Pattern recognition of number gestures based on a wireless surface EMG system

Using surface electromyography (sEMG) signal for efficient recognition of hand gestures has attracted increasing attention during the last decade, with most previous work being focused on recognition of upper arm and gross hand movements and some work on the classification of individual finger movements such as finger typing tasks. However, relatively few investigations can be found in the literature for automatic classification of multiple finger movements such as finger number gestures. This paper focuses on the recognition of number gestures based on a 4-channel wireless sEMG system. We investigate the effects of three popular feature types (i.e. Hudgins’ time–domain features (TD), autocorrelation and cross-correlation coefficients (ACCC) and spectral power magnitudes (SPM)) and four popular classification algorithms (i.e. k-nearest neighbor (k-NN), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and support vector machine (SVM)) in offline recognition. Motivated by the good performance of SVM, we further propose combining the three features and employing a new classification method, multiple kernel learning SVM (MKL-SVM). Real sEMG results from six subjects show that all combinations, except k-NN or LDA using ACCC features, can achieve above 91% average recognition accuracy, and the highest accuracy is 97.93% achieved by the proposed MKL-SVM method using the three feature combination (3F). Referring to the offline recognition results, we also implement a real-time recognition system. Our results show that all six subjects can achieve a real-time recognition accuracy higher than 90%. The number gestures are therefore promising for practical applications such as human–computer interaction (HCI).     

Use of flax oil to influence honey bee nestmate recognition

Fatty acids, normally found in comb wax, have a strong influence on nestmate recognition in honey bees, Apis mellifera L. Previous work has shown that bees from different colonies, when treated with 16- or 18-carbon fatty acids, such as oleic, linoleic, or linolenic acids, are much less likely to fight than bees from two colonies when only one of the two is treated. Previous work also shows that the influence of comb wax on recognition has practical applications; transfer of empty comb between colonies, before merger of those colonies, reduces fighting among workers within the merged colony. Flax oil contains many of the same fatty acids as beeswax. Here, we tested the hypothesis that treatment of individual bees with flax oil affects nestmate recognition; the results proved to be consistent with this hypothesis and showed that treated bees from different colonies were less likely to fight than untreated bees. These results suggest that flax oil may be useful in facilitating colony mergers.     

A Systematic Comparison of Supervised Classifiers

Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM). In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.     

Effective Automated Feature Construction and Selection for Classification of Biological Sequences

Background

Many open problems in bioinformatics involve elucidating underlying functional signals in biological sequences. DNA sequences, in particular, are characterized by rich architectures in which functional signals are increasingly found to combine local and distal interactions at the nucleotide level. Problems of interest include detection of regulatory regions, splice sites, exons, hypersensitive sites, and more. These problems naturally lend themselves to formulation as classification problems in machine learning. When classification is based on features extracted from the sequences under investigation, success is critically dependent on the chosen set of features.

Methodology

We present an algorithmic framework (EFFECT) for automated detection of functional signals in biological sequences. We focus here on classification problems involving DNA sequences which state-of-the-art work in machine learning shows to be challenging and involve complex combinations of local and distal features. EFFECT uses a two-stage process to first construct a set of candidate sequence-based features and then select a most effective subset for the classification task at hand. Both stages make heavy use of evolutionary algorithms to efficiently guide the search towards informative features capable of discriminating between sequences that contain a particular functional signal and those that do not.

Results

To demonstrate its generality, EFFECT is applied to three separate problems of importance in DNA research: the recognition of hypersensitive sites, splice sites, and ALU sites. Comparisons with state-of-the-art algorithms show that the framework is both general and powerful. In addition, a detailed analysis of the constructed features shows that they contain valuable biological information about DNA architecture, allowing biologists and other researchers to directly inspect the features and potentially use the insights obtained to assist wet-laboratory studies on retainment or modification of a specific signal. Code, documentation, and all data for the applications presented here are provided for the community at http://www.cs.gmu.edu/~ashehu/?q=OurTools.     

