Papers by avinash agrawal
Indian Journal of Critical Care Medicine, 2022
Coronavirus disease-2019 (COVID-19) pandemic is raging all over the world. As we are delving more... more Coronavirus disease-2019 (COVID-19) pandemic is raging all over the world. As we are delving more into management of COVID-19, certain new challenges are emerging. One of these is emergence or reactivation of viral infections belonging to Herpesviridae family, especially cytomegalovirus (CMV). Although we have come across the threat of fungal and resistant bacterial infections, experience regarding reactivation or coinfection with concomitant viral infections like CMV during the COVID pandemic is still limited. Whether CMV is a bystander or pathogen is difficult to say categorically and needs further research. In this case series, we intend to describe three patients of COVID-19 with CMV coinfections. To our knowledge, this is the first case series from India.
Proper use of wireless sensor networks (WSNs) can lower the rate of catastrophic failures, and in... more Proper use of wireless sensor networks (WSNs) can lower the rate of catastrophic failures, and increase the efficiency and productivity of industrial operations. Diversification of remote control mode is the inevitable trend of development of smart appliances. This paper proposes a review on remote control system of smart appliances based on Zigbee wireless sensor network. Status of the home appliances can be queried and controlled through the remote controller. The proposed work presents the design and implementation of a novel wireless sensor network based home security system with a modular self-reconfigurable remote controller.
Named entities are phrases denoting the names of persons, locations, organizations etc. in text d... more Named entities are phrases denoting the names of persons, locations, organizations etc. in text documents. These phrases are important for the access to document content, since they form the building blocks for the analysis of documents. Named Entity Recognition has applications in Natural Language Processing, document indexing, document annotation, translation, etc. NER plays an important role in various research areas of Natural Language Processing (NLP) like Question Answering and Summarization Systems, Information Retrieval, Machine Translation, Video Annotation, Semantic Web Search, Bioinformatics etc. The computational research of automatically identifying named entities in texts forms a vast and heterogeneous pool of strategies, methods and representations. In this paper, we will present an overview of the various methods used for implementing NER systems by giving the merits and demerits of each. We will also discuss some of the approaches suggested and implemented by NER sy...
International Journal of Scientific & Technology Research, 2014
Falling is among the most dangerous events that often happen among senior people, patients and ma... more Falling is among the most dangerous events that often happen among senior people, patients and may need immediate medical care. Automatic fall detection systems could help old people and patients to live independently. A real-time fall detection system may help us to detect fall events among elderly people in time and reduce the overall casualty rate. The proposed system uses the accelerometer and tilt sensors to design a realtime fall detection system that not only can distinguish up to 4 different kinds of fall events (forward, backward, rightward and leftward), but is also portable,wearable, low-cost and with high accuracy rate. Because the waist is the centre of gravity in the human body, the system is used more effectively when placed at the waist. The system includes an automatic real-time fall detection device, and GSM instant messaging function which can transfer fall alert, send emergency help messages. ————————————————————
International Journal of Innovative Research in Computer and Communication Engineering, 2014
Anaphora resolution has proven to be a very difficult problem of natural language processing, and... more Anaphora resolution has proven to be a very difficult problem of natural language processing, and it is useful in discourse analysis, language understanding and processing, information exaction, machine translation and many more. This paper represents an algorithm that instead of using a monolithic architecture for resolving anaphora, use the combination of constraint-based and preferences-based architectures, each uses a different source of knowledge, and proves effective on theoretical and computational basis. An algorithm identifies both inter-sentential and intrasentential antecedents of “Third person pronoun anaphors”, “Pleonastic it”, and “Lexical noun phrase anaphora”. The algorithm use Charniak parser (parser05Aug16) as an associated tool, and it relays on the output generated by it. Salience measures derived from parse tree, in order to find out accurate antecedents from the list of potential antecedents.
