Average Matching Rate Research Articles

Noninvasive visualization of the midline-crossing arterial variation in the deep inferior epigastric artery perforator flap using photoacoustic tomography for application in patients with abdominal scars

BackgroundThe importance of the subcutaneous arterial network crossing the midline in transverse abdominal flaps has been reported. Photoacoustic tomography can be used to noninvasively visualize subcutaneous vascular networks. We applied this novel technology preoperatively in patients undergoing breast reconstruction to detect individual variations in the midline-crossing arteries. MethodsSix patients scheduled to undergo breast reconstruction using free deep inferior epigastric artery perforator flaps were examined. Each scan of the 12×8-cm region took approximately 8min. The accuracy of the tentative arteries evaluation defined by photoacoustic tomography was compared with the arterial phase detected by intraoperative indocyanine green angiography. The number of perforator vessels used for the flap, surgical time for flap elevation, and perfusion area ratio were compared with those of the control group. ResultsThe average match rate between tentative arteries prediction by photoacoustic tomography and arterial-phase assessment by intraoperative angiography in 5 patients was 79.8%. Each midline crossing artery showed individual variations. The photoacoustic tomography group (PAT-1 to 5) showed 1.8 perforators per flap, 163minutes for flap elevation, and 93% perfusion area, with no significant differences from the control group (N=5). A 63-year-old woman (PAT-6) with abdominal scars, including a midline abdominal incision, showed a preserved midline crossing artery. The planned single perforator deep inferior epigastric perforator flap was successfully applied to the contralateral perfusion area. ConclusionsPhotoacoustic tomography noninvasively visualizes the subcutaneous midline-crossing arterial networks. Understanding individual vascular variations can support preoperative planning and surgical indication of abdominal flaps, especially in patients with postsurgical scars.

Muscle Property Optimization Based on Motion Intentionality for Motor Skill Augmentation

Understanding motion intentionality is important to augment motor skills. This can be explained by the anatomical structure and innate immune mechanisms of humans. This study aimed to analyze human motion using musculoskeletal information and estimate motion intentionality, motion direction, and muscle properties. The calculation method for the easy-to-move musculoskeletal direction in the task space was reversed to calculate the optimal muscle properties and matching rate for the motion direction. The analysis results of each walking and feint motion showed that the muscles were trained toward reduced muscular effort and improved skills for each motion. In addition, the results of the optimization of the matching rate and muscle properties indicate that the optimized muscle properties can express the motion better than the reference values, and the average matching rate increases by 2.41×10-1, particularly for a feint motion. Therefore, skill acquisition and augmentation were achieved.

Stereo Matching Method with Cost Volume Collaborative Filtering

Aiming at the problem of matching ambiguity and low disparity accuracy at the object boundary in stereo matching, a novel stereo matching algorithm with cost volume collaborative filtering is proposed. Firstly, for each pixel, two support windows are built, namely a local cross- support window as well as a global support window for the whole image. Secondly, a new adaptive weighted guide filter with a cross-support window as a kernel window is derived, and it is used to locally filter the cost volume. In addition, a minimum spanning tree is constructed in the whole image window, and then the minimum spanning tree filter is used to globally filter the cost volume. The collaborative filtering of cost volume is realized by fusing the filtering results of the local filter and global filter, so that each pixel can not only receive the support of the neighboring pixels in the local adaptive window, but can also receive the effective support of other pixels in the whole image, thus effectively eliminating the matching ambiguity in different texture regions while maintaining the disparity edges. The experimental results show that the average matching error rate of our method on the Middlebury stereo images is 3.17%. Compared with the other state-of-the-art methods, our method has higher robustness and matching accuracy, the generated disparity maps are smoother, and the disparity edges are better preserved.

