Mathews Correlation Research Articles

Predicting the risk of pipe failure using gradient boosted decision trees and weighted risk analysis

Pipe failure prediction models are essential for informing proactive management decisions. This study aims to establish a reliable prediction model returning the probability of pipe failure using a gradient boosted tree model, and a specific segmentation and grouping of pipes on a 1 km grid that associates localised characteristics. The model is applied to an extensive UK network with approximately 40,000 km of pipeline and a 14-year failure history. The model was evaluated using the Receiver Operator Curve and Area Under the Curve (0.89), briers score (0.007) and Mathews Correlation Coefficient (0.27) for accuracy, indicating acceptable predictions. A weighted risk analysis is used to identify the consequence of a pipe failure and provide a graphical representation of high-risk pipes for decision makers. The weighted risk analysis provided an important step to understanding the consequences of the predicted failure. The model can be used directly in strategic planning, which sets long-term key decisions regarding maintenance and potential replacement of pipes.

Classification of JAK1 Inhibitors and SAR Research by Machine Learning Methods

Janus kinase 1 (JAK1) is a key regulator of gene transcription, inhibition of JAK1 is an intervention for many diseases including rheumatoid arthritis and Crohn's disease. In this study, we collected a dataset containing 2982 JAK1 inhibitors, characterized molecules by MACCS fingerprints and Morgan fingerprints. We used support vector machine (SVM), decision tree (DT), random forest (RF) and extreme gradient boosting tree (XGBoost) algorithms to build 16 traditional machine learning classification models. Additionally, we utilized deep neural networks (DNN) to develop four deep learning models. The best model (Model 3B) built by RF and Morgan fingerprints achieved the accuracy (ACC) of 93.6% and Mathews correlation coefficient (MCC) of 0.87 on the test set. Furthermore, we made structure–activity relationship (SAR) analyses for JAK1 inhibitors, based on the output from the random forest models. After analyzing the important keys of two types of fingerprints, it was observed that some substructures such as pyrazole, pyrrolotriazolopyrimidine and pyrazolopyrimidine appeared frequently in highly active JAK1 inhibitors.

Classification of painful or painless diabetic peripheral neuropathy and identification of the most powerful predictors using machine learning models in large cross-sectional cohorts

BackgroundTo improve the treatment of painful Diabetic Peripheral Neuropathy (DPN) and associated co-morbidities, a better understanding of the pathophysiology and risk factors for painful DPN is required. Using harmonised cohorts (N = 1230) we have built models that classify painful versus painless DPN using quality of life (EQ5D), lifestyle (smoking, alcohol consumption), demographics (age, gender), personality and psychology traits (anxiety, depression, personality traits), biochemical (HbA1c) and clinical variables (BMI, hospital stay and trauma at young age) as predictors.MethodsThe Random Forest, Adaptive Regression Splines and Naive Bayes machine learning models were trained for classifying painful/painless DPN. Their performance was estimated using cross-validation in large cross-sectional cohorts (N = 935) and externally validated in a large population-based cohort (N = 295). Variables were ranked for importance using model specific metrics and marginal effects of predictors were aggregated and assessed at the global level. Model selection was carried out using the Mathews Correlation Coefficient (MCC) and model performance was quantified in the validation set using MCC, the area under the precision/recall curve (AUPRC) and accuracy.ResultsRandom Forest (MCC = 0.28, AUPRC = 0.76) and Adaptive Regression Splines (MCC = 0.29, AUPRC = 0.77) were the best performing models and showed the smallest reduction in performance between the training and validation dataset. EQ5D index, the 10-item personality dimensions, HbA1c, Depression and Anxiety t-scores, age and Body Mass Index were consistently amongst the most powerful predictors in classifying painful vs painless DPN.ConclusionsMachine learning models trained on large cross-sectional cohorts were able to accurately classify painful or painless DPN on an independent population-based dataset. Painful DPN is associated with more depression, anxiety and certain personality traits. It is also associated with poorer self-reported quality of life, younger age, poor glucose control and high Body Mass Index (BMI). The models showed good performance in realistic conditions in the presence of missing values and noisy datasets. These models can be used either in the clinical context to assist patient stratification based on the risk of painful DPN or return broad risk categories based on user input. Model’s performance and calibration suggest that in both cases they could potentially improve diagnosis and outcomes by changing modifiable factors like BMI and HbA1c control and institute earlier preventive or supportive measures like psychological interventions.

