Brain tumor (BT) is a serious issue and potentially deadly disease that receives much attention. However, early detection and identification of tumor type and location are crucial for effective treatment and saving lives. Manual diagnoses are time-consuming and depend on radiologist experts; the increasing number of new cases of brain tumors makes it difficult to process massive and large amounts of data rapidly, as time is a critical factor in patients’ lives. Hence, artificial intelligence (AI) is vital for understanding disease and its various types. Several studies proposed different techniques for BT detection and classification. These studies are on machine learning (ML) and deep learning (DL). The ML-based method requires handcrafted or automatic feature extraction algorithms; however, DL becomes superior in self-learning and robust in classification and recognition tasks. This research focuses on classifying three types of tumors using MRI imaging: meningioma, glioma, and pituitary tumors. The proposed DCTN model depends on dual convolutional neural networks with VGG-16 architecture concatenated with custom CNN (convolutional neural networks) architecture. After conducting approximately 22 experiments with different architectures and models, our model reached 100% accuracy during training and 99% during testing. The proposed methodology obtained the highest possible improvement over existing research studies. The solution provides a revolution for healthcare providers that can be used as a different disease classification in the future and save human lives.
18 January 2025 in ACM Transactions on Asian and Low-Resource Language Information Processing
Human nature is fundamentally driven by the need for interaction and attention, which are fulfilled through various sensory modalities, including hearing, sight, touch, taste, and smell. These senses enable us to perceive, understand, and engage with the world around us. The quality and depth of our interactions change considerably when we use multiple senses simultaneously, highlighting the importance of multimodal interactions in our daily lives. In the realm of technology, multimodal integration offers immense value, as it aims to create systems that can replicate or complement these natural human abilities for enhanced interaction. This article explores the significance of spatial multimodalities in machine learning, highlighting their role in improving model performance in applications such as autonomous driving, healthcare, and virtual assistants. It addresses challenges like the complexity of fusing diverse sensory data types and proposes solutions such as advanced data fusion techniques, adaptive learning algorithms, and transformer architectures. The goal is to provide an overview of state-of-the-art research and future directions for advancing human–computer interaction.
1 October 2023 in The Egyptian Journal of Language Engineering
Arabic handwritten text recognition faces significant challenges despite the large number of Arabic speakers. A critical review paper has analyzed previous research in this field, identifying problem areas and challenges faced by researchers. The paper focuses on trends in offline handwriting recognition systems and the unique characteristics of the Arabic language that pose technical challenges. The analysis involved comparing and contrasting previous research methods and performances to summarize critical problems and enumerate issues that must be addressed. The paper highlights several Arabic datasets that can be utilized as benchmarks for training, testing, and comparisons. These datasets are essential for evaluating the performance of Arabic handwriting recognition systems. Additionally, the paper concludes with a fundamental comparison and discussion of remaining open problems and trends in the field. It identifies several unresolved technical issues, such as the need for improved feature extraction and modeling techniques, as well as the need for large-scale, diverse datasets to facilitate better training and testing of Arabic handwriting recognition systems. Overall, the paper provides a comprehensive overview of the challenges and issues facing Arabic handwriting recognition and highlights areas where further research is needed.