Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban scenarios, existing algorithms suffer from low rates high false positives, as well general problem slow speed in industrial applications. This paper proposes i-YOLOX model for domestic based on deep learning algorithms. First, large number real-life images are collected into new image dataset. Second, lightweight operator involution incorporated feature extraction...

This study aimed to enhance the real-time performance and accuracy of vigilance assessment by developing a hidden Markov model (HMM). Electrocardiogram (ECG) signals were collected processed remove noise baseline drift. A group 20 volunteers participated in study. Their heart rate variability (HRV) was measured train parameters modified for assessment. The data using Baum-Welch algorithm obtain state transition probability matrix A^ observation B^. Finally, three with different patterns...

Embodied artificial intelligence (AI) tasks shift from focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual navigation using deep reinforcement learning (DRL) in indoor scenes, whose task aims train an agent can intelligently make a series of decisions arrive at pre-specified target location any possible starting positions only based egocentric views. However, most methods...

Defect-rich photocatalytic materials with excellent charge transfer properties are very popular. Herein, Sm-doped CeO2 nanorods were annealed in a N2 atmosphere to obtain the defective photocatalysts (Vo-Sm-CeO2). The morphology and structure of Vo-Sm-CeO2 systematically characterized. demonstrated an photodegradation performance methyl blue under visible light irradiation compared Sm-CeO2. Reactive oxygen species including OH, ·O2-, h+ confirmed play pivotal role removal pollutants via...

In this study, a personal acoustic comfort prediction model (PACPM) for exploring the of oceanauts in deep-sea manned submersible cabin was proposed, and an oceanauts' task performance (OTPM) constructed study. Based on performance, change characteristics six different pure-noise environments (the sound pressure levels noise audio are 40 dB (A), 45 50 55 60 65 (A) respectively) were analysed. An effective method improving proposed. According to analysis, at dB(A) higher than that other...

We describe a new fusion method for time-frequency distribution (TFD) that increases the ability to detect and classify time-varying signals while suppressing signal-dependent artifacts noise. This is achieved by applying least-squares algorithm estimate second-order approximation Volterra series coefficients of outputs selected TFDs. These are used TFDs generate TFD. The proposed compared with four other methods in terms resolution signal-to-noise ratio (SNR) (TF) plane. Five representative...

In the development of product design, one elements market competition for products is to meet Kansei needs users. Compared features, users pay more attention whether can match their emotions, which needs. The developers are eager get accurately and conveniently. This paper takes computer cloud platform as carrier based on collaborative filtering algorithm. We used personalized double matrix recommendation algorithm core, adjectives dimensionality reduction method filter image tags simplify...

Lighting in aircraft cabin is an important part of the interior lighting system. A reasonable design can improve quality flight services and enhance passenger satisfaction comfort. In this paper, method proposed based on DIALux calculation simulation software. Based a quantitative evaluation, calibration analysis average illuminance, glare uniformity illuminance from perspectives travel safety, visual comfort high service, explores proposes innovative approach to lighting. Finally, method,...

Abstract In traditional computer-aided design methods for manned submersible control panel layout, interactive input and modification are commonly used, which can’t support a global optimization process the layout. Therefore, genetic-ant algorithm is introduced into of layouts. Based on cognitive characteristics humans, layout principles summarized incorporated objective function variables during process. The fitness function, pheromone, heuristic information expressions optimizing...

Filtering image by eliminating irrelevant details as could possible while preserving structure edge and corner becomes very important in the fields such processing computer vision etc. In this paper, we present an Anisotropic Rolling Filter (ARF) for smoothing corner. The proposed filter implements extended cross bilateral filter, which range weights are updated iterative manner, spatial Gaussian computed anisotropic directions instead of isotropic directions. based on tensors calculated at...

Virtual Reality (VR) produces a highly realistic simulation environment to engage users with Immersive Environments (IVEs). To interact effectively users, VR builds intensive media through the multi-modal sense functions in lower level, such as visual, auditory, tactile, and olfactory senses. However, higher-level perceptions, e.g., temporal duration, of presence, cognitive load are less explored. These perceptions part critical evaluation criteria for design. In this paper, we divide...

In order to reduce the probability of human error in cockpit a civil aircraft, based on SHEL model, this paper classifies performance shaping factors (PSF) that affect factor reliability human-machine interface. Then it constructs relevant PSF system and uses interpretation structure model establish corresponding adjacency matrix. When multi-level recursive is obtained, Noisy-OR introduced construct Bayesian network, thus establishing new interface evaluation method. Real cases are used...

Bi 2 MoO 6 /BiOI composites were synthesized by solvothermal method and photocatalytic performances evaluated degrading methylene blue (MB). Experiment results show that /0.5BiOI has the best efficiency for eliminating 92% MB in h under excitation of visible light. Such superior performance is due to significantly enhanced ability absorb light separated photogenerated electrons holes.

Human motion is a key function to communicate information. In the application, short-form mobile video so popular all over world such as Tik Tok. The users would like add more VFX pursue creativity and personlity. Many special effects are added on short platform. These gives possibility show off these personality. common traditional way create template of VFX. However, in order synthesis perfect, have tedious attempt grasp timing rhythm new templates. It not easy-to-use especially for app....