Mohiuddin Ahmad

Human action recognition using shape and CLG-motion flow from multi-view image sequences

In this paper, we present a method for human action recognition from multi-view image sequences that uses the combined motion and shape flow information with variability consideration. A combined local-global (CLG) optic flow is used to extract motion flow feature and invariant moments with flow deviations are used to extract the global shape flow feature from the image sequences. In our approach, human action is represented as a set of multidimensional CLG optic flow and shape flow feature vectors in the spatial-temporal action boundary. Actions are modeled by using a set of multidimensional HMMs for multiple views using the combined features, which enforce robust view-invariant operation. We recognize different human actions in daily life successfully in the indoor and outdoor environment using the maximum likelihood estimation approach. The results suggest robustness of the proposed method with respect to multiple views action recognition, scale and phase variations, and invariant analysis of silhouettes.

HMM-based Human Action Recognition Using Multiview Image Sequences

In this paper, we present a novel method for human action recognition from any arbitrary view image sequence that uses the Cartesian component of optical flow velocity and human body silhouette feature vector information. We use principal component analysis (PCA) to reduce the higher dimensional silhouette feature space into lower dimensional feature space. The action region in an image frame represents Q-dimensional optical flow feature vector and R-dimensional silhouette feature vector. We represent each action using a set of hidden Markov models and we model each action for any viewing direction by using the combined (Q + R) -dimensional features at any instant of time. We perform experiments of the proposed method by using KU gesture database and manually captured data. Experimental results of different actions from any viewing direction are correctly classified by our method, which indicate the robustness of our view-independent method

Human action recognition using multi-view image sequences

Recognizing human action from image sequences is an active area of research in computer vision. In this paper, we present a novel method for human action recognition from image sequences in different viewing angles that uses the Cartesian component of optical flow velocity and human body shape feature vector information. We use principal component analysis to reduce the higher dimensional shape feature space into low dimensional shape feature space. We represent each action using a set of multidimensional discrete hidden Markov model and model each action for any viewing direction. We performed experiments of the proposed method by using KU gesture database. Experimental results based on this database of different actions show that our method is robust

Development of a noninvasive continuous blood pressure measurement and monitoring system

Non invasive continuous blood pressure measurement system is more useful than conventional blood pressure measurement systems. The arterial system is extraordinarily well regulated blood delivery network in human body. It responds very quickly according to the body movements like altered body position, or in sudden excitation. So now a days continuous blood pressure monitoring devices are becoming more essential. Many types of blood pressure measurement devices are available. Those devices allow only few blood pressure readings in every 10 minutes. In contrast to them, we develop a very low cost noninvasive continuous blood pressure measurement and monitoring system. It measures blood pressure using volume oscillometric method and photoplethysmography technique during a long time period continuously. The rate of change of blood volume in an organ such as finger has a linear relationship with blood pressure. This rate of change of blood volume in finger is measured by an optical sensor network which estimates blood pressure. It displays the numerical value of systolic and diastolic blood pressure in a mini LCD. Our developed system is reliable, accurate and less expensive.

Variable silhouette energy image representations for recognizing human actions

Recognizing human actions is an important topic in the computer vision community. One of the challenges of recognizing human actions is describing for the variability that arises when arbitrary view camera captures human performing actions. In this paper, we propose a spatio-temporal silhouette representation, called silhouette energy image (SEI), and multiple variability action models, to characterize motion and shape properties for automatic recognition of human actions in daily life. To address the variability in the recognition of human actions, several parameters, such as anthropometry of the person, speed of the action, phase (starting and ending state of an action), camera observations (distance from camera, slanting motion, and rotation of human body), and view variations are proposed. We construct the variability (or adaptable) models based on SEI and the proposed parameters. Global motion descriptors express the spatio-temporal properties of combined energy templates (SEI and variability action models). Our construction of the optimal model for each action and view is based on the support vectors of global motion descriptions of action models. We recognize different daily human actions of different styles successfully in the indoor and outdoor environment. Our experimental results show that the proposed method of human action recognition is robust, flexible and efficient.

Human emotion recognition using frequency & statistical measures of EEG signal

The purpose of the research is to evaluate the different human emotions through Electroencephalogram (EEG) signal and to receive information about the internal changes of brain state. The paper presents the detection of human emotion based on some salient features of EEG signal. For this purpose, seven emotional states have been specified such as relax, thought, memory related, motor action, pleasant, fear, and enjoying music. Several EEG signals have been collected for these states and analyzed using frequency transform and statistical measures. Different significant features have been extracted from the analyzed signal. Among various statistical measures skewness and kurtosis are chosen which indicate the largest dispersion in different mental states and help to evaluate different human emotions. Frequency analysis shows how the ranges of magnitude vary with different frequency components. On the basis of magnitude ranges different emotional states are identified. EEG signal provides an effective way in the functioning of the brain to study of mental behavior.

