B-Scopus

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/3730

Browse

Search Results

Now showing 1 - 10 of 25

AIR QUALITY INDEX PREDICTION MODEL USING TEMPORAL FUSION TRANSFORMER
(International Journal of Intelligent Systems and Applications in Engineering, 2024-02-02) Santhana Lakshmi, V; Vijaya, M S
Air pollution’ emerges as a substantial universal concern with far-reaching consequences for people health, affecting numerous persons worldwide. Its adverse effects encompass various respiratory and cardiovascular issues. The Air Quality Index (AQI) serves as a numeric gauge for evaluating air quality, furnishing details about pollutant levels like particulate matter, ammonia, carbon monoxide, NO2, ozone and SO2. The anticipation of AQI proves instrumental in empowering individuals and communities to undertake precautionary measures against the detrimental impacts of air pollution. Leveraging deep learning for AQI prediction becomes imperative. Positioned within machine learning, deep learning employs artificial neural networks as a potent tool to address complex challenges. This study employs an attention-based Arcane Neural Web, specifically the TFT, for constructing the estimating model. The model's efficacy is then juxtaposed with other deep learning models, including Long Short-Term Memory, Bidirectional Long Short-Term Memory, and Fenced Repeated Unit
GRAPH CONVOLUTIONAL NEURAL NETWORK FOR IC50 PREDICTION MODEL WITH DRUG SMILES GRAPHS AND GENE EXPRESSIONS OF AMYOTROPHIC LATERAL SCLEROSIS
(Journal of Theoretical and Applied Information Technology, 2024-01) Devipriya, S; Vijaya, M S
IC50 prediction for neurodegenerative disorders like Amyotrophic Lateral Sclerosis is crucial in biomedical studies. Traditional machine learning models that use molecular descriptors and gene expression for building IC50 prediction models produce less accuracy and also most of the descriptors created by different tools are irrelevant and undefined. In this paper, a Graph Convolutional Neural Network, a deep learning algorithm, is employed for constructing a more precise IC50 prediction model. The model leverages the structural properties of drug molecules represented in graph format, and incorporates gene expression data as global features. So, the model is able to learn drug-gene interactions better. The drug-gene interactivity is learned by the model without drug-induced gene expressions as it is not found for most of the diseases. The work is implemented with well-known and most relevant 80 drugs related to ALS based on the pIC50 values of 32 protein targets of ALS disorder. The Canonical Smiles graph and their corresponding IC50 values of 80 drugs have been derived from the ChEMBL databases. Based on information from the Repurposing Hub in the Depmap database gene expression data for drug-related genes connected with ALS-related conditions is collected. The predictive results show that the proposed GCNN model with fine-tuned hyperparameters achieves MAE of 0.18, RMSE of 0.16 and R2 Score of 0.90.
AN INTELLIGENT DEEP LEARNING BASED AQI PREDICTION MODEL WITH POOLED FEATURES
(Journal of Theoretical and Applied Information Technology, 2024-01-15) Lakshmi Santhana, V; Vijaya, M S
Airborne pollution poses a significant threat to public health, leading to detrimental health effects. Despite global economicgrowth, ensuring access to clean air has become increasingly challenging worldwide. The contamination of air occurs as dust particlesand smoke, released by vehicles and industries, suspend into the atmosphere, exacerbating the challenge of providing clean air forpeople. Hence, it is imperative to predict the Air Quality Index (AQI) to safeguard the lives of people, especially considering the severe health effects caused by the inhalation of small particles. This paper outlines a deep learning methodology for constructing Air Quality Index (AQI) prediction models. The models utilize hourly meteorological data and pollutant information, aiming to fulfill the critical requirement for precise assessments of air quality. The aim of this paper is to formulate predictive models for AQI in Thiruvananthapuram, Kerala, employing deep learning algorithms, thereby addressing the escalating challenge of air pollution in theregion. Deep neural network architectures, such as Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BI-LSTM), and Gated Recurrent Unit (GRU), are implemented to construct the prediction model. When compared to other algorithms,GRU demonstrated promising outcomes. The findings of this research contribute not only to the advancement of AQI prediction models but also highlight the practical significance of employing deep learning techniques for accurate and timely air quality assessments. The outcomes have practical implications for public health and environmental management, providing a basis for informed decision-making in mitigating the adverse effects of air pollution.
