Unmasking deception: a CNN and adaptive PSO approach to detecting fake online reviews.

Online reviews play a critical role in modern word-of-mouth communication, influencing consumers' shopping preferences and purchase decisions, and directly affecting a company's reputation and profitability. However, the credibility and authenticity of these reviews are often questioned due to the prevalence of fake online reviews that can mislead customers and harm e-commerce's credibility. These fake reviews are often difficult to identify and can lead to erroneous conclusions in user feedback analysis. This paper proposes a new approach to detect fake online reviews by combining convolutional neural network (CNN) and adaptive particle swarm optimization with natural language processing techniques. The approach uses datasets from popular online review platforms like Ott, Amazon, Yelp, TripAdvisor, and IMDb and applies feature selection techniques to select the most informative features. The paper suggests using attention mechanisms like bidirectional encoder representations from transformers and generative pre-trained transformer, as well as other techniques like Deep contextualized word representation, word2vec, GloVe, and fast Text, for feature extraction from online review datasets. The proposed method uses a multimodal approach based on a CNN architecture that combines text data to achieve a high accuracy rate of 99.4%. This outperforms traditional machine learning classifiers in terms of accuracy, recall, and F measure. The proposed approach has practical implications for consumers, manufacturers, and sellers in making informed product choices and decision-making processes, helping maintain the credibility of online consumer reviews. The proposed model shows excellent generalization abilities and outperforms conventional discrete and existing neural network benchmark models across multiple datasets. Moreover, it reduces the time complexity for both training and testing.

Controlled release of antimicrobial Cephalexin drug from silica microparticles.

Release of antimicrobial drugs in a controlled fashion for extended duration of time has been investigated for long. Such controlled-drug-releasing materials show promising applications in medicinal bandages. Along with antimicrobial agents, one could also incorporate other therapeutic drugs, to make such bandages more versatile. In this context, silica micro particles were synthesized using direct reduction method, in which the synthesis was done in the presence of Cephalexin. Cephalexin was chosen as an antimicrobial candidate. The morphological characterization shows formation of monodispersed, silica microparticles of ~200nm in size. The FTIR spectroscopy shows weak interaction of the drug molecule at its hydroxide (OH) site with oxygen ions on the silica surface. Upon conjugation, the UV-vis spectroscopy shows persistence of the Cephalexin signature, especially its R group, confirming its antimicrobial activity even after conjugation. Loading studies reveal 12% Cephalexin loading on silica. The antimicrobial studies were done on three micro-organisms, namely, Staphylococcus aureus, Bacillus subtilis and Escherichia coli. Using zone-of-inhibition studies, it was found that E. coli, did not respond to the delivery of Cephalexin either directly or via microparticles. However, for both S. aureus and B. subtilis, the particles showed controlled release of Cephalexin for the duration of 48h and continued maintenance and even increase in the zone of inhibition. This work demonstrates an effective protocol to prepare antimicrobial patches for controlled drug delivery.

Multiple origins of the mtDNA 9-bp deletion in populations of South India.

The origins and genetic affinities of the more than 500 tribal populations living in South Asia are widely disputed. This may reflect differential contributions that continental populations have made to tribal groups in South Asia. We assayed for the presence of the intergenic COII/tRNALys 9-bp deletion in human mtDNA in 646 individuals from 12 caste and 14 tribal populations of South India and compared them to individuals from Africa, Europe, and Asia. The 9-bp deletion is observed in four South Indian tribal populations, the Irula, Yanadi, Siddi, and Maria Gond, and in the Nicobarese. Length polymorphisms of the 9-bp motif are present in the Santal, Khonda Dora, and Jalari, all of whom live in a circumscribed region on the eastern Indian coast. Phylogenetic analyses of mtDNA control region sequence from individuals with the 9-bp deletion indicate that it has arisen independently in some Indian tribal populations. Other 9-bp deletion haplotypes are likely to be of Asian and African origin, implying multiple origins of the 9-bp deletion in South India. These results demonstrate varying genetic affinities of different South Indian tribes to continental populations and underscore the complex histories of the tribal populations living in South Asia.