ICSESD-2017, 2017
This Machine learning techniques have been used in various domains. The domain of Stock market is... more This Machine learning techniques have been used in various domains. The domain of Stock market is a promising domain in Machine learning approach. Using Internet technologies variety of structured and unstructured data, such as blogs, message threads, an enormous amount of technical data, company meetings, quarterly results of company etc has been generated. In such type of data can be helpful to compose knowledge and value. Recently, many applications have used to exploit such data for Data mining techniques. However, Stock market data has dependencies among different parameters, and its characteristics change with time, political and natural scenario. Therefore, it is complex to predict data even if state-of-the-art machine learning algorithms are used. In this paper, we discuss a various techniques for predicting power to manipulate stock prices. However, there is no defined framework for the problem to the best in stock market domain. The process recognizes positive and negative words within an article by using large dictionary which contains words that conveys sentiment. Each word in this dictionary can be gave a weight. The calculation of the positive and negative words is the final sentiment score produced by the model.
The proliferation of E-commerce sites has made web an excellent source of gathering customer revi... more The proliferation of E-commerce sites has made web an excellent source of gathering customer reviews about products; as there is no quality control anyone one can write anything which leads to review spam. This paper previews and reviews the substantial research on Review Spam detection technique. Further it provides state of art depicting some previous attempt to study review spam detection. KeywordsNatural language processing, reviews centric spam detection, reviewer centric spam detection
Journal of Family Medicine and Primary Care, 2021
Asthma is a prolonged disorder of the lungs. It excites airway routes and leads to morphological ... more Asthma is a prolonged disorder of the lungs. It excites airway routes and leads to morphological changes to narrow down the passage. This narrowing creates difficulty in breathing leading to uneasiness. Extreme asthma manifests as ruckus talking or being dynamic. The condition is termed as interminable respiratory sickness. Global initiative for asthma defined Asthma as "a heterogeneous disease, usually characterized by chronic airway inflammation. It is defined by the history of respiratory symptoms such as, wheeze, shortness of breath, chest tightness, and cough that vary over time and intensity together with variable expiratory airflow limitation. The airflow limitation may later become persistent". The asthma condition is manifested as episodes of breathlessness, wheezing, etc., In response to exposure to certain allergens and the symptoms may subside with time. However, repeated episodes of asthma may also prove fatal, if not managed properly. The symptoms of the diseases are curable with medication. Asthma is believed to be a multifactorial disorder affected not only by genetic predisposition but also by environmental factors. Asthma is a serious ailment. Asthma causes ~339 million cases throughout the world in a year and nearly 1000 deaths in a day. Almost 18% of the world population is at risk of the disease. As per GINA estimates, 100 million more cases would be added by the year 2025. Nearly, 25 million Americans are at risk of the disease. ~2 million clinical visits in America are attributed to the disease. The countries categorized as a low-and-middle-income group by the World Health Organization are the worst in the case of asthma-related deaths. [4] Nearly, 6% of Indian children and 2% of adults are presented with asthma symptoms per year in a population of 1.31 billion. [4] Underreporting and misdiagnosis of asthma are important contributors to variations in the number of
This paper introduces Named Entity Recognition approach for text corpus. Supervised Statistical m... more This paper introduces Named Entity Recognition approach for text corpus. Supervised Statistical methods are used to develop our system. Our system can be used to categorize NEs belonging to a particular domain for which it is being trained. As Named Entities appears in text surrounded by contexts (words that are left or right of the NE), we will be focusing on extracting NE contexts from text and then performing statistical computing on them. We are using n-gram model for extracting contexts from text. Our methodology first extracts left and right tri-grams surrounding NE instances in the training corpus and calculate their probabilities. Then all the extracted trigrams along with their calculated probabilities are stored in a file. During testing, system detects unrecognized NEs from the testing corpus and categorizes them using the tri-gram probabilities calculated during training time. The proposed system is made up of two modules i.e. Knowledge acquisition and NE Recognition. Kn...