Computer vision technique for freshness estimation from segmented eye of fish image

Preserving the quality of fish is a challenging task. Several different cooling methods and materials are used during their storage, transportation purpose. These are responsible factors that decide the freshness of a post harvested fish. In this proposed algorithm, a computer vision-based technique is developed to predict the freshness level of fish from its image. Eyes of the fish are considered as the region of interest, as a good correlation has been observed between the colour of the eye and different duration of storage day. It is segmented from the image of a fish sample and then a strategic framework is used for extraction of the discriminatory features. These extracted features show a degradation pattern which acts as an indicative parameter to determine the level of freshness of sample of fish. The proposed method provides a recognition accuracy of 96.67%. The experimental results indicate that this is an efficient and non-destructive methodology for detecting the fish freshness. The high accuracy of freshness detection and low computation time makes this non-destructive methodology efficient for real-world usage in the fish industry and market.     

A comparative genomic method for computational identification of prokaryotic translation initiation sites

The ever growing number of completely sequenced prokaryotic genomes facilitates cross-species comparisons by genomic annotation algorithms. This paper introduces a new probabilistic framework for comparative genomic analysis and demonstrates its utility in the context of improving the accuracy of prokaryotic gene start site detection. Our frame work employs a product hidden Markov model (PROD-HMM) with state architecture to model the species-specific trinucleotide frequency patterns in sequences immediately upstream and downstream of a translation start site and to detect the contrasting non-synonymous (amino acid changing) and synonymous (silent) substitution rates that differentiate prokaryotic coding from intergenic regions. Depending on the intricacy of the features modeled by the hidden state architecture, intergenic, regulatory, promoter and coding regions can be delimited by this method. The new system is evaluated using a preliminary set of orthologous Pyrococcus gene pairs, for which it demonstrates an improved accuracy of detection. Its robustness is confirmed by analysis with cross-validation of an experimentally verified set of Escherichia coli K-12 and Salmonella thyphimurium LT2 orthologs. The novel architecture has a number of attractive features that distinguish it from previous comparative models such as pair-HMMs.     

CRISPR-based DNA and RNA detection with liquid-liquid phase separation

The ability to detect specific nucleic acid sequences allows for a wide range of applications such as the identification of pathogens, clinical diagnostics, and genotyping. CRISPR-Cas proteins Cas12a and Cas13a are RNA-guided endonucleases that bind and cleave specific DNA and RNA sequences, respectively. After recognition of a target sequence, both enzymes activate indiscriminate nucleic acid cleavage, which has been exploited for sequence-specific molecular diagnostics of nucleic acids. Here, we present a label-free detection approach that uses a readout based on solution turbidity caused by liquid-liquid phase separation (LLPS). Our approach relies on the fact that the LLPS of oppositely charged polymers requires polymers to be longer than a critical length. This length dependence is predicted by the Voorn-Overbeek model, which we describe in detail and validate experimentally in mixtures of polynucleotides and polycations. We show that the turbidity resulting from LLPS can be used to detect the presence of specific nucleic acid sequences by employing the programmable CRISPR-nucleases Cas12a and Cas13a. Because LLPS of polynucleotides and polycations causes solutions to become turbid, the detection of specific nucleic acid sequences can be observed with the naked eye. We furthermore demonstrate that there is an optimal polynucleotide concentration for detection. Finally, we provide a theoretical prediction that hints towards possible improvements of an LLPS-based detection assay. The deployment of LLPS complements CRISPR-based molecular diagnostic applications and facilitates easy and low-cost nucleotide sequence detection.     

