Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
An intelligent approach to take care of mother and baby healthIJECEIAES
This is the era of technology and is widely used in every sector. In Bangladesh the use of technology is increasing day by day in many sectors. Health sector is one of them. This research is designed and developed to help the pregnant women to get weekly information on development and conditions of their health and the growing child inside their womb. This system will notify expectant mothers automatically about their health checkup date and time. It provides general and special health information to the expectant mothers. It is designed with user friendly interface so that an expectant mother can use this system very effectively. This system allows a unique secure login system and provides a unique suggestion to the expectant mothers.This system is very user friendly and useful.
Disease prediction in big data healthcare using extended convolutional neural...IJAAS Team
Diabetes Mellitus is one of the growing fatal diseases all over the world. It leads to complications that include heart disease, stroke, and nerve disease, kidney damage. So, Medical Professionals want a reliable prediction system to diagnose Diabetes. To predict the diabetes at earlier stage, different machine learning techniques are useful for examining the data from different sources and valuable knowledge is synopsized. So, mining the diabetes data in an efficient way is a crucial concern. In this project, a medical dataset has been accomplished to predict the diabetes. The R-Studio and Pypark software was employed as a statistical computing tool for diagnosing diabetes. The PIMA Indian database was acquired from UCI repository will be used for analysis. The dataset was studied and analyzed to build an effective model that predicts and diagnoses the diabetes disease earlier.
Framework for propagating stress control message using heartbeat based iot re...IJECEIAES
Abnormal level of stress is the root indicator factor to have significant impact over the health of heart and there is a close relationship between the stress levels with heart rate. Review of the existing literature showcase that there has been various work that has been carried out towards investigation of considering heart rate with an internet-of-things (IoT) system. Apart from this, existing system doesnt offer any instantaneous solution where certain intimation is offered in real-time to the user with wearables as a solution to control the stress condition. Therefore, the current paper introduces a novel framework where the sampled heart rates of the patients are captured by IoT deivices. The aggregated data are further forwarded to the cloud analytic system that uses correlation to extract the appropriate message. The system after being applied with teh machine learning approach could further extract the elite outcome followed by forwarding the contextual data to teh user. Using an analytical modelliig, the proposed system shows that it offers better accuracy and reduced processing time when compared with other machine learning approach and thereby it proves to be cost effective solution in IoT system over medical case study.
Survey of IOT based Patient Health Monitoring Systemdbpublications
The Internet of things has provided a promising opportunity and applications for medical services is one of the most important way or solution for taking care of population which is in rapid growth. Internet of things consists of communication and sensors; wireless body area network is highly suitable tool for the medical IOT device. In this survey we discuss mainly on practical issues for implementation of WBAN to health care service tool for the medical devices. The IoT applications are key enabling technologies in industries. A main aim of this survey paper is that it summarizes the present state-of-the-art IOT in industries and also in workflow hospitals systematically. In recent years wide range of opportunity and powerful of IOT applications are developed in industry. The health monitoring system is a big challenge for several researchers. In this paper introduced on the survey of different IOT applications are used for the health monitoring system. The IoT applications are used to decrease the problems which are related to health care system.
Predictive Data Mining for Converged Internet ofJames Kang
Kang, J. J., Adibi, S., Larkin, H., & Luan, T. (2016). Predictive data mining for Converged Internet of Things: A Mobile Health perspective. In Telecommunication Networks and Applications Conference (ITNAC), 2015 International (pp. 5-10). IEEE Xplore: IEEE. doi: http://dx.doi.org/10.1109/ATNAC.2015.7366781
Ecis final paper-june2017_two way architecture between iot sensors and cloud ...Oliver Neuland
Improving health care with IoT - Research into a weight monitoring bed - ECIS 2017 paper.
Resulting from smart furniture applications research project in Germany, Oliver Neuland and partners from AUT developed a smart bed concept which utilizes weight monitoring for AAL and elderly care. Initially strategies were applied to find meaningful use cases, later a prototype was developed. Here a paper presented during ECIS in Portugal which describes the architecture of the prototype.
An intelligent approach to take care of mother and baby healthIJECEIAES
This is the era of technology and is widely used in every sector. In Bangladesh the use of technology is increasing day by day in many sectors. Health sector is one of them. This research is designed and developed to help the pregnant women to get weekly information on development and conditions of their health and the growing child inside their womb. This system will notify expectant mothers automatically about their health checkup date and time. It provides general and special health information to the expectant mothers. It is designed with user friendly interface so that an expectant mother can use this system very effectively. This system allows a unique secure login system and provides a unique suggestion to the expectant mothers.This system is very user friendly and useful.
Disease prediction in big data healthcare using extended convolutional neural...IJAAS Team
Diabetes Mellitus is one of the growing fatal diseases all over the world. It leads to complications that include heart disease, stroke, and nerve disease, kidney damage. So, Medical Professionals want a reliable prediction system to diagnose Diabetes. To predict the diabetes at earlier stage, different machine learning techniques are useful for examining the data from different sources and valuable knowledge is synopsized. So, mining the diabetes data in an efficient way is a crucial concern. In this project, a medical dataset has been accomplished to predict the diabetes. The R-Studio and Pypark software was employed as a statistical computing tool for diagnosing diabetes. The PIMA Indian database was acquired from UCI repository will be used for analysis. The dataset was studied and analyzed to build an effective model that predicts and diagnoses the diabetes disease earlier.
Framework for propagating stress control message using heartbeat based iot re...IJECEIAES
Abnormal level of stress is the root indicator factor to have significant impact over the health of heart and there is a close relationship between the stress levels with heart rate. Review of the existing literature showcase that there has been various work that has been carried out towards investigation of considering heart rate with an internet-of-things (IoT) system. Apart from this, existing system doesnt offer any instantaneous solution where certain intimation is offered in real-time to the user with wearables as a solution to control the stress condition. Therefore, the current paper introduces a novel framework where the sampled heart rates of the patients are captured by IoT deivices. The aggregated data are further forwarded to the cloud analytic system that uses correlation to extract the appropriate message. The system after being applied with teh machine learning approach could further extract the elite outcome followed by forwarding the contextual data to teh user. Using an analytical modelliig, the proposed system shows that it offers better accuracy and reduced processing time when compared with other machine learning approach and thereby it proves to be cost effective solution in IoT system over medical case study.
Survey of IOT based Patient Health Monitoring Systemdbpublications
The Internet of things has provided a promising opportunity and applications for medical services is one of the most important way or solution for taking care of population which is in rapid growth. Internet of things consists of communication and sensors; wireless body area network is highly suitable tool for the medical IOT device. In this survey we discuss mainly on practical issues for implementation of WBAN to health care service tool for the medical devices. The IoT applications are key enabling technologies in industries. A main aim of this survey paper is that it summarizes the present state-of-the-art IOT in industries and also in workflow hospitals systematically. In recent years wide range of opportunity and powerful of IOT applications are developed in industry. The health monitoring system is a big challenge for several researchers. In this paper introduced on the survey of different IOT applications are used for the health monitoring system. The IoT applications are used to decrease the problems which are related to health care system.
Predictive Data Mining for Converged Internet ofJames Kang
Kang, J. J., Adibi, S., Larkin, H., & Luan, T. (2016). Predictive data mining for Converged Internet of Things: A Mobile Health perspective. In Telecommunication Networks and Applications Conference (ITNAC), 2015 International (pp. 5-10). IEEE Xplore: IEEE. doi: http://dx.doi.org/10.1109/ATNAC.2015.7366781
Ecis final paper-june2017_two way architecture between iot sensors and cloud ...Oliver Neuland
Improving health care with IoT - Research into a weight monitoring bed - ECIS 2017 paper.
