A study on giant panda recognition based on images of a large proportion of captive pandas

1. As a highly endangered species, the giant panda (panda) has attracted significant attention in the past decades. Considerable efforts have been put on panda conservation and reproduction, offering the promising outcome of maintaining the population size of pandas. To evaluate the effectiveness of conservation and management strategies, recognizing individual pandas is critical. However, it remains a challenging task because the existing methods, such as traditional tracking method, discrimination method based on footprint identification, and molecular biology method, are invasive, inaccurate, expensive, or challenging to perform. The advances of imaging technologies have led to the wide applications of digital images and videos in panda conservation and management, which makes it possible for individual panda recognition in a noninvasive manner by using image‐based panda face recognition method.
2. In recent years, deep learning has achieved great success in the field of computer vision and pattern recognition. For panda face recognition, a fully automatic deep learning algorithm which consists of a sequence of deep neural networks (DNNs) used for panda face detection, segmentation, alignment, and identity prediction is developed in this study. To develop and evaluate the algorithm, the largest panda image dataset containing 6,441 images from 218 different pandas, which is 39.78% of captive pandas in the world, is established.
3. The algorithm achieved 96.27% accuracy in panda recognition and 100% accuracy in detection.
4. This study shows that panda faces can be used for panda recognition. It enables the use of the cameras installed in their habitat for monitoring their population and behavior. This noninvasive approach is much more cost‐effective than the approaches used in the previous panda surveys.

     

Interaction of ethanol with opiate receptors

Addition of ethanol to rat brain homogenate containing opiate receptors inhibits at a concentration of 50 mM the stereospecific binding of 3H-naloxone at 37 degrees C but not at 0 degree C, with the ID50 being 462 mM under these conditions. The temperature-dependent inhibition of the ligand binding suggests that ethanol does not compete with naloxone for specific binding sites of opiate receptors and changes the structure of lipids in biological membranes. Scatchard's analysis has demonstrated that apart from a decrease in the number of highly affinity binding sites of 3H-naloxone, the total amount of the binding sites remains unchanged both in the presence and absence of ethanol and constitutes 453 and 549 fmol/mg protein. It is assumed that ethanol might interconvert highly and low-affinity binding sites. Analysis of the effect of ethanol on 3H-naloxone binding with opiate receptors contained by synaptic membranes obtained from animals with varying predisposition to voluntary alcoholization has shown that ethanol inhibits to a greater degree ligand binding with membranes obtained from rats predisposed to alcoholization. The possibility of the involvement of receptors in the biochemical mechanisms by which the initial alcoholic motivation is effected is under discussion.     

Solving the N-Queens problem with a binary Hopfield-type network

The application of a discrete Hopfield-type neural network to solving the NP-Hard optimization problem — the N-Queens Problem (NQP) — is presented. The applied network is binary, and at every moment each neuron potential is equal to either 0 or 1. The network can be implemented in the asynchronous mode as well as in the synchronous one with n parallel running processors. In both cases the convergence rate is up to 100%, and the experimental estimate of the average computational complexity is polynomial. Based on the computer simulation results and the theoretical analysis, the proper network parameters are established. The behaviour of the network is explained.     

Individual variability and population regulation: an individual-based model

To study the influence of individual variability on population dynamics an individual-based model of the dynamics of a single population consisting of different individuals is constructed. The model is based on differences in individual assimilation rates due to intraspecific competition and variability of initial weights. The model exhibits "imperfect regulation", i.e., the number of individuals in the population oscillates and sooner or later the population becomes extinct. When individual variability is included, the model produces longer population extinction times than without individual variability. The average extinction time is not however a monotonic function of the degree of individual variability.