Agris Nikitenko

The operational and indoor environmental quality of buildings has a significant impact on global energy consumption and human quality of life. One of the key directions for improving building performance is the optimization of building control systems. In modern buildings, the presence of numerous actuators and monitoring points makes manually designed control algorithms potentially suboptimal due to the complexity and human factors. To address this challenge, model predictive control based on artificial neural networks can be employed. The advantage of this approach lies in the model’s ability to learn and understand the dynamic behavior of the building from monitoring datasets. It should be noted that the effectiveness of such control models is directly dependent on the forecasting accuracy of the neural networks. In this study, we adapt neural network architectures such as GRU and TCN for use in the context of building model predictive control. Furthermore, we propose a novel hybrid architecture that combines the strengths of recurrent and convolutional neural networks. These architectures were compared using real monitoring data collected with a custom-developed device introduced in this work. The results indicate that, under the given experimental conditions, the proposed hybrid architecture outperforms both GRU and TCN models, particularly when processing large sequential input vectors.

This paper presents VREL NextGen, an international Internet of Things (IoT) education platform developed through European university collaboration. The platform addresses hands-on IoT education needs in the Industry 5.0 context through three distinct implementations: a microcontroller laboratory at the Silesian University of Technology, a building management sensor network at Riga Technical University, and a human-robot collaboration platform at Tallinn University of Technology. The system enables remote access to physical hardware while promoting resource sharing and standardized educational approaches. Implementation results demonstrate effective integration of theoretical knowledge with practical skills, supporting both fundamental engineering concepts and advanced IoT applications while emphasizing human-centric design principles of Industry 5.0

This research aims to demonstrate a machine learning (ML) algorithm-based indoor air quality (IAQ) monitoring and forecasting system for a public sector building use case. Such a system has the potential to automate existing heating/ventilation systems, therefore reducing energy consumption. One of Riga Technical University’s campus buildings, equipped with around 128 IAQ sensors, is used as a test bed to create a digital shadow including a comparison of five ML-based data prediction tools. We compare the IAQ data prediction loss using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) error metrics based on real sensor data. Gated Recurrent Unit (GRU) and Kolmogorov–Arnold Networks (KAN) prove to be the most accurate models regarding the prediction error. Also, GRU proved to be the most efficient model regarding the required computation time.

Predicting the growth of broiler chickens is an essential task in the poultry industry. The data used in the study include both the production environmental indicators (temperature, gas concentration, humidity, and others) and the growth rates of poultry (weight, amount of feed consumed, fall) by analyzing their correlations throughout several production cycles. The proposed approach includes several stages, starting with data pre-processing, broiler weight data augmentation, comparison with a reference model, definition, and detection of uncomfortable and dangerous environmental conditions. For the model-building part, the Long short-term memory (LSTM) artificial neural network is applied. The validation of the forecasting model is done by comparing the forecasted weight provided by the model with the actual weight measurements during the randomly selected bird life cycle and varied environmental conditions. The acquired results showed that the provided forecast accuracy is sufficient for production management.

The presented work proposes a practical approach to bird weight data processing and augmentation to enable production outcome forecast model training, which contributes to higher productivity. We suggest using the parametrized model, where parameter values are found through genetic optimization and thus are closely corresponding to broiler body weight factual measurements. The proposed approach is implemented as a stand-alone software system, exposing the models through containerized web services enabling different use scenarios.

Optimal performance parameters must be found in order to organize efficient heat and mass transfer and effective flue gas cooling using a wet scrubber. Mathematical models are widely used for system optimization. However, a significant number of the available models have application limitations. This study presents a universal model for heat and mass transfer simulation in a scrubber called a fog unit, which has been developed and validated. Validation was performed by comparing the experimental and calculated results. Good agreement was achieved among the data, with differences between results not exceeding 10%. The model facilitates an investigation of the effects of gas flow, droplet size, and sprayed water on heat recovery from flue gas. An experimental matrix for fog unit capacity which included five main variables was designed and analyzed. The boundaries of the parameters are set considering the results of the experiments. The optimization method used is the path of the steepest ascent. The obtained results show the parameter change steps to achieve higher capacity of the condenser. In the studied unit, the maximum condenser capacity is limited by a flue gas flow value of 0.01 Nm³/s. The condenser optimization study that was conducted is viewed as a basis for further studies.

This paper proposes a long-term adaptive distributed intelligent systems model which combines an organization theory and multi-agent paradigm—ViaBots. Currently, the need for adaptivity in autonomous intelligent systems becomes crucial due to the increase in the complexity and diversity of the tasks that autonomous robots are employed for. To deal with the design complexity of such systems within the ViaBots model, each part of the modeled system is designed as an autonomous agent and the entire model, as a multi-agent system. Based on the viable system model, which is widely used to ensure viability, (i.e., long-term autonomy of organizations), the ViaBots model defines the necessary roles a system must fulfill to be capable to adapt both to changes in its environment (like changes in the task) and changes within the system itself (like availability of a particular robot). Along with static role assignments, ViaBots propose a mechanism for role transition from one agent to another as one of the key elements of long term adaptivity. The model has been validated in a simulated environment using an example of a conveyor system. The simulated model enabled the multi-robot system to adapt to the quantity and characteristics of the available robots, as well as to the changes in the parts to be processed by the system.

The paper discuses several options to implement multi-robot systems focusing on coordination and action planning of the system. Particular implementation described in details as a case study...

In the present paper, a new and improved visual sensor data fusion method is proposed that uses visible and far-infrared light sensors. Additionally, lux meter data are used for decision level fusion of beliefs of recognised target classes. The database consisting of 4 ambient light condition images is created using Canon and FLIR cameras. The developed approach has been tested using database images, neural network training and classification, particularly for low light level conditions. Enhancements of target identification precision are proved by practical implementation and testing of the proposed method.