not sufficient to satisfy the job demands. This can lead to serious errors when the operator is overwhelmed by the task demands. Psychophysiological measures, such as heart rate and brain activity, can be used to monitor operator cognitive workload. In this paper, the most influential psychophysiological measures are extracted to characterize Operator Functional State (OFS) in automated tasks under a complex form of human–automation interaction. The fuzzy c-mean (FCM) algorithm is used and tested for its OFS classification performance. The results obtained have shown the feasibility and effectiveness of the FCM algorithm as well as the utility of the selected input features for OFS classification. Besides being able to cope with nonlinearity and fuzzy uncertainty in the psychophysiological data it can provide information about the relative importance of the input features as well as the confidence estimate of the classification results. The OFS pattern classification method developed can be incorporated into an adaptive aiding system in order to enhance the overall performance of a large class of safety–critical human–machine cooperative systems.     

Operator functional state estimation based on EEG-data-driven fuzzy model

This paper proposed a max–min-entropy-based fuzzy partition method for fuzzy model based estimation of human operator functional state (OFS). The optimal number of fuzzy partitions for each I/O variable of fuzzy model is determined by using the entropy criterion. The fuzzy models were constructed by using Wang–Mendel method. The OFS estimation results showed the practical usefulness of the proposed fuzzy modeling approach.     

Nonstationarity and duration of the cardiac interval time series in assessing the functional state of operator personnel

The influence of nonstationarity in the time series of cardiac intervals on the assessment of the functional state (FS) of operator personnel was analyzed with a three-factor model of heart rhythm variability (HRV). ECG recordings were made in supine position at rest and in the sedentary position before and after important operator testing. In all three cases, the FS assessments were not influenced by nonstationarity of the input data. The effect of nonstationarity was also negligible for some particular HRV indices. Reliable assessments could be obtained from relatively short samples (256 down to 32 RR intervals) with prior norming of the factor indices for the corresponding segment length. The influence of the time series duration on the HRV indices was examined in various FSs; stable indices and proper recording conditions were determined.     

May the Best Joint-Actions Win: Physiological Linkage During Competition

Previous work showed that, when we interact with other people, an alignment of psychophysiological measures occur as a clue about the intensity of the social interaction. Available evidence highlighted increase autonomic synchrony, known as physiological linkage, during intense dyadic situations, like conflictual conversations within romantic couples, friends, or therapeutic settings. Starting from the idea that higher physiological linkage could support better performance and be correlated with approach attitudes (Behavioral Activation System, BAS), in the present study a conflictual situation was proposed by making subjects compete during an attentional task and stressing the importance to win as a measure of future professional success. Autonomic activity (electrodermal: skin conductance level and response: SCL, SCR; and cardiovascular indices: heart rate: HR) was recorded during the task, where subjects received trial-related feedbacks on their performance, and an average score halfway which (fictitiously) assessed their position in terms of accuracy and reaction times with respect to the opponent. In parallel, behavioral inhibition and activation have been assessed by means of the Behavioral Inhibition/Activation System Questionnaire (BIS/BAS). 32 subjects coupled in 16 dyads were recruited. Intra-subject analyses revealed that, after the general evaluation assessing a winning condition, the behavioral performance improved and the electrodermal response increased. Also, correlational analyses showed a relation between BAS, and specifically BAS reward, with SCR. Inter-subject analyses showed higher synchrony in SCR and HR after the feedback. Such results confirm the increased synchronic effect after a highly conflictual condition, and the presence of a relation between subjective performance, approach-related motivations, and physiological linkage.     

The variability of the heart rhythm and the nature of the feedback as a result of operator activity in man]

In a memory task which required sustained attention, the positive or negative emotional state of an operator was created by introduction of two different types of feedback in accordance with the number of correct or wrong solutions. Standard and original indices were used for evaluation of the short-term variability of the heart rate (HRV) during performance. Changes in the HRV were observed only in the periods of performance with the failure type of the feedback. These changes reflected stabilization of heart bit-to-bit intervals. The original index of the fast HRV turned to be the most sensitive for testing HRV changes. Human autonomic reactions of such a kind during operator-like activity are known as a predictor for the functional state of dissatisfaction. This confirms the practical importance of application of the HRV indices for testing the ergonomic properties of the systems which control the operator-computer interaction.     