The evolution and impact of the Society for Vascular Surgery Resident and Student Program

ObjectiveThere is an ongoing national shortage in the vascular surgery (VS) workforce. To increase interest in the specialty, the Society for Vascular Surgery (SVS) Resident and Student Outreach Committee (RSOC) developed a dedicated general surgery (GS) resident and medical student (MS) program at the Vascular Annual Meeting (VAM) and invested in a scholarship program to help reduce attendee expenses. This study assesses the program’s effectiveness, correlating recipient feedback with the likelihood of matching into a VS training program. MethodsRecords related to the SVS VAM GS resident and MS program from 2013 to 2023 were reviewed, focusing on attendee evaluations of the program. The program included a simulation session from 2013 to 2019. VS training program match rates among scholarship recipients were determined. The annual average match rate in VS was used to divide the survey responses into two groups: below average (BA) and above average (AA) match rate groups. Survey responses were based on a 5-point Likert scale and allowed for comments. Responses were divided into high value, strongly favoring the activity (scores 4-5), and low value (scores 1-3) categories. The survey responses from the group of years with AA match rates were compared with the group of years with BA rates. ResultsThe SVS awarded 1040 GS resident and MS travel scholarships over the 10 years assessed. Overall, applicants had a 43% success rate in receiving a scholarship. During the study period, the annual number of applicants increased, whereas the number of scholarships and match success rates significantly decreased. The average match rate into VS among scholarship recipients was 50.2%. The survey response rate was 33%. During AA match rate years, evaluations for simulation allotted time and lectures were significantly more likely to be high value compared with BA years. Simulation content and the residency fair consistently had the most favorable evaluations (>90% high value), and overall, the program had a consistently positive impact on recipients’ interest in VS (>90% high value). Trainees in the AA group were significantly more likely to provide positive comments (73% vs 55%; P < .001). Numerous recipients commented on the need for a dedicated space to interact with faculty and mentors and highlighted simulation as the standout aspect of the program. ConclusionsThe SVS VAM RSOC program is positively correlated with attendee interest in VS, with approximately 50% of scholarship recipients matching into the field. The quality of the program and the number of scholarships correlate with VS match rates. Additional investments in similar programs could help close the workforce gap.

Three-dimensional reconstruction of aerosols based on spectral radiance matching

This paper evaluates a three-dimensional scene construction algorithm that assigns CALIPSO-observed profiles to receiving pixels in MODIS imagery through spectral radiance matching (SRM), so that a limited number of vertically resolved aerosol observations can be expanded into a regionally continuous three-dimensional aerosol structure. The SRM algorithm was tested using moderate resolution imaging spectro-radiometer (MODIS) and cloud-aerosol lidar and infrared pathfinder satellite observation (CALIPSO) data for the period of April 10–25, 2015. First, the spectral radiance channel and the surface reflectance channel were selected for combination tests to select the best channel combination 01-04-07-26 for the application of SRM algorithm in the field of aerosol three-dimensional reconstruction. The average aerosol matching rate for this channel combination can reach 90.57%, 81.64%, 78.6%, 74.12%, and 65.96% at extended distances of 5, 20, 30, 50, and 100 km, respectively. In addition, the combination of the average correct match rate and the reconstructed aerosol structure revealed that the most suitable extension distance is up to 100 km. Then, for the reconstruction profile validation, lidar sites under four weather conditions (clean sky, aerosol loading, thin clouds, and thick clouds) were selected for validation. The comparison results reveal that the average relative errors are about 30%, 60%, 30%–60%, and 70% for these four conditions, respectively. Overall, the average relative error of the reconstructed profiles within 100 km of the orbital track of CALIPSO (except under thick cloud conditions) is less than 60%, which is within a reasonable error envelop. There are also some limitations that can be improved later by adding more constraints: 1) it is difficult to reconstruct some short-time, small-scale aerosol or cloud features; 2) it is difficult to reconstruct some hierarchical structures under thick clouds due to signal attenuation caused by thick clouds; 3) there is an underestimation of the attenuated backscatter coefficient under clouds. Finally, for aerosol optical depth (AOD), the SRM algorithm largely underestimates AOD. The reconstructed AOD is in good agreement with aerosol robotic network (AERONET), with R2=0.8231 after removal of outliers.

Research on 3D virtual vision matching based on interactive color segmentation.

