1150 research outputs found
Sort by
GROWTH PERFORMANCE OF RABBITFISH (Siganus sutor) REARED IN INTERTIDAL BRACKISH WATER EARTHEN PONDS USING HAPA NETS
Get PDFPostgraduate Students PowerPoint Presentatio
Karatina University Librarian Dr. Everlyn Anduvare Organizing her Library Staff and Knowledge Ambassadors in Setting up a Community Library at Gitunduti Primary School in Karatina, Mathira Constituency, Nyeri County - November 2022
No full textSetting up of a community library in Gitunduti, Mathira Constituency, Nyeri Count
Control of Bacterial Wilt in Tomato Using Chitosan Intercalated with Tea Extracts.
No full textAbstract on control of Bacterial Wilt in TomatoIn this study, tea extracts were intercalated in chitosan gel to enhance the inhibitory effect of the complex on bacterial wilt in tomato. The disease caused by Ralstonia solanacearum can result in 100% crop loss under severe infection. Chitin was ground into powder of 0.1 mm size, deacetylated using concentrated NaOH solution and tea extracts from green, purple and black tea adsorbed through rotary evaporation. Confirmatory tests on effective adsorption were done using FTIR and XRD, while bioassay experiments were performed to determine efficacy of the chitosan intercalated with crude tea extracts (CICTE) on the pathogen and tomato growth. In vitro and In situ tests were carried out in growth chambers and greenhouse respectively. The greenhouse trials were conducted for a period of 2 years in three sites i.e. Gatundu, JKUAT and Makuyu. The bioassays demonstrated significant (p < 0.05) reduction of R. solanacearum turbidity marked by change of optical densities (OD) from 3.55 to 1.04. In addition, there was significant (p < 0.05) inhibition of the cultured R. solanacearum and reduced wilt incidence in tomato plants treated with CICTE and later inoculated with the pathogen. Tomato plants treated with CICTE also recorded a significantly (p < 0.05) higher yield compared to the control. The study therefore recommends utilization of CICTE as an effective and environmentally safe biopesticide for the devastating bacterial wilt pathogen
Deep Transfer Learning Optimization Techniques for Medical Image Classification: A Review
No full textDeep transfer learning optimization techniques for medical image classificationMedical image classification is a complex and challenging task due to the heterogeneous nature of medical data. Deep transfer learning has emerged as a promising technique for medical image classification, allowing the leveraging of knowledge from pre-trained models learned from large-scale datasets, resulting in improved performance with minimal training and overcoming the disadvantage of small data sets. This paper concisely overviews cutting-edge deep transfer learning optimization approaches for medical image classification. The study covers convolutional neural networks and transfer learning techniques, including relation-based, feature-based, parameter-based, and instance-based transfer learning. Classical classifiers such as Resnet, VGG, Alexnet, Googlenet, and Inception are examined, and their performance on medical image classification tasks is compared. The paper also discusses optimization techniques, such as batch normalization, regularization, and weight initialization, as well as data augmentation and kernel mathematical formulations. The study concludes by identifying challenges when using deep transfer learning for medical image classification and proposing potential future approaches for this field