Particle detection,number estimation,and feature measurement in gene transfer studies: optical fractionator stereology integrated with digital image processing and analysis

Assessing the efficacy of in vivo gene transfer often requires a quantitative determination of the number, size, shape, or histological visualization characteristics of biological objects. The optical fractionator has become a choice stereological method for estimating the number of objects, such as neurons, in a structure, such as a brain subregion. Digital image processing and analytic methods can increase detection sensitivity and quantify structural and/or spectral features located in histological specimens. We describe a hardware and software system that we have developed for conducting the optical fractionator process. A microscope equipped with a video camera and motorized stage and focus controls is interfaced with a desktop computer. The computer contains a combination live video/computer graphics adapter with a video frame grabber and controls the stage, focus, and video via a commercial imaging software package. Specialized macro programs have been constructed with this software to execute command sequences requisite to the optical fractionator method: defining regions of interest, positioning specimens in a systematic uniform random manner, and stepping through known volumes of tissue for interactive object identification (optical dissectors). The system affords the flexibility to work with count regions that exceed the microscope image field size at low magnifications and to adjust the parameters of the fractionator sampling to best match the demands of particular specimens and object types. Digital image processing can be used to facilitate object detection and identification, and objects that meet criteria for counting can be analyzed for a variety of morphometric and optical properties.     

Uniform Local Binary Pattern Based Texture-Edge Feature for 3D Human Behavior Recognition

With the rapid development of 3D somatosensory technology, human behavior recognition has become an important research field. Human behavior feature analysis has evolved from traditional 2D features to 3D features. In order to improve the performance of human activity recognition, a human behavior recognition method is proposed, which is based on a hybrid texture-edge local pattern coding feature extraction and integration of RGB and depth videos information. The paper mainly focuses on background subtraction on RGB and depth video sequences of behaviors, extracting and integrating historical images of the behavior outlines, feature extraction and classification. The new method of 3D human behavior recognition has achieved the rapid and efficient recognition of behavior videos. A large number of experiments show that the proposed method has faster speed and higher recognition rate. The recognition method has good robustness for different environmental colors, lightings and other factors. Meanwhile, the feature of mixed texture-edge uniform local binary pattern can be used in most 3D behavior recognition.     

Optimal Geometrical Set for Automated Marker Placement to Virtualized Real-Time Facial Emotions

In recent years, real-time face recognition has been a major topic of interest in developing intelligent human-machine interaction systems. Over the past several decades, researchers have proposed different algorithms for facial expression recognition, but there has been little focus on detection in real-time scenarios. The present work proposes a new algorithmic method of automated marker placement used to classify six facial expressions: happiness, sadness, anger, fear, disgust, and surprise. Emotional facial expressions were captured using a webcam, while the proposed algorithm placed a set of eight virtual markers on each subject’s face. Facial feature extraction methods, including marker distance (distance between each marker to the center of the face) and change in marker distance (change in distance between the original and new marker positions), were used to extract three statistical features (mean, variance, and root mean square) from the real-time video sequence. The initial position of each marker was subjected to the optical flow algorithm for marker tracking with each emotional facial expression. Finally, the extracted statistical features were mapped into corresponding emotional facial expressions using two simple non-linear classifiers, K-nearest neighbor and probabilistic neural network. The results indicate that the proposed automated marker placement algorithm effectively placed eight virtual markers on each subject’s face and gave a maximum mean emotion classification rate of 96.94% using the probabilistic neural network.     

Listening to speech in the presence of other sounds

Although most research on the perception of speech has been conducted with speech presented without any competing sounds, we almost always listen to speech against a background of other sounds which we are adept at ignoring. Nevertheless, such additional irrelevant sounds can cause severe problems for speech recognition algorithms and for the hard of hearing as well as posing a challenge to theories of speech perception. A variety of different problems are created by the presence of additional sound sources: detection of features that are partially masked, allocation of detected features to the appropriate sound sources and recognition of sounds on the basis of partial information. The separation of sounds is arousing substantial attention in psychoacoustics and in computer science. An effective solution to the problem of separating sounds would have important practical applications.     

