A self-driving car is a hot research topic in the field of intelligent transportation system, which can greatly alleviate traffic jams and improve travel efficiency. Scene classification one key technologies cars, provide basis for decision-making cars. In recent years, deep learning-based solutions have achieved good results problem scene classification. However, some problems should be further studied methods, such as how to deal with similarities among different categories differences...

Self-driving cars are a hot research topic in science and technology, which has great influence on social economic development. Deep learning is one of the current key areas field artificial intelligence research. It been widely applied image processing, natural language understanding, so on. In recent years, more deep learning-based solutions have presented self-driving achieved outstanding results. This paper presents review theories applications for cars. survey provides detailed...

High-voltage circuit breakers (HVCBs) play an important role in power systems, which can control and ensure the grids are working properly. Real-time fault diagnosis of HVCBs is essential issue for systems. In this paper, a novel approach based on adaptive kernel principal component analysis (KPCA) support vector machine (SVM) proposed real-time HVCBs. approach, sample reduction algorithm similarity degree function to analyze between samples, redundant data be eliminated. An KPCA method used...

Multiple robot cooperation is a challenging and critical issue in robotics. To conduct the cooperative hunting by multirobots unknown dynamic environments, robots not only need to take into account basic problems (such as searching, path planning, collision avoidance), but also cooperate order pursue catch evaders efficiently. In this paper, novel approach based on bioinspired neural network proposed for real-time multirobots, where locations of environment are changing. The used pursuing...

With the rapid development of object detection technology for unmanned aerial vehicles (UAVs), it is convenient to collect data from UAV photographs. They have a wide range applications in several fields, such as monitoring, geological exploration, precision agriculture, and disaster early warning. In recent years, many methods based on artificial intelligence been proposed detection, deep learning key area this field. Significant progress has achieved deep-learning-based detection. Thus,...

The indoor scene object detection technology is of important research significance, which one the popular topics in field understanding for robots. In recent years, solutions based on deep learning have achieved good results detection. However, there are still some problems to be further studied methods, such as lighting problem and occlusion caused by complexity environment. Aiming at these problems, an improved method neural networks proposed this article, uses a framework similar...

Autonomous localization and navigation, as an essential research area in robotics, has a broad scope of applications various scenarios. To widen the utilization environment augment domain expertise, simultaneous mapping (SLAM) underwater environments recently become popular topic for researchers. This paper examines key SLAM technologies vehicles provides in-depth discussion on background, existing methods, challenges, application domains, future trends SLAM. It is not only comprehensive...

Real-time path planning for autonomous underwater vehicle (AUV) is a very difficult and challenging task. Bioinspired neural network (BINN) has been used to deal with this problem its many distinct advantages: that is, no learning process needed realization also easy. However, there are some shortcomings when BINN applied AUV in three-dimensional (3D) unknown environment, including complex computing the environment large repeated size of obstacles bigger than detection range sensors. To...

Underwater dam crack detection and classification based on visible images is a challenging task. The underwater environment very complex with uneven illumination serious noise problems, which often leads to the distortion of detection. In addition, there are few methods suitable for classification. To solve these novel approach proposed. Firstly, dodging algorithm used eliminate in images. Subsequently, proposed, where local characteristics image blocks global connected domains both analysis...

Unmanned Aerial Vehicle (UAV) has been widely used in a variety of application, and the target search is one hot issues UAV research fields. Compared with single UAV, multi-UAV system can be competent for more complex tasks, higher execution efficiency stronger robustness. However, there exist some new challenges cooperative search, such as collaborative control area covering problems. To complete these tasks efficiently, problem modeled potential game, modified binary log linear learning...

Small object detection for unmanned aerial vehicle (UAV) image scenarios is a challenging task in the computer vision field. Some problems should be further studied, such as dense small objects and background noise high-altitude photography images. To address these issues, an enhanced YOLOv8s-based model detecting presented. The proposed incorporates parallel multi-scale feature extraction module (PMSE), which enhances capability by generating adaptive weights with different receptive fields...

A slag flow submodel has been developed to simulate the and phase transformation behaviors in coal gasifiers. The volume of fluid (VOF) model is used capture free surface flow, continuum force (CSF) employed calculate tension between gas liquid phase. treated as a Newtonian when temperature above critical viscosity (Tcv), plastic (Tf) Tcv. ash particle deposition, viscosity−temperature dependence, different thermal conductivity for are all included present simulation. For membrane wall...

In a slagging combustion system, some of ash/slag generated through the solid fuels is molten and adheres to tube surfaces or refractory wall during operation. A submodel for predicting slag droplet deposition in systems has been developed. The maximum spread diameter excess rebound energy have defined applied establish criterion. solidification also considered when impacts low-temperature surface, such as membrane surface. effect viscosity, surface tension, particle impact angle, velocity...

Water environment system is a complex system, and an agent-based model presents effective approach that has been implemented in water resource management research. Urban optimal allocation challenging critical issue systems, which belongs to the problem. In this paper, novel based on multiagent Q-learning proposed deal with approach, users of different regions city are abstracted into model. To realize cooperation among these stakeholder agents, maximum mapping value function-based algorithm...

Support vector regression (SVR) is one of the most powerful and widely used machine learning algorithms regarding prediction. The kernel type, penalty factor other parameters influence efficiency performance SVR deeply. optimization these held a hot issue. In this work, we propose based prediction approach using henry gas solubility algorithm (HGSO), which recent meta-heuristic inspired by Henry's law. First, are randomly generated in some certain ranges to form parameter population. Second,...

Autonomous robots are a hot research subject within the fields of science and technology, which has big impact on social-economic development. The ability autonomous robot to perceive understand its working environment is basis for solving more complicated issues. In recent years, an increasing number artificial intelligence-based methods have been proposed in field scene understanding robots, deep learning one current key areas this field. Outstanding gains attained based learning. Thus,...

Underwater organisms are an important part of the underwater ecological environment. More and more attention has been paid to perception environment by intelligent means, such as machine vision. However, many objective reasons affect accuracy biological detection, low-quality image, different sizes or shapes, overlapping occlusion organisms. Therefore, this paper proposes detection algorithm based on improved Faster-RCNN. Firstly, ResNet is used backbone feature extraction network Then,...

The low-light image enhancement is a challenging and hot research issue in the processing field. In order to enhance quality of images obtain full structure details, many algorithms have been proposed deep learning-based methods achieved great success this However, most learning require paired training data, which difficult obtain. And overall visual enhanced still not very satisfying. To deal with these problems, an unsupervised model based on improved Cycle-Consistent Generative...

Based on the situation of Guiyang’s water resources, society, economy, ecology, etc., a comprehensive evaluation index system resources carrying capacity is established by selecting appropriate indexes. analytic hierarchy process (AHP) and entropy method, an model constructed. The results showed that value in Guiyang City increased nearly 53% from 2009 to 2018, regulation control force pressure upward trend. Within ten years, total 0.4503—close H2 level—and membership degree over years...