Edge Analytics With Machine Learning Technique for Medical IoT Applications

Mapping Intimacies ◽

10.4018/978-1-7998-9132-1.ch008 ◽

2022 ◽

pp. 131-142

Author(s):

Jeya Mala D. ◽

Pradeep Reynold A.

Keyword(s):

Machine Learning ◽

Decision Making ◽

Data Analytics ◽

Machine Learning Technique ◽

Iot Applications ◽

Wide Range ◽

Learning Technique ◽

Internal Storage ◽

Iot Devices

Edge analytics are tools and algorithms that are deployed in the internal storage of IoT devices or IoT gateways that collect, process, and analyze the data locally rather than transmitting it to the cloud for analysis. Edge analytics is applied in a wide range of applications in which immediate decision making is required. In the case of general IoT data analytics on the cloud, the data need to be collected from the IoT devices and to be sent to the cloud for further processing and decision making. In life-critical applications such as healthcare, the time taken to send the data to the cloud and then getting back the processed data to take decisions will not be acceptable. Hence, in these kinds of MIoT applications, it is essential to have analytics to be done on the edge in order to avoid such delays. Hence, this chapter is providing an abstract view on the application of machine learning in MIoT so that the data analytics provides fruitful results to the stakeholders.

Download Full-text

Evaluation of the COVID-19 Era by Using Machine Learning and Interpretation of Confidential Dataset

Electronics ◽

10.3390/electronics10232910 ◽

2021 ◽

Vol 10 (23) ◽

pp. 2910

Author(s):

Andreas Andreou ◽

Constandinos X. Mavromoustakis ◽

George Mastorakis ◽

Jordi Mongay Batalla ◽

Evangelos Pallis

Keyword(s):

Machine Learning ◽

Real Time ◽

Research Study ◽

Nonlinear Least Squares ◽

Data Driven ◽

Machine Learning Technique ◽

Marquardt Algorithm ◽

Learning Technique ◽

Iot Devices ◽

Algorithmic Techniques

Various research approaches to COVID-19 are currently being developed by machine learning (ML) techniques and edge computing, either in the sense of identifying virus molecules or in anticipating the risk analysis of the spread of COVID-19. Consequently, these orientations are elaborating datasets that derive either from WHO, through the respective website and research portals, or from data generated in real-time from the healthcare system. The implementation of data analysis, modelling and prediction processing is performed through multiple algorithmic techniques. The lack of these techniques to generate predictions with accuracy motivates us to proceed with this research study, which elaborates an existing machine learning technique and achieves valuable forecasts by modification. More specifically, this study modifies the Levenberg–Marquardt algorithm, which is commonly beneficial for approaching solutions to nonlinear least squares problems, endorses the acquisition of data driven from IoT devices and analyses these data via cloud computing to generate foresight about the progress of the outbreak in real-time environments. Hence, we enhance the optimization of the trend line that interprets these data. Therefore, we introduce this framework in conjunction with a novel encryption process that we are proposing for the datasets and the implementation of mortality predictions.

Download Full-text

Effectiveness of a Hybrid Deep Learning Model Integrated with a Hybrid Parameterisation Model in Decision-Making Analysis

Knowledge Innovation Through Intelligent Software Methodologies, Tools and Techniques - Frontiers in Artificial Intelligence and Applications ◽

10.3233/faia200551 ◽

2020 ◽

Author(s):

Masurah Mohamad ◽

Ali Selamat

Keyword(s):

Neural Network ◽

Machine Learning ◽

Decision Making ◽

Deep Learning ◽

Missing Data ◽

Machine Learning Technique ◽

Processing Times ◽

Learning Technique ◽

Neural Network Algorithm ◽

Deep Learning Model

Deep learning has recently gained the attention of many researchers in various fields. A new and emerging machine learning technique, it is derived from a neural network algorithm capable of analysing unstructured datasets without supervision. This study compared the effectiveness of the deep learning (DL) model vs. a hybrid deep learning (HDL) model integrated with a hybrid parameterisation model in handling complex and missing medical datasets as well as their performance in increasing classification. The results showed that 1) the DL model performed better on its own, 2) DL was able to analyse complex medical datasets even with missing data values, and 3) HDL performed well as well and had faster processing times since it was integrated with a hybrid parameterisation model.