Digitally supported public health interventions through the lens of structural injustice: The case of mobile apps responding to violence against women and girls

Mobile applications (apps) have gained significant popularity as a new intervention strategy responding to violence against women and girls. Despite their growing relevance, an assessment from the perspective of public health ethics is still lacking. Here, we base our discussion on the understanding of violence against women and girls as a multidimensional, global public health issue on structural, societal and individual levels and situate it within the theoretical framework of structural injustice, including epistemic injustice. Based on a systematic app review we previously conducted, we evaluate the content and functions of apps through the lens of structural injustice. We argue that technological solutions such as apps may be a useful tool in the fight against violence against women and girls but have to be situated within the broader frame of public health that considers the structural dimensions of such violence. Ultimately, the concerns raised by structural injustice are—alongside key concerns of safety, data privacy, importance of human supportive contact, and so forth—crucial dimensions in the ethical assessment of such apps. However, research on the role and relevance of apps as strategies to address the structural and epistemic dimensions of violence remains scarce. This article aims to provide a foundation for further discussion in this area and could be applicable to other areas in public health policy and practice.     

Protein homology detection and fold inference through multiple alignment entropy profiles

Homology detection and protein structure prediction are central themes in bioinformatics. Establishment of relationship between protein sequences or prediction of their structure by sequence comparison methods finds limitations when there is low sequence similarity. Recent works demonstrate that the use of profiles improves homology detection and protein structure prediction. Profiles can be inferred from protein multiple alignments using different approaches. The "Conservatism-of-Conservatism" is an effective profile analysis method to identify structural features between proteins having the same fold but no detectable sequence similarity. The information obtained from protein multiple alignments varies according to the amino acid classification employed to calculate the profile. In this work, we calculated entropy profiles from PSI-BLAST-derived multiple alignments and used different amino acid classifications summarizing almost 500 different attributes. These entropy profiles were converted into pseudocodes which were compared using the FASTA program with an ad-hoc matrix. We tested the performance of our method to identify relationships between proteins with similar fold using a nonredundant subset of sequences having less than 40% of identity. We then compared our results using Coverage Versus Error per query curves, to those obtained by methods like PSI-BLAST, COMPASS and HHSEARCH. Our method, named HIP (Homology Identification with Profiles) presented higher accuracy detecting relationships between proteins with the same fold. The use of different amino acid classifications reflecting a large number of amino acid attributes, improved the recognition of distantly related folds. We propose the use of pseudocodes representing profile information as a fast and powerful tool for homology detection, fold assignment and analysis of evolutionary information enclosed in protein profiles.     

Robust Eye Center Localization through Face Alignment and Invariant Isocentric Patterns

The localization of eye centers is a very useful cue for numerous applications like face recognition, facial expression recognition, and the early screening of neurological pathologies. Several methods relying on available light for accurate eye-center localization have been exploited. However, despite the considerable improvements that eye-center localization systems have undergone in recent years, only few of these developments deal with the challenges posed by the profile (non-frontal face). In this paper, we first use the explicit shape regression method to obtain the rough location of the eye centers. Because this method extracts global information from the human face, it is robust against any changes in the eye region. We exploit this robustness and utilize it as a constraint. To locate the eye centers accurately, we employ isophote curvature features, the accuracy of which has been demonstrated in a previous study. By applying these features, we obtain a series of eye-center locations which are candidates for the actual position of the eye-center. Among these locations, the estimated locations which minimize the reconstruction error between the two methods mentioned above are taken as the closest approximation for the eye centers locations. Therefore, we combine explicit shape regression and isophote curvature feature analysis to achieve robustness and accuracy, respectively. In practical experiments, we use BioID and FERET datasets to test our approach to obtaining an accurate eye-center location while retaining robustness against changes in scale and pose. In addition, we apply our method to non-frontal faces to test its robustness and accuracy, which are essential in gaze estimation but have seldom been mentioned in previous works. Through extensive experimentation, we show that the proposed method can achieve a significant improvement in accuracy and robustness over state-of-the-art techniques, with our method ranking second in terms of accuracy. According to our implementation on a PC with a Xeon 2.5Ghz CPU, the frame rate of the eye tracking process can achieve 38 Hz.     

