Coding Dictionary Research Articles

A qualitative study of perspectives on research participation among individuals who recently experienced an abortion in Hawaiʻi

ObjectivesThe United States Code of Federal Regulations mandates extra protections for research involving pregnant participants seeking abortions. This study aims to understand the perspectives of abortion patients regarding recruitment, decision-making, and participation in research. Study designWe recruited adults in Hawaiʻi who reported at least one induced abortion in the previous 6 months. Recruitment strategies included online advertisements and flyers posted in reproductive health clinics. We conducted in-person, semistructured interviews exploring research preferences. The authors collaboratively reviewed the resulting transcripts and created a code dictionary. We reviewed, organized, condensed, and diagrammed the resulting data to identify dominant themes. ResultsBetween February and November 2019, we interviewed 25 participants aged 18–41 years who had medication (n = 14) or procedural (n = 11) abortions. Interviews ranged from 32 to 77 minutes (mean = 48 minutes). Four themes emerged: (1) people having abortions are capable of making informed decisions about research participation, (2) abortion-related stigma influences research decision-making, (3) people having abortions prefer to learn about study opportunities early and through participant-driven recruitment methods, and (4) the ideal role of the abortion provider in research is unclear. ConclusionsAbortion patients in this study want to be informed of research opportunities and feel capable of deciding about participation in research studies. Current federally mandated protections and common research practices could be revisited and revised to better reflect these preferences. ImplicationsRevision of federal regulations and optimization of recruitment methods may allow researchers to improve the research experience for patients having an abortion.

COVID-19Base v3: Update of the knowledgebase for drugs and biomedical entities linked to COVID-19.

COVID-19 has taken a huge toll on our lives over the last 3 years. Global initiatives put forward by all stakeholders are still in place to combat this pandemic and help us learn lessons for future ones. While the vaccine rollout was not able to curb the spread of the disease for all strains, the research community is still trying to develop effective therapeutics for COVID-19. Although Paxlovid and remdesivir have been approved by the FDA against COVID-19, they are not free of side effects. Therefore, the search for a therapeutic solution with high efficacy continues in the research community. To support this effort, in this latest version (v3) of COVID-19Base, we have summarized the biomedical entities linked to COVID-19 that have been highlighted in the scientific literature after the vaccine rollout. Eight different topic-specific dictionaries, i.e., gene, miRNA, lncRNA, PDB entries, disease, alternative medicines registered under clinical trials, drugs, and the side effects of drugs, were used to build this knowledgebase. We have introduced a BLSTM-based deep-learning model to predict the drug-disease associations that outperforms the existing model for the same purpose proposed in the earlier version of COVID-19Base. For the very first time, we have incorporated disease-gene, disease-miRNA, disease-lncRNA, and drug-PDB associations covering the largest number of biomedical entities related to COVID-19. We have provided examples of and insights into different biomedical entities covered in COVID-19Base to support the research community by incorporating all of these entities under a single platform to provide evidence-based support from the literature. COVID-19Base v3 can be accessed from: https://covidbase-v3.vercel.app/. The GitHub repository for the source code and data dictionaries is available to the community from: https://github.com/91Abdullah/covidbasev3.0.

Distributed energy‐efficient data reduction approach based on prediction and compression to reduce data transmission in IoT networks

SummaryIn the modern world, it will be necessary to deploy a large number of sensor devices to sense everything around us in order to detect changes, risks, and hazards and to mitigate them. This increasing number of sensor devices represents an essential data provider in the Internet of Things (IoT). The devices generate and transmit a huge amounts of data which requires a large amount of storage and high processing power to come real‐time processing and speed up the network. It also leads to an increase in high energy consumption. Thus, it is important to remove redundant data to reduce the data transmission before sending it to the gateway while maintaining a good level of data quality. In this paper, a distributed energy‐efficient data reduction (DEDaR) approach based on prediction and compression to minimize the data transmission in IoT Networks is proposed. The DEDaR is used in periods to make decision. In each period, the autoregressive prediction (ARP) is used to predict the data of the next period and make a decision on whether to send the data of the current period to the gateway or not. In the case of data transmission, the redundant data are eliminated using an efficient compression approach based on adaptive piecewise constant approximation (APCA), symbolic aggregate approximation (SAX), and finally fixed code dictionary (FCD) based on Huffman encoding. The simulation results based on real‐sensed data show that the proposed DEDaR approach outperforms the other recent methods in terms of data reduction percentage, transmitted data size, energy consumption, and data accuracy.