Resulting from smart furniture applications research project in Germany, Oliver Neuland and partners from AUT developed a smart bed concept which utilizes weight monitoring for AAL and elderly care. Initially strategies were applied to find meaningful use cases, later a prototype was developed. Here a paper presented during ECIS in Portugal which describes the architecture of the prototype.
Smart Health Prediction Using Data Mining.Data mining is a new powerful technology which is of high interest in computer world. It is a sub field of computer science that uses already existing data in different databases to transform it into new researches and results. It makes use of Artificial Intelligence, machine learning and database management to extract new patterns from large data sets and the knowledge associated with these patterns. The actual task is to extract data by automatic or semi-automatic means. The different parameters included in data mining includes clustering, forecasting, path analysis and predictive analysis.
DISEASE PREDICTION USING MACHINE LEARNING OVER BIG DATAcseij
Due to big data progress in biomedical and healthcare communities, accurate study of medical data
benefits early disease recognition, patient care and community services. When the quality of medical data
is incomplete the exactness of study is reduced. Moreover, different regions exhibit unique appearances of
certain regional diseases, which may results in weakening the prediction of disease outbreaks. In the
proposed system, it provides machine learning algorithms for effective prediction of various disease
occurrences in disease-frequent societies. It experiment the altered estimate models over real-life hospital
data collected. To overcome the difficulty of incomplete data, it use a latent factor model to rebuild the
missing data. It experiment on a regional chronic illness of cerebral infarction. Using structured and
unstructured data from hospital it use Machine Learning Decision Tree algorithm and Map Reduce
algorithm. To the best of our knowledge in the area of medical big data analytics none of the existing work
focused on both data types. Compared to several typical estimate algorithms, the calculation exactness of
our proposed algorithm reaches 94.8% with a convergence speed which is faster than that of the CNNbased
unimodal disease risk prediction (CNN-UDRP) algorithm.
Artificial intelligence (AI), machine learning, and data science have started to shape the delivery of health services. We see this in every critical step, from patient scheduling management to physically assisted surgery.
PREDICTIVE ANALYTICS IN HEALTHCARE SYSTEM USING DATA MINING TECHNIQUEScscpconf
The health sector has witnessed a great evolution following the development of new computer technologies, and that pushed this area to produce more medical data, which gave birth to multiple fields of research. Many efforts are done to cope with the explosion of medical data on one hand, and to obtain useful knowledge from it on the other hand. This prompted researchers to apply all the technical innovations like big data analytics, predictive analytics, machine learning and learning algorithms in order to extract useful knowledge and help in making decisions. With the promises of predictive analytics in big data, and the use of machine learning
algorithms, predicting future is no longer a difficult task, especially for medicine because predicting diseases and anticipating the cure became possible. In this paper we will present an overview on the evolution of big data in healthcare system, and we will apply a learning algorithm on a set of medical data. The objective is to predict chronic kidney diseases by using Decision Tree (C4.5) algorithm.
Proposed Model for Chest Disease Prediction using Data Analyticsvivatechijri
Chest diseases if not properly diagnosed in early stages can be fatal. Because of lack of skilled
knowledge or experiences of real life practitioners, many a times one chest disease is wrongly diagnosed for the
other, which leads to wrong treatment. Due to this the actual disease keeps on growing and become fatal. For
example, muscular chest pains can be treated for the heart disease or COPD is treated for Asthma. Early
prediction of chest disease is crucial but is not an easy task. Consequently, the computer based prediction system
for chest disease may play a significant role as a pre-stage detection to take proper actions with a view to recover
from it. However the choice of the proper Data Mining classification method can effectively predict the early
stage of the disease for being cured from it. In this paper, the three mostly used classification techniques such as
support vector machine (SVM), k-nearest neighbour (KNN) and artificial neural network (ANN) have been studied
with a view to evaluating them for chest disease prediction.
CONCEPTUAL MODEL FOR ELECTRONIC CLINICAL RECORD INFORMATION SYSTEMijistjournal
This study is drawn from an ongoing, large-scale project of implementing Electronic Clinical Record (ECR). The overall aim in this study is to develop a deeper understanding of the socio-technical aspects of the complexities and challenges emerging from the implementation of the ECR, and in particular to study how to manage a gradual transition to digital record. We have proposed ECR conceptual model. The end result of our research was a collection of ideas / surveys, and field work that clinical institutions and medical informatics must consider to ensure that patients and clinics do not lose long-term access to ECR and technology continually progress. Results of our study identified the need for more research in this particular area as no definitive solution to long-term access to electronic clinical records was revealed. Additionally, the research findings highlighted the fact that a few medical institutions may actually be concerned about long-term access to electronic records.
IoT and machine learning (ML) are becoming increasingly efficient in the medical and telemedicine areas all around the world. This article describes a system that employs latest technology to give a more accurate method of forecasting disease. This technology uses sensors to collect data from the body of the patient. The obtained sensor information is collected with NodeMcU before being transferred to the Cloud Platform "ThinkSpeak" through an ESP8266 Wi-Fi module. ThinkSpeak is a cloud server that provides real-time data streams in the cloud. For the best results, data currently saved in the cloud is evaluated by one of the machine learning algorithms, the KNN algorithm. Based on the findings of the analysis and compared with the data sets, the disease is predicted and a prescription for the relevant disease is issued.
COVID-19 knowledge-based system for diagnosis in Iraq using IoT environmentnooriasukmaningtyas
The importance and benefits of healthcare mobile applications is increasing rapidly, especially when such applications are connected to the internet of things (IoT). This paper describes a smart knowledge-based system (KBS) that helps patients showing symptoms of Influenza verify being infected with Coronavirus, commonly known as COVID-19. In addition to the systems’ diagnostic functionality, it helps these patients get medical assistance fast by notifying medical authorities using the IoT. This system displays patient’s location, phone number, date and time of examination. During the applications’ development, the developers used Twilio, short message service (SMS), WhatsApp, and Google map applications.
Smart Health Prediction Using Data Mining.Data mining is a new powerful technology which is of high interest in computer world. It is a sub field of computer science that uses already existing data in different databases to transform it into new researches and results. It makes use of Artificial Intelligence, machine learning and database management to extract new patterns from large data sets and the knowledge associated with these patterns. The actual task is to extract data by automatic or semi-automatic means. The different parameters included in data mining includes clustering, forecasting, path analysis and predictive analysis.
DISEASE PREDICTION USING MACHINE LEARNING OVER BIG DATAcseij
Due to big data progress in biomedical and healthcare communities, accurate study of medical data
benefits early disease recognition, patient care and community services. When the quality of medical data
is incomplete the exactness of study is reduced. Moreover, different regions exhibit unique appearances of
certain regional diseases, which may results in weakening the prediction of disease outbreaks. In the
proposed system, it provides machine learning algorithms for effective prediction of various disease
occurrences in disease-frequent societies. It experiment the altered estimate models over real-life hospital
data collected. To overcome the difficulty of incomplete data, it use a latent factor model to rebuild the
missing data. It experiment on a regional chronic illness of cerebral infarction. Using structured and
unstructured data from hospital it use Machine Learning Decision Tree algorithm and Map Reduce
algorithm. To the best of our knowledge in the area of medical big data analytics none of the existing work
focused on both data types. Compared to several typical estimate algorithms, the calculation exactness of
our proposed algorithm reaches 94.8% with a convergence speed which is faster than that of the CNNbased
unimodal disease risk prediction (CNN-UDRP) algorithm.
Artificial intelligence (AI), machine learning, and data science have started to shape the delivery of health services. We see this in every critical step, from patient scheduling management to physically assisted surgery.
