International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Machine learning has been used in many disciplines to reveal important patterns in data. One of the research disciplines that benefits from using these methods is eco-informatics. This branch of applied computer science to solve environmental problems uses computer algorithms to discover the impact of the environmental stress factors on the organisms’ abundance. Decision tree type of machine learning methods are particularly interesting for the computer scientists as well as ecologists, because they provide very easy interpretable structure without any practical knowledge in mathematics or the inner working of the algorithm. These methods do not rely only on classical sets, but many of them are using fuzzy set theory to overcome some problems like overfitting, robustness to data change and improved prediction accuracy. In this direction, this paper aims to discover the influence of one particular environmental stress factor (Saturated Oxygen) on real measured data containing information about the diatoms’ abundance in Lake Prespa, Macedonia, using weighted pattern tree (WPT) algorithm. WPT is a decision tree method variant that combines fuzzy set theory concepts, like similarity metrics, fuzzy membership functions and aggregation operators, to achieve better prediction accuracy, improve interpretability and increase the resistance to overfitting compared to the classical decision trees. In this study, we use Algebraic operators for aggregation. One WPT model is presented in this paper to relate the saturated oxygen parameter with the diatoms’ abundance and reveal which diatoms can be used to indicate certain water quality class (WQC). The obtained results are verified with the existing knowledge found in literature.

Protein classification is among the main themes in bioinformatics, for the reason that it helps understand the protein molecules. By classifying the protein structures, the evolutionary relations between them can be discovered. The knowledge for protein structures and the functions that they might have could be used to regulate the processes in organisms, which is made by developing medications for different diseases. In the literature, plethora of methods for protein classification are offered, including manual, automatic or semiautomatic methods. The manual methods are considered as precise, but their main problem is that they are time consuming, hence by using them a large number of protein structures stay uncategorized. Therefore, the researchers intensively work on developing methods that would afford classification of protein structures in automatic way with acceptable precision. In this paper, we propose an approach for classifying protein structures. Our protein voxel-based descriptor is used to describe the features of protein structures. For classification of unclassified protein structures, we use a k nearest neighbors classifier based on fuzzy logic. For evaluation, we use knowledge for the classification of protein structures in the SCOP database. We provide some results from the evaluation of our approach. The results show that the proposed approach provide accurate classification of protein structures with reasonable speed.

Fish like many living organisms have specific tolerant range of various environmental parameters, thus fish farming of specific types of fish species requires certain conditions that have to be reached. Moreover, the people that work in the fish farming ponds have to be engaged in all day activities to maintain the living fish habitat. Therefore, monitoring and taking actions to maintain the habitat’s sustainable environment for certain fish species inside of fishing ponds over distributed machine to machine communication, which will shorten the time needed for some basic actions, is the main motivation for this paper. In this paper we present an upgrade on a functional Internet of Things (IoT) system for monitoring fish farming ponds. The IoT system consists of various sensors that measure important factors of the water quality like temperature, light intensity or water level, as well as small board computer that processes the data and sends sound and visual notifications to the fish farming manager. The current system lacks the ability to process the data to the end-user via web or mobile platform. Due to remote distance of the fish farming ponds and their location dependence of clean fresh water, one solution of this problem is using expansion module like Wivity modem to enable the end users in real time to monitor and control certain aspects of the fish farming pond IoT system. Wivity modem allows user to communicate to the IoT system via WiFi connection, cellular, LoRaWAN or satellite communication; all in one product. Later on, this module can be integrated with IoT platforms including Japser, Microsoft Azure or Amazon Web Services. For future work, we plan to expand not only the applicable services on different platforms, but also add more control modules and sensors to the existing IoT system for specific fish species.

The research covers the usage of the random numbers in Monte Carlo simulations for air pollution models. Two new random number generators are developed; their strengths are compared with the existing random number generators. The results in this paper showed that the two newly developed random number generators achieved better results on a basis of failed test, however it extended the time for generating random numbers. In future we plan to use the newly developed random generators for filling the missing values in the measurements.

Ozone is health-hazardous air pollutant and his level in the living environment is very important to be tracked and understand. This specific gas in nowadays occurs as byproduct of certain human activities, especially with car pollution and naturally due to increased temperature. Therefore, it is important to understand the relationship between this variable. The focus of this paper is to model this relationship, with data collected for period of 3 months in 2014 and 2015(summer period). According to the models obtained with machine learning methods, high level concentrations of ozone was found if temperature of the air is higher than 30.15^oC and concentrations of NO₂ are lower than 16.93 mg/m³(in 2013). Encourage by this model, in this paper we go further and extend our research to include more data (from 2014 and 2015) and different methods to find other influencing factors that contributes to high concentration of ozone.

Noise pollution modelling can be used to provide information about growing noise pollution from the urban traffic. Various methods have been developed that aim at minimizing the noise pollution and improving the environment. Geographic Information System (GIS) can be adapted to gather, analyse and present noise information. The results in this paper demonstrated that most of regions surrounding the main streets are suffering from the noise pollution. As a main contribution of this paper, the first this-kind of study for the city of Skopje, practicing GIS capabilities for presenting noise information, we have produced a general picture of the traffic-induced noise pollution on annual level. The assessment showed that the used method in visualization can provide reliable information about noise pollution in any city or urban region. In this paper, we were focused, as a case study, for the city of Skopje.