Search

Speech signals contain abundant information on personal emotions, which plays an important part in the representation of human potential characteristics and expressions. However, the deficiency of emotion speech data affects the development of speech emotion recognition (SER), which also limits the promotion of recognition accuracy. Currently, the most effective approach is to make use of unsupervised feature learning techniques to extract speech features from available speech data and generate emotion classifiers with these features. In this paper, we proposed to implement autoencoders such as a denoising autoencoder (DAE) and an adversarial autoencoder (AAE) to extract the features from LibriSpeech for model pre-training, and then conducted experiments on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) datasets for classification. Considering the imbalance of data distribution in IEMOCAP, we developed a novel data augmentation approach to optimize the overlap shift between consecutive segments and redesigned the data division. The best classification accuracy reached 78.67% (weighted accuracy, WA) and 76.89% (unweighted accuracy, UA) with AAE. Compared with state-of-the-art results to our knowledge (76.18% of WA and 76.36% of UA with the supervised learning method), we achieved a slight advantage. This suggests that using unsupervised learning benefits the development of SER and provides a new approach to eliminate the problem of data scarcity. [ABSTRACT FROM AUTHOR]

Detecting animals to estimate abundance can be difficult, particularly when the habitat is dense or the target animals are fossorial. The recent surge in the use of thermal imagers in ecology and their use in animal detections can increase the accuracy of population estimates and improve the subsequent implementation of management programs. However, the use of thermal imagers results in many hours of captured flight videos which require manual review for confirmation of species detection and identification. Therefore, the perceived cost and efficiency trade-off often restricts the use of these systems. Additionally, for many off-the-shelf systems, the exported imagery can be quite low resolution (<9 Hz), increasing the difficulty of using automated detections algorithms to streamline the review process. This paper presents an animal species detection system that utilises the cost-effectiveness of these lower resolution thermal imagers while harnessing the power of transfer learning and an enhanced small object detection algorithm. We have proposed a distant object detection algorithm named Distant-YOLO (D-YOLO) that utilises YOLO (You Only Look Once) and improves its training and structure for the automated detection of target objects in thermal imagery. We trained our system on thermal imaging data of rabbits, their active warrens, feral pigs, and kangaroos collected by thermal imaging researchers in New South Wales and Western Australia. This work will enhance the visual analysis of animal species while performing well on low, medium and high-resolution thermal imagery. [ABSTRACT FROM AUTHOR]

Oceanic eddy is a common natural phenomenon that has large influence on human activities, and the measurement and detection of offshore eddies are significant for oceanographic research. The previous classical detecting methods, such as the Okubo–Weiss algorithm (OW), vector geometry algorithm (VG), and winding angles algorithm (WA), not only depend on expert's experiences to set an accurate threshold, but also need heavy calculations for large detection regions. Differently from the previous works, this paper proposes a deep eddy detection neural network with pixel segmentation skeleton on high frequency radar (HFR) data, namely, the deep eddy detection network (DEDNet). An offshore eddy detection dataset is firstly constructed, which has origins from the sea surface current data measured by two HFR systems on the South China Sea. Then, a spatial globally optimum and strong detail-distinguishing pixel segmentation network is presented to automatically detect and localize offshore eddies in a flow chart. An eddy detection network based on fully convolutional networks (FCN) is also presented for comparison with DEDNet. Experimental results show that DEDNet performs better than the FCN-based eddy detection network and is competitive with the classical statistics-based methods. [ABSTRACT FROM AUTHOR]

This work determines whether hyperspectral imaging is suitable for discriminating ore from waste at the point of excavation. A prototype scanning system was developed for this study. This system combined hyperspectral cameras and a three-dimensional LiDAR, mounted on a pan-tilt head, and a positioning system which determined the spatial location of the resultant hyperspectral data cube. This system was used to obtain scans both in the laboratory and at a gold mine in Western Australia. Samples from this mine site were assayed to determine their gold concentration and were scanned using the hyperspectral apparatus in the laboratory to create a library of labelled reference spectra. This library was used as (i) the reference set for spectral angle mapper classification and (ii) a training set for a convolutional neural network classifier. Both classification approaches were found to classify ore and waste on the scanned face with good accuracy when compared to the mine geological model. Greater resolution on the classification of ore grade quality was compromised by the quality and quantity of training data. The work provides evidence that an excavator-mounted hyperspectral system could be used to guide a human or autonomous excavator operator to selectively dig ore and minimise dilution. [ABSTRACT FROM AUTHOR]

Quantification of halloysite and kaolinite in clay deposits from X-ray diffraction (XRD) commonly requires extensive sample preparation to differentiate the two phyllosilicates. When assessing hundreds of samples for mineral resource estimations, XRD analyses may become unfeasible due to time and expense. Fourier transform infrared (FTIR) analysis is a fast and cost-effective method to discriminate between kaolinite and halloysite; however, few efforts have been made to use this technique for quantified analysis of these minerals. In this study, we trained machine- and deep-learning models on XRD data to predict the abundance of kaolinite and halloysite from FTIR, chemical composition, and brightness data. The case study is from the Cloud Nine kaolinite–halloysite deposit, Noombenberry Project, Western Australia. The residual clay deposit is hosted in the saprolitic and transition zone of the weathering profile above the basement granite on the southwestern portion of the Archean Yilgarn Craton. Compared with XRD quantification, the predicted models have an R2 of 0.97 for kaolinite and 0.96 for halloysite, demonstrating an excellent fit. Based on these results, we demonstrate that our methodology provides a cost-effective alternative to XRD to quantify kaolinite and halloysite abundances. [ABSTRACT FROM AUTHOR]