PREDICTIVE ANALYTICS IN HEALTHCARE SYSTEM USING DATA MINING TECHNIQUEScscpconf
The health sector has witnessed a great evolution following the development of new computer technologies, and that pushed this area to produce more medical data, which gave birth to multiple fields of research. Many efforts are done to cope with the explosion of medical data on one hand, and to obtain useful knowledge from it on the other hand. This prompted researchers to apply all the technical innovations like big data analytics, predictive analytics, machine learning and learning algorithms in order to extract useful knowledge and help in making decisions. With the promises of predictive analytics in big data, and the use of machine learning
algorithms, predicting future is no longer a difficult task, especially for medicine because predicting diseases and anticipating the cure became possible. In this paper we will present an overview on the evolution of big data in healthcare system, and we will apply a learning algorithm on a set of medical data. The objective is to predict chronic kidney diseases by using Decision Tree (C4.5) algorithm.
Proposed Model for Chest Disease Prediction using Data Analyticsvivatechijri
Chest diseases if not properly diagnosed in early stages can be fatal. Because of lack of skilled
knowledge or experiences of real life practitioners, many a times one chest disease is wrongly diagnosed for the
other, which leads to wrong treatment. Due to this the actual disease keeps on growing and become fatal. For
example, muscular chest pains can be treated for the heart disease or COPD is treated for Asthma. Early
prediction of chest disease is crucial but is not an easy task. Consequently, the computer based prediction system
for chest disease may play a significant role as a pre-stage detection to take proper actions with a view to recover
from it. However the choice of the proper Data Mining classification method can effectively predict the early
stage of the disease for being cured from it. In this paper, the three mostly used classification techniques such as
support vector machine (SVM), k-nearest neighbour (KNN) and artificial neural network (ANN) have been studied
with a view to evaluating them for chest disease prediction.
CONCEPTUAL MODEL FOR ELECTRONIC CLINICAL RECORD INFORMATION SYSTEMijistjournal
This study is drawn from an ongoing, large-scale project of implementing Electronic Clinical Record (ECR). The overall aim in this study is to develop a deeper understanding of the socio-technical aspects of the complexities and challenges emerging from the implementation of the ECR, and in particular to study how to manage a gradual transition to digital record. We have proposed ECR conceptual model. The end result of our research was a collection of ideas / surveys, and field work that clinical institutions and medical informatics must consider to ensure that patients and clinics do not lose long-term access to ECR and technology continually progress. Results of our study identified the need for more research in this particular area as no definitive solution to long-term access to electronic clinical records was revealed. Additionally, the research findings highlighted the fact that a few medical institutions may actually be concerned about long-term access to electronic records.
IoT and machine learning (ML) are becoming increasingly efficient in the medical and telemedicine areas all around the world. This article describes a system that employs latest technology to give a more accurate method of forecasting disease. This technology uses sensors to collect data from the body of the patient. The obtained sensor information is collected with NodeMcU before being transferred to the Cloud Platform "ThinkSpeak" through an ESP8266 Wi-Fi module. ThinkSpeak is a cloud server that provides real-time data streams in the cloud. For the best results, data currently saved in the cloud is evaluated by one of the machine learning algorithms, the KNN algorithm. Based on the findings of the analysis and compared with the data sets, the disease is predicted and a prescription for the relevant disease is issued.
COVID-19 knowledge-based system for diagnosis in Iraq using IoT environmentnooriasukmaningtyas
The importance and benefits of healthcare mobile applications is increasing rapidly, especially when such applications are connected to the internet of things (IoT). This paper describes a smart knowledge-based system (KBS) that helps patients showing symptoms of Influenza verify being infected with Coronavirus, commonly known as COVID-19. In addition to the systems’ diagnostic functionality, it helps these patients get medical assistance fast by notifying medical authorities using the IoT. This system displays patient’s location, phone number, date and time of examination. During the applications’ development, the developers used Twilio, short message service (SMS), WhatsApp, and Google map applications.
New methodology to detect the effects of emotions on different biometrics in...IJECEIAES
Recently, some problems have appeared among medical workers during the diagnosis of some diseases due to human errors or the lack of sufficient information for the diagnosis. In medical diagnosis, doctors always resort to separating human emotions and their impact on vital parameters. In this paper, a methodology is presented to measure vital parameters more accurately while studying the effect of different human emotions on vital signs. Two designs were implemented based on the microcontroller and National Instruments (NI) myRIO. Measurements of four different vital parameters are measured and recorded in real time. At the same time, the effects of different emotions on those vital parameters are recorded and stored for use in analysis and early diagnosis. The results proved that the proposed methodology can contribute to the prediction and diagnosis of the initial symptoms of some diseases such as the seventh nerve and Parkinson’s disease. The two proposed designs are compared with the reference device (beurer) results. The design using NI myRIO achieved more accurate results and a response time of 1.4 seconds for real-time measurements compared to its counterpart based on microcontrollers, which qualifies it to work in intensive care units.
In this paper, a novel cloud-based WBAN health management system is introduced to. This system can be used for people’s health information collection, record, storage and transmission, health status monitoring and assessment, health education, telemedicine, and remote health management. Therefore it can provide health management services on-demand timely, appropriately and without boundaries.
Intelligent Healthcare Monitoring in IoTIJAEMSJORNAL
The developing of IoT-based health care systems must ensure and increase the safety of the patients, their quality of life and other health care activities. We may not be aware of the health condition of the patient during the sleeping hours. To overcome this problem. This paper proposes an intelligent healthcare monitoring system which monitors and maintains the patient health condition at regular intervals. The heart rate sensor and temperature sensor would help us analyze the patients’ current health condition. In case of major fluctuations in consecutive intervals a buzzer is run in order to notify the hospital staff and doctors. The monitored details are stored in the cloud "ThingSpeak". The doctor can view the patient health condition using Virtuino simulator. This system would help in reducing the random risks of tracing a patient medical highly. Arduino UNO is used to implement this intelligent healthcare monitoring system.
Real-time Heart Pulse Monitoring Technique Using Wireless Sensor Network and ...IJECEIAES
Wireless Sensor Networks (WSNs) for healthcare have emerged in the recent years. Wireless technology has been developed and used widely for different medical fields. This technology provides healthcare services for patients, especially who suffer from chronic diseases. Services such as catering continuous medical monitoring and get rid of disturbance caused by the sensor of instruments. Sensors are connected to a patient by wires and become bed-bound that less from the mobility of the patient. In this paper, proposed a real-time heart pulse monitoring system via conducted an electronic circuit architecture to measure Heart Pulse (HP) for patients and display heart pulse measuring via smartphone and computer over the network in real-time settings. In HP measuring application standpoint, using sensor technology to observe heart pulse by bringing the fingerprint to the sensor via used Arduino microcontroller with Ethernet shield to connect heart pulse circuit to the internet and send results to the web server and receive it anywhere. The proposed system provided the usability by the user (userfriendly) not only by the specialist. Also, it offered speed andresults accuracy, the highest availability with the user on an ongoing basis, and few cost.
The International Journal of Pharmacetical Sciences Letters (IJPSL) is an international online journal in English published everyday. The aim of this is to publish peer reviewed research and review articles without delay in the developing field of engineering and science Research.
International Journal of Computational Engineering Research(IJCER)ijceronline
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
An internet of things-based automatic brain tumor detection systemIJEECSIAES
Due to the advances in information and communication technologies, the usage of the internet of things (IoT) has reached an evolutionary process in the development of the modern health care environment. In the recent human health care analysis system, the amount of brain tumor patients has increased severely and placed in the 10th position of the leading cause of death. Previous state-of-the-art techniques based on magnetic resonance imaging (MRI) faces challenges in brain tumor detection as it requires accurate image segmentation. A wide variety of algorithms were developed earlier to classify MRI images which are computationally very complex and expensive. In this paper, a cost-effective stochastic method for the automatic detection of brain tumors using the IoT is proposed. The proposed system uses the physical activities of the brain to detect brain tumors. To track the daily brain activities, a portable wrist band named Mi Band 2, temperature, and blood pressure monitoring sensors embedded with Arduino-Uno are used and the system achieved an accuracy of 99.3%. Experimental results show the effectiveness of the designed method in detecting brain tumors automatically and produce better accuracy in comparison to previous approaches.
