Search

Parameter tuning of PID controller for liquid level control of beer filling machine was studied in this paper, which can meet the demand of accurate controlling in beer production and improve the rapidity under the same conditions. Firstly, an improved genetic algorithm was proposed which has been verified by eight kinds of test functions. Simulation results revealed that, in comparation with other modified particle swarm optimization algorithm and modified genetic algorithm, the algorithm proposed in this work is not only capable to improve the convergence speed and precision under the same experimental conditions but also to improve the probability to converge to the optimal value. Finally, the proposed algorithm was applied to the parameter tuning of the PID controller of beer filling machine for liquid level control. Superior property had been obtained, which implied an effective improvement in the rapidity with the premise of steady-state error exclusion. [ABSTRACT FROM AUTHOR]

The current unsupervised domain adaptation person re-identification (re-ID) method aims to solve the domain shift problem and applies prior knowledge learned from labelled data in the source domain to unlabelled data in the target domain for person re-ID. At present, the unsupervised domain adaptation person re-ID method based on pseudolabels has obtained state-of-the-art performance. This method obtains pseudolabels via a clustering algorithm and uses these pseudolabels to optimize a CNN model. Although it achieves optimal performance, the model cannot be further optimized due to the existence of noisy labels in the clustering process. In this paper, we propose a stable median centre clustering (SMCC) for the unsupervised domain adaptation person re-ID method. SMCC adaptively mines credible samples for optimization purposes and reduces the impact of label noise and outliers on training to improve the performance of the resulting model. In particular, we use the intracluster distance confidence measure of the sample and its K-reciprocal nearest neighbour cluster proportion in the clustering process to select credible samples and assign different weights according to the intracluster sample distance confidence of samples to measure the distances between different clusters, thereby making the clustering results more robust. The experiments show that our SMCC method can select credible and stable samples for training and improve performance of the unsupervised domain adaptation model. Our code is available at https://github.com/sunburst792/SMCC-method/tree/master. [ABSTRACT FROM AUTHOR]

In the process of product collaborative design, the association between designers can be described by a complex network. Exploring the importance of the nodes and the rules of information dissemination in such networks is of great significance for distinguishing its core designers and potential designer teams, as well as for accurate recommendations of collaborative design tasks. Based on the neighborhood similarity model, combined with the idea of network information propagation, and with the help of the ReLU function, this paper proposes a new method for judging the importance of nodes—LLSR. This method not only reflects the local connection characteristics of nodes but also considers the trust degree of network propagation, and the neighbor nodes' information is used to modify the node value. Next, in order to explore potential teams, an LA-LPA algorithm based on node importance and node similarity was proposed. Before the iterative update, all nodes were randomly sorted to get an update sequence which was replaced by the node importance sequence. When there are multiple largest neighbor labels in the propagation process, the label with the highest similarity is selected for update. The experimental results in the related networks show that the LLSR algorithm can better identify the core nodes in the network, and the LA-LPA algorithm has greatly improved the stability of the original LPA algorithm and has stably mined potential teams in the network. [ABSTRACT FROM AUTHOR]

A band selection method based on two layers selection (TLS) strategy, which forms an optimal subset from all-bands set to reconstitute the original hyperspectral imagery (HSI) and aims to cost a fewer bands for better performances, is proposed in this paper. As its name implies, TLS picks out the bands with low correlation and a large amount of information into the target set to reach dimensionality reduction for HSI via two phases. Specifically, the fast density peaks clustering (FDPC) algorithm is used to select the most representative node in each cluster to build a candidate set at first. During the implementation, we normalize the local density and relative distance and utilize the dynamic cutoff distance to weaken the influence of density so that the selection is more likely to be carried out in scattered clusters than in high-density ones. After that, we conduct a further selection in the candidate set using mRMR strategy and comprehensive measurement of information (CMI), and the eventual winners will be selected into the target set. Compared with other six state-of-the-art unsupervised algorithms on three real-world HSI data sets, the results show that TLS can group the bands with lower correlation and richer information and has obvious advantages in indicators of overall accuracy (OA), average accuracy (AA), and Kappa coefficient. [ABSTRACT FROM AUTHOR]

For many applications, finding rare instances or outliers can be more interesting than finding common patterns. Existing work in outlier detection never considers the context of deep web. In this paper, we argue that, for many scenarios, it is more meaningful to detect outliers over deep web. In the context of deep web, users must submit queries through a query interface to retrieve corresponding data. Therefore, traditional data mining methods cannot be directly applied. The primary contribution of this paper is to develop a new data mining method for outlier detection over deep web. In our approach, the query space of a deep web data source is stratified based on a pilot sample. Neighborhood sampling and uncertainty sampling are developed in this paper with the goal of improving recall and precision based on stratification. Finally, a careful performance evaluation of our algorithm confirms that our approach can effectively detect outliers in deep web. [ABSTRACT FROM AUTHOR]

In order to realize smooth gait planning and stability control of a quadruped robot, a new controller algorithm based on CPG-ZMP (central pattern generator-zero moment point) is put forward in this paper. To generate smooth gait and shorten the adjusting time of the model oscillation system, a new CPG model controller and its gait switching strategy based on Wilson-Cowan model are presented in the paper. The control signals of knee-hip joints are obtained by the improved multi-DOF reduced order control theory. To realize stability control, the adaptive speed adjustment and gait switch are completed by the real-time computing of ZMP. Experiment results show that the quadruped robot’s gaits are efficiently generated and the gait switch is smooth in the CPG control algorithm. Meanwhile, the stability of robot’s movement is improved greatly with the CPG-ZMP algorithm. The algorithm in this paper has good practicability, which lays a foundation for the production of the robot prototype. [ABSTRACT FROM AUTHOR]