Given the prevalent issues surrounding accuracy and efficiency in contemporary stereo-matching algorithms, this research introduces an innovative image segmentation-based approach. The proposed methodology integrates residual and Swim Transformer modules into the established 3D Unet framework, yielding the Res-Swim-UNet image segmentation model. The algorithm estimates the disparateness of segmented outputs by employing regression techniques, culminating in a comprehensive disparity map. Experimental findings underscore the superiority of the proposed algorithm across all evaluated metrics. Specifically, the proposed network demonstrates marked improvements, with IoU and mPA enhancements of 2.9% and 162%, respectively. Notably, the average matching error rate of the algorithm registers at 2.02%, underscoring its efficacy in achieving precise stereoscopic matching. Moreover, the model's enhanced generalization capability and robustness underscore its potential for widespread applicability.

A Framework Study on the Application of AIGC Technology in the Digital Reconstruction of Cultural Heritage

Abstract AIGC is currently a hot field and a future trend in AI applications, and addressing the challenge of digitally reconstructing cultural heritage under the influence of AI technology is a pressing issue that requires immediate resolution. The article proposes an application framework for AIGC technology that is based on refining its meaning and designing a specific process for applying it to the digital reconstruction of cultural heritage. A high-definition camera is used to acquire relevant images of cultural heritage. The image features are extracted by the SIFT algorithm optimized by the PROSAC algorithm. The color features are acquired by combining the color histogram, color moment, and color correlation diagram. The 3D laser scanning technology is used to obtain the 3D point cloud data of the cultural heritage; the KD-tree improved ICP algorithm is introduced to improve the efficiency of point cloud alignment; the dense reconstruction of the 3D point cloud data of the cultural heritage is realized based on CMVS/PMVS; and the immersive 3D experience system of the cultural heritage is constructed by combining with platforms such as Unity3D. The average matching rate of the optimized SITF algorithm to the image features of cultural heritage is about 74.91%, and the maximum alignment time of the ICP algorithm to the cultural heritage point cloud data based on KD-tree is 9.241 s. The cultural heritage immersive 3D experience system has a satisfaction rate of 56.75%, and the density reconstructed model’s surface has an average deviation of only 0.34 mm from the real surface. The user satisfaction rating for the immersive 3D experience system for cultural heritage is 56.75%. Based on AIGC technology, it can revitalize cultural heritage and achieve digital reconstruction and inheritance innovation of cultural heritage.

Stereo Matching Algorithm of Multi-Feature Fusion Based on Improved Census Transform

This article proposes an improved stereo matching algorithm in order to address the issue that the conventional Census transform is overly dependent on the center pixel of the window, which makes the algorithm susceptible to noise interference and results in low matching accuracy in regions with weak texture and complex texture. In the cost calculation stage, the noise threshold is set utilizing the absolute difference detection approach, and pixels that exceed the threshold are replaced with the mean gray values of the neighboring pixels in the 3 × 3 window. This stage also includes the introduction of the gradient cost, which is coupled with the edge and feature point information to provide the final matching cost. The cross approach is employed to build the adaptive support domain and aggregate the costs during the cost aggregation stage. The disparity is finally calculated using the WTA technique, and a multi-step refinement process is employed to produce the final disparity map. The experiments demonstrate that the proposed algorithm has good anti-noise performance. Compared with other improved algorithms or composite algorithms, the average matching rate of the four standard images on the Middlebury test platform is 5.53%, which is higher than the remaining algorithms, indicating that the matching accuracy is high. The proposed algorithm provides ideas for subsequent improved algorithms.

