Matching Results Research Articles

Visible light infrared matching algorithm based on improved SuperPoint and linear converter

In order to solve the problems of high difficulty and mismatch rate in heterogeneous image matching of visible light and infrared images, a deep learning matching algorithm based on improved SuperPoint and linear transformer is proposed. The algorithm first introduces the idea of feature pyramid to construct a feature description branch based on the SuperPoint network structure, and trains it based on the hinge loss function, so as to better learn the multi-scale deep features of visible light and infrared images and increase the similarity of image point pair descriptors with the same name; in the feature matching module, the linear transformer is used to improve the SuperGlue matching algorithm and aggregate features to improve matching performance. The proposed algorithm is experimentally verified on multiple data sets. The results show that compared with the existing algorithms, the algorithm achieves better matching results and improves the matching accuracy.

Online bilateral matching methodology for anti-epidemic resources based on spatial transmission risk

This paper focuses on the online anti-epidemic resource allocation between demanders and suppliers considering the epidemic spatial spread. The spatial crowdsourcing with sharing platform is an effective way for anti-epidemic resource allocation, and a reasonable online matching strategy can improve the efficiency of resource utilization. The paper proposes online matching heuristic strategy (HSTRF-LRLUF strategy) and designs an online batch bilateral matching algorithm for anti-epidemic resources, which considers the impact of grid spatial aggregation and diffusion risk of emerging infectious diseases. The population distribution within grids and the commuting patterns between grids can provide decision support for selecting online matching strategies of anti-epidemic resources. A larger matching time window focusing on the spatial transmission risk (TR) of the epidemic can obtain better matching results. However, with a smaller matching time window, the decision makers can focus on spatial agglomeration risk (OR) or spatial diffusion risk (IR). The paper effectively combines the spatial crowdsourcing model with the anti-epidemic resource allocation to achieve the allocation of emergency resources to individuals. A combined anti-epidemic resource online matching heuristic strategies is designed from the spatial agglomeration risk and the spatial diffusion risk. Decision makers can dynamically adjust the online matching strategies of anti-epidemic resources by evaluating the spatial agglomeration risk, the spatial diffusion risk, and the overall spatial transmission risk based on the real-time spread of the epidemic and the supply of anti-epidemic resources.

Prediction of tennis match results based on logistic regression

More and more people like tennis, and the demand for the accuracy of predicting the results of tennis matches in sports betting is getting higher and higher. In this paper, a model is built to predict the results of tennis matches. In this paper, we first use the random forest model to analyze the factors that will have an impact on the outcome of the game, and the authors have selected out five factors that may have an impact on the outcome, which are: break of serve, Serve, Score, Net points , And they were assigned proportionally and the distribution was Break of serve 34.10%, Serve 24.30%, Score 38.00%, Net points 3.60% and using these proportions the influencing factors were calculated numerically, in this paper, the calculated value is named “momentum”. Then Pearson's correlation coefficient was used to analyze the relationship between momentum and match results, and the analysis found that the correlation between momentum and match results was as high as 0.807. Finally, a logistic regression model was used to predict and test the results of tennis matches. The final test results found that the model established in this paper has a high accuracy rate, and the research results also provide a new idea for tennis betting industry.

Research on Quantifying and Evaluating Tennis Match Momentum Based on Comprehensive Analytical Methods

Momentum is crucial in tennis matches, influencing player performance and match outcomes. However, quantifying and evaluating momentum has long been a challenge in sports science research. This study aims to quantify momentum in tennis matches by establishing a hierarchical analysis-based model for momentum flow. The model analyzes factors affecting momentum through five criteria: Service Level, Catch Level, Competition Result, Finishing Ability, and Winning Streak, with respective weights of approximately (0.1, 0.1, 0.2, 0.4, 0.2). Subsequently, the study assigns scores to these criteria based on different actions within a match. By multiplying the weights and scores, the momentum of each player is quantified, and the ratio of the two players' momentum provides a measure of momentum flow during the match. To assess the impact of momentum on match outcomes, the study employs k-means++ clustering analysis, violin plot analysis, and point-biserial correlation analysis. The point-biserial correlation analysis reveals a positive correlation coefficient of 0.66 between a player's momentum and their victory. Similar results are derived from the violin plot and clustering analysis. Therefore, it can be concluded that there is a significant association between the direction of momentum flow and a player's success in a match.

