Dynamic Matching Algorithm Research Articles

A New Joint Training Method for Facial Expression Recognition with Inconsistently Annotated and Imbalanced Data

Facial expression recognition (FER) plays a crucial role in various applications, including human–computer interaction and affective computing. However, the joint training of an FER network with multiple datasets is a promising strategy to enhance its performance. Nevertheless, widespread annotation inconsistencies and class imbalances among FER datasets pose significant challenges to this approach. This paper proposes a new multi-dataset joint training method, Sample Selection and Paired Augmentation Joint Training (SSPA-JT), to address these challenges. SSPA-JT models annotation inconsistency as a label noise problem and selects clean samples from auxiliary datasets to expand the overall dataset size while maintaining consistent annotation standards. Additionally, a dynamic matching algorithm is developed to pair clean samples of the tail class with noisy samples, which enriches the tail classes with diverse background information. Experimental results demonstrate that SSPA-JT achieved superior or comparable performance compared with the existing methods by addressing both annotation inconsistencies and class imbalance during multi-dataset joint training. It achieved state-of-the-art performance on RAF-DB and CAER-S datasets with accuracies of 92.44% and 98.22%, respectively, reflecting improvements of 0.2% and 3.65% over existing methods.

Constructing and Realising an Employment Platform for Slash Youth in the Age of Digital Intelligence

The current employment environment is becoming increasingly complex, with many job seekers competing with each other in more concentrated and narrower fields, worsening the job market as well as inhibiting the career potential of job seekers. There is a need to provide better employment guidance and employment quality assessment for slash youth. This study attempts to design a job recommendation model for slash youths by combining an improved collaborative filtering algorithm and a dynamic bilateral matching algorithm (BMA). The test results show that the precision rate of the BMA is always the largest with the increase of the number of clusters, with the highest value reaching 90.04%; the average ranking inverse curve of bilateral matching has the fastest growth rate, with the maximum value of 62.04%, which is 34.26% and 10.06% higher than the other two maximum values, and the optimal number of clusters is set to 24. The highest precision rate of the algorithm is 82.17% when the number of recommendations is 10. The algorithm also performed better in terms of recommendation diversity, with a maximum value of around 0.28. The recommendation success rate and satisfaction value reached 87.72% and 47.86%, respectively. The recommendation precision of the model designed in this study is high. It is conducive to solving problems such as difficulty in recruiting and finding jobs, and promotes the healthy development of the recruitment market.

Fairness-Aware Dynamic Ride-Hailing Matching Based on Reinforcement Learning

The core issue in ridesharing is designing reasonable algorithms to match drivers and passengers. The ridesharing matching problem, influenced by various constraints such as weather, traffic, and supply–demand dynamics in real-world scenarios, requires optimization of multiple objectives like total platform revenue and passenger waiting time. Due to its complexity in terms of constraints and optimization goals, the ridesharing matching problem becomes a central issue in the field of mobile transportation. However, the existing research lacks exploration into the fairness of driver income, and some algorithms are not practically applicable in the industrial context. To address these shortcomings, we have developed a fairness-oriented dynamic matching algorithm for ridesharing, effectively optimizing overall platform efficiency (expected total driver income) and income fairness among drivers (entropy of weighted amortization fairness information between drivers). Firstly, we introduced a temporal dependency of matching outcomes on subsequent matches in the scenario setup and used reinforcement learning to predict these temporal dependencies, overcoming the limitation of traditional matching algorithms that rely solely on historical data and current circumstances for order allocation. Then, we implemented a series of optimization solutions, including the introduction of a time window matching model, pruning operations, and metric representation adjustments, to enhance the algorithm’s adaptability and scalability for large datasets. These solutions also ensure the algorithm’s efficiency. Finally, experiments conducted on real datasets demonstrate that our fairness-oriented algorithm based on reinforcement learning achieves improvements of 81.4%, 28.5%, and 79.7% over traditional algorithms in terms of fairness, platform utility, and matching efficiency, respectively.

Resource Allocation in Multi-Carrier Multiplexed NOMA Cooperative System

Non-orthogonal multiple access (NOMA) cooperative communication technology can combine the advantages of NOMA and cooperative communication, providing high spectrum efficiency and increasing user coverage for next-generation wireless systems. However, the research on NOMA cooperative communication technology is still in a preliminary stage and has mainly concentrated on the scenario of fewer users. This paper focuses on a user-centered NOMA collaboration system in an ultra-dense network, and it constructs a resource allocation optimization problem to meet the demands of each user. Then, this paper decomposes the optimization problem into two subproblems; one is the grouping match among multiple relays and users, and the other is jointly allocating power and subcarrier resources. Accordingly, a dynamic packet matching algorithm based on Gale–Shapley and an iterative algorithm based on the difference of convex functions programing are proposed. Compared with existing schemes, the proposed algorithms can improve system throughput while ensuring the quality of service of users.

