Nowadays, wireless sensor networks (WSN) are widely used in agriculture monitoring to improve the quality and productivity of farming. In this application, sensors gather different types of data (i.e., humidity, carbon dioxide level, and temperature) in real-time scenarios. Thus, data gathering, transmission, and rapid response to new circumstances require a secured data mechanism to avoid malicious adversaries. Therefore, this paper focuses on data security from the data origin source to the end-user, and proposes a general data security model that is independent of the network topology and structure, and can be widely used in the agriculture monitoring application. The developed model considers practical aspects, the architecture of the sensor node, as well as the necessity to save energy while ensuring data security, and optimize the model through the application of organizational and technical measures. The model evaluation is conducted through simulation in terms of energy consumption. The result shows that the proposed model ensures good data security at the cost of a slight increase in energy consumption at receiver and sender nodes, and energy consumption per bit, up to 2%, 7%, and 1.3%, respectively, due to overhead added for authentication in the network.

Intravenous (IV) infusion therapy allows the infusion fluid to be inserted directly into the patient’s vein. It is used to place medications directly into the bloodstream or for blood transfusions. The probability that a hospitalized patient will receive some kind of infusion therapy, intravenously, is 60–80%. The paper presents a smart IV infusion dosing system for detection, signaling, and monitoring of liquid in an IV bottle at a remote location. It consists of (i) the sensing and computation layer—a system for detection and signaling of fluid levels in the IV bottle and a system for regulation and closing of infusion flow, (ii) the communication layer—a wireless exchange of information between the hardware part of the system and the client, and (iii) the user layer—monitoring and visualization of IV therapy reception at a remote location in real time. All layers are modular, allowing upgrades of the entire system. The proposed system alerts medical staff to continuous and timely changes of IV bottles, which can have positive effects on increasing the success of IV therapy, especially in oncology patients. The prescribed drip time of IV chemotherapy for the full effect of cytostatics should be imperative.

Dairy cows identification and monitoring on small cattle farms are usually based on the utilization of barcode technology. This kind of identification technology is unsuitable for dairy cows milking and feeding process automation. Radio Frequency Identification (RFID) technology is a better solution in this case. This paper describes the research and implementation of the milking cycle´s automated monitoring with the use of RFID tags conducted on a small cattle farm in the Republic of Serbia. This solution is based on RFID system which consists of two parts. First part includes control box, two Ultra High Frequency (UHF) RFID readers operating at frequency of 915 MHz and RFID tags glued onto the dairy cow ear labels. Second part includes software modules for acquisition and collecting data from RFID tags to build up an archive due to supervision and analysis of the milking cycle. Reading accuracy of RFID system in the observed period was 99.8 % in average. A group of dairy cows having a settled milking cycle within an interval of 12h ± 5 % had a 1.5 % better yield and a 0.08 better quality in comparison with a group of dairy cows having a milking cycle variance higher than 20 %. RFID system implemented in described way can be easily integrated into a new or existing farm management system in order to have better production results which depend on several factors including settled milking cycles

Anomaly-based intrusion detection systems identify the computer network behavior which deviates from the statistical model of typical network behavior. Binary classifiers based on supervised machine learning are very accurate at classifying network data into two categories: normal traffic and anomalous activity. Most problems with supervised learning are related to the large amount of data required to train the classifiers. Feature selection can be used to reduce datasets. The goal of feature selection is to select a subset of relevant input features to optimize the evaluation and improve performance of a given classifier. Feature scaling normalizes all features to the same range, preventing the large size of features from affecting classification models or other features. The most commonly used supervised machine learning models, including decision trees, support vector machine, k-nearest neighbors, weighted k-nearest neighbors and feedforward neural network, can all be improved by using feature selection and feature scaling. This paper introduces a new feature scaling technique based on a hyperbolic tangent function and damping strategy of the Levenberg–Marquardt algorithm.