1,721,080 research outputs found
Respiration Measurement in a Simulated Setting Incorporating the Internet of Things
Full text linkThe Internet of Things (IoT) in healthcare has gained significant attention in recent years. This study demonstrates an adaptation of IoT in healthcare by illustrating a method of respiration rate measurement from a platform that simulates breathing. Respiration rate is a crucial physiological measure in monitoring critically ill patients. The devised approach, with further development, may be suitable for integration into neonatal intensive care units (NICUs) to measure infants’ respiration rate. A potential advantage of this method is that it monitors respiration using a wireless non-contact method and could add benefits such as preservation of skin integrity. The paper aimed to assess the accuracy of an IoT-integrated ultrasound (US)-based method for measuring respiration rate. Chest movement due to respiration was simulated by a platform with a controllable moving surface. The magnitude and frequency of the movements were accurately controlled by a signal generator. The surface movements were tracked using US as a reliable and cost-effective technology. ESP8266 NodeMCU was used to wirelessly record the US signal and ThingSpeak and Matlab© were used to analyze and visualize the data in the cloud. A close relationship between the measured rate of the simulated respiration and the actual frequency was observed. The study demonstrated a possible adaption of IoT for respiration rate measurement, however further work will be needed to ensure security and reliability of data handling before use of the system in medical environments
Computerised accelerometric machine learning techniques and statistical developments for human balance analysis
Full text linkBalance maintenance is crucial to participating in the activities of daily life. Balance is often
considered as the ability to maintain the centre of mass (COM) position within the base of
support. Primarily, to maintain balance, reliance is placed on the balance related sensory
systems i.e., the visual, proprioceptive and vestibular. Several factors can affect a person’s
balance such as neurological diseases, ageing, medication and obesity etc. To gain insight into
the balance operations, studies rely on statistical and machine learning techniques. Statistical
techniques are used for inferencing while machine learning techniques proved effective for
interpretation.
The focus of this study was on the issues encountered in human balance analysis such as the
quantification of balance by relevant features, the relationships between COM and ground
projected body sway, the performance of various sensory systems in balance analysis, and their
relationships between the directions of body sway (i.e., mediolateral (ML) and anteriorposterior
(AP)). A portable wireless accelerometry device was developed, balance analysis
methods based on the inverted pendulum were devised and evaluated for their accuracy and
reliability against a setup designed to allow manual balance measurements. Balance data were
collected from 23 healthy adult subjects with the mean (standard deviation) of the age, height
and weight: 24.5 (4.0) years, 173.6 (6.8) cm, and 72.7 (9.9) kg respectively. The accelerometry
device was attached to the subjects at the approximate position of the illac crest, while they
performed 30 seconds trials of the four conditions associated with a standard balance test called
the modified Clinical Test of Sensory Interaction and Balance (mCTSIB). These required
standing on a hard (ground) surface with the eyes open, standing on hard surface with the eyes
closed, standing on a compliant surface (sponge, 10 cm thick) with the eyes open and standing
on a compliant surface with the eyes closed. Statistical and machine learning techniques such
as t-test, Wilcoxon signed-rank test, the Mann-Whitney U test, Analysis of variance (ANOVA),
Kruskal-Wallis test, Friedman test, correlation analysis, linear regression, Bland and Altman
analysis, principal component analysis (PCA), K-means clustering, and Kohonen neural
network (KNN) were employed for interpreting the measurements.
The findings showed close agreement between the developed balance analysis methods and the
related measurements from the manual setup for balance analysis. The COM was observed to
be responsible for differing amount of sway across the subjects and could affect both the angle
and ground projected sway. The AP direction was more sensitive to sway than the ML
direction. The subjects were observed to depend more on their proprioceptive system to control
balance. The proprioceptive system was observed to have a greater impact in controlling the
AP velocity of the subjects as compared to their visual system. The proprioceptive system had
no impact on the ML velocity. The visual system was responsible for the control of the ML
velocity and for reducing the acceleration in both directions.