성장소설 표지디자인에 나타난 시각적 의미패턴 연구

As Korea grew after liberation, social and cultural changes occurred and were reflected in the content and cover design of coming-of-age novels. In a situation where Korea's bildungsroman is also changing and developing, we found that research on cover design for this was very insufficient, and attempted to study the characteristic semantic system of the cover design of Korean bildungsroman by era. The research method targets the cover designs of 166 coming-of-age novels published from the 1970s to 2023. First, the meaning of keywords and titles by era of the content of the coming-of-age novels is analyzed, and second, the meaning of the cover design of the coming-of-age novels is visualized. Analyze it by dividing it into images, colors, and typography, and check the flow and patterns of change by era. Third, we analyzed the relationship between keywords and visual elements by era in the content of coming-of-age novels. Looking at the analysis results, firstly, the composition of the parts of speech in the title by era appeared to be diversifying and becoming more complex, from 1 type of ‘noun’ structure in the 1970s to 17 types of parts of speech in the 2020s. Second, in terms of images, the oil painting technique of illustrations was used the most, and as the 2000s progressed, the frequency of using the entire cover as an image increased, and the use of stripes also gradually expanded. In terms of color, in the 1970s the hue distribution was medium brightness and low saturation, in the 1990s it was a hue distribution of wide brightness and saturation with warm colors and neutral colors, and in the 2020s the hue distribution was again centered on neutral colors and cool colors with medium brightness and low saturation. appear. In terms of typography, horizontal writing, center alignment, single line, serif, asymmetrical layout, and color changes were used to emphasize headings. Third, the concreteness and abstractness of titles and images were analyzed. In the 1970s, abstract expressions were very high, and concrete expressions were used more in the 2000s. In terms of visualization of the title, the average matching rate was 63%, and it was analyzed that the specificity of the title affects image visualization. In general, keyword visualization was relatively high in the 1970s, but the matching rate gradually decreased thereafter.

Accuracy of pharmacy student self-assessment of a single sterile compounding technique following didactic training

IntroductionThe primary objective was to determine pharmacy students' ability to self-assess sterile compounding technique in a single evaluation three semesters after training in the curriculum. MethodsSchool of pharmacy (SOP) students were trained and assessed on sterile compounding technique during their second year of school, with no additional formal assessments provided later in the curriculum. From 2016 to 2018, 262 students were asked to compound a simulated sterile product in their third year of pharmacy school and self-evaluate their technique, which was compared to an instructor evaluation with both people using the same rubric. ResultsTwo thresholds were used to define successful assessment: strict (ability to detect ideal technique) and lenient (ability to detect harmful technique). The average match rate was 70.2% and 87.6% in the strict and lenient analyses, respectively, with outcomes varying between categories. In the product preparation and inspecting product categories, students who disagreed with assessors tended to misidentify their incorrect technique as correct. ConclusionsPharmacy students who assessed themselves on sterile compounding technique three semesters after formal sterile compounding training were able to accurately self-assess in most cases, but when disagreeing with an assessor, commonly identified their incorrect technique as correct. Most students demonstrated the ability to self-assess sterile compounding technique and are prepared to assess their own sterile compounding in practice. SOPs could consider whether sterile compounding training coupled with self-assessment throughout the curriculum would be beneficial to further improve students' sterile compounding ability and accuracy of self-assessment.

HADES: Hash-Based Audio Copy Detection System for Copyright Protection in Decentralized Music Sharing

Preventive measures to stop copyright infringement are yet to be implemented on current decentralized music-sharing platforms. There is no mechanism to reject modified audio before they go online, so some decentralized music platforms become places full of pirated audio files. To address this problem, a perceptual hash-based audio detection method for copyright protection in decentralized music sharing was proposed. Chromaprint, an open-source audio fingerprint program, generates a hash value to detect copyright infringement. To assess the perceptual hash technique’s robustness, Chromaprint generates a hash value from an audio file that can be modified with several signal processing attacks. The results of the detection system show that Chromaprint is very effective at spotting copyright infringement, with an average match rate of 92.64%. Deployed using a public Ethereum blockchain test network, the execution time from hashing to uploading to the IPFS distributed storage is only 616.3 ms.

