The reduction of the population and labour force in rural areas, adverse climate changes, soil pollution and degradation, and reduced soil fertility necessitate new and intensive approaches to and methods of vegetable production. In this study, a new high-tech, small-scale hydroponic system based on the Internet of Things (IoT) for growing leafy vegetables was designed. For the assembly of the high-tech small-scale hydroponic system, low-cost materials and sensors are used, allowing remote monitoring and process automation during the cultivation of leafy vegetables and seedlings. Experimental investigations of the installation were conducted, with lettuce as the grown crop. The environmental and technological parameters of the system were monitored and analysed in order to assess the suitability of the system. The obtained results confirm that the small-scale hydroponic system maintained the set parameters of air temperature, air humidity and pH of the nutrient solution within the optimal limits for growing lettuce. Other parameters, such as temperature and electrical conductivity of the nutrient solution, had small deviations from the required optimal limits. In the initially set experiment, 75% germination of the lettuce seeds was achieved. The main advantages of the proposed hydroponic system are the simplicity of its management and easy installation. Furthermore, it offers the possibility for remote monitoring and control without any high requirements towards the experience of the user with such facilities. The designed and implemented small hydroponic system can help small and medium-sized vegetable growers achieve indoor sustainable farming of leafy vegetables year-round.

The integration of information and communication technologies into agriculture lead to the development of precision agriculture. Nowadays it relies on Internet of Things devices, geospatial data, historical and real-time information, which has the potential to transform farming into smart farming. However the use of Big Data requires significantly different skills and knowledge, compared to what many farmers and agronomists possess, which is an obstacle for their effective use. This study aims to summarize and provide insight into the common methods used for data analysis in a wide variety of agricultural applications. Initially, the basic characteristics and sources of agricultural data are explained. Next, a review of the common data analysis methods (classification, clustering and regressions) is provided, containing information about the data sources used as well as the desired goal of the analysis. At the end of the paper, a summary is given on the applicability of data analysis methods depending on the desired goals.

During the last decades photovoltaic solar energy has continuously increased its share in the electricity mix and has already surpassed 5% globally. Even though photovoltaic (PV) installations are considered to require very little maintenance, their efficient exploitation relies on accounting for certain environmental factors that affect energy generation. One of these factors is the soiling of the PV surface, which could be observed in different forms, such as dust and bird droppings. In this study, visible spectrum data and machine learning algorithms were used for the identification of soiling. A methodology for preprocessing the images is proposed, which puts focus on any soiling of the PV surface. The performance of six classification machine learning algorithms is evaluated and compared—convolutional neural network (CNN), support vector machine (SVM), random forest (RF), k-nearest neighbor (kNN), naïve-Bayes, and decision tree. During the training and validation phase, RF proved to be the best-performing model with an F1 score of 0.935, closely followed by SVM, CNN, and kNN. However, during the testing phase, the trained CNN achieved the highest performance, reaching F1 = 0.913. SVM closely followed it with a score of 0.895, while the other two models returned worse results. Some results from the application of the optimal model after specific weather events are also presented in this study. They confirmed once again that the trained convolutional neural network can be successfully used to evaluate the soiling state of photovoltaic surfaces.

The digitalization of the contemporary engineering education relies greatly on the development of virtual and remote laboratories. This study presents the design and development of the Engine for Virtual Electrical Engineering Equipment (EVEEE). It is aimed at allowing easy creation of realistic virtual labs, which provide educational experience, similar to that of traditional laboratory exercises. The study presents the engine's architecture, its use-cases, the main actors and their roles as well as the implementation of its public and administrative parts.

Animal welfare is a daily concern for livestock farmers. It is known that the activity of cows characterizes their general physiological state and deviations from the normal parameters could be an indicator of different kinds of diseases and conditions. This pilot study investigated the application of machine learning for identifying the behavioral activity of cows using a collar-mounted gyroscope sensor and compared the results with the classical accelerometer approach. The sensor data were classified into three categories, describing the behavior of the animals: “standing and eating”, “standing and ruminating”, and “laying and ruminating”. Four classification algorithms were considered—random forest ensemble (RFE), decision trees (DT), support vector machines (SVM), and naïve Bayes (NB). The training relied on manually classified data with a total duration of 6 h, which were grouped into 1s, 3s, and 5s piles. The obtained results showed that the RFE and DT algorithms performed the best. When using the accelerometer data, the obtained overall accuracy reached 88%; and when using the gyroscope data, the obtained overall accuracy reached 99%. To the best of our knowledge, no other authors have previously reported such results with a gyroscope sensor, which is the main novelty of this study.