The use of virtual keyboards in mobile devices such as smartphones and tablets has become an essential tool for inputting information. The sound of keystrokes has been observed in previous studies to be recorded along with ambient noises, such as those produced by uncontrolled student noise, fans, doors and windows, moving cars, and similar sources. The presence of such noises negatively affects the quality of the keystrokes signal, which in turn affects keystroke analysis. The traditional FFT-based denoising methods are vital but they are often limited by their inability to adapt to the varying characteristics of real-world audio and noises. This paper proposes an enhanced Fast Fourier Transform (FFT) with an adaptive threshold technique that reduces ambient noises. The adaptive threshold technique is developed to identify frequency bins that contain noise and set their sizes to zero or attenuate them to reduce the noise. The paper evaluates the performance of the enhanced FFT with adaptive threshold on keystrokes recorded audio and validates it through extensive experimentation. The results show that the enhanced FFT outperforms the traditional FFT in terms of speed and the amount of noise removed from the recorded audio signal, indicating a significant improvement.

UN Department of Economics and Social Affairs predicted that the world population will increase by 2 billion in 2050 with over 50% from the Sub-Saharan Africa (SSA). Considering the level of poverty and food insecurity in the region, there is an urgent need for a sustainable increase in agricultural produce. However, farming approach in the region is primarily traditional. Traditional farming is characterized by high labor costs, low production, and under/oversupply of farm inputs. All these factors make farming unappealing to many. The use of digital technologies such as broadband, Internet of Things (IoT), Cloud computing, and Big Data Analytics promise improved returns on agricultural investments and could make farming appealing even to the youth. However, initial cost of smart farming could be high. Therefore, development of a dedicated IoT cloud-based platform is imperative. Then farmers could subscribe and have their farms managed on the platform. It should be noted that majority of farmers in SSA are smallholders who are poor, uneducated, and live in rural areas but produce about 80% of the food. They majorly use 2G phones, which are not internet enabled. These peculiarities must be factored into the design of any functional IoT platform that would serve this group. This paper presents the development of such a platform, which was tested with smart irrigation of maize crops in a testbed. Besides the convenience provided by the smart system, it recorded irrigation water saving of over 36% compared to the control method which demonstrates how irrigation is done traditionally.