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.

     

Putative candidate genes for blood pressure control in the SHR.BN-RNO8 congenic substrains

The SHR-Lx congenic strain carrying a differential segment of chromosome 8 of BN and PD origin was recently shown to exhibit a significant decrease in blood pressure as compared to the SHR strain. There were two positional candidate genes for blood pressure control mapped to the differential segment: the rat kidney epithelial potassium channel gene (Kcnj1) and brain dopamine receptor 2 gene (Drd2). Bot these genes were separated into SHR.BN-RNO8 congenic substrains. In this communication, we are presenting the assignment of two further putative candidate genes, which might be involved in blood pressure control to the BN/PD differential segment of the SHR-Lx congenic strain. These are: the gene coding for smooth muscle cell specific protein 22 (Sm22) defined by the D8Mcw1 marker and neuronal nicotinic acetylcholine receptor gene cluster, defined by the D8Bord1 marker. Moreover, the glutamate receptor gene Grik4 which also maps to the differential segment of the SHR-Lx should be taken into account. The genetic separation of all these putative candidate genes of blood pressure control is being performed by recombinations and subsequent selection using (SHR×SHR-Lx) intercross population.     

Determination of antibody affinity by using antigenic and antibody immunosorbents

To determine the affinity of the active centers of antibodies, cellulose immunosorbents for antibodies and antigens have been used. The fixation of serum proteins on the sorbent, the interaction of fixed antibodies with a monovalent antigen and the graphic analysis of the results thus obtained allows one to assess not only the concentration of the effective active centers on the sorbent, but also all known characteristics of antibody affinity: the average association constant K0, the common association constant Kt, the geometric association constant Kg, the average association constants which determine the affinity of different antibody groups. The use of antigenic immunosorbent permits one to determine the value of the average internal association constant K0. The determination of antibody affinity in hyperimmune antiplague sera by means of immunosorbents and red blood cells coated with capsular antigen has resulted in obtaining similar values of affinity indices.     

Algal single cell protein from wastewater treatment and renovation process

A Source of high-quality protein for animal feed, based upon algae recovered in the process of upgrading waste oxidation pond effluents and promising to be particularly economical, is being developed at the Technion. Unlike other types of single cell protein(SCP), the algal protein does not have to return the full production cost but only that of concentration and final processing. The balance is shared by the value of waste disposal and the reclaimed water. Whereas such systems as activated sludge require considerable mechanical energy to supply the oxygen needed for aerobically degrading organics in wastewater, oxidation ponds utilize solar energy for that purpose. The sludge obtained when their effluents are clarified consists largely of algae, bacteria, fungi, and zooplankton in relative proportions varying with operating conditions, and contains 40–60%(dry basis) high-quality protein. The high rate oxidation pond (a particularly intensive type of pond) produces on the average 34 g/m²7sol;day solids, or over 100 tons/ha (hectare) annually. Two clarification routes have been found promising: centrifugation and alum flocculation followed by frothflotation. The latter route is less expensive in terms of both fixed and operating cost, and gives clarified effluent of higher quality, which can be seasonally stored with minimal eutrophication because the aluminum removes most of the phosphate from the effluent. A good product has been obtained by drum-drying the concentrate, and preliminary feeding tests have indicated that it can replace at least 1/4 of the soymeal in broiler rations and 2/3 of the fishmeal in carp feed. No ill effect of the aluminum in the product recovered by alum flocculation has been found so far a process for removing and recycling the aluminum has been developed nonetheless, in case ill effects do show up in further tests. The combined value of the benefits derived from a system centered around the high-rate oxidation pond with clarification by flocculation–flotation, in terms of waste treatment by alternative means, potable water saved, and soymeal replaced, significantly exceeds estimated cost.