Research on Momentum Prediction of Tennis Match Based on Scoring Model and Multilayer Perceptron

During a tennis match, players may encounter various circumstances that can significantly influence their performance. This force, known as "momentum," can drastically alter the game's flow and ultimately determine the winner. Addressing the challenge of analyzing and predicting momentum shifts, this study applied the Entropy Weight TOPSIS method combined with fuzzy comprehensive evaluation to assess player performance across technical, physical, and psychological factors. These methods provided a comprehensive analysis of the players' performance metrics, revealing patterns linked to momentum changes. Following this, Pearson correlation analysis was conducted to identify key performance indicators strongly associated with match outcomes. These indicators were then integrated into a Multilayer Perceptron (MLP) model, which demonstrated high predictive accuracy, with an R-value of 0.868, effectively capturing momentum shifts in real-time. The study's findings offer valuable insights for improving strategic decision-making during matches and hold potential applications in other fields that require real-time predictive analysis.

Suspense and Surprise: The Role of Bookmakers’ Spreads

Uncertainty in a competition's final result can affect the event's demand via suspense and surprise. Based on a sample of more than 50,000 professional tennis matches, this paper shows how information from bookmaker prices, implied probabilities, and price spreads contain relevant information that explains the uncertainty in the final results of the matches. There is a negative relation between the implied probability for the favorite and the different measures of match result uncertainty proposed and a positive relationship between the spread and these measures when the bookmaker sets prices based on information. This second relation disappears when the bookmaker sets prices based on betting volumes. The results have potential implications both for organizers in scheduling matches with higher levels of uncertainty and for punters in setting strategies that predict the exact result of a match.

BPFNN Based Football Player Value Prediction by Introducing Historic Information

With extensively successful applications of artificial neural networks in many scenarios of classification and prediction, research related to the world most popular sport - football - has undoubtedly attracted researchers to carry out their works with aid of such powerful tools. Despite that most of these works are oriented to predict match results and game strategies, only very a few are designed for player value prediction, which is of great importance with the rapid growth of the football players’ transfer market. In this paper, we propose a BP feedforward neural network framework which integrates both the empirically determined variables and some historical information. Comparative ablation experiments on one dataset FINAL verified the necessity of some factors especially the highest_values which inspired the inclusion of available historical information into the framework. For further verifying the efficiency of integrating historical information, we embedded the value columns of FIFA17 to FIFA21 into the data of FIFA22. Comparative experiments showed an 11% improvement on the precision with the help of historical values, verifying the efficiency of this strategy. Experiments were also conducted for determining the choice of the number of layers, the ratio of the training set and test set, the learning rate, and the process of the missed information.

A Segment Augmentation and Prediction Consistency Framework for Multi-Label Unknown Intent Detection

Multi-label unknown intent detection is a challenging task where each utterance may contain not only multiple known but also unknown intents. To tackle this challenge, pioneers proposed to predict the intent number of the utterance first, then compare it with the results of known intent matching to decide whether the utterence contains unknown intent(s). Though they have made remarkable progress on this task, their methods still suffer from two important issues: (1) It is inadequate to extract multiple intents using only utterance encoding; (2) Optimizing two sub-tasks (intent number prediction and known intent matching) independently leads to inconsistent predictions. In this article, we propose to incorporate segment augmentation rather than only use utterance encoding to better detect multiple intents. We also design a prediction consistency module to bridge the gap between the two sub-tasks. Empirical results on MultiWOZ2.3 and MixSNIPS datasets show that our method achieves state-of-the-art performance and significantly improves the best baseline.

Machine learning-based football match prediction system

This study develops a machine learning-based system to predict English Premier League (EPL) outcomes, employing models such as Principal Component Analysis (PCA), K-Nearest Neighbors (KNN), Random Forests, and Support Vector Machines (SVM). The analysis covered a large dataset of matches, with the data normalized to ensure consistency and accuracy across models. Among the methods used, Random Forests showed the most robust performance in predicting match outcomes, particularly in forecasting wins and losses. However, both Random Forests and SVM encountered difficulties in accurately predicting draws, which points to areas where further refinement is needed. The prediction probabilities largely fell within a specific range, indicating the models' ability to identify patterns, but significant overfitting was observed in the models. This overfitting suggests that while the models performed well on the training data, they struggled to generalize to new, unseen data, highlighting the importance of implementing more effective regularization techniques to prevent overfitting and improve the models' overall predictive accuracy in real-world scenarios.