Utility of Point-of-Care Ultrasound (POCUS) for predicting risk of magnesium toxicity in critically ill pre-eclamptic patients
Indian Journal of Anaesthesia, 2021
Indian Journal of Critical Care Medicine, 2020
International Journal of Contemporary Pediatrics, 2020
Background: Child abuse is one of the problems in our society which still needs to be highlighted... more Background: Child abuse is one of the problems in our society which still needs to be highlighted for general public in our country. It is a pressing human right issue and public health concern and the efforts to assess the awareness and mass education is very limited. Current study aimed to access knowledge and attitude for child abuse among parents attending a tertiary care hospital.Methods: The study was conducted amongst parents visiting pediatric OPD at Kempegowda institute of medical sciences, Bengaluru. Total 200 Parents were required to answer a series of questionnaire and then was statically analyzed.Results: It was seen that majority of parents lack knowledge regarding child abuse, 25% of parents believe that child abuse is just sexual violence, 23% parents thought that stubborn children can only be handled by physical punishment, 46% parents believed that only a girl child can be a victim of sexual abuse and only 19% had firm belief that boys can also be victim, 45% of pa...
International Journal of Advanced Research, 2019
Critical analysis of all pregnancies with heart disease, misses and near misses over 1-year period along with expert group so as to optimize outcome and improve patient care – Need-based analysis
Heart India, 2019
Introduction: Cardiac disorders complicate approximately 1%–3% of pregnancies and present a real ... more Introduction: Cardiac disorders complicate approximately 1%–3% of pregnancies and present a real challenge to treating healthcare providers.Maternal mortality may be as high as 7% when New York Heart Association (NYHA) Classes III and IV patients are combined. In contrast, Classes I and II combined yield a mortality of 0.5%. Similarly, fetal mortality maybe as high as 30% in Class III and IV patients, in contrast to 2% for Classes I and II. Managing pregnant patients with complex cardiac disease mandates participation from a multidisciplinary team early in the pregnancy. Audit of misses and near misses helps to determine causes of maternal mortality and morbidity and identify gaps in care. Aims and Objectives: To assess burden of maternal cardiac disease and its influence on maternal and fetal outcome. To assess gaps in multidisciplinary care and to analyze causes associated with increased morbidity and mortality. Methods: A retrospective analysis of all pregnant patients with heart disease admitted to department of obstetrics and gynecology at tertiary care center from January 2017 to January 2018. Results: Of 9563 deliveries, there were 108 cases of pregnancy with heart disease (1.12%). Majority of patients in study cohort belonged to low socioeconomic status and had rural background. 36 patients (33.33%) were primi-gravida; majority presented for antenatal care in the third trimester. 82 (75.92%) in functional Class (NYHA) I – II, predominant cardiac lesion was rheumatic valvular disease diagnosed in 101 patients (93.5%); 60 patients (58.82%) had vaginal delivery, 63 (64%) were delivered before 37 weeks and 6 patients had medical termination of pregnancy. 10 patients (9.2%) developed cardiac failure and 8 (7.4%) had atrial fibrillation. There were 4 maternal death and 8 near misses. Conclusion: The present study highlights need of training of physicians and obstetrician working at peripheral centres for early diagnosis, timely referral and strengthening pre-pregnancy counselling.
International Journal of Contemporary Pediatrics, 2019
Background: Identifying common etiological organisms among cases of suspected sepsis and their se... more Background: Identifying common etiological organisms among cases of suspected sepsis and their sensitivity pattern for common antibiotics will help in initiating appropriate therapy. Finding association of positive culture with other markers of infection like total leucocyte count, haemoglobin, C-reactive protein.Methods: Descriptive and an observational study conducted in Kempegowda Institute of Medical Sciences, hospital paediatric intensive care unit, Bangalore, Karnataka, India. Data was collected prospectively. Duration of study was for 1 year from February 2018 to February 2019.Results: During the study, 52 cases admitted to paediatric intensive care unit were suspected to have sepsis and 91 samples were sent for culture. Out of these, 46 were blood, 34 were of urine and 11 others (pleural, CSF, ET). Among these samples tested 26% (18) of blood, 23.5% (8) of urine and 45.45% (5) of other samples showed organisms.Conclusions: In this study, author were able to know the common e...