Rapid growth of web and its applications has created a colossal importance for recommender systems. Being applied in various domains, recommender systems were designed to generate suggestions such as items or services based on user interests. Basically, recommender systems experience many issues which reflects dwindled effectiveness. Integrating powerful data management techniques to recommender systems can address such issues and the recommendations quality can be increased significantly. Recent research on recommender systems reveals an idea of utilizing social network data to enhance traditional recommender system with better prediction and improved accuracy. This paper expresses views on social network data based recommender systems by considering usage of various recommendation algorithms, functionalities of systems, different types of interfaces, filtering techniques, and artificial intelligence techniques. After examining the depths of objectives, methodologies, and data sources of the existing models, the paper helps anyone interested in the development of travel recommendation systems and facilitates future research direction. We have also proposed a location recommendation system based on social pertinent trust walker (SPTW) and compared the results with the existing baseline random walk models. Later, we have enhanced the SPTW model for group of users recommendations. The results obtained from the experiments have been presented. [ABSTRACT FROM AUTHOR]

To study incremental machine learning in tensor space, this paper proposes incremental tensor discriminant analysis. The algorithm employs tensor representation to carry on discriminant analysis and combine incremental learning to alleviate the computational cost. This paper proves that the algorithm can be unified into the graph framework theoretically and analyzes the time and space complexity in detail. The experiments on facial image detection have shown that the algorithm not only achieves sound performance compared with other algorithms, but also reduces the computational issues apparently. [ABSTRACT FROM AUTHOR]

It is necessary to improve the performance of the object detection algorithm in resource-constrained embedded devices by lightweight improvement. In order to further improve the recognition accuracy of the algorithm for small target objects, this paper integrates 5 × 5 deep detachable convolution kernel on the basis of MobileNetV2-SSDLite model, extracts features of two special convolutional layers in addition to detecting the target, and designs a new lightweight object detection network—Lightweight Microscopic Detection Network (LMS-DN). The network can be implemented on embedded devices such as NVIDIA Jetson TX2. The experimental results show that LMS-DN only needs fewer parameters and calculation costs to obtain higher identification accuracy and stronger anti-interference than other popular object detection models. [ABSTRACT FROM AUTHOR]

In the paper, the flight time deviation of Lithuania airports has been analyzed. The supervised machine learning model has been implemented to predict the interval of time delay deviation of new flights. The analysis has been made using seven algorithms: probabilistic neural network, multilayer perceptron, decision trees, random forest, tree ensemble, gradient boosted trees, and support vector machines. To find the best parameters which give the highest accuracy for each algorithm, the grid search has been used. To evaluate the quality of each algorithm, the five measures have been calculated: sensitivity/recall, precision, specificity, F-measure, and accuracy. All experimental investigation has been made using the newly collected dataset from Lithuania airports and weather information on departure/landing time. The departure flights and arrival flights have been investigated separately. To balance the dataset, the SMOTE technique is used. The research results showed that the highest accuracy is obtained using the tree model classifiers and the best algorithm of this type to predict is gradient boosted trees. [ABSTRACT FROM AUTHOR]

The shearer is one of the core equipment of the fully mechanized coal face. The fast and accurate positioning of the shearer is the prerequisite for its memory cutting, intelligent height adjustment, and intelligent speed adjustment. Inertial navigation technology has many advantages such as strong autonomy, good concealment, and high reliability. The accurate positioning of the shearer based on inertial navigation can not only determine its operating position but also measure the direction of movement. However, when inertial navigation is used to locate the shearer in motion, the cumulative errors will occur, resulting in inaccurate positioning of the shearer. The accuracy of the initial alignment is directly related to the working precision of the inertial navigation system. In order to improve the efficiency and accuracy of initial alignment, an improved initial alignment method is proposed in this paper, which uses a fruit fly-optimized Kalman filter algorithm for initial alignment. In order to improve the filtering performance, the fruit fly-optimized Kalman filter algorithm uses an improved fruit fly algorithm to realize the adaptive optimization of system noise variance. Finally, simulation and experiments verify the effectiveness of the fruit fly-optimized Kalman filter algorithm. [ABSTRACT FROM AUTHOR]

Renewable energy (RE) systems play a key role in producing electricity worldwide. The integration of RE systems is carried out in a distributed aspect via an autonomous hybrid microgrid (A-HMG) system. The A-HMG concept provides a series of technological solutions that must be managed optimally. As a solution, this paper focuses on the application of a recent nature-inspired metaheuristic optimization algorithm named a multimodal delayed particle swarm optimization (MDPSO). The proposed algorithm is applied to an A-HMG to find the minimum levelized cost of energy (LCOE), the lowest loss of power supply probability (LPSP), and the maximum renewable factor (REF). Firstly, a smart energy management scheme (SEMS) is proposed to coordinate the power flow among the various system components that formed the A-HMG. Then, the MDPSO is integrated with the SEMS to perform the optimal sizing for the A-HMG of a fishing village that is located in the coastal city of Essaouira, Morocco. The proposed A-HMG comprises photovoltaic panels (PV), wind turbines (WTs), battery storage systems, and diesel generators (DGs). The results of the optimization in this location show that A-HMG system can be applied for this location with a high renewable factor that is equal to 90%. Moreover, the solution is very promising in terms of the LCOE and the LPSP indexes that are equal to 0.17$/kWh and 0.12%, respectively. Therefore, using renewable energy can be considered as a good alternative to enhance energy access in remote areas as the fishing village in the city of Essaouira, Morocco. Furthermore, a sensitivity analysis is applied to highlight the impact of varying each energy source in terms of the LCOE index. [ABSTRACT FROM AUTHOR]

This paper proposes a novel test generation algorithm based on extreme learning machine (ELM), and such algorithm is costeffective and low-risk for analog device under test (DUT). This method uses test patterns derived from the test generation algorithm to stimulate DUT, and then samples output responses of the DUT for fault classification and detection. The novel ELM-based test generation algorithm proposed in this paper contains mainly three aspects of innovation. Firstly, this algorithm saves time efficiently by classifying response space with ELM. Secondly, this algorithm can avoid reduced test precision efficiently in case of reduction of the number of impulse-response samples. Thirdly, a new process of test signal generator and a test structure in test generation algorithm are presented, and both of them are very simple. Finally, the abovementioned improvement and functioning are confirmed in experiments. [ABSTRACT FROM AUTHOR]

