Abstract Metal additive manufacturing (AM) technologies have made significant progress in the basic theoretical field since their invention 1970s. However, performance instability during continuous processing, such as thermal history, residual stress accumulation, and columnar grain epitaxial growth, consistently hinders broad application standardized industrial production. To overcome these challenges, performance-control-oriented hybrid AM (HAM) been introduced. These technologies, by...

Traditional training algorithms in artificial neural networks (ANNs) show some inherent weaknesses, such as the possibility of falling into local optimum, slow learning speed, and inability to determine optimal neuronal structure. To remedy deficiencies traditional networks, this paper proposes a novel network classifier (NNC) using beetle antennae search (BAS) algorithm, termed BASNNC. The BAS algorithm is explored optimize weights NNC. proposed BASNNC adopts three-layer structure,...

As the volume of data available for analysis grows, feature selection is becoming a vital part ensuring accurate classification results. In problems, selecting small number features reduces computational complexity, but right important to maintain high level accuracy. this paper, we present method based on hybrid improved quantum-behavior particle swarm optimization, called HI-BQPSO. The HI-BQPSO combines filtering with an optimization algorithm greatly reduce dimensionality so as overcome...

Particle swarm optimization (PSO) has attracted many researchers interested in dealing with various problems, owing to its easy implementation, few tuned parameters, and acceptable performance. However, the algorithm is trap local optima because of rapid losing population diversity. Therefore, improving performance PSO decreasing dependence on parameters are two important research hot points. In this paper, we present a human behavior-based PSO, which called HPSO. There remarkable...

Recent research has shown that neural network techniques can be used successfully for ground rainfall estimation from radar measurements. The is a nonparametric method representing the relationship between measurements and rate. derived directly dataset consisting of rain gauge effectiveness by using networks influenced many factors such as representativeness sufficiency training dataset, generalization capability to new data, season change, location so on. In this paper, novel scheme...

Industrial Automation (IA) and Artificial Intelligence (AI) need an integrated platform. Due to the uncertainty of time required for training or reasoning tasks, it is difficult ensure real-time performance AI in factory. Thus this paper, we carry out a detailed survey on cloud-edge computing-based Cyber Intelligent Control Operating System (ICICOS) industrial automation artificial intelligence. The ICICOS built based IEC61499 programming method used replace obsolete Programmable Logic...

Insufficient illumination makes driver face detection at night challenging. This paper proposes an adaptive attenuation quantification retinex (AAQR) method to enhance the details of nighttime images. There are three phases in this method: restriction, prediction, and quantification. The performance proposed was evaluated by employing a robust via sparse representation. collected images were categorized into groups (up-down, left-right, mixed) according distribution each image. Results have...

Abstract Hierarchical quantum state sharing (HQSTS) provides a way for the from one party to another among multiple parties asymmetrically. In process, it is necessary ensure legitimacy and authenticity of participants defend against attacks caused by neglecting authentication. Hence, we propose three-phase probabilistic HQSTS protocol with identity Firstly, verified in authentication phase, which effectively prevents impersonation deception. Secondly, sender Alice sends target three agents...

The idea of using a one-time-one-key design has been widely applied in conventional cryptography. With the security theory cryptology, encryption algorithms are made public while all secrets encoded only keys. This paper applies chaos to cryptography develop one-time-one-algorithm design. A general is given generate clock key, substitution box, permutation box and operational sign functions for scheme. scheme then implemented system manage tradeoff between speed algorithm.

This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets, which unrealistically assume that each image should contain at least one clear uncluttered object. has led to saturation in performance for state-of-the-art SOD models when evaluated on datasets. However, these are still far from satisfactory applied real-world scenes. Based our analyses, we propose new high-quality dataset update the previous saliency benchmark. Specifically,...

Ground-based remote observation systems are vulnerable to atmospheric turbulence, which can lead image degradation. While some methods mitigate this turbulence distortion, many have issues such as long processing times and unstable restoration effects. Furthermore, the physics of is often not fully integrated into reconstruction algorithms, making their theoretical foundations weak. In paper, we propose a method for mitigation using optical flow convolutional neural networks (CNN). We first...

An operational radar rainfall estimation system based on the adaptive radial basis function (RBF) neural network is developed. During process of training and cross validation, was computed only at gauge locations. Once done, networks applied to full coverage area radar. Such large-scale application estimate poses several questions in context applications. This letter addresses two those questions, namely: 1) feasibility adaptively updating RBF models a daily 2) ability high spatial...

Particle Swarm Optimisation (PSO) is a population-based stochastic optimisation algorithm. The most important advantages of the PSO are that easy to implement and there few parameters adjust, but get trapped in local optimum. In this paper, premature convergence standard investigated based on Markov chain. First, according difference model algorithm, particle state sequence swarm defined one-step transition probability introduced; it shown all chains their properties analysed. Second, for...

In recent years, Deep Learning has promoted the rapid development of artificial intelligence and penetrated into various fields, but massive data transmission Artificial Intelligence (AI) training in network will affect real-time performance system. As is known to all, very important industrial field, especially motion control. If system responding slowly, it cannot receive or send acquisition control commands on time. Finally, this hinder popularization AI technology field automation....

This letter presents a novel multi-robot task allocation and path planning method that considers robots' maximum range constraints in large-sized workspaces, enabling robots to complete the assigned tasks within their limits. Firstly, we developed fast planner solve global paths efficiently. Subsequently, propose an innovative auction-based approach integrates our into auction phase for reward computation while considering accounts extra obstacle-avoiding travel distances rather than ideal...

This work investigates the manufacturing operations of focal firms to manage enhancement environmental sustainability (EnS). To achieve this, indirect and direct effects operational transparency (OPT) sustainable (SUP) between business practices (EBPr) EnS are proposed. By leveraging resource-based view theory, this study seeks clarify how integrating can enhance a firm’s ability challenges effectively. Aligning with concepts appears be an appropriate choice for sustainability. A...

With the development of society and economy, more high buildings large mansions come forth, it is imperative to seek an automatic patrol solution. The a mobile robot platform presented in this paper, which includes basic design principles, mechanical design, motion control, sensors system implementation modular software design. hardware equipped with two differential driven wheels including shaft encoders for tracking. also contained several ultrasonic obstacle detection avoidance. A couple...