Code Recognition Research Articles

Error Compensation for Low-Density Circular Gratings Based on Linear Image-Type Angular Displacement Measurements

The image-type angular displacement measurement method based on linear image recognition has garnered attention because of its higher frequency response, strong fault tolerance, and high robustness. In the small-size image angular displacement measuring device, due to the limited pixel size, the circular grating cannot place more lines when realizing single-channel absolute coding recognition on a small diameter grating disk. This leads to larger errors in angular displacement measurement when the line density of the grating disk is low. To improve the measurement accuracy of small-scale displacement, the present work aimed to reduce this error by studying the error compensation method involving low-density grating disks. First, the mechanism of linear image-type angular displacement measurements is described, and a measurement algorithm based on linear scan images is proposed. Second, the measurement error model for low-density grating disks is established according to the proposed measurement algorithm. Third, a simplified error compensation algorithm based on a harmonic model is developed. Finally, simulations and experiments are performed to verify the performance of the proposed algorithm. Simulation results show that the developed harmonic compensation algorithm can effectively reduce the error caused by the low-density circular grating. When the proposed error compensation algorithm is applied to a grating disk with a 62 mm diameter and 2 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">^N</i> lines, the measurement accuracy is improved from 8.14” to 4.78”. The proposed error compensation algorithm can significantly improve the accuracy of linear image-type angular displacement measurements involving low-density grating disks, and the results presented herein laid a foundation for improving the accuracy and engineering applicability of angular displacement measurement technology.

Abstract PR002: Insights into the histone code recognition by the ATAD2B bromodomain

Abstract The ATPase family, AAA domain-containing protein 2 (ATAD2/ANCCA), is an AAA nuclear co-regulator protein containing two ATPase domains and a bromodomain. Its closely related paralog, ATAD2B (KIAA1240), also contains two ATPase domains and a bromodomain. The AAA ATPase domains are broadly associated with ATP-driven molecular remodeling reactions while the bromodomains are evolutionarily conserved, chromatin ‘reader’ domains known to regulate gene expression by binding to acetyllysine on histones. Extensive studies on ATAD2 discuss its upregulation and correlation with poor prognosis in various cancers. Despite sharing high structural and sequence similarity with ATAD2, ATAD2B remains a poorly understood paralog. While previous immunostaining studies detected high expression levels of ATAD2B in breast carcinoma, there is minimal information on its role in oncogenesis. Previously, we have shown that the ATAD2B BRD can recognize mono- and di-acetyllysine modifications on N-terminal tails of histones H4 and H2A. However, since initiation and progression of cancer are characterized by multivalent histone marks, our goal is to understand how crosstalk between combinatorial histone modifications affects the acetyllysine recognition activity of the ATAD2B BRD. We hypothesize that the bromodomain recognizes the acetyllysine mark on multivalent histones and interacts with the chromatin and the ATPase domain. We expect that our results will explain the function of the ATAD2B bromodomain in the context of the overall role of ATAD2B in normal biological and cellular processes. Since bromodomains are excellent drug targets, blocking their activity will also suggest how to disrupt their possible role in oncogenesis. In this study, we have combined various innovative and interdisciplinary approaches ranging from biochemistry and structural biology to functional genomics and cellular biology to gain insights into how crosstalk between different histone H4 PTMs can modulate the chromatin ‘reader’ activity of the ATAD2B BRD. Binding affinities obtained from ITC indicate that the ATAD2B BRD can recognize the acetyllysine mark amongst multiple histone H4 PTMs. Most of these adjacent PTMs are permissible and show high affinities, while some combinations weaken the acetyllysine interaction. Our novel X-ray structures demonstrate a unique binding mode of ATAD2B BRD compared to ATAD2. While the difference in ligand selectivity could suggest that ATAD2B may regulate different biological functions, our cellular assays, including western blot and functional genomic studies, indicate that ATAD2B is conserved in its ability to bind the chromatin. Finally, we discuss how known ‘onco’ mutations within the histone H4 tail region, occurring at or around sites of PTMs, can affect the ATAD2B BRD - acetyllysine coordination. Overall, our study highlights how crosstalk between various histone PTMs regulates the ‘reader’ domain of ATAD2B and affects its recruitment to the chromatin, thus providing new insights for developing therapeutic interventions for treating various diseases. Citation Format: Margaret Phillips, Kathleen Quinn, Cameron Montgomery, Samuel P. Boyson, Sunsik Chang, Jay C. Nix, Seth E. Frietze, Karen C. Glass. Insights into the histone code recognition by the ATAD2B bromodomain. [abstract]. In: Proceedings of the AACR Special Conference: Cancer Epigenomics; 2022 Oct 6-8; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2022;82(23 Suppl_2):Abstract nr PR002.

