Abstract:

Signals obtained from biological systems exhibit pronounced complexity. The patterns of change contain valu- able information about the dynamics of underlying control mechanism of the complex biological systems. Human gait is a complex process with multiple inputs and numerous outputs. Various complexity analysis tools have been proposed to extract information from human gait time series. In this study, we used recently developed threshold based symbolic entropy to compare the spontaneous output of the human locomotors system during constrained and metronomically paced walking protocols. For that purpose, stride interval time series of healthy subjects who walked for 1 h at normal, slow and fast rates under different conditions was transformed into symbol sequences. Normalized corrected Shannon entropy (NCSE) was computed from the symbol sequences of the stride inter- val time series. The findings indicated that the unprompted output of human locomotors system is more complex during unconstrained normal walking as compared with slow, fast or metronomically paced walking

Abstract:

This article analyzes the tools and methods used in the analysis of emotions from text for the purpose of managing society. It illustrates the influence of emotions on the management of people, society and businesses processes. Their importance and the changes that occurs over time in the processes of managing society. The role that social networks plays in managing society and the methods they uses. We researched different websites and software, observed their mechanisms for data collection, its analysis and use for the purpose of managing society. In general, we analyze the most common methods, the factors that affects the choice of a particular method, their influence and based on our analy-sis, give recommendations for improving the process of analyzing emotions for the purpose of managing society.

Abstract:

Electroencephalography (EEG) is a method to measure the electrical activity of brain signals by electrodes attached to the scalp at multiple locations. In this study we used the EEG signals of Alcoholic and Control subjects were obtained from Machine Learning repository according to the 10-20 International System. There were 29 subjects from control group and 29 from alcoholic comprising of electrodes from different brain lobes such as Central Lobe (C3, C4), Frontal (F3, F4, F7, F8), Occipital Lobe (O1, O2), Parietal Lobe (P3, P4), Temporal Lobe (T7) and Front Polar (Fp1, Fp2). In the first phase, the nonlinear complexity based features are computed such as Approximate Entropy, Sample Entropy and Wavelet Entropy. These features for each electrode are passed as input to the Machine Learning classifiers such as Multilayer Perceptron (MPL), K-nearest Neighbor (KNN) and LIB Support Vector Machine (SVM) to classify for alcoholic and control group. The highest accuracy was obtained using MLP of 98.22 % at electrode C3. Moreover, above 90% accuracy was obtained using MPL at electrode C3, C4, F7; KNN at electrodes C3, C4, F7 and LIB SVM at electrodes C3, C4, F7 where KNN gives highest accuracy of 97.67% at electrode C4 and LIB SVM an accuracy of 94.67 % at electrode F7. Secondly, the ensemble methods are employed such as Minimum, Maximum, Sum, Average, Product, Majority Vote, Bayes, Decision Template and Dempster Shefer Fusion. Using ensemble methods most electrodes depicted higher accuracy than individual classifier such as Electrode F4, Fp2, O1, O2 and T7. While electrode C3 the ensemble methods Moving Average, DT, DFT gives highest accuracy of 98.22% and at electrodes C4 Moving Average, Sum, Average, DT, DFT provided an accuracy of 97.11%.

Abstract:

Signals obtained from biological systems exhibit pronounced complexity. The patterns of change contain valuable information about the dynamics of underlying control mechanism of the complex biological systems. Human gait is a complex process with multiple inputs and numerous outputs.Various complexity analysis tools have been proposed to extract information from human gait time series. In this study, we used recently developed threshold based symbolic entropy to compare the spontaneous output of the human locomotors system during constrained and metronomically paced walking protocols. The findings indicated that the unprompted output of human locomotors system is more complex during unconstrained normal walking as compared with slow, fast or metronomically paced walking. The results was compared with the Multiscale Entropy (MSE) Analysis proposed and we concluded that the Symbolic Analysis is more robust than multiscale entropy method as well as our method is also useful for smaller time series whereas MSE is not suitable for shorter time series.

Abstract:

The chronological vacillations in the stride to stride interval provide a noninvasive method to assess the influence of malfunction of human gait and its alterations with disease and age. To extract information from the human stride interval, various complexity analysis techniques have been proposed. In the present study, the comparison of two recently developed complexity analysis methodologies: multiscale entropy (MSE) and symbolic entropy (SyEn) has been made. These techniques were applied to stride interval time series data of human gait walking at normal and metronomically paced stressed conditions. Wilcoxon-rank-sum test (Mann-Whitney-Wilcoxon (MWW) test) was used to find the significant difference between the groups. For each method of analysis, parameters were adjusted to optimize the separation of the groups. The symbolic entropy method provided maximum separation at wide range of threshold values and this measure was found to be more robust for analyzing the human gait data as compared to multiscale entropy in the presence of dynamical and observational noise. The results of this study can have implication modeling physiological control mechanism and for quantifying human gait dynamics in physiological and stressed conditions.