It was concluded that for comparison of postural sway information, subjects with closely
related COM positions should be compared, comparison should be carried out in respect to the
base of their support. The sway normalisation by dividing with COM position should be
performed to reduce the obscuring effect of the COM. Enhancement of the proprioceptive
system should be carried out to reduce the AP velocity while enhancement of the visual system
should be used to reduce the ML sway and acceleration in ML and AP directions. The velocity
in the AP direction should be used to examine the performance of the proprioceptive system
while the ML velocity and acceleration should be used for the visual system. The vestibular
system characterised sway more in the AP direction, and hence, the AP direction should be
used to examine its performance in balance
Development and evaluation of vision processing algorithms in multi-robotic systems.
Full text linkThe trend in swarm robotics research is shifting to the design of more complicated systems in which the robots have abilities to form a robotic organism. In such systems, a single robot has very limited memory and processing resources, but the complete system is rich in these resources. As vision sensors provide rich surrounding awareness and vision algorithms also requires intensive processing. Therefore, vision processing tasks are the best candidate for distributed processing in such systems. To perform distributed vision processing, a number of scenarios are considered in swarm and the robotic organism form. In the swarm form, as the robots use low bandwidth wireless communication medium, so the exchange of simple visual features should be made between robots. This is addressed in a swarm mode scenario, where novel distance vector features are exchanged within a swarm of robots to generate a precise environmental map. The generated map facilitates the robot navigation in the environment. If features require encoding with high density information, then sharing of such features is not possible using the wireless channel with limited bandwidth. So methods were devised which process such features onboard and then share the process outcome to perform vision processing in a distributed fashion. This is shown in another swarm mode scenario in which a number of optimisation stages are followed and novel image pre-processing techniques are developed which enable the robots to perform onboard object recognition, and then share the process outcome in terms of object identity and its distance from the robot, to localise the objects. In the robotic organism, the use of reliable communication medium facilitates vision processing in distributed fashion, and this is presented in two scenarios. In the first scenario, the robotic organism detect objects in the environment in distributed fashion, but to get detailed surrounding awareness, the organism needs to learn these objects. This leads to a second scenario, which presents a modular approach to object classification and recognition. This approach provides a mechanism to learn newly detected objects and also ensure faster response to object recognition. Using the modular approach, it is also demonstrated that the collective use of 4 distributed processing resources in a robotic organism can provide 5 times the performance of an individual robot module. The overall performance was comparable to an individual less flexible robot (e.g., Pioneer-3AT) with significant higher processing capability
Artificial intelligence and statistical techniques to predict probability of injury survival
Full text linkThe aim of this study is to design, develop and evaluate artificial intelligence and statistical techniques to predict the probability of survival in traumas using knowledge acquired from a database of confirmed traumas outcomes (survivors and not survivors). Trauma in this study refers to body injuries from accidents or other means.
Quantifying the effects of traumas on individuals is challenging as they have many forms, affect different organs, differ in severity and their consequence could be related to the individual's physiological attributes (e.g. age, fragility, premedical condition etc). It is known that appropriate intervention improves survival and may reduce disabilities in traumas. Determining the probability of survival in traumas is important as it can inform triage, clinical research and audit. A number of methods have been reported for this purpose. These are based on a combination of physiological and anatomical examination scores. However, these methods have shortcomings as for example, combining the scores from injuries for different organs is complicated.
A method for predicting probability of survival in traumas needs to be accurate, practical and accommodate broad cases. In this study Sheffield Hallam University, Sheffield Children's Hospital, Sheffield University and the Trauma Audit and Research Network (TARN) collaborated to develop improved means of predicting probability of survival in traumas. The data used in this study were trauma cases and their outcomes provided by the TARN. The data included 47568 adults (age: mean = 59.9 years, standard deviation = 24.7 years) with various injuries. In total, 93.3% of cases had survived and 6.7% of cases had not survived. The data were partitioned into calibration (2/3 of the data) and evaluation (1/3 of the data). The trauma parameters used in the study were: age, respiration rate (RR), systolic blood pressure (SBP), pulse (heart) rate (PR) and the values obtained from two trauma scoring systems called Abbreviated Injury Score (AIS) and Glasgow Coma Score (GCS). Intubation and Pre-exiting Medical Condition (PMC) data were also considered.