A weakly supervised approach for recycling code recognition

Waste sorting at the household level is a virtuous process that can greatly increase material recycling and boost the circular economy. To this purpose, waste must be differentiated by material (e.g., PVC, Polyethylene, Paper, Glass, Aluminum, etc.), a task that can be simplified by printing a recycling code on the product case. Unfortunately, the large number of recycling codes printed on products makes this process unfriendly for many users. In this work, we propose a vision-based mobile application to support users in recognizing recycling codes for proper waste sorting. The proposed system combines a dual-head CNN with an image processing pipeline (based on domain knowledge) in order to improve: (i) the reliability of symbol detection/classification and (ii) the weakly-supervised labeling of new samples during iterative training. Our experimental results prove the feasibility of developing effective applications with minimum effort in terms of data collection and labeling, which is one of the main obstacles to successfully applying deep-learning techniques to real-world problems.

Definition of a saxitoxin (STX) binding code enables discovery and characterization of the anuran saxiphilin family

American bullfrog (Rana castesbeiana) saxiphilin (RcSxph) is a high-affinity "toxin sponge" protein thought to prevent intoxication by saxitoxin (STX), a lethal bis-guanidinium neurotoxin that causes paralytic shellfish poisoning (PSP) by blocking voltage-gated sodium channels (NaVs). How specific RcSxph interactions contribute to STX binding has not been defined and whether other organisms have similar proteins is unclear. Here, we use mutagenesis, ligand binding, and structural studies to define the energetic basis of Sxph:STX recognition. The resultant STX "recognition code" enabled engineering of RcSxph to improve its ability to rescue NaVs from STX and facilitated discovery of 10 new frog and toad Sxphs. Definition of the STX binding code and Sxph family expansion among diverse anurans separated by ∼140 My of evolution provides a molecular basis for understanding the roles of toxin sponge proteins in toxin resistance and for developing novel proteins to sense or neutralize STX and related PSP toxins.

Machine learning FSO-SAC-OCDMA code recognition under different weather conditions

Nowadays, transmitting and receiving data with high speed and a high level of security are the main demands. So, a new model of spectral amplitude coding optical code division multiple access (SAC-OCDMA) is suggested in this paper, based on a free space optical (FSO) communication system using coherent sources. Three different codes: enhanced double weight (EDW), modified double weight (MDW) and multi-diagonal (MD) codes are assigned to our proposed model with the direct detection (DD) technique. Furthermore, the model is simulated under different weather conditions including clear air (CA), light mist (LM), very light fog, and light fog (LF). The system performance is evaluated through its bit error rate (BER), Q-factor, received power, and signal to noise ratio (SNR). Moreover, classification of the information received by the three different SAC-OCDMA using three different codes (EDW, MDW, and MD) is still challenging. So, two different machine learning (ML) algorithms are used, in this study, to classify the data received using the different codes. Detecting which code is received at the receiver end is important in order to reduce code error detection. Two algorithms: K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are adopted to classify different codes used for data transmission under four different weather conditions. The ML input dataset consists of the obtained simulation results, including Q-factor, BER, and SNR. Each feature is to be normalized before using ML. The obtained results show that the performance of the proposed FSO model achieved the longest propagation range under CA weather conditions, 7 km, while the shortest is under LF, which is 0.98 km. This is due to the attenuation of fog that causes signal degradation. The FSO system that uses EDW gives the best result under different weather conditions, while the system that uses MD code gives the worst performance. Also, the highest power is achieved when the EDW code is used at 5.5 km. The EDW has a received power of − 21.58 dBm, while the received power is − 22.04 dBm and − 23.8 dBm for MDW and MD codes, respectively. As for classification between the received information coming from three different codes under different weather conditions, both algorithms, KNN and SVM, achieve promising results in most cases. They showed more than 97% of classification accuracy under CA, LM, and LF weather conditions.

