4.Conference Paper (06)

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/3946

Browse

Now showing 1 - 6 of 6

AN EXPLORATORY DATA ANALYSIS ON AIR QUALITY DATA OF TRIVANDRUM
(Springer Link, 2023) Santhana Lakshmi, V; Vijaya, M S
Data analysis is the most integral part of any research. It is the process of examining the data using statistical methods to identify the hidden patterns and trends which aid in making decisions. This helps in understanding the distribution, correlation, outliers, and missing values found in the data. In this paper, data analysis is performed over the air pollutant data and the meteorological data that influences air pollution. The meteorological data for the period of 4 years of Trivandrum city was taken for the purpose of analysis. The dataset includes 26,544 instances and 23 features. Pollutant parameters such as PM2.5, PM10, CO, SO2, ozone, NOX, and NH3 are considered for analysis. Meteorological features taken for analysis include temperature, dew, humidity, wind speed, wind direction, etc. Meteorological features play a substantial role in identifying air pollution. Boxplots, heat maps, pair plots, and histograms were used to reveal the distribution and correlation between the attributes. From the analysis, it has been identified that the features like sea level pressure, PM2.5, PM10, CO, NOX, NH3, SO2, and ozone are positively correlated with air quality index whereas features like, dew, humidity, wind speed, cloud cover are negatively correlated with air quality index. The results of the data analysis assist in preparing the data for further research.
OPTIMIZING PRE-PROCESSING FOR FOETAL CARDIAC ULTRA SOUND IMAGE CLASSIFICATION
(Springer Link, 2023-03-28) Divya, M O; Vijaya, M S
Recent research shows that Foetal cardiac anomalies which gets diagnosed postnatally makes a grave negative impact on the delivery outcome. The situation becomes lethal when severe anomalies get diagnosed after the baby is born. Many medical researches shows that delivery outcome could be better when the anomaly is diagnosed prenatally. There are hardly any research and development happening in this area where automation and prediction are on prime focus for finding the cardiac anomaly using Ultra Sound Imaging Technique (USIT). The USIT during the second trimester is universal for every pregnant woman also the second trimester is the best time to take appropriate medical assistance for the foetus in case of anomaly. This research is experimental study to setup a standard dataset for foetal cardiac anomaly USITs and to identify the appropriate pre-processing technique for binary classification of USIT. The 1200 images in the dataset are organised in two classes half of the images are with anomaly and other half without anomaly. The class with anomaly includes images representations from 17 anomalies which is theoretically established as structural anomalies of heart. All anomalies are present in the dataset approximately equal in ratio. The dataset has undergone the following pre-processing techniques, blur removal, noise removal and contrast normalisation. The Alex-net model is trained to create a binary classifier for the FetalEcho dataset after applying the different pre-processing techniques. Eight rounds of classification have been performed with eight versions of the FetalEcho dataset. The worst results were shown by the row dataset (FetalEcho_V01) when the classification experiment have been performed with the AlexNet classifier. The dataset FetalEcho_V05, created after removing blur and noise, is identified as the best performance for classification, amongst the eight datasets.
MULTI-CLASS CLASSIFICATION OF INSECTS USING DEEP NEURAL NETWORKS
(IEEE Xplore, 2023-05-24) Santhiya, M; Priyadharshini, A; Agshalal Sheeba, J; Karpagavalli, S
Insects are crucial to the functioning of nature. There are more than a million described species of living beings in the modern world. Since the majority of today’s farmers and agriculturalists are newer generations of people, identifying and classifying insects is essential. The classification of insects is a difficult undertaking in the agricultural industry. In the proposed work, multi-class classification of insects using a Convolutional Neural Network architecture, VGG19 had been carried out. In the taxonomic classification of insects, 5 insects fall within insecta class which include butterfly, dragonfly, grasshopper, ladybird, and mosquito data had been collected to train, test, and validate the convolutional neural network, The performance of the model had been analyzed using different parameters and presented.
