Practical Application Using the Clustering Algorithm

This chapter will survey the clustering algorithm that is unsupervised learning among data mining and machine learning techniques. The most popular clustering algorithm is the K-means clustering algorithm; It can represent a cluster of data. The K-means clustering algorithm is an essential factor in finding an appropriate K value for distributing the training dataset. It is common to find this value experimentally. Also, it can use the elbow method, which is a heuristic approach used in determining the number of clusters. One of the present clusterings applied studies is the particulate matter concentration clustering algorithm for particulate matter distribution estimation. This algorithm divides the area of the center that the fine dust distribution using K-means clustering. It then finds the coordinates of the optimal point according to the distribution of the particulate matter values. The training dataset is the latitude, longitude of the observatory, and PM10 value obtained from the AirKorea website provided by the Korea Environment Corporation. This study performed the K-means clustering algorithm to cluster feature datasets. Furthermore, it showed an experiment on the K values to represent the cluster better. It performed clustering by changing K values from 10 to 23. Then it generated 16 labels divided into 16 cities in Korea and compared them to the clustering result. Visualizing them on the actual map confirmed whether the clusters of each city were evenly bound. Moreover, it figures out the cluster center to find the observatory location representing particulate matter distribution.

Development of a Mobile Edge Device and an Information System to Analyze Particulate Matter Distribution as a mHealth Service

Particulate matter is an air pollutant consistent of very small particles that are suspended in the air. Shortterm exposure may result in respiratory symptoms such as shortness of breath, throat and nose irritation, chest tightness, coughing, in addition to eye irritation. The research aimes at creating a prototype of a mobile sensor system that can be used to analyze the particulate matter pollution on a location and on a time scale to measure the degree of pollution in the city. The engineering requirement to construct the edge device includes temperature (humidity) sensor, particulate matter sensor, GPS module, and an LCD for displaying the current sensor values. The health data of the mobile edge device can be analyzed through a developed analytics system, which allows the user to identify and avoid pollution sources. For the implementation of the web service the framework ReactJS, NodeJS with Express.js, and the database MongoDB are being used. The mHelath service is evaluated through field trials: New Year’s Eve, various source identifications, and a demonstration through a journey from the subway station to the university. The paper outlines a mHealth service, which can collect data records of the surroundings and analyze the particulate matter in an information system to visualize risk locations of a user.

Temporal and spatial variability of the suspended particulate matter in the Gdansk Deep and Eastern Gotland Basin

The work was carried out in the south-eastern part of the Baltic Sea on the meridional section along the Russian–Polish border during 2015–2018 using the CTD-sounding. The suspended particulate matter samples were taken with the use of ultrafiltration of sea water (0.4 micron filters). The research was focused on identifying the temporal and spatial variability of suspended particulate matter distribution after a series of inflows of the North Sea waters in 2014–2016. The vertical structure of the suspended particulate matter distribution in the south-eastern Baltic, both on a seasonal and interannual scale, contains the main features common for all marine basins, namely increased concentrations of SPM at the sea surface and bottom and an intermediate layer of minimum concentrations located at a depth of 50–70 m. Seasonal fluctuations in the SPM concentration are very significant and are mainly due to the seasonal variation of bioproduction in the surface layer of the sea and the flow of rivers. The confirmation of the barrier role of density boundaries (thermocline and halocline) in sedimentation and geochemical processes has not been obtained.