METHODS: Fresh specimens of chondracanthids were collected from the buccal cavity of two species of deep-sea fishes (fish hosts were frozen), Chaunax abei Le Danois, 1978 (Lophiiformes: Chaunacidae) and Setarches longimanus (Alcock, 1894) (Perciformes: Setarchidae), caught at a depth of 212 m in Suruga Bay, Japan (34° 37'48.87″ N, 138° 43'2.958″ E). Both the species are described and illustrated based on ovigerous females.
RESULTS: The genus Avatar gen. nov. can readily be distinguished from all other chondracanthid genera by the following combination of features: cephalothorax slightly wider than long with anterior pair of large and posterior pair of small lateral lobes, and two pairs of ventro-lateral processes; the very posteriormost part of the first pedigerous somite contributes to the neck; cylindrical trunk with two pairs of blunt proximal fusiform processes; antennule with small knob terminally; antenna bearing distal endopodal segment; labrum protruding ventrally; two pairs of biramous legs each with 2-segmented rami. Kokeshioides gen. nov. has the following combinations of features that distinguish it from other chondracanthid genera: body flattened, without lateral processes; cephalothorax much wider than long, with paired anterolateral and posterolateral lobes, folded ventrally; the very posteriormost part of the first pedigerous somite contributes to the neck; mandible elongate; legs unique, heavily sclerotized, represented by two pairs of acutely pointed processes.
CONCLUSION: With the addition of two new genera presently reported, the family Chondracanthidae currently includes 52 valid genera. Among the described genera Avatar gen. nov. seems to be very primitive, while Kokeshioides gen. nov. is highly advanced. The deduced evolutionary history of chondracanthid genera is also discussed.
RESULT: Images of four monogenean species namely Sinodiplectanotrema malayanus, Trianchoratus pahangensis, Metahaliotrema mizellei and Metahaliotrema sp. (undescribed) were used to develop an automated technique for identification. K-nearest neighbour (KNN) was applied to classify the monogenean specimens based on the extracted features. 50% of the dataset was used for training and the other 50% was used as testing for system evaluation. Our approach demonstrated overall classification accuracy of 90%. In this study Leave One Out (LOO) cross validation is used for validation of our system and the accuracy is 91.25%.
CONCLUSIONS: The methods presented in this study facilitate fast and accurate fully automated classification of monogeneans at the species level. In future studies more classes will be included in the model, the time to capture the monogenean images will be reduced and improvements in extraction and selection of features will be implemented.