Trends in application and match outcomes for hematology and oncology fellowship: An analysis of charting outcomes from 2008 to 2022.

e23004 Background: The rapidly evolving advances in the field of oncology make it attractive to many internal medicine residents and graduates who must secure a position through the hematology and oncology fellowship match to get a chance to complete training in oncology. We aim to evaluate the trends in the application, competitiveness, and match rates of the hematology and oncology fellowship match based on the category of applicants. Methods: This is a retrospective cohort study of applicants who applied for the hematology and oncology fellowship from 2008 to 2022 based on the match data released by the National Residency Match Program (NRMP). The number of applicants, type of applicants, number of positions, and match outcomes was evaluated. Applicant types were classified into US-allopathic graduates and non-US-allopathic graduates. Chi-square tests were used to compare the match outcomes and the applicant types. Results: A total of 11,357 applicants participated in the hematology and oncology fellowship match during the study period. The number of applicants increased from 724 in 2008 to 894 in 2022 (a 23% increase), while the number of positions increased from 424 to 663 (a 36% increase). The average match rate was 68.5% during the study period, rising from 57.5% in 2008 to 73.5% in 2022. US allopathic graduates have a higher match rate when compared to non-US allopathic graduates (83.8% vs 56.2%; p &lt; 0.00001). Although this disparity is maintained over time, it progressively narrowed (77.2% vs 42.5% in 2008 compared to 85.4% vs 63.3% in 2022). Fifty-three percent of applicants matched in their top 3 programs (36.5% in 1st, 11.2% in 2nd, and 7.3% in 3rd). The percentage of applicants matched in their top 3 programs increased from 53.4% in 2009 to 57.4% in 2022 (range: 50-62%). Conclusions: The hematology and oncology fellowship match is highly competitive with outcomes more favorable to US-allopathic graduates than non-US allopathic graduates. Most successful applicants matched in one of their top three programs. [Table: see text]

Online map-matching assisted by object-based classification of driving scenario

Different types of roads in complex road networks may run side-by-side or across in 2D or 3D spaces, which causes mismatched segments using existing online map-matching algorithms. A driving scenario that represents the driving environment can inform map-matching algorithms. Images from vehicle cameras contain extensive information about driving scenarios, such as surrounding key objects. This research utilized vehicle images and developed an object-based method to classify driving scenarios (Object-Based Driving-Scenario Classification: OBDSC) to calculate the probabilities of the current image in predefined types of driving scenarios. We implemented an online map-matching algorithm with the OBDSC method (OMM-OBDSC) to obtain optimal matching segments. The algorithm was tested on nine trajectories and OpenStreetMap data in Shanghai and compared with five benchmark algorithms in terms of the match rate, recall and accuracy. The OBDSC method is also applied to the benchmark algorithms to verify the effectiveness of map matching. The results show that our algorithm outperforms the benchmark algorithms with both the original interval and downsampled intervals (96.6%, 96.5%, 93.7% on average with 1–20 s intervals for the three metrics, respectively). The average match rate has improved by 8.9% for all benchmark algorithms after the addition of the OBDSC method.

Objective evaluation of tongue diagnosis ability using a tongue diagnosis e-learning/e-assessment system based on a standardized tongue image database.

In Kampo medicine, tongue examination is used to diagnose the pathological condition "Sho," but an objective evaluation method for its diagnostic ability has not been established. We constructed a tongue diagnosis electronic learning and evaluation system based on a standardized tongue image database. This study aims to verify the practicality of this assessment system by evaluating the tongue diagnosis ability of Kampo specialists (KSs), medical professionals, and students. In the first study, we analyzed the answer data of 15 KSs in an 80-question tongue diagnosis test that assesses eight aspects of tongue findings and evaluated the (i) test score, (ii) test difficulty and discrimination index, (iii) diagnostic consistency, and (iv) diagnostic match rate between KSs. In the second study, we administered a 20-question common Kampo test and analyzed the answer data of 107 medical professionals and 56 students that assessed the tongue color discrimination ability and evaluated the (v) correct answer rate, (vi) test difficulty, and (vii) factors related to the correct answer rate. In the first study, the average test score was 62.2 ± 10.7 points. Twenty-eight questions were difficult (correct answer rate, <50%), 34 were moderate (50%-85%), and 18 were easy (≥85%). Regarding intrarater reliability, the average diagnostic match rate of five KSs involved in database construction was 0.66 ± 0.08, and as for interrater reliability, the diagnostic match rate between the 15 KSs was 0.52 (95% confidence interval, 0.38-0.65) for Gwet's agreement coefficient 1, and the degree of the match rate was moderate. In the second study, the difficulty level of questions was moderate, with a correct rate of 81.3% for medical professionals and 82.1% for students. The discrimination index was good for medical professionals (0.35) and poor for students (0.06). Among medical professionals, the correct answer group of this question had a significantly higher total score on the Kampo common test than the incorrect answer group (85.3 ± 8.4 points vs. 75.8 ± 11.8 points, p < 0.01). This system can objectively evaluate tongue diagnosis ability and has high practicality. Utilizing this system can be expected to contribute to improving learners' tongue diagnosis ability and standardization of tongue diagnosis.

