We gratefully thank Wuhan Urban Construction Group 2023 Annual Scientific Research Project (NO.7) for funding this work.

1. Concrete sample image acquisition
<ol>
	<li>Transport concrete to the workplace, where it will be poured by the pump truck.</li>
	<li>To capture images, switch on the shooting equipment by moving the power key switch to the right and turning it to the ON position. Adjust the camera&#39;s mode knob to the green automatic mode, ensuring the camera lens is parallel to the concrete surface, and press the Shutter Key. Capture 20 image samples of non-vibrated concrete, saving them in .jpg format with an acquisition resolution of 1024 x 1024 pixels, as illustrated in Figure 1.</li>
	<li>Insert the vibrating part of the concrete vibration equipment (plug-in concrete vibrating rod) into the concrete. Connect the power supply, and then switch on the concrete vibration equipment by setting it to the ON position.</li>
	<li>When there is some collapse on the surface of the concrete (caused by the vibration discharging air inside the concrete, leading to the sinking of surface aggregates to fill the gaps, resulting in concrete collapse) and some cement slurry appears, keep the camera lens parallel to the concrete surface and press the Shutter Key. Collect 20 image samples of vibrating concrete, as shown in Figure 2.</li>
	<li>Continue operating the vibration equipment. When there is no obvious collapse on the concrete surface, no cement slurry appears, and no bubbles are generated, stop the vibration process, and capture 20 image samples of vibrated concrete, as shown in Figure 3.</li>
</ol>
2. Sample image gray binarization
<ol>
	<li>Utilize the imread() function of MATLAB software to read the .jpg file as the unit format data of 1024 pixels x 1024 pixels x 3 color channels, representing the red, green, and blue channel values of the image.</li>
	<li>Next, apply the MATLAB function rgb2gray to convert the image to grayscale, denoted by the format gray value = rgb2gray(jpg file name). Calculate the gray value of each pixel according to Equation (1), and save the gray value as the unit8 format data of 1024 x 1024. 
	GR(i,j) = 0.2989R(i,j) + 0.587G(i,j) + 0.114B(i,j)&#160; &#160; (1) 
	where, GR(i,j) is the gray value of the pixel point, R(i,j)&#160;is the red channel value of the pixel point, G(i,j) is the green channel value of the pixel point, and B(i,j)&#160; is the blue channel value of the pixel point.</li>
	<li>Alter the binary value of the gray values greater than the pixel threshold &#952; to 1 and set the binary value of the gray values less than the &#952; pixel to 0.</li>
	<li>After obtaining the binarized gray results, save the outcome as 1024 x 1024 logical format data. In this case, &#952; represents the binarization threshold, and its values are 50, 100, 150, and 200 for different vibration state concrete sample images, as depicted in Figure 5, Figure 6, and Figure 7.</li>
</ol>
3. Calculation of directional gradient eigenvalue
<ol>
	<li>Calculate the horizontal and vertical binary gradient of each pixel in the image using the following equation28 
	Tp = R(x, y + 1) - R(x, y - 1), Th = R(x+1, y) - R(x-1, y) 
	where Th is the horizontal binarized gradient, Tp is the vertical binarized gradient, R is the binarized logical format data, x is the row number of the binarized matrix, and y is the column number of the binarized matrix.</li>
	<li>Calculate the binary gradient direction and size of each point using the following equation29 
	<img alt="Equation 1" src="/files/ftp_upload/65731/65371eq01.jpg" style="margin: auto;" /> 
	where T is the binary gradient size, &#945;T is the binary gradient direction, Th is the horizontal binary gradient, and Tp is the vertical binary gradient.</li>
