Carukia barnesi (Cb), Malo kingi (Mk) and Chironex fleckeri (Cf) are dangerous Australian box jellyfish species that provoke distinct and not well understood envenomation syndromes. Specifically, Cb and Mk are small, rare and able to induce a systemic syndrome of generalised muscle pain and catecholamine excess termed “Irukandji syndrome”; Cf has been widely regarded as one of the most venomous organisms in the animal kingdom causing severe sting site pain combined with potentially lethal cardiotoxicity. Building on past studies of major chirodropid and carybdeid species venoms, this study compared the utility of various cubozoan specific antibody reagents to better define the relationships between venom proteins from both exemplar Irukandji species (Cb and Mk) and the archetype C. fleckeri box jellyfish. With the aid of commercial ovine derived Cf-specific antivenom, mouse antibodies reactive to Cb and Mk and rabbit antibodies specific to two Cf toxins (CfTX-1 and 2), as well as human sera, the cross-reactivity of jellyfish species-specific polyclonal antibodies against these three cubozoan venoms was investigated. Immunoblot assays revealed distinc levels of immune recognition across the three species, indicating that Mk specific reagents may bind both Irukandji and Cf venoms. Irukandji venom appears to be antigenic with the exception of a few proteins in the range of 43/46 kDa maybe homologous to CfTX-1 and 2. The implications of such antibody binding for future antivenom development require further investigation.

Sign Language Recognition (SLR) aims to bridge speech-impaired and general communities by recognizing signs from given videos. Researchers still face challenges developing efficient SLR systems because of the video’s complex background, light illumination, and subject structures. Recently many researchers developed a skeleton-based sign language recognition system to overcome the subject and background variation of hand gesture signs. However, skeleton-based SLR is still under exploration due to the lack of information and annotations on hand key points. More recently, researchers included body and face information with the hand gesture for the SLR, but their performance and efficiency are unsatisfactory. We proposed a Multi-Stream Graph-based Deep Neural Network (SL-GDN) for a skeleton-based SLR system to overcome the problems. The main purpose of the proposed SL-GDN approach is to improve the efficiency and performance of the SLR system with a low computational cost based on the human body pose in the form of 2D landmark locations. In the procedure, firstly, we constructed a skeleton graph based on the selected 27 whole-body key points among 67 key points to solve the inefficiency problems. Then we proposed multi-stream SL-GDN to extract features from the whole-body skeleton graph for four streams. Finally, we concatenated the four different features and applied a classification module to refine the feature and recognize corresponding sign classes. Our data-driven and graph construction method increases the system’s flexibility and brings high generability to adapt various data samples. We used three large-scale benchmark SLR datasets to evaluate the proposed model: WLASL, AUTSL and CSL. The demonstrated performance accuracy table proved the superiority of the proposed model, and we believe this will be considered a great invention in the SLR domain.