Artificial Tactile Recognition Enabled by Flexible Low-Voltage Organic Transistors and Low-Power Synaptic Electronics.

The advancement of self-powered intelligent strain systems for human-computer interaction is crucial toward wearable and energy-saving applications. Simultaneously, lowering operating voltage and thus reducing power consumption are of particular interests. A brain-like smart synaptic hardware system is considered as a promising candidate for low-power, parallel computing and learning processes. However, the combination of low-voltage organic transistors and energy efficient smart synapse hardware systems driven by a tactile signal has been hindered by the limited materials and technology. Here, by employing an elastomeric copolymer poly(vinylidene fluoride-co-hexafluoropropylene) (PVDF-HFP) with a high HFP content of 25 mol %, flexible, low-voltage transistors (|VG| ≤ 3 V) and a low energy consumption synapse ≤ 9.2 × 10-17 J are devised simultaneously, along with the lowest quality factor (R = Pw × VG, 2.76 × 10-16 J V). Furthermore, based on the low voltage and low power consumption characteristics, flexible artificial tactile recognition system and Morse code recognition are established without any computing supporting. Mechanical flexibility, cycling stability, image contrast enhancement functions, and simulated pattern recognition accuracy of the multilayer perceptron neural network are also simulated. This work recommends a route of exploiting low voltage, low power consumption synaptic systems and smart human-machine interfaces with low energy loss based on flexible organic synaptic transistors.

Online Control Method of Small- and Medium-Sized Electromechanical Equipment Based on Deep Neural Network

In order to improve the online control effect of small- and medium-sized electromechanical equipment, this paper studies the online control method of small- and medium-sized electromechanical equipment combined with the deep audit network. Moreover, starting from the signal basis of online control signal recognition and channel coding recognition of electromechanical equipment, this paper determines the type of online control signal and channel coding type of electromechanical equipment required for the experiment. This paper compares the signals under different types of online control signals for electromechanical devices and clarifies the differences in amplitude, frequency, phase, and spectrum in time-domain waveforms. In addition, through the elaboration of different channel coding theories, this paper clarifies the differences in coding methods. Through the experimental research, it can be seen that the online control effect of the small- and medium-sized electromechanical equipment based on the deep neural network proposed in this paper is very good.

Augmented reality material management system based on post-processing of aero-engine blade code recognition

The efficient management of aero-engine blades plays a vital role in improving material turnover and productivity, while the automatic recognition of blade code provides support for digital production. However, there is a lack of discussion about intelligent recognition, result correction, and effective solutions to material management methods for aero-engine blades. There is still a lot of manual work. Therefore, we developed an augmented reality (AR) material management system based on the post-processing of aero-engine blade code recognition, which not only supports the semi-automatic recognition of blade codes but also provides users with guidance on efficient storage and selection. Firstly, we proposed a line classification method of code Optical Character Recognition (OCR) recognition results to determine the structural relationship of discrete characters. Secondly, we constructed a Bayes error correction model which fuses the noise channel model to achieve the post-processing correction of wrong codes. Lastly, we developed the AR auxiliary guidance module to guide users on warehousing. The results show that the proposed line classification algorithm outperforms the baseline method, achieving a high success rate in terms of line classification. Post-processing error correction is effective in improving the accuracy of OCR results. In addition, AR visualization guidance can lead to a significant improvement in efficiency in material entry and out for aero-engine blades. In conclusion, the system proposed in this paper provides an effective solution to material management for the aero-engine blade.

