Realistic Smile Expression Recognition Approach Using Ensemble Classifier with Enhanced Bagging

A robust smile recognition system could be widely used for many real-world applications.Classification of a facial smile in an unconstrained setting is difficult due to the invertible and wide variety in face images.In this paper,an adaptive model for smile expression classification is suggested that integrates a fast features extraction algorithm and cascade classifiers.Our model takes advantage of the intrinsic association between face detection,smile,and other face features to alleviate the over-fitting issue on the limited training set and increase classification results.The features are extracted taking into account to exclude any unnecessary coefficients in the feature vector;thereby enhancing the discriminatory capacity of the extracted features and reducing the computational process.Still,the main causes of error in learning are due to noise,bias,and variance.Ensemble helps to minimize these factors.Combinations of multiple classifiers decrease variance,especially in the case of unstable classifiers,and may produce a more reliable classification than a single classifier.However,a shortcoming of bagging as the best ensemble classifier is its random selection,where the classification performance relies on the chance to pick an appropriate subset of training items.The suggested model employs a modified form of bagging while creating training sets to deal with this challenge(error-based bootstrapping).The experimental results for smile classification on the JAFFE,CK+,and CK+48 benchmark datasets show the feasibility of our proposed model.

THE PRELIMINARY APPLICATION OF IN SITU HYBRIDI-ZATION IN DETECTING PROTO-ONCOGENES EXPRESSION IN HUMAN LEUKEMIC CELLS

An in situ hybridization technique with 35S labelled proto-oncogene probes (c-myc & c-fes) was used to detect their expression in bone marrow cells of 22 cases of leukemia of various types and immature granulocytes and erythroblasts of 16 nomal myelograms as controls. Both c-myc and c-fes were detectable in leukemic cells as well as in immature granulocytes and erythroblasts of normal bone marrow, but the expression extent varied in different cases. The levels of c-myc expression in leukemic cells were higher than those in controls (P<0.001). There was no difference of c-fes expression in two groups of bone marrow cells (P>0.05). This technique provides us a new method in studying variations of proto-oncogene expression in leukemic cells.

Secure and efficient implementation of facial emotion detection for smart patient monitoring system

Background:Machine learning has enabled the automatic detection of facial expressions,which is particularly beneficial in smart monitoring and understanding the mental state of medical and psychological patients.Most algorithms that attain high emotion classification accuracy require extensive computational resources,which either require bulky and inefficient devices or require the sensor data to be processed on cloud servers.However,there is always the risk of privacy invasion,data misuse,and data manipulation when the raw images are transferred to cloud servers for processing facical emotion recognition(FER)data.One possible solution to this problem is to minimize the movement of such privatedata.Methods:In this research,we propose an efficient implementation of a convolutional neural network(CNN)based algorithm for on-device FER on a low-power field programmable gate array(FPGA)platform.This is done by encoding the CNN weights to approximated signed digits,which reduces the number of partial sums to be computed for multiply-accumulate(MAC)operations.This is advantageous for portable devices that lack full-fledged resourceintensivemultipliers.Results:We applied our approximation method on MobileNet-v2 and ResNet18 models,which were pretrained with the FER2013 dataset.Our implementations and simulations reduce the FPGA resource requirement by at least 22%compared to models with integer weight,with negligible loss in classification accuracy.Conclusions:The outcome of this research will help in the development of secure and low-power systems for FER and other biomedical applications.The approximation methods used in this research can also be extended to other imagebasedbiomedicalresearchfields.

Express and sensitive detection of multiple miRNAs via DNA cascade reactors functionalized photonic crystal array

Array based detection techniques with fluorescence signal reading is a powerful tool for multiple targets analysis. However,when applied fluorescence array for micro RNA detection, time-consuming multi-steps surface signal amplification is usually required due to the low abundance of micro RNA in total RNA expressions, which impairs detection efficiency and limits its application in point of care test(POCT) manner. Herein, DNA cascade reactors(DCRs) functionalized photonic crystal(PC)array was fabricated for express and sensitive detections of mi RNA-21 and mi RNA-155. DCRs were assembled by interval conjugation of self-quenched hairpin DNA probes to single strand DNA nanowire synthesized by rolling circle amplification,which generated cascade DNA hybridization reactions in response to target mi RNAwith instant fluorescence recovery signal. PC array patterns with multi-structure colors further amplified fluorescence with their respective photonic bandgaps(PBGs)matching with the emission peaks of fluorescence molecules labelled on DCRs. The as-prepared DCRs functionalized PC array demonstrated express and sensitive simultaneous detections of mi RNA-21 and mi RNA-155 with hundreds f M detection limits only in 15 min, and was successfully applied in fast quantifications of low abundance mi RNAs from cell lysates and spiked mi RNAs from human serum, which would hold great potential for disease diagnosis and therapeutic effect monitoring with a POCT manner.