An internet of things-based automatic brain tumor detection systemnooriasukmaningtyas
Due to the advances in information and communication technologies, the usage of the internet of things (IoT) has reached an evolutionary process in the development of the modern health care environment. In the recent human health care analysis system, the amount of brain tumor patients has increased severely and placed in the 10th position of the leading cause of death. Previous state-of-the-art techniques based on magnetic resonance imaging (MRI) faces challenges in brain tumor detection as it requires accurate image segmentation. A wide variety of algorithms were developed earlier to classify MRI images which are computationally very complex and expensive. In this paper, a cost-effective stochastic method for the automatic detection of brain tumors using the IoT is proposed. The proposed system uses the physical activities of the brain to detect brain tumors. To track the daily brain activities, a portable wrist band named Mi Band 2, temperature, and blood pressure monitoring sensors embedded with Arduino-Uno are used and the system achieved an accuracy of 99.3%. Experimental results show the effectiveness of the designed method in detecting brain tumors automatically and produce better accuracy in comparison to previous approaches.
Advancing the cybersecurity of the healthcare system with self- optimising an...Petar Radanliev
This article advances the knowledge on teaching and training new artificial intelligence algorithms, for securing, preparing,
and adapting the healthcare system to cope with future pandemics. The core objective is to develop a concept healthcare
system supported by autonomous artificial intelligence that can use edge health devices with real-time data. The article constructs two case scenarios for applying cybersecurity with autonomous artificial intelligence for (1) self-optimising predictive cyber risk analytics of failures in healthcare systems during a Disease X event (i.e., undefined future pandemic), and (2) self-adaptive forecasting of medical production and supply chain bottlenecks during future pandemics. To construct the two testing scenarios, the article uses the case of Covid-19 to synthesise data for the algorithms – i.e., for optimising and securing digital healthcare systems in anticipation of Disease X. The testing scenarios are built to tackle the logistical challenges and disruption of complex production and supply chains for vaccine distribution with optimisation algorithms.
THE EPISTEMOLOGICAL BASES THAT SUPPORT REASONING OF CLINICAL DIAGNOSISamsjournal
We find difficulties when defining disease in relation to a set of sufficient and necessary characters that we
can see repeated uniformly in every instance of this term or under the principle in which all its members
have identical properties as they have a common nature. In studying the term disease, we have to explore
other principles which could help us categorize it.
In this work, we analyze other alternatives. Following the epistemologist Cesar Lorenzano, we claim that
each disease is a clinical theory, and each patient is an example of that theory. How we learn is through
exemplary demonstrations that teachers practically show. It is what we call paradigmatic exemplars
necessary for doctors to incorporate the theoretical structure of each disease, which, together with the
clinical case models, instructs how the patient can present himself to the consultation.
How do the doctors select from all the diseases the one that best fits as a hypothesis for their patient? How
does the doctor elaborate and epistemically justify his diagnosis?
We can explain this subject through Pierce's abductive reasoning, with the elements of structuralist
metatheory and the use of paradigmatic exemplars.
THE APPLICATION OF MATHEMATICAL MODELS IN MANAGEMENT OF AQUIFERamsjournal
Before feeling water -shortage crisis human has understood the importance of water From the
religious texts. Considering recent conditions of the world the water will replace most recent
boundaries, at future. Imamzadeh Jaafar plain is located 5 kilometers northeast of Gachsaran, south
of Kohgilooye and Boerahmad province. The plain has 61km 2 area extents and contains two,
alluvial and carbonate aquifers. These aquifers supply the water needs, agricultural, industrial and
domestic. Highly exploitation and transportation of groundwater resources, especially by National Oil
Company, caused highly drawdown in alluvial aquifer, 1.85m in a 5 years period from 1361 to
1365 as reported by Mahab Ghods Consulting Engineers. There are two artificial recharge
projects, 1 flood spreading system and 1 recharge ponds system, in the plain. To present the future
water resources management program the hydrogeological behaviors of the alluvial aquifer and the
effects of artificial recharge must be evaluated. edrock, hydrodynamic coefficients, topography, water
resources and were collected, field surveys were performed and required maps were prepared. Using
conceptual model and MODFLOW PMWIN code the mathematical model of the plain was
calibrated against water year 1380 -81 and then verified against water year 1384 - 85. The verified
model was used to predict future conditions of aquifer. The results implied the rapid response of
aquifer to precipitation due to high aquifer ransmissivity, positive water budget at year 1385
comparing year 65, change of direction of groundwater flow from plain outlet to the center of
plain in response to highly exploitation at the center of plain, water level in the wells located
downward the flood spreading system will raise as 1 to 6m and water level in t he wells located
downward the recharge pond system will lower as 1 to 4m.
Advanced Medical Sciences: An International Journal (AMS)amsjournal
Advanced Medical Sciences: An International Journal (AMS) is a quarterly open access peer-reviewed journal that publishes articles which contribute new results in all areas of the Medical Sciences. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on understanding advances in Medical Sciences and establishing new collaborations in these areas.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Medical Sciences.
A CROSS-SECTIONAL STUDY ANALYSING THE LEVEL OF DEPRESSION AND ITS CAUSATIVE F...amsjournal
Depression is a pathological state of the mind characterised lack of self-confidence and self-esteem. The
cause of depression is multi factorial and various physical, psychological, environmental and genetic
factors have been implicated in the causation of depression. Despite being a serious condition in all age
groups, depression is more common and significant in the geriatric population as it is associated with
significant morbidity and mortality. Various scales have been developed to assess depression of which the
Geriatric Depression Scale is most suited for elderly population. It has a long form and short form, the
latter being more appropriate for elderly patients with dementia. In our study, we aim to analyse the
prevalence of depression among elderly patients visiting the outpatient departments of a tertiary care
hospital and determine the factors influencing depression in them. The study was an Observational cross sectional
study carried out on 51 elderly patients over the age of 60 years attending the various outpatient
departments of PSG Hospital. The Geriatric Depression Scale Short form was used to determine the
prevalence of depression. A self-designed questionnaire considering various factors causing depression
was administered to determine the factors influencing depression. It was found that among 51 elders in the
age group of 60 to 80 years, 58.8% were depressed of which 54% were males and 68% were females.
Financial fears regarding future and income insufficiency were the most important factors contributing to
depression. This shows that monetary fear is a major factor resulting in depression. The most effective
strategy to combat depression is to ensure appropriate self-report. The government and other organizations
must ensure that better support, both financial and other services like healthcare are provided to the
elderly in order to prevent depressive illnesses.
Depression is a state of feeling sad, miserable and down in the dumps with loss of self-confidence. Depression despite being a serious condition in all age groups is more common and significant in the
geriatric population as it is associated with morbidity and mortality. The cause of depression is multifactorial. Various scales have been developed to assess depression of which the Geriatric Depression
Scale is most suited for elderly population and those with dementia. In our study, we aim to analyse the prevalence of depression among elderly patients visiting the outpatient departments of a tertiary care hospital and determine the factors influencing depression in them. The study was an Observational study carried out on 51 elderly patients over the age of 60 years attending the outpatient departments of PSG Hospital. The Geriatric Depression Scale Short form was used to determine the prevalence of depression. A
self-designed questionnaire considering various factors causing depression was administered to determine
the factors influencing depression. It was found that among 51 elders in the age group of 60 to 80 years,
58.8% were depressed of which 54% were males and 68% were females. Financial fears regarding future
and income insufficiency were the most important factors contributing to depression. This shows that
monetary fear is a major factor resulting in depression. The government and other organizations must
ensure that better support both financial and other services like healthcare are provided to the elderly in
order to prevent depressive illnesses.
