Length-weight relationships of fishes from tributaries of the Volta River, Ghana Part 1: Analysis of pooled data sets

The parameters a and b of length-weight relationships of the form W = a L super(b) were estimated for 45 fish species sampled in the Oti, Pru and Black Volta rivers, Ghana. Also, the slope and intercepts of regressional enabling standard to total length conversions were estimated for each of these same species. The estimates of b, which ranged from 2.35 to 3.27 have a mean of 2.98, with a s.e. of 0.036. These results are complemented with a brief discussion of the need for data summaries such as presented in this article.

Differences in Dolphin Mortality Rates in Night and Day Sets for the U.S. Eastern Tropical Pacific Tuna Purse Seine Fishery

Because dolphins sometimes travel with yellowfin tuna, Thunnus albacares, in the eastern tropical Pacific (ETP), purse seiners use the dolphins to locate and capture tuna schools. During the process of setting the purse seine nets, dolphins often become entangled and drown before they can be released. Data for the U.S. purse seine fleet in the ETP during 1979-88 show that dolphin mortality rates in sets made during the night are higher than mortality rates in sets made during the day. Even with efforts to reduce nightset mortality rates through the use of high intensity floodlights, night set mortality rates remain higher. The data are also used to simulate a regulation on the fishery aimed at eliminating night sets and show that dolphin mortality rates would decrease.

On-line learning of mutually orthogonal subspaces for face recognition by image sets.

We address the problem of face recognition by matching image sets. Each set of face images is represented by a subspace (or linear manifold) and recognition is carried out by subspace-to-subspace matching. In this paper, 1) a new discriminative method that maximises orthogonality between subspaces is proposed. The method improves the discrimination power of the subspace angle based face recognition method by maximizing the angles between different classes. 2) We propose a method for on-line updating the discriminative subspaces as a mechanism for continuously improving recognition accuracy. 3) A further enhancement called locally orthogonal subspace method is presented to maximise the orthogonality between competing classes. Experiments using 700 face image sets have shown that the proposed method outperforms relevant prior art and effectively boosts its accuracy by online learning. It is shown that the method for online learning delivers the same solution as the batch computation at far lower computational cost and the locally orthogonal method exhibits improved accuracy. We also demonstrate the merit of the proposed face recognition method on portal scenarios of multiple biometric grand challenge.