Reza Saatchi

Respiration Rate Monitoring Methods: A Review

Respiration rate is an important indicator of a persons health, and thus it is monitored when performing clinical evaluations. There are different approaches for respiration monitoring, but generally they can be classed as contact or noncontact. For contact methods, the sensing device (or part of the instrument containing it) is attached to the subjects body. For noncontact approaches the monitoring is performed by an instrument that does not make any contact with the subject. In this article a review of respiration monitoring approaches (both contact and noncontact) is provided. Concerns related to the patients recording comfort, recording hygiene, and the accuracy of respiration rate monitoring have resulted in the development of a number of noncontact respiration monitoring approaches. A description of thermal imaging based and vision based noncontact respiration monitoring approaches we are currently developing is provided. Pediatr. Pulmonol. 2011; 46:523–529.

Feature extraction and classification of electrocardiogram (ECG) signals related to hypoglycaemia

Nocturnal hypoglycaemia has been implicated in the sudden deaths of young people with diabetes. Experimental hypoglycaemia has been found to prolong the ventricular repolarisation and to affect the T wave morphology. It is postulated that abnormally low blood glucose could in certain circumstances, be responsible for the development of a fatal cardiac arrhythmia. We have used automatic extraction of both time-interval and morphological features, from the electrocardiogram (ECG) to classify ECGs into normal and arrhythmic. Classification was implemented by artificial neural networks (ANN) and linear discriminant analysis (LDA). The ANN gave more accurate results. Average training accuracy of the ANN was 85.07% compared with 70.15% on unseen data. This study may lead towards the demonstration of the possible relationship between cardiac function and abnormally low blood glucose.

Tracking human face features in thermal images for respiration monitoring

A method has been developed to track a region related to respiration process in thermal images. The respiration region of interest (ROI) consisted of the skin area around the tip of the nose. The method was then used as part of a non-contact respiration rate monitoring that determined the skin temperature changes caused by respiration. The ROI was located by the first determining the relevant salient features of the human face physiology. These features were the warmest and coldest facial points. The tracking method was tested on thermal video images containing no head movements, small random and regular head movements. The method proved valuable for tracking the ROI in all these head movement types. It was also possible to use this tracking method to monitor respiration rate involving a number of head movement types. Currently, more investigations are underway to improve the tracking method so that it can track the ROI in cases larger head movements.

Facial Tracking in Thermal Images for Real-Time Noncontact Respiration Rate Monitoring

A noncontact respiration rate monitor is developed. The method detected and tracked the face and then matched a pre-selected template in order to track a facial point of interest associated with respiration, located beneath the nostril. A region of interest (ROI) was then specified around the detected point of interest. Unwanted noise in the image was removed using image processing techniques. Feature extraction and signal processing techniques were applied to this ROI to compute the respiration feature and thereafter the respiration rate. It was shown that the method could detect and continuously track the subjects face by enclosing it in a rectangle. The method updated the location of the ROI and also determined respiration rate in a noncontact manner. The computation time for each frame was 40 ms, making it suitable for real-time respiration monitoring. Further work is in progress to enhance the algorithm to eliminate the need for pre-selection of a template.

A Novel Quality of Service Assessment of Multimedia Traffic over Wireless Ad Hoc Networks

With the extensive growth of the Internet, wireless technology, and multimedia applications, quality of service (QoS) monitoring and measurement of the networks have become important. Network measurements are carried out to obtain information about important QoS parameters such as delay, loss and jitter. Each type of multimedia applications has its own requirements and limits on these parameters. To evaluate the QoS of multimedia applications transmitted over wireless networks, a fuzzy logic assessment system has been developed. The system showed how the end-to-end QoS could be measured without the necessity for complex mathematical models. The measured QoS were classified into three categories Good, Average, and Poor regions. In addition, and based on the proposed system, the distributions and the overall QoS were estimated. The results indicated that the measured QoS was a good indication of the network conditions and resource availability.

