Search

Malaria is a significant global health issue, responsible for the highest rates of morbidity and mortality globally. This paper introduces a very effective and precise convolutional neural network (CNN) method that employs advanced deep learning techniques to automate the detection of malaria in images of red blood cells (RBC). Furthermore, we present an emerging and efficient deep learning method for differentiating between cells infected with malaria and those that are not infected. To thoroughly evaluate the efficiency of our approach, we do a meticulous assessment that involves comparing different deep learning models, such as ResNet-50, MobileNet-v2, and Inception-v3, within the domain of malaria detection. Additionally, we conduct a thorough comparison of our proposed approach with current automated methods for malaria identification. An examination of the most current techniques reveals differences in performance metrics, such as accuracy, specificity, sensitivity, and F1 score, for diagnosing malaria. Moreover, compared to existing models for malaria detection, our method is the most successful, achieving an accurate score of 1.00 in all statistical matrices, confirming its promise as a highly efficient tool for automating malaria detection. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) has gained significant attention in computer vision and human‐computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self‐attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model's comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI‐HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001. [ABSTRACT FROM AUTHOR]

The aim of this paper is to build a Question-Answering (QA) system considering Bengali and English language whose task is to generate questions along with their answers. There are two different process modules for Bengali and English. In each module, the main part is Question Generator (QG) which generates possible questions from a sentence by choosing a possible phrase as an answer-phrase. After that, the system has to perform some NLP tasks such as main verb decomposition, subjectauxiliary inversion (for English), replace answer-phrase with the question tag. Considering bivokti (িবভি), postfix and singular-plural, we have to choose the proper question tag and their form in Bengali. The selected answer-phrase for a question is used as the answer to that question. Another task of this system is to store the generated questions and their valid answers. Finally, the questions and their answers are displayed on the screen. The performance and accuracy of the system are evaluated on different Bengali and English texts. The performance of the system on question generation is 78.33% compared to the human being and the average percentage of accuracy of the generated questions is 76%. [ABSTRACT FROM AUTHOR]