New Indices for Evaluating the Functional State in Patients with Angina Pectoris

Traditional indices used to evaluate the functional state in patients with ischemic heart disease (IHD) by testing under conditions of exercise take into account changes in the heart rate (HR), arterial pressure, and the ST segment only during exercise and, for the most part, take into account do not information about the recovery period. The authors show on the basis of the analyses of the regression of ST and HR in patients with angina pectoris that the traditional indices are more effective during exercise. They suggest new standardized nondimensional indices to evaluate the state of patients with myocardial ischemia, i.e., the standardized duration and amplitude of fast recovery (SDFR and SAFR) of ST depression. Most likely, SAFR reflects the share of cardiomyocytes in the metastable state in the total number of the cells affected by short-term ischemia, and SDFR may be an index of the time of the change in the metastable state. Comparative study of the standardized indices of myocardial ischemia showed that the rate–pressure product, SDFR, and SAFR are independent values and may be recommended for evaluating the functional state in patients with IHD.     

Monitoring Cognitive and Emotional Processes Through Pupil and Cardiac Response During Dynamic Versus Logical Task

The paper deals with the links between physiological measurements and cognitive and emotional functioning. As long as the operator is a key agent in charge of complex systems, the definition of metrics able to predict his performance is a great challenge. The measurement of the physiological state is a very promising way but a very acute comprehension is required; in particular few studies compare autonomous nervous system reactivity according to specific cognitive processes during task performance and task related psychological stress is often ignored. We compared physiological parameters recorded on 24 healthy subjects facing two neuropsychological tasks: a dynamic task that require problem solving in a world that continually evolves over time and a logical task representative of cognitive processes performed by operators facing everyday problem solving. Results showed that the mean pupil diameter change was higher during the dynamic task; conversely, the heart rate was more elevated during the logical task. Finally, the systolic blood pressure seemed to be strongly sensitive to psychological stress. A better taking into account of the precise influence of a given cognitive activity and both workload and related task-induced psychological stress during task performance is a promising way to better monitor operators in complex working situations to detect mental overload or pejorative stress factor of error.     

Load Index Metrics for an Optimized Management of Web Services: A Systematic Evaluation

The lack of precision to predict service performance through load indices may lead to wrong decisions regarding the use of web services, compromising service performance and raising platform cost unnecessarily. This paper presents experimental studies to qualify the behaviour of load indices in the web service context. The experiments consider three services that generate controlled and significant server demands, four levels of workload for each service and six distinct execution scenarios. The evaluation considers three relevant perspectives: the capability for representing recent workloads, the capability for predicting near-future performance and finally stability. Eight different load indices were analysed, including the JMX Average Time index (proposed in this paper) specifically designed to address the limitations of the other indices. A systematic approach is applied to evaluate the different load indices, considering a multiple linear regression model based on the stepwise-AIC method. The results show that the load indices studied represent the workload to some extent; however, in contrast to expectations, most of them do not exhibit a coherent correlation with service performance and this can result in stability problems. The JMX Average Time index is an exception, showing a stable behaviour which is tightly-coupled to the service runtime for all executions. Load indices are used to predict the service runtime and therefore their inappropriate use can lead to decisions that will impact negatively on both service performance and execution cost.     

Real-time detection of workload changes using heart rate variability

This work presents a novel approach to detecting real-time changes in workload using heart rate variability (HRV). We propose that for a given workload state, the values of HRV vary in a sub-range of a Gaussian distribution. We describe methods to monitor a HRV signal in real-time for change points based upon sub-Gaussian fitting. We tested our method on subjects sitting at a computer performing a low workload surveillance task and a high workload video game task. The proposed algorithm showed superior performance compared to the classic CUSUM method for detecting task changes.     

Effects of phase vector and history extension on prediction power of adaptive-network based fuzzy inference system (ANFIS) model for a real scale anaerobic wastewater treatment plant operating under unsteady state

A conceptual neural fuzzy model based on adaptive-network based fuzzy inference system, ANFIS, was proposed using available input on-line and off-line operational variables for a sugar factory anaerobic wastewater treatment plant operating under unsteady state to estimate the effluent chemical oxygen demand, COD. The predictive power of the developed model was improved as a new approach by adding the phase vector and the recent values of COD up to 5–10 days, longer than overall retention time of wastewater in the system. History of last 10 days for COD effluent with two-valued phase vector in the input variable matrix including all parameters had more predictive power. History of 7 days with two-valued phase vector in the matrix comprised of only on-line variables yielded fairly well estimations. The developed ANFIS model with phase vector and history extension has been able to adequately represent the behavior of the treatment system.     