A comparative analysis of biochemical and hematological parameters in diabeti...amsjournal
This study evaluated the biochemical and the hematological parameters in diabetic and non- diabetic patients. The measured biochemical parameters were fasting blood sugar, serum alanine aminotransferase (SGPT/ALT), total cholesterol, urea, creatinine and hematological parameters were hemoglobin, total white blood cell, neutrophil, lymphocyte,monocyte, eosinophil and ESR. There were 403 diabetic and 320 non-diabetic subjects included in this study and the study was carried out in BIRDEM (Bangladesh Institute of Research & Rehabilitation in Diabetes, Endocrine and Metabolic Disorders) General Hospital). It was observed that the mean values of SGPT/ALT (p<0.001),><0.001)><0.001)><0.001),><0.004),><0.001) of hematological parameters were significantly higher in diabetic patients than in the non-diabetic patients. In univariate analysis, all biochemical parameters and only four hematological parameters were found significantly associated with fasting blood sugar after adjusted with age and sex. The fasting blood sugar correlates highly with the other biochemical parameters but less or none with the hematological parameters. Our findings demonstrated that control of increased biochemical parameters and abnormal hematological levels in the early stage of diabetes mellitus may help the patients to raise quality of life.
Student information management system project report ii.pdfKamal Acharya
Our project explains about the student management. This project mainly explains the various actions related to student details. This project shows some ease in adding, editing and deleting the student details. It also provides a less time consuming process for viewing, adding, editing and deleting the marks of the students.
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)MdTanvirMahtab2
This presentation is about the working procedure of Shahjalal Fertilizer Company Limited (SFCL). A Govt. owned Company of Bangladesh Chemical Industries Corporation under Ministry of Industries.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Overview of the fundamental roles in Hydropower generation and the components involved in wider Electrical Engineering.
This paper presents the design and construction of hydroelectric dams from the hydrologist’s survey of the valley before construction, all aspects and involved disciplines, fluid dynamics, structural engineering, generation and mains frequency regulation to the very transmission of power through the network in the United Kingdom.
Author: Robbie Edward Sayers
Collaborators and co editors: Charlie Sims and Connor Healey.
(C) 2024 Robbie E. Sayers
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
CFD analysis is incredibly effective at solving mysteries and improving the performance of complex systems!
Here's a great example: At a large natural gas-fired power plant, where they use waste heat to generate steam and energy, they were puzzled that their boiler wasn't producing as much steam as expected.
R&R and Tetra Engineering Group Inc. were asked to solve the issue with reduced steam production.
An inspection had shown that a significant amount of hot flue gas was bypassing the boiler tubes, where the heat was supposed to be transferred.
R&R Consult conducted a CFD analysis, which revealed that 6.3% of the flue gas was bypassing the boiler tubes without transferring heat. The analysis also showed that the flue gas was instead being directed along the sides of the boiler and between the modules that were supposed to capture the heat. This was the cause of the reduced performance.
Based on our results, Tetra Engineering installed covering plates to reduce the bypass flow. This improved the boiler's performance and increased electricity production.
It is always satisfying when we can help solve complex challenges like this. Do your systems also need a check-up or optimization? Give us a call!
Work done in cooperation with James Malloy and David Moelling from Tetra Engineering.
More examples of our work https://www.r-r-consult.dk/en/cases-en/
Cosmetic shop management system project report.pdfKamal Acharya
Buying new cosmetic products is difficult. It can even be scary for those who have sensitive skin and are prone to skin trouble. The information needed to alleviate this problem is on the back of each product, but it's thought to interpret those ingredient lists unless you have a background in chemistry.
Instead of buying and hoping for the best, we can use data science to help us predict which products may be good fits for us. It includes various function programs to do the above mentioned tasks.
Data file handling has been effectively used in the program.
The automated cosmetic shop management system should deal with the automation of general workflow and administration process of the shop. The main processes of the system focus on customer's request where the system is able to search the most appropriate products and deliver it to the customers. It should help the employees to quickly identify the list of cosmetic product that have reached the minimum quantity and also keep a track of expired date for each cosmetic product. It should help the employees to find the rack number in which the product is placed.It is also Faster and more efficient way.
Welcome to WIPAC Monthly the magazine brought to you by the LinkedIn Group Water Industry Process Automation & Control.
In this month's edition, along with this month's industry news to celebrate the 13 years since the group was created we have articles including
A case study of the used of Advanced Process Control at the Wastewater Treatment works at Lleida in Spain
A look back on an article on smart wastewater networks in order to see how the industry has measured up in the interim around the adoption of Digital Transformation in the Water Industry.
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
The Benefits and Techniques of Trenchless Pipe Repair.pdf
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASES
1. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
DOI: 10.5121/ams.2021.8301 1
INTERNET OF THINGS BASED MODEL FOR
IDENTIFYING PEDIATRIC EMERGENCY CASES
Juliet Gathoni Muchori1
, Gabriel Kamau1
, and Faith Mueni Musyoka2
1
Department of Information Technology, Murang’a University of Technology,
Murang’a, Kenya
2
Department of Mathematics, Computing & Information Technology, University of
Embu, Embu, Kenya
ABSTRACT
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
KEYWORDS
Internet of Things, message queuing telemetry transport, Amazon web service, World health organization
1. INTRODUCTION
Children's health emergency cases are on the rise. The need for convenient, efficient, affordable,
urgent, and preventive medication has led to the development of e-health models over the past
years. These models measure vital body parameters, analyze and diagnose diseases and
conditions to aid medical decision-making. Current systems are manual therefore, they need
specialization and automation to enhance service delivery in hospitals.
Modern e-health models are based on cloud computing, IoT gadgets, wearable sensors, and
modern data analytical methods. Some are also linked to medical databases for efficiency and
data retrieval.
The United Nations Convention on the Rights of the Child (UNCRC) Lansdown stated that
children have a right to be heard and participate in healthcare issues [1]. Among the issues
include understanding their health conditions, giving their views, and participating in health
decision-making. Currently, parents and healthcare professionals are the ones who take that role.
Usage of e-health solutions can remove the barriers and assist children to communicate with
health care professionals [2]. The use of IoT gadgets will assist the children to express
themselves electronically by analyzing their vital body parameters and hence emergency status.
2. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
2
In this paper, we propose an IoT based model, that employs peripherals and BalenaFin gadgets
with Raspberry Pi compute module at its core for vital body parameter data collection. The
gadgets use Bluetooth and other protocols such as MQTT for data communication. Data is sent to
a cloud server database infrastructure and later machine learning techniques are applied to the
data to categorize children into emergency, no emergency, and moderate emergency.
Several models on e-health have been proposed showing that there are severalIoT gadgets made
by different manufacturers for semantic sensing [3]. These devices collect data using different
data formats, which causes a problem in device interoperability, and data normalization. Jin and
Kim [3] created an e-health model that addresses interoperability issues in the IoT devices and
supporting data with different style formats.
The rest of the paper presents related works methodology used, implementation, results,
discussion, and conclusion.
2. RELATED WORKS
Studies focusing on children cases exist, for instance, Jangra and Gupta created a system for
monitoring and recording patients data [5]. The model consisted of three sensors that collected
heart rate, temperature, and blood pressure data from the patients, raising alerts whenever it
encountered abnormalities. In [5] normal Blood Pressure range was 80-120 mm Hg while the
body temperature normal range was 36.5-37.5C and Heart Rate normal range was 60-100
beats/min. The model also used the data collected to analyze and predict chronic disorders using
data mining techniques. The challenge with the model is that it is suited for specific chronic
diseases such as heart attack.
