The most aggressive form of brain tumor is gliomas, which leads to concise life when high grade. The early detection of glioma is important to save the life of patients. MRI is a commonly used approach for brain tumors evaluation. However, the massive amount of data provided by MRI prevents manual segmentation in a reasonable time, restricting the use of accurate quantitative measurements in clinical practice. An automatic and reliable method is required that can segment tumors accurately. To achieve end-to-end brain tumor segmentation, a hybrid deep learning model RMU-Net is proposed. The architecture of MobileNetV2 is modified by adding residual blocks to learn in-depth features. This modified Mobile Net V2 is used as an encoder in the proposed network, and upsampling layers of U-Net are used as the decoder part. The proposed model has been validated on BraTS 2020, BraTS 2019, and BraTS 2018 datasets. The RMU-Net achieved the dice coefficient scores for WT, TC, and ET of 91.35%, 88.13%, and 83.26% on the BraTS 2020 dataset, 91.76%, 91.23%, and 83.19% on the BraTS 2019 dataset, and 90.80%, 86.75%, and 79.36% on the BraTS 2018 dataset, respectively. The performance of the proposed method outperforms with less computational cost and time as compared to previous methods.

GSA is badly suffering from slow convergence rate and poor local search ability, when solving complex optimization problems. To solve this problem, a new hybrid population-based algorithm is proposed with the combination of dynamic multi swarm particle swarm optimization and gravitational search algorithm (GSADMSPSO). The proposed algorithm has divided the main population of masses into smaller sub-swarms and also stabilizing them by presenting new neighborhood strategy. Then, by adopting the global search ability of proposed algorithm, each agent (particle) improves the position and velocity. The main idea is to integrate the ability of GSA with the DMSPSO to enhance the performance of exploration and exploitation of a proposed algorithm. In order to evaluate the competences of the proposed algorithm, benchmark functions are employed. The experimental results have been confirmed a better performance of GSADMSPSO as compared to the other gravitational and PSO variants in terms of fitness rate.

Urdu language is being spoken by over 64 million people and its Roman script is very popular, especially on social networking sites. Most users prefer Roman Urdu over English grammar for communication on social networking platforms such as Facebook, Twitter, Instagram and WhatsApp. For research, Urdu is a poor resource language as there are a few research papers and projects that have been carried out for the language and vocabulary enhancement in comparison to other languages especially English. A lot of research has been made in the domain of sentiment analysis in English but only a limited work has been performed on the Roman Urdu language. Sentiment analysis is the method of understanding human emotions or points of view, expressed in a textual form about a particular thing. This article proposes a deep learning model to perform data mining on emotions and attitudes of people using Roman Urdu. The main objective of the research is to evaluate sentiment analysis on Roman Urdu corpus containing RUSA-19 using faster recurrent convolutional neural network (FRCNN), RCNN, rule-based and N-gram model. For assessment, two series of experiments were performed on each model, binary classification (positive and negative) and tertiary classification (positive, negative, and neutral). Finally, the evaluation of the faster RCNN model is analyzed and a comparative analysis is performed for the outcomes of four models. The faster RCNN model outperformed others as the model achieves an accuracy of 91.73% for binary classification and 89.94% for tertiary classification.

Multi-culture facial expression recognition remains challenging due to cross cultural variations in facial expressions representation, caused by facial structure variations and culture specific facial characteristics. In this research, a joint deep learning approach called racial identity aware deep convolution neural network is developed to recognize the multicultural facial expressions. In the proposed model, a pre-trained racial identity network learns the racial features. Then, the racial identity aware network and racial identity network jointly learn the racial identity aware facial expressions. By enforcing the marginal independence of facial expression and racial identity, the proposed joint learning approach is expected to be purer for the expression and be robust to facial structure and culture specific facial characteristics variations. For the reliability of the proposed joint learning technique, extensive experiments were performed with racial identity features and without racial identity features. Moreover, culture wise facial expression recognition was performed to analyze the effect of inter-culture variations in facial expression representation. A large scale multi-culture dataset is developed by combining the four facial expression datasets including JAFFE, TFEID, CK+ and RaFD. It contains facial expression images of Japanese, Taiwanese, American, Caucasian and Moroccan cultures. We achieved 96% accuracy with racial identity features and 93% accuracy without racial identity features.

Power quality disturbances (PQDs) occur as the use of non-linear load and renewable-based micro-grids increases. This paper presents a new algorithm that consists of the discrete orthogonal S-transform (DOST) in the feature extraction stage, compressive sensing (CS) in the feature reduction stage, and a deep stacking network (DSN) for the automatic classification of single and multiple PQDs. It compresses the extracted feature matrix (orthogonal S-matrix coefficients) to minimize the computational process and provide more diversified features. Firstly, PQDs data is generated from a modified IEEE 13 bus system with wind grid integration, both synthetically and in real time. Moreover, compressive measurements of 24 types of multiple PQDs events and nine types of single PQDs events of synthetic and real data, and 12 type of three-phase single and multiple PQDs from the modified IEEE wind grid integration are fed to a proposed DSN classifier for PQD recognition. The DOST-based CS feature extraction technique achieves good robustness and time-frequency localization while retaining useful information. The DSN classifier method utilizes a Batch-mode gradient as a fine-tune, which has less noise gradient and improved efficiency of PQD classification. A noise level of 20 dB to 50 dB is considered. Other models, such as k-Nearest Neighbor (KNN), Multiclass Support Vector Machine (MSVM), and ensemble learner methods, are also developed to compare the efficiency. The high classification results demonstrate that the DOST-CS feature extraction and the DSN classifier have high precision in identifying multiple power quality events, even in noisy conditions.

Text classification (TC) is a crucial practice in case of organizing a vast number of documents. The computational complexity of the TC process is usually high because of the large dimensionality of the feature space. Feature Selection (FS) procedures are used to extract the helpful information from the feature space and results in dimensionality reduction. The development of the FS method that reduces the dimensionality of feature space without compromising the categorization accuracy is desirable. This paper proposes a Self-Inertia Weight Adaptive Particle Swarm Optimization (SIW-APSO) based FS methodology to enhance the performance of text classification systems. SIW-APSO has fast convergence phenomena due to its high search competency and ability to find feature sub-set efficiently. For text classification, the K-nearest neighbors algorithm is used. The experimental analysis shows that the proposed method outperformed the existing state-of-the-art algorithms on the Reuters-21578 data set by achieving 98.60% precision, 96.56% recall, and 97.57% F1 score.