Search results for: Lee C. Hastie

Authors: Godwin A. Otogo, Sansanee Wangvoralak, Graham J. Pierce, Lee C. Hastie, Beth Scott

Abstract:

The squid Loligo forbesii is suspected to be an important species in marine food webs, as it can strongly impact its prey and be impacted upon by predation, competition, fishing and/or climate variability. To quantify these impacts in the food web, the measurement of its trophic position and ecological role within well-studied ecosystems is essential. An Ecopath model was balanced and run for the Moray Firth ecosystem and was used to investigate the significance of this squid’s trophic roles. The network analysis routine included in Ecopath with Ecosim (EwE) was used to estimate trophic interaction, system indicators (health condition and developmental stage) and food web features. Results indicated that within the Moray Firth squid occupy a top trophic position in the food web and also a major prey item for many other species. Results from Omnivory Index (OI) showed that squid is a generalized feeder transferring energy across wide trophic levels and is more important as a predator than that as a prey in the Moray Firth ecosystem. The results highlight the importance of taking squid into account in the management of Europe’s living marine resources.

Keywords: Squid, Loligo forbesii, Ecopath, Moray Firth, Trophic level

Procedia PDF Downloads 462

Authors: Simon Espigolé, Igor Shalyminov, Helen Hastie

Abstract:

Deep machine learning techniques including deep neural networks (DNN) have been used to model language and dialogue for conversational agents to perform tasks, such as giving technical support and also for general chit-chat. They have been shown to be capable of generating long, diverse and coherent sentences in end-to-end dialogue systems and natural language generation. However, these systems tend to imitate the training data and will only generate the concepts and language within the scope of what they have been trained on. This work explores how deep neural networks can be used in a task that would normally require human creativity, whereby the human would read the movie description and/or watch the movie and come up with a compelling, interesting movie title. This task differs from simple summarization in that the movie title may not necessarily be derivable from the content or semantics of the movie description. Here, we train a type of DNN called a sequence-to-sequence model (seq2seq) that takes as input a short textual movie description and some information on e.g. genre of the movie. It then learns to output a movie title. The idea is that the DNN will learn certain techniques and approaches that the human movie titler may deploy that may not be immediately obvious to the human-eye. To give an example of a generated movie title, for the movie synopsis: ‘A hitman concludes his legacy with one more job, only to discover he may be the one getting hit.’; the original, true title is ‘The Driver’ and the one generated by the model is ‘The Masquerade’. A human evaluation was conducted where the DNN output was compared to the true human-generated title, as well as a number of baselines, on three 5-point Likert scales: ‘creativity’, ‘naturalness’ and ‘suitability’. Subjects were also asked which of the two systems they preferred. The scores of the DNN model were comparable to the scores of the human-generated movie title, with means m=3.11, m=3.12, respectively. There is room for improvement in these models as they were rated significantly less ‘natural’ and ‘suitable’ when compared to the human title. In addition, the human-generated title was preferred overall 58% of the time when pitted against the DNN model. These results, however, are encouraging given the comparison with a highly-considered, well-crafted human-generated movie title. Movie titles go through a rigorous process of assessment by experts and focus groups, who have watched the movie. This process is in place due to the large amount of money at stake and the importance of creating an effective title that captures the audiences’ attention. Our work shows progress towards automating this process, which in turn may lead to a better understanding of creativity itself.

Keywords: creativity, deep machine learning, natural language generation, movies

Procedia PDF Downloads 309

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 98

Authors: Luvuno N. Jele, Warwick W. Hastie, Andrew Green

Abstract:

Calcarenite is a clastic sedimentary beach rock composed of more than 50% sand sized (0.0625 – 2 mm) carbonate grains. In South Africa, these rocks occur as a narrow belt along most of the coast of KwaZulu-Natal and sporadically along the coast of the Eastern Cape. Calcarenites contain a high percentage of calcium carbonate, and due to a number of its physical and structural features, like porosity, cementing material, sedimentary structures, grain shape, and grain size; they are more prone to chemical and mechanical weathering. The objective of the research is to study the strength and compressibility characteristics of the calcarenites along the coast of KwaZulu-Natal to be able to better understand the geotechnical behaviour of these rocks, which may help to predict areas along the coast which may be potentially susceptible to failure/differential settling resulting in damage to property. A total of 148 cores were prepared and analyzed. Cores were analyzed perpendicular and parallel to bedding. Tests were carried out in accordance with the relevant codes and recommendations of the International Society for Rock Mechanics, American Standard Testing Methods, and Committee of Land and Transport Standard Specifications for Road and Bridge Works for State Road Authorities. Test carried out included: x-ray diffraction, petrography, shape preferred orientation (SPO), 3-D Tomography, rock porosity, rock permeability, ethylene glycol, slake durability, rock water absorption, Duncan swelling index, triaxial compressive strength, Brazilian tensile strength and uniaxial compression test with elastic modulus. The beach-rocks have a uniaxial compressive strength (UCS) ranging from 17,84Mpa to 287,35Mpa and exhibit three types of failure; (1) single sliding shear failure, (2) complete cone development, and (3) splitting failure. Brazilian tensile strength of the rocks ranges from 2.56 Mpa to 12,40 Ma, with those tested perpendicular to bedding showing lower tensile strength. Triaxial compressive tests indicate calcarenites have strength ranging from 86,10 Mpa to 371,85 Mpa. Common failure mode in the triaxial test is a single sliding shear failure. Porosity of the rocks varies from 1.25 % to 26.52 %. Rock tests indicate that the direction of loading, whether it be parallel to bedding or perpendicular to bedding, plays no significantrole in the strength and durability of the calcarenites. Porosity, cement type, and grain texture play major roles.UCS results indicate that saturated cores are weaker in strength compared to dry samples. Thus, water or moisture content plays a significant role in the strength and durability of the beach-rock. Loosely packed, highly porous and low magnesian-calcite bearing calcarenites show a decrease in strength compared to the densely packed, low porosity and high magnesian-calcite bearing calcarenites.

Keywords: beach-rock, calcarenite, cement, compressive, failure, porosity, strength, tensile, grains

Procedia PDF Downloads 78