Download Full-text

MicroServices Suite for Smart City Applications

Sensors ◽

10.3390/s19214798 ◽

2019 ◽

Vol 19 (21) ◽

pp. 4798 ◽

Cited By ~ 5

Author(s):

Claudio Badii ◽

Pierfrancesco Bellini ◽

Angelo Difino ◽

Paolo Nesi ◽

Gianni Pantaleo ◽

...

Keyword(s):

Smart City ◽

Data Analytics ◽

First Generation ◽

Smart Cities ◽

Data Gathering ◽

Iot Applications ◽

Wide Range ◽

Data Flows ◽

Iot Devices ◽

The Internet Of Things

Smart Cities are approaching the Internet of Things (IoT) World. Most of the first-generation Smart City solutions are based on Extract Transform Load (ETL); processes and languages that mainly support pull protocols for data gathering. IoT solutions are moving forward to event-driven processes using push protocols. Thus, the concept of IoT applications has turned out to be widespread; but it was initially “implemented” with ETL; rule-based solutions; and finally; with true data flows. In this paper, these aspects are reviewed, highlighting the requirements for smart city IoT applications and in particular, the ones that implement a set of specific MicroServices for IoT Applications in Smart City contexts. Moreover; our experience has allowed us to implement a suite of MicroServices for Node-RED; which has allowed for the creation of a wide range of new IoT applications for smart cities that includes dashboards, IoT Devices, data analytics, discovery, etc., as well as a corresponding Life Cycle. The proposed solution has been validated against a large number of IoT applications, as it can be verified by accessing the https://www.Snap4City.org portal; while only three of them have been described in the paper. In addition, the reported solution assessment has been carried out by a number of smart city experts. The work has been developed in the framework of the Select4Cities PCP (PreCommercial Procurement), funded by the European Commission as Snap4City platform.

Download Full-text

What Should Investors Care About? Mutual Fund Ratings by Analysts vs. Machine Learning Technique

SSRN Electronic Journal ◽

10.2139/ssrn.3702749 ◽

2020 ◽

Author(s):

Si Cheng ◽

Ruichang Lu ◽

Xiaojun Zhang

Keyword(s):

Machine Learning ◽

Mutual Fund ◽

Machine Learning Technique ◽

Learning Technique

Download Full-text

The Development of a Quantitative Precipitation Forecast Correction Technique Based on Machine Learning for Hydrological Applications

Atmosphere ◽

10.3390/atmos11010111 ◽

2020 ◽

Vol 11 (1) ◽

pp. 111 ◽

Cited By ~ 2

Author(s):

Chul-Min Ko ◽

Yeong Yun Jeong ◽

Young-Mi Lee ◽

Byung-Sik Kim

Keyword(s):

Machine Learning ◽

Heavy Rainfall ◽

Extreme Rainfall ◽

Machine Learning Techniques ◽

Precipitation Forecast ◽

Machine Learning Technique ◽

Rainfall Forecast ◽

Quantitative Precipitation Forecast ◽

Correction Technique ◽

Learning Technique

This study aimed to enhance the accuracy of extreme rainfall forecast, using a machine learning technique for forecasting hydrological impact. In this study, machine learning with XGBoost technique was applied for correcting the quantitative precipitation forecast (QPF) provided by the Korea Meteorological Administration (KMA) to develop a hydrological quantitative precipitation forecast (HQPF) for flood inundation modeling. The performance of machine learning techniques for HQPF production was evaluated with a focus on two cases: one for heavy rainfall events in Seoul and the other for heavy rainfall accompanied by Typhoon Kong-rey (1825). This study calculated the well-known statistical metrics to compare the error derived from QPF-based rainfall and HQPF-based rainfall against the observational data from the four sites. For the heavy rainfall case in Seoul, the mean absolute errors (MAE) of the four sites, i.e., Nowon, Jungnang, Dobong, and Gangnam, were 18.6 mm/3 h, 19.4 mm/3 h, 48.7 mm/3 h, and 19.1 mm/3 h for QPF and 13.6 mm/3 h, 14.2 mm/3 h, 33.3 mm/3 h, and 12.0 mm/3 h for HQPF, respectively. These results clearly indicate that the machine learning technique is able to improve the forecasting performance for localized rainfall. In addition, the HQPF-based rainfall shows better performance in capturing the peak rainfall amount and spatial pattern. Therefore, it is considered that the HQPF can be helpful to improve the accuracy of intense rainfall forecast, which is subsequently beneficial for forecasting floods and their hydrological impacts.

Download Full-text