Predictors of goal difference and match outcome in Polish handball PGNiG Superleague in the season before, during and after the COVID-19 pandemic - regression analysis

ABSTRACT The aim of the study was to determine which technical and tactical actions are predictors of the goal difference and the outcome of the handball match in the seasons before, during, and after the COVID-19 pandemic. The study material is official statistics of the Polish PGNiG Superleague in 493 matches. Multivariate and logistic regression analysis was used to demonstrate predictive factors. The predictors of goal difference are the number and effectiveness of throws from 6, 7, and 9 metres, the number of fouls, fast breaks, and goalkeeper effectiveness. The biggest contributors are the effectiveness of the goalkeeper’s defence, the number of throws from the 6th metre, and the effectiveness of throws from 6th and 9th metres. The constant predictors of winning in all seasons are the number of throws from the 6th metre, the efficiency of throws from the 6th and 9th metres, and the efficiency of goalkeepers saves. The strongest predictor of winning in the pre-and post-pandemic seasons is playing matches at home. In the pandemic season, no such relationship was shown. In sports training, offensive and defensive actions involving the demonstrated predictors should be improved to increase their level and decrease it in opponents.

Automated matching and visualisation of magnetic flux leakage data in shale gas pipeline based on ICP and DBSCAN algorithm

ABSTRACT Magnetic flux leakage (MFL) is a non-destructive testing method for shale gas pipeline safety monitoring. Despite many pipelines have completed two or more rounds of internal inspection and have accumulated substantial data, effectively analyzing and utilizing this MFL data remains a significant challenge. To that end, this study proposes a novel combined model that integrates Iterative Closest Point (ICP) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) fusion to match multiple MFL data. The model outputs the matching result and visualisation images of MFL data acquired in different years. Furthermore, RMSE (root mean square error) and overlap rate have been used to evaluate the model. The results indicate that the average distance error of matched defects between two datasets decreased by 72.5%, and the overlap rate increased by 20%. Additionally, the DBSCAN Fusion shows better computational efficiency with an increase in defect quantity within the pipe segments. Finally, the impact of different datasets on the model’s matching accuracy is discussed in this study. The findings show that small-scale datasets or higher false detection rates lead to decreased accuracy. The proposed model fully leverages MFL data to achieve rapid matching of defects, offering a dependable and effective technical solution for safety monitoring and corrosion prediction in shale gas pipelines.

Is Travel Associated With Match Performance in Elite North American Professional Soccer? An Exploratory Study.

Travel fatigue impacts cognitive and physiologic systems, but its association with elite soccer match performance is unclear. In this retrospective observational study, we aimed to explore the association between travel and match outcomes in elite North American soccer. Travel data and match outcomes(team points or goals scored and conceded) and physical performance outcomes from 26 elite professional soccer teams and their players were analyzed (148 matches [team-based data] and 1252 player matches from 297 players; age 22.7 [4.5]y). Player- and match-level correlations between performance measures and both acute and cumulated travel metrics were analyzed. Cumulative travel metrics were positively associated with team (travel distance [r = .20; 95% CI, .03-.25], travel time [r = .20; .06-.37], and time away [r = .20; .06-.37]) and individual player (travel distance, [r = .14; .08-.19], travel time [r = .17-.23], and time away [r = .13; .07-.18]) high-intensity running. Cumulative time away was negatively associated with team points (r = -.14; -.28 to -.001) and positively associated with goals conceded (r = .14; .01-.27); no clear association between acute travel metrics and match outcomes or physical performance was observed. As travel cumulated, away teams and their players ran more but for less reward (team points), although the magnitude of these associations was small. These data are exploratory and do not imply acausal relationship; however, further research should consider cumulation of travel.

Dynamic entrainment: A deep learning and data-driven process approach for synchronization in the Hodgkin-Huxley model.

Resonance and synchronized rhythm are significant phenomena observed in dynamical systems in nature, particularly in biological contexts. These phenomena can either enhance or disrupt system functioning. Numerous examples illustrate the necessity for organs within the human body to maintain their rhythmic patterns for proper operation. For instance, in the brain, synchronized or desynchronized electrical activities can contribute to neurodegenerative conditions like Huntington's disease. In this paper, we utilize the well-established Hodgkin-Huxley (HH) model, which describes the propagation of action potentials in neurons through conductance-based mechanisms. Employing a "data-driven" approach alongside the outputs of the HH model, we introduce an innovative technique termed "dynamic entrainment." This technique leverages deep learning methodologies to dynamically sustain the system within its entrainment regime. Our findings show that the results of the dynamic entrainment technique match with the outputs of the mechanistic (HH) model.

