Poaching is a persistent issue that threatens many of earth’s species including therhino. The methods used by poachers are varied, but many use guns to carry outtheir illegal activities. Gunfire is extremely loud and can be heard for kilometres.This thesis investigates whether it is possible to aid anti-poaching efforts in Kenyawith a gunshot detection and estimation device using an array of microphones. Ifsuccessful, the device could be placed around the savannah or any exposed areaand warn if poaching is taking place in the nearby. If a shot is fired within theaudible range of the device’s microphones, a trained machine learning algorithmdetects the shot on the edge using a microprocessor. The detection runs in realtime and achieved an accuracy of 93% on an unbalanced data set, where themajority class was the one without gunshots. Once a detection has been made, thereceived signal power to each microphone is used to produce a direction of arrivalestimate. The estimate can produce an angle estimate with a standard deviationof 66.78° for a gunshot, and with a standard deviation of 7.65° when testing themodel with white noise. Future implementations could use several devices thatdetected the same event, and fuse their estimates to locate the shooter’s position.All of this information, as well as the sound file, can be used to alert and assistlocal wildlife services. The challenges of this project have been centred aroundmaking a system run in real time with only a microprocessor on the edge, whilealso prioritizing low cost components for future deployment. / Project Ngulia

Um estudo comparativo entre os principais modelos empíricos e semi-empíricos de predição de nível de sinal para comunicações móveis celulares é descrito neste trabalho. Medidas de cobertura outdoor em ambiente urbano foram comparadas com os resultados simulados a partir dos modelos de Okumura-Hata e Lee, lkegami, Walfisch-Bertoni e Walfisch-Ikegami. As medidas de potência de sinal recebido foram realizadas na cidade de Conceição das Alagoas, MG, a partir da única estação rádio-base (ERB) da cidade, operando na banda A com tecnologia AMPS/TDMA. Foi utilizada como portadora de teste o canal de controle analógico 328. As informações foram coletadas em algumas ruas da cidade, por meio de equipamento instalado em veículo, em diferentes posicionamentos em relação a ERB, de forma a se obter amostras de cobertura em diferentes cenários, seja em visada direta, em obstrução parcial ou total. O modelo de Ikegami se mostrou apropriado para predição de níveis de sinal recebido no ambiente estudado, apresentando desvio médio 5,81 dB em relação às medidas realizadas. / A comparative study among the main empiric and semi-empiric models of prediction of signal leveI for cellular mobile communications is described in this work. Measurements of covering outdoor in an urban environment were compared to the simulated results from the models of Okumura-Hata, Lee, Ikegami, Walfisch-Bertoni and Walfisch-Ikegami. The measurements of received signal level were accomplished in some streets of the city of Conceição das Alagoas, MG, starting from the only radio base station of the city, operating in the A band with AMPS/TDMA technology. The 328-analog control channel was used as test carrier. The measurements were carried out using some equipment installed in a vehicle, in different positions in relation to the radio base station, in order to obtain covering profile in different circunstances such as line-of-sight, non line-of-sight, and partial obstruction. The model of Ikegami was shown appropriate for prediction of the received signal levels in the studied environment, exhibiting an average deviation of 5,81 dB in relation to the accomplished measurements.

Um estudo comparativo entre os principais modelos empíricos e semi-empíricos de predição de nível de sinal para comunicações móveis celulares é descrito neste trabalho. Medidas de cobertura outdoor em ambiente urbano foram comparadas com os resultados simulados a partir dos modelos de Okumura-Hata e Lee, lkegami, Walfisch-Bertoni e Walfisch-Ikegami. As medidas de potência de sinal recebido foram realizadas na cidade de Conceição das Alagoas, MG, a partir da única estação rádio-base (ERB) da cidade, operando na banda A com tecnologia AMPS/TDMA. Foi utilizada como portadora de teste o canal de controle analógico 328. As informações foram coletadas em algumas ruas da cidade, por meio de equipamento instalado em veículo, em diferentes posicionamentos em relação a ERB, de forma a se obter amostras de cobertura em diferentes cenários, seja em visada direta, em obstrução parcial ou total. O modelo de Ikegami se mostrou apropriado para predição de níveis de sinal recebido no ambiente estudado, apresentando desvio médio 5,81 dB em relação às medidas realizadas. / A comparative study among the main empiric and semi-empiric models of prediction of signal leveI for cellular mobile communications is described in this work. Measurements of covering outdoor in an urban environment were compared to the simulated results from the models of Okumura-Hata, Lee, Ikegami, Walfisch-Bertoni and Walfisch-Ikegami. The measurements of received signal level were accomplished in some streets of the city of Conceição das Alagoas, MG, starting from the only radio base station of the city, operating in the A band with AMPS/TDMA technology. The 328-analog control channel was used as test carrier. The measurements were carried out using some equipment installed in a vehicle, in different positions in relation to the radio base station, in order to obtain covering profile in different circunstances such as line-of-sight, non line-of-sight, and partial obstruction. The model of Ikegami was shown appropriate for prediction of the received signal levels in the studied environment, exhibiting an average deviation of 5,81 dB in relation to the accomplished measurements.