Innovative Drug and Disease Prediction with Dimensionality Reduction and Intelligence Based Random Walk Methods

Some faulty genes causing cancer disease are inherited and some are caused by lifestyle factors. This research focuses on the implication of utilizing a family history information as a risk factor in estimating cancer incidence rate and the cost of insurance. The Maximum Likelihood Estimator (MLE) approach is applied to estimate the cancer incidence rates, while the transition probabilities correspond to each event under the insurance coverage are estimated using a continuous Markov Model. This study emphasizes on the application of R Analytics in assessing the risk factor and the graduation procedure of the estimated incidence rates. Our results show that the insurance cost for people with family history of cancer is significantly higher in comparison to those without family history of the disease especially for females. Overall, the cost of cancer insurance for both gender categories increases as age increases.

Section: Literature Reviewmentioning

confidence: 95%

Evaluation of Risk Factor for Cancer Insurance using R Analytics

Asmuni¹

2020

“…It can be viewed as the probability that a relevant document is retrieved by the query. To achieve recall of 100%, all documents returns in response to any query [12], [14]. Recall is defined as Table 6 shows the performance measure of different classifiers using Gabor features.…”

Section: Classificationmentioning

confidence: 99%

Machine Learning Approach towards Tomato Leaf Disease Classification

Gadade¹

2020

India in an agricultural country and the detection of diseases in first stage is very important to increase the crop yield. The bacterial spot, late blight, septoria leaf spot and yellow curved leaf diseases affect the crop quality of tomatoes. In this paper, to detect symptoms of disease, we have developed a module that classifies the plant leaf disease automatically. This paper presents a performance measure for different feature extraction techniques for tomato leaf disease detection including GLCM, Gabor and SURF and classification techniques including decision trees, SVM, KNN and Naïve Bayes. The dataset contains 500 images of tomato leaves with seven symptoms of diseases. We have modeled a system for automatic feature extraction and classification. We have evaluated the performance of the system using different performance measures to conclude with appropriate features set and classification technique for tomato leaf disease classification. The experimental results validate that Gabor features effectively recognizes different types of tomato leaf diseases. Accuracy of SVM is better as compared to other classification techniques but the execution time is more.

“…Several methods for whole heart segmentation in CT images have been proposed ( [1], [13]- [16]) that mostly utilized atlas or registration-based segmentation methods that are time consuming. In latest, Bui et al, [17] proposed random walk [18] mode segmentation method to segment the heart in contrast enhanced CT images where the heart and its substructures are clearly shown. This is different to the problem that is presented in this paper.…”

Section: Introductionmentioning

confidence: 99%

Level Set Based Whole Heart Segmentation in Non-Contrast Enhanced CT Images

Mokri¹

2019

Segmentation of the whole heat in CT images prior to lung radiotherapy is crucial to avoid undesirable radiation. In addition, heart segmentation is equally important in cardiovascular disease medical image analysis. However, heart segmentation in non-contrast enhanced CT image is a challenging problem due to the similarity of the grey level intensities of the heart with its surroundings. This paper aims to propose an automated heart segmentation method in non-contrast enhanced CT images. The method first identifies important slices during lung segmentation process to define an elliptical volume of interest (VOI) that approximately confines the heart region. Then 2D distance regularized (DRLSE) method is used to segment the heart slice by slice. The segmentation results are further improved by a refined elliptical VOI constructed from 3 different shapes of ellipses. Then 3 stages of DRLSE are used to obtain the final heart boundary. The segmentation results are validated based on Jaccard and Dice coefficients, false positive ratio (RFP) and false negative ratio (RFN) using 10 patient datasets where the average of Jaccard value of 0.86 and Dice value of 0.93 are obtained. Both values are more than 0.85 that indicates good heart segmentation in thoracic non-contrast enhanced CT image.