HELIX, 2018
Natural language Processing (NLP) is a field of artificial intelligence and computational linguis... more Natural language Processing (NLP) is a field of artificial intelligence and computational linguistics concerned with interaction of humans with machines. Social Networking sites (SNS) is a widely used communication tool today. Sometimes it gives rise to the problem of flaming. A flaming incident is triggered by comments and action made by user in SNS that ends up damaging reputation or causing negative impact on the target party. The paper proposes an architecture to overcome this problem. The training dataset used contains a total of 17282 tweets already annotated as positive, negative and neutral. The test dataset that has been used contains a total of 4382 tweets already annotated as positive, negative and neutral. Result of machine learning techniques used in the proposed architecture are reported and discussed in this paper.
HELIX, 2018
This paper is devoted to a new method that uses combined technique of pseudo relevance feedback a... more This paper is devoted to a new method that uses combined technique of pseudo relevance feedback and co-occurring term technique for query expansion to improve cross language information retrieval along with selective document technique to reduce search space. The base is an Information Retrieval (IR) system which uses cosine similarity technique to retrieve and rank documents and a multilingual module using dictionary based translation where the tf-idf values are calculated and stored in inverted index which is term based index. The threshold value is used as a selection medium for documents which reduces the search space of index reducing the overall time for retrieval. A Query Expansion (QE) module is added in to the said system. The aim is to use QE to overcome the limitations of dictionary based translation, and to retrieve more relevant results. The system is validated with several measures, which shows the difference in the result before expansion and after expansion.
Perceptions of Undergraduate Students and Faculty about Utility of Multimodal Instructional Approach to Aid Learning
Journal of Research in Medical Education & Ethics, 2018
Journal of Research in Medical Education & Ethics, 2018
In this paper, we propose a novel scene text detection method named TextMountain. The key idea of... more In this paper, we propose a novel scene text detection method named TextMountain. The key idea of TextMountain is making full use of border-center information. Different from previous works that treat center-border as a binary classification problem, we predict text center-border probability (TCBP) and text center-direction (TCD). The TCBP is just like a mountain whose top is text center and foot is text border. The mountaintop can separate text instances which cannot be easily achieved using semantic segmentation map and its rising direction can plan a road to top for each pixel on mountain foot at the group stage. The TCD helps TCBP learning better. Our label rules will not lead to the ambiguous problem with the transformation of angle, so the proposed method is robust to multi-oriented text and can also handle well with curved text. In inference stage, each pixel at the mountain foot needs to search the path to the mountaintop and this process can be efficiently completed in parallel, yielding the efficiency of our method compared with others. The experiments on MLT, ICDAR2015, RCTW-17 and SCUT-CTW1500 databases demonstrate that the proposed method achieves better or comparable performance in terms of both accuracy and efficiency. It is worth mentioning our method achieves an F-measure of 76.85% on MLT which outperforms the previous methods by a large margin. Code will be made available.
International Journal of Engineering & Technology, 2018
Diabetes is characterized by impaired metabolism of glucose caused by insulin deficiency. Diabeti... more Diabetes is characterized by impaired metabolism of glucose caused by insulin deficiency. Diabetic retinopathy is the eye disease, is caused by retinal damage which is generally formed as a result of diabetes mellitus. It is a serious vascular disorder for which early detection and the treatment are required to inhibit the intense vision loss. Also, the diagnosis entails skilled professionals for detection because non-automatic screening methods are very time consuming and are not that efficient for a large number of retinal images. This paper provides a broad review of various techniques and methodologies used by the authors for diabetic retinopathy detection and classification. Furthermore, most recent work and developments are studied in this paper. We are proposing an advanced deep learning CNN approach for automatic diagnosis of DR from color fundus images.
Uploads
Papers by avinash agrawal