Brain tumor detection in the initial stage is becoming an intricate task for clinicians worldwide. The diagnosis of brain tumor patients is rigorous in the later stages, which is a serious concern. ...Although there are related pragmatic clinical tools and multiple models based on machine learning (ML) for the effective diagnosis of patients, these models still provide less accuracy and take immense time for patient screening during the diagnosis process. Hence, there is still a need to develop a more precise model for more accurate screening of patients to detect brain tumors in the beginning stages and aid clinicians in diagnosis, making the brain tumor assessment more reliable. In this research, a performance analysis of the impact of different generative adversarial networks (GAN) on the early detection of brain tumors is presented. Based on it, a novel hybrid enhanced predictive convolution neural network (CNN) model using a hybrid GAN ensemble is proposed. Brain tumor image data is augmented using a GAN ensemble, which is fed for classification using a hybrid modulated CNN technique. The outcome is generated through a soft voting approach where the final prediction is based on the GAN, which computes the highest value for different performance metrics. This analysis demonstrated that evaluation with a progressive-growing generative adversarial network (PGGAN) architecture produced the best result. In the analysis, PGGAN outperformed others, computing the accuracy, precision, recall, F1-score, and negative predictive value (NPV) to be 98.85, 98.45%, 97.2%, 98.11%, and 98.09%, respectively. Additionally, a very low latency of 3.4 s is determined with PGGAN. The PGGAN model enhanced the overall performance of the identification of brain cell tissues in real time. Therefore, it may be inferred to suggest that brain tumor detection in patients using PGGAN augmentation with the proposed modulated CNN technique generates the optimum performance using the soft voting approach.
The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, ...namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals.
Artificial intelligence (AI) has been shown to be a formidable instrument in managing Big Healthcare Data, and it has seen considerable success in bioinformatics. The advancement of big data in ...biological sciences has given rise to big data analytics (BDA) and artificial intelligence (AI). Because the AI methodologies used in bioinformatics are parallel and iterative, scalable big data management employing distributed and parallel technology is possible. The growth of bioinformatics has resulted in significant storage and administration issues; to share information, such large amounts of data must be handled efficiently. Computational developments in information technology have enabled analytical systems to cope with such data. Therefore, this study emphasizes the impact of big data and BDA in bioinformatics. A practical use of BDAs and AI in cancer classification was given, combining a unique Analysis of Variance (ANOVA) approach with Ant Colony Optimization (ACO) as a hybrid feature selection to pick significant genes while minimizing gene redundancy. Deep Convolutional Neural Networks (DCNN) were employed to classify the datasets. It is because microarray data are produced from gene expression data, and it frequently has a limited number of samples but a huge feature collection size. Using the same datasets, the suggested system outperformed earlier state-of-the-art approaches. The results of the proposed model on all the Leukemia, DLBCL, Colon, and SRDCT datasets revealed an average classification accuracy of 97.7%, 99.9%, 99.9% and 100%, respectively.
AutoML Trading: A Rule-Based Model to Predict the Bull and Bearish Market Padhi, Dushmanta Kumar; Padhy, Neelamadhab; Panda, Baidyanath ...
Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering,
03/2024
Journal Article
Abstract Premature ovarian failure (POF) is unexplained amenorrhoea (>6 months), increased FSH (>20 IU/l) and LH occurring before 40 years. Several genes are reported as having significance in POF, ...including genes governing regulation of the hypothalamic–pituitary–ovarian axis, but their role in ovarian physiology is not known. Deletions or translocations in Xq arm have been found to be associated with POF, assuming presence of ovarian-related genes but ovary-related function of these genes is unclear. Several researchers have suggested specific loci on Xq critical region, POF1 and POF2 and genes DIA , FMR1 and FMR2 . The understanding of ovarian physiology, its regulation and genes involved is important to explain the causes of POF. Some genes coordinate development of germ cell to primordial stage, e.g. GDF9 , BMP15 and NGF , while others regulate development of further stages, such as FSH and LH. Mutation in these genes may lead to female infertility and are likely to be candidate genes for POF. Recently, association between blepharophimosis–ptosis–epicanthus inversus syndrome type 1 and POF has emerged as a possibility. Galactosaemia is also shown to be important in POF due to toxic effects of accumulated galactose or downstream products. Thus, understanding the role of several genes can be used for the appropriate genetic diagnosis, research and in the clinical practice of POF.
Objective. Present study was designed for carrying out the mutational analysis of the entire Androgen receptor (AR) gene including two microsatellite (CAG)n, (GGN)n, promoter region in cases of ...premature ovarian failure (POF) and primary amenorrhea (PA).
Design. Previous reports of AR knockout mice model showed POF phenotype, this draws an attention on the role of AR gene in the aetiology of POF for the case-control association studies in POF samples (n = 133), PA samples (n = 63) and control samples (n = 200).
Results. We identified six mutations including four novel mutations, i.e. c.636G > A, c.1885 + 9C > A, c.1948A > G, c.1972C > A, and two previously reported mutations, i.e. c.639G > A, c.2319−78T > G. Repeat length variation was noted in the two microsatellite regions CAG and GGN, located in the coding region of exon 1 at the N-terminal region of the AR gene. The CAG repeat length was homogenously distributed with the same frequency and no association among all cases and controls. The GGN repeat showed a significant association among the SS and SL allele with p = 0.0231 and p = 0.0476, respectively, among the POF/control samples.
Conclusions. Thus, AR gene mutations may play a role in the genetic cause of POF. Identification of the underlying genetic alteration of the AR gene is important for a proper diagnosis of POF subjects.