Análisis del comportamiento del CTC con problemas de clases muy desbalanceadas del repositorio KEEL

En este proyecto se analiza y compara el comportamiento del algoritmo CTC diseñado por el grupo de investigación ALDAPA usando bases de datos muy desbalanceadas. En concreto se emplea un conjunto de bases de datos disponibles en el sitio web asociado al proyecto KEEL (http://sci2s.ugr.es/keel/index.php) y que han sido ya utilizadas con diferentes algoritmos diseñados para afrontar el problema de clases desbalanceadas (Class imbalance problem) en el siguiente trabajo: A. Fernandez, S. García, J. Luengo, E. Bernadó-Mansilla, F. Herrera, "Genetics-Based Machine Learning for Rule Induction: State of the Art, Taxonomy and Comparative Study". IEEE Transactions on Evolutionary Computation 14:6 (2010) 913-941, http://dx.doi.org/10.1109/TEVC.2009.2039140 Las bases de datos (incluidas las muestras del cross-validation), junto con los resultados obtenidos asociados a la experimentación de este trabajo se pueden encontrar en un sitio web creado a tal efecto: http://sci2s.ugr.es/gbml/. Esto hace que los resultados del CTC obtenidos con estas muestras sean directamente comparables con los obtenidos por todos los algoritmos obtenidos en este trabajo.

An update of the J48Consolidated WEKA’s class: CTC algorithm enhanced with the notion of coverage

This document aims to describe an update of the implementation of the J48Consolidated class within WEKA platform. The J48Consolidated class implements the CTC algorithm [2][3] which builds a unique decision tree based on a set of samples. The J48Consolidated class extends WEKA’s J48 class which implements the well-known C4.5 algorithm. This implementation was described in the technical report "J48Consolidated: An implementation of CTC algorithm for WEKA". The main, but not only, change in this update is the integration of the notion of coverage in order to determine the number of samples to be generated to build a consolidated tree. We define coverage as the percentage of examples of the training sample present in –or covered by– the set of generated subsamples. So, depending on the type of samples that we use, we will need more or less samples in order to achieve a specific value of coverage.

J48Consolidated: an implementation of CTC algorithm for WEKA

The CTC algorithm, Consolidated Tree Construction algorithm, is a machine learning paradigm that was designed to solve a class imbalance problem, a fraud detection problem in the area of car insurance [1] where, besides, an explanation about the classification made was required. The algorithm is based on a decision tree construction algorithm, in this case the well-known C4.5, but it extracts knowledge from data using a set of samples instead of a single one as C4.5 does. In contrast to other methodologies based on several samples to build a classifier, such as bagging, the CTC builds a single tree and as a consequence, it obtains comprehensible classifiers. The main motivation of this implementation is to make public and available an implementation of the CTC algorithm. With this purpose we have implemented the algorithm within the well-known WEKA data mining environment http://www.cs.waikato.ac.nz/ml/weka/). WEKA is an open source project that contains a collection of machine learning algorithms written in Java for data mining tasks. J48 is the implementation of C4.5 algorithm within the WEKA package. We called J48Consolidated to the implementation of CTC algorithm based on the J48 Java class.

Behaviour of marine microflora towards antibiotics 1. Sensitivity towards chlortetracycline (CTC)

The sensitivity of 61 cultures of bacteria isolated from fish towards chlortetracycline (CTC) at 5 ppm and 20 ppm levels has been determined on two solid media: sea water agar (SWA) and a distilled water based medium consisting of peptone, beef extract, glucose and NaCI (PBGA). The cultures employed consisted of (i) gram-negative rods of marine origin (Achromobacter, Pseudomonas, Vibrio and Flavobacterium) and (ii) gram positive organisms (Micrococci and Corynebacterium). Depending on the inhibition zone diameter, the order of CTC sensitivity was found to be PseudomonasCTC levels of 5 and 20 ppm. The SWA enhanced the development of resistance in majority of the cultures as compared to PBGA. PBG broth containing CTC at less than 10 ppm exerted a bacteriostatic effect only while that containing 10 ppm or more exerted a bactericidal effect on Achromobacter, Pseudomonas and Micrococci cultures. The significance of these results in fish preservation by CTC is discussed.

Bacterial flora of fresh and iced Indian mackerel (Rastrelliger kanagurta) and its response to chlortetracycline (CTC) treatment

Quantitative and qualitative studies on the bacterial flora of fresh Indian mackerel (Rastrelliger kanagurta) have been made. The total native flora as well as 5 ppm CTC insensitive flora of the fish showed variations with season. About 90% of the fresh fish flora was sensitive to 5 ppm CTC. The natural flora of the fresh fish consisted of Vibrios, Pseudomonas, Achromobacter, Flavobacterium, Corynebacteria, Micrococci, Bacillus and yeasts. In the CTC insensitive flora, Vibrios predominated followed by yeasts. The selection of bacterial genera during storage of the fish in ice and in 5 ppm CTC incorporated ice has also been investigated. At the time of spoilage, Pseudomonas was found to be the dominant flora of the fish stored in both types of ice.

