The rapid growth of the global population has placed immense pressure on agriculture to enhance food production while addressing environmental and socioeconomic challenges such as biodiversity loss, water scarcity, and climate variability. Addressing these challenges requires adopting modern techniques and advancing agricultural research. Although some techniques, such as machine learning and deep learning, are increasingly used in agriculture, progress is constrained by the lack of large labelled datasets. This constraint arises because collecting data is often time-consuming, labour-intensive, and requires expert knowledge for data annotation. To mitigate data limitations, transfer learning (TL) offers a viable solution by allowing pre-trained models to be adapted for agricultural applications. Many researchers have demonstrated TL’s potential to advance agriculture. Despite its importance, there is a lack of a comprehensive review, which could be essential to guide researchers in this field. Given the significance and the lack of a review paper, this paper provides a review dedicated to TL in agriculture, offering three main contributions. First, we provide an in-depth background study on TL and its applications in agriculture. Second, we offer a comprehensive examination of TL-based agricultural applications, covering pre-trained models, dataset sources, input image types, implementation platforms, and TL approaches. Third, based on an exploration of the existing studies, we identify the challenges faced when applying TL in agriculture. Finally, to address the identified challenges, we recommend suggestions for future research directions.

Agriculture has a crucial role in both the economy and food supply. However, the frequent occurrence of plant diseases can have a significant negative influence on the production of foods. Timely detection of a disease is important for its effective management, e.g., targeted use of pesticides. Conventional Plant Disease Detection (PDD) methods are manual, slow, tedious, and prone to errors, thereby increasing the risk of significant yield losses. Recently, various data-driven approaches, including Deep Learning and Computer Vision-based approaches, have been explored for PDD. However, the scarcity of large and annotated datasets and the limited scalability of these approaches have prompted researchers to turn to the Self-Supervised Learning (SSL) approach. In this review, we provide the very first conceptual grounding for the SSL approach in PDD. By reviewing a large body of recent related works in the literature, we thoroughly analyse and categorise them into generative, predictive, contrastive and hybrid SSL models. Moreover, this review analyses various recent datasets and performance metrics used in these models. Finally, we explain the research challenges and key research directions aimed at advancing PDD through the SSL approach.

A cluster-randomized trial of Vi-TT was conducted in Dhaka, Bangladesh, using JE vaccine as the control. A subset of 1,500 children were randomly selected on 2:1 basis (Vi-TT vs JE) to assess immune response. Blood was collected before vaccination, and on days 28, 545 and 730 post-vaccination and plasma anti-Vi-IgG response was measured. A robust, persistent antibody response was induced after single dose of Vi-TT, even after 2 years of vaccination. While there is no accepted serological antibody threshold of protection, analyzing the antibodies of children who received Vi-TT provides evidence that may later be useful in predicting population protection.

Outdoor parking systems are one of the most crucial needs in a smart city to find vacant parking spaces in outdoor environments, such as roadsides, university campuses, and so on. In a typical outdoor parking system, the detection of a vehicle entering and leaving the parking zone is a major step. At present, there are numerous external sensor-based and camera-based parking systems available to detect the entrance and leaving of vehicles. Camera-based parking systems rely on sophisticated camera set-ups, while sensor-based parking systems require the installation of sensors at the parking spots or vehicles’ sides. Due to such complication, the deployment and maintenance costs of the existing parking systems are very high. Furthermore, the need for additional hardware and network capacity increases the cost and complexity, which makes it difficult to use for large deployment. This paper proposes an approach for outdoor parking utilizing only smartphone integrated sensors that do not require manpower support nor additional sensor installation. The proposed algorithm first receives sensor signals from the driver’s phone, performs pre-processing to recognize the context of drivers, which is followed by context flow recognition. The final result is obtained from context flow recognition which provides the output of whether the driver is parking or unparking. The proposed approach is validated with a set of comprehensive experiments. The performance of the proposed method is favorable as it uses only the smartphone’s internal sensors to recognize whether the cars are entering or leaving the parking area.