Innovative multi-stage matching for counting anything

Few-shot counting (FSC) is the task of counting the number of objects in an image that belong to the same category, by using a provided exemplar pattern. By replacing the exemplar, we can effectively count anything, even in cases where we have no prior knowledge of that category’s exemplar. However, due to the variations within the same category and the impact of inter-class similarity, it is challenging to achieve accurate intra-class similarity matching using conventional similarity comparison methods. To tackle these issues, we propose a novel few-shot counting method called Multi-stage Exemplar Attention Match Network (MEAMNet), which increases the accuracy of matching, reduces the impact of noise, and enhances similarity feature matching. Specifically, we propose a multi-stage matching strategy to obtain more stable and effective matching results by acquiring similar feature in different feature spaces. In addition, we propose a novel feature matching module called Exemplar Attention Match (EAM). With this module, the intra-class similarity representation in each stage will be enhanced to achieve a better matching of the key feature. Experimental results indicate that our method not only significantly surpasses the state-of-the-art (SOTA) methods in most evaluation metrics on the FSC-147 dataset but also achieves comprehensive superiority on the CARPK dataset. This highlights the outstanding accuracy and stability of our matching performance, as well as its exceptional transferability. We will release the code at https://github.com/hzg0505/MEAMNet.

Multi-Temporal Snow-Covered Remote Sensing Image Matching via Image Transformation and Multi-Level Feature Extraction

To address the challenge of image matching posed by significant modal differences in remote sensing images influenced by snow cover, this paper proposes an innovative image transformation-based matching method. Initially, the Pix2Pix-GAN conversion network is employed to transform remote sensing images with snow cover into images without snow cover, reducing the feature disparity between the images. This conversion facilitates the extraction of more discernible features for matching by transforming the problem from snow-covered to snow-free images. Subsequently, a multi-level feature extraction network is utilized to extract multi-level feature descriptors from the transformed images. Keypoints are derived from these descriptors, enabling effective feature matching. Finally, the matching results are mapped back onto the original snow-covered remote sensing images. The proposed method was compared to well-established techniques such as SIFT, RIFT2, R2D2, and ReDFeat and demonstrated outstanding performance. In terms of NCM, MP, Rep, Recall, and F1-measure, our method outperformed the state of the art by 177, 0.29, 0.22, 0.21, and 0.25, respectively. In addition, the algorithm shows robustness over a range of image rotation angles from −40° to 40°. This innovative approach offers a new perspective on the task of matching multi-temporal snow-covered remote sensing images.

IMPACT OF ANCHOR BORROWER’S PROGRAMME ON LIVELIHOOD OF SMALLHOLDER RICE FARMERS IN KANO STATE, NIGERIA

The study was carried out to assess the impact of anchor borrower’s program on livelihood of smallholders’ rice farmers in Kano Sate, Nigeria. A Multi-stage sampling technique was employed to 303 beneficiaries and 303 non- beneficiaries. Data were analysed using propensity score matching. The result of Stratified matching shows participants in the ABP experienced significant (p<0.001) increase in their asset of about N 60,347.885 than the non-participants. However, participants in the ABPs experienced insignificant increase in income of about N 93,361.638 than the non-participants. The result of Kernels matching shows that participants in the ABP scheme experienced insignificant decrease in output of about -4.516 (kg/bags) than the non-participants. It was concluded that, ABP have no significant impact on the yield and income of participating rice farmers in the areas. It was recommended that the project should be reviewed by government and come up with a certain policy which will necessitate proper implementation and its sustainability.

