Melanoma Classification using Convolutional Neural Network Model Integrated with Tabular Model
Melanoma is a major skin cancer type that has a very high death rate. The various sorts of skin abrasions cause an imprecise analysis because of their high resemblance. Precise categorization of the skin abrasions in the premature phase will allow dermatologists to cure the affected individuals in well time and hence saving their lives. This is backed by a research that shows that 90% of the cases are curable, if identified in the initial phase. With the advancements in the computing power and image classification, automatic detection of the melanoma using computer algorithms has become far reliable. With many methods used, neural networks prove to be the best solution devised to attain the highest accuracy in classifying melanoma through early symptoms. We did our survey to find the drawbacks of recent models that serve this purpose with the goal to overcome them and provide a better solution. With the findings based on this survey, we proposed a model that stives to overcome the drawbacks concluded from the previous models. With an accuracy of ~96%, the proposed model provides better solution in prediciting whether the skin lesions are malignant or not.
Published by: Harshkumar Modi, Bhavya Chhabra, Sukkrit
Author: Harshkumar Modi
Paper ID: V7I4-1427
Paper Status: published
Published: July 18, 2021
Facial Recognition with Expression
In this paper, motions are a strong tool in communication and a technique that humans show their emotions is through their facial expressions. one among the difficult and powerful tasks in social communications is countenance recognition, as in non-verbal communication, facial expressions are key. In the field of computing, face expression Recognition (FER) may be a spirited analysis space, with many recent studies using Convolutional Neural Networks (CNNs). during this paper, we demonstrate the classification of FER supported static images, using CNNs, while not requiring any pre-processing or feature extraction tasks. The paper conjointly illustrates techniques to improve future accuracy throughout this space by victimisation preprocessing, which includes face detection and illumination correction. Feature extraction is utilized to extract the foremost prominent components of the face, together with the jaw, mouth, eyes, nose, and eyebrows. what is more, we tend to conjointly discuss the literature review and gift our CNN design, and the challenges of victimisation max-pooling and dropout, that eventually aided in higher performance. we tend to obtained a check accuracy of 61.7% on FER2013 throughout a seven-classes classification task compared to seventy five.2% in progressive classification.
Published by: Manoj P., Mahesh N., Shivakumar Vishwakarma R., Alpha Vijayan
Author: Manoj P.
Paper ID: V7I4-1410
Paper Status: published
Published: July 18, 2021
Digital health care system for medical report/ certificate sharing
The health care services industry is always showing signs of change and supporting new advancements and advances. This paper describes our blockchain architecture as a new system solution to supply a reliable mechanism for secure and efficient medical record exchanges. It is going to revolutionize the e-Health industry with greater efficiency by eliminating many of the intermediates as we know them today. Digital Health Care (DHC) reform suggests a new consumer paradigm in data and information processing. Here users can be distributed or access networked collaborative care to a centralized repository of personal health records. The new approach in this paper is to explore the Advanced Block-Chain paradigm for e-Health record-keeping and while addressing the special needs of patient privacy. As society is moving towards peer networking and online practices, we are going to combine the best parts of the two worlds in both the healthcare regulation and the technology revolution while formulating advanced solutions.