Aiming at the phenomenon of slow convergence rate and low accuracy of bat algorithm, a novel bat algorithm based on differential operator and Lévy lights trajectory is proposed. In this paper, a differential operator is introduced to accelerate the convergence speed of proposed algorithm, which is similar to mutation strategy "DE/best/2" in differential algorithm. Lévy lights trajectory can ensure the diversity of the population against premature convergence and make the algorithm effectively jump out of local minima. 14 typical benchmark functions and an instance of nonlinear equations are tested; the simulation results not only show that the proposed algorithm is feasible and effective, but also demonstrate that this proposed algorithm has superior approximation capabilities in high-dimensional space. [ABSTRACT FROM AUTHOR]

In today's society, image resources are everywhere, and the number of available images can be overwhelming. Determining how to rapidly and effectively query, retrieve, and organize image information has become a popular research topic, and automatic image annotation is the key to text-based image retrieval. If the semantic images with annotations are not balanced among the training samples, the low-frequency labeling accuracy can be poor. In this study, a dual-channel convolution neural network (DCCNN) was designed to improve the accuracy of automatic labeling. The model integrates two convolutional neural network (CNN) channels with different structures. One channel is used for training based on the low-frequency samples and increases the proportion of low-frequency samples in the model, and the other is used for training based on all training sets. In the labeling process, the outputs of the two channels are fused to obtain a labeling decision. We verified the proposed model on the Caltech-256, Pascal VOC 2007, and Pascal VOC 2012 standard datasets. On the Pascal VOC 2012 dataset, the proposed DCCNN model achieves an overall labeling accuracy of up to 93.4% after 100 training iterations: 8.9% higher than the CNN and 15% higher than the traditional method. A similar accuracy can be achieved by the CNN only after 2,500 training iterations. On the 50,000-image dataset from Caltech-256 and Pascal VOC 2012, the performance of the DCCNN is relatively stable; it achieves an average labeling accuracy above 93%. In contrast, the CNN reaches an accuracy of only 91% even after extended training. Furthermore, the proposed DCCNN achieves a labeling accuracy for low-frequency words approximately 10% higher than that of the CNN, which further verifies the reliability of the proposed model in this study. [ABSTRACT FROM AUTHOR]

This study proposes a multilayer hybrid deep-learning system (MHS) to automatically sort waste disposed of by individuals in the urban public area. This system deploys a high-resolution camera to capture waste image and sensors to detect other useful feature information. The MHS uses a CNN-based algorithm to extract image features and a multilayer perceptrons (MLP) method to consolidate image features and other feature information to classify wastes as recyclable or the others. The MHS is trained and validated against the manually labelled items, achieving overall classification accuracy higher than 90% under two different testing scenarios, which significantly outperforms a reference CNN-based method relying on image-only inputs. [ABSTRACT FROM AUTHOR]

This paper demonstrates that nonnegative matrix factorisation is mathematically related to a class of neural networks that employ negative feedback as a mechanism of competition. This observation inspires a novel learning algorithm which we call Divisive Input Modulation (DIM). The proposed algorithm provides a mathematically simple and computationally efficient method for the unsupervised learning of image components, even in conditions where these elementary features overlap considerably. To test the proposed algorithm, a novel artificial task is introduced which is similar to the frequently-used bars problem but employs squares rather than bars to increase the degree of overlap between components. Using this task, we investigate how the proposed method performs on the parsing of artificial images composed of overlapping features, given the correct representation of the individual components; and secondly, we investigate how well it can learn the elementary components from artificial training images. We compare the performance of the proposed algorithm with its predecessors including variations on these algorithms that have produced state-of-the-art performance on the bars problem. The proposed algorithm is more successful than its predecessors in dealing with overlap and occlusion in the artificial task that has been used to assess performance. [ABSTRACT FROM AUTHOR]

This paper proposes a new multiobjective evolutionary algorithm based on the black hole algorithm with a new individual density assessment (cell density), called “adaptive multiobjective black hole algorithm” (AMOBH). Cell density has the characteristics of low computational complexity and maintains a good balance of convergence and diversity of the Pareto front. The framework of AMOBH can be divided into three steps. Firstly, the Pareto front is mapped to a new objective space called parallel cell coordinate system. Then, to adjust the evolutionary strategies adaptively, Shannon entropy is employed to estimate the evolution status. At last, the cell density is combined with a dominance strength assessment called cell dominance to evaluate the fitness of solutions. Compared with the state-of-the-art methods SPEA-II, PESA-II, NSGA-II, and MOEA/D, experimental results show that AMOBH has a good performance in terms of convergence rate, population diversity, population convergence, subpopulation obtention of different Pareto regions, and time complexity to the latter in most cases. [ABSTRACT FROM AUTHOR]

Inspired by the behavior of dandelion sowing, a new novel swarm intelligence algorithm, namely, dandelion algorithm (DA), is proposed for global optimization of complex functions in this paper. In DA, the dandelion population will be divided into two subpopulations, and different subpopulations will undergo different sowing behaviors. Moreover, another sowing method is designed to jump out of local optimum. In order to demonstrate the validation of DA, we compare the proposed algorithm with other existing algorithms, including bat algorithm, particle swarm optimization, and enhanced fireworks algorithm. Simulations show that the proposed algorithm seems much superior to other algorithms. At the same time, the proposed algorithm can be applied to optimize extreme learning machine (ELM) for biomedical classification problems, and the effect is considerable. At last, we use different fusion methods to form different fusion classifiers, and the fusion classifiers can achieve higher accuracy and better stability to some extent. [ABSTRACT FROM AUTHOR]

