136879 research outputs found
Sort by
Perception and Localization for Rural Roads
No full textA significant majority of the state of the art autonomous sensing and navigation technologies rely on good lane markings or detailed 3D maps of the environment and are more suited for urban communities. On the other hand, a large number of rural roads in the U.S. do not have lane markings and have irregular boundaries. These challenges are common to many small and rural communities (SRCs), defined as an incorporated city, town or village with a population of less than 50,000. These communities are sparsely connected and cover huge areas. The objective of this work is to develop an efficient sensing and navigation system for SRCs. To this end we develop a novel Rural Road Detection dataset for training and evaluation of sensing algorithms. We also propose road descriptors along with an initialization technique for localization that allows for fast global pose estimation on crowd sourced topological maps such as the Open Street Map (OSM). We test our algorithms on (real world) maps and benchmark them against other map based localization as well as SLAM algorithms. Our results show that the proposed method can narrow down the pose to within 50 centimeters of the ground truth significantly faster than the state of the art methods
Analyzing Cricket Songs with Machine Learning
Get PDFGiven the recordings of cricket songs, we aimed to apply machine learning and audio signal processing techniques to (1) discover intrageneric and intraspecies relationships in the songs and (2) create models that could classify the songs into their correct genus and species. First, we took out noise in the audio files using a high pass filter. Then, we represented the cricket songs in three different forms: mel spectrograms, mel frequency cepstrum coefficients, and magnitude power spectrums. We achieved our first objective by reducing the dimensionality of the three extracted audio features to visualize how the cricket songs clustered in 2D space. We found that cricket songs belonging to the same genus are generally similar, which gave us hope that constructing a high accuracy genus classification model would be possible. We were not able to conclude that cricket songs belonging to the same species are similar because the dataset used did not have enough audio files per species. As a result of our initial findings, we constructed genus classification models using shallow convolutional neural network architectures and mel spectrograms as input. Because there was only a small number of cricket song files available for training, we reduced our models��� scopes to only classify inputs into 5 genera. Rather than extracting a single mel spectrogram per each available audio file, we extracted multiple 3-second mel spectrograms per each available audio file and used this set of mel spectrograms as our training set. We found that the more mel spectrograms extracted per available audio file, the higher the model���s accuracy became. Our highest-performing genus classification model has a validation loss of 0.1637 and a validation accuracy of 94.30%. Later in the research, we obtained a larger dataset that could be used for species classification. As such, we constructed species classification models using the same approaches taken for the genus classification models. These models classified inputs into 9 different species. Our highest-performing species classification model has a validation loss of 0.2849 and a validation accuracy of 92.28%. The high accuracy of our genus and species classification models confirmed that it would be possible to classify cricket songs using machine learning techniques. This finding is pivotal for the entomology field as there has not been much documented research regarding insect song classification. Of course, our classification models were quite limited in scope; however, we believe that with more data and a deeper model, more generalized insect song classification models are possible. The fact that we were able to employ simple yet effective techniques to discover insights in relatively small cricket song datasets should encourage entomologists that the application of machine learning to cricket songs is still worthwhile even if the field has a lack of publicly available data
Advanced Evaluation of Materials Applied to Hydrogen Service Compressor and Stress Reduction Design of Compressor Rotors
Get PDFLectur