In [3], a model is developed to address the device interoperability issue and normalization of
data. It proposes various gadgets that measure different parameters, for instance, the IoT blood
pressure gadget is used to measure blood pressure-related data, electromyography gadgets collect
data related to body muscles, and the galvanic skin response gadget is used to gather patients'
emotional behaviors. Further, a close look at these technologies shows that most analysis of a
patient's information involves temperature, blood pressure, muscle data, and skin responses.
However, the challenge with the model is that it only tested interoperability issues and largely
neglected data analysis.
Another related low-cost sensor e-health model that offers medical services was also created [6].
The model uses low power and has an increased data accuracy [6]. It can perform medical checks
using Sensor Controllers (SC), and the results are communicated to mobile or tablet devices,
from SC and logical gateways. The model, which uses IoT gadgets like body position sensor,
ECG, Airflow, electromyogram-EMG, thermometer, glucose sensor, galvanic skin response
sensor, and blood pressure gadgets, has been shown to produce accurate results hence good for
hospitals. The limitation of the model is that it fails to indicate the level of emergency of a
patient.
Another related model constructed using different IoT gadgets which assisted in collecting data
about the quality of air, the temperature, detection of earthquakes, level of light, level of humidity
among others is proposed [4]. Using this data, the model makes meaningful insights for decision-
making. IoT gadgets used in water management were also used to ensure the water is well
distributed within the hospital premise efficiently. The gadgets assisted to reduce the wastage of
water via leaking. The IoT gadgets were used to monitor when the dustbin was full and needed to
be emptied. This reduced the human efforts to keep on checking the bin now and then in addition
3. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
3
to raising the standards of hygiene within the hospital premises. Further, the model used gadgets
like smart wheelchairs and body stretchers.
3. METHODOLOGY
A. Experimental Planning and Preparation of Materials
In this study, an experimental research design is used based on a recorded data that includes heart
rate, blood pressure, oxygen levels, and body temperature gotten from the child subject seeking
medical attention. The recorded body parameters are sent to the BalenaFin industrial grade
development board via Bluetooth Low Energy (BLE) protocol. The board has Bluetooth, WIFI,
and ethernet communication features.
The central development board referred to as the central device, has a program developed using
python programming language, to hold and save the vitals, in this case, heart rate, body
temperature, oxygen levels, and blood pressure.
The peripheral device is enabled to be easily discovered and connected to the central device using
a MAC address. The actual MAC address of the device is also saved with the data of the child to
assist identify the child and the age.
The central device operates in active mode since it is receiving the recorded data. The pairing
process is
preconfigured and connections established with the data. Data received on the central device is
first stored locally on a .csv file as backup, at the same time it is sent to a cloud server via the
internet connection to the internet hotspot. The MQTT that transports messages between devices
sends data to the cloud server and stores it in a database.
A cloud server is set up on an Amazon Web Service (AWS) instance with the Debian/Ubuntu
operating system. Anaconda development environment installed on the virtual machine (cloud
server) to facilitate the use of Jupyter notebook computational software. A NoSQL time series
influx database is also installed for data storage from subscribed MQTT topics.
B. Population, Sampling and Sample Size
The study population included children seeking treatment at Murang’a level 5 hospital and
Kangema level 4 hospital. Both hospitals are located in Murangacounty, Kenya. The two
hospitals were chosen because they have specialized departments that deal with child healthcare.
On average, 40 children visit Murang’a level 5 hospital while 30 children visit Kangema level 4
hospital per day. Thisdata was collected to assist in the general testing of the model. Therefore.
We used purposive sampling to determine the sample size. The patient demographics were high
since it served children from neighboring counties and referrals.
We used the following formula to calculate the sample size as proposed in Michael Slovin (1960)
n=N/(1+Ne^2)
Where n=number of sample size
N=Total population
e=confidential level.
4. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
4
We got a confidence level of 0.02. It provides a 98% level of accuracy. From a population of 40
at the Murang’a level 5 hospital, we obtained a sample size of 59 children i.e.
n=N/(1+Ne^2)
n=40/(1+(40*0.02^2)
n=40/(1+0.024)
n=39.3
n=39
In addition, we obtained a sample of 33 children from a population of 33 at the Kangema level 4
hospital i.e.
n=N/(1+Ne^2)
n=33/(1+(33*0.02^2)
n=30/(1+0.0132)
n=33.4
n=33
This information on sample sizes used in this study is shown in Table 1.
Table 1: Study Sample
Population Sample
Murang’a
level 5 hospital
40 39
Kangema
level 4 hospital
33 33
Total 73 72
C. Data Collection
In this study, Data recorded in the past three months in both hospitals was used to train the
machine learning algorithm, that was implemented in the model.
D. Data Analysis
Heart rate, blood pressure, temperature, and oxygen levels were used to classify emergency cases.
Random Forest classifier was used to make predictions on the data. Anaconda helps in analytics.
It is a software that was installed along with numerous analytical tools and libraries including
Jupyter notebook. A python3 virtual environment was set up and SciKit-Learn, scipy, NumPy,
Matplotlib, pandas among other libraries. The virtual environment was created to keep all
libraries native to the application and development. Using the Jupyter notebook a Random Forest
Classifier is trained using hospital recorded data. 75% of the data was used in training while 25%
validating the model accuracy. A large part of the dataset was used to train the model to achieve
higher accuracy and only a small sample was used to validate.
E. Ethical Considerations
Issues such as children's privacy, data protection, accessibility, and rights were considered by
ensuring that the data collected from the hospitals were only viewed by the specialists concerned.
Also, in the creation of the model, only the medics were able to view the data on the frontend
5. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
5
screen. We also obtained permission from relevant local authorities and bodies to handle the data
such as NACOSTI, county health services and the Ministry of education in Muranga, Kenya.
4. IMPLEMENTATION
A. Factors Needed to Identify Children Emergency Cases
Children show a specific range of symptoms to indicate a need for urgent medication. These
symptoms are detected by the use of IoT - based gadgets since it is not easy to measure them
accurately using standard equipment and also due to age. They include blood pressure, heart rate,
body temperature, respiratory rate, and oxygen concentration.
Heart Rate: The heart rate indicates the number of times the heart beats per minute[7]. The child
heart rate values are indicated in the heart rate table [8].
Body Temperature:
Body temperature in children is considered as one of the most contributing factors to medical
consultation in children and referred to fever as a symptom that contributes up to 25% as to why
consultation is crucial for children. [9]. From the research temperature can be as low as 360C
when a child is asleep to 37.80C when the child is active, however for clinical and research
purposes, fever is defined as 380c or higher. The most considered value for normal temperature
for children is 36.5-37.50C.
Blood Pressure: For children, blood pressure value depends on age. Children from birth to one
month have a blood pressure value of 67 to 84 systolic blood pressure over 31 to 45 diastolic
[10]. Children from one month to twelve months have a blood pressure of 72 to 104 systolic over
37 to 56 diastolic. When a child turns a year old, their blood pressure tends to progress towards
adult values. For example, 1 to 2 years child has blood pressure values changes to systolic 86 to
106, diastolic 42 to 63, a child aged 3 to 5 has a blood pressure of systolic 89 to 112, diastolic 46
to 72, a child aged 6 to 11 years, have a blood pressure of systolic 97 to 120, diastolic 57 to 80.
Twelve years and above have the same blood pressure as adults because their heart and breathing
muscles have developed to almost the level of adult implying that their blood pressure is systolic
110 to 131, diastolic 64 to 83
Oxygen levels: It is the amount of oxygen circulating in the blood. From the pediatric chart, the
value ranges from >90% to 100%
B. Health IOT - Based Gadget for Monitoring Children Health Cases.
Pulse Oximeter:It is a device used to measure the oxygen level of the blood. It checks on how
well oxygen is being sent to parts of your body furthest from your heart, such as the arms and
legs.