For data mining, reducing the unnecessary redundant attributes which was known as attribute reduction (AR), in particular, reducts with minimal cardinality, is an important preprocessing step. In the paper, by a coding method of combination subset of attributes set, a novel search strategy for minimal attribute reduction based on rough set theory (RST) and fish swarm algorithm (FSA) is proposed. The method identifies the core attributes by discernibility matrix firstly and all the subsets of noncore attribute sets with the same cardinality were encoded into integers as the individuals of FSA. Then, the evolutionary direction of the individual is limited to a certain extent by the coding method. The fitness function of an individual is defined based on the attribute dependency of RST, and FSA was used to find the optimal set of reducts. In each loop, if the maximum attribute dependency and the attribute dependency of condition attribute set are equal, then the algorithm terminates, otherwise adding a single attribute to the next loop. Some well-known datasets from UCI were selected to verify this method. The experimental results show that the proposed method searches the minimal attribute reduction set effectively and it has the excellent global search ability. [ABSTRACT FROM AUTHOR]

In recent years, the optimization of multi-objective service composition in distributed systems has become an important issue. Existing work makes a smaller set of Pareto-optimal solutions to represent the Pareto Front (PF). However, they do not support complex mapping of the Pareto-optimal solutions to quality of service (QoS) objective space, thus having limitations in providing a representative set of solutions. We propose an enhanced multi-objective differential evolution algorithm to seek a representative set of solutions with good proximity and distributivity. Specially, we propose a dual strategy to adjust the usage of different creation operators, to maintain the evolutionary pressure toward the true PF. Then, we propose a reference vector neighbor search to have a fine-grained search. The proposed approach has been tested on a real-world dataset that locates a representative set of solutions with proximity and distributivity. [ABSTRACT FROM AUTHOR]

Per-user pricing is possible with cloud computing, a relatively new technology. It provides remote testing and commissioning services through the web, and it utilizes virtualization to make available computing resources. In order to host and store firm data, cloud computing relies on data centers. Data centers are made up of networked computers, cables, power supplies, and other components. Cloud data centers have always had to prioritise high performance over energy efficiency. The biggest obstacle is finding a happy medium between system performance and energy consumption, namely, lowering energy use without compromising system performance or service quality. These results were obtained using the PlanetLab dataset. In order to implement the strategy we recommend, it is crucial to get a complete picture of how energy is being consumed in the cloud. Using proper optimization criteria and guided by energy consumption models, this article offers the Capsule Significance Level of Energy Consumption (CSLEC) pattern, which demonstrates how to conserve more energy in cloud data centers. Capsule optimization's prediction phase F1-score of 96.7 percent and 97 percent data accuracy allow for more precise projections of future value. [ABSTRACT FROM AUTHOR]

It is challenging to perform path planning tasks in complex marine environments as the unmanned surface vessel approaches the goal while avoiding obstacles. However, the conflict between the two subtarget tasks of obstacle avoidance and goal approaching makes the path planning difficult. Thus, a path planning method for unmanned surface vessel based on multiobjective reinforcement learning is proposed under the complex environment with high randomness and multiple dynamic obstacles. Firstly, the path planning scene is set as the main scene, and the two subtarget scenes including obstacle avoidance and goal approaching are divided from it. The action selection strategy in each subtarget scene is trained through the double deep Q-network with prioritized experience replay. A multiobjective reinforcement learning framework based on ensemble learning is further designed for policy integration in the main scene. Finally, by selecting the strategy from subtarget scenes in the designed framework, an optimized action selection strategy is trained and used for the action decision of the agent in the main scene. Compared with traditional value-based reinforcement learning methods, the proposed method achieves a 93% success rate in path planning in simulation scenes. Furthermore, the average length of the paths planned by the proposed method is 3.28% and 1.97% shorter than that of PER-DDQN and dueling DQN, respectively. [ABSTRACT FROM AUTHOR]

Inspired by the group decision making process, ensembles or combinations of classifiers have been found favorable in a wide variety of application domains. Some researchers propose to use the mixture of two different types of classification algorithms to create a hybrid ensemble. Why does such an ensemble work? The question remains. Following the concept of diversity, which is one of the fundamental elements of the success of ensembles, we conduct a theoretical analysis of why hybrid ensembles work, connecting using different algorithms to accuracy gain. We also conduct experiments on classification performance of hybrid ensembles of classifiers created by decision tree and naïve Bayes classification algorithms, each of which is a top data mining algorithm and often used to create non-hybrid ensembles. Therefore, through this paper, we provide a complement to the theoretical foundation of creating and using hybrid ensembles. [ABSTRACT FROM AUTHOR]

Object tracking based on sparse representation has given promising tracking results in recent years. However, the trackers under the framework of sparse representation always overemphasize the sparse representation and ignore the correlation of visual information. In addition, the sparse coding methods only encode the local region independently and ignore the spatial neighborhood information of the image. In this paper, we propose a robust tracking algorithm. Firstly, multiple complementary features are used to describe the object appearance; the appearance model of the tracked target is modeled by instantaneous and stable appearance features simultaneously. A two-stage sparse-coded method which takes the spatial neighborhood information of the image patch and the computation burden into consideration is used to compute the reconstructed object appearance. Then, the reliability of each tracker is measured by the tracking likelihood function of transient and reconstructed appearance models. Finally, the most reliable tracker is obtained by a well established particle filter framework; the training set and the template library are incrementally updated based on the current tracking results. Experiment results on different challenging video sequences show that the proposed algorithm performs well with superior tracking accuracy and robustness. [ABSTRACT FROM AUTHOR]

Object detection is one of the most critical areas in computer vision, and it plays an essential role in a variety of practice scenarios. However, small object detection has always been a key and difficult problem in the field of object detection. Therefore, considering the balance between the effectiveness and efficiency of the small object detection algorithm, this study proposes an improved YOLOX detection algorithm (BGD-YOLOX) to improve the detection effect of small objects. We present the BigGhost module, which combines the Ghost model with a modulated deformable convolution to optimize the YOLOX for greater accuracy. At the same time, it can reduce the inference time by reducing the number of parameters and the amount of computation. The experimental results show that BGD-YOLOX has a higher average accuracy rate in terms of small target detection, with mAP0.5 up to 88.3% and mAP0.95 up to 56.7%, which surpasses the most advanced object detection algorithms such as EfficientDet, CenterNet, and YOLOv4. [ABSTRACT FROM AUTHOR]

