A brain tumour is one of the major reasons for death in humans, and it tenth most common type that affects people all ages. However, if detected early, treatable types tumours. Brain tumours are classified using biopsy, which not usually performed before definitive surgery. An image classification technique diseases important accelerating treatment process avoiding surgery errors from manual diagnosis by radiologists. The advancement technology machine learning (ML) can assist radiologists...

Cancer of the brain is most common in elderly and young can be fatal both. Brain tumours heal better if they are diagnosed treated quickly. When it comes to processing medical images, deep learning method essential aiding humans diagnosing various diseases. Classifying an step that relies heavily on doctor’s experience training. A smart system for detecting classifying these aid non-invasive diagnosis using MRI (magnetic resonance imaging) images. This work presents a novel hybrid CNN-based...

Diabetes mellitus is a common illness associated with high morbidity and mortality rates. Early detection of diabetes essential to prevent long-term health complications. The existing machine learning model struggles accuracy reliability issues, as well data imbalance, hindering the creation dependable prediction model. research addresses issue using novel deep mechanism called convolutional gated recurrent unit (CGRU), which could accurately detect diabetic disorder their severity level. To...

<i>Rumex obtusifolius</i> Linnaeus (R. <i>obtu</i>. L.) is one of the vital broad-leaved weeds in grassland that needs removal. It affects dairy products and reduces their quality. Hand-removal methods are costly time-consuming. Chemical treatment using herbicides has a negative impact on crops causes environmental pollution. In smart farming, weeding performed by computer vision to recognize efficiently effectively. Conventional machine learning (ML)-based algorithms face challenges,...

There are numerous pre-trained Convolutional Neural Networks (CNN) introduced in the literature, such as AlexNet, VGG-19, and ResNet. These CNN models could be reused applied to tackle different image recognition problems. Unfortunately, these complex have a large number of convolutional filters. To complexity challenge, this research aims evolve VGG-19 using an efficient two-layers optimizer. The proposed optimizer performs filters selection last layers guided by accuracy linear SVM...

Diabetes, characterized as a persistent metabolic condition, requires efficient self-management approaches to achieve optimal health results. Mobile applications have emerged auspicious instruments for facilitating diabetes self-care. This research seeks enhance the development of Diabetes Self-Management Apps through incorporation user-centric methodologies. Employing Semi-Structured Interviews (SSI) involving both end users and healthcare professionals, study aims discern user requirements...

Sketch-based image retrieval (SBIR) utilizes sketches to search for images containing similar objects or scenes. Due the proliferation of touch-screen devices, sketching has become more accessible and therefore received increasing attention. Deep learning emerged as a potential tool SBIR, allowing models automatically extract features learn from large amounts data. To best our knowledge, there is currently no systematic literature review (SLR) SBIR with deep learning. Therefore, aim this...

This paper attempts to discuss the evolution of retrieval approaches focusing on development, challenges and future direction image retrieval. It highlights both already addressed outstanding issues. The explosive growth data leads need research development Image Retrieval. However, researches are moving from keyword, low level features semantic features. Drive towards is due problem keywords which can be very subjective time consuming while cannot always describe high concepts in users'...

This article includes a systematic review that identifies and summarizes the many behavioral change techniques (BCTs), health theories, advanced based on artificial intelligence (AI) currently used to manage diabetes. The focuses assessing efficacy of diabetes self-care applications leverage these cutting-edge in their development use. study provides latest comprehensive findings report through Preferred Reporting Items for Systematic Reviews Meta-Analyses (PRISMA) 2020 reporting guidelines....

Moving beyond mouse and keyboard, the evolution of human-computer interaction (HCI) has been an interest research in recent years which witnessed development from text-based like using a keyboard to graphic user interface (GUI) based on mouse, cumbersome data gloves tracking devices visual-based computer application. One fields is by hand gestures interact with computer. However, complexity set lot challenges be tracked. In real-time, application requires high accurate detection recognition....

Abstract Malaysia, just like its neighbouring countries in the region, has a rich and diverse culture heritage treasures. What makes Malaysia more unique is diversity as multi-racial multicultural country. These cultural heritages might become lost extinct without any efforts preserving safeguarding due to modernization, assimilation, globalization. We present an overview of different available preserve these treasures found from literature. Digital preservation that computer graphics, media...

Abstract Mixed Reality (MR) is the next evolution of human interacting with computer as MR has ability to combine physical environment and digital making them coexist each other. Interaction still a huge research area in Augmented (AR) but very less MR, this due current advanced display techniques not robust intuitive enough let user naturally interact 3D content. New on interaction have been widely studied, technique when system able invoke more than one input modalities. Multimodal...

Recent improvements formulated in the area of video captioning have brought rapid revolutions its methods and performance models. Machine learning deep techniques are both employed this regard. However, there is a lack tracing latest studies their remarkable results. Although several been proposed employing ML DL algorithms different other areas, no systematic review utilizing task. This study aims to examine, evaluate, synthesize into thorough Systematic Literature Review (SLR) that...

Handwriting recognition is the ability of a computer to receive and interpret intelligible handwritten input. Recognition systems are divided into two categories: holistic approach analytical approach. A handles whole input image, while involves steps namely; segmentation combination. began long time ago mainly in Latin Chinese characters. However, little effort has been devoted Arabic The domain handwriting script presents unique technical challenges given more attention recently than other...

Abstract Augmented Reality (AR) is a technology to display the virtual object by overlaying on physical marker in real environment. Nowadays, handheld device becomes trend AR since it has high processing power and compatible with system. However, most of applications did not fully support interaction from multiple users for collaborative interface. Therefore, this research aim develop multi-user AR. There are few phases involved design application called ARGarden. All that been done...