Design scheme of ship risk prediction model from the perspective of artificial intelligence

Vessels sailing at sea are full of risks, accidents occur frequently, and it is easy to cause heavy casualties and property losses. To this end, this article focuses on how to build a high-precision and rapid ship risk prediction model, and proposes a design plan for a ship risk prediction model based on big data and artificial intelligence. The plan includes a basic data layer, a technical business layer, and an application layer, with a focus on The technical research scheme of the graph representation model construction of the ship risk big data, the dynamic graph matching algorithm and the ship risk prediction is elaborated in detail, and finally the experimental design method of the scheme is given. The design scheme proposed in this paper can provide reference and inspiration for the research and development of marine risk system.

Fuzzy Matching Learning for Dynamic Resource Allocation in Cellular V2X Network

Benefiting from the global deployment and fast commercialization of cellular systems, cellular-enabled vehicle-to-everything (V2X) opens up a significant prospect in the foreseeable future, for supporting proliferating vehicular services. Reliable and efficient resource allocation is a prerequisite for enjoying excellent quality of vehicular communication experiences, which yet still remains a serious challenge due to the inherent vehicle mobility and network heterogeneity. In this work, taking the rapidly varying channel state information (CSI) into consideration, we investigate the joint time-frequency allocation problem for the heterogeneous cellular V2X network, where resource sharing based on hierarchical reuse among different V2X communication types are granted. To address the high dynamics of V2X environment, a mapped fuzzy space is introduced, in which the uncertain CSI is interpreted as fuzzy numbers. This could effectively avoid the deterioration of such dynamic environment to the stability and convergence of optimization mechanisms. On this basis, we construct a two-side many-to-many fuzzy matching game (MM-FMG) to formulate the optimization problem with the dynamic and uncertain information, and further propose a vehicle-resource dynamic matching algorithm to solve this MM-FMG problem. Our developed scheme can achieve both reliable and efficient resource assignment by excluding the precise CSI, which is hence more suitable to the concerned V2X scenarios. Finally, the superior performances of our designed algorithm are demonstrated via numerical simulations.

The Effect of Thickness-Based Dynamic Matching Mechanism on a Hyperledger Fabric-Based TimeBank System

In a community with an aging population, helping each other is a must society function. Lacking mutual trust makes the need for a fair and transparent service exchange platform on top of the public service administration’s list. We present an efficient blockchain-based TimeBank realization with a newly proposed dynamic service matching algorithm (DSMA) in this work. The Hyperledger Fabric (or Fabric in short), one of the well-known Consortium Blockchains, is chosen as our system realization platform. It provides the identity certification mechanism and has an extendable network structure. The performance of a DSMA is measured by the waiting time for a service to get a match, called the service-matching waiting time (SMWT). In our DSMA, the decision as to whether a service is to get a match or wait for a later chance depends dynamically on the total number of contemporarily available services (i.e., the thickness of the service market). To better the proposed TimeBank system’s service quality, a Dynamic Tuning Strategy (DTS) is designed to thicken the market size. Experimental results show that a thicker market makes on-chain nodes have more links, and in turn, they find a match easier (i.e., consume a shorter SMWT).

Aerobics Movement Decomposition Action Teaching System Based on Intelligent Vision Sensor

With the development of the times, teaching has not only stayed between people, but also gradually developed into the teaching interaction between man and machine. In the past, the teaching form was relatively single and old. Based on the intelligent visual sensor, this paper develops an auxiliary teaching system for the decomposition of aerobics action and reasonably uses the Internet and algorithms to catalog a series of aerobics action systems into the system. The DTW dynamic motion matching algorithm of the system will recognize human actions more accurately. The system will feed back human actions to the system in real time based on human feature recognition. Then, after comparison, the system will display the standard posture of this action and the aerobics posture in the next step. Therefore, this system develops teaching not only in class, but everywhere. The system not only improves the teaching quality of aerobics, but also strengthens the physical quality of teenagers. It has a new understanding of the standardization of aerobics teaching. After the function of the system is complete, the system will be distributed to aerobics learners. In many feedback information, the average use satisfaction has reached about 80%, which is a good performance index for the performance of the system itself.