REVOLUTIONIZING FOETAL CARDIAC ANOMALY DIAGNOSIS: UNLEASHING THE POWER OF DEEP LEARNING ON FOETALECHO IMAGES
(Journal of Theoretical and Applied Information Technology, 2023) Divya, M O; Vijaya, M S
The use of Artificial Intelligence (AI) has amplified in various fields, with remarkable results in medicine in recent times. Despite the potential of AI in the medical field, there are still many unexplored areas due to data unavailability. One such area is cardiac foetal anomaly diagnosis, which is poorly diagnosed globally with a rate of only 50%. The complexity of the task requires a high level of expertise to understand minute hints and conduct thorough exams for accurate image captures. In this research, the FoetalEcho_V01 dataset was used for foetal cardiac anomaly diagnosis, consisting of pre-classified ultrasound images representing 15 different anomalies and a class representing normal heart images. The deep learning models which are efficient in producing potential classifiers for ultra sound scan images are identified. The models are CNN, AlexNet, VGG16 and ResNet50. The best performing deep learning models were used to produce classifiers, and their performance was evaluated. The results showed that the deep learning models performed well on the FoetalEcho_V01 dataset images for diagnosing structural cardiac anomalies in the foetus, with consistent performance as demonstrated by the calculated standard deviation. The results obtained from the research for the FetalEcho_V05 dataset are as follows. The CNN model achieved a precision of 0.94, recall of 0.89, accuracy of 0.90, and F1 score of 0.91. Comparatively, the AlexNet model demonstrated a precision of 0.92, recall of 0.87, accuracy of 0.89, and F1 score of 0.89. The VGG16 model exhibited precision of 0.91, recall of 0.85, accuracy of 0.87, and F1 score of 0.88. Lastly, the ResNet50 model displayed a precision of 0.93, recall of 0.90, accuracy of 0.93, and F1 score of 0.93. Among these models, the CNN model emerged as the best classifier for the FetalEcho_V05 dataset, with its superior performance in terms of precision, recall, accuracy, and F1 score.
TEMPORAL FUSION TRANSFORMER: A DEEP LEARNING APPROACH FOR MODELING AND FORECASTING RIVER WATER QUALITY INDEX
(International Journal of Intelligent Systems and Applications in Engineering, 2023-07-23) Jitha P, Nair; Vijaya, M S
Water quality is a major factor when it comes to human and environmental health. The WQI is a key performance indicator for water management effectiveness. Water quality changes over time due to several seasonal attributes and physiochemical properties. Asthe seasons change at each site, the weather records are transformed into time series data, and the values of the physiochemical parameters shift accordingly. This paper introduces a novel temporal fusion transformer architecture for modelling and forecasting river water quality index. The WQI prediction model for the Bhavani River utilizes the temporal fusion transformer to incorporate temporal features fromvarious scales of time series data obtained from monitoring stations.The performance results of the study are compared with other existing prediction models and demonstrated the effectiveness of the temporal fusion transformer approach for modelling and forecasting river water quality.
ARTIFICIAL INTELLIGENT MODELS FOR AUTOMATIC DIAGNOSIS OF FOETAL CARDIAC ANOMALIES: A META-ANALYSIS
(Springer Link, 2023-01-01) Divya, M O; Vijaya, M S
The foetal anomaly scanning is one of the most challenging areas where accuracy of diagnosis much fluctuating with respect to the expertise of the radiologist and the mental equilibrium of the radiologist at the time of scanning. Amongst the various anomalies, foetal heart anomaly diagnosis expects precise and sensitive intellectual presence since perilous congenital heart diseases are one of the common causes resulting in the major population of infant mortality or into permanent natal faults. The accuracy of manual diagnosis of foetal cardiac abnormalities from the ultrasound scan images vary based on the human expertise and the presence of mind. Therefore, the scope of computer-assisted judgement can produce accurate diagnosis irrespective of the operator’s profile. Numerous researches are going on to explore the scope of computer-assisted judgement of abnormalities using ultrasound imaging technique (USIT), specifically using machine learning and deep learning models. This work exploits the opportunities of computer-assisted diagnosis in foetal cardiac anomaly diagnosis as this is one of the most sensitive areas where appropriate diagnosis can save a life and a wrong diagnosis may lose a life unnecessarily.