PC‐SNet for automated detection of prostate cancer in multiparametric‐magnetic resonance imaging

AbstractProstate cancer (PCa) is responsible for the maximum deaths of men across the world after lung cancer; hence, it should be diagnosed in the initial stages. Magnetic resonance imaging (MRI) commonly diagnoses PCa due to better visibility of desired organ and cancerous region over other modalities. Therefore, development of MRI‐based computer‐aided diagnosis (CAD) systems for PCa has become a recent area of research. Conventional methodologies used by researchers and radiologists were time consuming and prone to subjective errors due to manual interpretation. Thus, the CAD system helps in the early detection of PCa by reducing the computational complexity and increasing the detection accuracy with less chances of subjective errors. This article proposes a deep learning–based methodology named prostate cancer segmentation network (PC‐SNet) for the segmentation of the region of interest (ROI) from the MRI sub‐modalities T2‐weighted (T2W) and dynamic contrast enhanced (DCE). Further, the performance is analyzed using parameters such as accuracy, Mathews correlation coefficient (MCC), dice similarity coefficient (DSC), Jaccard Index (JI) or intersection over union (IOU), F‐score, and Hausdorff distance (HD). Finally, the performance of PC‐SNet is found to outperform fully convolutional network (FCN), semantic pixel wise segmentation (SegNet), residual network (ResNet), UNet, and ENet architectures.

Harnessing Fuzzy Rule Based System for Screening Major Histocompatibility Complex Class I Peptide Epitopes from the Whole Proteome: An Implementation on the Proteome of Leishmania donovani.

The development of peptide-based vaccines is enhanced by immunoinformatics, which predicts the patterns that B cells and T cells recognize. Although several tools are available for predicting the Major histocompatibility complex (MHC-I) binding peptides, the wide variants of human leucocyte antigen allele make it challenging to choose a peptide that will induce an immune response in a majority of people. In addition, for a peptide to be considered a potential vaccine candidate, factors such as T cell affinity, proteasome cleavage, and similarity to human proteins also play a major role. Identifying peptides that satisfy the earlier cited measures across the entire proteome is, therefore, challenging. Hence, the fuzzy inference system (FIS) is proposed to detect each peptide's potential as a vaccine candidate and assign it either a very high, high, moderate, or low ranking. The FIS includes input features from 6 modules (binding of 27 major alleles, T cell propensity, pro-inflammatory response, proteasome cleavage, transporter associated with antigen processing, and similarity with human peptide) and rules derived from an observation of features on positive samples. On validation of experimentally verified peptides, a balanced accuracy of ∼80% was achieved, with a Mathew's correlation coefficient score of 0.67 and an F-1 score of 0.74. In addition, the method was implemented on complete proteome of Leishmania donovani, which contains ∼4,800,000 peptides. Lastly, a searchable database of the ranked results of the L. donovani proteome was made and is available online (MHC-FIS-LdDB). It is hoped that this method will simplify the identification of potential MHC-I binding candidates from a large proteome.

Simulating urban growth through case-based reasoning

ABSTRACT Case-based reasoning (CBR) simplifies knowledge acquisition and is suitable for researching complex geographical problems. However, CBR analyses of land-use changes are difficult to apply in the study of urban growth due to shortcomings in the case structure and model algorithms. In response, this study proposes a three-step urban-growth simulation model based on CBR (UGSCBR). First, to adapt the CBR to an urban-growth simulation process, the characteristics of regional differentiation in geographical spaces are determined. Second, a comprehensive retrieval method is developed that improves upon traditional case-retrieval methods by giving full play to the comprehensive function of each component of the case. Third, a quantity demand constraint indirectly adds a time factor to solve the initial blurriness of the traditional CBR-inference cycle. Taking Jixi city as the research area, we test the accuracy of the proposed model. The total accuracy of simulation results is 95.4%, and the Kappa is 87.4%. The figure of merit and Mathews correlation coefficient are 0.151 and 0.23, respectively, indicating that the model can meet the application requirements. The results show that the UGSCBR model has strong flexibility and simplicity, and it provides an effective prediction method for urban growth.