A dynamic impedance matching algorithm of three-stub tuners based on equivalent circuit analysis

Three-stub waveguides are common impedance matching devices which are essential for a wide range of high-power microwave applications. Based on equivalent circuit analysis method, this article presents a novel matching algorithm which can be applied for three-stub tuners to implement continuous, automatic and real-time impedance matching. Equivalent model of a stub waveguide is firstly established by using transmission lines in series and capacitors in parallel. Then, according to the proposed model, the mathematical expression of reflection coefficient at different stub depth is derived by using currently detected reflection coefficient and stub depth. Later, based on the derived expression, an algorithm is developed to determine the optimum insertion depths of the stubs when VSWR is minimum. The S 11 parameters of the stub waveguide which are calculated by the method agree well with those measured by vector network analyser. Meanwhile, the algorithm is able to limit reflection coefficient under –10 dB and can easily be redesigned for waveguides of different sizes. Thus, it shows a promising future in industrial impedance matching applications.

Hierarchical stroke mesh: a new progressive matching method for detecting multi-scale road network changes using OpenStreetMap

Spatial feature matching is the key to detecting incremental changes in spatial data and extracting the updated information. The accuracy of spatial feature matching can depend on the structural organization of the data being compared; inconsistent data structures make comparison more difficult. OpenStreetMap (OSM) road network data, for example, is updated frequently to the point of being unstable, making the matching process used in information extraction susceptible to interference. To use OSM for comparison with other road data sources, this problem must be addressed. This paper proposes a new multi-scale dynamic matching algorithm based on a hierarchical stroke mesh (HSM) to detect matches between OSM data and professional surveying and mapping data and to update the change information. By improving the integrity and continuity of the stroke generation method and its algorithm for evaluating the importance of information, the algorithm proposed in this paper identifies the spatial hierarchy contained in the road network and abstracts the road network. The result is the HSM. The algorithm is based on multi-scale matching constraint rules designed from coarse to fine in terms of both resolution and granularity. It is used to detect one-to-one or one-to-many mapping relationships among different mesh levels (mesh, mesh boundary segment, and mesh inner segment). This allows progressive iterative matching between the older survey data and the newer OSM data. The results show that the HSM algorithm proposed in this paper can detect incremental changes between the two vector data sources quickly and accurately. Compared with others, this algorithm can effectively improve matching accuracy while sacrificing little performance.

A Rail Fastener Tightness Detection Approach Using Multi-source Visual Sensor.

At present, the method of two-dimensional image recognition is mainly used to detect the abnormal fastener in the rail-track inspection system. However, the too-tight-or-too-loose fastener condition may cause the clip of the fastener to break or loose due to the high frequency vibration shock, which is difficult to detect from the two-dimensional image. In this practical application background, 3D visual detection technology provides a feasible solution. In this paper, we propose a fundamental multi-source visual data detection method, as well as an accurate and robust fastener location and nut or bolt segmentation algorithm. By combining two-dimensional intensity information and three-dimensional depth information generated by the projection of line structural light, the locating of nut or bolt position and accurate perception of height information can be realized in the dynamic running environment of railway. The experimental results show that the static measurement accuracy in the vertical direction using the structural light vision sensor is 0.1 mm under the laboratory condition, and the dynamic measurement accuracy is 0.5 mm under the dynamic train running environment. We use dynamic template matching algorithm to locate fasteners from 2D intensity map, which achieves 99.4% accuracy, then use the watershed algorithm to segment the nut and bolt from the corresponding depth image of located fastener. Finally, the 3D shape of the nut and bolt is analyzed to determine whether the nut or bolt height meets the local statistical threshold requirements, so as to detect the hidden danger of railway transportation caused by too loose or too tight fasteners.

A novel approach for Sparse Imaging of Through-wall Radar

Aiming at the problem of segmented weak orthogonal matching pursuit (SWOMP) imaging blur in the process of through-wall radar (TWR) imaging, a dynamic threshold weak orthogonal matching pursuit algorithm (DWOMP) is introduced in this paper, which can significantly improve the imaging performance. Firstly, the TWR compressed sensing simulation model and over-complete dictionary are established by using Chirp signal radar echo data. Then the specific process of DWOMP algorithm is proposed and used to reconstruct multi-sparse target scenes. Finally, the DWOMP algorithm is compared with Basis Pursuit (BP) algorithm and SWOMP algorithm through simulation experiments. The simulation results show that in the same experimental conditions, the imaging time of DWOMP algorithm is about 3/5 of that of BP algorithm, and the imaging resolution of DWOMP algorithm is better than that of SWOMP algorithm.