Impacts of Irrigated Water Use on Household’s Income in South Wollo Zone, Amhara Regional State, Ethiopia

Agriculture is the backbone of the Sub-Saharan African economy. Ethiopia's GDP is also shared by 45 from the agriculture sectors. However, it is confronted and challenged by variable rainfall and climate changes. Particularly, in South Wollo zone, agriculture is not exceptional in facing such daunting challenges and effects of variable rainfall and climate change despite there are abundant alternative irrigated water resources. River and groundwater sources have not yet been used as alternative uses for agricultural production. As a result, rural households' income couldn’t meet their minimum food and nonfood requirements. This study, thus, attempted to evaluate the impact of irrigated water use on rural household's income in South Wollo Zone, Amhara regional state, Ethiopia. In pursuit of this, it employed a descriptive type of research design and triangulated research approach that consists of both quantitative and qualitative techniques. Primary and secondary data were collected from small scale irrigated households and secondary sources. Binary logistic regression was used to determine major significant factors that affect households' irrigated water use for agricultural production. A propensity core matching model was employed to evaluate irrigated water use and agriculture on household’s income. This study result (binary logistic regression result) showed that the household’s family size, land size and willingness were significant factors that determined irrigated water use for agricultural production at 95 percent level of significance. The propensity score matching model result also shows that irrigated water use significantly created significant impact on household’s income. It is, thus, keenly important to change and improve the smallholder farmer’s land size, extension services, rural credit, technology, education level, awareness about family size, and willingness to use irrigated water sources, such as, ground and river water for agriculture agricultural production that increase their level of income.

Does the geographic region of plastic surgery away rotations influence residency match success by region?

Integrated plastic surgery is consistently one of the most competitive residency specialties to successfully match. Students, advisors, and mentors are constantly looking for strategies to increase the odds of successfully matching. Away rotations (AR) give students and residency programs a chance to experience each other and get a gage of program fit and gives the student ability to show interest in a geographic region. The purpose of this study is to determine if completing an away rotation in a specific geographic region increases the chances of matching there. U.S. medical student seniors from 2018-2023 applying into integrated plastic surgery were analyzed. The Texas STAR survey was used as a data source. Data was collected on the number of applications, interviews, AR, applicant home region, and match outcome and stratified into 4 regions, central, northeast, south, and west based on AAMC program listings. Applicant statistics such as standardized exam scores were also collected. Linear and logistic regression were conducted assess associations with increased interviews and successfully matching in specific geographic regions. χ² and independent T-tests were used to assess associations between match outcome and applicant statistics. 401 applicants with 28561 applications were included for analysis. Match success was 78.3%. Most applicants completed at least 1 AR (85.9%) with a mean of 2.04 per applicant. Completing more AR in a region resulted in significantly more interview offers in that area, with an average increase of 1.3 interviews for each AR completed (p<.001). Completing more AR and having more interviews in a particular region increased the odds of matching in that region (p<.05). Number of interviews, completing an AR, USMLE Step 2 score, alpha omega alpha membership, and cumulative quartile rank were associated with increased match success. Completing AR in specific geographic regions increased the number of interviews and chances of matching in the same region.

Sports Results Prediction Model Using Machine Learning

Within the past few decades, more and more people use Machine learning technology to predict sports performance. This paper aims to research the possibility of sports results prediction with good precision. Machine learning methods are often used to create model that will produce a representative output of the probable match result. This can assist coaches and managers in evaluating player performance, identifying skills, predicting injuries, and evaluating game strategy. Thanks to the good accuracy of the forecast, one of the constantly evolving areas is sports betting. Finally, considering the current research review, a framework is proposed to develop a system based on artificial intelligence to predict the outcome of a football match. This research provides information on how system learning algorithms have proven to be useful and how they can produce success. This research also reviews the research of data mining systems to predict athletic performance and evaluate the strengths and weaknesses of each system.

The impact of e-sports championships on stock prices of sponsoring companies

This paper studies the impact of esports matches results on the dynamics of sponsoring companies shares. Statistics on three main esports leagues is reviewed: Defense of the Ancient 2, League of legends and Counter Strike: Global Offensive, with Samsung, MegaFon, Intel, HTC corporation, MSI, Asus, Comcast Xfinity, Logitech, Lenovo, BMW, Honda, AMD and a number of several lesser-known companies as sponsors. The study will test the assumption concerning the growth of share prices of the companies sponsoring esports events. Another purpose of the study is to identify the most profitable esports teams and championships. The work will also include an event analysis designed to answer the question of which leagues for which sponsor companies may be preferable in terms of return on investment and why. In particular, the event window will be considered in the context of the teams in middle places, as well as in the context of the winners and losers in a particular esports league. In addition, all sponsors will be divided into their production areas to track the impact of the industry factor. The main result is that the profitability of companies associated with the video game industry will have low correlation with the outcomes of matches of esports teams. The findings show that if a team has the least number of sponsors, there is a greater return on shares than for other teams with a greater number of sponsors.