Initially a detailed statistical exploration of the manner trauma these trauma parameters related to the probability of survival outcomes was carried out and the results were interpreted. The resulting information assisted the development of three methods to predict probability of survival. These were based on Bayesian statistical approach called predictive statistical diagnosis (PSD), a new method called Iterative Random Comparison classification (IRCC) and the third method combined the IRCC with the fuzzy inference system (FIS). The performance of these methods was compared with each other as well as the method of predicating survival used by the TARN called Ps14 (the name refers to probability of survival method reported in 2014).
The study primarily focused on Trauma Brain Injury (TBI) as they represented the majority of the cases. For TBI, the developed IRCC performed best amongst all methods including Ps14. It predicted survivors and not survivors with 97.2% and 75.9% accuracies respectively. In comparison, the predication accuracy for Ps14 for survivors and not survivors were 97.4% and 40.2%.
The study provided resulted in new findings that indicated the manner trauma parameters affect probability of survival and resulted in new artificial intelligence and statistical methods of determining probability survival in trauma
Internet of medical things – integrated, ultrasound-based respiration monitoring system for incubators
Full text linkThe study's aim was to develop a non-contact, ultrasound (US) based respiration rate
and respiratory signal monitor suitable for babies in incubators. Respiration rate
indicates average number of breaths per minute and is higher in young children than
adults. It is an important indicator of health deterioration in critically ill patients. The
current incubators do not have an integrated respiration monitor due to complexities in
its adaptation. Monitoring respiratory signal assists in diagnosing respiration rated
problems such as central Apnoea that can affect infants. US sensors are suitable for
integration into incubators as US is a harmless and cost-effective technology.
US beam is focused on the chest or abdomen. Chest or abdomen movements, caused
by respiration process, result in variations in their distance to the US transceiver located
at a distance of about 0.5 m. These variations are recorded by measuring the time of
flight from transmitting the signal and its reflection from the monitored surface.
Measurement of this delay over a time interval enables a respiration signal to be
produced from which respiration rate and pauses in breathing are determined.
To assess the accuracy of the developed device, a platform with a moving surface was
devised. The magnitude and frequency of its surface movement were accurately
controlled by its signal generator. The US sensor was mounted above this surface at a
distance of 0.5 m. This US signal was wirelessly transmitted to a microprocessor board
to digitise. The recorded signal that simulated a respiratory signal was subsequently
stored and displayed on a computer or an LCD screen. The results showed that US could
be used to measure respiration rate accurately. To cater for possible movement of the
infant in the incubator, four US sensors were adapted. These monitored the movements
from different angles. An algorithm to interpret the output from the four US sensors
was devised and evaluated. The algorithm interpreted which US sensor best detected
the chest movements.
An IoMT system was devised that incorporated NodeMcu to capture signals from the
US sensor. The detected data were transmitted to the ThingSpeak channel and
processed in real-time by ThingSpeak’s add-on Matlab© feature. The data were
processed on the cloud and then the results were displayed in real-time on a computer
screen. The respiration rate and respiration signal could be observed remotely on
portable devices e.g. mobile phones and tablets. These features allow caretakers to have
access to the data at any time and be alerted to respiratory complications.
A method to interpret the recorded US signals to determine respiration patterns, e.g.
intermittent pauses, were implemented by utilising Matlab© and ThingSpeak Server.