Semi-Global Stereo Matching Algorithm Based on Multi-Scale Information Fusion

Semi-global matching (SGM) has been widely used in binocular vision. In spite of its good efficiency, SGM still has difficulties in dealing with low-texture regions. In this paper, an SGM algorithm based on multi-scale information fusion (MSIF), named SGM-MSIF, is proposed by combining multi-path cost aggregation and cross-scale cost aggregation (CSCA). Firstly, the stereo pairs at different scales are obtained by Gaussian pyramid down-sampling. The initial matching cost volumes at different scales are computed by combining census transform and color information. Then, the multi-path cost aggregation in SGM is introduced into the cost aggregation at each scale and the aggregated cost volumes are fused by CSCA. Thirdly, the disparity map is optimized by internal left-right consistency check and median filter. Finally, experiments are conducted on Middlebury datasets to evaluate the proposed algorithm. Experimental results show that the average error matching rate (EMR) of the proposed SGM-MSIF algorithm reduced by 1.96% compared with SGM. Compared with classical cross-scale stereo matching algorithm, the average EMR of SGM-MSIF algorithm reduced by 0.92%, while the processing efficiency increased by 58.7%. In terms of overall performance, the proposed algorithm outperforms the classic SGM and CSCA algorithms. It can achieve high matching accuracy and high processing efficiency for binocular vision applications, especially for those with low-texture regions.

Match Outcomes for Cardiovascular Disease Fellowship Training: 2010 to 2021.

Background This study elucidates recent trends in application and match rates in the Cardiovascular Disease Fellowship Match. We hypothesized that (1) match rates have increased with time; (2) match rates are highest for US allopathic graduates; and (3) most candidates match at 1 of their top 3 ranked fellowship choices. Methods and Results This was a retrospective cohort study of all applicants in the Cardiovascular Disease Fellowship Match from 2010 to 2021 (n=14 674). Chi-square tests were used to compare trends over time and match rates by applicant archetype (US allopathic graduates and non-US allopathic graduates). The annual number of applicants increased from 1184 to 1575 (33% increase) while training positions increased 718 to 1045 (46% increase) over the study period. The percentage of applicants that matched increased from 61% in 2010 to 66% in 2021 (P=0.090). The average match rate was 70% over the study period. During each year, US allopathic graduates had higher match rates than non-US allopathic graduates (P<0.001), but this disparity narrowed with time (83% versus 41% in 2010 and 83% versus 54% in 2021). Most applicants matched at 1 of their top 3 choices (first, 37%; second, 12%; third, 7%). Applicants matching at 1 of their top 3 choices decreased from 51% in 2010 to 48% in 2021 (P=0.704). Conclusions The Cardiovascular Disease Fellowship Match has remained equally competitive over the past decade. US allopathic graduates have an advantage over non-US allopathic graduates. Most applicants match at 1 of their top 3 ranked fellowship choices.

The census place project: A method for geolocating unstructured place names

Researchers use microdata to study the economic development of the United States and the causal effects of historical policies. Much of this research focuses on county- and state-level patterns and policies because comprehensive sub-county data is not consistently available. We describe a new method that geocodes and standardizes the towns and cities of residence for individuals and households in decennial census microdata from 1790–1940. We release public crosswalks linking individuals and households to consistently-defined place names, longitude-latitude pairs, counties, and states. Our method dramatically increases the number of individuals and households assigned to a sub-county location relative to standard publicly available data: we geocode an average of 83% of the individuals and households in 1790–1940 census microdata, compared to 23% in widely-used crosswalks. In years with individual-level microdata (1850–1940), our average match rate is 94% relative to 33% in widely-used crosswalks. To illustrate the value of our crosswalks, we measure place-level population growth across the United States between 1870 and 1940 at a sub-county level, confirming predictions of Zipf’s Law and Gibrat’s Law for large cities but rejecting similar predictions for small towns. We describe how our approach can be used to accurately geocode other historical datasets.