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.
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.
RECURRRENT NEURAL NETWORK BASED MODEL FOR AUTISM SPECTRUM DISORDER PREDICTION USING CODON ENCODING
(Springer Link, 2022) Pream Sudha, V; Vijaya, M S
Deep learning methods are noteworthy tools that go together with traditional machine learning techniques to enable computers learn from data and create smarter applications. Deleterious gene classification is an important task in a standard computational framework for biomedical data analysis. As gene sequences are high dimensional and do not represent explicit attributes for computational modelling, extracting features from them becomes a complex task. Recently neural deep learning architectures automatically extract valuable features from input patterns. The principal idea of this work is to exploit the power of Recurrent Neural Networks (RNN) to learn sequential patterns through high-level information associated with observed signals which in turn can be used for classification. Classification of affected genes that cause disease like Autism-spectrum disorder (ASD) is a noteworthy challenge in biomedical research. Long Short Term Memory (LSTM) units go well with sequence-based tasks with long-term dependencies and hence this work examines a stacked LSTM architecture for classifying genes causing ASD. The model is trained and tested with two hand crafted datasets and a codon encoded dataset. Experiments revealed the superiority of these advanced recurrent units compared to the traditional Deep Neural Networks and Bi-directional RNNs distinctively with codon encoded dataset.
OVERLAPPING COMMUNITY STRUCTURE DETECTION USING TWITTER DATA
(International Journal on Emerging Technologies, 2020) Sathiyakumari, K; Vijaya, M S
Overlapping community detection is progressively becoming a significant issue in social network analysis (SNA). Faced with massive amounts of information while simultaneously restricted by hardware specifications and computation time limits, it is difficult for clustering analysis to reflect the latest developments or changes in complex networks. Techniques for finding community clusters mostly depend on models that impose strong explicit and/or implicit priori assumptions. As a consequence, the clustering effects tend to be unnatural and stay away from the intrinsic grouping natures of community groups. In this method, a process of enumerating highly cohesive maximal community cliques is performed in a random graph, where strongly adjacent cliques are mingled to form naturally overlapping clusters. These approaches can be considered as a generalization of edge percolation with great potential as a community finding method in real-world graphs. The main objective of this work is to find overlapping communities based on the Clique percolation method. Variants of clique percolation method such as Optimized Clique percolation method, Parallel Clique percolation method have also been implemented. This research work focuses on the Clique Percolation algorithm for deriving community from a sports person’s networks. Three algorithms have been applied for finding overlapping communities in the sports person network in which CPM algorithm discovered more number of communities than OCPM and PCPM. CPM overlapping algorithm discovered 198 communities in the network. OCPM algorithm found 180 different sizes of communities. PCPM algorithm discovered 170 communities and different size of the node in the graph. The community measures such as size of the community, length of community and modularity of the community are used for evaluating the communities. The proposed parallel method found a large number of communities and modularity score with less computational time. Finally, the parallel method shows the best performance is detecting overlapping communities from the sports person network.

B-Scopus

Browse

Filters

Settings

Sort By

Results per page

Search Results