DNA flow cytometry of breast carcinoma after acetic-acid fixation

Aqueous acetic acid was used to fix and store specimens of tissue prior to dissociation into nuclear suspensions for flow cytometric quantitation of DNA. The optimum concentration was 20 volumes of glacial acetic acid in 80 volumes of distilled water. Both neoplastic and benign nuclei were easily released from the fixed tissue blocks by slicing and shaking. Residual undissociated tissue was suitable for microscopic examination to confirm its identity. The nuclei fluoresced brightly after staining with propidium iodide, and yielded histograms similar to those from unfixed samples. Acetic-acid fixation resulted in slightly broader G1 and G0 peaks in the DNA histograms in comparison to unfixed cells, but fluorescent debris was less and correlation between the flow cytometric S-phase fraction (SPF) and in vitro thymidine labelling index (TLI) was better than with unfixed cells. Twenty-one of thirty-nine acetic-acid-fixed breast carcinomas had DNA indices in excess of 1.0 (increased nuclear DNA content in comparison to benign cells), and eighteen had DNA indices of 1.0 (normal or near-normal). The SPF was usually in excess of the TLI, but the two were significantly correlated (r = 0.72, P less than 0.0001). However, a significant correlation of SPF with TLI held only for the group with DNA index greater than 1.0. DNA indices greater than 1.0 were associated with high SPF and TLI, and high SPF and TLI each associated with low content of estrogen receptor.     

Statistical geometry based prediction of nonsynonymous SNP functional effects using random forest and neuro-fuzzy classifiers

There is substantial interest in methods designed to predict the effect of nonsynonymous single nucleotide polymorphisms (nsSNPs) on protein function, given their potential relationship to heritable diseases. Current state-of-the-art supervised machine learning algorithms, such as random forest (RF), train models that classify single amino acid mutations in proteins as either neutral or deleterious to function. However, it is frequently the case that the functional effect of a polymorphism on a protein resides between these two extremes. The utilization of classifiers that incorporate fuzzy logic provides a natural extension in order to account for the spectrum of possible functional consequences. We generated a dataset of single amino acid substitutions in human proteins having known three-dimensional structures. Each variant was uniquely represented as a feature vector that included computational geometry and knowledge-based statistical potential predictors obtained though application of Delaunay tessellation of protein structures. Additional attributes consisted of physicochemical properties of the native and replacement amino acids as well as topological location of the mutated residue position in the solved structure. Classification performance of the RF algorithm was evaluated on a training set consisting of the disease-associated and neutral nsSNPs taken from our dataset, and attributes were ranked according to their relative importance. Similarly, we evaluated the performance of adaptive neuro-fuzzy inference system (ANFIS). The utility of statistical geometry predictors was compared with that of traditional structural and evolutionary attributes employed by other researchers, revealing an equally effective yet complementary methodology. Among all attributes in our feature set, the statistical geometry predictors were found to be the most highly ranked. On the basis of the AUC (area under the ROC curve) measure of performance, the ANFIS and RF models were equally effective when only statistical geometry features were utilized. Tenfold cross-validation studies evaluating AUC, balanced error rate (BER), and Matthew's correlation coefficient (MCC) showed that our RF model was at least comparable with the well-established methods of SIFT and PolyPhen. The trained RF and ANFIS models were each subsequently used to predict the disease potential of human nsSNPs in our dataset that are currently unclassified (http://rna.gmu.edu/FuzzySnps/).     

Artificial intelligence-based approaches for modeling the effects of spirulina growth mediums on total phenolic compounds

Spirulina is a microalga and its phenolic compound is affected by growth mediums. In this study, Artificial intelligence (AI) based models, namely the Adaptive-Neuro Fuzzy Inference System (ANFIS) and Multilayer perceptron (MLP) models, and Step-Wise-Linear Regression (SWLR) were used to predict total phenolic compounds (TPC) of the spirulina algae. Spirulina productivity (P), extraction yield (EY), total flavonoids (TF), percent of flavonoid (%F) and percent of phenols (%P) are considered as input variables with the corresponding TPC as an output variable. From the result, TPC has a high positive correlation with the input variables with R = 0.99999. Also, the models showed that the ANFIS and SWLR gives superior result in the testing phase and increased its accuracy by 2% compared to MLP model in the prediction of TPC.     