Blood Pressure and Heart Rate Sensor: It can be explained as an IoT gadget, used to indicate the
pressure of the blood. It uses a non-invasive method where the piercing is not necessary [11]. It
measures systolic and diastolic, and it also indicates the values of the hate rate.
Temperature sensor: It is an IoT device used to determine the temperature level of a human
being. [13].
6. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
6
C. Model Design
BalenaFin carrier board with Raspberry Pi compute module at its core, is the central device of the
system. It is an industrial design grade, power-efficient, Bluetooth and Wi-Fi data transmission
protocol enabled, and it is suitable for this model.
Both the recorded data and simulated data using python libraries, are separated in a way to clearly
indicate the body temperature, heart rate, blood pressure, and oxygen concentration among
others. The data is saved in a comma separated values file.
A Bluetooth network is designed with a piconet topology. The network has a central device,
attached with a raspberry pi 3 module, and the data assumed to have been collected using
peripheral devices from the hospitals. The central device is powered using jack barrel power
supply type and connectivity is configured for both Bluetooth and Wi-Fi. A data packet Bluetooth
scanning, collection, and saving python3 program is run on the central device.
Advertised data packets in this case the recorded and simulated data, are scanned, collected, and
saved on a .csv file on the central device for backup awaiting transmission to a cloud server. The
data is later sent to an AWS cloud server database via MQTT. It is from here, where the
developed front-facing dash application query data, analyses using machine learning techniques
and visualizes emergency inferences. Figure 1 shows the initial concept design. The following
IoT technologies and devices were used;
1. BalenaFin
BalenaFin is a suitable industrial customized development board designed with the Raspberry Pi
Compute Module 3 and 3+. It acts as a breakout and carrier board. It gives access to internal
firmware (RasbianOs) and wireless communication protocols such as Bluetooth version 4.2 that
comes on board as a radio connectivity protocol. It operates at a frequency of 2.4GHZ, and can
sense nearby Bluetooth devices up to a range of 10m.
It has a robust design for deployment in the field, for instance, in hospitals with suitable
enclosures, and enough computational power for resource processes such as threading, pairing,
connecting, and disconnecting. The board is powered by 6V-24V power sources. In addition, it
has extended GPIO pins for scalability and integration with other pediatric systems. In this work,
we took advantage of the computational resources, Bluetooth, and Wi-Fi wireless data
transmission protocols onboarded.
The dual-band 802.11ac standard, 2.4GHz and also 5GHz Wi-Fi is also on the hardware and can
simultaneously be used when in a place without a wired 10/100 Ethernet connection to send and
receive data.
2. Sensor’s devices and simulated data
Smart bands at times referred to as bracelets are modern generic wrist-worn electronic gadgets.
They are mostly customized for health reference and sport activity monitoring. Initially, the
devices were used as pedometers. However, the latest advancements have made the device
applications increase significantly since 2012 (e.g in the health sector). They are cheaper and
meet functionality, standard hardware, and software requirements. They can be bought off the
shelf at a cost of less than Ksh 7000. Most of them are not accurate and need configuration and
some information from the user such as age, weight, and height among others.
7. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
7
Accurate smart bracelets measure heart rate, blood pressure, oxygen levels, and body temperature
when worn on the wrist. They have temperature, optical, ECG, photoelectric, and vibration
sensors that can provide valuable information about a child. It is worn with a grip on the wrist for
accurate results since the system is non-intrusive and can be affected by weather actors and
surrounding environments.
Normally the bands have specific android applications to pair to the peripheral device and collect
data. They have authentication keys that have expiry sessions per user.
3. Cloud Server
Data storage, data analysis, and serving the front-facing application are done on Amazon Web
Services (AWS) ec2 cloud server. It is a t2-micro instance with Linux operating system. The data
sent from the microcontroller is received in a database installed on the server. Also, the dash
application developed was deployed on the instance. It has 8 vCPUs, and 64 GB of hard disc,
providing enough memory to do basic computation and data storage.
4. Software
Development of the microcontroller firmware and algorithms was done in the python3
programming language. The Bluetooth data collection and transmission programs were also
developed in python3 with the use of Bluetooth and Wi-Fi libraries and packages that help in
channeling.
For data analysis and visualization, the Plotly Dash application was used since it is a productive
python framework for building web analytic applications and has various data representation
methods and charts. It was developed on top of Flask, React.js, and Plotly.js, which are ideal for
building data visualization applications, with highly custom user interfaces in python. It was
suited for data-related work in python. Data was queried from the database analyzed and
visualized on the application.
5. Data transmission protocols
Data transmission protocols are set standards and sets of rules that allow computers and systems
to exchange data. Also, they are responsible for how they interpret and format the data. Data
transmission protocols are different depending on the need, application, and physical factors. It
defines the packet structure and control commands that manage the communication session, for
instance, Bluetooth wireless, IP(TC/IP), 802.11 wireless Wi-Fi, and ATM. Any application can
employ one or more of these data transmission protocols. In this work, Wi-Fi, Ethernet and also
Bluetooth were used. Ethernet was used for debugging, interfacing as well as sharing the internet
with the central device. Bluetooth was used as an assumption that the recorded and simulated
data, were transmitted to the central device using it
6. Plotly Dash
A dash application is a data analytical app purposely developed for this work to visualize and
persist data to the pediatrician. It was developed on top of the flask, plotly.js, react.js framework,
and python programming language. The application visualizes real-time data streams and handles
real-time classification. In addition, data can be back-traced to view historical records and
classify specific subsets of the data.
8. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
8
Figure 1: Initial conceptual diagram
The central device, simulated and recorded data interoperability
The operating system was installed on the compute module, a Raspbian Os. Wi-Fi name and
password are configured to connect the device to the internet. The work of the central device is to
act as a client from a client-server perspective by scanning and collecting simulated data and
recorded advertised by python libraries and sensors gargets respectively. MAC addresses
representing sensor garget are used whenever communication is needed. BalenaFin is powered
with the barrel jack power supply and connected on Ethernet LAN cable to the computer via
Secure Shell (SSH) for debugging and programming.
Parameter Simulation, Data Collection, and Transmission to AWS
A coding program to simulate data from peripheral devices was developed to generate and send
data to the AWS cloud server for saving. The parameter ranges were selected carefully according
to Murang’a Provincial Hospital and World Health Organization (WHO) standards for children’s
health for pediatric use.
The data was published to a health_channel topic and the server-side program got the data from
the central device remotely. At the same time, the data is saved on the central device on a .csv file
as shown below.
On the AWS IoT Core, the subscription program subscribes to the health_channel and saves the
data to the influx time-series database. Timestamps for the recorded data are also recorded. The
data saved in the influx database is as shown in figure 2.
Figure 2: Simulated data saved in influxdb
9. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
9
Data collected were analyzed to uncover insights. A Random Forest classifier was trained using
labeled data collected from the hospital records of about 820 records. Labeling entailed working
closely with a pediatrician to uncover the emergency state based on the 6 parameters, namely,
age, body temperature, blood pressure, heart rate, and oxygen level. 72 data points saved on a
.csv file were used for the machine learning process.
There are three classes a child is classified into based on their vital body parameters. Important
Sklearn modules are imported and data loaded to pandas data frame tables using pandas to create
a data set for machine learning. The data is inspected and cleaned. Independent and dependent
variables are declared using NumPy and later split into training and testing sets in the ratio of 3:1.
Feature scaling is later done and the data fit the training set. The model is tested using the testing
data set and the classifier feature importance analyzed as shown in Figure 3 to know the
contribution and essence of each parameter in the training process.
