Suwarna Gothane | JNTU , hyderabad (original) (raw)

Papers by Suwarna Gothane

Part of the Lecture Notes in Electrical Engineering book series (LNEE,volume 838), 2022

Solid waste management is crucial in India. In metropolitan India, nearly, 377 million population... more Solid waste management is crucial in India. In metropolitan India, nearly, 377 million population produces 62 million tons of municipal solid waste per annum, 70% is collected, 20% is treated, and 50% is neglected. With the current rate of increase in population, it will be incremental till 2025. Domestic house waste per person is also important parameter in metro cities. Exposed garbage every day results in contaminated land. Here, objective is to suggest an approach to develop an IoTenabled waste management system to improve soil quality for agricultural activities and minimize human intervention helps to reduce human time and effort. Approach helps in control pollution and diseases caused due to environmental pollution. Here, we have performed data analytics using Weka tool and Microsoft Excel. We have used monthly-recycling-and-waste-collection-statistics data set for performing analytics and noticed contribution of curb waste maximum compare to other types of waste. There is a demand to provide technology for waste management.

From the day internet came into existence, the era of social networking sprouted. In the beginnin... more From the day internet came into existence, the era of social networking sprouted. In the beginning, no one may have thought internet would be a host of numerous amazing services like the social networking. Today we can say that online applications and social networking websites have become a non-separable part of one’s life. Many people from diverse age groups spend hours daily on such websites. Despite the fact that people are emotionally connected together through social media, these facilities bring along big threats with them such as cyber-attacks, which includes cyberbullying.

International Journal of Innovative Technology and Exploring Engineering, 2020

Conduction of seminar is crucial and essential for the students who find difficult in understandi... more Conduction of seminar is crucial and essential for the students who find difficult in understanding more or less understanding on subject topics. Seminar creates interest in student understanding by means of better teaching aids compare to normal classroom chalk and board/talk session. Seminar plays vital role in business as well educational fields to grasp subject inside. Conducting a successful technical seminar requires careful preparation. Seminar MLRIT focuses on mandatory course of Technical Seminar for empowering students and overall personality development.

Plant disease is an ongoing challenge for smallholder farmers, which threatens income and food se... more Plant disease is an ongoing challenge for smallholder farmers, which threatens income and food security. The recent revolution in smartphone penetration and computer vision models has created an opportunity for image classification in agriculture. Convolutional Neural Networks (CNNs) are considered state-of-the-art in image recognition and offer the ability to provide a prompt and definite diagnosis. In this paper, the performance of a pre-trained ResNet34 model in detecting crop disease is investigated. The developed model is deployed as a web application and is capable of recognizing 7 plant diseases out of healthy leaf tissue. A dataset containing 8,685 leaf images; captured in a controlled environment, is established for training and validating the model. Validation results show that the proposed method can achieve an accuracy of 97.2% and an F1 score of greater than 96.5%. This demonstrates the technical feasibility of CNNs in classifying plant diseases and presents a path towa...

The protection and convenience of smooth traffic by the road network are governed to a large exte... more The protection and convenience of smooth traffic by the road network are governed to a large extent by the superiority of maintenance. By early identification of problem, the rapid deterioration of the roadways can be prevented. The primary intention of maintenance is to allow the movement of traffic at a desired speed, safety and not as much of cost. Road network can be preserved and prolonged if sufficient maintenance measures are undertaken at proper time. Potholes, cracks, patches etc., are some types of road surface distresses mostly used to perform manually. In the current field practices, road distress data assessment is reported to be done through distress data collection and processing of the collected raw data. This process is a labor-intensive and time consuming process and can also slows down the road maintenance management. By considering necessity for automation at present, distress data collection is increasingly being shifted towards atomization. In this paper, we an...

Road network consist of various problems. Pothole, crack and patches are the common problems of r... more Road network consist of various problems. Pothole, crack and patches are the common problems of road network. Various manual and automated solutions have been proposed by the expertise in the previous work. To overcome the problem we have came here with a novel solution approach to identify road quality. Identification of maintenance severity level and providing repair solution is done using WEKA tool 3.7. This paper presents comparison summary of classification approach and estimated which algorithm gives efficient accuracy for classification. In this paper we have obtained highest accuracy of classification 98.84 % by Support Vector Machine (SMO Function).