Flexible thermochromic fabrics enabling dynamic colored display

Color-changeable fibers can provide diverse functions for intelligent wearable devices such as novel information displays and human–machine interfaces when woven into fabric. This work develops a low-cost, effective, and scalable strategy to produce thermochromic fibers by wet spinning. Through a combination of different thermochromic microcapsules, flexible fibers with abundant and reversible color changes are obtained. These color changes can be clearly observed by the naked eye. It is also found that the fibers exhibit excellent color-changing stability even after 8000 thermal cycles. Moreover, the thermochromic fibers can be fabricated on a large scale and easily woven or implanted into various fabrics with good mechanical performance. Driven by their good mechanical and physical characteristics, applications of thermochromic fibers in dynamic colored display are demonstrated. Dynamic quick response (QR) code display and recognition are successfully realized with thermochromic fabrics. This work well confirms the potential applications of thermochromic fibers in smart textiles, wearable devices, flexible displays, and human–machine interfaces.Graphical

Cigarette box code recognition based on machine vision

This paper addresses this challenge by using machine vision to firstly collect cigarette box image data and process the images with grayscale and binarization, and then extract the characters to be trained by extracting the region of interest and doing threshold segmentation in turn. The SVM classifier was used to train the extracted characters, and finally the characters were recognized in turn, and the recognition effects of different classifiers were compared and analyzed, and it was concluded that the SVM classifier has the best effect and is suitable for enterprise production.

DeepZF: improved DNA-binding prediction of C2H2-zinc-finger proteins by deep transfer learning.

Cys2His2 zinc-finger (C2H2-ZF) proteins are the largest class of human transcription factors and hence play central roles in gene regulation and cell function. C2H2-ZF proteins are characterized by a DNA-binding domain containing multiple ZFs. A subset of the ZFs bind diverse DNA triplets. Despite their central roles, little is known about which of their ZFs are binding and how the DNA-binding preferences are encoded in the amino acid sequence of each ZF. We present DeepZF, a deep-learning-based pipeline for predicting binding ZFs and their DNA-binding preferences given only the amino acid sequence of a C2H2-ZF protein. To the best of our knowledge, we compiled the first in vivo dataset of binding and non-binding ZFs for training the first ZF-binding classifier. Our classifier, which is based on a novel protein transformer, achieved an average AUROC of 0.71. Moreover, we took advantage of both in vivo and in vitro datasets to learn the recognition code of ZF-DNA binding through transfer learning. Our newly developed model, which is the first to utilize deep learning for the task, achieved an average Pearson correlation greater than 0.94 over each of the three DNA binding positions. Together, DeepZF outperformed extant methods in the task of C2H2-ZF protein DNA-binding preferences prediction: it achieved an average Pearson correlation of 0.42 in motif similarity compared with an average correlation smaller than 0.1 achieved by extant methods. By applying established interpretability techniques, we show that DeepZF inferred biologically relevant binding principles, such as the effect of amino acid residue positions on ZF DNA-binding potential. DeepZF code, model, and results are available via github.com/OrensteinLab/DeepZF. Supplementary data are available at Bioinformatics online.

Breathing new life into death certificates: Extracting handwritten cause of death in the LIFE-M project

The demographic and epidemiological transitions of the past 200 years are well documented at an aggregate level. Understanding differences in individual and group risks for mortality during these transitions requires linkage between demographic data and detailed individual cause of death information. This paper describes the digitization of almost 185,000 causes of death for Ohio to supplement demographic information in the Longitudinal, Intergenerational Family Electronic Micro-database (LIFE-M). To extract causes of death, our methodology combines handwriting recognition, extensive data cleaning algorithms, and the semi-automated classification of causes of death into International Classification of Diseases (ICD) codes. Our procedures are adaptable to other collections of handwritten data, which require both handwriting recognition and semi-automated coding of the information extracted.

Ecological Concept of Basic Computer Vision and Visual Communication of Advertising under the Concept of Ecological Design

With the importance people attach to the harmony of ecosystem in modern society, the concept of ecological design has been adopted in some industries and is gradually being valued and recognized by people. In real life, advertising design and production is an important field of art design. With the rapid development of society and the continuous updating of network information technology, network advertising and visual communication design inevitably collide. As a new form of advertising, network advertising had become a part of people’s network life. This paper analyzes the technical characteristics of image transformation, image enhancement, image restoration, image coding, and image recognition in computer vision processing. Through the image processing algorithm and program of computer, the advertising image can be processed to realize the functions of recognition, restoration, coding, enhancement, and transformation of advertising image. This thesis had studied the visual communication design in modern online advertising under the concept of ecological design. Using computer vision processing technology, this thesis had studied how to process the ecological concept and advertising visual communication content through computer vision technology, which will help to better improve the configuration of online advertising and create a more pleasant visual environment. It is of great significance to promote the rapid development of online advertising industry.