LUNG CANCER DISEASE PREDICTION AND CLASSIFICATION BASED ON FEATURE SELECTION METHOD USING BAYESIAN NETWORK, LOGISTIC REGRESSION, J48, RANDOM FOREST, AND NAÏVE BAYES ALGORITHMS
(IEEE Xplore, 2023-05-26) Viji Cripsy, J; Divya, T
People who have never smoked can get lung cancer, but smokers have a higher risk than non-smokers. Any aspect of the respiratory system can be affected by lung cancer, which can start anywhere in the lungs, Different classification methods are used for lung cancer prediction. This article uses five different classification algorithms to predict lung cancer in patients using Kaggle dataset. Bayesian Network, Logistic Regression, J48, Random Forest and Naive Bayes methods are used, Based on the carefully identified correct and incorrect cases, the quality of the result was measured using the evaluation technique and the WEKA tool. The experimental results showed that Logistic Regression performed best (91.90 % ), followed by Naive Bayes (90.29 % ), Bayesian Network (88.34 % ), j48 (86.08 % ) and Random Forest (90.93 % ).
A SURVEY AND ANALYSIS OF DEEP LEARNING TECHNIQUES FOR BIRD SPECIES CLASSIFICATION
(IEEE Xplore, 2023-07-07) Sivaranjani, B; Karpagavalli, S
The ability to accurately identify the species of a bird in an image is crucial. A bird’s species identification can be accomplished using images and audios. In earlier periods, the audio of birds are utilized to possibly recognize the different species of birds. But, background noise from things like birds, insects, and the wind makes it difficult for this method to produce a reliable result. Comparatively, observer’s finds images are better than audios. Using images, people are better able to discriminate between birds. However, because of the inexperience of most bird watchers and the similarity of bird forms and backgrounds, identifying birds can be difficult. To address this, Deep Learning (DL) models have been implemented to efficiently extract features from photos collected for recognition. DL models for bird species identification provides more accuracy. The recently proposed transfer learning and spatial pyramid pooling efficiently classify bird spicies. Another recently proposed Mask-CNN based method solved few shot classifcation problem effectively. But, both of these method are suffered to distinguish the subcategory of spicies form main categories. In this article, the of bird species identification techniques are studied in brief to encourage further research in this field. First, the review is planned to investigate the DL algorithms for identifying the different bird species types. Next, the merits and demerits of every algorithms are analyzed based on its performance. Finally, potential improvements are emphasized to achieve greater efficiency in identifying the bird species.
SECURED DATA TRANSMISSION USING PARETO OPTIMIZATION BASED LION SWARM OPTIMIZATION AND DOUBLE ENCRYPTION BASED BLOWFISH ALGORITHM IN WSN
(Association for Computing Machinery, 2023-12) Gripsy Viji, J; Kowsalya, R; Banupriya, C.V; Sathya, R
The protection of wireless sensor networks is a complex challenge due to the inherent characteristics of the sensors themselves. These sensors are characterized by their low memory capacity, constrained energy resources, and lack of early awareness regarding their specific placement within the distribution environment. In order to safeguard the integrity and confidentiality of data during transmission, it is imperative to uphold fundamental security measures. This duty elucidates many methodologies for safeguarding data transmission. The primary objective of this research endeavor is to ensure the security of the Wireless Sensor Network (WSN). Several studies and approaches have been proposed; nonetheless, the comprehensive understanding of time and safety remains largely unexplored. The current methodologies exhibit limitations in terms of temporal efficiency and the security of Wireless Sensor Networks (WSNs). In order to address the aforementioned concerns, this research study proposes the utilization of the Pareto Optimization Based Lion Swarm Optimization and Double Encryption based Blowfish method (PLSO-DEBF) method as a means to enhance overall system performance. The primary contributions of this study encompass the development of a comprehensive system model, the utilization of PLSO-DEBF for the selection of transmission nodes, and the incorporation of secure data transmission inside the system model. By leveraging the efficient algorithms of Wireless Sensor Networks (WSNs), this approach demonstrates enhanced performance.