60 research outputs found
DSAIL power management board: Powering the Raspberry Pi autonomously off the grid
No full textThe Raspberry Pi is a credit card sized single board computer that finds its use in very diverse projects. Being a computer it runs on a full operating system and can be interfaced with a wide range of hardware. Its ability to collect and store data and its superior processing capabilities gives it an edge over other microprocessors. When used to collect data away from the grid, alternative methods of powering the Raspberry Pi have to be used. An ideal powering system should be autonomous, allowing the Raspberry Pi to be deployed indefinitely without the need to check on the system due to power shortcomings. In this paper we introduce the DSAIL Power Management Board that is used to power the Raspberry Pi autonomously. We have developed a prototype and used it to collect ecological data from a conservancy in Central Kenya
Approximate Bayesian inference for robust speech processing
No full textSpeech processing applications such as speech enhancement and speaker identification rely on the estimation of relevant parameters from the speech signal. Theseparameters must often be estimated from noisy observations since speech signals are rarely obtained in ‘clean’ acoustic environments in the real world. As a result, the parameter estimation algorithms we employ must be robust to environmental factors such as additive noise and reverberation. In this work we derive and evaluate approximate Bayesian algorithms for the following speech processing tasks: 1) speech enhancement 2) speaker identification 3) speaker verification and 4) voice activity detection.Building on previous work in the field of statistical model based speech enhancement, we derive speech enhancement algorithms that rely on speaker dependent priors over linear prediction parameters. These speaker dependent priors allow us to handle speech enhancement and speaker identification in a joint framework. Furthermore, we show how these priors allow voice activity detection to be performed in a robust manner.We also develop algorithms in the log spectral domain with applications in robust speaker verification. The use of speaker dependent priors in the log spectral domain is shown to improve equal error rates in noisy environments and to compensate for mismatch between training and testing conditions.Ph.D., Electrical Engineering -- Drexel University, 201
Raspberry Pi based recording system for acoustic monitoring of bird species
No full textSevere degradation of ecosystems due to human encroachment and climate change call for close monitoring of the ecosystems in order to conserve them. Ecosystems have a lot of acoustic data that can be used to study changes taking place in them remotely. In this paper, we present an acoustic system that is based on the Raspberry Pi and is used to collect audio recordings for use in acoustic monitoring of birds. The system has been designed to work optimally in the field. It has been able to collect good quality acoustic data of several bird species during its pilot deployment. Acoustic data collected over a reasonable amount of time will be used to create datasets that will be used in developing machine learning models for automatic classification of bird species. This will offer a tool to provide continuous monitoring of ecosystems.National Research Fund Kenya (NRF
A Bioacoustic Record of a Conservancy in the Mount Kenya Ecosystem
No full textFigure 3b -
The DeKUWC with locations of the point counts and acoustic recorders indicated. The 20 point count locations are labelled A-T (a) and the acoustic recorder locations are labelled 1-8 (b)
Deep learning models for the early detection of maize streak virus and maize lethal necrosis diseases in Tanzania
No full textThis research article was published by International Journal of Innovative Research & Development 2024Agriculture is considered the backbone of Tanzania’s economy, with more
than 60% of the residents depending on it for survival. Maize is the country’s
dominant and primary food crop, accounting for 45% of all farmland production.
However, its productivity is challenged by the limitation to detect maize diseases
early enough. Maize streak virus (MSV) and maize lethal necrosis virus (MLN) are
common diseases often detected too late by farmers. This has led to the need
to develop a method for the early detection of these diseases so that they can
be treated on time. This study investigated the potential of developing deep-
learning models for the early detection of maize diseases in Tanzania. The
regions where data was collected are Arusha, Kilimanjaro, and Manyara. Data
was collected through observation by a plant. The study proposed convolutional
neural network (CNN) and vision transformer (ViT) models. Four classes of
imagery data were used to train both models: MLN, Healthy, MSV, and WRONG.
The results revealed that the ViT model surpassed the CNN model, with 93.1
and 90.96% accuracies, respectively. Further studies should focus on mobile
app development and deployment of the model with greater precision for early
detection of the diseases mentioned above in real life
- …
