Praveen Kumar Kollu

Praveen Kumar Kollu

Auto-generated profile, based on publicly available information

Praveen Kumar Kollu

Department of Computer Science and Engineering, V.R.Siddhartha Engineering College, Andhra Pradesh, India

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 April 2025 in IEEE Access
Verified
Journal Article
Open access
SAShaik Shakeel Ahamad
Shaik Shakeel Ahamad
KKK. Praveen Kumar
K. Praveen Kumar
SGSankuratri Sri Ganesh
Sankuratri Sri Ganesh
FAFayez Alharbi
Fayez Alharbi
SASultan Awad Alharby
Sultan Awad Alharby
SKSuvarna Vani Koneru
Suvarna Vani Koneru
The life expectancy of a population is a vital measure of its overall health and healthcare quality. This study use machine learning methods, notably XGBoost, to predict life expectancy in industrialized and emerging countries. XGBoost, or Extreme Gradient Boosting, is a robust machine-learning technique renowned for its precision and efficiency in handling structured data. The objective is to develop a precise prediction model and identify the primary factors influencing life expectancy. The experimental findings indicate that our XGBoost-based model effectively forecasts life expectancy in both industrialized and developing nations. Mean Absolute Error, Mean Squared Error, and R² score are used for model selection. XGBoost is selected because to its mean squared error of 2.45, mean absolute error of 1.03, and R² scores of 0.99 for the training set and 0.97 for the testing set. We conduct feature significance analysis to identify the most relevant factors affecting life expectancy. Our results underscore the significance of variables such as HIV/AIDS, income composition, and adult mortality in influencing life expectancy. The model's findings may assist lawmakers and healthcare professionals in making educated decisions to enhance public health outcomes, allocate resources efficiently, and formulate focused solutions.

1 September 2018
Verified
Conference Paper
Closed access
SKSuvarna Vani Koneru
Suvarna Vani Koneru
MRM Arul Raj
M Arul Raj
MPM Padmaja
M Padmaja
PKPraveen Kumar Kollu
Praveen Kumar Kollu
LBLokesh Bokinala
Lokesh Bokinala
AJA Jitendra
A Jitendra
Remote sensing plays a key role to monitor the earth resources. Remote sensing uses High Resolution Satellites to capture and observe the various conditions of the earth like Land cover and Land use which provides the information regarding how much of land is covered by forest, wetland, water body and how much of land is used by people for rural development, urbanization and agricultural in digital images. Digital Image Processing is useful in decrypt satellite data which helps to know change detection and land cover classification. In this research, satellite data are used to investigate trees and identifying trees on the earth surface, where it is very difficult task to identify trees from high resolution satellite imagery. Digital Image Processing consists of various techniques like image enhancement, segmentation, feature extraction and classifying the extracted features. In this research, Cartosat2 images are used for detection and enumeration of trees. With utilization of digital image processing, the information can be known that is available in the satellite image. Image processing helps to refines the available data in the satellite images without any loss. Image segmentation is used to analyze the image in a understandable form, where it cleaves the image in the form of pixels. Basically it is used to detect and classify the shapes or object boundaries and other relevant data in the digital images. Contrast Limited Adaptive Histogram Equalization(CLAHE) is one of the effective simple techniques for enhancing image quality. Active Contour Model with masking is best suit for image Segmentation and feature Detection and Tree Enumeration.

1 October 2016
Verified
Conference Paper
Closed access
KVK Suvarna Vani
K Suvarna Vani
KKK Praveen Kumar
K Praveen Kumar
Proteins can be classified among the four structural classes of All-Alpha, All-Beta, Alpha+Beta and Alpha/Beta which are further subdivided into 27 folds. Protein fold classification problem is cited in the literature as a challenging unbalanced classification problem with the accuracy results being as low as 51.1% on the bench mark data set of Ding et al. and highest accuracy at 60.5% using 2500 features. We represent the proteins as 11-length feature vectors and adopt Synthetic Minority Over-sampling Technique (SMOTE) based boosting approach to balance the data to address the 27-way fold classification problem. We build C4.5 decision tree classifier in combination with SMOTE boosting algorithm using the novel contact map features and show that the prediction accuracy is enhanced to 64%. An additional advantage of our approach is the reduced dimensionality of the feature vector which is 11 whereas literature uses more than 100 features on average. Further, we propose an algorithm ExtractPatterns that extracts (non)rectangular 2D regions of contacts from the off-diagonal region in linear time. A feature vector of length 11 is formed using this study constituting diagonal and off-diagonal statistical features.