	<li>Determine the size of the image segmentation block, denoted as n, where the value of n is [ 1,9]. Set the segmentation line for each n pixel in the y direction along the x direction, effectively dividing the image into n x n square blocks based on the segmentation line&#39;s position. Any parts of the image that cannot form complete square blocks are then removed.</li>
	<li>Partition binary gradient direction&#160;&#945;T (value of the binary gradient direction &#945;T is [ 0&#176;, 360&#176;]) into m parts, resulting in m directional gradient statistical angle intervals. Proceed to calculate the gradient statistical value for each block&#39;s gradient statistical angle interval.
	<ol>
		<li>Based on the binary gradient direction of each pixel in the block, classify the pixels into the appropriate gradient statistical angle interval of each direction.</li>
		<li>Sum the binary gradient of the pixels in the gradient statistical angle interval of each direction in the counterclockwise direction to obtain the gradient statistical value of that interval. The obtained results for gradient statistical angle interval directional gradient statistics are depicted in Figure 8, Figure 9, and Figure 10 for block sizes n equal to 8, 128, and 512, respectively .</li>
	</ol>
	</li>
</ol>
4. Constructing directional gradient feature vector
<ol>
	<li>Divide samples into required calculation areas, where each calculation area consists of four adjacent blocks based on the block results obtained in step 3.3. For instance, considering 16 x 16 resolution pixels and a block size of 4 x 4, the image is divided into (16 / 4-1) x ( 16 / 4-1 ) = 9 calculation areas.</li>
	<li>Calculate the statistical value of the directional gradient within angle interval of the gradient statistics of each block in the calculation area. Subsequently, obtain the feature vector with the directional gradient statistics as the component.</li>
	<li>Combine the directional gradient feature vectors from each calculation area to obtain the image&#39;s directional gradient feature vector.</li>
</ol>
5. SVM training
<ol>
	<li>Randomly select 42 samples from the three vibration states to create the training group, leaving the remaining 18 samples as the test group.</li>
	<li>Utilize the fitcecoc function of MATLAB for SVM training; the format is 
	SVM = fitcecoc (trainingFeatures, Trainingeigenvalue) 
	where SVM is the support vector machine to be trained, trainingFeatures is the training group image directional gradient feature vector, and Trainingeigenvalue is the characteristic value of the vibration state of the training group. The characteristic values of the vibration state of the non-vibrated concrete, vibrating concrete, and vibrated concrete samples are 1, 2, and 3, respectively.</li>
	<li>Save the trained SVM using the Save function in .mat format.</li>
</ol>
6. Verification of SVM recognition accuracy
<ol>
	<li>Using MATLAB&#39;s prediction function, input the test group sample image&#39;s directional gradient feature vector into the trained SVM to obtain the calculated value of the vibration state feature for each test sample. The format is as follows: 
	testgroupcalculateseigenvalues = predict (SVM, testFeature) 
	where testgroupcalculateseigenvalues is the calculated value of the vibration state feature, and SVM is the support vector machine trained in step 5. testFeature is the directional gradient feature vector of the test group sample image.</li>
	<li>Determine the test set sample recognition results by feeding the test set into the trained SVM. Count the number of samples for which the test set recognition results match the actual state, and then calculate the recognition accuracy by dividing the number of correct samples by the total number of test set samples.
	<ol>
		<li>If the test recognition accuracy is higher than 94%, consider the SVM recognition as effective. If it is lower than 94%, return to step 1.1 and adjust the binarization threshold, block size n, and the number of directional gradient statistical intervals m.</li>
	</ol>
	</li>
</ol>