Abstract:

The guide Heart rate signals provide valuable information for assessing the state of autonomic nervous system that control functioning of heart. Heart rate variability analysis is an important non-invasive tool that has been widely used for assessing autonomic control of heart using linear and non-linear techniques since last three decades. Different methods used to detect these beats include ECG, blood pressure etc. but ECG has great importance because it gives a complete and clear waveform. Heart rate variability analysis is a tool that assesses the autonomic nervous system. It is based on the measurement of changing heart rate signals. In past two decades a large number of research efforts were made and a number of techniques were proposed for heart rate variability. In this study, the techniques used for HRV analysis includes linear (time and frequency domain) and non-linear techniques. We have used different classifiers and their methods to check heart rate variations in healthy cases and diseased cases. Methods showing highest accuracy include Naïve Bayes method of Bayes classifier; sequential minimal optimization (SMO) of functions classifier, lazy locally weighted learning (LWL) method, AdaBoost and logical model tree. Among all these methods LMT (logical model tree) is considered as best method with the accuracy level of 92.5%. In this study 10 folds cross-validation was used as test option. Cross-validation is a technique to assess the accuracy of results where the goal is predicted. In 10 folds cross-validation 10 times repetition occurs and the result is obtained by taking mean accuracy.

Abstract:

With the development of deep learning techniques, deep neural network (NN)-based methodshave become the standard for vision tasks such as tracking human motion and pose estimation,recognizing human activity, and recognizing faces. Deep learning techniques have improvedthe design, implementation, and deployment of complex and diverse applications, which arenow being used in a wide variety of fields, including biomedical engineering. The applicationof computer vision techniques to medical image and video analysis has resulted in remarkableresults in recognizing events. The inbuilt capability of convolutional neural network (CNN)in extracting features from complex medical images, coupled with long short term memorynetwork (LSTM)’s ability to maintain the temporal information among events, has createdmany new horizons for medical research. Gait is one of the critical physiological areas thatcan reflect many disorders associated with aging and neurodegeneration. A comprehensiveand accurate gait analysis can provide insights into human physiological conditions. Existinggait analysis techniques require a dedicated environment, complex medical equipment, andtrained staff to collect the gait data. In the case of wearable systems, such a system can altercognitive abilities and cause discomfort for patients.Additionally, it has been reported that patients usually try to perform better duringthe laboratory gait test, which may not represent their actual gait. Despite technologicaladvances, we continue to encounter limitations when it comes to measuring human walkingin clinical and laboratory settings. Using current gait analysis techniques remains expensiveand time-consuming and makes it difficult to access specialized equipment and expertise.Therefore, it is imperative to have such methods that could give long-term data aboutthe patient’s health without any dual cognitive tasks or discomfort while using wearablesensors. Hence, this thesis proposes a simple, easy-to-deploy, inexpensive method for gaitdata collection. This method is based on recording walking videos using a smartphonecamera in a home environment under free conditions. Deep NN then processes those videosto extract the gait events after classifying the positions of the feet. The detected eventsare then further used to quantify various spatiotemporal parameters of the gait, which areimportant for any gait analysis system.In this thesis, walking videos were used that were captured by a low-resolution smartphonecamera outside the laboratory environment. Many deep learning-based NNs wereimplemented to detect the basic gait events like the foot position in respect of the groundfrom those videos. In the first study, the architecture of AlexNet was used to train the modelfrom scratch using walking videos and publicly available datasets. An overall accuracyof 74% was achieved with this model. However, the LSTM layer was included with thesame architecture in the next step. The inbuilt capability of LSTM regarding the temporalinformation resulted in improved prediction of the labels for foot position, and an accuracyof 91% was achieved. However, there is hardship in predicting true labels at the last stage ofthe swing and the stance phase of each foot.In the next step, transfer learning is used to get the benefit of already trained deep NNs byusing pre-trained weights. Two famous models inceptionresnetv2 (IRNV-2) and densenet201(DN-201) were used with their learned weights for re-training the NN on new data. Transferlearning-based pre-trained NN improved the prediction of labels for different feet’ positions.It especially reduced the variations in the predictions in the last stage of the gait swing andstance phases. An accuracy of 94% was achieved in predicting the class labels of the testdata. Since the variation in predicting the true label was primarily one frame, it could beignored at a frame rate of 30 frames per second.The predicted labels were used to extract various spatiotemporal parameters of thegait, which are critical for any gait analysis system. A total of 12 gait parameters werequantified and compared with the ground truth obtained by observational methods. TheNN-based spatiotemporal parameters showed a high correlation with the ground truth, andin some cases, a very high correlation was obtained. The results proved the usefulness ofthe proposed method. The parameter’s value over time resulted in a time series, a long-termgait representation. This time series could be further analyzed using various mathematicalmethods. As the third contribution in this dissertation, improvements were proposed to theexisting mathematical methods of time series analysis of temporal gait data. For this purpose,two refinements are suggested to existing entropy-based methods for stride interval timeseries analysis. These refinements were validated on stride interval time series data of normaland neurodegenerative disease conditions downloaded from the publicly available databankPhysioNet. The results showed that our proposed method made a clear degree of separationbetween healthy and diseased groups.In the future, advanced medical support systems that utilize artificial intelligence, derivedfrom the methods introduced here, could assist physicians in diagnosing and monitoringpatients’ gaits on a long-term basis, thus reducing clinical workload and improving patientsafety.