Identifying individual animals at different points in space and time is vital for effective wildlife monitoring and biodiversity conservation. While existing computer vision methods have shown promise in re-identifying animals, their capability in Animal Re-Identification (Animal ReID) remains restricted by the inherent visual variations, specifically high intra- and low inter-identity variations. High intra-identity variations refer to high visual diversity within the same individual due to pose or form changes and occlusions, and low inter-identity variations refer to subtle visual differences between distinct individuals due to fine-grained appearances. To address these challenges, we propose the Clip-based Animal RE-identification (CARE) framework, which leverages the image-conditioned textual description generation and individual-level semantic feature alignment, mitigating the negative impacts of visual variations in Animal ReID. Crucially, we have packaged CARE into a stand-alone toolkit and piloted it with stakeholders, facilitating real-world wildlife monitoring for biodiversity conservation. Extensive experiments on benchmark and in-the-wild datasets further demonstrate that CARE consistently outperforms state-of-the-art methods, validating its effectiveness in Animal ReID. Explore more about CARE at https://ml4sg.auckland.ac.nz/animal-re-identification-model/.

Identifying individual animals within large wildlife populations is essential for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown promise in animal re-identification (Animal ReID) by leveraging data from camera traps. However, existing Animal ReID datasets rely exclusively on visual data, overlooking environmental metadata that ecologists have identified as highly correlated with animal behavior and identity, such as temperature and circadian rhythms. Moreover, the emergence of multimodal models capable of jointly processing visual and textual data presents new opportunities for Animal ReID, but existing datasets fail to leverage these models' text-processing capabilities, limiting their full potential. To address these limitations, we propose MetaWild, a multimodal Animal ReID dataset comprising 20,890 images across six species, paired with environmental metadata extracted from embedded camera trap overlays and scene contexts. Additionally, to facilitate the use of metadata in existing ReID methods, we propose the Meta-Feature Adapter (MFA), a lightweight module that can be incorporated into existing vision-language model (VLM)-based Animal ReID methods, allowing ReID models to leverage both environmental metadata and visual information to improve ReID performance. Experiments on MetaWild show that combining baseline ReID models with MFA to incorporate metadata consistently improves performance compared to using visual information alone, validating the effectiveness of incorporating metadata in re-identification. We hope that our proposed dataset can inspire further exploration of multimodal approaches for Animal ReID. Our dataset and supplementary materials are available at https://jim-lyz1024.github.io/MetaWild/.

AI, especially deep learning algorithm, has proved its potential in wind power prediction; however, the lack of explainability is the main concern to address and this work is the first to investigate the emerging Liquid Neural Network (LNN) to provide necessary transparency in wind power prediction. LNN utilizes the mathematical abstraction of C.elegans and demonstrates liquid/robust behavior in learning and estimation for unseen data. For comparative analysis, the LNN family (i.e., closed form continuous (CfC), Liquid Time Constant) and state-of-the-art recurrent networks (e.g., LSTM and GRU) and 1D-CNN are considered, and the CfC neural network provides the best results on unseen data. CfC models with fully connected layers using only 25 neurons have provided superior results for wind power prediction in different time spans, resolutions, and number of variables.

This article presents a new artificial neural network (ANN)-based calibration mechanism for analog-to-digital converters (ADCs). The proposed mechanism applies ANN to realize the bijective vector recovery mapping (VRM) for nonlinearity calibration and thus effectively suppresses both harmonic distortions and spurs. A new ANN-based calibrator is designed to calibrate both single-channel nonlinearity and interchannel mismatches and significantly improve the performance of ADCs. Through signal-fitting-based training process and noise adding, the proposed mechanism and calibrator can calibrate the general nonlinearity and mismatches of ADCs, including but not limited to the typical nonideality that conventional calibration techniques commonly concern (such as interstage gain error, digital-to-analog converter (DAC) error, and timing mismatch). For verification, an on-chip ANN-based calibrator is implemented in a 12-bit 600-MS/s four-channel time-interleaved (TI) ADC prototype. The measurement results show that signal-to-noise-and-distortion ratio (SNDR) and spurious-free dynamic range (SFDR) are improved from 32.79 and 35.30 to 62.45 and 74.21 dB, respectively. Another off-chip ANN-based calibrator is applied to a commercial 12-bit 5.4-GS/s four-channel ADC, and the results show that the SNDR and SFDR are improved from 42.38 and 43.17 to 53.98 and 78.25 dB, respectively.

Featured with a more complicated configuration, the modelling, analysis, and derivation of multiport converters (MPCs) requires much more effort than conventional two-port converters. The duality principles from circuit theory and graph theory can serve well as a powerful tool to deal with these challenges. However, a fundamental property of duality has been missing in the power electronics community for over 40 years, i.e., different dual MPC topologies can come from the same original MPC, even for those with planar circuits. And this indeed limits our understanding of the MPCs. To fill this gap, the missing theoretical foundations are provided in this work, forming the generalized duality principles for systematic modelling, analysis, and derivations of MPCs. The theoretical foundations are firstly presented through advanced concepts in graph theory. Then, extensive MPCs are selected as examples to validate the feasibility of this theory. It is shown that a 3-port non-isolated MPC can have 8 different duals (for MPCs with more ports, this number will go even higher) and these duals are related to each other by common electrical relationships. Therefore, their modelling, analysis, and operation design can be achieved in a systematic way.