26 January 2024 in IEEE Access
The advent of the fifth-generation mobile communication technology (5G) era has catalyzed significant advancements in medical diagnosis delivery, primarily driven by the surge in medical data from wearable Internet of Medical Things (IoMT) devices. Nonetheless, the IoMT paradigm grapples with challenges related to data security, privacy, constrained computational capabilities at the edge, and an inadequate architecture for handling traditionally error-prone data. In this context, our research offers: (1) an exhaustive review of large-scale medical data propelled by IoMT, (2) an exploration of the prevailing cloud-edge Artificial Intelligence (AI) framework tailored for IoMT, and (3) an insight into the application of Edge Federated Learning (EFL) in bolstering medical big data analytics to yield secure and superior diagnostic outcomes. We place a particular emphasis on the proliferation of IoMT wearable devices that incessantly stream medical data, either from patients or healthcare institutions, to centralized repositories. Furthermore, we introduce a federated cloud-edge AI blueprint designed to position computational resources proximate to the edge network, facilitating real-time diagnostic feedback to patients. We conclude by delineating prospective research trajectories in enhancing IoMT through AI integration.
1 January 2019 in International journal of electrical and computer engineering systems
Location-based services (LBS) are a significant permissive technology. One of the main components in indoor LBS is the indoor positioning system (IPS). IPS utilizes many existing technologies such as radio frequency, images, acoustic signals, as well as magnetic sensors, thermal sensors, optical sensors, and other sensors that are usually installed in a mobile device. The radio frequency technologies used in IPS are WLAN, Bluetooth, Zig Bee, RFID, frequency modulation, and ultra-wideband. This paper explores studies that have combined WLAN fingerprinting and image processing to build an IPS. The studies on combined WLAN fingerprinting and image processing techniques are divided based on the methods used. The first part explains the studies that have used WLAN fingerprinting to support image positioning. The second part examines works that have used image processing to support WLAN fingerprinting positioning. Then, image processing and WLAN fingerprinting are used in combination to build IPS in the third part. A new concept is proposed at the end for the future development of indoor positioning models based on WLAN fingerprinting and supported by image processing to solve the effect of people presence around users and the user orientation problem.
1 January 2023 in International Journal of Engineering
The development of location-based services requires an increasingly accurate positioning system technology. Research on outdoor positioning systems has achieved satisfactory accuracy and has been commonly used in various location-based services. The research trend is now shifting toward the Indoor Positioning System (IPS). One technique that is widely used in Wi-Fi-based IPS is fingerprinting. The fingerprinting technique on Wi-Fi uses the Received Signal Strength Indicator (RSSI) value. The problem that occurs is that the results of RSSI measurements on smartphones of different brands will produce different RSSI values, also known as device diversity. Device diversity will cause a decrease in system accuracy. This study aims to offer a solution to the problem of device diversity in Wi-Fi IPS based on RSSI Fingerprinting, i.e., to get a minor distance error. The proposed solution is to modify the original database radio map into two new databases: the difference database and the ratio database. The Difference Database Radiomap was able to reduce the average value of distance errors by 24.3% in Meizu and 28% in OPPO. Then, using the Radiomap database ratio, the average value of distance errors could be reduced by 13% in Meizu and 24% in OPPO. From the calculation, Radiomap database ratio can provide solutions to the problem of device diversity for an Indoor Positioning System better than the difference database radiomap if we looked at reduced distance error.
1 January 2024 in International Journal of Engineering
The widespread availability of large language models (LLMs) has encouraged many individuals to explore chatbot development for their business needs. However, creating chatbots for handling sensitive information, like in healthcare, can be challenging. Mistakes made by these bots when extracting information or providing health recommendations can have serious consequences. When developing a chatbot for pharmacy recommendations, it is essential for the bot to effectively extract symptom-related information and other relevant patient data and then offer recommendations for actions or medications based on that information. In this study, we proposed a straightforward and effective approach that combines regular expression templates for information extraction with forward chaining for inference to create a pharmacy recommendation chatbot called SmartFarma. In scenarios like pharmacy recommendations, we will demonstrate that the use of regular expression templates is sufficient and produces better results than some machine learning methods. Additionally, by using regular expressions, SmartFarma can be developed with transparent data handling, allowing experts to trace, monitor, and evaluate its recommendations. This research primarily focuses on the extraction of patient information. Our model, as proposed, achieved an impressive score of 81.54%, outperforming both the Biomedical Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT) models.
8 November 2024 in IEEE Access
Presents corrections to the paper, (Corrections to “A Review on the Application of Internet of Medical Things in Wearable Personal Health Monitoring: A Cloud-Edge Artificial Intelligence Approach”).