Improved breast cancer detection using fusion of bimodal sonographic features through binary firefly algorithm

ABSTRACT Breast cancer is a major health issue and causes a larger number of deaths in women. As per GLOBOCAN statistics, breast cancer has surpassed lung cancer in 2020 with 2.3 million anticipated new cases which is 11.7% of total cancer cases. Sonography is used in addition to mammography to detect, describe and locate breast lesions effectively. Elastography and Echography are widely used sonographic techniques as they provide different and distinctive information for identifying breast diseases. To obtain improved detection performance, this work focuses on the fusion of Local Binary Pattern (LBP) texture features from ultrasound elastogram and echogram images followed by feature selection using Binary Firefly Algorithm (BFA) with Optimum Path Forest (OPF) classifier accuracy as a fitness function for feature selection. This method produces 97.3% accuracy, 96.2% sensitivity, 98.2% specificity, 97.3% precision, 96.2% F1 score, 94.71% Balanced Classification Rate, and Mathews Correlation Coefficient of 0.884 outperforming existing works.

A machine learning-based intrusion detection for detecting internet of things network attacks

The Internet of Things (IoT) refers to the collection of all those devices that could connect to the Internet to collect and share data. The introduction of varied devices continues to grow tremendously, posing new privacy and security risks—the proliferation of Internet connections and the advent of new technologies such as the IoT. Various and sophisticated intrusions are driving the IoT paradigm into computer networks. Companies are increasing their investment in research to improve the detection of these attacks. By comparing the highest rates of accuracy, institutions are picking intelligent procedures for testing and verification. The adoption of IoT in the different sectors, including health, has also continued to increase in recent times. Where the IoT applications became well known for technology researchers and developers. Unfortunately, the striking challenge of IoT is the privacy and security issues resulting from the energy limitations and scalability of IoT devices. Therefore, how to improve the security and privacy challenges of IoT remains an important problem in the computer security field. This paper proposes a machine learning-based intrusion detection system (ML-IDS) for detecting IoT network attacks. The primary objective of this research focuses on applying ML-supervised algorithm-based IDS for IoT. In the first stage of this research methodology, feature scaling was done using the Minimum-maximum (min–max) concept of normalization on the UNSW-NB15 dataset to limit information leakage on the test data. This dataset is a mixture of contemporary attacks and normal activities of network traffic grouped into nine different attack types. In the next stage, dimensionality reduction was performed with Principal Component Analysis (PCA). Lastly, six proposed machine learning models were used for the analysis. The experimental results of our findings were evaluated in terms of validation dataset, accuracy, the area under the curve, recall, F1, precision, kappa, and Mathew correlation coefficient (MCC). The findings were also benchmarked with the existing works, and our results were competitive with an accuracy of 99.9% and MCC of 99.97%.

Classification of cardiac diseases from ECG signals through bio inspired classifiers with Adam and R-Adam approaches for hyperparameters updation

This study emphasizes the classification of different cardiac diseases through bio-inspired classifiers with and without hyperparameters selection. Principal Component Analysis (PCA), Linearity Preserving Projection (LPP), Kernel-Linear Discriminant Analysis (K-LDA), and Variational Bayesian Matrix Factorization (VBMF) are used for the dimensionality reduction of ECG Signals. After the dimensionality reduction, the ECG features were classified using several classifiers such as Particle Swarm Optimization (PSO), Fish Swarm Optimization (FSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Support Vector Machine with (RBF (kernel)), K Nearest Neighbor (KNN) and Naïve Bayesian Classifier (NBC). The average accuracy for the classifiers without hyperparameters selection is 64.99%. Further, the classifiers (PSO, FSO, WOA, and GWO) performance is enhanced through the selection of hyperparameters by the Adam and Randomized Adam (R-Adam) approaches. The average accuracy for the classifiers with Adam and R-Adam is at 72.32% and 85.63%. In this research, the MIT-BIH datasets of Atrial Fibrillation (AF), Premature Ventricular Contraction (PVC), ST Change (ST), Supra Ventricular Tachycardia (SVT), Ventricular Tachycardia (VT) and Normal Sinus Rhythm (NSR) are utilized from the physionet archived database. The Overall Accuracy (OA), Mean Square Error (MSE), F1-Score (F1), Fowlkes Mallows Index (FM), Mathew Correlation Coefficient (MCC) and Error Rate (ER) of the different classifiers with and without Adam and R-Adam methods are evaluated. The result demonstrates that the GWO-R-Adam classifier with the LPP dimensionality reduction technique with 98.90% overall accuracy in classifying {ST}-{NSR} classes outperforms all other classifiers in terms of classification performance measures.