To retrieve the desired information from the Web, an efficient information search methods are req... more To retrieve the desired information from the Web, an efficient information search methods are required due to the information explosion on the Internet. We find that both the query and the indexed web content are often related with a variety of perspective information with much analysis on users' search intention and the alternate forms of Web content, which can provide much important information to designate the ranking relevance in Web search. Ranking the results of a user query is one of the problems in this context and for addressing this problem previous approaches have used frequencies of database values and the common problem in most is ranking is done in a user and query-independent manner. For ranking query results in Web databases a novel query- and user-dependent approach is proposed in this paper. Based on two corresponding ideas of user and query resemblance a ranking model is introduced to derive a ranking function for a given user query. The results of similar que...

IJCSIET-ISSUE5-VOLUME2-SERIES3 Page 1 ADAPTIVE ROBUST TECHNIQUES FOR BACKGROUND SUBTRACTION USING... more IJCSIET-ISSUE5-VOLUME2-SERIES3 Page 1 ADAPTIVE ROBUST TECHNIQUES FOR BACKGROUND SUBTRACTION USING CLUSTERING ALGORITHM CHAITHANYA NASKANTI chaithanyanaskanti@gmail.com M.TECH MRS. SUWARNA GOTHANE gothane.suvarna@gmail.com ASSOCIATE PROFESSOR CMRTC, MEDCHAL, HYDERABAD 2 Abstract: Background subtraction is essential part of video analysis. Video analysis includes background model followed by a regularization scheme. A model of the background allows it to be distinguished up on a per-pixel basis from the foreground with original image, while the regularization combines information from adjacent pixels within the image. In this paper we present a new method based on kmeans Algorithm to find out the objects, which are used to estimate per-pixel background distribution with the foreground. Backend image: Which is already stored whenever we start the camera? Foreground image: Which are captured by the webcam and these are compared with the background image to get the status. KMeans produce...

The growing number of datasets published on the Web as linked data brings both opportunities for ... more The growing number of datasets published on the Web as linked data brings both opportunities for high data availability of data. As the data increases challenges for querying also increases. It is very difficult to search linked data using structured languages. Hence, we use Keyword Query searching for linked data. In this paper, we propose different approaches for keyword query routing through which the efficiency of keyword search can be improved greatly. By routing the keywords to the relevant data sources the processing cost of keyword search queries can be greatly reduced. In this paper, we contrast and compare four models – Keyword level, Element level, Set level and query expansion using semantic and linguistic analysis. These models are used for keyword query routing in keyword search.

Association mining has seen its development right through data mining ,which reveal implicit rela... more Association mining has seen its development right through data mining ,which reveal implicit relationship among data attributes It is the research topic in data mining and use for applications such as business, science, society and everyone .Association rule helps in marketing, decision making, business management ,cross marketing ,catalog designing ,clustering ,classification etc. Finding small database sets could be done with the help of predictive analysis method. The paper enlightens the combinational categorization of association and classification data mining. For fields like medicine where a lot several patients consult doctor, but every patient has got different personal details not necessarily may suffer with same disease. So the doctor may look for a classifier, which could present all details about every patient and in future necessary medications can be provided. However there have been many other classification methods like CMAR, CPAR MCAR and MMA and CBA. Some advance ...

We can all agree that social media is a double-edged it has many advantages and also has many dis... more We can all agree that social media is a double-edged it has many advantages and also has many disadvantages. Everything begins with a piece of information be it correct or incorrect, one of them is spreading false information or Fake news. These days detecting fake news on social media has recently become an emerging research that is very challenging task for any organizational body. Fake news detection on social media has unique characteristics and challenges that make it extremely hard for it to be classified into fake or real. Apart from that the extensive spread of fake news can have a serious impact on society. Majorly fake news can break the standard balance of the way society works. It might get people into believing into false content that might cause serious harm to ones property. Fake news is usually spread by certain group of people in the society who have certain political connections or attempt to make free money out of one's hard earning. Most important thing is that fake news changes the way people think and they intend to doubt on each and every other news even if it is real. As we notice this is a major problem we have to help remove the negative effects caused by fake news both to public and the balance in natural mankind ecosystem. Our project aims at investigating the reasons, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the performance. We even try to implement the best algorithms to get the fastest performance needed which will boost the overall performance of the model.