Evaluating the Relationship between Permeability and Moisture Damage of Asphalt Concrete Pavements

AbstractLimiting the presence of water inside an asphalt concrete (AC) pavement can slow down the process involved in water diffusion, hydration, adhesion loss, and other mechanisms of moisture damage. In the past, numerous studies have been conducted on the topic of moisture damage and permeability, but very few studies have related permeability with moisture damage in AC. This study evaluates whether such relation exists. In essence, a field survey is conducted to identify a set of pavements (bad) that suffer from moisture damage and a set of pavements (good) that do not exhibit moisture damage. Field permeability tests and coring are conducted on the pavements. Laboratory permeability tests are performed on the field cores. An indirect tensile strength ratio (TSR) of wet- to dry-conditioned core samples is determined in the laboratory and used as a moisture damage potential parameter. Wet conditioning is performed by using a recently developed moisture-induced sensitivity test (MIST) device and a well-...

Electronic energy meter with remote monitoring and billing system

Electronic energy meter is capable of taking readings and can store it into its memory. Taking energy meter reading is time consuming and an expensive task. The meter reader travels for a long distance and take the reading manually to prepare the bill. Consumers have to go to the billing office, stand in a long line and submit the bill. This is a boring job and time consuming also. It can be avoided by remote monitoring of electronic energy meter and prepaid billing system by the use of cash card. In this paper measurement of energy, remote monitoring, preparing of bill and billing system is presented. Low cost ATMEGA8L microcontroller is used here to control the whole system. Sampling of voltage and current is done by it. Then it processes data to achieve power in that instant. Then it stores the value of total energy consumed by the consumer and can calculate energy charge according to the tariff. LCD display is attached with this system to show total energy consumed, power factor and amount of charge etc. Communication between central energy distribution office and energy meter is done through power line. Complex tariff rate set up and cash card based billing is possible in this system. Electronic meter gives high accuracy for nonlinear loads than conventional rotating disc type electro-mechanical meter. Greater accuracy and stability can be maintained in this system.

Cognitive State Estimation by Effective Feature Extraction and Proper Channel Selection of EEG Signal

This paper presents a cognitive state estimation system focused on some effective feature extraction based on temporal and spectral analysis of electroencephalogram (EEG) signal and the proper channel selection of the BIOPAC automated EEG analysis system. In the proposed approach, different frequency components (i) real value; (ii) imaginary value; (iii) magnitude; (iv) phase angle and (v) power spectral density of the EEG data samples during different mental task performed to assess seven types of human cognitive states — relax, mental task, memory related task, motor action, pleasant, fear and enjoying music on the three channels of BIOPAC EEG data acquisition system — EEG, Alpha and Alpha RMS signal. Also the time and time-frequency-based features were extracted to compare the performance of the system. After feature extraction, the channel efficacy is evaluated by support vector machine (SVM) based on the classification rate in different cognitive states. From the experimental results and classification accuracy, it is determined that the overall accuracy for alpha channel shows much improved result for power spectral density than the other frequency based features and other channels. The classification rate is 69.17% for alpha channel whereas for EEG and alpha RMS channel it is found 47.22% and 32.21%, respectively. For statistical analysis standard deviation shows better result for alpha channel and it is found 65.4%. The time-frequency analysis shows much improved result for alpha channel also. For the mean value of DWT coefficients the accuracy is highest and it is 81.3%. Besides the classification accuracy, SVM shows better performance in compare with kNN classifier.

PHYSIOLOGICAL SIGNAL ANALYSIS FOR COGNITIVE STATE ESTIMATION

The purpose of this paper is to identify inconsistency in human physiological signals based on cognitive states by measuring and analyzing bio-signals. In this paper, the cognitive states are estimated using physiological signal analysis. The parameters are electrocardiogram (ECG), electromyogram (EMG), electroencephalogram (EEG) and blood pressure (BP). The signals have been collected using BIOPAC system in which the subjects were induced to undergo the specific sequence of the cognitive state. For getting physiological signals during different conditions, we utilized power point slide show, video clips and question answer method which elicits mental reactions from the subjects. Data is taken before and after four tasks that encompassed the motor action (MA), thought (TH), memory related (MR) and emotion (EM). These measured values are analyzed using BIOPAC Acknowledge software. It was found that the motor action and thought states have effects on BP while MR and EM state mainly affect the ECG measurement. The decibel value and frequency found for EM state in ECG are minimum compared to relaxed state (RS) condition. Similarly, the maximum frequency and dB value is found for MR state. No significant variation was seen for MA and TH states. Thus it was decided that the MR and EM states mainly affect the ECG measurement. For BP the value increases in MA state and decreases in TH state. The MA state mainly affects the EMG signal while other states have no significant changes. The EEG mainly detects the signal of task performed by the specific brain region where the electrodes are placed. In EEG analysis, the electrodes are placed in occipital lobe region which gives mainly the variation in alpha amplitude of EEG with eyes closed and eyes opened. Alpha wave amplitudes vary with the subjects attention to mental tasks performed with eyes closed.