Comparative study of different wavelength selection methods in the transfer of crop kernel qualitive near-infrared models

The calibration transfer of qualitative models is of great significance for the further application and popularization of near-infrared spectroscopy (NIRS) in agriculture. Appropriate wavelength selection can effectively improve the transfer efficiency. In this study, the performances of some wavelength selection methods in the transfer of qualitative models were evaluated and compared under the combinations of different pretreatment conditions and transfer algorithms. The compared methods included full-spectrum, synergy interval partial least squares (SIPLS), variable importance in projection (VIP), correlation analysis–based wavelength selection (CAWS) method, and screening wavelengths with consistent and stable signals method (SWCSS). The transfers of two batches of crop kernel datasets (wheat kernel and corn kernel datasets) between instruments were used for testing. The differences in spectral ranges, pretreatments, and transfer algorithms affected the accuracy of the qualitative models during the transfer, and the results showed that CAWS showed a better transfer efficiency than other wavelength selection methods under the combinations of various pretreatment conditions and transfer algorithms. The validation Mathews correlation coefficients (tMCCp) of the transferred CAWS-optimized wheat and corn models (0.718 and 1, respectively) were respectively the second-highest and highest among the tMCCp of the models under all treatment combinations. Additionally, the comparison of the spectral ranges selected by these methods suggested that a better transfer efficiency can be achieved under the co-occurrence of the following conditions: the spectral ranges used for modeling contain characteristic absorption peaks are related to the target to be identified, and the response between instruments is relatively consistent.

LBCEPred: a machine learning model to predict linear B-cell epitopes.

B-cell epitopes have the capability to recognize and attach to the surface of antigen receptors to stimulate the immune system against pathogens. Identification of B-cell epitopes from antigens has a great significance in several biomedical and biotechnological applications, provides support in the development of therapeutics, design and development of an epitope-based vaccine and antibody production. However, the identification of epitopes with experimental mapping approaches is a challenging job and usually requires extensive laboratory efforts. However, considerable efforts have been placed for the identification of epitopes using computational methods in the recent past but deprived of considerable achievements. In this study, we present LBCEPred, a python-based web-tool (http://lbcepred.pythonanywhere.com/), build with random forest classifier and statistical moment-based descriptors to predict the B-cell epitopes from the protein sequences. LBECPred outperforms all sequence-based available models that are currently in use for the B-cell epitopes prediction, with 0.868 accuracy value and 0.934 area under the curve. Moreover, the prediction performance of proposed models compared to other state-of-the-art models is 56.3% higher on average for Mathews Correlation Coefficient. LBCEPred is easy to use tool even for novice users and has also shown the models stability and reliability, thus we believe in its significant contribution to the research community and the area of bioinformatics.

On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery

The vast majority of the outlet glaciers and ice streams of the polar ice sheets end in the ocean. Ice mass loss via calving of the glaciers into the ocean has increased over the last few decades. Information on the temporal variability of the calving front position provides fundamental information on the state of the glacier and ice stream, which can be exploited as calibration and validation data to enhance ice dynamics modeling. To identify the calving front position automatically, deep neural network-based semantic segmentation pipelines can be used to delineate the acquired SAR imagery. However, the extreme class imbalance is highly challenging for the accurate calving front segmentation in these images. Therefore, we propose the use of the Mathews correlation coefficient (MCC) as an early stopping criterion because of its symmetrical properties and its invariance towards class imbalance. Moreover, we propose an improvement to the distance map-based binary cross-entropy (BCE) loss function. The distance map adds context to the loss function about the important regions for segmentation and helps accounting for the imbalanced data. Using Mathews correlation coefficient as early stopping demonstrates an average 15% dice coefficient improvement compared to the commonly used BCE. The modified distance map loss further improves the segmentation performance by another 2%. These results are encouraging as they support the effectiveness of the proposed methods for segmentation problems suffering from extreme class imbalances.

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations.