Indian roads have various distress issues, enormous stress, and immense need of rejuvenation to h... more Indian roads have various distress issues, enormous stress, and immense need of rejuvenation to handle the augmented need of the Indian economy, vast traffic, and heavy vehicle speed. To overcome the problem of road network, we developed a method to track roadworthiness. Identification of severity level and accuracy is achieved using MATLAB. This paper presents SVM evaluation on real road network images. Using GLCM feature extraction and support vector machine classifier, we achieved 81.3% accuracy results.

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021

When we look at images or videos, we can easily locate and identify the objects of our interest w... more When we look at images or videos, we can easily locate and identify the objects of our interest within moments. Passing on this intelligence to computers is nothing but object detection - locating the object and identifying it. Object Detection has found its application in a wide variety of domains such as video surveillance, image retrieval systems, autonomous driving vehicles and many more. Various algorithms can be used for object detection but we will be focusing on the YoloV3 algorithm. YOLO stands for "You Only Look Once". The YOLO model is very accurate and allows us to detect the objects present in the frame. YOLO follows a completely different approach. Instead of selecting some regions, it applies a neural network to the entire image to predict bounding boxes and their probabilities. YOLO is a single deep convolutional neural network that splits the input image into a set of grid cells, so unlike image classification or face detection, each grid cell in YOLO algo...

International Journal for Research in Applied Science and Engineering Technology, Nov 14, 2017

The basic idea of this project is to develop application software to detect the presence of brain... more The basic idea of this project is to develop application software to detect the presence of brain tumour in MRI images. This project aims to develop accurate determination of tumor in the brain tumour. Here we are using image processing techniques to detect exact position of tumour. Actually we are performing morphological operations on MRI segmented and enhanced image.

International Journal of Advanced Research in Computer Science

International journal of simulation: systems, science & technology

With the massive improvements in the road transport network in India, the road safety is becoming... more With the massive improvements in the road transport network in India, the road safety is becoming the major concern of the authorities. The road safety is primarily defined by the motor skills of the driver. Nevertheless, the effects of road conditions on safety cannot be ignored. The authorities responsible for road maintenance are struggling to provide the higher maintenance of the roads to provide better, faster and safe transportation. Thus the demand for the research to automate the detection of the road conditions cannot be disregarded. A number of research attempts are carried out in order to detect the road condition based on the potholes. Nonetheless the detection process is highly time complex and makes the maintenance process delayed. Also, majority of the parallel research outcomes failed to measure multiple potholes in a single image and cannot distinguish the potholes based on the emergency of repair. Thus this work defines a newer dimension of pothole detection for road images, which contains higher number of potholes in a single image and makes the process faster by reducing the change of false detection. The false detection is usually the images in the dataset without having significant damages. Also, this work extracts the parameters for determining the potholes existence as the major outcome. Yet another outcome of this work is to classify the potholes based on the urgency of repair. The final outcome of the work is to automate the detection facility to provide a timely maintenance alert and deliver a better road condition in India.

NCCSIGMA-16, 2016

Wireless Sensor Network (WSN) is promising topic of technical, social, and economic importance. T... more Wireless Sensor Network (WSN) is promising topic of technical, social, and economic importance. The sensing technology combined with processing power and wireless communication makes it rewarding for being exploited great quantity in future. The inclusion of wireless communication technology also incurs various types of security threats. Meanwhile, supplying privacy and security is an inseparable part of this technology. Without providing enough security, the promising benefits of this flourishing technology will be misused and worthless. In this paper we investigate the security related issues and challenges in wireless sensor networks. We identify the security threats, review proposed security mechanisms for wireless sensor networks. We also discuss the holistic view of security for ensuring layered and robust security in wireless sensor networks.

2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016

Convenience and safety of road is very important and crucial in society. Statistics of accidental... more Convenience and safety of road is very important and crucial in society. Statistics of accidental deaths has shown a growing drift in India. Accidents on road network with vehicle collision can lead to injuries or even deaths and causes economy loss. Reasons for accident includes over speeding, drunken driver and defects in vehicle as well as bad road condition. Places near residential areas, pedestrian crossing, around schools, college and other educational institutions are the major zone of accidents. Mega cities traffic in India is increasing day by day due to increase in the population. In this paper we have figure out the factor influencing the accidents and identified which factor is more accident prone with Info Gain Attribute Evaluator function using WEKA tool. We have also performed association classification using Apriori algorithm and identified best rule for accident dataset.