Search

Some people in society have impaired cognitive senses like speech and hearing where they cannot behave like normal people. It is quite a complex task for abnormal people to understand as well as recognize the gestures of normal people. This initiates to delve into the study of review of Sign Language Recognition (SLR), in specific to, machine learning techniques. In this work, a review of machine learning techniques based on SLR were portrayed. Several studies related to ML papers have been collected and discussed with their merits and demerits. Thus, the observation dictates that recognition of hand gesture is still a challenging task. There are two sorts of gesture recognition, namely, static and dynamic gesture recognition. Static gesture recognition is developed from the dynamic gesture recognition. Almost, Convolutional Neural Networks (CNNs), Hidden Markov Models (HMM) and Histogram analysis were used as recognition classifiers for sign language. Dynamic gesture recognition process operates on tracking the centroid of hand gesture. It changes the visual information in time basis. Henceforth, study on dynamic gesture recognition needs to be more focused using Machine learning techniques. Comparative analysis is done in perspectives of significance of segmentation models, feature extraction and vision-based approaches. [ABSTRACT FROM AUTHOR]

Nowadays in the era of automation, the postal automation system is one of the major research areas. Developing a postal automation system for a nation like India is much troublesome than other nations because of India's multi-script and multi-lingual behavior. This proposed work will be helpful in the postal automation of district names of Punjab (state) written in Gurmukhi script, which is the official language of the state in North India. For this, a holistic approach i.e. a segmentation-free technique has been used with the help of Convolutional Neural Network (CNN) and Deep learning (DL). For the purpose of recognition, a database of 22 000 images (samples) which are handwritten in Gurmukhi script for all the 22 districts of Punjab is prepared. Each sample is written two times by 500 different writers generating 1000 samples for each district name. Two CNN models are proposed which are named as ConvNetGuru and ConvNetGuruMod for the purpose of recognition. Maximum validation accuracy achieved by ConvNetGuru is 90% and ConvNetGuruMod is 98%. [ABSTRACT FROM AUTHOR]

A disaster is a devastating incident that causes a serious disruption of the functions of a community. It leads to loss of human life and environmental and financial losses. Natural disasters cause damage and privation that could last for months and even years. Immediate steps need to be taken and social media platforms like Twitter help to provide relief to the affected public. However, it is difficult to analyze high-volume data obtained from social media posts. Therefore, the efficiency and accuracy of useful data extracted from the enormous posts related to disaster are low. Satellite imagery is gaining popularity because of its ability to cover large temporal and spatial areas. But, both the social media and satellite imagery require the use of automated methods to avoid the errors caused by humans. Deep learning and machine learning have become extremely popular for text and image classification tasks. In this paper, a review has been done on natural disaster detection through information obtained from social media and satellite images using deep learning and machine learning. [ABSTRACT FROM AUTHOR]

Background: Akin to cervical squamous intra-epithelial neoplasia (CIN), anal squamous intra-epithelial lesion (a-SIL) is attributed to persistent infection with high-risk human papilloma virus infection. Amplification of human telomerase reverse transcriptase (hTERT) gene and aneuploidy are known to correlate with CIN evolution. It is plausible that the underlying genetic events in a-SIL are similar. We conducted this cross-sectional analytical study with the objective of determining expression of hTERT gene expression and chromosome 7, as marker of cell ploidy in a-SIL. Methods: Conventional anal cytology was performed in 86 adult consenting subjects with history of receptive anal intercourse (RAI) and 4 controls without history of RAI. Cases with a-SIL and controls were subjected to fluorescent in-situ hybridization (FISH) to evaluate hTERT gene and chromosome 7 expression, as marker of cell ploidy. Results were expressed as number of abnormal nuclei (≥3 respective signals), maximum degree of amplification, mean signals/nucleus and proportion of cases showing abnormal nuclei. Results: Twenty cases showed a-SIL; with 15 atypical squamous cells of undetermined significance (ASCUS), 3 low grade squamous intra-epithelial lesion (LSIL) and 2 cases of high-risk cytology. Expression of both hTERT gene and chromosome 7 increased from controls to ASCUS to LSIL with concomitant increase in proportion of cases having abnormal hTERT gene and chromosome 7 expression. Conclusions: Positive association of hTERT gene with a-SIL suggests its possible role in evolution of anal squamous abnormalities. Increase in chromosome 7 also correlated positively with a-SIL. These findings corroborate the similarities between squamous carcinogenesis in CIN and a-SIL. [ABSTRACT FROM AUTHOR]

Background: In India, sexuality not confirming to hetero‑conjugal and peno‑vaginal norm is abhorred and discriminated against. Individuals engaging in Receptive Anal Intercourse (RAI) are marginalized. Reappraisal of their sexual health conditions is likely to promote inclusive health care. Methods: Eighty‑five consenting adults with RAI history were recruited from a tertiary care hospital in Delhi. Clinico‑demographic data was noted and anal cytology samples were reported by Bethesda 2014 terminology. Results: There were 29 transgenders (TGs), 51 males (31 bisexual) and five females. Fifty‑four subjects were Human Immunodeficiency Virus (HIV) infected (22 TGs, 31 males (17 bisexual) and one female) and 52 were receiving anti‑retroviral treatment (ART). Thirty‑one subjects had anal warts (6 TGs, 20 males, five females). Anal cytology revealed squamous intra‑epithelial lesions (SIL) in 20 (5 TGs, 13 males, two females). TGs had significantly risker sexual practices than homosexual males, bisexual males and females, with consistently earlier age of first RAI exposure and frequent childhood (≤16 years) RAI experience compared to homosexual males, bisexual males and females, even after stratification by HIV status, warts and SIL. Conclusions: TGs had the highest sexual health risk profile including higher frequency of HIV infection compared to other subjects with RAI history. Bisexuality was common; their risk profile was variably lower than homosexual males. Mindfulness of above is likely to help overcome barriers to health care access and promote compassionate approach at all levels including primary care physicians. [ABSTRACT FROM AUTHOR]

Chromosomes are the genetic information carriers. Any modification to the structure or the number of chromosomes results in a medical condition termed as genetic defect. In order to uncover the genetic defects, the chromosomes are imaged during the cell division process. The images thus generated are termed as metaspread images and are used for identifying the genetic defects. It has been observed that the metaspread images generally suffer from intensity inhomogeneity and the chromosomes are also present in varied orientations, and as a result finding genetic defects from such images is a tedious process. Therefore, cytogeneticists manually select the images that can be used for the purpose of uncovering the genetic defects and the generation of the karyotype. In the proposed approach, a novel method is being presented using DenseNet architecture of the convolutional neural networks-based classifier, which classifies the human metaspread images into two distinct categories, namely, analyzable and non-analyzable based on the orientation of the chromosomes present in the metaspread images. This classification process will help to select the most prominent metaspread images for karyotype generation that has least amount of touching and overlapping chromosomes. The proposed method is novel in comparison to the earlier methods as it works on any type of image, be it G band images, MFISH images or the Q-banded images. The proposed method has been trained by using a ground truth of 156 750 metaspread images. The proposed classifier has been able to achieve an error rate of 1.46%. [ABSTRACT FROM AUTHOR]