Search

Fake or misleading information detection is attracting researchers from all around the world in recent years as both society and the political world are greatly influenced by it. Moreover, various popular social media sites such as Twitter, Facebook, Instagram, etc. have accelerated the increase in the dissemination of rumors, false cures, conspiracy theories in the forms of posts, articles, videos, URLs during the COVID-19 pandemic. Thus there is an extensive need to find new techniques to verify or check the reliability of the online contents, which has inspired us to conduct this research to automatically detect misleading information. Our main aim is to create a three-level voting model to categorize the information into two classes: ‘real’ or ‘misleading’. Five conventional mining algorithms and three ensemble models have been deployed with two distinct feature extraction techniques accompanying multiple sets of n-gram profiles on a benchmark dataset. Our research outcome shows that the Linear Support Vector Machine algorithm and Bagging ensemble model classifier have carried out significantly in recognizing misleading information which has been surpassed by our proposed novel three-level voting scheme. Our proposed model yields the best performance using TF-IDF for feature extraction with 96% accuracy.

Research on cyberbullying detection is gaining increasing attention in recent years as both individual victims and societies are greatly affected by it. Moreover, ease of access to social media platforms such as Facebook, Instagram, Twitter, etc. has led to an exponential increase in the mistreatment of people in the form of hateful messages, bullying, sexism, racism, aggressive content, harassment, toxic comment etc. Thus there is an extensive need to identify, control and reduce the bullying contents spread over social media sites, which has motivated us to conduct this research to automate the detection process of offensive language or cyberbullying. Our main aim is to build single and double ensemble-based voting model to classify the contents into two groups: ‘offensive’ or ‘non-offensive’. For this purpose, we have chosen four machine learning classifiers and three ensemble models with two different feature extraction techniques combined with various n-gram analysis on a dataset extracted from Twitter. In our work, Logistic Regression and Bagging ensemble model classifier have performed individually best in detecting cyberbullying which has been outperformed by our proposed SLE and DLE voting classifiers. Our proposed SLE and DLE models yield the best performance of 96% when TF-IDF (Unigram) feature extraction is applied with K-Fold cross-validation.

Squamous cell carcinoma (SCC) of external auditory canal (EAC) is extremely rare. Although surgery followed by radio (chemo) therapy is the contemporary standard of care, radical radio (chemo) therapy has been successfully used as an anatomical as well as functional organ preservation modality. Radical brachytherapy is a promising alternative in early-stage SCC-EAC. We report our initial experience on the feasibility of using commercially available plastic earbud along with soft flexible earpiece of stethoscope as a radioactive source career applicator of remote after-loading high-dose rate radioactive sources (Ir192).

Ipsilateral breast or chest wall recurrence remains one the most common site of disease recurrence and significantly increases the morbidity and mortality. The current standard of care for ipsilateral breast tumour recurrence has been mastectomy. However, various recent studies showed that there is feasibility of repeat breast conservation surgery with reirradiation. Reirradiation in breast cancer is complicated approach. Many physicians are reluctant to reirradiate breast with restricted data available. This paper will review the current literature on reirradiation for locally recurrent breast cancer

In this era of technology-based training and education, audio and video teletraining has become an effective tool for Distance Education. This article describes the potential benefits of teletraining, needs assessment for teletraining decisions, and the teletraining design techniques to deliver complex training systems and educational programs to enhance distance learning in remote education/training sites in a cost-effective manner.

A preliminary checklist of Polygalaceae in Indian subcontinent has been prepared on the basis of primary observations of different taxa belonging to this family in wild habitats and on secondary observations based on examined herbarium specimens and taxonomic literature. On the Indian subcontinent (comprising Bangladesh, Bhutan, Myanmar, Nepal, Pakistan, Sri Lanka and India), the family Polygalaceae is poorly represented (6.37% of global distribution). The present paper deals with a brief review of distribution, phytoendemism, possible fossil ancestry, economic potential and survival threat on existing taxa. The present status of phytoendemism of Polygalaceae in Indian subcontinent (35.29% in 2002-2007) has been compared to the data of previous investigations (21.87% in 1939-1940) done in the XX century. The increasing rate of endemism either indicates towards increasing number of endemic taxa or decreasing span of distribution of pan-endemic taxa belonging to this family. For a better understanding of the functional aspects of species dynamics the percentage of rate of endemism of a particular group of plants has been used as key index here. The growing on same geographical location has been recorded in different time intervals and has further been considered to narrate the academic studies in form of qualitative economic appraisal of renewable resources for ensuring its conservation sustainable utilization. Una revisión preliminar de Polygalaceae en el subcontinente indio ha sido preparada sobre la base de la observación de diferentes especies pertenecientes a esta familia en un hábitat natural y el análisis de especímenes de herbario y de literatura taxonómica. En el subcontinente indio (Bangladesh, Bhutan, Myanmar, Nepal, Pakistan, Sri Lanka e India) la familia Polygalaceae está pobremente representada (6,37% de la distribución global). Este artículo trata la distribución, fitoendemismo, posibles fósiles ancestrales, potencial económico y riesgos de supervivencia de especies existentes. El estado actual de fitoendemismo en Polygalaceae en el subcontinente indio (35,29% en 2002-2007) ha sido comparado con la información de investigaciones anteriores (21,87% en 1939-1940) finalizadas en el siglo XX. El aumento de la tasa de endemismo indica un incremento en el número de especies endémicas o un lapso de decrecimiento de especies pan-endémicas pertenecientes a esta familia. Para una mejor comprensión de los aspectos funcionales del porcentaje dinámico de las especies, la tasa de endemismo de un grupo determinado ha sido usada aquí como un indicador clave. El crecimiento en una misma zona geográfica ha sido registrado en intervalos de tiempo diferente y posteriormente es considerado para narrar los estudios académicos en la forma de presupuestos económicos de recursos renovables para asegurar su conservación y uso sostenible.

This article provides information about the prospects and limitations of the Artificial Intelligence and Expert Systems as they relate to training systems and educational programs. The article describes the potential benefits of expert systems and how it can be gainfully employed in training environment, industry, and business management to perform complex jobs. The limitations of the applications of the Artificial Intelligence are discussed as some tend to believe that human mind and computers think alike and AI machines can function like a real expert in every aspect of training and education.