QMVO-SCDL: A new regression model for fMRI pain decoding using quantum-behaved sparse dictionary learning

The exponential growth of functional magnetic reasoning imaging (fMRI) data offers a great opportunity for basic and clinical research to explore functional brain activity. Nonetheless, due to the lack of effective and efficient tools for handling high-dimensional and complex fMRI data, this potential has still not been fully explored. A critical issue to be addressed is to identify clinically relevant features from high dimensional fMRI data in a fast and accurate manner. To address this problem, a new quantum-behaved multiverse optimization (QMVO) approach is proposed for fMRI dimensionality reduction and a new prediction approach based on L1-norm sparse coding and adaptive dictionary learning (SCDL) is developed to decode the whole brain fMRI data. QMVO is designed to enhance local search ability, avoid premature convergence, and increase population diversity among individuals. Further, to efficiently re-estimate parameters of the prediction model with new available data, a new SCDL sparse coding is proposed, which requires no training and needs minimal parameters to tune. The proposed QMVO-SCDL model is applied to a pain-evoked fMRI dataset to decode the pain perception level. Results show that QMVO-SCDL can decode pain levels and identify predictive fMRI patterns with high accuracy, high convergence speed, and short consumption time. Moreover, the performance of the proposed model outperforms different recent ML techniques. Therefore, the proposed model has a great promise to be a powerful tool for fMRI decoding.

Deep hashing with self-supervised asymmetric semantic excavation and margin-scalable constraint

Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative hash codes for images associated with multiple semantics for two main reasons, 1) similarity constraints designed in most of the existing methods are based upon an oversimplified similarity assignment(i.e., 0 for instance pairs sharing no label, 1 for instance pairs sharing at least 1 label), 2) the exploration in multi-semantic relevance are insufficient or even neglected in many of the existing methods. These problems significantly limit the discrimination of generated hash codes. In this paper, we propose a novel Deep Hashing with Self-Supervised Asymmetric Semantic Excavation and Margin-Scalable Constraint(SADH) approach to cope with these problems. SADH implements a self-supervised network to sufficiently preserve semantic information in a semantic feature dictionary and a semantic code dictionary for the semantics of the given dataset, which efficiently and precisely guides a feature learning network to preserve multi-label semantic information using an asymmetric learning strategy. By further exploiting semantic dictionaries, a new margin-scalable constraint is employed for both precise similarity searching and robust hash code generation. Extensive empirical research on four popular benchmarks validates the proposed method and shows it outperforms several state-of-the-art approaches. The source codes URL of our SADH is:http://github.com/SWU-CS-MediaLab/SADH.

English-language Business Discourse as a Basis for Reflecting Speech Strategies

The problem of defining business discourse is to determine its place in the common national language. The aim of the proposed research is to systematize the scientific views of linguists to define the concept of business discourse in modern linguistics and identify its features as one of the institutional types of discourse. The concept of “discourse” is very ambiguous. It comes from the Latin word discursus, which literally means running in different directions. Gradually, the term acquires a huge number of different meanings. However, with all the variety of approaches, it is worth noting two main ones. Proponents of the first approach understand discourse as fragments of reality that have a temporal length, logic of unfolding (plot) and which are a finished work formed on the basis of the organization of meanings using the semantic code (dictionary, etc.). Discourse is part of the continuous movement of human experience. Due to this, it reflects the unique coincidence of circumstances in which and for which it was created. Determining the basic conditions for successful interaction of communicators of political discourse, we share the views of scholars. There are different views on the communicative and functional spheres of business discourse. Some scholars understand very narrowly the scope of application of this type of discourse, limiting it only to the professional activities of businessmen, others, on the contrary, significantly expand the range of situations in which business discourse may occur, including, in addition to business correspondence, negotiations, including telephone, and concluding agreements, as well as the procedure for hiring and firing, advertising, legal aspects and forms of business activity, policies, issues related to business coverage in the media, secular conversation and much more.

