Novel Method for Three-Dimensional Facial Expression Recognition Using Self-Normalizing Neural Networks and Mobile Devices

Introduction To date, most ways to perform facial expression recognition rely on two-dimensional images, advanced approaches with three-dimensional data exist. These however demand stationary apparatuses and thus lack portability and possibilities to scale deployment. As human emotions, intent and even diseases may condense in distinct facial expressions or changes therein, the need for a portable yet capable solution is signified. Due to the superior informative value of three-dimensional data on facial morphology and because certain syndromes find expression in specific facial dysmorphisms, a solution should allow portable acquisition of true three-dimensional facial scans in real time. In this study we present a novel solution for the three-dimensional acquisition of facial geometry data and the recognition of facial expressions from it. The new technology presented here only requires the use of a smartphone or tablet with an integrated TrueDepth camera and enables real-time acquisition of the geometry and its categorization into distinct facial expressions. Material and Methods Our approach consisted of two parts: First, training data was acquired by asking a collective of 226 medical students to adopt defined facial expressions while their current facial morphology was captured by our specially developed app running on iPads, placed in front of the students. In total, the list of the facial expressions to be shown by the participants consisted of “disappointed”, “stressed”, “happy”, “sad” and “surprised”. Second, the data were used to train a self-normalizing neural network. A set of all factors describing the current facial expression at a time is referred to as “snapshot”. Results In total, over half a million snapshots were recorded in the study. Ultimately, the network achieved an overall accuracy of 80.54% after 400 epochs of training. In test, an overall accuracy of 81.15% was determined. Recall values differed by the category of a snapshot and ranged from 74.79% for “stressed” to 87.61% for “happy”. Precision showed similar results, whereas “sad” achieved the lowest value at 77.48% and “surprised” the highest at 86.87%. Conclusions With the present work it can be demonstrated that respectable results can be achieved even when using data sets with some challenges. Through various measures, already incorporated into an optimized version of our app, it is to be expected that the training results can be significantly improved and made more precise in the future. Currently a follow-up study with the new version of our app that encompasses the suggested alterations and adaptions, is being conducted. We aim to build a large and open database of facial scans not only for facial expression recognition but to perform disease recognition and to monitor diseases’ treatment progresses.     

Gregor Johann Mendel and Modern Evolutionary Biology: Developmental genetics with model organisms

In Darwin’s and Mendel’s times, researchers investigated a wealth of organisms, chosen to solve particular problems for which they seemed especially well suited. Later, a focus on a few organisms, which are accessible to systematic genetic investigations, resulted in larger repertoires of methods and applications in these few species. Genetic animal model organisms with large research communities are the nematode Caenorhabditis elegans, the fly Drosophila melanogaster, the zebrafish Danio rerio, and the mouse Mus musculus. Due to their specific strengths, these model organisms have their strongest impacts in rather different areas of biology. C. elegans is unbeatable in the analysis of cell-to-cell contacts by saturation mutagenesis, as worms can be grown very fast in very high numbers. In Drosophila, a rich pattern is generated in the embryo as well as in adults that is used to unravel the underlying mechanisms of morphogenesis. The transparent larvae of zebrafish are uniquely suited to study organ development in a vertebrate, and the superb versatility of reverse genetics in the mouse made it the model organism to study human physiology and diseases. The combination of these models allows the in-depth genetic analysis of many fundamental biological processes using a plethora of different methods, finally providing many specific approaches to combat human diseases. The plant model Arabidopsis thaliana provides an understanding of many aspects of plant biology that might ultimately be useful for breeding crops.     

Phytochemical screening and antiviral activity of some medicinal plants from the island Soqotra

Methanol and hot-aqueous extracts of 25 different plant species, used in Yemeni traditional medicine and growing, partly as endemic plants, on the island Soqotra have been investigated for their antiviral activity. In addition, the phytochemical identification of the main chemical constituents was performed. The extracts were assayed in two in vitro viral systems, which used influenza virus type A/MDCK cells and herpes simplex virus type 1/Vero cells, at non-cytotoxic concentrations. The herpes simplex virus type 1 showed more sensitivity than the influenza virus type A against the extracts investigated. The methanol extracts of Boswellia ameero, Boswellia elongata, Buxus hildebrandtii, Cissus hamaderohensis, Cleome socotrana, Dracaena cinnabari, Exacum affine, Jatropha unicostata and Kalanchoe farinacea showed anti-influenza virus type A activity with 50% inhibition (IC50) concentrations ranging from 0.7 to 12.5 microg/mL. In addition, 17 plants of the 25 investigated exhibited anti-HSV-1 activity. The antiviral activity of some active extracts was also observed on a molecular level.     

Über die Motilität der Spermatozoen

Zusammenfassung Die für meine Arbeit untersuchten Ejaculate ergaben folgende Befunde: Menge: zwischen 2–5,5 ccm, im Durchschnitt 3,5 ccm. Zahl der Samenf?den pro Kubikzentimeter: 51–106, im Durchschnitt 73 Millionen. Verflüssigung des anfangs sagoartig geronnenen Ejaculates nach 5–10 Min. In dem per onaniam in ein Glas gewonnenen Ejaculat verlieren die Samenf?den bei K?rpertemperatur ihre Beweglichkeit nach 6–11 Std.; bei 6°C aufbewahrt, zeigen sie nach leichtem Erw?rmen noch nach 96–100 Std. Beweglichkeit; bei Zimmertemperatur blieben sie 28–73 Std. beweglich. Im Condomejaculat kann schon nach 30 Min. eine deutliche Sch?digung der Motilit?t der Spermatozoen eintreten, die nach 2 Std. vollst?ndig wird. Durch Ausspülen und W?ssern des Condoms wird seine spermatozide Wirkung nicht aufgehoben. Wird nach einem Coitus condomatus das Ejaculat sofort in ein Glas übertragen, so tritt keine Einschr?nkung der Motilit?t der Spermatozoen auf.