Directional Gradient Histogram and SVM for Identifying Concrete Vibration States

<ol>
	<li>Jiang, L., Tian, Z., Wang, K., Sun, X. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Estimating+the+segregation+of+concrete+under+vibration+based+on+electrical+method.">Estimating the segregation of concrete under vibration based on electrical method.</a> Concrete. 1, 41-44 (2023).</li><li>Ren, B., Ye, Z., Wang, D., Wu, B., Tan, Y. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Evaluation+of+segregation+degree+of+hardening+concrete+using+improved+Mask+R-CNN.">Evaluation of segregation degree of hardening concrete using improved Mask R-CNN.</a> Journal of Hydroelectric Engineering. 41 (5), 93-102 (2022).</li><li>Hu, J., Qin, M., Wang, H., Liu, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Study+on+the+influence+of+vibration+frequency+on+the+performance+of+concrete.">Study on the influence of vibration frequency on the performance of concrete.</a> Highway. 65 (12), 111-114 (2020).</li><li>Bian, C., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Experimental+study+on+characterization+of+evaluation+indexes+for+vibration+compaction+of+fresh+concrete.">Experimental study on characterization of evaluation indexes for vibration compaction of fresh concrete.</a> Journal of Hydroelectric Engineering. 39 (2), 67-80 (2020).</li><li>Liu, Z., Zhou, M., Bai, J., Mou, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Influence+of+vibration+time+on+the+strength+and+homogeneity+of+rubber+concrete.">Influence of vibration time on the strength and homogeneity of rubber concrete.</a> Industrial Construction. 42, 509-512 (2012).</li><li>Cheng, Y., Gou, Z., Wang, Y. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Testing+Investigation+on+Effects+of+Mixing,+Vibrating+and+Curing+on+Strength+of+High-Performance+Concrete.">Testing Investigation on Effects of Mixing, Vibrating and Curing on Strength of High-Performance Concrete.</a> Journal of Northeastern University (Natural Science). 31 (12), 1790-1793 (2010).</li><li>Zhao, Y., Chen, S., Liu, Z. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Influence+mechanism+of+high-frequency+vibration+on+concrete+antifreeze+and+application+in+construction+of+tunnels+in+cold+regions.">Influence mechanism of high-frequency vibration on concrete antifreeze and application in construction of tunnels in cold regions.</a> Industrial Construction. 44 (5), 101-105 (2014).</li><li>Quan, L., Tian, B., Li, S., He, Z., He, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Evolution+characteristics+of+flexural+fatigue+performance+of+dense+concrete+consolidated+with+high+frequency+vibration+applied+in+airport+pavement.">Evolution characteristics of flexural fatigue performance of dense concrete consolidated with high frequency vibration applied in airport pavement.</a> Journal of Traffic and Transportation Engineering. 20 (2), 34-45 (2020).</li><li>Cai, Y., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Influence+of+coarse+aggregate+settlement+induced+by+vibration+on+long-term+chloride+transport+in+concrete:+a+numerical+study.">Influence of coarse aggregate settlement induced by vibration on long-term chloride transport in concrete: a numerical study.</a> Materials and Structures. 55 (9), 1-18 (2022).</li><li>Cai, Y., Liu, Q. F., Yu, L., Meng, Z., Avija, B. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=An+experimental+and+numerical+investigation+of+coarse+aggregate+settlement+in+fresh+concrete+under+vibration.">An experimental and numerical investigation of coarse aggregate settlement in fresh concrete under vibration.</a> Cement and Concrete Composites. 122 (7), 104153 (2021).</li><li>Wang, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Development+and+application+of+concrete+vibrating+robot+system+for+high+arch+dam.">Development and application of concrete vibrating robot system for high arch dam.</a> Journal of Hydraulic Engineering. 53 (6), 631-654 (2022).</li><li>Chen, C., Li, X., Qiu, Z., Yao, W., Zhu, H. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Research+Progress+of+Construction+Robots.">Research Progress of Construction Robots.</a> Journal of Architecture and Civil Engineering. 39 (4), 58-70 (2022).</li><li>Shen, H., Zhang, W., Liu, J., Qiu, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Development+and+Prospect+of+Construction+Robots+for+High+Rise+Buildings.">Development and Prospect of Construction Robots for High Rise Buildings.</a> Construction Technology. 46 (8), 105-108 (2017).</li><li>Dalal, N., Triggs, B. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Histograms+of+Oriented+Gradients+for+Human+Detection.">Histograms of Oriented Gradients for Human Detection.</a> IEEE Computer Society Conference on Computer Vision &amp; Pattern Recognition. , (2005).</li><li>Zhou, W., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Gradient-based+Feature+Extraction+From+Raw+Bayer+Pattern+Images.">Gradient-based Feature Extraction From Raw Bayer Pattern Images.</a> IEEE Transactions on Image Processing. (99), 1 (2021).