Development of a Novel c-MET-Based CTC Detection Platform.

UNLABELLED: Amplification of the MET oncogene is associated with poor prognosis, metastatic dissemination, and drug resistance in many malignancies. We developed a method to capture and characterize circulating tumor cells (CTC) expressing c-MET using a ferromagnetic antibody. Immunofluorescence was used to characterize cells for c-MET, DAPI, and pan-CK, excluding CD45(+) leukocytes. The assay was validated using appropriate cell line controls spiked into peripheral blood collected from healthy volunteers (HV). In addition, peripheral blood was analyzed from patients with metastatic gastric, pancreatic, colorectal, bladder, renal, or prostate cancers. CTCs captured by c-MET were enumerated, and DNA FISH for MET amplification was performed. The approach was highly sensitive (80%) for MET-amplified cells, sensitive (40%-80%) for c-MET-overexpressed cells, and specific (100%) for both c-MET-negative cells and in 20 HVs. Of 52 patients with metastatic carcinomas tested, c-MET CTCs were captured in replicate samples from 3 patients [gastric, colorectal, and renal cell carcinoma (RCC)] with 6% prevalence. CTC FISH demonstrated that MET amplification in both gastric and colorectal cancer patients and trisomy 7 with gain of MET gene copies in the RCC patient. The c-MET CTC assay is a rapid, noninvasive, sensitive, and specific method for detecting MET-amplified tumor cells. CTCs with MET amplification can be detected in patients with gastric, colorectal, and renal cancers. IMPLICATIONS: This study developed a novel c-MET CTC assay for detecting c-MET CTCs in patients with MET amplification and warrants further investigation to determine its clinical applicability. Mol Cancer Res; 14(6); 539-47. ©2016 AACR.

Variabilidade espacial de MO, P, K e CTC do solo sob diferentes usos e manejos

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Inorganic phosphates in juices from different parts of sugarcane stalks (cultivars ctc 9, ctc 15 and ctc 16)

This study aimed to quantify, the inorganic phosphates in sugarcane juice from nodes and internodes of three sugarcane cultivars. The experimental design was a randomized block in factorial scheme 3x2. The main treatments were three sugarcane cultivars and two parts of the stalk (nodes and internodes). The inorganic phosphates contents were determined for each treatment. The results were subjected to variance analysis by the F test; when statistically significant, means were compared by the Tukey test at 5% probability. It is concluded that the three cultivars (CTC 9, CTC 16 and CTC 15) showed similar values regarding the content of inorganic phosphates present in the juice, and these values are considered adequate for a good performance in juice clarification. For the different parts of the stem, differences were observed in the levels of the nutrient studied, which showed a higher concentration in the node than in the internode.

Desenho e Análise de Processo de Candidatura ao P.2020: estudo de caso via CTC/GP, do IPL

Melhorar o desempenho organizacional, através do (re)desenho dos processos de negócios, é uma premente e desafiadora questão para promover a eficiência e eficácia organizacional. O presente trabalho aborda a Gestão de Processos de Negócio e conceitos que lhe estão subjacente, enquanto ferramenta ao dispor da gestão para planear, modelar, executar, analisar, controlar e melhorar o operacional do processo. Para tal, recorreu-se a um estudo de caso, realizado no Centro de Transferência e Valorização de Conhecimento e Gabinete de Projetos (CTC/GP), do Instituto Politécnico de Leiria (IPL), referente ao processo de candidatura de projetos em co-promoção, no novo quadro comunitário. A escolha deste estudo de caso prendeu-se com o facto de o CTC/GP ser uma unidade orgânica do IPL que, entre outras atividades, articula a academia com o tecido empresarial da região de Leiria, contribuindo para a criação de uma economia de valor acrescentado, suportada por produtos exportáveis e competitivos ao nível da qualidade. Por outro lado, o processo de candidatura de projetos em co-promoção é um processo de grande rendibilidade para o instituto. A grande contribuição deste trabalho foi, por um lado, munir a equipa de um fluxograma do supra citado processo, numa ferramenta de fácil utilização e premiável às mudanças de paradigma e, por outro, apresentar várias questões de partida para investigações futuras.

The Get Marketer Challenge Innovation: Challenging students using a tournament style competition

This paper presents an assessment innovation which used a tournament style competition to challenge and engage first year marketing students. The course-wide competition required student teams to solve real-world marketing problems for industry sponsors. Student feedback reflects enjoyment of the task and the competition, with students welcoming the opportunity to put theory into practice. Student attendance in the lectures and tutorials involving team presentations was improved. This structure can be adapted for any course with large enrolments. We recommend that instructors adopting a tournament structure consider grading mechanisms that promote equal effort and additional rewards, such as bonus marks, for teams progressing in subsequent rounds.