Ali Hilal Ali Athary

This paper presents an original approach to Human Activity Recognition (HAR) tasks based on wearable sensors data. We have trained a Bidirectional Long-Short Term Memory (BLSTM) Recurrent Neural Network (RNN) model to predict the physical activity of subjects taken from the mHealth dataset. PCA has been used to reduce dimensionality of the dataset while keeping the total variation at no less than 85%. The resulting dataset consisted of 15 features instead of features at a reduction rate of 34.7% The mhealth has 12 different activities recorded out of 10 subjects. We present a comparison of the PCA-BLSTM approach to several classical machine learning models. Results indicated that the PCA-BLSTM model has registered the highest accuracy of 97.64%. The SVM algorithm has registered the least accuracy of 64.67.

An aquaponic is a system that combines aquaculture with hydroponic to form a bio-integrated structure that aims at achieving a symbiotic environment for both aqualife and crops growth. Fish excretions in fish tanks contains ammonia which is poisonous and is considered very dangerous on fish survival. However, ammonia can be converted by the action of the nitrifying bacteria into Nitrites and then to Nitrates which can be used as nutrients for the plants, hence the symbiotic relationship between the two. The aim of this project is to monitor and control aquaponics by using Internet of Things (IoT) technology by recording various parameters in real time settings. Our proposed system consists of sensors that measure pH, temperature, Oxygen and ammonia levels. In turn, these sensors are connected to a remote database over the internet to enable users to get the values of these sensors. We used NodeMcu to acquire sensors data and deliver them to a web server. The low power consumption of the system has resulted in the possibility of powering it by solar power. We have registered levels of ammonia without the action of aquaculture part between 0.05 to 0.4 mg/L over a period of one week. These values have since risen to a dangerous level of 0.5 mg/L leading fish deaths. However, a stable range of 0.02 to 0.04 mg/L were registered with the integration of the aquaculture part. In addition, a normal pH level of 6.5 to 8 were recorded and the temperature was between (23-25.57) C.