An exponential search enhanced dynamic sort-based interest matching algorithm for interest management in distributed simulation

Interest management is employed in most distributed simulation to filter irrelevant messages on network and is essential for the performance and scalability of simulation systems. In High-Level Architecture (HLA), the data distribution management (DDM) adopts an interest matching algorithm to filter unnecessary communications among federates by computing the overlap statuses between the update and subscription regions. In many spatial applications, only a portion of regions changes gradually at each time step. Hence, dynamic matching for selective modified regions is necessary. The dynamic sort-based matching algorithm has proved to be the most efficient. However, the existing dynamic sort-based matching algorithms do not separate modified regions from static regions, which will produce large amounts of unnecessary comparisons and swap operations between modified and static regions. To solve the problem, we propose an exponential search enhanced dynamic sort-based interest matching algorithm called EDSIM. In EDSIM, (1) the modified regions are separated from static regions; thus, the latter are independent from the sorting operations; (2) an exponential search method is adopted to calculate the rechecking sets for modified regions, reducing unnecessary bound comparisons between modified and static regions; (3) a bubble-sort-based matching algorithm is used to update the overlap statuses between modified regions. Experimental results demonstrate that the EDSIM algorithm achieves significantly better performance than the major existing dynamic matching algorithms under various experimental scenarios.

3D Gesture Recognition Based on Handheld Smart Terminals

With the popularity of smart devices, it has become impossible for traditional human-computer interaction techniques to accommodate people's needs. This article proposes an iOS-based three dimensional (3D) gesture recognition system, gathering users' specific gestures from their handheld smart terminals to judge implications of these gestures, so to control other smart terminals with more natural human-computer interactions. In this article, gestures were recognized by reading data about corresponding 3D gesture data with motion sensors of smart terminals using optimized dynamic time warping (DTW) algorithm. As to this algorithm, curve paths were delimited via slope based on features of mobile devices and dynamic programming. Meanwhile, this algorithm reduced computational load for template matching and costs of gesture recognition by preliminarily storing upper and lower boundaries of delimited areas with linked lists or setting distortion thresholds. In this article, efficiency and precision of recognition schemes were tested and verified on cellphones. The results suggested that the improved algorithm was less time-consuming than classical algorithms, and required less time for computational load for template matching. Furthermore, it was demonstrated that the gesture recognition based on dynamic template matching algorithms, with higher recognition efficiency and precision, could bring better experiences of human-computer interactions.

Cellular V2X Communications in Unlicensed Spectrum: Harmonious Coexistence With VANET in 5G Systems

With the increasing demand for vehicular data transmission, limited dedicated cellular spectrum becomes a bottleneck to satisfying the requirements of all cellular vehicle-to-everything (V2X) users. To address this issue, unlicensed spectrum is considered to serve as the complement to support cellular V2X users. In this paper, we study the coexistence problem of cellular V2X users and vehicular ad hoc network (VANET) users over the unlicensed spectrum. To facilitate the coexistence, we design an energy sensing-based spectrum sharing scheme, where cellular V2X users are able to access the unlicensed channels fairly while reducing the data transmission collisions between cellular V2X and VANET users. In order to maximize the number of active cellular V2X users, we formulate the scheduling and resource allocation problem as a two-sided many-to-many matching with peer effects. We then propose a dynamic vehicle-resource matching algorithm and present the analytical results on the convergence time and computational complexity. Simulation results show that the proposed algorithm outperforms existing approaches in terms of the performance of the cellular V2X system when the unlicensed spectrum is utilized.

Multi-Scenarios Dynamic Matching Algorithm for Hierarchical Treatment System

In China, 10% of medical resource are general hospital which treat 86% patients. This will lead the health resources in these hospitals become insufficient and exhaust, even if the resources in other hospitals idle. Previous studies have indicated that the scattering resource systems will result in significant imbalances if it lacks stable and effective match. To deal with Two-Sided Matching (TSM) problem in hierarchical medical system, a matching decision-making approach based on multiple scenarios was proposed. The algorithm was designed to adapt four kinds of scenarios, it analyzed multi-context matching satisfaction degree of these cooperation situations in different forms of environment respectively and specifically．By comparing the examples, the multi - scenario dynamic matching method is superior to the random matching algorithm and the “F-Y” algorithm (improved G - S algorithm), and it is effective to obtain the stable and feasible solution. This paper showed a multi-scenarios dynamic matching algorithm for hierarchical treatment system by modifying comprehensive satisfaction integration function and differential adjustment function. This paper concentrated on the stability and total satisfaction goals of system matching. This method serves as a decision-making reference for the bilateral matching encountered in the problem of “hierarchical treatment system” around the world.

