Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network.

The measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized by inefficiency and time consumption. On the other hand, it has the potential to induce heightened stress levels in pigs. This research introduces a hybrid 3D point cloud denoising approach for precise pig weight estimation. By integrating statistical filtering and DBSCAN clustering techniques, we mitigate weight estimation bias and overcome limitations in feature extraction. The convex hull technique refines the dataset to the pig's back, while voxel down-sampling enhances real-time efficiency. Our model integrates pig back parameters with a convolutional neural network (CNN) for accurate weight estimation. Experimental analysis indicates that the mean absolute error (MAE), mean absolute percent error (MAPE), and root mean square error (RMSE) of the weight estimation model proposed in this research are 12.45 kg, 5.36%, and 12.91 kg, respectively. In contrast to the currently available weight estimation methods based on 2D and 3D techniques, the suggested approach offers the advantages of simplified equipment configuration and reduced data processing complexity. These benefits are achieved without compromising the accuracy of weight estimation. Consequently, the proposed method presents an effective monitoring solution for precise pig feeding management, leading to reduced human resource losses and improved welfare in pig breeding.

All-Solid-State Thin Film Lithium/Lithium-Ion Microbatteries for Powering the Internet of Things.

As the world steps into the era of Internet of Things (IoT), numerous miniaturized electronic devices requiring autonomous micropower sources will be connected to the internet. All-solid-state thin-film lithium/lithium-ion microbatteries (TFBs) combining solid-state battery architecture and thin-film manufacturing are regarded as ideal on-chip power sources for IoT-enabled microelectronic devices. However, unlike commercialized lithium-ion batteries, TFBs are still in the immature state, and new advances in materials, manufacturing, and structure are required to improve their performance. In this review, the current status and existing challenges of TFBs for practical application in internet-connected devices for the IoT are discussed. Recent progress in thin-film deposition, electrode and electrolyte materials, interface modification, and 3D architecture design is comprehensively summarized and discussed, with emphasis on state-of-the-art strategies to improve the areal capacity and cycling stability of TFBs. Moreover, to be suitable power sources for IoT devices, the design of next-generation TFBs should consider multiple functionalities, including wide working temperature range, good flexibility, high transparency, and integration with energy-harvesting systems. Perspectives on designing practically accessible TFBs are provided, which may guide the future development of reliable power sources for IoT devices.