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.

Strategy on International Fisheries Research: an update

The Strategy on International Fisheries Research's activities on information and aquaculture in Asia, SubSaharan Africa, Latin and North America are presented.

Reducing feed costs in semi-intensive finfish culture: an update on mixed feeding schedules and an idea for enhancing endogenous food supply in ponds

Some interesting ideas on improving the cost-effectiveness of feeding in semi-intensive finfish aquaculture are presented.

Length-weight relationship of fishes from coral reefs and lagoons of New Caledonia: an update

Length-weight relationships of 316 reef and lagoon fish from New Caledonia (SW Pacific Ocean) belonging to 68 families are computed. A total of 43,750 individuals was used for this purpose. Fish were sampled by different techniques such as rotenone poisoning, handline and bottom longline fishing, gill and trammel nets, and trawling in various isotopes (coral reefs, lagoon bottoms and mangroves).

Growth, mortality and recruitment of Nile perch Lates niloticus (L. Centropomidae) in the Nyanza Gulf of Lake Victoria: an evaluation update

A reassessment of the estimates of growth, mortality and recruitment patterns of Nile Perch, Lates niloticus was made based on data from commercial landings collected during the Catch Assessment Survey Programme. Two sets of length frequency data, one each from beach seining and hook and line fisheries, were analyzed. Values of L8 = 169 and 230 (cm TL) and K= 0.18 yr-1 and 0.195 yr-1 were obtained. The total mortality estimates from the catch curve analysis were Z = 0.72 yr-1 and 0.94 yr-1, respectively, with a natural mortality M of about 0.35 for a mean environmental temperature of 27oC. The highest peak for recruitment was in November, December and January with a minor one in June, indicating recruitment of two cohorts per year. These results are discussed and compared to previously available information on L. niloticus in Lake Victoria.