DNA barcode goes two-dimensions: DNA QR code web server

The DNA barcoding technology uses a standard region of DNA sequence for species identification and discovery. At present, "DNA barcode" actually refers to DNA sequences, which are not amenable to information storage, recognition, and retrieval. Our aim is to identify the best symbology that can represent DNA barcode sequences in practical applications. A comprehensive set of sequences for five DNA barcode markers ITS2, rbcL, matK, psbA-trnH, and CO1 was used as the test data. Fifty-three different types of one-dimensional and ten two-dimensional barcode symbologies were compared based on different criteria, such as coding capacity, compression efficiency, and error detection ability. The quick response (QR) code was found to have the largest coding capacity and relatively high compression ratio. To facilitate the further usage of QR code-based DNA barcodes, a web server was developed and is accessible at http://qrfordna.dnsalias.org. The web server allows users to retrieve the QR code for a species of interests, convert a DNA sequence to and from a QR code, and perform species identification based on local and global sequence similarities. In summary, the first comprehensive evaluation of various barcode symbologies has been carried out. The QR code has been found to be the most appropriate symbology for DNA barcode sequences. A web server has also been constructed to allow biologists to utilize QR codes in practical DNA barcoding applications.     

An accurate sequentially Markov conditional sampling distribution for the coalescent with recombination

The sequentially Markov coalescent is a simplified genealogical process that aims to capture the essential features of the full coalescent model with recombination, while being scalable in the number of loci. In this article, the sequentially Markov framework is applied to the conditional sampling distribution (CSD), which is at the core of many statistical tools for population genetic analyses. Briefly, the CSD describes the probability that an additionally sampled DNA sequence is of a certain type, given that a collection of sequences has already been observed. A hidden Markov model (HMM) formulation of the sequentially Markov CSD is developed here, yielding an algorithm with time complexity linear in both the number of loci and the number of haplotypes. This work provides a highly accurate, practical approximation to a recently introduced CSD derived from the diffusion process associated with the coalescent with recombination. It is empirically demonstrated that the improvement in accuracy of the new CSD over previously proposed HMM-based CSDs increases substantially with the number of loci. The framework presented here can be adopted in a wide range of applications in population genetics, including imputing missing sequence data, estimating recombination rates, and inferring human colonization history.     

Hybridocytochemistry with non-radioactive probes as a tool for biomedical research and cytodiagnostics

The advent of DNA and RNA labelling techniques which allow non-autoradiographic detection of specific nucleic acid sequences has opened new possibilities for rapid diagnosis at the nucleic acid level. There are already practical applications. However, in order to fully compete with radioactive procedures an increase in sensitivity is still desired.     

Shedding light on health and disease using molecular beacons.

The detection and identification of pathogens is often painstaking due to the low abundance of diseased cells in clinical samples. The genomic sequences of the pathogen can be amplified through methods such as the polymerase chain reaction and nucleic acid sequence-based amplification, but the nucleic acid targets are often lost among other unintended products of amplification. Novel nucleic acid probes known as molecular beacons have been developed allowing for the rapid and specific detection of genetic markers of a disease. Molecular beacons are hairpin-forming oligonucleotides labelled at one end with a quencher and at the other end with a fluorescent reporter dye. In the absence of target, the fluorescence is quenched. In the presence of target, the hairpin structure opens upon beacon/target hybridisation, resulting in the restoration of fluorescence. The ability to transduce target recognition into a fluorescence signal with high signal-to-background ratio, coupled with an improved specificity, has allowed molecular beacons to enjoy a wide range of biological and biomedical applications. Here, we describe the basic features of molecular beacons, review their applications in disease detection and diagnosis and discuss some of the issues and challenges of in vivo studies. The aim of this paper is to foster the development of new molecular beacon-based assays and to stimulate the application of this technology in laboratory and clinical studies of health and disease.