35. Acceptability of Proposed Stewardship Interventions to Reduce Preoperative Screening and Treatment of Asymptomatic Bacteriuria

Abstract Background In 2019, the IDSA Clinical Practice guidelines on asymptomatic bacteriuria (ASB) recommended that clinicians no longer screen or treat patients for ASB before non-urological surgeries. However, it remains to be seen whether these guideline recommendations alone will produce changes in practice. Understanding clinical decision-making about preoperative urine screening and treatment can help design effective interventions to facilitate guideline concordance and support antibiotic stewardship. Our project objective was to qualitatively assess barriers and facilitators to reducing preoperative urine testing and treatment. Methods We conducted semi-structured interviews with 24 participants (surgeons, advance practice providers, pharmacists, infectious disease physicians, epidemiologists) at 4 Veterans Administration hospitals. We solicited feedback on 4 proposed interventions (substitution, lab restrictions, audit and feedback, interactive workshop), and invited suggestions on other interventions. Three researchers separately coded 20% of interview notes to sort responses to each intervention into acceptable, possibly acceptable, and not acceptable. The team then compared coding, resolved differences by consensus, and refined the code dictionary to ensure intercoder agreement; then each member coded one third of remaining notes. Results Participants expressed concerns about de-implementing routine urine testing and treatment for specific procedures and specialties (e.g., cardiothoracic). Some actively sought to identify and treat ASB. Participants found audit and feedback and substitution of different infection-control practices most acceptable. Participants suggested changes to make interventions more acceptable or feasible (e.g., tailoring to procedure, educational tailoring). Participants also identified new potential interventions (e.g. order set changes, collaborative decision making, education on potential harms, identification of testing costs). Table 1. Acceptability of Proposed Interventions by Percentage of Participants. Percentages Do Not Add up to 100% Because Some Interviewees Did Not Answer Every Question. Conclusion Interventions to optimize urine screening and treatment for patients undergoing surgeries may require tailoring for surgical specialties, and should address clinical concerns about intervention feasibility. Disclosures Kalpana Gupta, MD, MPH, Abbott (Shareholder)DBC Pri-Med (Consultant)Glaxo Smith Kline (Consultant)Moderna (Shareholder)Nabriva Therapeutics (Consultant)Pfizer (Other Financial or Material Support, Grant to the institution)Qiagen (Consultant)Rebiotix (Consultant)Spero Therapeutics (Consultant)Utility Therapeutics (Consultant) Daniel Suh, MS MPH, General Electric (Shareholder)Merck (Shareholder)Moderna (Shareholder)Smile Direct Club (Shareholder) Bruce Alexander, PharmD, Bruce Alexander Consulting (Independent Contractor) Marin Schweizer, PhD, 3M (Grant/Research Support)PDI (Grant/Research Support)

Pansharpening of WorldView-2 Data via Graph Regularized Sparse Coding and Adaptive Coupled Dictionary.

The spectral mismatch between a multispectral (MS) image and its corresponding panchromatic (PAN) image affects the pansharpening quality, especially for WorldView-2 data. To handle this problem, a pansharpening method based on graph regularized sparse coding (GRSC) and adaptive coupled dictionary is proposed in this paper. Firstly, the pansharpening process is divided into three tasks according to the degree of correlation among the MS and PAN channels and the relative spectral response of WorldView-2 sensor. Then, for each task, the image patch set from the MS channels is clustered into several subsets, and the sparse representation of each subset is estimated through the GRSC algorithm. Besides, an adaptive coupled dictionary pair for each task is constructed to effectively represent the subsets. Finally, the high-resolution image subsets for each task are obtained by multiplying the estimated sparse coefficient matrix by the corresponding dictionary. A variety of experiments are conducted on the WorldView-2 data, and the experimental results demonstrate that the proposed method achieves better performance than the existing pansharpening algorithms in both subjective analysis and objective evaluation.

Automatic lumen border detection in IVUS images using dictionary learning and kernel sparse representation

Intravascular ultrasound (IVUS) images display the cross-sectional information of the lumen, from which the diameter and length of the lumen are accurately measured to calculate the volume. More importantly, they provide the tissue information of the plaque, thus assisting the diagnosis of coronary heart disease and effective interventional therapy. In this study, a fully automatic method is presented for the detection of the lumen contours in IVUS images of the coronary artery. First, texture feature vectors are extracted from the original images with a patch size of 3 × 3. The sparse coding and kernel dictionary learning are used to employ the features to construct two dictionaries for positive and negative tissues, respectively. Then a series of preprocessing helps to reduce the impact of artifacts, calculation cost and get approximate Region of interest (ROI). A kernel-cluster algorithm based on linear discrimination method is developed to classify the pixels in the ROI. In the end, morphological operations are used to improve the detection quality. Publicly available evaluation indicators are applied to the proposed algorithm with 326 test images of different structures. Mean value of the total results (JACC: 0.87, HD: 0.35, PAD: 0.09) outperforms the other automatic methods of the participants in the challenge. Besides, compared with the recent methods used on the same dataset, the proposed method shows good performance and high accuracy. Furthermore, kernel method and preprocessing steps are effective in acquiring better detection results by reducing the influences of artifacts.