The method successfully detected respiratory pauses by identifying lack of chest
movements. The approach can be useful in diagnosing central apnoea. In central apnoea,
respiratory pauses are accompanied by cessation of chest or abdominal movements. The
devised system will require clinical trials and integration into an incubator by
conforming to the medical devices directives. The study demonstrated the integration
of IoMT-US for measuring respiration rate and respiratory signal. The US produced
respiration rate readings compared well with the actual signal generator's settings of the
platform that simulated chest movements
Development of a non-contact respiration monitoring device
No full textProyecto ConfidencialDavó Esplugues, I. (2012). Development of a non-contact respiration monitoring device. https://riunet.upv.es/handle/10251/28931.Archivo delegad
Development of Doppler ultrasound for measuring the neonatal heart rate at birth.
Full text linkThe heart rate of a newborn baby is a very important measure of its health and is routinely required to be documented at every birth. The imprecise measurement and lack of real-time
documentation of the neonatal heart rate at birth has been recognised for many years but auscultation still remains the recommended method in routine births. The heart rate of the
fetus is measured and documented during pregnancy and labour by Doppler ultrasound but immediately after birth the heart rate is measured by auscultation. Auscultation is well
recognised to be inaccurate and undocumented in real-time.to obtain the beats per minute heart rate. The contrast with determining and documenting the fetal heart rate with the
neonatal heart rate is remarkable. Recently a new ECG device has been developed in an attempt to provide more continuous monitoring and documentation of the neonatal heart rate
has been developed. There has also been investigation of the use of a hand-held foetal Doppler recently to determine the neonatal heart rate immediately after birth. It was found to
be very effective but has not been seriously considered by the International Liaison Committee On Resuscitation. One reason may be the fact that, unlike the ECG, but similar to
a stethoscope, the Doppler is not hands-free, as it requires one member of the resuscitation team to keep the transducer on the neonatal chest. Experience of over 50 years shows that even the slowest and weakest fetal hearts can be detected by Doppler ultrasound.
This research was to develop and test a hands-free version of a hand-held fetal Doppler device and to test this device for accuracy and functionality on adults and neonates. The
initial study was carried out on healthy adult volunteers using a standard hand-held fetal Doppler device. The Doppler heart rate was compared with the ECG heart rate and found to
have good correlation. The Bland Altman Plot of Doppler vs ECG showed all but two measurements were within the 95% confidence intervals.
A problem with documentation and the need for a hands-free transducer was highlighted.
This initial study fuelled the drive to construct a modified Doppler device to be hands-free and document electronically the heart rate results in real time. The problem of precise
documentation of both the Doppler heart rate and the ECG heart rate was explored. A further modification was required and the final device tested in a second adult study. This showed much improved ease of use during the investigation, excellent correlation and that the Doppler usually determined the heart rate consistently before the ECG.
The final part of the study involved using the modified hands free Doppler device on neonates at the Children’s Hospital Sleep Unit and comparing the Doppler heart rate with that of the hospital ECG. This demonstrated that the modified Doppler device was truly hands-free and, in the opinion of the parents, highly acceptable for use on their neonate
Routing protocols performance and intelligent quality of service applied to MANETs.