Assessment and improvement of quality of service in wireless networks using fuzzy and hybrid genetic-fuzzy approaches

Fuzzy and hybrid genetic-fuzzy approaches were used to assess and improve quality of service (QoS) in simulated wireless networks. Three real-time audio and video applications were transmitted over the networks. The QoS provided by the networks for each application was quantitatively assessed using a fuzzy inference system (FIS). Two methods to improve the networks’ QoS were developed. One method was based on a FIS mechanism and the other used a hybrid genetic-fuzzy system. Both methods determined an optimised value for the minimum contention window (CWmin) in IEEE 802.11 medium access control (MAC) protocol. CWmin affects the time period a wireless station waits before it transmits a packet and thus its value influences QoS. The average QoS for the audio and video applications improved by 42.8% and 14.5% respectively by using the FIS method. The hybrid genetic-fuzzy system improved the average QoS for the audio and video applications by 35.7% and 16.5% respectively. The study indicated that the devised methods were effective in assessing and significantly improving QoS in wireless networks.

Use of pattern recognition for signatures generated by laser desorption–ion mobility spectrometry of polymeric materials

This paper describes the use of an artificial neural network (ANN) for pattern recognition of ion mobility signatures of polymeric materials produced by the method known as laser ablation–ion mobility spectrometry (LA-IMS). This technique has been used to examine a wide range of polymer-based materials. Mobilization of the sample was achieved using a laser and the ion mobility spectrometer gave characteristic signatures for materials introduced as vapours. The application of the ANN to the analysis of the IMS signatures has resulted in a novel method for discriminating polymeric materials. Initial pattern recognition results obtained from several polymers showed an accuracy of 100% in both the test and use domains. Negative ion mobility signatures are presented to demonstrate how the signatures were treated before analysis using the ANN. Future development of the technique is discussed, including the use of mass spectrometry to identify the species produced by the action of the laser and the use of on-line neural network pattern recognition techniques. The ANN approach is applicable to other process and environmental monitoring situations.

Thermal image processing for real-time non-contact respiration rate monitoring

A real-time thermal imaging based, non-contact respiration rate monitoring method was developed. It measured the respiration related skin surface temperature changes under the tip of the nose. Facial tracking was required as head movements caused the face to appear in different locations in the recorded images over time. The algorithm detected the tip of the nose and then, a region just under it was selected. The pixel values in this region in successive images were processed to determine respiration rate. The segmentation method, used as part of the facial tracking, was evaluated on 55,000 thermal images recorded from 14 subjects with different extent of head movements. It separated the face from image background in all images. However, in 11.7% of the images, a section of the neck was also included, but this did not cause an error in determining respiration rate. The method was further evaluated on 15 adults, against two contact respiration rate monitoring methods that tracked thoracic and abdominal movements. The three methods gave close respiration rates in 12 subjects but in 3 subjects, where there were very large head movements, the respiration rates did not match.

Medical Devices for Measuring Respiratory Rate in Children: a Review

Respiratory rate is an important vital sign used for diagnosing illnesses in children as well as prioritising patient care. All children presenting acutely to hospital should have a respiratory rate measured as part of their initial and ongoing assessment. However measuring the respiratory rate remains a subjective assessment and in children can be liable to measurement error especially if the child is uncooperative. Devices to measure respiratory rate exist but many provide only an estimate of respiratory rate due to the associated methodological complexities. Some devices are used within the intensive care, post-operative or more specialised investigatory settings none however have made their way into the everyday clinical setting. A non-contact device may be better tolerated in children and not cause undue stress distorting the measurement. Further validation and adaption to the acute clinical setting is needed before such devices can supersede current methods.

Eyes' corners detection in infrared images for real-time noncontact respiration rate monitoring

A thermal imaging based noncontact respiration rate monitoring approach is developed. The approach identified and tracked the face region in the image. The two corners where the eyes and nose meet were detected by selecting the two highest temperature regions within the face. From these sites, the nose and the nostril were identified. A respiration region of interest (ROI) was specified under the nostril. The skin surface temperature in this region is affected most by respiration. The selected ROI in each recorded thermal image was represented by a single feature. A respiration signal was produced from the plot of the feature across the series of recorded images. Respiration rate was determined by using the frequency of the highest peak in the frequency spectrum. The approach was evaluated on 5 adult subjects. It was shown that it could track the face, determine the ROI and respiration successfully in real-time, even when there were some head movements.