</li><li>He, B., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Railway+Fastener+Defects+Detection+under+Various+Illumination+Conditions+using+Fuzzy+C-Means+Part+Model.">Railway Fastener Defects Detection under Various Illumination Conditions using Fuzzy C-Means Part Model.</a> Transportation Research Record. 2675 (4), 271-280 (2021).</li><li>Xu, X., Quan, C., Ren, F. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Facial+expression+recognition+based+on+Gabor+Wavelet+transform+and+Histogram+of+Oriented+Gradients.">Facial expression recognition based on Gabor Wavelet transform and Histogram of Oriented Gradients.</a> IEEE International Conference on Mechatronics &amp; Automation. , (2015).</li><li>Cortes, C., Vapnik, V. N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Support+Vector+Networks.">Support Vector Networks.</a> Machine Learning. 20 (3), 273-297 (1995).</li><li>Burges, C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+Tutorial+on+Support+Vector+Machines+for+Pattern+Recognition.">A Tutorial on Support Vector Machines for Pattern Recognition.</a> Data Mining and Knowledge Discovery. 2 (2), 121-167 (1998).</li><li>Yang, C., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Identification+of+Pleurotus+Ostreatus+From+Different+Producing+Areas+Based+on+Mid-Infrared+Spectroscopy+and+Machine+Learning.">Identification of Pleurotus Ostreatus From Different Producing Areas Based on Mid-Infrared Spectroscopy and Machine Learning.</a> Spectroscopy and Spectral Analysis. 43 (2), 577-582 (2023).</li><li>Chaabane, S. B., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Face+recognition+based+on+statistical+features+and+SVM+classifier).">Face recognition based on statistical features and SVM classifier).</a> Multimedia Tools and Applications. 81 (6), 8767-8784 (2022).</li><li>Saleh, M. R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Experiments+with+SVM+to+classify+opinions+in+different+domains.">Experiments with SVM to classify opinions in different domains.</a> Expert Systems with Applications. 38 (12), 14799-14804 (2011).</li><li>Zhang, Y., Liu, Y., Wang, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Reliability+Prediction+of+Coal+Mine+Water+Disasters+Emergency+Rescue+System+Based+on+Improved+SVM.">Reliability Prediction of Coal Mine Water Disasters Emergency Rescue System Based on Improved SVM.</a> Journal of Zhengzhou University (Engineering Science). 36 (3), 115-119 (2015).</li><li>Cao, Y., Song, D., Hu, X., Sun, Y. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Fault+Diagnosis+of+Railway+Point+Machine+Based+on+Improved+Time-Domain+Multiscale+Dispersion+Entropy+and+Support+Vector+Machine.">Fault Diagnosis of Railway Point Machine Based on Improved Time-Domain Multiscale Dispersion Entropy and Support Vector Machine.</a> Acta Electronica Sinica. 51 (1), 117-127 (2023).</li><li>Li, Q., Yuze, C., Yu, B., Ning, C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Two-stage+support+vector+machine+method+for+failure+mode+classification+of+reinforced+concrete+columns.">Two-stage support vector machine method for failure mode classification of reinforced concrete columns.</a> Engineering Mechanics. 39 (2), 148-158 (2022).</li><li>Yang, Y., Zhang, W., Yu, H., Chai, W., Liu, D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Analysis+on+the+relationships+between+ultrasonic+parameters+and+the+stress+state+in+loaded+concrete+based+on+improved+support+vector+machines).">Analysis on the relationships between ultrasonic parameters and the stress state in loaded concrete based on improved support vector machines).</a> Journal of Vibration and Shock. 42 (2), 175-224 (2023).</li><li>Yan, K., Shi, C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Prediction+of+elastic+modulus+of+normal+and+high+strength+concrete+by+support+vector+machine.">Prediction of elastic modulus of normal and high strength concrete by support vector machine.</a> Construction &amp; Building Materials. 24 (8), 1479-1485 (2010).</li><li>Hussein, I. J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Fully-automatic+identification+of+gynaecological+abnormality+using+a+new+adaptive+frequency+filter+and+histogram+of+oriented+gradients+(HOG).">Fully-automatic identification of gynaecological abnormality using a new adaptive frequency filter and histogram of oriented gradients (HOG).</a> Expert Systems. 39 (3), 12789 (2022).</li><li>Chandrakala, M., Devi, P. D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Two-stage+classifier+for+face+recognition+using+HOG+features.">Two-stage classifier for face recognition using HOG features.</a> Materials Today: Proceedings. 47, 5771-5775 (2021).</li><li>Long, C., Yichi, Z., Zhangkai, L., Dandan, D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Low-Light+Image+Enhancement+Based+on+RAW+Domain+Image.">Low-Light Image Enhancement Based on RAW Domain Image.</a> Journal of Computer-Aided Design &amp; Computer Graphics. 35 (2), 303-311 (2023).</li><li>Wang, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Development+and+application+of+concrete+vibrating+robot+system+for+high+arch+dam.">Development and application of concrete vibrating robot system for high arch dam.</a> Journal of Hydraulic Engineering. 53 (6), 631-654 (2022).</li></ol>

