Internet of Things (IoT) is a concept that allows physical objects with computational and sensory support to connect with each other and access services across the Internet. The IoT idea was introduced to connect devices through the Internet and facilitate access to information for users. The wide range of potential applications of IoT also includes agriculture, where extensive use of IoT is expected in the future. The aim of this work was to present the IoT concept as a basis for monitoring and control systems used in farm production processes. IoT devices play a key role, with a focus on their realization by available microcontroller platforms and appropriate sensors such as Arduino products. Autonomous sensor devices gather data within monitoring systems and participate in the control process by sending signals to the actuators. Such an IoT based system provides users with the opportunity to remotely monitor conditions and production process. This system enables users to accomplish savings in inputs, achieve cost reduction and trace the production process on the farm.

The stress level has been recognized as one of the key factors in the determination of life quality of the individuals. The sensor data obtained by testing patients to various stress levels are very important in order to understand better the circumstances that lead to elevated stress. This paper gives a description of the possible system capable of complex event monitoring of sensor data. The dataset used supplied the stress levels of several patients. The artificial neural network was created for the classification of stress levels and its results can be further used in an IoT system with complex event processing capabilities.

The electromechanical design of the HDD (Hard Disk Drive) renders it more susceptible to failures than other components of the computer system. The failure of HDD leads to permanent data loss, which is typically more expensive than HDD itself. The SMART (Self-Monitoring, Analysis and Reporting Technology) system warns the user if any HDD parameter has exceeded the predefined threshold value needed for safe HDD operation. Machine learning methods take advantage of dependence between multiple SMART parameters in order to make failure prediction more precise. In this paper, we present a failure prediction model based on the anomaly detection method involving an adjustable decision boundary. SMART parameters are ranked by the importance and the 13 most significant ones are used as the initial feature set in our model. In the following stage, we optimized the feature set by removing those that have no major contribution to the anomaly detection model, forming the final feature set comprising seven features only. The proposed anomaly detection model achieved 96.11% failure detection rate on average, with 0% false detection rate in ten random tests. The proposed model predicted more than 80% of failures 24 hours before their actual occurrence, which enables timely data backup.

A review of advanced wireless sensor nodes, networks, and applications in precision agriculture has been presented. Features of several commercial and prototype sensor node platforms designed and implemented for agricultural applications have been described. Basics of sensor network protocols and topologies have been reviewed together with numerous applications. Advanced machine learning approaches in this field (especially, Kernel Methods, Gaussian Processes, and Deep Neural Networks) have also been discussed.

European honeybee colonies are the most important pollinator insects and source of honey and other useful products. Honeybee colonies today face new diseases and pests as well as pollution which threaten their survival and endanger whole food production which relies on honey bee pollination. Internet of Things (IoT) technology enables integration of wireless sensors inside beehives to enable remote monitoring of various beehive parameters from remote location using Internet. Detection of certain critical events in beehive is hard to be explicitly program due to complex dependence between multiple input parameters. Machine learning algorithms give computers the ability to learn to detect these events without being explicitly programmed. Detection of these event from streams of data collected from IoT sensors is possible using Complex Event Processing (CEP) which applies machine induced knowledge do detect and warn beekeepers about certain events in beehive.