This article proposes a cuckoo algorithm (GFCS) based on the global feedback strategy and innovatively introduces a "re-fly" mechanism. In GFCS, the process of the algorithm is adjusted and controlled by a dynamic global variable, and the dynamic global parameter also serves as an indicator of whether the algorithm has fallen into a local optimum. According to the change of the global optimum value of the algorithm in each round, the dynamic global variable value is adjusted to optimize the algorithm. In addition, we set new formulas for the other main parameters, which are also adjusted by the dynamic global variable as the algorithm progresses. When the algorithm converges prematurely and falls into a local optimum, the current optimum is retained, and the algorithm is initialized and re-executed to find a better value. We define the previous process as "re-fly." To verify the effectiveness of GFCS, we conducted extensive experiments on the CEC2013 test suite. The experimental results show that the GFCS algorithm has better performance compared to other algorithms when considering the quality of the obtained solution. [ABSTRACT FROM AUTHOR]

The computer vision community has taken a keen interest in recent developments in activity recognition and classification in sports videos. Advancements in sports have a broadened the technical interest of the computer vision community to perform various types of research. Images and videos are the most frequently used components in computer vision. There are numerous models and methods that can be used to classify videos. At the same time, there no specific framework or model for classifying and identifying sports videos. Hence, we proposed a framework based on deep learning to classify sports videos with their appropriate class label. The framework is to perform sports video classification using two different benchmark datasets, UCF101 and the Sports1-M dataset. The objective of the framework is to help sports players and trainers to identify specific sports from the large data source, then analyze and perform well in the future. This framework takes sports video as an input and produces the class label as an output. In between, the framework has numerous intermediary processes. Preprocessing is the first step in the proposed framework, which includes frame extraction and noise reduction. Keyframe selection is carried out by candidate frame extraction and an enhanced threshold-based frame difference algorithm, which is the second step. The final step of the sports video classification framework is feature extraction and classification using CNN. The proposed framework result is compared with pretrained neural networks such as AlexNet and GoogleNet, and then the results are also compared. Three different evaluation metrics are used to measure the accuracy and performance of the framework. [ABSTRACT FROM AUTHOR]

With the increasing complexity of users' needs and increasing uncertainty of a single web service in big data environment, service composition becomes more and more difficult. In order to improve the solution accuracy and computing speed of the constrained optimization model, several improvements are raised on ant colony optimization (ACO) and its calculation strategy. We introduce beetle antenna search (BAS) strategy to avoid the danger of falling into local optimization, and a service composition method based on fusing beetle-ant colony optimization algorithm (Be-ACO) is proposed. The model first generates search subspace for ant colony through beetle antenna search strategy and optimization service set by traversing subspace based on ant colony algorithm. Continuously rely on beetle antenna search strategy to generate the next search subspace in global scope for ant colony to traverse and converge to the global optimal solution finally. The experimental results show that compared with the traditional optimization method, the proposed method improves combination optimization convergence performance and solution accuracy greatly. [ABSTRACT FROM AUTHOR]

Automated guided vehicles (AGVs) are popular subsets of robots that come in various shapes and sizes. The group's use in the industry ranges from applications for carrying pallets, carts, and utensils to helping the elderly or transporting medicine to hospitals. Even recently, they have been used in libraries to carry books on shelves. The main part of an AGV includes its body, motor, driver, processor, and sensors, which are more or less the same in all types of AGVs, and addons vary depending on the application and the work environment. The part that affects AGV performance is the control strategy, to which researchers have shown different approaches. Using various techniques and simulations to obtain a model is the key and can help to improve and evaluate the performance of the strategy of the robot. In this study, based on the actual design of the AGV system, all data and components are described, and the simulation is performed in MATLAB software. Then, for controlling the platform based on the PID controller tuning, four methods of Ziegler Nichols, empirical, Particle Swarm Optimization (PSO), and Beetle Antennae Searching (BAS) (optimizer) are discussed, and the results are compared in the four paths including the circle, ellipse, Spiral and 8-shaped paths by observing and testing the tuned PID parameters. Finally, a series of subsequent experiences were carried out in CoppeliaSim (VREP) as a famous robot simulator to overcome the environmental constraints for the same paths that were used in Matlab based on the extracted PID values. Based on the results, the empirical methods, PSO, and BAS errors are very close together. But in general, the BAS algorithm is the fastest, and the PSO had better performance. In general, the maximum error is linked to the path of 8 shapes and the minimum is related to circle shape one. Finally, the analysis of results in different paths in both simulators shows the same results. Therefore, concerning the limited test on the real platform and using the PID coefficients obtained from the simulation shows the model's ability for the researchers in robotic research. [ABSTRACT FROM AUTHOR]

This study proposed an algorithm called selective strategy differential evolution (SSDE) to handle the complexity of the stochastic internal task scheduling problem in cross-docking terminals. The aims of this study are to assign workers and transfer equipment to internal operations and sequence those operations under randomness and uncertainty with the purpose to minimise total tardiness. The main feature of SSDE is its ability to adapt itself in order to execute the best search strategy. The proposed algorithm was tested on 16 instances using generated data based on real-case scenarios of a pharmaceutical distribution centre. The results showed the significant performance of SSDE to other existing algorithms in terms of solution quality and computational time. The key success factors of SSDE are the use of various search strategies in a single run and the application of suitable termination conditions. [ABSTRACT FROM AUTHOR]