The authors have nothing to disclose.

This paper utilizes the support vector machine (SVM) to learn the image features of various concrete vibration state samples. Based on the machine learning outcomes, a concrete vibration state recognition method based on image recognition is proposed. To enhance the recognition accuracy, it is crucial to control the parameters of the three key steps: image segmentation, image binarization, and directional gradient eigenvalue extraction. According to the test results, a smaller binarization threshold is employed to prepro...

Concrete is a fundamental building material extensively used in the construction industry. During pumping, the concrete frequently develops voids that require compaction through vibration. Inadequate vibration may result in a honeycombed concrete surface, while excessive vibration can lead to concrete segregation1,2. The quality of vibration operation significantly impacts the strength3,4,5,6 and durability of the formed concrete structures7,8. Cai et al.9,10 conducted a study that combined experimental research with numerical analysis to investigate the influence mechanism of vibration on aggregate settlement and concrete durability. The findings revealed that vibration time and aggregate particles exert a substantial impact on aggregate settlement, while aggregate density and the plastic viscosity of the cement-based material have minimal effects. Vibration causes aggregate deposition at the bottom of the concrete specimens. Moreover, as the vibration time increases, the chloride ion concentration decreases at the bottom of the concrete specimens while significantly increasing at the top9,10.
Currently, the assessment of concrete vibration state relies predominantly on manual judgment. As the construction industry continues to progress through intelligent reforms, robot operations have emerged as the future direction11,12. Consequently, a crucial challenge in intelligent vibration operations is how to enable robots to identify the vibration state of concrete.
The histogram of the oriented gradient is a technique that utilizes the intensity gradient of pixels or the distribution of edge directions as a descriptor to characterize the representation and shape of objects in images13,14. This approach operates on the local grid cells of the image, providing robust stability in characterizing image changes under various geometric and optical conditions.
Zhou et al.15 proposed a method for directly extracting directional gradient features from Bayer mode images. This approach omits numerous steps in calculating the directional gradient by matching the color filter column with the gradient operator, thereby significantly reducing the computational requirements for directional gradient image recognition. He et al.16 utilized the directional gradient histogram as the underlying feature and employed the mean clustering algorithm to classify rail fasteners and determine whether the fasteners are defective. The recognition results indicated that the histogram of the oriented gradient feature exhibited high sensitivity to fastener defects, meeting the needs of railway maintenance and repair. In another study, Xu et al.17 preprocessed face image features using Gabor wavelet filtering and reduced the dimension of feature vectors through binary coding and the HOG algorithm. The average recognition accuracy of the method is 92.5%.
The support vector machine (SVM)18 is used to map the vector into a high-dimensional space and establishes a separating hyperplane with a suitable direction to maximize the distance between two parallel hyperplanes. This allows for the classification of support vectors19. Scholars have improved and optimized this classification technology, leading to its application in various fields such as image recognition20,21, text classification22, reliability prediction23, and fault diagnosis24.
Li et al.25 developed a two-stage SVM model for seismic failure pattern recognition, focusing on three seismic failure modes. The analysis results indicate that the proposed two-stage SVM method can achieve more than 90% accuracy for the three failure modes. Yang et al.26 integrated an optimization algorithm with the SVM to simulate the relationship between the five ultrasonic parameters and the stress of the loaded concrete. The performance of an unoptimized SVM is unsatisfactory, particularly in the low-stress stage. However, traversing the model optimized by the algorithm yields improved results, albeit with lengthy computation times. In comparison, the particle swarm optimization optimized SVM significantly reduces the calculation time while delivering optimal simulation results. Yan et al.27 employed SVM technology and introduced a precision-insensitive loss function to predict the elastic modulus of high-strength concrete, comparing its prediction accuracy against the traditional regression model and neural network model. The research findings demonstrate that the SVM technology produces a smaller prediction error for elastic modulus compared to other methods.
This paper collects image samples of concrete under various vibration states and describes the concrete&#39;s different states using the directional gradient histogram technique. The directional gradient is employed as a feature vector for training the SVM, and the study focuses on the viability of using the directional gradient histogram-SVM technology to identify the vibration state of concrete. Additionally, the paper analyzes the influence mechanism between three key parameters-binarization threshold, directional gradient statistical block size, and directional gradient statistical interval number-in the feature extraction process of the directional gradient histogram and the recognition accuracy of the SVM.

<table><tbody><tr><td>camera</td><td>SONY</td><td>A6000</td><td>The sensor size is 23.5x15.6mm, the maximum acquisition resolution is 1440 * 1080, and the effective pixel is 24.3 million.</td></tr><tr><td>concrete</td><td>Wuhan Construction Changxin Technology Development Co., Ltd.</td><td>C30 pumping concrete</td><td>According to the standard of &#039; concrete strength test and evaluation standard &#039; ( GB / T 50107-2010 ), the standard value of cubic compressive strength is 30 MPa pumping concrete.</td></tr><tr><td>Matlab</td><td>MathWorks</td><td>Matlab R2017a</td><td>MATLAB&#039;s programming interface provides development tools for improving code quality maintainability and maximizing performance.&lt;br/&gt; It provides tools for building applications using custom graphical interfaces.&lt;br/&gt; It provides tools for combining MATLAB-based algorithms with external applications and languages</td></tr><tr><td>Processor&amp;nbsp;</td><td>Intel</td><td>12th Gen Intel(R) Core (TM) i7-12700H @ 2.30GHz</td><td>64-bit Win11 processor&amp;nbsp;</td></tr></tbody></table>

image recognition and parameter analysis of concrete vibration state based on support vector machine

