speed and accuracy
Recently Published Documents


TOTAL DOCUMENTS

1378
(FIVE YEARS 524)

H-INDEX

54
(FIVE YEARS 13)

10.29007/qz2g ◽  
2022 ◽  
Author(s):  
Sy Hieu Dau ◽  
Quang My Han Doan ◽  
Chiu Hy Ta ◽  
Nguyen An Khang Le ◽  
Nguyen Thanh Dat Khau

In the industrial context, there are key factors that directly affect the system’s efficiency. Higher demands for both quantity and quality in today’s market call for constant research and development of technologies for automating production and quality control. Machine vision is a solution to increase speed and accuracy in defect detection. However, applications from machine vision are only effective if there is good data input. This is the reason why a machine vision system, needs high-quality input images from a well-designed illumination system. These illumination systems are designed to highlight faults in products. Therefore, the images obtained will provide optimized data for easier image processing thus directly increase the processing speed, accuracy, and overall system performance. To achieve this goal, this paper presents a few approaches to enhance and optimize images by implements illumination techniques into a miniature model of pharmaceutical bottle assembly line using machine vision as the inspector block. In this paper, we will evaluate the critical needs of using customize illumination system for quality inspection on an assembly line.


Biology ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 104
Author(s):  
Elisa F. D. Canetti ◽  
Scott Gayton ◽  
Ben Schram ◽  
Rodney Pope ◽  
Robin M. Orr

Firefighters work in strenuous conditions for prolonged periods wearing up to 20 kg of personal protective equipment. This often contributes to significant heat and cardiovascular strain. This study examined the relationships between psychological and physical measures taken prior to undertaking a 15 min firefighting task, and the occurrence of heat stress and high levels of fatigue following the task. Nine qualified firefighters completed a 15 min “live burn” scenario designed to mimic a fire started by a two-seater couch in a lounge room and completed simulated tasks throughout the duration. Logical reasoning, speed and accuracy, general motivation and fatigue, and physical and mental effort were recorded pre-scenario, and at 0- and 20-min post-scenario. General motivation and fatigue scores at 0- and 20-min post-scenario were highly correlated with each other (rs = 0.90; p = 0.001). The general motivation and fatigue scores, at 0- and 20-min post-scenario, were also strongly related to pre-task logic/reasoning test scores (Post 0 rs = −0.77, p = 0.016; Post 20 rs = −0.87, p = 0.002). Firefighters with lower logical reasoning and speed and accuracy scores were more susceptible to fatigue and impaired cognition when exposed to rises in core temperature and heat stress.


Author(s):  
Shanshan Yang ◽  
Jinjin Chao

Nowadays, there are too many large-scale speech recognition resources, which makes it difficult to ensure the scheduling speed and accuracy. In order to improve the effect of large-scale speech recognition resource scheduling, a large-scale speech recognition resource scheduling system based on grid computing is designed in this paper. In the hardware part, microprocessor, Ethernet control chip, controller and acquisition card are designed. In the software part of the system, it mainly carries out the retrieval and exchange of information resources, so as to realize the information scheduling of the same type of large-scale speech recognition resources. The experimental results show that the information scheduling time of the designed system is short, up to 2.4min, and the scheduling accuracy is high, up to 90%, in order to provide some help to effectively improve the speed and accuracy of information scheduling.


2022 ◽  
Vol 2022 ◽  
pp. 1-12
Author(s):  
Hengliang Chen ◽  
Zilin Li ◽  
Fei Luo

To provide a basic quantitative mathematical model for data analysis, decision-making support, and application of information systems oriented to emergency research, this paper established an information transmission response model for school students under such system mathematically based on actual school information transmission data during COVID-19 prevention. This paper proposes an emergency information management method—a two-step emergency information management method. It can be referenced for promotion of the development of IT-based school management, enhancement of IT application in school emergency information management, and improvement of the speed and accuracy of information transmission.


2022 ◽  
Vol 17 (01) ◽  
pp. C01015
Author(s):  
A. Samalan ◽  
S. Basnet ◽  
L. Bonechi ◽  
L. Cimmino ◽  
R. D’Alessandro ◽  
...  

Abstract The MUon RAdiography of VESuvius (MURAVES) project aims at the study of the summital cone of Mt. Vesuvius, an active volcano near Naples (Italy), by measuring its density profile through muon flux attenuation. Its data, combined with those from gravimetric and seismic measurement campaigns, will be used for better defining the volcanic plug at the bottom of the crater. We report on the development of an end-to-end simulation framework, in order to perform accurate investigations of the effects of the experimental constraints and to compare simulations, under various model hypotheses, with the actual observations. The detector simulation setup is developed using GEANT4 and a study of cosmic particle generators has been conducted to identify the most suitable one for our simulation framework. To mimic the real data, GEANT4 raw hits are converted to clusters through a simulated digitization: energy deposits are first summed per scintillator bar, and then converted to number of photoelectrons with a data-driven procedure. This is followed by the same clustering algorithm and same tracking code as in real data. We also report on the study of muon transport through rock using PUMAS and GEANT4. In this paper we elaborate on the rationale for our technical choices, including trade-off between speed and accuracy. The developments reported here are of general interest in muon radiography and can be applied in similar cases.


