The aim of this study is to control home devices using a non invasive brain computer interface (BCI). The Electroencephalographic signals (EEG) recorded from the brain activity using the Emotiv EPOCH headset are interfaced with the help of mouse emulator to a graphical user interface (GUI) on the computer screen. The user will use this GUI to control various devices in a smart home. This application will be very useful especially for people with special needs.

In this chapter, we explain the two types of power consumption found in a complementary metal-oxide-semiconductor (CMOS) circuit. In general, a CMOS circuit tends to dissipate power at all times—be it active or inactive. The power consumed by the circuit when it is performing computational tasks is known as dynamic power. On the contrary, the power lost due to current leakage during which the circuit is dormant is referred to as static power. By carefully and properly designing the circuit, current leakage can be suppressed to its minimum. Hence, dynamic power consumption is usually significantly higher than its static counterpart. Some of the techniques that could be adopted to save dynamic power consumption include reducing the supply voltage, clock frequency, clock power, and dynamic effective capacitance. By probing into the activity factors of the design modules, the techniques can be applied to those with high power consumption.

In this paper, the characteristics of an electrostatic separator were modeled using artificial neural network (ANN). The model was constructed by considering the misclassified middling product during separation, where system parameters (voltage level, rotation speed, electrode position, etc) were varied. The ANN architecture was optimized through the variation in the neuron number, percentage of testing data and percentage of validation data. Performance of the network was assessed by the error indicators, namely mean square error (MSE) and coefficient of determination (R-square). It is found that, lesser number of neurons and lower percentage of both training and validation dataset contributes to better network performance. Additionally, network architecture thus derived was selected for a detailed study on the various combinations performance corresponding to the input and output variables. The results consequently suggest a simplified network structure with reduced number of input variables for modeling of this nonlinear process