In this paper, the directional gradient histogram technology is employed to extract the features of concrete image samples captured under different vibration states. The support vector machine (SVM) is utilized to learn the relationship between image features and vibration state. The machine learning results are subsequently used to assess the feasibility of the concrete vibration state. Simultaneously, the influence mechanism of the calculation parameters of the directional gradient histogram on the recognition accuracy is analyzed. The results demonstrate the feasibility of using the directional gradient histogram-SVM technology to identify the vibration state of concrete. The recognition accuracy initially increases and then decreases as the block size of the directional gradient, or the number of statistical intervals increases. The recognition accuracy also decreases linearly with the increase of the binarization threshold. By using sample images with a resolution of 1024 pixels x 1024 pixels and optimizing the feature extraction parameters, a recognition accuracy of 100% can be attained.

This protocol aims to analyze how the three-vector calculation parameters of the directional gradient feature affect the accuracy of the SVM in identifying the concrete vibration state. The primary calculation parameters of the directional gradient feature vector include the directional gradient statistical block size, the number of directional gradient statistical angle intervals, and the binary gray threshold. This section uses three main calculation parameters as variables to design the test. The test parameter levels...

Watch this Scientific Journal Video about Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines at JoVE.com

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines 

The protocol described in this paper utilizes the directional gradient histogram technique to extract the characteristics of concrete image samples under various vibration states. It employs a support vector machine for machine learning, resulting in an image recognition method with minimal training sample requirements and low computer performance demands.

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

In this paper, the directional gradient histogram technology is employed to extract the features of concrete image samples captured under different ...

image-recognition-parameter-analysis-concrete-vibration-state-based

Research

Education

JoVE Core

JoVE Journal

Civil Engineering

Engineering

Unit 1

Mixing, Placing and Curing Concrete 

SCIENTISTS IN ACTION

881 Views.  Wuhan University. The protocol described in this paper utilizes the directional gradient histogram technique to extract the characteristics of concrete image samples under various vibration states. It employs a support vector machine for machine learning, resulting in an image recognition method with minimal training sample requirements and low computer performance demands.

Video: Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines 

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Proprioceptive drift, which is a perceptual shift in body-part position from the unseen real body to a visible body-like image, has been measured as the behavioral correlate for the sense of ownership. Previously, the estimation of proprioceptive drift was limited to one spatial dimension, such as height, width, or depth. As the hand can move freely in 3D, measuring proprioceptive drift in only one dimension is not sufficient for the estimation of the drift in real life situations. In this article, we provide a novel method to estimate proprioceptive drift on a 2D plane using the mirror illusion by combining an objective behavioral measurement (hand position tracking) and subjective, phenomenological assessment (subjective assessment of hand position and questionnaire) with a sophisticated machine learning approach. This technique permits not only an investigation of the underlying mechanisms of the sense of ownership and agency but also assists in the rehabilitation of a missing or paralyzed limb and in the design rules of real-time control systems with a self-body-like usability, in which the operator controls the system as if it were part of his/her own body.

This article describes a novel method to estimate proprioceptive drift on a 2D plane using the mirror illusion and combining a psychophysical procedure with an analysis using machine learning.

Proprioceptive drift, which is a perceptual shift in body-part position from the unseen real body to a visible body-like image, has been measured as the ...

Behavior

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

For slender and lightweight structures, vibration serviceability is a matter of growing concern, often constituting the critical design requirement. With designs governed by the dynamic performance under human-induced loads, a strong demand exists for the verification and refinement of currently available load models. The present contribution uses a 3D inertial motion tracking technique for the characterization of the in-field pedestrian behavior. The technique is first tested in laboratory experiments with simultaneous registration of the corresponding ground reaction forces. The experiments include walking persons as well as rhythmical human activities such as jumping and bobbing. It is shown that the registered motion allows for the identification of the time variant pacing rate of the activity. Together with the weight of the person and the application of generalized force models available in literature, the identified time-variant pacing rate allows to characterize the human-induced loads. In addition, time synchronization among the wireless motion trackers allows identifying the synchronization rate among the participants. Subsequently, the technique is used on a real footbridge where both the motion of the persons and the induced structural vibrations are registered. It is shown how the characterized in-field pedestrian behavior can be applied to simulate the induced structural response. It is demonstrated that the in situ identified pacing rate and synchronization rate constitute an essential input for the simulation and verification of the human-induced loads. The main potential applications of the proposed methodology are the estimation of human-structure interaction phenomena and the development of suitable models for the correlation among pedestrians in real traffic conditions.