Problem-solving and coping in family adaptation of children with Down Syndrome

To analyze problem-solving and coping strategies of parents of children with Down Syndrome in family adaptation. This is a qualitative research that used the Resiliency Model of Family Stress, Adjustment, and Adaptation. Participants were mothers and/or fathers from 40 families of children aged 1 to 7 years diagnosed with DS. Directed content analysis was performed, supported by software and considering a code dictionary. Problem-solving and coping proved to be a set of actions, behaviors, efforts, and communications that contributed to family adaptation and favored balance between the demands imposed by Down Syndrome and the acquisition of resources by the family. In the first moment, which corresponds to the time of news or diagnosis of the syndrome and the first days after birth, internal and external resources, which represent coping, are developed to accept and refocus ideas and feelings towards Down Syndrome. Over time these resources have an effect and cause changes in family functioning patterns and in the relationship of these families with the outside world, as they seek child development.

Dictionary-Based interpolation technique for text quality enhancement

This paper presents a new dictionary-based interpolation technique to improve text quality when the resolution of an image is increased, so that the text can be displayed on a high-resolution display device. The proposed algorithm analyzes an image and extracts the shape of the text from the image. Further, it encodes and decodes the pattern of the text, and enhances the legibility of the text using a pre-trained code dictionary. Therefore, the proposed method improves text quality in terms of sharpness. In the experiments, the proposed algorithm outperformed benchmark methods for all test images. Specifically, the proposed method reduced the blur index by up to 0.112.

The Poly Code Character of the English Learners’ Dictionaries

The paper deals with one of the most relevant questions of semiosis in English lexicography. The article studies the mechanism of double encoding a message (verbally and pictographically) to optimize the perception, processing, and storage of information by the user of the dictionary. The aim of the given research is to determine the features of an English poly code dictionary entry as a communicative phenomenon of educational lexicography. The study is based on five lexicographic sources, traditionally called the big five. The research material includes 1640 poly code entries. The article suggests a new interpretation of a poly code entry as a threefold unity of a lemma (the headword), a verbal definition, and a picture. These three constituents jointly name, interpret, and visualize the meaning of a dictionary entry. The article also analyzes the configuration of a poly code entry informational potential in terms of increasing/decreasing of the information presented by the iconic constituent in comparison with the verbal one. The research proves that the whole set of poly code dictionary entries reflects a particular view of the world characterized by absolute anthropocentricity and specific Anglo-Saxon bias. The results of the performed research are significant for English language teaching and learning as they prove that pictographic illustrations that accompany verbal explanations are not purely ornamental. They optimize the readers’ activity of searching, understanding, and memorizing the necessary information

Frequency Event Categorization in Power Distribution Systems Using Micro PMU Measurements

Frequency is an important metric for power stability. To enhance the situational awareness in power distribution systems, this paper proposes a data-driven approach that utilizes the data from micro phasor measurement units (μPMU) to categorize frequency events observed in distribution feeders. The proposed approach has three layers, each of which analyzes if a frequency event is propagated from the transmission system, formed inside a distribution feeder or falsely produced by instantaneous frequency (IF) estimation algorithms, respectively. In the first layer, the Granger causality is utilized to compare the causal relations from measurements across different locations to decide if an event is propagated from the transmission side. In the second layer, a trained sparse coding dictionary is utilized to unmix the physical causes of a frequency event. In the third layer, a moving z-score based event-pair detector is applied to identify if a frequency event is algorithm-induced. The proposed approach is tested using the μPMU measurements collected from Lawrence Berkeley National Laboratory (LBNL) and Riverside Public Utility (RPU).