Figure 3: Feature importance
Dash Application
The glance view of all parameters on the dash application is as shown in Figure 4 where real-time
data per child is visualized. Figure 5 shows the emergency classifications and top 10 latest
children with their respective data records using the simulated data.
Figure 4: Parameter values visualization per child
10. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
10
Figure 5: Plotly dash web application processing and visualizing data with emergency
classes as inferences.
The Dash application ran in near real-time with auto-refresh. Any new data saved in the database
is analyzed in real-time and classified as either emergency (class 0), no emergency (class 1), and
moderate emergency (class 2). The children's IDs alongside their emergency classes are tabulated
on a table for medics to plan the emergency cases. The trained model used Body temperature,
oxygen concentration, heart rate, age, systole, and diastole as features. The three classes represent
the emergency levels.
Top to latest children patients attending at that instance is displayed in real-time with
functionality to retrieve historical children data. Body temperature and heart rate were the most
essential features as seen in the feature importance score. The application is responsive on all
platforms including mobile phones.
5. RESULTS
After the analysis of the data collected from the hospital records, it indicated that there were36
emergency cases, 21 no emergency cases, and 15 moderate cases. The above analysis was done
with the assistance of medics, wheretemperature was given the first priory, followed by oxygen
levels and heartrate, and lastly the blood pressure. Blood pressure was given the least importance
in the analysis because, rarely do children suffer from blood pressure related conditions.
In relation to both expert views and pediatric chart values, the table 2 below, indicates that the
model displayed the following number of records after it was tested with the testing data from the
hospitals.
Table 2: results of the model after using the testing data
Emergency
cases
No. of records according to Expert Judgement /
pediatric chart
36
No. of records displayed by the model 34
Moderate cases No. of records according to Expert Judgement /
pediatric chart
15
No. of records displayed by the model 17
Non-
emergency
No. of records according to Expert Judgement /
pediatric chart
21
No. of records displayed by the model 21
11. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
11
The confusion matrix in table 3 below shows the performance of the machine learning algorithm,
its accuracy value being 0.968609865470852, which is 0.97 in two decimal places, or 97%
accuracy level
Table 3: Confusion matrix for the model
0.968609865470852
Accuracy 0.97 223
Macro avg 0.96 0.96 0.96 223
Weighted avg 0.97 0.97 0.97 223
Predicted emergency status EMERGENCY MODERATE NON EMERGENCY
Actual Emergency Status
EMERGENCY 46 4 0
MODERATE 1 46 1
NON EMERGENCY 0 1 124
The trained algorithm was saved and used in a dash application used to classify the children's
emergency status.
6. DISCUSSION
In a collection of 72 records for testing the model, the model was in a position to produce 100%
accuracy, in displaying the exact records of moderate status children, which is a total of 21 out of
21 records, 94% accuracy in displaying the exact records of emergencystatus children, which is a
total of 34 out of 36 records, and it was able to display the exact records of moderate data that is
15 out of 15 records, though the two emergency status records were classified under moderate.
This can be improved by increasing the number of datasets when training the model and would
result into a more reliable model to assist in pediatric section. This is mainly for arranging the
pediatric children whose emergency status, cannot be viewed physically.
Several machine learning algorithms such as SVM, Decision tress and random forest classifiers
were used to determine the best to be used in the model implementation, but the most effective
one, was the random forest classifier since it was able to deal with vitals that do not have a big
feature importance in the classification of children such as the blood pressure
7. CONCLUSION AND FUTURE WORK
The model had a 97% accuracy level, after it was tested with 72 records from a hospital where
out of 21 non-emergency records, it displayed all the 21 records, out of 36 emergency records, it
displayed 34 records and out of 15 moderate, it added two emergency records to the group.
To further this work, more data should be used to further train the model, and raise the accuracy
to 100%. Also, Exploration of Bluetooth range and other architecture should be done to open new
ways of covering other age groups and utilize other body parameters. In addition, the
implementation of an alert system on this work is vital to alert pediatricians when attending to
12. Advanced Medical Sciences: An International Journal (AMS) Vol 8, No.1/2/3, August 2021
12
multiple patients. Hence future work should focus on alert systems. Time spent with each patient
can also be explored to unfold the quality of service intelligence from the data collected.
REFERENCES
[1] P. McCafferty, “Implementing Article 12 of the United Nations Convention on the Rights of the
Child in Child Protection Decision-Making: a Critical Analysis of the Challenges and Opportunities
for Social Work”, Jun. 09, 2021.
[2] P. Svedberg, S. Arvidsson, I. Larsson, I.-M. Carlsson, and J. M. Nygren, “Barriers and Enablers
Affecting Successful Implementation of the Electronic Health Service Sisom: Multicenter Study of
Child Participation in Pediatric Care,” J. Med. Internet Res., vol. 21, no. 11, p. e14271, Nov. 2019.
[3] W. Jin and D. H. Kim, “Design and Implementation of e-Health System Based on Semantic Sensor
Network Using IETF YANG,” Sensors, vol. 18, no. 2, Feb. 2018, DOI: 10.3390/s18020629.
[4] A. Kakkar and A. Garg, “Pervasive Health Monitoring of Special Child using IoT and Cloud
Technologies,” 2019 International Conference on Intelligent Computing and Control Systems
(ICCS). 2019, DOI: 10.1109/iccs45141.2019.9065375.
[5] P. Jangra and M. Gupta, “A Design of Real-Time Multilayered Smart Healthcare Monitoring
Framework Using IoT,” 2018 International Conference on Intelligent and Advanced System (ICIAS).
2018, DOI: 10.1109/icias.2018.8540606.
[6] N. Petrellis, M. Birbas, and F. Gioulekas, “On the Design of Low-Cost IoT Sensor Node for e-Health
Environments,” Electronics, vol. 8, no. 2. p. 178, 2019, DOI: 10.3390/electronics8020178.
[7] S. Fleming et al., “Normal ranges of heart rate and respiratory rate in children from birth to 18 years
of age: a systematic review of observational studies,” Lancet, vol. 377, no. 9770, pp. 1011–1018,
Mar. 2011.
[8] C. Novak, K. Forbes, and P. Gill, “PedsCases: A Learning Module for the Approach to Pediatric
Anemia,” MedEdPORTAL, vol. 12, no. 1. 2016, DOI: 10.15766/mep_2374-8265.10319.
[9] E. Barbi, P. Marzuillo, E. Neri, S. Naviglio, and B. S. Krauss, “Fever in Children: Pearls and
Pitfalls,” Children, vol. 4, no. 9, Sep. 2017, DOI: 10.3390/children4090081.
[10] J. T. Flynn et al., “Clinical Practice Guideline for Screening and Management of High Blood Pressure
in Children and Adolescents,” Pediatrics, vol. 140, no. 3. p. e20171904, 2017, DOI:
10.1542/peds.2017-1904.
[11] M. Pasha and S. M. W. Shah, “Framework for E-Health Systems in IoT-Based Environments,”
Wireless Communications and Mobile Computing, vol. 2018. pp. 1–11, 2018, DOI:
10.1155/2018/6183732.
[12] M. Sharma, S. Kacker, and M. Sharma, “A Brief Introduction and Review on Galvanic Skin
Response,” International Journal of Medical Research Professionals, vol. 2, no. 6. 2016, DOI:
10.21276/ijmrp.2016.2.6.003.
[13] Z. Alansari, S. Soomro, M. R. Belgaum, and S. Shamshirband, “The Rise of Internet of Things (IoT)
in Big Healthcare Data: Review and Open Research Issues,” Advances in Intelligent Systems and
Computing. pp. 675–685, 2018, DOI: 10.1007/978-981-10-6875-1_66.