MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext Editorial: Human-in-the-loop cyber-physical systems

Yau KA

Front Neurorobot, 2022;16:1073881.
PMID: 36451678 DOI: 10.3389/fnbot.2022.1073881
Fulltext A Distributed Testbed for 5G Scenarios: An Experimental Study

Chamran MK, Yau KA, Noor RMD, Wong R

Sensors (Basel), 2019 Dec 19;20(1).
PMID: 31861500 DOI: 10.3390/s20010018

This paper demonstrates the use of Universal Software Radio Peripheral (USRP), together with Raspberry Pi3 B+ (RP3) as the brain (or the decision making engine), to develop a distributed wireless network in which nodes can communicate with other nodes independently and make decision autonomously. In other words, each USRP node (i.e., sensor) is embedded with separate processing units (i.e., RP3), which has not been investigated in the literature, so that each node can make independent decisions in a distributed manner. The proposed testbed in this paper is compared with the traditional distributed testbed, which has been widely used in the literature. In the traditional distributed testbed, there is a single processing unit (i.e., a personal computer) that makes decisions in a centralized manner, and each node (i.e., USRP) is connected to the processing unit via a switch. The single processing unit exchanges control messages with nodes via the switch, while the nodes exchange data packets among themselves using a wireless medium in a distributed manner. The main disadvantage of the traditional testbed is that, despite the network being distributed in nature, decisions are made in a centralized manner. Hence, the response delay of the control message exchange is always neglected. The use of such testbed is mainly due to the limited hardware and monetary cost to acquire a separate processing unit for each node. The experiment in our testbed has shown the increase of end-to-end delay and decrease of packet delivery ratio due to software and hardware delays. The observed multihop transmission is performed using device-to-device (D2D) communication, which has been enabled in 5G. Therefore, nodes can either communicate with other nodes via: (a) a direct communication with the base station at the macrocell, which helps to improve network performance; or (b) D2D that improve spectrum efficiency, whereby traffic is offloaded from macrocell to small cells. Our testbed is the first of its kind in this scale, and it uses RP3 as the distributed decision-making engine incorporated into the USRP/GNU radio platform. This work provides an insight to the development of a 5G network.
Fulltext Floating Fog: extending fog computing to vast waters for aerial users

Hassan N, Aazam M, Tahir M, Yau KA

Cluster Comput, 2023;26(1):181-195.
PMID: 35464821 DOI: 10.1007/s10586-022-03567-6

There are thousands of flights carrying millions of passengers each day, having three or more Internet-connected devices with them on average. Usually, onboard devices remain idle for most of the journey (which can be of several hours), therefore, we can tap on their underutilized potential. Although these devices are generally becoming more and more resourceful, for complex services (such as related to machine learning, augmented/virtual reality, smart healthcare, and so on) those devices do not suffice standalone. This makes a case for multi-device resource aggregation such as through femto-cloud. As our first contribution, we present the utility of femto-cloud for aerial users. But for that sake, a reliable and faster Internet is required (to access online services or cloud resources), which is currently not the case with satellite-based Internet. That is the second challenge we try to address in our paper, by presenting an adaptive beamforming-based solution for aerial Internet provisioning. However, on average, most of the flight path is above waters. Given that, we propose that beamforming transceivers can be docked on stationery ships deployed in the vast waters (such as the ocean). Nevertheless, certain services would be delay-sensitive, and accessing their on-ground servers or cloud may not be feasible (in terms of delay). Similarly, certain complex services may require resources in addition to the flight-local femto-cloud. That is the third challenge we try to tackle in this paper, by proposing that the traditional fog computing (which is a cloud-like but localized pool of resources) can also be extended to the waters on the ships harboring beamforming transceivers. We name it Floating Fog. In addition to that, Floating Fog will enable several new services such as live black-box. We also present a cost and bandwidth analysis to highlight the potentials of Floating Fog. Lastly, we identify some challenges to tackle the successful deployment of Floating Fog.
Fulltext Healthcare professionals' perspectives on artificial intelligence (AI)-based mobile applications (apps) for diabetes education and behavioural management

Lim PC, Chong YW, Chie QT, Zainal H, Yau KA, Teoh SH

Digit Health, 2025;11:20552076251329991.
PMID: 40162163 DOI: 10.1177/20552076251329991

BACKGROUND: The global prevalence of diabetes mellitus is escalating rapidly. Similarly in Malaysia, diabetes prevalence among adults rose exponentially. Artificial intelligence (AI) integrated into mobile health applications (apps) presents a promising avenue for enhancing diabetes management through personalized patient education and behaviour modification. However, adoption rates remain low, primarily due to limited awareness and technological challenges, especially among older adults.
OBJECTIVE: This study aimed to explore Malaysian healthcare professionals' (HCPs') perspectives on the use of AI in mobile apps for diabetes education and behavioural management.
METHODS: Qualitative study using semi-structured interviews with 19 HCPs across Malaysia. Interviews were conducted via video conferencing, recorded, transcribed, and analysed using thematic analysis with NVivo 14 software.
RESULTS: Seven key themes emerged: (1) acceptance and trust, (2) impact on patient behaviour, (3) skills and abilities required, (4) problems and obstacles, (5) key features and functions, (6) HCPs' and patients' information needs, and (7) strategies for increasing patient adoption. HCPs expressed positive sentiments towards AI-based apps, highlighting their potential for continuous, personalized education and real-time feedback. However, significant concerns were raised about accessibility for older adults, data privacy, and the apps' ability to modify entrenched behaviours without human intervention.
CONCLUSION: AI-based mobile apps show potential for improving diabetes management, but successful implementation requires addressing challenges. Strategies should focus on developing user-friendly interfaces, providing comprehensive education for patients and providers, and ensuring robust data protection. Future research should quantify the impact on patient outcomes and explore effective integration of human support with AI capabilities.