Search Results (3)

Smart farms refer to spaces and technologies that utilize networks and automation to monitor and manage the environment and livestock without the constraints of time and space. As various devices installed on farms are connected to a network and automated, farm conditions can be observed remotely anytime and anywhere via smartphones or computers. These smart farms have evolved into smart livestock farming, which involves collecting, analyzing, and sharing data across the entire process from livestock production and growth to post-shipment distribution and consumption. This data-driven approach aids decision-making and creates new value. However, in the process of evolving smart farm technology into smart livestock farming, challenges remain in the essential requirements of data collection and intelligence. Many livestock farms face difficulties in applying intelligent technologies. In this paper, we propose an intelligent monitoring system framework for smart livestock farms using artificial intelligence technology and implement deep learning-based intelligent monitoring. To detect cattle lesions and inactive individuals within the barn, we apply the RT-DETR method instead of the traditional YOLO model. YOLOv5 and YOLOv8 are representative models in the YOLO series, both of which utilize Non-Maximum Suppression (NMS). NMS is a postprocessing technique used to eliminate redundant bounding boxes by calculating the Intersection over Union (IoU) between all predicted boxes. However, this process can be computationally intensive and may negatively impact both speed and accuracy in object detection tasks. In contrast, RT-DETR (Real-Time Detection Transformer) is a Transformer-based real-time object detection model that does not require NMS and achieves higher accuracy compared to the YOLO models. Given environments where large-scale datasets can be obtained via CCTV, Transformer-based detection methods like RT-DETR are expected to outperform traditional YOLO approaches in terms of detection performance. This approach reduces computational costs and optimizes query initialization, making it more suitable for the real-time detection of cattle maintenance behaviors and related abnormal behavior detection. Comparative analysis with the existing YOLO technique verifies RT-DETR and confirms that RT-DETR shows higher performance than YOLOv8. This research contributes to resolving the low accuracy and high redundancy of traditional YOLO models in behavior recognition, increasing the efficiency of livestock management, and improving productivity by applying deep learning to the smart monitoring of livestock farms. Full article

This study introduces an innovative smart impact detection system designed for real-time monitoring of shipment status and path integrity. Leveraging the advanced capabilities of the ESPRESSIF ESP32-S3-MINI-1U-N8 microcontroller, which integrates Wi-Fi, a display, a memory card slot, and accelerometers, this detector represents a significant advancement in shipment tracking technology. The device is engineered to continuously measure impact magnitudes in terms of g-force, and records data when predefined impact thresholds are exceeded. These data are then wirelessly transmitted to a remote server, providing users with the ability to track shipment status and path via a dedicated application. The performance testing revealed impact measurements ranging from −0.5 to 2 g, with occasional peaks reaching approximately 4.5 g, demonstrating the system’s sensitivity and reliability in diverse conditions. This smart impact detector not only facilitates continuous monitoring, but also enhances the ability to respond swiftly to potential shipment violations, thus providing a novel solution for ensuring shipment integrity. This research contributes to the field by presenting a comprehensive real-time impact detection system that integrates modern microcontroller technology with effective monitoring capabilities, setting a new benchmark for shipment tracking systems. Full article

This paper proposes a software and hardware solution for real time condition monitoring applications. The proposed device, called XpertTrack, exchanges data through the GPRS protocol over a GSM network and monitories temperature and vibrations of critical merchandise during commercial shipments anywhere on the globe. Another feature of this real time tracker is to provide GPS and GSM positioning with a precision of 10 m or less. In order to interpret the condition of the merchandise, the data acquisition, analysis and visualization are done with 0.1 °C accuracy for the temperature sensor, and 10 levels of shock sensitivity for the acceleration sensor. In addition to this, the architecture allows increasing the number and the types of sensors, so that companies can use this flexible solution to monitor a large percentage of their fleet. Full article