A Spatial-Spectral Classification Method Based on Deep Learning for Controlling Pelagic Fish Landings in Chile.

Fishing has provided mankind with a protein-rich source of food and labor, allowing for the development of an important industry, which has led to the overexploitation of most targeted fish species. The sustainable management of these natural resources requires effective control of fish landings and, therefore, an accurate calculation of fishing quotas. This work proposes a deep learning-based spatial-spectral method to classify five pelagic species of interest for the Chilean fishing industry, including the targeted Engraulis ringens, Merluccius gayi, and Strangomera bentincki and non-targeted Normanichthtys crockeri and Stromateus stellatus fish species. This proof-of-concept method is composed of two channels of a convolutional neural network (CNN) architecture that processes the Red-Green-Blue (RGB) images and the visible and near-infrared (VIS-NIR) reflectance spectra of each species. The classification results of the CNN model achieved over 94% in all performance metrics, outperforming other state-of-the-art techniques. These results support the potential use of the proposed method to automatically monitor fish landings and, therefore, ensure compliance with the established fishing quotas.

A Generic Semi-Supervised and Active Learning Framework for Biomedical Text Classification.

Biomedical text classification requires having training examples labeled by clinical specialists, a process that can be costly. To address this problem, active learning incrementally selects a subset of the most informative unlabeled examples, samples that are then labeled and used to train a given classifier, seeking to reduce the number of labeled samples. Nonetheless, the other unlabeled examples are not used by active learning, but incorporating semi-supervised techniques that use unlabeled samples could improve the representativeness of the data and the discriminatory power of the classifiers. This work proposes a generic semi-supervised learning framework for improving active learning and reducing the number of labeled training examples in biomedical text classification. The proposed framework combines manually annotated training examples selected by active learning and pseudo-labels obtained from a trained classifier. To evaluate the proposed framework, three biomedical datasets with textual information on obesity and smoking habit were used across different classification algorithms. The classification results show that the proposed framework can reduce the number of training examples that are manually labeled by clinical specialists by a 10% without affecting the performance of the classifiers. This performance is attributable to the ability of the classifiers to correctly select and label the training examples. Clinical relevance- We demonstrate the effectiveness of the proposed semi-supervised learning framework to reduce manual labeling efforts of biomedical texts by clinical specialists for the training of classifiers.

FREGEX: A Feature Extraction Method for Biomedical Text Classification using Regular Expressions.

In this work, we present FREGEX a method for automatically extracting features from biomedical texts based on regular expressions. Using Smith-Waterman and Needleman-Wunsch sequence alignment algorithms, tokens were extracted from biomedical texts and represented by common patterns. Three manually annotated datasets with information on obesity, obesity types, and smoking habits were used to evaluate the effectiveness of the proposed method. Features extracted using consecutive sequences of tokens (n-grams) were used for comparison, and both types of features were mathematically represented using the TF-IDF vector model. Support Vector Machine and Naïve Bayes classifiers were trained, and their performances were ultimately used to assess the ability of the feature extraction methods. Results indicate that features based on regular expressions not only improved the performance of both classifiers in all datasets but also use fewer features than n-grams, especially in those datasets containing information related to anthropometric measures (obesity and obesity types).

Extracting Information from Electronic Medical Records to Identify the Obesity Status of a Patient Based on Comorbidities and Bodyweight Measures.

Obesity is a chronic disease with an increasing impact on the world's population. In this work, we present a method of identifying obesity automatically using text mining techniques and information related to body weight measures and obesity comorbidities. We used a dataset of 3015 de-identified medical records that contain labels for two classification problems. The first classification problem distinguishes between obesity, overweight, normal weight, and underweight. The second classification problem differentiates between obesity types: super obesity, morbid obesity, severe obesity and moderate obesity. We used a Bag of Words approach to represent the records together with unigram and bigram representations of the features. We implemented two approaches: a hierarchical method and a nonhierarchical one. We used Support Vector Machine and Naïve Bayes together with ten-fold cross validation to evaluate and compare performances. Our results indicate that the hierarchical approach does not work as well as the nonhierarchical one. In general, our results show that Support Vector Machine obtains better performances than Naïve Bayes for both classification problems. We also observed that bigram representation improves performance compared with unigram representation.

Effect of the degree of substitution of octenyl succinic anhydride-banana starch on emulsion stability.

Banana starch was esterified with octenylsuccinic anhydride (OSA) at different degree substitution (DS) and used to stabilize emulsions. Morphology, emulsion stability, emulsification index, rheological properties and particle size distribution of the emulsions were tested. Emulsions dyed with Solvent Red 26 showed affinity for the oil phase. Backscattering light showed three regions in the emulsion where the emulsified region was present. Starch concentration had higher effect in the emulsification index (EI) than the DS used in the study because similar values were found with OSA-banana and native starches. However, OSA-banana presented greater stability of the emulsified region. Rheological tests in emulsions with OSA-banana showed G'>G" values and low dependence of G' with the frequency, indicating a dominant elastic response to shear. When emulsions were prepared under high-pressure conditions, the emulsions with OSA-banana starch with different DS showed a bimodal distribution of particle size. The emulsion with OSA-banana starch and the low DS showed similar mean droplet diameter than its native counterpart. In contrast, the highest DS led to the highest mean droplet diameter. It is concluded that OSA-banana starch with DS can be used to stabilize specific emulsion types.

Preparation and characterization of octenylsuccinylated plantain starch.

Plantain starch was esterified with octenylsuccinic anhydride (OSA) at two concentrations (3 and 15% w/w) of OSA. The morphology, granule size distribution, pasting, gelatinization, swelling, and solubility of granules and structural features of the starch polymers were evaluated. Granules of the OSA-modified starches increased in size during cooking more than did the granules of the native starch, and the effect was greater at the higher OSA concentration. Pasting viscosities also increased, but gelatinization and pasting temperatures and enthalpy of gelatinization decreased in the OSA-modified starches. It was concluded that insertion of OS groups effected disorder in the granular structure. Solubility, weight average molar mass, Mw¯, and z-average radius of gyration, RGz, of the amylopectin decreased as the OSA concentration increased, indicating a decrease in molecular size.