ІНФОРМАЦІЙНІ ПАРАМЕТРИ КОДОВИХ АНСАМБЛІВ, СИНТЕОВАНИХ НА ОСНОВІ ОДНОГО МОДУЛЯ

The advantages of digital methods of processing, displaying, storing and transmitting information. Currently, various conversion methods and efficient coding methods are used to increase the speed of information transfer, maintain high accuracy and provide the required latent accuracy. In particular, timer (temporary) signal constructions, which, in comparison with other coding methods, for example, positional (bitwise) coding, can reduce costs by more than two times. In the work, the information parameters of the code ensembles synthesized at a constant duration "m" are evaluated. Determined the conditions for the formation of a code ensemble and calculate the number of code dictionary implementations on a segment of a nyquist elements.In order to use the communication channel efficiently, the proposed increase in the entropy of the transmitted ensemble is due to the use of code sets with different number of information segments and at a constant length of the code word. A significant increase in the weight of the synthesized ensemble ensured an increase in the value of the module А0 =19 integer times K є 8:18 .The maximum values of the module are calculated in which the greatest number of code words is synthesized: At: КА0 =13, Np=8; КА0 =14, Np=10 КА0 =15, Np=15; КА0 =17, Np=16 КА0 =18, Np=10; КА0 =19, Np=6 КА0 =20, Np=1 For these КА0 values, the entropy value is H=3.269, which is less than the entropy of the Russian text H=4.35. In accordance with code words that satisfy the conditions of the quality equation. The methods and algorithms of reliable reception of code words under the influence of interference in the channel used were analyzed.Studies and calculations have shown that the use of temporary signal structures synthesized on the basis of a onemodule can significantly reduce the value of entropy for the transmission of Russian text.

Endmember Learning with K-Means through SCD Model in Hyperspectral Scene Reconstructions.

This paper proposes a simple yet effective method for improving the efficiency of sparse coding dictionary learning (DL) with an implication of enhancing the ultimate usefulness of compressive sensing (CS) technology for practical applications, such as in hyperspectral imaging (HSI) scene reconstruction. CS is the technique which allows sparse signals to be decomposed into a sparse representation “a” of a dictionary . The goodness of the learnt dictionary has direct impacts on the quality of the end results, e.g., in the HSI scene reconstructions. This paper proposes the construction of a concise and comprehensive dictionary by using the cluster centres of the input dataset, and then a greedy approach is adopted to learn all elements within this dictionary. The proposed method consists of an unsupervised clustering algorithm (K-Means), and it is then coupled with an advanced sparse coding dictionary (SCD) method such as the basis pursuit algorithm (orthogonal matching pursuit, OMP) for the dictionary learning. The effectiveness of the proposed K-Means Sparse Coding Dictionary (KMSCD) is illustrated through the reconstructions of several publicly available HSI scenes. The results have shown that the proposed KMSCD achieves ~40% greater accuracy, 5 times faster convergence and is twice as robust as that of the classic Spare Coding Dictionary (C-SCD) method that adopts random sampling of data for the dictionary learning. Over the five data sets that have been employed in this study, it is seen that the proposed KMSCD is capable of reconstructing these scenes with mean accuracies of approximately 20–500% better than all competing algorithms adopted in this work. Furthermore, the reconstruction efficiency of trace materials in the scene has been assessed: it is shown that the KMSCD is capable of recovering ~12% better than that of the C-SCD. These results suggest that the proposed DL using a simple clustering method for the construction of the dictionary has been shown to enhance the scene reconstruction substantially. When the proposed KMSCD is incorporated with the Fast non-negative orthogonal matching pursuit (FNNOMP) to constrain the maximum number of materials to coexist in a pixel to four, experiments have shown that it achieves approximately ten times better than that constrained by using the widely employed TMM algorithm. This may suggest that the proposed DL method using KMSCD and together with the FNNOMP will be more suitable to be the material allocation module of HSI scene simulators like the CameoSim package.

Sample Selection with SOMP for Robust Basis Recovery in Sparse Coding Dictionary Learning

Sparse Coding Dictionary (SCD) learning is to decompose a given hyperspectral image into a linear combination of a few bases. In a natural scene, because there is an imbalance in the abundance of materials, the problem of learning a given material well is directly proportional to its abundance in the training scene. By a random selection of pixels to train a given dictionary, the probability of bases learning a given material is proportional to its distribution in the scene. We propose to use SOMP residue for sample selection with each iteration for a more robust or ‘more complete’ learning. Experiments show that the proposed method learns from both background and trace materials accurately with over 0.95 in Pearson correlation coefficient. Furthermore, the proposed implementation has resulted in considerable improvements in Target Detection with Adaptive Cosine Estimator (ACE).