The abnormal growth of human healthy cells is called cancer. One of the major types of cancer is sarcoma, mostly found in human bones and soft tissue cells. It commonly occurs in children. According to a survey of the United States of America, there are more than 17,000 sarcoma patients registered each year which is 15% of all cancer cases. Recognition of cancer at its early stage saves many lives. The proposed study developed a framework for the early detection of human sarcoma cancer using deep learning Recurrent Neural Network (RNN) algorithms. The DNA of a human cell is made up of 25,000 to 30,000 genes. Each gene is represented by sequences of nucleotides. The nucleotides in a sequence of a driver gene can change which is termed as mutations. Some mutations can cause cancer. There are seven types of a gene whose mutation causes sarcoma cancer. The study uses the dataset which has been taken from more than 134 samples and includes 141 mutations in 8 driver genes. On these gene sequences RNN algorithms Long and Short-Term Memory (LSTM), Gated Recurrent Units and Bi-directional LSTM (Bi-LSTM) are used for training. Rigorous testing techniques such as Self-consistency testing, independent set testing, 10-fold cross-validation test are applied for the validation of results. These validation techniques yield several metrics such as Area Under the Curve (AUC), sensitivity, specificity, Mathew's correlation coefficient, loss, and accuracy. The proposed algorithm exhibits an accuracy of 99.6% with an AUC value of 1.00.

Hybrid Active Contour Mammographic Mass Segmentation and Classification

This research implements a novel segmentation of mammographic mass. Three methods are proposed, namely, segmentation of mass based on iterative active contour, automatic region growing, and fully automatic mask selection-based active contour techniques. In the first method, iterative threshold is performed for manual cropped preprocessed image, and active contour is applied thereafter. To overcome manual cropping in the second method, an automatic seed selection followed by region growing is performed. Given that the result is only a few images owing to over segmentation, the third method uses a fully automatic active contour. Results of the segmentation techniques are compared with the manual markup by experts, specifically by taking the difference in their mean values. Accordingly, the difference in the mean value of the third method is 1.0853, which indicates the closeness of the segmentation. Moreover, the proposed method is compared with the existing fuzzy C means and level set methods. The automatic mass segmentation based on active contour technique results in segmentation with high accuracy. By using adaptive neuro fuzzy inference system, classification is done and results in a sensitivity of 94.73%, accuracy of 93.93%, and Mathew’s correlation coefficient (MCC) of 0.876.

Envisaging Employee Churn Using MCDM and Machine Learning

Employee categorisation differentiates valuable employees as eighty per cent of profit comes from twenty per cent of employees. Also, retention of all employees is quite challenging and incur a cost. Previous studies have focused on employee churn analysis using various machine learning algorithms but have missed the categorisation of an employee based on accomplishments. This paper provides an approach of categorising employees to quantify the importance of the employees using multi-criteria decision making (MCDM) techniques, i.e., criteria importance through inter-criteria correlation (CRITIC) to assign relative weights to employee accomplishments and fuzzy Measurement Alternatives and Ranking according to the Compromise Solution (MARCOS) method to divide employees into three categories. Followed by executing churn analysis of each category of employees and original dataset using machine learning algorithms to investigate the importance of employee categorisation. CatBoost, Support Vector Machine, Decision Tree, Random Forest and XGradient Boost algorithms have been used to analyse the categorised and non-categorised dataset on the accuracy, precision, recall and Mathew's Correlation Coefficient (MCC) to derive the best suitable algorithm for the used dataset. CatBoost algorithm showed the best results regarding performance measurements for categorised employees are better than all employee datasets.

Symptom Based Explainable Artificial Intelligence Model for Leukemia Detection

Leukemia is not only fatal in nature, it is also extremely expensive to treat. However, leukemia detection at early stage can save lives and money of the affected people, specially children among whom leukemia as a cancer type is very common. In this paper, we propose an explainable supervised machine learning model that accurately predicts the likelihood of early-stage leukemia based on symptoms only. The proposed model is developed based on primary data collected from two major hospitals in Bangladesh. Sixteen features of the datasets are collected through a survey on leukemia and non-leukemia patients in consultation with a specialist physician. Our explainable supervised model is based on a decision tree classifier which provides significantly better results compared to other algorithms and generates explainable rules that are ready to use. We have employed Apriori algorithm for generating explainable rules for leukemia prediction. In addition, feature analysis and feature selection are performed on the dataset to show the strength of individual features and enhance the performance of the classification models. Several classifiers are experimented on the dataset to show how the proposed model that is simple yet explainable, performs significantly better compared to most other models that we have used. The decision tree model proposed in our experiments has achieved 97.45% of accuracy, 0.63 of Mathew’s Correlation Coefficient (MCC) and 0.783 of area under Receiver Operating Characteristic (ROC) curve on the test set. We have also made the dataset and the source code of the methods used in this work available for future use by the researchers, which can be found in the following link: https://github.com/AkterHossain312/BDLeukemiaWithML.

