Case-based reasoning has considerable potential to model decision support systems for smart agriculture, assisting farmers in managing farming operations. However, with the explosive amount of sensing data, these systems may achieve poor performance in knowledge management like case retrieval and case base maintenance. Typical approaches of case retrieval have to traverse all past cases for matching similar ones, leading to low efficiency. Thus, a new case retrieval algorithm for agricultural case-based reasoning systems is proposed in this paper. At the initial stage, an association table is constructed, containing the relationships between all past cases. Afterwards, attributes of a new case are compared with an entry case. According to the similarity measurement, associated similar or dissimilar cases are then compared preferentially, instead of traversing the whole case base. The association of the new case is generated through case retrieval and added in the association table at the step of case retention. The association table is also updated when a closer relationship is detected. The experiment result demonstrates that our proposal enables rapid case retrieval with promising accuracy by comparing a fewer number of past cases. Thus, the retrieval efficiency of our proposal outperforms typical approaches.

System dynamics and algebraic graph theory provide the mathematical framework to understand the dynamical and topological features of complex networks, among them the synchronization properties of wireless sensor networks (WSN), a far from trivial subject that may be of great importance for many WSN applications. In this paper, we apply some of these mathematical tools to assess the ease of synchronization of a WSN which has been specifically designed to support surveillance applications.

The deployment of the nodes in a Wireless Sensors and Actuators Network (WSAN) is typically restricted by the sensing and acting coverage. This implies that the locations of the nodes may be, and usually are, not optimal from the point of view of the radio communication. And also when the transmission power is tuned for those locations, there are other unpredictable factors that can cause connectivity failures, like interferences, signal fading due to passing objects, and of course, radio irregularities. A control based self-adaptive system is a typical solution to improve the energy consumption while keeping a good connectivity. In this paper, we explore how the communication range for each node evolves along the iterations of an energy saving self-adaptive transmission power controller when using different parameter sets in an outdoor scenario, providing a WSAN that automatically adapts to surrounding changes keeping a good connectivity. The results obtained in this paper show how the parameters with the best performance keep a k-connected network, where k is in the range of the desired node degree plus or minus a specified tolerance value. In addition, the worst performance shows how a bad parameters choice can create isolated islands, groups of nodes disconnected from the rest of the network.

The deployment of the nodes in a Wireless Sensor and Actuator Network (WSAN) is typically restricted by the sensing and acting coverage. This implies that the locations of the nodes may be, and usually are, not optimal from the point of view of the radio communication. Additionally, when the transmission power is tuned for those locations, there are other unpredictable factors that can cause connectivity failures, like interferences, signal fading due to passing objects and, of course, radio irregularities. A control-based self-adaptive system is a typical solution to improve the energy consumption while keeping good connectivity. In this paper, we explore how the communication range for each node evolves along the iterations of an energy saving self-adaptive transmission power controller when using different parameter sets in an outdoor scenario, providing a WSAN that automatically adapts to surrounding changes keeping good connectivity. The results obtained in this paper show how the parameters with the best performance keep a k-connected network, where k is in the range of the desired node degree plus or minus a specified tolerance value.