Latitudinal variation in seagrass communities with special emphasis on post-tsunami status in the Andaman and Nicobar archipelago, India.

We studied spatial variation in seagrass communities in the Andaman and Nicobar archipelago (ANI), India using latitude as a surrogate variable. We classified the ANI into five latitudinally distinct island groups: North & Middle Andaman, Ritchie's archipelago, South Andaman, Little Andaman, and the Nicobar archipelago. We evaluated the Importance Value Index (IVI) for species to determine the ecologically dominant seagrasses within each Island group. Later, we related our findings to investigate the three decadal pre- and post-tsunami status of seagrass habitats in the ANI which were severely impacted by the Indian Ocean tsunami of 2004. Six of the 11 observed species, such as Halophila ovalis, Halophila beccarii, Halophila minor, Halodule pinifolia, Thalassia hemprichii, and Cymodocea rotundata, dominated the seagrass population among all island groups. Seagrass composition significantly varied across the five investigated latitudinal gradients. Seagrass communities in 'Ritchie's Archipelago and Nicobar' and 'South Andaman and Little Andaman' revealed the highest and lowest variation. Further, Ritchie's Archipelago and Nicobar had the highest species richness (n = 10), followed by North & Middle Andaman (n = 8), and the lowest in South and Little Andaman (n = 6). Despite similar species richness and composition, Nicobar contributed to the highest seagrass coverage compared to the lowest recorded in the Ritchie's Archipelago. Our observations on the re-colonization of disturbed areas by early successional and historical species suggest recovery of the seagrass population in the ANI post-disturbance. Lastly, co-variates associated with latitude as a surrogate warrant further investigation.

RHSOFS: Feature Selection Using the Rock Hyrax Swarm Optimization Algorithm for Credit Card Fraud Detection System.

In recent years, detecting credit card fraud transactions has been a difficult task due to the high dimensions and imbalanced datasets. Selecting a subset of important features from a high-dimensional dataset has proven to be the most prominent approach for solving high-dimensional dataset issues, and the selection of features is critical for improving classification performance, such as the fraud transaction identification process. To contribute to the field, this paper proposes a novel feature selection (FS) approach based on a metaheuristic algorithm called Rock Hyrax Swarm Optimization Feature Selection (RHSOFS), inspired by the actions of rock hyrax swarms in nature, and implements supervised machine learning techniques to improve credit card fraud transaction identification approaches. This approach is used to select a subset of optimal relevant features from a high-dimensional dataset. In a comparative efficiency analysis, RHSOFS is compared with Differential Evolutionary Feature Selection (DEFS), Genetic Algorithm Feature Selection (GAFS), Particle Swarm Optimization Feature Selection (PSOFS), and Ant Colony Optimization Feature Selection (ACOFS) in a comparative efficiency analysis. The proposed RHSOFS outperforms existing approaches, such as DEFS, GAFS, PSOFS, and ACOFS, according to the experimental results. Various statistical tests have been used to validate the statistical significance of the proposed model.

Semantic Analysis and Topic Modelling of Web-Scrapped COVID-19 Tweet Corpora through Data Mining Methodologies.

The evolution of the coronavirus (COVID-19) disease took a toll on the social, healthcare, economic, and psychological prosperity of human beings. In the past couple of months, many organizations, individuals, and governments have adopted Twitter to convey their sentiments on COVID-19, the lockdown, the pandemic, and hashtags. This paper aims to analyze the psychological reactions and discourse of Twitter users related to COVID-19. In this experiment, Latent Dirichlet Allocation (LDA) has been used for topic modeling. In addition, a Bidirectional Long Short-Term Memory (BiLSTM) model and various classification techniques such as random forest, support vector machine, logistic regression, naive Bayes, decision tree, logistic regression with stochastic gradient descent optimizer, and majority voting classifier have been adapted for analyzing the polarity of sentiment. The effectiveness of the aforesaid approaches along with LDA modeling has been tested, validated, and compared with several benchmark datasets and on a newly generated dataset for analysis. To achieve better results, a dual dataset approach has been incorporated to determine the frequency of positive and negative tweets and word clouds, which helps to identify the most effective model for analyzing the corpora. The experimental result shows that the BiLSTM approach outperforms the other approaches with an accuracy of 96.7%.

A low-cost solution for documenting distribution and abundance of endangered marine fauna and impacts from fisheries.

Fisheries bycatch is a widespread and serious issue that leads to declines of many important and threatened marine species. However, documenting the distribution, abundance, population trends and threats to sparse populations of marine species is often beyond the capacity of developing countries because such work is complex, time consuming and often extremely expensive. We have developed a flexible tool to document spatial distribution and population trends for dugongs and other marine species in the form of an interview questionnaire supported by a structured data upload sheet and a comprehensive project manual. Recognising the effort invested in getting interviewers to remote locations, the questionnaire is comprehensive, but low cost. The questionnaire has already been deployed in 18 countries across the Indo-Pacific region. Project teams spent an average of USD 5,000 per country and obtained large data sets on dugong distribution, trends, catch and bycatch, and threat overlaps. Findings indicated that >50% of respondents had never seen dugongs and that 20% had seen a single dugong in their lifetimes despite living and fishing in areas of known or suspected dugong habitat, suggesting that dugongs occurred in low numbers. Only 3% of respondents had seen mother and calf pairs, indicative of low reproductive output. Dugong hunting was still common in several countries. Gillnets and hook and line were the most common fishing gears, with the greatest mortality caused by gillnets. The questionnaire has also been used to study manatees in the Caribbean, coastal cetaceans along the eastern Gulf of Thailand and western Peninsular Malaysia, and river dolphins in Peru. This questionnaire is a powerful tool for studying distribution and relative abundance for marine species and fishery pressures, and determining potential conservation hotspot areas. We provide the questionnaire and supporting documents for open-access use by the scientific and conservation communities.