DeepFungusDet: MobileNetV3 Model in Medical Imaging for Fungal Disease Detection

Опубликована: Март 1, 2024

A fungal infection in humans is a pathological state resulting from the infiltration and proliferation of fungi within body. Microorganisms known as are present air, water, soil, plants. The can cause skin to become red inflamed causing bad oral genital effects article presents deep learning technique for identifying infections using MobileNetV3, which compact resilient convolutional neural network (CNN). model trained on wide variety datasets, demonstrating its efficiency mobility real-time detection portable devices. categorize identify various across different conditions capabilities. findings result an excellent accuracy speed infections, indicating potential rapid accessible healthcare, agriculture, environmental monitoring. work investigates effectiveness MobileNetV3 named DeepFungusDet broad dataset containing infections. This has been implemented at numbers epochs highest identification 93.14% epoch 13 loss 0.4494, promise recognizing tool provides option via mobile devices, paving way future research use crucial field fungus identification. represent major step forward provide prospects developing practical diagnostic tools healthcare industry related fields.

Язык: Английский

Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections

Türk doğa ve fen dergisi :/Türk doğa ve fen dergisi, Год журнала: 2024, Номер 13(1), С. 152 - 160

Опубликована: Март 26, 2024

Fungi play a pivotal role in our ecosystem and human health, serving as both essential contributors to environmental sustainability significant agents of disease. The importance precise fungi detection cannot be overstated, it underpins effective disease management, agricultural productivity, the safeguarding global food security. This research explores efficacy vision transformer-based architectures for classification microscopic images various fungal types enhance infections. study compared pre-trained base Vision Transformer (ViT) Swin models, evaluating their capability feature extraction fine-tuning. incorporation transfer learning fine-tuning strategies, particularly with data augmentation, significantly enhances model performance. Utilizing comprehensive dataset without reveals that Transformer, when fine-tuned, exhibits superior accuracy (98.36%) over ViT (96.55%). These findings highlight potential models automating refining diagnosis infections, promising advancements medical imaging analysis.

Язык: Английский

APPLICATION OF AI-ENHANCED IMAGE PROCESSING METHODS FOR EDUCATIONAL APPLIED PHYSICS EXPERIMENTS

Environment Technology Resources Proceedings of the International Scientific and Practical Conference, Год журнала: 2024, Номер 2, С. 417 - 423

Опубликована: Июнь 22, 2024

This article examines the use of an AI-powered automated image analysis system. The system's purpose is to enhance workflow students during applied physics laboratory experiments, helping them analyze images and perform accurate microobject counting. On software side, system incorporates machine learning algorithms for visual processing applications using Python its’ extension libraries – CV2, Tensorflow, Keras, SkLearn etc.. hardware consists a camera microprocessor, which, in conjunction with software, recognition counting real-time. goal automate experiments which microobjects, be it organic or human-made, usually done manually. During these aid this system, are exposed modern workflow, further preparing future work environments, teaching about process automation, increasing their interest micro-scale related science subjects. Automation technology combined automatic data logging from allows fast micro-object

Язык: Английский