The image segmentation refers to the extraction of region of interest and it plays a vital role in medical image processing. This work proposes multilevel thresholding based on optimization technique for the extraction of region of interest and compression of DICOM images by an improved prediction lossless algorithm for telemedicine applications. The role of compression algorithm is inevitable in data storage and transfer. Compared to the conventional thresholding, multilevel thresholding technique plays an efficient role in image analysis. In this paper, the Particle Swarm Optimization (PSO), Darwinian Particle Swarm Optimization (DPSO), and Fractional Order Darwinian Particle Swarm Optimization (FODPSO) are employed in the estimation of the threshold value. The simulation results reveal that the FODPSO-based multilevel level thresholding generate superior results. The fractional coefficient in FODPSO algorithm makes it effective optimization with fast convergence rate. The classification and blending prediction-based lossless compression algorithm generates efficient results when compared with the JPEG lossy and JPEG lossless approaches. The algorithms are tested for various threshold values and higher value of PSNR indicates the proficiency of the proposed segmentation approach. The performance of the compression algorithms was validated by metrics and was found to be appropriate for data transfer in telemedicine. The algorithms are developed in Matlab2010a and tested on DICOM CT images.
Recently, artificial intelligence applications in magnetic resonance imaging have been applied in several clinical studies. The analysis of brain tumors without human intervention is considered a significant area of research because the extracted brain images need to be optimized using a segmentation algorithm that is highly resilient to noise and cluster size sensitivity problems and automatically detects the region of interest (ROI). In this paper, an improved orthogonal gamma distribution-based machine-learning approach is used to analyze the under-segments and over-segments of brain tumor regions to automatically detect abnormalities in the ROI. Further data imbalances due to improper edge matching in the abnormal region is sampled by matching the edge coordinates and sensitivity, and the selectivity parameters are measured using the machine learning algorithm. The benchmark medical image database was collected and analyzed to validate the efficiency and accuracy of the optimal automatic detection in tumor and non-tumor regions. The mean error rate of the algorithm was determined using a mathematical formulation. The system is evaluated based on experimental results that showed the method of orthogonal gamma distribution with the machine learning approach attained an accuracy of 99.55% in detecting brain tumors. This research contributes to the field of brain abnormality detection and analysis without human intervention in the health care sector. INDEX TERMS Magnetic resonance imaging, gamma distribution, machine-learning algorithm, brain abnormality.
Twitter sentiment analysis is an automated process of analyzing the text data which determining the opinion or feeling of public tweets from the various elds. For example, in marketing eld, political eld huge number of tweets is posting with hash tags every moment via internet from one user to another user. This sentiment analysis is a challenging task for the researchers mainly to correct interpretation of context in which certain tweet words are di cult to evaluate what truly is negative and positive statement from the huge corpus of tweet data. This problem violates the integrity of the system and the user reliability can be signi cantly reduced. In this paper, we identify the each tweet word and we are assigning a meaning into it. The feature work is combined with tweet words, word2vec, stop words and integrated into the deep learning techniques of Convolution neural network model and Long short Term Memory, these algorithms can identify the pattern of stop word counts with its own strategy. Those two models are well trained and applied for IMDB dataset which contains 50,000 movie reviews. With huge amount of twitter data is processed for predicting the sentimental tweets for classi cation. With the proposed methodology, the samples are experimentally collected from the real-time environment can be discriminated well and the e cacy of the system is improved. The result of Deep Learning algorithms aims to rate the review tweets and also able to identify movie review with testing accuracy as 87.74% and 88.02%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.