Accurate monitoring of fire and smoke plays an irreplaceable role in preventing fires and safeguarding the safety of citizens' lives and property. The network structure of YOLOv5 is simple, but using convolution to extract features will lead to some problems such as limited receptive field, poor feature extraction ability, and insufficient feature integration. In view of the current defects of YOLOv5 target detection algorithm, a new algorithm model named Swin-YOLOv5 was proposed in this work. Swin transformation mechanism was introduced into YOLOv5 network, which enhanced the receptive field and feature extraction ability of the model without changing the depth of the model. In order to enrich the feature map splicing method of weighted Concat and enhance the feature fusion ability of model pairs, the feature splicing method of three output heads of feature fusion layer network was improved. The feature fusion module was further modified, and the weighted feature splicing method was introduced to improve the network feature fusion ability. Experimental results show that the map (average rage accuracy) of this method rises faster than the benchmark algorithm. Under the same experimental dataset, the map of this algorithm is improved by 0.7%, and the high-precision target detection speed is improved by 1.8 FPS (fast packet switch). Under the same experimental dataset, the improved algorithm could more accurately detect the targets that were not detected or detected inaccurately by the original algorithm, which embodied the adaptability of real scene detection and had practical significance. This work provided an opportunity for the application of fire-smoke detection in forest and indoor scenes and also developed a feasible idea for feature extraction and fusion of YOLOv5. [ABSTRACT FROM AUTHOR]

In order to solve the problem of vowel acoustic modeling in the Mongolian language and provide more scientific core technical support for speech recognition system, a vowel acoustic model based on the clustering algorithm and speech recognition technology was proposed. The language vowel recognition system and Mongolian speech recognition system are constructed, the Mongolian vowel acoustic database is mainly designed, and the number of vowel samples is constantly increased to ensure the acoustic and linguistic phenomena that may be encountered in the Mongolian vowel database. At the same time, classification modeling and context modeling are used to improve the accuracy of the acoustic model. Through experiments, it is found that the experimental results of sparse tritones show that the model has the highest recognition accuracy of 45% for sentences and 86% for words, which is more than 2% higher than before, providing some technical support for Mongolian learning and pronunciation. [ABSTRACT FROM AUTHOR]

Semantic segmentation based on deep learning has undergone remarkable advancements in recent years. However, due to the neglect of the shallow features, the problems of inaccurate segmentation have persisted. To address this issue, a semantic segmentation network-attention-based auxiliary extraction and hybrid subsampled network (AAEHS-Net) is suggested in this study. To extract more deep information and the shallow features, the complementary and enhanced extraction module (CEEM) is utilized by the network. As a result, the edge segmentation of the model is improved. Moreover, to reduce the loss of features, a hybrid subsampled module (HSM) is introduced. Meanwhile, global max pool and global avg pool module (GAGM) is designed as an attention module to enhance the features with global and important information and maintain feature continuity. The proposed AAEHS-Net is evaluated on three datasets: the aerial drone image dataset, the Massachusetts roads dataset, and the Massachusetts buildings dataset. On the three datasets, AAEHS-Net achieves 1.15%, 0.88%, and 2.1% higher accuracy than U-Net, reaching 90.12%, 96.23%, and 95.15%, respectively. At the same time, our proposed network has obtained the best values for all evaluation metrics in three datasets compared to the currently popular algorithms. [ABSTRACT FROM AUTHOR]

In many research tasks, the speed and accuracy of flame detection using supply chain have always been a challenging task for many researchers, especially for flame detection of small objects in supply chain. In view of this, we propose a new real-time target detection algorithm. The first step is to enhance the flame recognition of small objects by strengthening the feature extraction ability of multi-scale fusion. The second step is to introduce the K-means clustering method into the prior bounding box of the algorithm to improve the accuracy of the algorithm. The third step is to use the flame characteristics in YOLO+ algorithm to reject the wrong detection results and increase the detection effect of the algorithm. Compared with the YOLO series algorithms, the accuracy of YOLO+ algorithm is 99.5%, the omission rate is 1.3%, and the detection speed is 72 frames/SEC. It has good performance and is suitable for flame detection tasks. [ABSTRACT FROM AUTHOR]

Faced with the upsurge of digital technology, many small and medium-sized startups are aware of the opportunities and challenges it brings and are actively responding to digital transformation. Digital transformation is a type of strategic change with certain risks. On the one hand, this requires business leaders to have a sense of change, and on the other hand, it also requires certain resources to be invested. As a result, in the real world, not all small and medium-sized entrepreneurial firms have the ability or inclination to implement digital transformation. SMEs' digital transformation has become a key factor in promoting the national economy's transition from new and old kinetic energy and providing new prospects for development of small and medium firms. As a starting point, this study devises an index system for assessing the digital maturity of small and medium-sized businesses. Based on the AHP method in the multicriteria framework, a hierarchical structure is established for each index, a three-layer basic framework is established, and the weight of the evaluation index is calculated. Second, this work establishes a BP network model for digital transformation maturity assessment of startups based on AHP and establishes a three-layer BP network structure. This work aims to optimize BP network using the improved ISFLA algorithm. It improves the adaptive step size update formula in the SFLA algorithm by using the mutation operator and improves the evolution method of the worst individual of the frog to the simultaneous evolution of multiple poor individuals. The constructed ISFLA-BP algorithm is then used to evaluate the digital transformation maturity of small and medium-sized startups. Finally, systematic and comprehensive experiments are carried out to verify superiority as well as feasibility of the method. [ABSTRACT FROM AUTHOR]

With the emergence and development of artificial intelligence, design is no longer a process that can be completed only by creativity and knowledge. This article introduces research based on voice data mining and further discusses the optimization and application of rhetorical methods for e-commerce advertising. This article is working from two main aspects: one is to use association rule models in speech data mining to obtain useful rule relationships between Chinese prosody parameters, and the other is to use neural networks and data items in speech data mining. Using computer technology can make online advertisements interact with users. In addition to clicking on advertisements to jump to product pages, online advertisements also have multichannel sensory feelings, which can provide rich information and stimulate interest through interaction with users. We need to optimize the rhetoric of the advertisement and pay attention to the combination of the beauty of speech and the content of the advertisement when designing the advertisement. At the same time, we must also pay attention to the accuracy and elegance of the advertising language and wording. [ABSTRACT FROM AUTHOR]