Learning probabilistic protein-DNA recognition codes from DNA-binding specificities using structural mappings.

Knowledge of how proteins interact with DNA is essential for understanding gene regulation. Although DNA-binding specificities for thousands of transcription factors (TFs) have been determined, the specific amino acid–base interactions comprising their structural interfaces are largely unknown. This lack of resolution hampers attempts to leverage these data in order to predict specificities for uncharacterized TFs or TFs mutated in disease. Here we introduce recognition code learning via automated mapping of protein–DNA structural interfaces (rCLAMPS), a probabilistic approach that uses DNA-binding specificities for TFs from the same structural family to simultaneously infer both which nucleotide positions are contacted by particular amino acids within the TF as well as a recognition code that relates each base-contacting amino acid to nucleotide preferences at the DNA positions it contacts. We apply rCLAMPS to homeodomains, the second largest family of TFs in metazoans and show that it learns a highly effective recognition code that can predict de novo DNA-binding specificities for TFs. Furthermore, we show that the inferred amino acid–nucleotide contacts reveal whether and how nucleotide preferences at individual binding site positions are altered by mutations within TFs. Our approach is an important step toward automatically uncovering the determinants of protein–DNA specificity from large compendia of DNA-binding specificities and inferring the altered functionalities of TFs mutated in disease.

Analysis of Combination of Parking System with Face Recognition and QR Code using Histogram of Oriented Gradient Method

Security is very important everywhere, including in the campus environment. To provide security and comfort for those who park their vehicles, a parking application is needed that can provide vehicle security while undergoing academic activities on campus. QR code (Quick Response Code) is a technology for converting written data into a two-dimensional code, which is printed on a more compact medium capable of storing various types of data. The most common individual part used to identify a person is the face because it has the unique characteristics of everyone. Histogram of Oriented Gradient (HOG) is a feature extraction used for face identification based on histogram of gradient orientation and gradient magnitude. This application is implemented using the Dlib library for facial recognition. The implementation of this method is expected to improve parking security and provide a record of parked vehicles. The results of testing the implementation of facial recognition methods into android applications show very satisfactory results. With the results of testing the QR code scanning accuracy of 100% and an accuracy of 90% for a 7% damage rate and an accuracy of 85% for a 15% damage rate, and the results of facial recognition testing of 90% on face photos wearing helmets and an accuracy of 92% on photo of face without helmet.

Flexibility of flanking DNA is a key determinant of transcription factor affinity for the core motif

Selective gene regulation is mediated by recognition of specific DNA sequences by transcription factors (TFs). The extremely challenging task of searching out specific cognate DNA binding sites among several million putative sites within the eukaryotic genome is achieved by complex molecular recognition mechanisms. Elements of this recognition code include the core binding sequence, the flanking sequence context, and the shape and conformational flexibility of the composite binding site. To unravel the extent to which DNA flexibility modulates TF binding, in this study, we employed experimentally guided molecular dynamics simulations of ternary complex of closely related Hox heterodimers Exd-Ubx and Exd-Scr with DNA. Results demonstrate that flexibility signatures embedded in the flanking sequences impact TF binding at the cognate binding site. A DNA sequence has intrinsic shape and flexibility features. While shape features are localized, our analyses reveal that flexibility features of the flanking sequences percolate several basepairs and allosterically modulate TF binding at the core. We also show that lack of flexibility in the motif context can render the cognate site resistant to protein-induced shape changes and subsequently lower TF binding affinity. Overall, this study suggests that flexibility-guided DNA shape, and not merely the static shape, is a key unexplored component of the complex DNA-TF recognition code.

