Related references
Note: Only part of the references are listed.
Article
Green & Sustainable Science & Technology
Normaisharah Mamat et al.
Summary: An accurate image retrieval technique is needed due to the increasing number of images, and it is important to implement fast, simple, and automatic image annotation techniques. This study focuses on the agriculture field and uses automatic image annotation to classify the ripeness of oil palm fruit and recognize different types of fruits. The proposed approach improves fruit classification methods and enhances production for farmers. Simple and effective models using deep learning with You Only Look Once (YOLO) versions are developed and trained with a dataset of 100 oil palm fruit images and 400 images of various fruits in RGB format. The performance and accuracy of the models in annotating 3500 fruit images are evaluated, achieving excellent results with an mAP of 98.7% for oil palm fruit and 99.5% for different types of fruit.
Article
Computer Science, Artificial Intelligence
Yu-Dong Zhang et al.
Summary: This study proposed a novel artificial intelligence system for fruit category classification, which achieved a high accuracy rate on the test set by extracting features from fruit images and using autoencoder as the classifier.
Article
Agronomy
Ting-Wei Huang et al.
Summary: This article introduces the importance of pineapples in Taiwan and their classification method. Due to the difficulty in storing and the tendency to rot, farmers need to filter out the high-water content pineapples. The authors propose an automatic classification method using embedded onboard computing processors, servo, and an ultrasonic sensor to build a hitting machine that can automatically separate pineapples. The proposed method utilizes acoustic spectrogram spectroscopy to classify pineapples and achieved high accuracy through deep learning-based convolutional neural network (CNN) testing.
Article
Computer Science, Artificial Intelligence
Atif Mahmood et al.
Summary: This study utilized machine learning techniques to classify the maturity level of jujube fruits, achieving high success rates with two different convolutional neural network models. The VGG16 model showed superior performance in jujube classification, making it a recommended choice for developing an automated harvesting and sorting system.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Green & Sustainable Science & Technology
Khalied Albarrak et al.
Summary: Date fruit is a high-valued confectionery and fruit crop, with an annual production of approximately 8.46 million tons globally. The absence of an autonomous system for date fruit classification is a common problem in the industry. Machine Learning techniques have been employed to develop an efficient date classification model, achieving a 99% accuracy rate.
Article
Multidisciplinary Sciences
Shahnawaz Ayoub et al.
Summary: This paper investigates the challenging task of automatic image caption prediction and proposes an approach using pre-trained models and attention mechanism to enhance prediction accuracy.
Review
Computer Science, Information Systems
Sumbul Alam et al.
Summary: Various factors such as inheritance and surroundings influence the growth of neurodevelopmental disorders like ASD and ADHD. Traditional diagnostic methods carry a risk of misdiagnosis and are time-consuming and costly. Machine learning and deep learning techniques offer accurate and cost-effective solutions for early diagnosis and treatment of these disorders.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2022)
Article
Chemistry, Multidisciplinary
Yonis Gulzar et al.
Summary: Melanoma skin cancer, one of the most common diseases, requires early detection for saving lives. The Vision Transformer (ViT) model, utilizing self-attention mechanism, has shown to learn long-range spatial relations in images. Comparative analysis reveals that the hybrid TransUNet method excels in skin lesion image segmentation.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Fuzhen Zhuang et al.
Summary: Transfer learning aims to improve the performance of target learners by transferring knowledge from related source domains, reducing the reliance on target-domain data. This survey aims to systematize and summarize existing research studies in order to help readers understand the current status and ideas in the area of transfer learning.
PROCEEDINGS OF THE IEEE
(2021)
Article
Chemistry, Analytical
KwangEun Ko et al.
Summary: This study proposed a novel method for detecting tomato ripeness using multiple streams of convolutional neural networks, achieving an accuracy of 96% through analysis of multi-view images and stochastic decision fusion for final classification results.
Article
Multidisciplinary Sciences
Sumeer Ahmad Khan et al.
Summary: This paper examines the modeling of features in medical imaging using BOVW representations and convolutional neural networks. By comparing with hand-crafted HSIFT features, it is found that HSIFT features outperform learned features in discriminating anatomy image classes.
Article
Agriculture, Multidisciplinary
Suharjito et al.
Summary: This research focuses on creating a mobile application using lightweight CNN models, ImageNet transfer learning, 9-angle crop data augmentation, and post-training quantization. The best model achieved an overall test accuracy of 0.893 on TensorFlow Lite with 96 ms classification time per image, outperforming other models.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Plant Sciences
Zhenzhu Su et al.
Summary: In this study, the combination of hyperspectral imaging and deep learning was utilized for the detection of strawberry maturity degree and SSC, achieving successful results. By constructing 1D and 3D deep learning models, different maturity levels of strawberries were accurately identified and SSC was precisely determined.
FRONTIERS IN PLANT SCIENCE
(2021)
Proceedings Paper
Computer Science, Cybernetics
Cinmayii A. Garillos-Manliguez et al.
Summary: The maturity of fruits plays a crucial role in various aspects of the agriculture industry. Precise classification of papaya fruit maturity remains a challenge, but with the use of deep learning and imaging technologies, high-dimensional data can be processed intelligently without harming the fruit. The proposed multimodal-late fused architecture shows great potential in estimating fruit maturity and other industrial applications.
2021 18TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, COMPUTING SCIENCE AND AUTOMATIC CONTROL (CCE 2021)
(2021)
Review
Computer Science, Artificial Intelligence
Santi Kumari Behera et al.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2020)
Article
Plant Sciences
Chengquan Zhou et al.
FRONTIERS IN PLANT SCIENCE
(2020)
Article
Multidisciplinary Sciences
Yonis Gulzar et al.
Proceedings Paper
Computer Science, Artificial Intelligence
N. Saranya et al.
COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING
(2020)
Review
Agriculture, Multidisciplinary
Vijay Kakani et al.
JOURNAL OF AGRICULTURE AND FOOD RESEARCH
(2020)
Article
Automation & Control Systems
M. Shamim Hossain et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2019)
Article
Computer Science, Information Systems
Hamdi Altaheri et al.
Review
Horticulture
Stefano Musacchi et al.
SCIENTIA HORTICULTURAE
(2018)