A protocol is presented for the characterization of the in-field pedestrian behavior and the simulation of the resulting structural response. Field-tests demonstrate that the in situ identified pacing rate and synchronization rate among the participants constitute an essential input for the simulation and verification of the human-induced loads.

For slender and lightweight structures, vibration serviceability is a matter of growing concern, often constituting the critical design requirement. With ...

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

The effectiveness of many structural health monitoring techniques depends on the placement of sensors and the location of input forces. Algorithms for determining optimal sensor and forcing locations typically require data, either simulated or measured, from the damaged structure. Embedded sensitivity functions provide an approach for determining the best available sensor location to detect damage with only data from the healthy structure. In this video and manuscript, the data acquisition procedure and best practices for determining the embedded sensitivity functions of a structure is presented. The frequency response functions used in the calculation of the embedded sensitivity functions are acquired using modal impact testing. Data is acquired and representative results are shown for a residential scale wind turbine blade. Strategies for evaluating the quality of the data being acquired are provided during the demonstration of the data acquisition process.

The data acquisition procedure for determining embedded sensitivity functions is described. Data is acquired and representative results are shown for a residential scale wind turbine blade.

The effectiveness of many structural health monitoring techniques depends on the placement of sensors and the location of input forces. Algorithms for ...

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

As individuals increasingly live in cities, methods to study their everyday movements and the data that can be collected becomes important and valuable. Eye-tracking informatics are known to connect to a range of feelings, health conditions, mental states and actions. But because vision is the result of constant eye-movements, teasing out what is important from what is noise is complex and data intensive. Furthermore, a significant challenge is controlling for what people look at compared to what is presented to them.
The following presents a methodology for combining and analyzing eye-tracking on a video of a natural and complex scene with a machine learning technique for analyzing the content of the video. In the protocol we focus on analyzing data from filmed videos, how a video can be best used to record participants&#39; eye-tracking data, and importantly how the content of the video can be analyzed and combined with the eye-tracking data. We present a brief summary of the results and a discussion of the potential of the method for further studies in complex environments.

The objective of the protocol is to detail how to collect video data for use in the laboratory; how to record eye-tracking data of participants looking at the data and how to efficiently analyze the content of the videos that they were looking at using a machine learning technique.

As individuals increasingly live in cities, methods to study their everyday movements and the data that can be collected becomes important and valuable. ...

Environment

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

The rapid development of X-ray imaging techniques with image processing and analysis skills has enabled the acquisition of CT images of granular soils with high-spatial resolutions. Based on such CT images, grain-scale mechanical behavior such as particle kinematics (i.e., particle translations and particle rotations), strain localization and inter-particle contact evolution of granular soils can be quantitatively investigated. However, this is inaccessible using conventional experimental methods. This study demonstrates the exploration of the grain-scale mechanical behavior of a granular soil sample under triaxial compression using synchrotron X-ray micro-tomography (&#956;CT). With this method, a specially fabricated miniature loading apparatus is used to apply confining and axial stresses to the sample during the triaxial test. The apparatus is fitted into a synchrotron X-ray tomography setup so that high-spatial resolution CT images of the sample can be collected at different loading stages of the test without any disturbance to the sample. With the capability of extracting information at the macro scale (e.g., sample boundary stresses and strains from the triaxial apparatus setup) and the grain scale (e.g., grain movements and contact interactions from the CT images), this procedure provides an effective methodology to investigate the multi-scale mechanics of granular soils.

The protocol describes procedures to acquire high-spatial resolution computed tomography (CT) images of a granular soil during triaxial compression, and to apply image processing techniques to these CT images to explore the grain-scale mechanical behavior of the soil under loading.

The rapid development of X-ray imaging techniques with image processing and analysis skills has enabled the acquisition of CT images of granular soils ...

A Method for Evaluating Timeliness and Accuracy of Volitional Motor Responses to Vibrotactile Stimuli

Artificial sensory feedback (ASF) systems can be used to compensate for lost proprioception in individuals with lower-limb impairments. Effective design of these ASF systems requires an in-depth understanding of how the parameters of specific feedback mechanism affect user perception and reaction to stimuli. This article presents a method for applying vibrotactile stimuli to human participants and measuring their response. Rotating mass vibratory motors are placed at pre-defined locations on the participant's thigh, and controlled through custom hardware and software. The speed and accuracy of participants' volitional responses to vibrotactile stimuli are measured for researcher-specified combinations of motor placement and vibration frequency. While the protocol described here uses push-buttons to collect a simple binary response to the vibrotactile stimuli, the technique can be extended to other response mechanisms using inertial measurement units or pressure sensors to measure joint angle and weight bearing ratios, respectively. Similarly, the application of vibrotactile stimuli can be explored for body segments other than the thigh.