Polar Code Parameter Recognition Algorithm Based on Dual Space

To improve the performance of polar code parameter recognition in the fields of intelligent communication, communication detection, and network countermeasures, we propose a new recognition scheme for the additive white Gaussian noise (AWGN) channel. The scheme turns parameter recognition problems into hypothetical tests and is effective due to the check relationship between the received codeword and the dual space determined by the correct parameters. First, a sub-matrix is obtained by removing the frozen-bit-index rows of the polar code generator matrix, and then its dual matrix is calculated. To check the relationship of the dual matrix and codewords, the average likelihood ratio of codewords is introduced as a test statistic, and then the corresponding decision threshold is deduced. Next, the degree of conformity of polar code recognition is defined, and the minimum code length and code rate corresponding to the highest degree of conformity are chosen to calculate the index of information-bit positions by a Gaussian approximation (GA) construction algorithm. Finally, the chosen code length, code rate, and corresponding index are provided as the recognition results. Simulation results show that the algorithm can achieve effective parameter recognition in both high-signal-to-noise (SNR) and low-SNR environments, and that the algorithm’s recognition performance increases with decreasing code rate and code length. The parameter recognition rate with a code length of 128 and code rate of 1/5 is close to 100% when the SNR is 4 dB, and the algorithm complexity increases almost linearly with the decreasing code rate and the increasing length of the intercepted data.

Calculation and Performance Evaluation of Text Similarity Based on Strong Classification Features

Abstract Based on the strong classification feature recognition algorithm, the calculation algorithm of a text semantic similarity is studied with the performance evaluation in this paper. In order to achieve a general algorithm for this function, the semantic function library based on a semantic recognition code as a comparison object is designed. It drives the algorithm modules of two fuzzy neuron deep convolution machine learning, and between these two processes of machine learning, a rigid algorithm based on Fourier transform frequency domain feature is extracted. Finally, a more complex machine learning general algorithm is realized by the use of external data fuzzy algorithm and de-fuzzy algorithm before and after the algorithm module. It is also a technical innovation in this paper. Through the performance evaluation based on the subjective evaluation of volunteers, it is found that the system focuses on the text semantic similarity evaluation of the Chinese language, and achieves a comparison result of 81.78% of the artificial judgment accuracy rate, and only 5.52% of the volunteers believe that the system judgment result is completely different from that of manual judgment.

Perbandingan Face Recognition dan QR Code Dalam Sistem Absensi Menggunakan Geolocation Berbasis Mobile

Abstract— The development of increasingly sophisticated technology makes mobile devices become main alternative in managing life's affairs. Mobile device that offers services and computing is a smartphone. The sophistication of smartphone technology can be used to process attendance. Attendance system is a system that can record presence of each user, attendance system can be processed using several types of attendance including conventional attendance using a signature and digital attendance using Face Recognition and QR code. Processing attendance system, the geolocation feature can be used to find location. This study aims to explain and determine the best digital attendance method between Face Recognition and QR code using geolocation. Based on the explanation of previous research and comparing the Face Recognition and QR code methods in processing the attendance system, the results obtained that the QR code method is the best method for digital attendance because it has high accuracy and is easier to implement.&#x0D; Key Words— Attendance System, Mobile Device, Geolocation, Face Recognition, QR code

STBC Recognition for OFDM Transmissions: Channel Decoder Aided Algorithm

Recently, the process of space-time block coding (STBC) recognition has found applications in a wide range of wireless transmissions. Numerous investigations on this topic have been developed for single-carrier transmissions and a few studies have been introduced for orthogonal frequency division multiplexing (OFDM) transmissions. The previous research work in the literature has focused on exploiting the space-time redundancy to blindly estimate the type of STBC signal. In this work, we propose a new approach to design a STBC recognizer for OFDM transmissions by taking benefits from the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a posteriori</i> probabilities provided by a channel decoder. The mathematical treatments have shown that the exact maximum-likelihood (ML) solution to this problem is computationally demanding in the absence of a closed form. Therefore, we settle for the expectation-maximization (EM) algorithm as a low-complexity procedure to perform STBC recognition. In addition, we develop a channel estimation algorithm to be integrated into the proposed recognition algorithm. Simulation results are presented to confirm the theoretical analysis, with exhibiting superior recognition performance over the state-of-the-art algorithms.