Semi-supervised Long-tail Endoscopic Image Classification

Objective To explore the semi-supervised learning (SSL) algorithm for long-tail endoscopic image classification with limited annotations. Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir, the largest gastrointestinal public dataset with 23 diverse classes. Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling. After splitting the training dataset and the test dataset at a ratio of 4:1, we sampled 20%, 50%, and 100% labeled training data to test the classification with limited annotations. Results The classification performance was evaluated by micro-average and macro-average evaluation metrics, with the Mathews correlation coefficient (MCC) as the overall evaluation. SSL algorithm improved the classification performance, with MCC increasing from 0.8761 to 0.8850, from 0.8983 to 0.8994, and from 0.9075 to 0.9095 with 20%, 50%, and 100% ratio of labeled training data, respectively. With a 20% ratio of labeled training data, SSL improved both the micro-average and macro-average classification performance; while for the ratio of 50% and 100%, SSL improved the micro-average performance but hurt macro-average performance. Through analyzing the confusion matrix and labeling bias in each class, we found that the pseudo-based SSL algorithm exacerbated the classifier's preference for the head class, resulting in improved performance in the head class and degenerated performance in the tail class. Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification, especially when the labeled data is extremely limited, which may benefit the building of assisted diagnosis systems for low-volume hospitals. However, the pseudo-labeling strategy may amplify the effect of class imbalance, which hurts the classification performance for the tail class.

A Comparative Study of Machine Learning Regression Approach on Dental Caries Detection

Cavities are the most prevalent consequence of dental caries, an infectious condition that weakens the structure of the teeth and may be spread from person to person. Research on dental caries, which is considered one of the most widespread problems with oral health, has been conducted with the purpose of early diagnosis owing to the discomfort and expense of treatment. In recent years, artificial intelligence has been utilized to construct models for estimating the probability of dental caries. In the current research work, the Machine learning technique has been provided as the prominent solution in providing the prediction model to detect dental caries. This research work reports a few machine learning algorithms such as Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and Naïve Bayes (NB) for providing a model for dental caries detection. Finally, the said algorithms are evaluated over the influencing parameters such as accuracy, precision, recall, F1-Score, and Mathews Correlation Coefficient (MCC). The empirical analysis shows that the DT provides a more accurate model with an accuracy level of 85.62%.

A comparative study of corporate credit ratings prediction with machine learning

Credit scores are critical for financial sector investors and government officials, so it is important to develop reliable, transparent and appropriate tools for obtaining ratings. This study aims to predict company credit scores with machine learning and modern statistical methods, both in sectoral and aggregated data. Analyses are made on 1881 companies operating in three different sectors that applied for loans from Turkey’s largest public bank. The results of the experiment are compared in terms of classification accuracy, sensitivity, specificity, precision and Mathews correlation coefficient. When the credit ratings are estimated on a sectoral basis, it is observed that the classification rate considerably changes. Considering the analysis results, it is seen that logistic regression analysis, support vector machines, random forest and XGBoost have better performance than decision tree and k-nearest neighbour for all data sets.

Classification and Region Analysis of COVID-19 Infection Using Lung CT Images and Deep Convolutional Neural Networks

COVID-19 is a global health problem. Consequently, early detection and analysis of the infection patterns are crucial for controlling infection spread as well as devising a treatment plan. This work proposes a two-stage deep Convolutional Neural Networks (CNNs) based framework for delineation of COVID-19 infected regions in Lung CT images. In the first stage, initially, COVID-19 specific CT image features are enhanced using a two-level discrete wavelet transformation. These enhanced CT images are then classified using the proposed custom-made deep CoV-CTNet. In the second stage, the CT images classified as infectious images are provided to the segmentation models for the identification and analysis of COVID-19 infectious regions. In this regard, we propose a novel semantic segmentation model CoV-RASeg, which systematically uses average and max pooling operations in the encoder and decoder blocks. This systematic utilization of max and average pooling operations helps the proposed CoV-RASeg in simultaneously learning both the boundaries and region homogeneity. Moreover, the idea of attention is incorporated to deal with mildly infected regions. The proposed two-stage framework is evaluated on a standard Lung CT image dataset, and its performance is compared with the existing deep CNN models. The performance of the proposed CoV-CTNet is evaluated using Mathew Correlation Coefficient (MCC) measure (0.98) and that of proposed CoV-RASeg using Dice Similarity (DS) score (0.95). The promising results on an unseen test set suggest that the proposed framework has the potential to help the radiologists in the identification and analysis of COVID-19 infected regions.