Full text linkThe wireless revolution prompted by the success of IEEE 802.11 standard has pressed the research community to deal with requirements of new wireless networks. In particular, wireless ad-hoc networks which are, specifically, a collection of wireless mobile nodes dynamically forming a temporary network without the use of any preexisting infrastructure or centralised administration. Routing protocols used in ad-hoc networks must automatically and continually adjust to environments. Most emerging network services require specialised Quality-of-Service (QoS) functionalities that cannot be provided by the current QoS-unaware routing protocols.Despite the large amount of research in these areas, several issues still need further investigation. The following points have become main concerns: i) traditional use of the hop count metric does not capture the very nature of wireless paths, resulting in poor performance of wireless networks; ii) the lack of comprehensive simulation methods to effectively observed performance of networks in various conditions and iii) the complexity of multi-constraint routing decisions, resulting in poor service quality in the end-user's point of view.This study takes an experimental approach to the evaluation of ad-hoc routing protocols and focuses on routing parameters as well as multimedia application QoS performance. In this thesis, we tackle the above mentioned issues and implement an efficient solution for the multi-constraint problem based on network measurements of valid experiments set-up. This study is exclusively based on simulations using NS-2 network simulator. In order to obtain an overview of the limitations of current conventional routing protocols, AODV and DSR protocols are used and their limitations in terms of QoS are measured and discussed. Operating conditions vary greatly from a static, lightly loaded network to constantly moving nodes with up to 10 simultaneous transmission connections. The results show that network performance degrades quickly and that QoS requirement was hardly met by any of these protocols.To evaluate the overall network performance, a new fuzzy logic assessment approach was developed taking into account the QoS parameters requirement of the transmitted application. Critical parameters were obtained through detailed simulation experiments under demanding operating conditions. These parameters were used as input to the fuzzy logic system to allow the computation of a single metric to represent the input variables (i.e. delay, jitter and throughput). The end results show that without a complicated mathematical model, a QoS value can be computed. This study addresses both theoretical aspects of QoS performance and routing progress in ad-hoc networks as well as practical issues in the set-up of simulation based studies.Finally, this study indicated that intelligent techniques can be effective for processing multiple QoS metrics to obtain an overall parameter that represents the application QoS. They can be adapted, not only to QoS routing, but to various aspects of QoS provisioning techniques
Thermal imaging developments for respiratory airflow measurement to diagnose apnoea
Full text linkSleep-disordered breathing is a sleep disorder that manifests itself as intermittent
pauses (apnoeas) in breathing during sleep. The condition disturbs the sleep and
can results in a variety of health problems. Its diagnosis is complex and involves
multiple sensors attached to the person to measure electroencephalogram (EEG),
electrocardiogram (ECG), blood oxygen saturation (pulse oximetry, S
Thermal and Visual Imaging and Accelerometry Developments to Assist with Arthritis Diagnosis
Full text linkJuvenile Idiopathic Arthritis (JIA) is a disease that causes pain and inflammation in the joints of children. Its early diagnosis is important to avoid damage to the joints. Joint warmth, redness and movement restriction may be indicators of active arthritis hence accurate objective means to measure temperature, colour and range of movement (ROM) at the joint may assist diagnosis.
In this study, three techniques with a potential to assist clinicians in diagnosing JIA were developed. These were based on high-resolution thermal imaging (HRTI), visual imaging and accelerometry. A detailed correlation analysis was performed between the developed methods and the consultant's clinical assessment of JIA diagnosis.
Twenty-two patients (age: mean=10.6 years, SD = 2 years) with JIA diagnosis were recruited. 18 participated in the thermal/visual imaging study only, 2 in the accelerometry study only and 2 in both thermal/visual imaging and accelerometry studies. Thermal and visual images of the front and back of the knees and ankles of 20 patients were studied. All ethical approvals from Sheffield Hallam University and the National Health Service (NHS) were duly obtained before commencing the study.
The thermal/visual imaging study involved developing image processing techniques to accurately identify and segment the regions of interest (ROIs). A tracking algorithm to accurately locate the ROIs was also implemented. An accelerometry system that is capable of recording movements from 4 channels was developed and its signals were processed by frequency spectrum analysis, short-time Fourier transform and wavelet packet analysis.
The thermal imaging results showed a combined 71% correlation (for the front of knees and ankles) with clinical assessment. It may be possible that patients whom their arthritic joint was cooler than their healthy joints may have relied on their healthy leg more extensively for mobility (due to the pain on the arthritic leg) thus increasing its joints temperature. It was also found that JIA may affect the skin colour with a combined 42% correlation between the knees and ankles. The accelerometry results showed a 75% correlation with clinical assessment.
The study for the first time brought together the three techniques of thermal imaging, visual imaging and accelerometry to assist with JIA diagnosis. The study demonstrated that the developed techniques have potential in assisting clinicians with JIA diagnosis. Improvements in timely diagnosis allow more effective treatment and can reduce the likelihood of joint damage in rheumatoid arthritis
- …