The prediction role of feeling of injustice on network social mobilization

Purpose By drawing on the research paradigm of collective action that occurs in physical space, the present study aims to explore the antecedent predictors of network social mobilization – feeling of injustice – and discuss the emotional mechanism of this prediction: mediating effect of anger and resentment. Design/methodology/approach Micro-blog postings about network social mobilization were collected to develop the dictionary of codes of fairness, anger and resentment. Then, according to the dictionary, postings on Sina Weibo were coded and analyzed. Findings The feeling of injustice predicted network social mobilization directly. The predictive value was 27% and 33%, respectively during two analyses. The feeling of injustice also predicted social mobilization indirectly via anger and resentment. In other words, anger and resentment account for the active mechanism in which the feeling of injustice predicts network social mobilization. Mediating effect value was 29.63% and 33.33% respectively. Research limitations/implications This study is our first exploration to use python language to collect data from human natural language pointing on micro-blog, a large number of comments of netizen about certain topic were crawled, but a small portion of the comments could be coded into analyzable data, which results in a doubt of the reliability of the study. Therefore, we should put the established model under further testing. Practical implications In the cyberspace, this study confirms the mechanism of network social mobilization, expands and enriches the research on social mobilization and deepens the understanding of social mobilization. Social implications This study provides an empirical evidence to understand the network social mobilization, and it gives us the clue to control the process of network social mobilization. Originality/value This study uses the Python language to write Web crawlers to obtain microblog data and analyze the microblog content for word segmentation and matching thesaurus. It has certain innovation.

Identifying cultural codes of students in order to develop advert messages

Today it is necessary to improve effectiveness of advert messages used in advertising campaign of entrance exams at the Russian Plekhanov University of Economics. The problem can be resolved by designing such messages in compliance with authenticity of discourse of target audience respondents. ZMET-analysis – the method of metaphor extraction was used as the method of research. For this purpose a social survey was conducted, where a random set of well-known visual images for Russian mentality was shown to recipients, who were asked to choose from the list of psycho-emotional conditions provided in the questionnaire an unlimited number of personal associations. As a result of the social survey (the sample made up 603 people) mathematic and statistic analysis was carried out and a probability model of visual symbols impact on customer decision was built. Later a focus-group was organized (12 volunteers, 3rd year students) and a dictionary of cultural codes was developed. This dictionary was used in the enrollment campaign of 2018. To check the earlier research in-depth interview was arranged (3 participants, 3rd year students), on the basis of which the dictionary of cultural codes was revised and preliminary advert messages for entrance exams of 2019–2020 at the Russian Plekhanov University of Economics were developed.

Robust visual tracking via global context regularized Locality-constrained Linear Coding

Locality-constrained Linear Coding (LLC) based visual tracking can give a better and faster tracking performance than traditional sparse representation based tracking methods. However, the existing LLC based methods often use the anchor points near the target to build the sparse coding dictionary for local sparse coding. It may cause a problem that it is hard to discriminate the difference between the negative and positive anchor points in sparse coding dictionary when facing severe background clutter, illumination change and occlusion. In this paper, we propose a context aware sparse coding method to achieve robust visual tracking. The proposed method can prevent the negative anchor points from disturbing the classifier accuracy because it uses a global context regularizer to constrain the sparse coding value of those negative anchor points that are similar to the positive anchor points. Experiment results show that our method can achieve a better tracking performance than state-of-the-art tracking methods do.

Novel orthogonal based collaborative dictionary learning for efficient face recognition

Dictionary learning (DL) methods are widely used for pattern recognition in recent years. In most DL methods, the l1 norm is employed to promote sparsity of the coding. However, the usage of the sparse coding based methods is limited since solving the l1 based sparse coding is very time-consuming. In this paper, a novel orthogonal collaborative dictionary learning (CDL) method is proposed for accurate and efficient face classification. In this method, several class-specific dictionaries and one common dictionary are learned jointly from the training data, where the class-specific dictionaries are used to model the appearance of the subjects and the common dictionary is used to model the facial variations. To learn these dictionaries, we introduce an orthogonality promoting term to encourage the facial variations to be independent of the appearance as much as possible, and introduce a scatter constraint term to remove the variations in the class-specific dictionaries. Since CDL can derive analytical solutions for both code learning and dictionary updating, it is much more efficient than many other DL methods in terms of training and classification. Experiments conducted on seven face databases show that CDL outperforms many state-of-the-art DL methods and coding methods in both accuracy and efficiency.