This paper demonstrates how an irrigation management system (IMS) can practically be implemented by deploying a wireless sensor network (WSN). Specifically, the paper describes an IMS which was set up in Manja township, city of Blantyre. Deployment of IMS in rural areas of developing countries like Malawi is a challenge as grid power is scarce. For the system to be self-sustained in terms of power, the study used solar photovoltaic and rechargeable batteries to power all electrical devices. The system incorporated a remote monitoring mechanism through a General Packet Radio Service modem to report soil temperature, soil moisture, WSN link performance, and photovoltaic power levels. Irrigation valves were activated to water the field. Preliminary results in this study have revealed a number of engineering weaknesses of deploying such a system. Nevertheless, the paper has highlighted areas of improvement to develop a robust, fully automated, solar-powered, and low-cost IMS to suit the socioeconomic conditions of small scale farmers in developing countries. Recently, there have been few publications on the application of WSNs to PA. Keshtgary and Deljoo [3] discussed the simulation of WSN for agriculture using OPNET simulation tools in which random and grid topologies were compared. They evaluated the performance of the networks by monitoring delay, throughput, and load. This approach, however, lacks practical aspects where some simulation assumptions are invalid. Zhou and others [4] presented a WSN deployment for an irrigation system using ZigBee protocol. This study did not monitor the performance of
Intrusion prediction is a key task for forecasting network intrusions. Intrusion detection systems have been primarily deployed as a first line of defence in a network, however; they often suffer from practical testing and evaluation due to unavailability of rich datasets. This paper evaluates the detection accuracy of determining all states (AS), the current state (CS), and the prediction of next state (NS) of an observation sequence, using the two conventional Hidden Markov Model (HMM) training algorithms, namely, Baum Welch (BW) and Viterbi Training (VT). Both BW and VT were initialised using uniform, random and count-based parameters and the experiment evaluation was conducted on the CSE-CIC-IDS2018 dataset. Results show that the BW and VT countbased initialisation techniques perform better than uniform and random initialisation when detecting AS and CS. In contrast, for NS prediction, uniform and random initialisation techniques perform better than BW and VT count-based approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.