The connectivity and grade of service of an Internet Service Provider (ISP) in the Philippines is observed and analysed in this research. Traditionally, the sensitivity of the antennas for wireless access points are done manually by monitoring the signal levels onsite during the installation process. Ten subscriber locations are randomly selected as test points. The connectivity of these subscribers is observed given that their sensitivities are set manually. Finally, a proposed artificial neural network algorithm is presented to improve the availability of the internet link. The proposed algorithm incorporates the random variations of the received signal levels of the internet access points and possible degradation of signals from attenuation due to rain. Experiment results show that at least 75% increase in availability is observed using the proposed algorithm during rainy events

Detecting faces in images remains a challenge in image processing and is currently an active area of research. A frontal face detection algorithm is presented in this paper. Skin colors were used to initially detect possible faces in the image. Using a search window, possible faces are processed using edge detection. These are then classified as faces or non faces using an artificial neural network classifier. The algorithm was tested in images with varying sizes and number of faces. Results from experiments demonstrate successful face detections. Ideas for future work are also included to close the paper.

No abstract

This paper discusses the design of a broadband wireless network infrastructure which itself is a rain measurement platform for applications such as disaster alarm and sudden hazard decision management systems. A sensor testbed is setup which consists of a hybrid broadband wireless network in conjunction with real-time acoustic rain rate point sensors and complementary rain gauges. The testbed simulates the commercial deployment of a line-of-sight wireless backbone (implemented via a 26 GHz line of sight link) and broadband wireless access network at 5 GHz and 2.4 GHz. Combined wireless signal fade, acoustic power and tipping bucket rain rate measurements over a several month span indicate the feasibility of using rain-induced attenuation and fade durations to trigger imminent-hazard alerts.

A new engineering methodology is proposed to improve the automation process in monitoring the water quality in a small scale aquaculture system. Behavioural Response Analysis using Vision Engineering Network or BRAVENet is proposed, as a support system to a traditional sensor-based system, to monitor critical water quality parameters such as temperature, pH, salinity and dissolved oxygen. BRAVENet is based on the reactions or behavioural responses of tiger prawns to different water conditions. The performance of both the sensor-based system and BRAVENet are analysed and discussed. It is shown that the BRAVENet can identify unsafe levels of water parameters and is a good monitoring and prediction tool for water conditions especially those instances when industry grade sensors fail or become erroneous. Promising results show that BRAVENet can be used as a support system, if not as a replacement, in continuously monitoring the status of the critical water quality parameters of aquaculture systems.