An AI tracking and delivery system for the distribution of maternity kits : case study: the health sector – Nigeria
Authors
Date
2021Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Artificial intelligence is being used in the health sector of developed countries and it has improved the lives of humans greatly such as detecting cancers and different types of brain tumours and diagnosing cardiovascular diseases within a short period. AI has been used to make decisions for humans based on some observed symptoms identified in the human body. AI is also used in speech technology for healthcare to process human speech in order to identify languages, gender and age and also for the purpose of detecting some physical and mental disease which have been known to cause changes in human speech. For example, the Automatic Speech Recognition (ASR) technology has been used in the healthcare sector to fix speech and hearing impairments of patients. AI is also used to study the emotions of humans and it has been used to handle complex situations difficult for health specialists, such as tracking and detecting patients with corona virus through an application and the development of vaccines.
On the other hand, developing countries are still struggling to keep up with the use of AI in their health sectors. Embedding AI in improving the services provided by the health sector in Nigeria is a long-overdue transformation. Most especially in the maternity section. Pregnant women ought to be given proper health care attention irrespective of whether they live in the urban area, metropolitan area, semi-rural area, or rural area. It is based on this that this research was carried to compare the present distribution system of maternity kits to pregnant women and a designed proposed model.
This research work focused on identifying the issues related to the distribution of maternity kits in Nigeria and the design and development of an AI system that would help to ensure the effective distribution of maternity kits to pregnant women. Two types of questionnaires were administered. The use of online questionnaires and paper-based questionnaires enabled participants of this study to state the issues they face as regards the collection of maternity kits in government hospitals. It was discovered that many of the participants believed that services in the health sector of Nigeria need to be improved. Based on the survey carried out, about 50% of the participants were willing to share their addresses to be used for maternity kit distribution and about a quarter of the participants were willing to share their photos and fingerprints to be used in the AI system for maternity kit distribution. Participants' opinions varied in the information they were willing to share with the government hospitals and Non-governmental Organisations (NGOs) as regards the use of text, voice, and fingerprints for AI purposes.
In the design and development of the system, the pregnant woman’s due date was predicted by the Machine Leaning Algorithm. Photos were detected to determine if she has been registered in the system. Google Map API was used to navigate to her location, and Twilio messaging API was used to send her messages to inform her of the maternity kit distribution date.
In the development of a proposed model, AI for facial detection was used. It was discovered that the facial recognition model was not 100% efficient in identifying people of the black race especially people from the same family because they have similar facial features.
Several strategies are recommended for the full functioning of the proposed model. Firstly, it is important to note that only one researcher carried out this design hence some other technical skills which the researcher did not possess is required for full deployment and implementation of the model. Secondly, most of the APIs used were the free versions, for a more efficient model, paid versions may be required.
...
Keywords
Metadata
Show full item recordCollections
- Pro gradu -tutkielmat [29678]
Related items
Showing items with similar title or keywords.
-
Practices and Infrastructures for Machine Learning Systems : An Interview Study in Finnish Organizations
Muiruri, Dennis; Lwakatare, Lucy Ellen; Nurminen, Jukka K.; Mikkonen, Tommi (Institute of Electrical and Electronics Engineers (IEEE), 2022)Using interviews, we investigated the practices and toolchains for machine learning (ML)-enabled systems from 16 organizations across various domains in Finland. We observed some well-established artificial intelligence ... -
Adversarial Attack’s Impact on Machine Learning Model in Cyber-Physical Systems
Vähäkainu, Petri; Lehto, Martti; Kariluoto, Antti (Peregrine Technical Solutions, 2020)Deficiency of correctly implemented and robust defence leaves Internet of Things devices vulnerable to cyber threats, such as adversarial attacks. A perpetrator can utilize adversarial examples when attacking Machine ... -
LiquidAI : Towards an Isomorphic AI/ML System Architecture for the Cloud-Edge Continuum
Systä, Kari; Pautasso, Cesare; Taivalsaari, Antero; Mikkonen, Tommi (Springer Nature Switzerland, 2023)A typical Internet of Things (IoT) system consists of a large number of different subsystems and devices, including sensors and actuators, gateways that connect them to the Internet, cloud services, end-user applications ... -
Strategic cyber threat intelligence : Building the situational picture with emerging technologies
Voutilainen, Janne; Kari, Martti (Academic Conferences International, 2020)In 2019, e-criminals adopted new tactics to demand enormous ransoms from large organizations by using ransomware, a phenomenon known as “big game hunting.” Big game hunting is an excellent example of a sophisticated and ... -
On Attacking Future 5G Networks with Adversarial Examples : Survey
Zolotukhin, Mikhail; Zhang, Di; Hämäläinen, Timo; Miraghaei, Parsa (MDPI AG, 2023)The introduction of 5G technology along with the exponential growth in connected devices is expected to cause a challenge for the efficient and reliable network resource allocation. Network providers are now required to ...