Vahid Zakeri

Discrimination of Tooth Layers and Dental Restorative Materials Using Cutting Sounds

Dental restoration begins with removing carries and affected tissues with air-turbine rotary cutting handpieces, and later restoring the lost tissues with appropriate restorative materials to retain the functionality. Most restoration materials eventually fail as they age and need to be replaced. One of the difficulties in replacing failing restorations is discerning the boundary of restorative materials, which causes inadvertent removal of healthy tooth layers. Developing an objective and sensor-based method is a promising approach to monitor dental restorative operations and to prevent excessive tooth losses. This paper has analyzed cutting sounds of an air-turbine handpiece to discriminate between tooth layers and two commonly used restorative materials, amalgam and composite. Support vector machines were employed for classification, and the averaged short-time Fourier transform coefficients were selected as the features. The classifier performance was evaluated from different aspects such as the number of features, feature scaling methods, classification schemes, and utilized kernels. The total classification accuracies were 89% and 92% for cases included composite and amalgam materials, respectively. The obtained results indicated the feasibility and effectiveness of the proposed method.

Using electromechanical signals recorded from the body for respiratory phase detection and respiratory time estimation: A comparative study

Electrocardiogram derived respiratory (EDR) is a non-invasive technique to estimate respiratory signal. As an alternative, recent studies suggest using Seismocardiogram to estimate respiratory signal, so called accelerometer derived respiration (ADR). In this study we compared the performance of ADR and EDR in precise detection of respiration phases (inhale and exhale timing). We also compared time lag between breath cycles extracted by use of ADR and EDR, and ground truth (respiratory signal recorded using chest band strain gauge). For this comparative analysis, Seismocardiogram, Single lead electrocardiogram (Lead II), and respiratory signal (using a chest band strain gauge) were recorded from 19 healthy subjects. Principal component analysis (PCA) and envelope detection methods are used to compute EDR and ADR. Initial results show that ADR in z-direction (back to front) seems promising approach in addition to the EDR with accuracy of above 85% in identifying respiration phases (inhale and exhale). 87% of breath cycles extracted from ADR had acceptable time lag compared to ground truth (respiratory signal recorded using a chest band strain gauge). ADR was able to correctly classify heartbeats to inhale and exhale classes with classification accuracy of around 76%.

Identification of respiratory phases using seismocardiogram: A machine learning approach

This study was aimed at developing an algorithm that could identify the respiratory phases, i.e. inspiration (I) or expiration (E), by analysing seismocardiogram (SCG) cycles. In order to better assess SCG cycles, it is needed to discriminate the cycles based on their position in the respiratory phases. The total 2146 SCG cycles obtained from 45 subjects were studied, in which 1109 cycles were in phase I, and the rest in phase E. Support vector machine (SVM), a powerful machine learning algorithm, was employed to identify the respiratory phase of SCG cycles. The systolic interval of each SCG cycle was divided to 32 equal bins, and the averages of these bins obtained the feature vector associated with each cycle. The SVM model was trained using half the data, and then was tested on the other half. The developed model could correctly identify 88% of the testing data. The obtained results are promising and can establish a solid ground for further analysis.

Preliminary results on quantification of Seismocardiogram morphological changes, using principal component analysis.

A methodology, based on principal component analysis, is proposed to quantify beat to beat Seismocardiogram changes. The proposed method was tested over a population of 94 subjects including 35 ischemic heart disease patients. The results showed that there was an insignificant overlap between the diseased and the healthy populations in the number of principal components (NPC) and that further development of this method might yield a classification index for myocardial abnormalities. In addition such an index has potential utility in patient monitoring.

Analyzing Seismocardiogram Cycles to Identify the Respiratory Phases

Goal: the objective of this study was to develop a method to identify respiratory phases (i.e., inhale or exhale) of seismocardiogram (SCG) cycles. An SCG signal is obtained by placing an accelerometer on the sternum to capture cardiac vibrations. Methods: SCGs from 19 healthy subjects were collected, preprocessed, segmented, and labeled. To extract the most important features, each SCG cycle was divided to equal-sized bins in time and frequency domains, and the average value of each bin was defined as a feature. Support vector machines was employed for feature selection and identification. The features were selected based on the total accuracy. The identification was performed in two scenarios: leave-one-subject-out (LOSO), and subject-specific (SS). Results: time-domain features resulted in better performance. The time-domain features that had higher accuracies included the characteristic points correlated with aortic-valve opening, aortic-valve closure, and the length of cardiac cycle. The average total identification accuracies were 88.1% and 95.4% for LOSO and SS scenarios, respectively. Conclusion: the proposed method was an efficient, reliable, and accurate approach to identify the respiratory phases of SCG cycles. Significance: The results obtained from this study can be employed to enhance the extraction of clinically valuable information such as systolic time intervals.

Studying the Design of PWM Controllers for Air Motors With an Indirect Approach of Speed Measurement

Efficiency of the air motors is a function of different variables, including the head and velocity of the fluid at the inlet and outlet of the air motor, and the load on its shaft. Among these variables, angular velocity control of air motors is a challengeable area for engineering. Although servo valves seem to be promising solutions for this application, however, they are slow and expensive. As a result, they cannot properly manage the fluctuations and discontinuities of the flow as well as the disturbances in the load for the optimum efficiency. This paper has studied designing of a PWM controller for air motors by investigating different pulses with different frequencies and duty cycles. In addition, considering practical point of view, speed-measurement in rotary systems can be challengeable and sometimes impossible. These changes such as detachment and reattachment of the shaft of the system, or installing the encoder around the shaft are sometimes impossible practically Thus, this paper has also presented an indirect method of speed-measurement by using vibration signature of air motors measured by accelerometers and microphones. The experimental results indicate the capability and suitability of this indirect measurement.Copyright

Tooth materials monitoring scheme for dental operations using cutting sounds

This paper introduces a monitoring scheme for discerning the boundary of the tooth in dental operations. In this scheme, tooth structures and dental fillings were discriminated based on their cutting sounds. Support vector machines were employed for classification; and averaged short time Fourier transform coefficients were selected as the features. The results confirmed capability and feasibility of the proposed scheme.

A Comparative Study of Different Control Strategies for a Magnetorheological Haptic System

Magnetorheological (MR) dampers are a new generation of adjustable dampers that can generate large resistive forces against motion with low power. This feature is a unique characteristic that idealizes them for many applications including haptics. A haptic interface system is developed that includes a magnetorheological (MR) damper on the master side and a linear DC motor on the slave side. In this system, the slave motion follows the master and the force experienced by the slave is reflected to the master. The major challenge in this arrangement is control of the MR damper to create the desired resistive force. This paper investigates the different strategies for controlling the MR damper. In haptics, rather than the perfect tracking of a desired force, it is more convenient to generate a force in the master that is ‘similar’ to the actual force sensed by the slave. In addition, in many applications of MR dampers such as suspension systems, seismic response reduction, etc., perfect tracking is unneeded. Considering all of these factors, this paper proposes the concept of ‘similarity’ between the desired force and the resistive force of the MR damper. ‘Similarity’ means whenever the desired force is large, the resistive force should also be large, and whenever the desired force is small, the resistive force should then be small. Based on this concept, three controllers are applied and tested in both open loop and closed loop schemes: a gain controller, a fuzzy logic controller, and a lookup table controller. The results of these controllers are evaluated and compared to each other with respect to smaller time delays and smaller and smoother control inputs. In the absence of major differences in the results, the closed loop gain controller appeared to be a suitable choice for control because of its simple scheme and its ease of application.Copyright