Nonstationarity and duration of the R-R-segment in the diagnostics of functional states of operators

The effect of the nonstationarity of R-R interval series on the diagnostics of functional states of operators has been analyzed. The functional states were diagnosed by means of a factor model of heart rate variability. The heart rate was recorded in the supine position, before the performance of an important task, and after its completion. A high resistance of the diagnostics of functional states to nonstationarity was found for all periods. Indices of heart rate variability resistant to nonstationarity were defined. Also, the effect of R-R segment duration on functional states diagnostics was explored. The results obtained allow one to conclude that the diagnostics of functional states based on the three-factor model of heart rate variability can be used on short segments within a range of 256 divided 32 R-R intervals. The indices of the factor model of heart rate variability must be normalized for corresponding R-R segment duration before diagnostics. In addition, the effect of the duration of R-R segment on the indices of heart rate variability was analyzed for different functional states. The indices resistant to the duration of R-R segments and conditions necessary for heart rate recording were defined.     

Comparision of some models for estimation of reflectance of hypericum leaves under stress conditions

Lack of water resources and high water salinity levels are among the most important growth-restricting factors for plants species of the world. This research investigates the effect of irrigation levels and salinity on reflectance of Saint John’s wort leaves (Hypericum perforatum L.) under stress conditions (water and salt stress) by multiple linear regression (MLR), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Empirical and heuristics modeling methods were employed in this study to relate stress conditions to leaf reflectance. It was found that the constructed ANN model exhibited a high performance than multiple regression and ANFIS in estimating leaf reflectance accurately.     

Adaptive neuro-fuzzy modelling of anaerobic digestion of primary sedimentation sludge

Modelling of anaerobic digestion systems is difficult because their performance is complex and varies significantly with influent characteristics and operational conditions. In this study, Adaptive Neuro-Fuzzy Inference System (ANFIS) were used for modelling of anaerobic digestion system of primary sludge of Kayseri municipal WasteWater Treatment Plant (WWTP). Effluent Volatile Solid (VS) and methane yield were predicted by the ANFIS. Two stage models were performed. In the first stage, effluent VS concentration was predicted using pH, VS concentration, flowrate of pre-thickened sludge and temperature of the influent as input parameters. In the second stage, effluent VS concentration in addition to first stage input parameters were used as input parameters to predict methane yield. The low Root Mean Square Error (RMSE) and high Index of agreement (IA) values were obtained with subtractive clustering method of a first order Sugeno type inference. The model performance was evaluated with statistical parameters. According to statistical evaluations, the models satisfactorily predict effluent VS concentration and methane yield.     

Dna Flow Cytometry of Breast Carcinoma After Acetic-Acid Fixation

ABSTRACT Aqueous acetic acid was used to fix and store specimens of tissue prior to dissociation into nuclear suspensions for flow cytometric quantitation of DNA. the optimum concentration was 20 volumes of glacial acetic acid in 80 volumes of distilled water. Both neoplastic and benign nuclei were easily released from the fixed tissue blocks by slicing and shaking. Residual undissociated tissue was suitable for microscopic examination to confirm its identity. the nuclei fluoresced brightly after staining with propidium iodide, and yielded histograms similar to those from unfixed samples. Acetic-acid fixation resulted in slightly broader G₁ and G₀ peaks in the DNA histograms in comparison to unfixed cells, but fluorescent debris was less and correlation between the flow cytometric S-phase fraction (SPF) and in vitro thymidine labelling index (TLI) was better than with unfixed cells. Twenty-one of thirty-nine acetic-acid-fixed breast carcinomas had DNA indices in excess of 1.0 (increased nuclear DNA content in comparison to benign cells), and eighteen had DNA indices of 1.0 (normal or near-normal). the SPF was usually in excess of the TLI, but the two were significantly correlated (r= 0.72, P>0.0001). However, a significant correlation of SPF with TLI held only for the group with DNA index < 1.0. DNA indices < 1.0 were associated with high SPF and TLI, and high SPF and TLI each associated with low content of estrogen receptor.     

Experiments and ANFIS modelling for the biodegradation of penicillin-G wastewater using anaerobic hybrid reactor

The performance of an anaerobic hybrid reactor (AHR) for treating penicillin-G wastewater was investigated at the ambient temperatures of 30-35 °C for 245 days in three phases. The experimental data were analysed by adopting an adaptive network-based fuzzy inference system (ANFIS) model, which combines the merits of both fuzzy systems and neural network technology. The statistical quality of the ANFIS model was significant due to its high correlation coefficient R² between experimental and simulated COD values. The R² was found to be 0.9718, 0.9268 and 0.9796 for the I, II and III phases, respectively. Furthermore, one to one correlation among the simulated and observed values was also observed. The results showed the proposed ANFIS model was well performed in predicting the performance of AHR.