1 August 2017
Verified
Conference Paper
Closed access
SKSuvarna Vani Koneru
Suvarna Vani Koneru
KKK Praveen Kumar
K Praveen Kumar
MSM Veda Sri
M Veda Sri
Protein structure comparison is one of the most challenging problem in bioinformatics. This problem is modeled as a contact map overlap problem in which the similarity of the two proteins being compared is measured by the amount of overlap between their corresponding protein contact maps. To find a maximum overlap is proved to be an NP-hard problem in this area. Protein contact map is a two dimensional representation of protein tertiary structure. The goal of this work is to find frequent sub-graphs from contact maps. We propose a simple and computationally inexpensive algorithm is depth first search approach to contact map overlap problem for finding sub graphs from whole contact map of each protein structure. The sub-graph approach is evaluating on two bench mark data sets are SOKOL and SKOLNICK. It is interesting to note that along with achieving better sub-graphs is also obtained for certain protein folds. Further these sub graphs are used successfully in addressing the problem of protein fold classification.

1 April 2018
Verified
Conference Paper
Closed access
APA. Raghuvira Pratap
A. Raghuvira Pratap
JPJ V D Prasad
J V D Prasad
KKK Praveen Kumar
K Praveen Kumar
SBS Babu
S Babu
In this paper, we propose a solution to optimize traffic control by considering the earlier traffic analysis methodologies and social data. Traffic control system is a worldwide problem and the social networking sites can be plugged as a source of information for event identification, such as road traffic congestion and car accidents. Big amount of social data will increase in the upcoming years as the usage of portable electronic devices and Internet begin serving a larger population. Here with the availability of the driver's location data from portable and smart devices and feeds from micro-blogging sites such as Facebook and Twitter play a vital role in discovering a proper solution to traffic control in major noted cities. Social webs authorize population to achieve an integrity and give them participate it to produce a neighborhood. We produce a substantive monitoring blueprint for communication experience credit from the report of Twitter pour. The arrangement was designed from strand as occasion-driven root, lean on employment oriented composition and obtains chirps from Twitter planted on discrete search criteria being processes twitters, by letter of text digging methods; and performs Tweet regulation. To detect a target event, tweets have to be classified and clustered based on features like keywords in a tweet, structure of tweet and their context. Users are using Twitter to report real-life events. It focuses on identifying those events by analyzing this text stream in Twitter. The traffic detection system was inked for realtime monitoring of many areas of the road network, that allow for detection of traffic events almost in real time.

25 August 2023
Verified
Conference Paper
Closed access
HAHari Sai Babu Avvaru
Hari Sai Babu Avvaru
SDSrinivasa Reddy Dasarapalli
Srinivasa Reddy Dasarapalli
PKPraveen Kumar Kollu
Praveen Kumar Kollu
Satellite image utilization for data interpretation has significantly increased in the current scenario. Deep learning techniques have gained widespread popularity for analyzing satellite image data. However, a major challenge in this field is the presence of haze, which hampers accurate interpretation. Haze occurs when fine dust, smoke, or light vapors reduce the air's transparency, resulting in a lack of contrast in affected regions of satellite images. To tackle this issue, atmospheric correction is commonly employed, but it is a complex and time-consuming process that requires knowledge of various geophysical factors to achieve precise results. Hence, the objective of this research is to develop and implement image processing algorithms that can effectively restore pixels affected by haze, thereby improving the interpretability of satellite images. The proposed work consists of two main phases. Firstly, noise reduction techniques will be applied to the images to enhance their quality. In the second phase, a Convolutional Neural Network with a Residual structure will be utilized to dehaze the images. The evaluation of the proposed system will focus on the Kondapalli region and its surrounding areas in the Kondapalli dataset. This research aims to develop a robust solution that can enhance satellite images affected by haze, providing clearer and more interpretable data for various applications. The effectiveness of the proposed system will be compared with the Dark Object Subtraction method.