Rahul Goswami CST - 16 (original) (raw)

Uploads

Papers by Rahul Goswami CST - 16

Processing and Analysis of Biomedical Information, 2019

Several deaths occur each year because of burns. Despite advancements in burn care, proper burns ... more Several deaths occur each year because of burns. Despite advancements in burn care, proper burns diagnosis and treatment of burn patients still remains a major challenge. Automated methods to give an early assessment of the total body surface area (TBSA) burnt and/or the burns depth can be extremely helpful for better burns diagnosis. Researchers are considering the use of visual images of burn patients to develop these automated burns diagnosis methods. As the skin architecture varies across different parts of the body, and so the burn impact on different body parts. So, it is likely that the body part specific visual images based automatic burns diagnosis assessment methods would be more effective than generic visual images based methods. Considering this, we explore this problem of classifying the body part of burn images. To the best of our knowledge, ours is the first attempt to classify burnt body part images. In this work, we consider 4 different burnt body parts: face, hand, back, and inner arm, and we present the effectiveness of independent and dependent deep learning models (using ResNet-50) in classifying the different burnt body parts images.

Conference Proceedings of ICDLAIR2019, 2021

Potholes are an ever-increasing problem in India leading to several accidents and wear & tear in ... more Potholes are an ever-increasing problem in India leading to several accidents and wear & tear in the vehicles. As the size of potholes increases with time, therefore, detection and redressal of these potholes at early stages is essential which can avert accidents and provide a comfortable ride to the road users. In this paper, a robust, fully automated, versatile pothole detection system POCONet- POthole COnvolution Network, is proposed for improving the existing pothole detection methods and accurately detecting a pothole. An object detection model, trained by using a multi-layered convolution network YOLOv2, is used for detecting the potholes in the video feed collected from smartphones and is then marked on the maps using their respective GPS location. The trial runs, using the model depicts an accuracy level above 88% at different speeds of observing vehicle. Thus, the proposed system provides a cost-efficient, fully automated road assessment technique, which includes the detect...

The shedding of an oil drop due to gradually increasing water shear flow is studied for different... more The shedding of an oil drop due to gradually increasing water shear flow is studied for different resting times. Resting time is the duration of the drop after placing on a surface and before starting the flow. Acrylic surface is chosen. Applied drag balances the adhesion, and the drop starts to shed. The velocity of the water flow right at that point is called the critical velocity of shedding of the drop. The velocity is found to be higher for the drops with higher resting times. Result shows that the contact length becomes higher for drops with higher resting times, making the adhesion to be higher. Therefore, higher drag becomes necessary for the drop to shed. So, the critical velocity increases. In general, the velocity is found to decrease with the increase in the drop volume. Deformation and crawling are observed when a drop sheds.

SSRN Electronic Journal, 2017

The shedding of silicon oil drops from a glass surface due to water cross flow is presented. The ... more The shedding of silicon oil drops from a glass surface due to water cross flow is presented. The surface was placed inside a rectangular channel filled with water, and on top of the surface a drop of given size was placed. Various sizes of the drops were used for the experiment. The flow of water was gradually increased so that the drop sheds when the drag and the adhesion balance each other. The cross-flow velocity of water at that point was called the critical velocity. The critical velocity was found to decrease with increase in drop size. The contact lengths and heights were found to increase with the drop size. The increase in the contact length increases the adhesion, but the increase in height raises the drag applied. Hence the critical velocity decreases.

International Journal of Applied and Basic Medical Research, 2017

Background: Removal of impacted third molars is the most common oral surgical procedure. Many inv... more Background: Removal of impacted third molars is the most common oral surgical procedure. Many investigators have questioned the necessity of removal in patients who are free of symptoms or associated pathologies. Aim: The aim of this retrospective study was to evaluate the incidence of caries on distal aspect of mandibular second molars in patients referred for corresponding third molar assessment and to identify its association with angular position and depth of the impacted mandibular third molars based on the classification of Pell and Gregory. Methodology: Records of 150 patients with impacted third molar presenting to the Department of Oral and Maxillofacial Surgery, Sri Rajiv Gandhi College of Dental Sciences and Hospital, were assessed retrospectively. The radiographic angulation and depth of mandibular third molar impaction were determined and compared to determine the relationship with incidence of caries on the distal surface of the second molar. Results: According to this study results, 37.5% cases show caries on the distal aspect of mandibular second molars. The incidence of caries with mesioangular impacted third molars was 55%. A majority of these mesioangular cases were Level B and Class I as per the Pell and Gregory classification. Conclusion: The prophylactic extraction of mandibular third molars is indicated if the angulation is between 30° and 70° and is justified by incidence of distal caries in the second molars.

Lecture Notes in Mechanical Engineering, 2016

Low speed wind tunnel (LSWT) is a device, generating uniform airflow relative to a model of the b... more Low speed wind tunnel (LSWT) is a device, generating uniform airflow relative to a model of the body that measures aerodynamic force and pressure distribution to simulate with actual conditions. This paper will lay emphasis on the procedure adopted in the design of a tunnel (open circuit blow down type) along with the detailed analysis of flow through it and forces generated on an airfoil NACA 4412 with the help of CFD based software Fluent 6.3. In purview of the designing and testing economics, it is not feasible to go for the real time simulation at original facilities. So, we have decided to make this small scale LSWT as forces and pressures developed by the model can be applied to the prototype by multiplying the force co-efficient obtained in the computational analysis of the model with the factor ½ ρ ∞v ∞ 2 AP having values of parameters in the factor corresponding to full scale.

British Journal of Medicine and Medical Research, 2016

International Journal of Medical and Pharmaceutical Case Reports, 2016

Wind tunnel is an aerodynamic test facility. It is mostly used to study flow patterns around bodi... more Wind tunnel is an aerodynamic test facility. It is mostly used to study flow patterns around bodies and measure aerodynamic forces on them. In the present paper an open circuit blow down type wind tunnel has been designed using standard design rules given by R. D.. The speed in test section is 40 m/s and static pressure drop is 30mm of water column. The design has been validated using commercial CFD code FLUENT 6.3.