Estimation of playable piano fingering by pitch-difference fingering match model

Most existing statistical models used to predict piano fingering apply explicit constraints among fingers and between fingers and notes; however, they disregard the relationship among notes. Furthermore, the state transfer matrix of HMM often makes the fingering of notes in compact scales unplayable without moving the hands. The direct adoption of notes interferes with mapping between specific pitches and the corresponding fingering. Inspired by human annotation and the note span constraints used in rule-based methods (in which fingering knowledge is acquired from span), we developed a model by which to match pitch difference and finger sequences (PdF). Playable fingering is achieved by combining learned finger-transfer knowledge with priori finger-transfer knowledge. The playability of the model was evaluated using a novel index, referred to as the irrational fingering rate (IFR). Experiment results demonstrate that the proposed model outperforms the third-order hidden Markov finger annotation model in terms of average match rate (by 4.06%) and highest match rate (by 2.87%). The proposed scheme also resolves the unplayable-without-hand-movement problem in compact scales.

Taekwondo Action Recognition Method Based on Partial Perception Structure Graph Convolution Framework

Action recognition in Taekwondo competitions and training is an important task, which can provide a very valuable reference factor for technicians, athletes, and coaches. We propose a graph convolution framework with part of the perception structure to recognize, decompose, and analyze Taekwondo actions. Taking advantage of the long short-term memory of a part of the perception structure, the recognized Taekwondo actions are marked in time series, and then features are extracted from the graph convolution level to obtain the spatial and temporal associations between joints. Predict the action category and perform score matching based on the manual tag database. Finally, it is verified on our self-made Taekwondo competition data set. Our method has an average accuracy of 90% in action recognition, and an average action score matching rate of 74.6%. The accuracy of action recognition is high, which provides great assistance to Taekwondo e training and competitions.

A knowledge infused context driven dialogue agent for disease diagnosis using hierarchical reinforcement learning

Disease diagnosis is an essential and critical step in any disease treatment process. Automatic disease diagnosis has gained immense popularity in recent years, owing to its effiacy, easy accessability and reliablity. The major challenges for the diagnosis agent are inevitably large action space (symptoms) and varieties of diseases, which demand either rich domain knowledge or an intelligent learning framework. We propose a novel knowledge-infused context-driven (KI-CD) hierarchical reinforcement learning (HRL) based diagnosis dialogue system, which leverages a bayesian learning-inspired symptom investigation module called potential candidate module (PCM) for aiding context-aware, knowledge grounded symptom investigation. The PCM module serves as a context and knowledge guiding companion for lower-level policies, leveraging current context and disease-symptom knowledge to identify candidate diseases and potential symptoms, and reinforcing the agent for conducting an intelligent and context guided symptom investigation with the information enriched state and an additional critic known as learner critic. The knowledge-guided symptom investigation extracts an adequate set of symptoms for disease identification, whereas the context-aware symptom investigation aspect substantially improves topic (symptom) transition and enhances user experiences. Furthermore, we also propose and incorporate a hierarchical disease classifier (HDC) with the model for alleviating symptom state sparsity issues, which has led to a significant improvement in disease classification accuracy. The proposed framework outperforms the current state-of-the-art method on the multiple benchmarked datasets and, in all evaluation metrics other than dialogue length (diagnosis success rate, average match rate, symptom identification rate, and disease classification accuracy by 7.1 %, 0.23 %, 19.67 % and 8.04 %, respectively), which firmly establishes the effiacy of the proposed bayesian learning-inspired context-driven symptom investigation and disease diagnosis methodology 11The code is available at https://github.com/NLP-RL/KI-CD..