2022 ◽  
Author(s):  
Maik Bieleke ◽  
Eve Legrand ◽  
Astrid Mignon ◽  
Peter M Gollwitzer

Forming implementation intentions (i.e., if-then planning) is a powerful self-regulation strategy that enhances goal attainment by facilitating the automatic initiation of goal-directed responses upon encountering critical situations. Yet, little is known about the consequences of forming implementation intentions for goal attainment in situations that were not specified in the if-then plan. In three experiments, we assessed goal attainment in terms of speed and accuracy in an object classification task, focusing on situations that were similar or dissimilar to critical situations and required planned or different responses. The results of Experiments 1 and 3 provide evidence for a facilitation of planned responses in critical and in sufficiently similar situations, enhancing goal attainment when the planned response was required and impairing it otherwise. In Experiment 3, additional unfavorable effects however emerged in situations that were dissimilar to the critical one but required the planned response as well. We discuss theoretical implications as well as potential benefits and pitfalls emerging from these non-planned effects of forming implementation intentions.


2022 ◽  
Vol 355 ◽  
pp. 02054
Author(s):  
Sijun Xie ◽  
Yipeng Zhou ◽  
Iker Zhong ◽  
Wenjing Yan ◽  
Qingchuan Zhang

In the industrial area, the deployment of deep learning models in object detection and tracking are normally too large, also, it requires appropriate trade-offs between speed and accuracy. In this paper, we present a compressed object identification model called Tailored-YOLO (T-YOLO), and builds a lighter deep neural network construction based on the T-YOLO and DeepSort. The model greatly reduces the number of parameters by tailoring the two layers of Conv and BottleneckCSP. We verify the construction by realizing the package counting during the input-output warehouse process. The theoretical analysis and experimental results show that the mean average precision (mAP) is 99.50%, the recognition accuracy of the model is 95.88%, the counting accuracy is 99.80%, and the recall is 99.15%. Compared with the YOLOv5 combined DeepSort model, the proposed optimization method ensures the accuracy of packages recognition and counting and reduces the model parameters by 11MB.


2022 ◽  
Vol 2160 (1) ◽  
pp. 012078
Author(s):  
Xinhai Li ◽  
Haixin Luo ◽  
Lingcheng Zeng ◽  
Chenxu Meng ◽  
Yanhe Yin

Abstract Currently, the check of the relay protection pressure plate’s throw-out status is mainly carried out manually, due to the extremely large number of decompression plates, manual methods can cause detection errors due to fatigue. This paper proposes the processing of relay protection pressure plate photographs by using image processing techniques, the Faster R-CNN image recognition algorithm uses the feature of generating detection frames directly using RPN to identify the platen throwback status of the processed platen images, greatly improving the speed and accuracy of the detection frame generation. The experimental results show that, the method proposed in this paper effectively solves the problem of errors arising from manual verification checks of platen throwbacks, reduced workload for substation staff, the platen recognition rate can be over 98% correct.


2021 ◽  
Vol 4 (4) ◽  
Author(s):  
Maria Elide Vanutelli ◽  
◽  
Giulia Pirovano ◽  
Chiara Esposto ◽  
Claudio Lucchiari

Mathematics, being a very ancient discipline, is usually seen as a formal subject that must be learned for school purposes, which is very far from creativity and fun. Also, mathematical skills are often considered a talent, so students are easily divided into gifted and not gifted, with a focus on speed and accuracy rather than encouraging the process of juggling between divergent and convergent thinking. In the present paper, we aimed at investigating the relationship between mathematical reasoning and different aspects of creative thinking, such as divergent and convergent creativity, aesthetic appreciation, and humor. To do so, 146 second and third graders in a primary school in Milan have been recruited and tested with mathematical and creative tasks. Correlational analyses showed significant positive relations between flexibility and originality dimensions of creativity and mathematical performance. Results are discussed by providing a theoretical framework about the relation between mathematics and creative skills.


2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yangyang Tian ◽  
Wandeng Mao ◽  
Shaoguang Yuan ◽  
Diming Wan ◽  
Yuanhui Chen

The traditional image object detection algorithm applied in power inspection cannot effectively position power components, and the accuracy of recognition is low in scenes with some interference. In this research, we proposed a data-driven power detection method based on the improved YOLOv4-tiny model, which combined the ResNet-D module and the adjusted Res-CBAM to the backbone network of the existing YOLOv4-tiny module. We replaced the CSPOSANet module in the YOLOv4-tiny backbone network with the ResNet-D module to reduce the FLOPS required by the model. At the same time, the adjusted Res-CBAM whose feature fusion ways were replaced with stacking in the channels was combined as an auxiliary classifier. Finally, the features of five different receptive scales were used for prediction, and the display of the results was optimized by merging the prediction boxes. In the experiment, 57134 images collected on the power inspection line were processed and labeled, and the default anchor boxes were re-clustered, and the speed and accuracy of the model were evaluated by video and validation set of 3459 images. Processing multiple pictures and videos collected from the power inspection projects, we re-clustered the default anchor box and tested the speed and accuracy of the model. The results show that compared with the original YOLOv4-tiny model, the accuracy of our method that can position objects under occlusion and complex lighting conditions is guaranteed while the detection speed is about 13% faster.


Sign in / Sign up

Export Citation Format

Share Document