TM-Aligner: Multiple sequence alignment tool for transmembrane proteins with reduced time and improved accuracy

Membrane proteins plays significant role in living cells. Transmembrane proteins are estimated to constitute approximately 30% of proteins at genomic scale. It has been a difficult task to develop specific alignment tools for transmembrane proteins due to limited number of experimentally validated protein structures. Alignment tools based on homology modeling provide fairly good result by recapitulating 70–80% residues in reference alignment provided all input sequences should have known template structures. However, homology modeling tools took substantial amount of time, thus aligning large numbers of sequences becomes computationally demanding. Here we present TM-Aligner, a new tool for transmembrane protein sequence alignment. TM-Aligner is based on Wu-Manber and dynamic string matching algorithm which has significantly improved its accuracy and speed of multiple sequence alignment. We compared TM-Aligner with prevailing other popular tools and performed benchmarking using three separate reference sets, BaliBASE3.0 reference set7 of alpha-helical transmembrane proteins, structure based alignment of transmembrane proteins from Pfam database and structure alignment from GPCRDB. Benchmarking against reference datasets indicated that TM-Aligner is more advanced method having least turnaround time with significant improvements over the most accurate methods such as PROMALS, MAFFT, TM-Coffee, Kalign, ClustalW, Muscle and PRALINE. TM-Aligner is freely available through http://lms.snu.edu.in/TM-Aligner/.

Sub-Channel and Power Allocation for Non-Orthogonal Multiple Access Relay Networks With Amplify-and-Forward Protocol

In this paper, we study the resource allocation problem for a single-cell non-orthogonal multiple access (NOMA) relay network where an OFDM amplify-and-forward relay allocates the spectrum and power resources to the source–destination (SD) pairs. We aim to optimize the resource allocation to maximize the average sum-rate. The optimal approach requires an exhaustive search, leading to an NP-hard problem. To solve this problem, we propose two efficient many-to-many two-sided SD pair-subchannel matching algorithms, in which the SD pairs and sub-channels are considered as two sets of players chasing their own interests. The proposed algorithms can provide a sub-optimal solution to this resource allocation problem in affordable time. Both the static matching algorithm and the dynamic matching algorithm converge to a pair-wise stable matching after a limited number of iterations. Simulation results show that the capacity of both proposed algorithms in the NOMA scheme significantly outperforms the conventional orthogonal multiple access scheme. The proposed matching algorithms in NOMA scheme also achieve a better user-fairness performance than the conventional orthogonal multiple access.

Autonomous underwater vehicle optimal path planning method for seabed terrain matching navigation

To solve the problem of existing methods of terrain matching having low precision in the areas with small eigenvalues, this work presents an Autonomous Underwater Vehicle optimal path planning method for seabed terrain matching navigation to avoid these areas. The method demonstrates high matching precision on each match area. This method has built the field map and value map that represents obstacle and matching performance, respectively, and the planning algorithm, which includes dynamic matching algorithm, cost function, search length and min-length, second-goal point and dynamic path planing algorithm, was proposed on basic of A star algorithm. Terrain-entropy and terrain-variance-entropy were introduced as criteria in the cost function to represent the matching performance. Then, joint criteria, which were calculated by a Back Propagation Neural Network, and fuzzy criteria were introduced and proved to be feasible through simulation experiments. The path planning method on the basic of fuzzy criteria, in terms of time consumption, was a more suitable method than the one based on joint criteria for the same terrain matching accuracy.

Duplicate video detection for large-scale multimedia

Since rapid growth of IT technologies, the use of multimedia data such as image and videos are explosively increasing. It is an important aspect of not only for users but also researchers. Duplicate images and videos are rapidly increasing and it causes difficulties in retrieval and management as well. It also causes copyright problems. In this paper, we discus prior duplicate video detection techniques and overcome previous research problems using block histogram and dynamic matching approach duplicate video detection method. We improved excessive abstract of previous block mean-value based feature extraction method to be robust in various video transformations. Also, we created feature vector of timely histogram by unit of blocks to reflect video features. We proposed dynamic matching algorithm to match videos which is suitable for large-scale video data. To evaluate our proposal, we used VIREO video datasets which is provided by Hong Kong City University and Carnegie Mellon University and MUSCLE-VCD-2007 dataset which is provided by INRIA. Our method showed 90 % of accuracy on duplicate video detection. Our proposed method showed robustness especially in various video transformations. Also, we tested video clustering test to prove our method and dynamic matching method showed 5 times fast compare to existing method which is suitable for real-time and large-scale video detection process.