Published by: Komal Suresh Raut
Author: Komal Suresh Raut
Paper ID: V7I4-1393
Paper Status: published
Published: July 18, 2021
Multidrug-resistant Acinetobacter baumanii infections – A dreadful superbug to humans
Acinetobacter baumanii is considered to be one of the significant pathogens causing nosocomial infections and outbreaks in hospital settings, especially in ICU. The dreadful concern with Acinetobacter infections is their ability to gain resistance against all commonly used antibiotics like Penicillin, cephalosporins, Fluoroquinolones, carboxypenicillin, carbapenems as a result this Multi-Drug Resistant (MDR) strains increases patient hospital stay, cost of treatment, mortality, and morbidity among affected patients. A total of 146 Acinetobacter isolates were received from various clinical samples. Samples received were routinely subjected to Culture. Gram staining was done. The smear showed Gram-Negative Coccobacilli taken and subjected for further biochemical reactions. Antibiotic susceptibility testing was done by Kirby Bauer disc diffusion method in Muller -Hinton agar plate. The majority of Acinetobacter baumanii isolates were received from the 19-40 age group (45.8%), followed by the 41- 60 (26% ) age group. Most of the Acinetobacter baumanii strains were isolated from wound swab 33.5%, followed by urine 29.4%, sputum 17.1%, Blood 10.2%.Antibiotic sensitivity of 146 Acinetobacter baumanii isolates showed Highest resistance to Ampicillin (100%), Gentamycin (70.5%),Cotrimoxazole (68.4%) , Piperacillin Tazobactam (66.4%) , Ciprofloxacin (63%), Nitrofurantoin (61.6%) , Ceftriaxone (61.6%). Levofloxacin, Amikacin, Tigecycline, Colistin were found to be the most effective antibiotics with a sensitivity of 73.2%, 87.6%, 91.7%, 100% respectively. Of 146 isolates 63 (43%) were Multi-Drug Resistant, i.e isolates showing resistance to more than 3 classes of antibiotics. Hence strict infection control and antimicrobial stewardship policies should be implemented in hospitals to reduce mortality and morbidity associated with Acinetobacter baumanii infections.
Published by: Dr. N. A. Fairoz Banu, Dr. Chitralekha Saikumar
Author: Dr. N. A. Fairoz Banu
Paper ID: V7I4-1398
Paper Status: published
Published: July 18, 2021
Face Mask Detection
Manual surveillance of whether people are wearing a mask or not is not only costly but also a risky process. In this present world, which is being hit by the Coronavirus pandemic, the risk of spread of virus is exponentially high when people are not wearing mask. Thus, the automation of the process of detection of people not wearing mask had become a necessity. Our project uses deep learning techniques to determine whether a person is wearing a mask or not. Our proposed system identifies the mask violators automatically which reduces the risk of transmission of virus and also makes it easier for the authority to monitor the mask violators and take action against them without being put at risk of transmitting the virus. We use MobileNetV2 architecture to efficiently achieve best accuracy which is the key to our system. We were able to achieve accuracy of 99.22% after training the model. Detecting and tracking the face mask is the main aim of the project.
Published by: Bhaskar N. Patel, Siddhant Sipoliya, Shashwat Mishra, Shreyansh, Sreelatha P. K.
Author: Bhaskar N. Patel
Paper ID: V7I4-1379
Paper Status: published
Published: July 18, 2021
The Pink City litter survey: Litter investigation of Kardhani Market Malviya Nagar, Jaipur
Nowadays, Litter is a worldwide problem. Every country expends a large amount of money to clean up litter. The USA expended almost 11 billion dollars annually. Litter is an environmental problem which not only responsible for air, water, and soil pollution but also produces harmful effects on humans, animals, plants, and the risk of fire hazards, endangering. Litter is big a problem also in India. Annual waste generation is almost 62 million tons in India, only 43 million tons collected by the different Govt. & private bodies. It is clear that almost 19-million-ton waste remains in the form of litter so our study focused on identifying the nature and source of litter and on solving this problem. We did a survey to identify nature, source, and public attitudes towards litter. We did 2 types of litter surveys in the Satkaar market, Jaipur (Rajasthan). In the first survey, we collected litter material from three streets of the Satkaar market then took it to the lab for analysis. Firstly we categorized litter into seven categories plastic, paper and cardboard, composite material, glass item, metallic items, food and vegetable waste, and other category waste (foam, rubber, cigarette butts, flower and garland, cloths, bird feather). we found that most littering items ids plastic (almost 40% of total % weight of litter ), average recyclable litter is 34.66 % and biodegradable litter is about 43%.in the second survey I made a set of 23 questions to know the attitude and behavior of public towards litter. We found in this survey that most people think that litter is a crime, both administration, and the public are responsible for litter when the educational level increased then the habit of littering is reduced.
Published by: Ishfaq Ul Abass, Sanjay Kumar Meena, Sumit Kumar, Satynarayan Chaudhary, Shan Ahmad Mir, Raghvendra Sharma
Author: Ishfaq Ul Abass
Paper ID: V7I4-1382
Paper Status: published
Published: July 18, 2021
