The research focuses on the implementation of a human detection and geolocation system using aerial drones to complement search and rescue. The study includes the characterization of the human detection system for thermal and optical imagery by determining the frame accuracy, true and false positive rates. Geolocation was achieved using triangulated-adjusted GPS data and integration of Google Maps.
1 October 2021 in Renewable and Sustainable Energy Reviews
In smart cities and urban areas, localized weather monitoring will be a readily available feature. Checking the air quality in small area urban motifs, specifically schools and universities situated near a national primary road and mid to high-rise condominiums with increasing sources of pollutants, e.g. particulate matter (PM), becomes a need for risk assessment. An aerial sensor system, consisting of an unmanned aerial vehicle (UAV) and a sensor payload, is designed and implemented. Measurements for PM concentration are taken at various elevations, and during heavy and light traffic conditions. Results show trends relating PM concentration with elevation and traffic conditions.
Current designs for 3D printed hand prosthetics are only capable of basic hand gestures given their fully mechanical structure. That said, the purpose of this thesis is to give users greater flexibility and control over 3D printed hand prosthetics by modifying and improving existing open-source prosthetics models. This will be accomplished by integrating two control modules with the 3D printed prosthetic hand - (a) a brain-computer interface, and (b) a voice recognition module - which will serve as its two primary modes of control.
A low-cost wireless glove controller that detects finger gestures was developed using makeshift flex sensors and a digital accelerometer. The performance of the makeshift flex sensors was compared to that of commercially available ones. A system using Arduino, Bluetooth, and Processing was developed to allow the user to specify desired finger gestures for controlling a variety of robotic devices. A simple mobile robot (mobot) was used to demonstrate the capabilities of the glove in controlling devices. A 3D virtual environment was also created for the virtualization of the user's hand movements detected by the glove controller. Inside this virtual environment, the user-defined finger gestures also allowed the user to control elements inside the virtual environment which can branch out to various applications including rehabilitation and body-oriented gaming.
This work aims to analyze the EEG signals produced by facial gestures and eye movements called artifacts. Although these signals are considered contaminants in EEG signals used for medical diagnosis, these are observed in order to consider the possibility of using them as inputs for certain applications. As such, the project aims to observe distinct signal patterns in the EEG signals acquired for certain facial gestures as a preliminary work to facial gesture detection. Using the Emotiv Epoc Neuroheadset, the cross correlation between pairs of 14 channels for six facial gestures and their frequency response are compared. These facial gestures are blink, left wink, right wink, raise brow, smile, and clench. Particular channel pairs are found to be highly correlated for certain facial gestures and can be used as possible means of detecting these gestures. In the frequency domain, only the gestures smile and clench registered a distinctive frequency response among the other gestures. Moreover, the Emotiv Epoc neuroheadset paired with the Arduino Duemilanove board was found to be an effective tool as a controller for household appliances. Also, the neuroheadset was useful in developing an extended communication platform. As such not only does it prove to be a viable device for developing systems in aiding the physically-challenged, but also provides a glimpse of the potential advances in the field of Brain-Computer Interfaces.