Semantic feature recognition in colour images is required for identifying uneven patterns in object detection and classification. The semantic features are identified by segmenting the colorimetric sensor array features through machine learning paradigms. Semantic segmentation is a method for identifying distinct elements in an image. This can be considered a task involving image classification at the pixel level. This article introduces a semantic feature-dependent array segmentation method (SFASM) to improve recognition accuracy due to irregular semantics. The proposed method incorporates a deep convolutional neural network for detecting the semantic and un-semantic features based on sensor array representations. The colour distributions per array are identified for horizontal and vertical semantics analysis. In this analysis, deep learning classifies the uneven patterns based on colour distribution, i.e. the consecutive and scattered colour distribution pixels in an array are correlated for their similarity. This similarity identification is maximized through max-pooling and recurrent iterations, preventing detection errors. The proposed method classifies the semantic features for further correlation sections, improving the accuracy. The proposed method's performance is thus validated using the metrics precision, analysis time and F1-Score. [ABSTRACT FROM AUTHOR]

Traditional texture cluster algorithms are frequently used in engineering; however, despite their widespread application, these algorithms continue to suffer from drawbacks including excessive complexity and limited universality. This study will focus primarily on the analysis of the performance of a number of different texture clustering algorithms. In addition, the performance of traditional texture classification algorithms will be compared in terms of image size, clustering number, running time, and accuracy. Finally, the performance boundaries of various algorithms will be determined in order to determine where future improvements to these algorithms should be concentrated. In the experiment, some traditional clustering algorithms are used as comparative tools for performance analysis. The qualitative and quantitative data both show that there is a significant difference in performance between the different algorithms. It is only possible to achieve better performance by selecting the appropriate algorithm based on the characteristics of the texture image. [ABSTRACT FROM AUTHOR]

Due to advancements in scientific research and technological innovation, as well as the proliferation of the Internet of things, the Internet, and big data, the general public has gradually become aware of a new type of intelligent nursing system model known as the smart nursing system. The smart nursing system is a sensing system and information platform for the elderly in their homes, communities, and institutions for elderly care. Based on this, it provides timely, efficient, and cost-effective elderly care services in real time. These services utilize the Internet of things and the Internet as well. Through the monitoring of video data, we are able to differentiate the visual motions of these elderly individuals and determine whether they are in a normal life state or a fall state. This has the potential to better meet the diverse and multifaceted needs of senior citizens, enhance the quality of life of senior citizens in their final years, and provide senior citizens with greater humanistic care and spiritual solace. Our team has developed an intelligent nursing system based on the visual action recognition algorithm, also known as the deep learning (DL) algorithm. As a result of our simulation tests, we discovered that the algorithm can accurately identify the living situations of elderly individuals at home. [ABSTRACT FROM AUTHOR]

Adenomoma is a common disease occurring in the female uterus. The symptoms and pain of adenomoma seriously troubled the physical and mental health of contemporary women. However, because of the significant advantages of nondestructive and low price, ultrasound examination is used as the main imaging method for clinical diagnosis of gynecological diseases at the present stage and is often used in the initial screening and postoperative diagnosis and treatment of uterine diseases. Imaging provides a very rich information in the medical diagnosis of tumor and is a very important basis for the disease diagnosis and treatment at this stage. Ultrasound images are different from medical images such as X-ray and MRI. Because of the characteristics of imaging principles and noise interference, ultrasound images need to rely on rich clinical experience of doctors in the process of disease diseases, which increases the difficulty and work burden of doctors to some extent. Therefore, the project aims to study the deep learning segmentation method suitable for ultrasonic images. Combined with the Deeplab network in the convolutional neural network, comparing the results of the FCN network, and then finding that the Deeplab network has obvious advantages as an image segmentation model of uterine adenomyoma. In clinical practice, it can reduce the work burden of doctors and try in the direction of uterine adenomyomas ultrasound image segmentation, to fill the gap in this field. [ABSTRACT FROM AUTHOR]

Due to the development and application of information technology, a series of modern information technologies represented by 5G, big data, and artificial intelligence are changing rapidly, and people's requirements for video coding standards have become higher. In the High-Efficiency Video Coding (HEVC) standard, the coding block division is not flexible enough, and the prediction mode is not detailed enough. A new generation of Versatile Video Coding (VVC) standards was born. VVC inherits the hybrid coding framework adopted by HEVC, improves the original technology of each module, introduces a series of new coding technologies, and builds on this greatly improving the coding efficiency. Compared with HEVC, the block division structure of VVC has undergone great changes, retaining the quad-tree (QT) division method and increasing the multi-type tree (MTT) division method, which brings high coding complexity. To reduce the computational complexity of VVC coding block division, a fast decision algorithm for VVC intra-frame coding based on texture characteristics and machine learning is proposed. First, we analyze the characteristics of the CU partition structure decision and then use the texture complexity of the CU partition structure decision to terminate the CU partition process early; for CUs that do not meet the early termination of the partition, use the global sample information, local sample information, and context information. The three-category feature-trained tandem classifier framework predicts the division type of CU. The experimental results show that in the full intra mode, compared with the existing VTM10.0, the encoding output bit rate is increased by 1.36%, and the encoding time is saved by 52.63%. [ABSTRACT FROM AUTHOR]

Cracks are one of the most common types of imperfections that can be found in concrete pavement, and they have a significant influence on the structural strength. The purpose of this study is to investigate the performance differences of various spatial clustering algorithms for pavement crack segmentation and to provide some reference for the work that is being done to maintain pavement currently. This is done by comparing and analyzing the performance of complex crack photos in different settings. For the purpose of evaluating how well the comparison method works, the indices of evaluation of NMI and RI have been selected. The experiment also includes a detailed analysis and comparison of the noisy photographs. According to the results of the experiments, the segmentation effect of these cluster algorithms is significantly worse after adding Gaussian noise; based on the NMI value, the mean-shift clustering algorithm has the best de-noise effect, whereas the performance of some clustering algorithms significantly decreases after adding noise. [ABSTRACT FROM AUTHOR]

