To find out what other people think has been an essential part of information-gathering behaviors. And in the case of movies, the movie reviews can provide an intricate insight into the movie and can help decide whether it is worth spending time on. However, with the growing amount of data in reviews, it is quite prudent to automate the process, saving on time. Sentiment analysis is an important field of study in machine learning that focuses on extracting information of subject from the textual reviews. The area of analysis of sentiments is related closely to natural language processing and text mining. It can successfully be used to determine the attitude of the reviewer in regard to various topics or the overall polarity of the review. In the case of movie reviews, along with giving a rating in numeric to a movie, they can enlighten us on the favorableness or the opposite of a movie quantitatively; a collection of those then gives us a comprehensive qualitative insight on different facets of the movie. Opinion mining from movie reviews can be challenging due to the fact that human language is rather complex, leading to situations where a positive word has a negative connotation and vice versa. In this study, the task of opinion mining from movie reviews has been achieved with the use of neural networks trained on the "Movie Review Database" issued by Stanford, in conjunction with two big lists of positive and negative words. The trained network managed to achieve a final accuracy of 91%.
Character recognition from handwritten images has received greater attention in research community of pattern recognition due to vast applications and ambiguity in learning methods. Primarily, two steps including character recognition and feature extraction are required based on some classification algorithm for handwritten digit recognition. Former schemes exhibit lack of high accuracy and low computational speed for handwritten digit recognition process. The aim of the proposed endeavor was to make the path toward digitalization clearer by providing high accuracy and faster computational for recognizing the handwritten digits. The present research employed convolutional neural network as classifier, MNIST as dataset with suitable parameters for training and testing and DL4J framework for hand written digit recognition. The aforementioned system successfully imparts accuracy up to 99.21% which is higher than formerly proposed schemes. In addition, the proposed system reduces computational time significantly for training and testing due to which algorithm becomes efficient.
Human papilloma virus (HPV) is a serious threat to human life globally with over 100 genotypes including cancer causing high risk HpVs. Study on protein interaction maps of pathogens with their host is a recent trend in 'omics' era and has been practiced by researchers to find novel drug targets. in current study, we construct an integrated protein interaction map of HpV with its host human in Cytoscape and analyze it further by using various bioinformatics tools. We found out 2988 interactions between 12 HPV and 2061 human proteins among which we identified MYLK, CDK7, CDK1, CDK2, JAK1 and 6 other human proteins associated with multiple viral oncoproteins. The functional enrichment analysis of these top-notch key genes is performed using KEGG pathway and Gene Ontology analysis, which reveals that the gene set is enriched in cell cycle a crucial cellular process, and the second most important pathway in which the gene set is involved is viral carcinogenesis. Among the viral proteins, E7 has the highest number of associations in the network followed by E6, E2 and E5. We found out a group of genes which is not targeted by the existing drugs available for HpV infections. it can be concluded that the molecules found in this study could be potential targets and could be used by scientists in their drug design studies. Human papilloma virus (HPV) is associated with approximately 5% of all human cancers affecting 0.6 million people worldwide with cervical, anal, oropharyngeal, penile and vulvovaginal cancers 1-3. Among these cancers, cervical cancer ranks 4th in affecting women worldwide 4 while in developing countries it ranks second 5. According to World Health Organization (WHO) current factsheets, there are more than 100 genotypes of HPV, out of which 14 strains are high-risk. The most talked about high-risk HPV strains are HPV 6, 11, 16, 18, 31, 33, 35, 45, 52 and 58 with type 16 and 18 responsible for 70% of cervical cancer cases 6-8. HPV is a serious threat to human life and it is causing 250,000 deaths annually, among which 85% of cases are occurring in low and middle-income countries 9. HPV is a small ~8 kb in size, non-enveloped circular dsDNA virus 5,10. The HPV genome encodes 8 proteins among which 2 are structural viral capsid proteins (L1 and L2) while 6 are non-structural viral proteins (E1, E2, E4, E5, E6, E7) 10,11. Besides these 8 proteins, there are a few other macromolecules found in literature which are actually the transcripts made by the fusion of two existing HPV proteins. E8∧E2, a transcript, is created by the fusion of E8 with carboxy terminal of E2 12 , and E1∧E4 is generated by the fusion of E1 to the Open Reading Frame (ORF) of E4 13. Protein interaction network provides a plethora of information when it comes to virus-host relationship because viruses entirely depend upon the host factors for their survival 14,15. Viruses tend to regulate host biological processes by manipulating its cell proteome. Researchers have been using network biology for designing novel antiviral drug therapies 16. ...
Optical character recognition is gaining immense importance in the domain of deep learning. With each passing day, handwritten digits (0–9) data are increasing rapidly, and plenty of research has been conducted thus far. However, there is still a need to develop a robust model that can fetch useful information and investigate self-build handwritten digit data efficiently and effectively. The convolutional neural network (CNN) models incorporating a sigmoid activation function with a large number of derivatives have low efficiency in terms of feature extraction. Here, we designed a novel CNN model integrated with the extreme learning machine (ELM) algorithm. In this model, the sigmoid activation function is upgraded as the rectified linear unit (ReLU) activation function, and the CNN unit along with the ReLU activation function are used as a feature extractor. The ELM unit works as the image classifier, which makes the perfect symmetry for handwritten digit recognition. A deeplearning4j (DL4J) framework-based CNN-ELM model was developed and trained using the Modified National Institute of Standards and Technology (MNIST) database. Validation of the model was performed through self-build handwritten digits and USPS test datasets. Furthermore, we observed the variation of accuracies by adding various hidden layers in the architecture. Results reveal that the CNN-ELM-DL4J approach outperforms the conventional CNN models in terms of accuracy and computational time.
Background Influenza A virus (IAV) infection is a serious public health problem not only in South East Asia but also in European and African countries. Scientists are using network biology to dig deep into the essential host factors responsible for regulation of virus infections. Researchers can explore the virus invasion into the host cells by studying the virus-host relationship based on their protein-protein interaction network. Methods In this study, we present a comprehensive IAV-host protein-protein interaction network that is obtained based on the literature-curated protein interaction datasets and some important interaction databases. The network is constructed in Cytoscape and analyzed with its plugins including CytoHubba, CytoCluster, MCODE, ClusterViz and ClusterOne. In addition, Gene Ontology and KEGG enrichment analyses are performed on the highly IAV-associated human proteins. We also compare the current results with those from our previous study on Hepatitis C Virus (HCV)-host protein-protein interaction network in order to find out valuable information. Results We found out 1027 interactions among 829 proteins of which 14 are viral proteins and 815 belong to human proteins. The viral protein NS1 has the highest number of associations with human proteins followed by NP, PB2 and so on. Among human proteins, LNX2, MEOX2, TFCP2, PRKRA and DVL2 have the most interactions with viral proteins. Based on KEGG pathway enrichment analysis of the highly IAV-associated human proteins, we found out that they are enriched in the KEGG pathway of basal cell carcinoma. Similarly, the result of KEGG analysis of the common host factors involved in IAV and HCV infections shows that these factors are enriched in the infection pathways of Hepatitis B Virus (HBV), Viral Carcinoma, measles and certain other viruses. Conclusion It is concluded that the list of proteins we identified might be used as potential drug targets for the drug design against the infectious diseases caused by Influenza A Virus and other viruses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.