This study provides an in-depth analysis and research on multimedia fusion privacy protection algorithms based on IoT data security in a network regulation environment. Aiming at the problem of collusion and conspiracy to deceive users in the process of outsourced computing and outsourced verification, a safe, reliable, and collusion-resistant scheme based on blockchain is studied for IoT outsourced data computing and public verification, with the help of distributed storage methods, where smart devices encrypt the collected data and upload them to the DHT for storage along with the results of this data given by the cloud server. After testing, the constructed model has a privacy-preserving budget value of 0.6 and the smallest information leakage ratio of multimedia fusion data based on IoT data security when the decision tree depth is 6. After using this model under this condition, the maximum value of the information leakage ratio of multimedia fusion data based on IoT data security is reduced from 0.0865 to 0.003, and the data security is significantly improved. In the consensus verification process, to reduce the consensus time and ensure the operating efficiency of the system, a consensus node selection algorithm is proposed, thereby reducing the time complexity of the consensus. Based on the smart grid application scenario, the security and performance of the proposed model are analyzed. This study proves the correctness of this scheme by using BAN logic and proves the security of this scheme under the stochastic prediction machine model. Finally, this study compares the security aspects and performance aspects of the scheme with some existing similar schemes and shows that the scheme is feasible under IoT. [ABSTRACT FROM AUTHOR]

The click-through rate (CTR) prediction task is used to estimate the probabilities of users clicking on recommended items, which are extremely important in recommender systems. Recently, the deep factorization machine (DeepFM) algorithm was proposed. The DeepFM algorithm incorporates a factorization machine (FM) to learn not only low-order features but also the interactions of higher-order features. However, DeepFM lacks user diversity representations and does not consider the text. In view of this, we propose a text-attention FM (TAFM) based on the DeepFM algorithm. First, the attention mechanism in the TAFM algorithm is used to address the diverse representations of users and goods and to mine the features that are most interesting to users. Second, the TAFM model can fully learn text features through its text component, text attention component, and N-gram text feature extraction component, which can fully explore potential user preferences and the diversity among user interests. In addition, the convolutional autoencoder in the TAFM can learn some higher-level features, and the higher-order feature mining process is more comprehensive. On the public dataset, the better performing models in the existing models are deep cross network (DCN), DeepFM, and product-based neural network (PNN), respectively, and the AUC score metrics of these models hover between 0.698 and 0.699. The AUC score of our design model is 0.730, which is at least 3% higher than that of the existing models. The accuracy metric of our model is at least 0.1 percentage points higher than that of existing models. [ABSTRACT FROM AUTHOR]

To enhance the visualization effect of substation high-voltage electrical equipment vulnerability, this study proposes an ISSA-LSTM coupled video overlay algorithm-based substation high-voltage electrical equipment vulnerability visualization and monitoring model. Using the improved α blending algorithm combined with the inverse sampling of video background color, overlaying visible video as well as infrared video, using the improved adaptive weighted two-dimensional principal component analysis (W2DPCA) to fuse the base layer, selecting the detail layer as the final detail layer, obtaining the final fusion frame, and realizing the visualization and monitoring of substation high-voltage electrical equipment vulnerability, and introducing the improved sparrow search algorithm (ISSA) to establish long and short-term memory network prediction model to reduce the prediction error and improve the monitoring accuracy rate. The experimental results show that the monitoring frames obtained by this method can reflect rich details of substation high-voltage electrical equipment, and the texture color and equipment edge contrast are enhanced to facilitate accurate determination of substation high-voltage electrical equipment vulnerability, and the prediction accuracy of ISSA-LSTM model is as high as 99.85%. [ABSTRACT FROM AUTHOR]

Aiming to solve the problems of low fault tolerance, low throughput, and high delay in traditional methods, an improved method of the blockchain cross-chain consensus algorithm based on weighted PBFT is proposed. This article constructs a blockchain cross-chain exchange model based on cluster centers and divides the nodes in the blockchain system into consensus service nodes, cross-chain exchange nodes, and application nodes to improve the performance of consensus computing services. On this basis, according to the weighted PBFT consensus mechanism, the blockchain consensus environment is set up, and the distribution of nodes in the consensus domain and the blockchain signature scheme are obtained. Therefore, the blockchain cross-chain consensus optimization algorithm is designed to reduce throughput and delay and optimize the consensus effect. The experimental results show that the proposed method can effectively improve the shortcomings of traditional methods, with high throughput and low latency, and strong security. It shows that it is a low resource consumption and secure consensus method. [ABSTRACT FROM AUTHOR]

One of the important and challenging tasks in cloud computing is to obtain the usefulness of cloud by implementing several specifications for our needs, to meet the present growing demands, and to minimize energy consumption as much as possible and ensure proper utilization of computing resources. An excellent mapping scheme has been derived which maps virtual machines (VMs) to physical machines (PMs), which is also known as virtual machine (VM) placement, and this needs to be implemented. The tremendous diversity of computing resources, tasks, and virtualization processes in the cloud causes the consolidation method to be more complex, tedious, and problematic. An algorithm for reducing energy use and resource allocation is proposed for implementation in this article. This algorithm was developed with the help of a Cloud System Model, which enables mapping between VMs and PMs and among tasks of VMs. The methodology used in this algorithm also supports lowering the number of PMs that are in an active state and optimizes the total time taken to process a set of tasks (also known as makespan time). Using the CloudSim Simulator tool, we evaluated and assessed the energy consumption and makespan time. The results are compiled and then compared graphically with respect to other existing energy-efficient VM placement algorithms. [ABSTRACT FROM AUTHOR]