This article describes a technique for applying vibrotactile stimuli to the thigh of a human participant, and measuring the accuracy and reaction time of the participant&#39;s volitional response for various combinations of stimulation location and frequency.

Artificial sensory feedback (ASF) systems can be used to compensate for lost proprioception in individuals with lower-limb impairments.  Effective design ...

Bioengineering

Studying Ice Cream Melting Behavior Using a Computer Vision System

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

Melting behavior is one of the most important quality indices of ice cream. It is usually evaluated by gravimetric methods and expressed in terms of starting time and rate of melting. However, the aspect of ice cream during melting is also important because shape retention is linked to a good structure of the product. The protocol proposed here illustrates a computer vision system (CVS) that can be used to support the already existing gravitational methodology to calculate two new melting indices related to shape retention and melting rate. Pictures of ice cream during melting are taken every 15 min for a total of 90 min. Afterward, digital images are elaborated using a purposely developed image processing method to calculate ice cream area, height, and width. The ratio between height and width at each melting time, referred to&#160;the ratio at time 0 (Rt/R0), is an index of the shape retention of ice cream, while the area at the different melting times referred to the area at time 0 (At/A0) is related to the melting rate. This computer vision system allows the obtaining of highly sensitive and reliable results, and it can be applied not only to ice cream but also to different food matrices, such as whipped milk cream or egg albumen.

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Here, we present a protocol based on a computer vision system (CVS) to determine the melting behavior of multi-phase food systems.

Melting behavior is one of the most important quality indices of ice cream. It is usually evaluated by gravimetric methods and expressed in terms of ...

Assessing Vision via Shape Recognition in Random Dot Kinematograms

Motion-Acuity Test for Visual Field Acuity Measurement with Motion-Defined Shapes

The standard visual acuity measurements rely on stationary stimuli, either letters (Snellen charts), vertical lines (vernier acuity) or grating charts, processed by those regions of the visual system most sensitive to the stationary stimulation, receiving visual input from the central part of the visual field. Here, an acuity measurement is proposed based on discrimination of simple shapes, that are defined by motion of the dots in the random dot kinematograms (RDK) processed by visual regions sensitive to motion stimulation and receiving input also from the peripheral visual field. In the motion-acuity test, participants are asked to distinguish between a circle and an ellipse, with matching surfaces, built from RDKs, and separated from the background RDK either by coherence, direction, or velocity of dots. The acuity measurement is based on ellipse detection, which with every correct response becomes more circular until reaching the acuity threshold. The motion-acuity test can be presented in negative contrast (black dots on white background) or in positive contrast (white dots on black background). The motion defined shapes are located centrally within 8 visual degrees and are surrounded by RDK background. To test the influence of visual peripheries on centrally measured acuity, a mechanical narrowing of the visual field to 10 degrees is proposed, using opaque goggles with centrally located holes. This easy and replicable narrowing system is suitable for MRI protocols, allowing further investigations of the functions of the peripheral visual input. Here, a simple measurement of shape and motion perception simultaneously is proposed. This straightforward test assesses vision impairments depending on the central and peripheral visual field inputs. The proposed&#160;motion-acuity test advances the capability of standard tests to reveal spare or even strengthened vision functions in patients with injured visual system, that until now remained undetected.

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

A novel motion-based acuity test that allows the assessment of central and peripheral visual processing in low-vision and healthy individuals, along with goggles limiting peripheral vision compatible with MRI protocols, are described here. This method offers a comprehensive vision assessment for functional impairments and dysfunctions of the visual system.

The standard visual acuity measurements rely on stationary stimuli, either letters (Snellen charts), vertical lines (vernier acuity) or grating charts, ...

Neuroscience

Decoding Auditory Imagery with Multivoxel Pattern Analysis

Source: Laboratories of Jonas T. Kaplan and Sarah I. Gimbel&#8212;University of Southern California
Imagine the sound of a bell ringing. What is happening in the brain when we conjure up a sound like this in the "mind's ear?" There is growing evidence that the brain uses the same mechanisms for imagination that it uses for perception.1 For example, when imagining visual images, the visual cortex becomes activated, and when imagining sounds, the auditory cortex is engaged. However, to what extent are these activations of sensory cortices specific to the content of our imaginations? 
One technique that can help to answer this question is multivoxel pattern analysis (MPVA), in which functional brain images are analyzed using machine-learning techniques.2-3 In an MPVA experiment, we train a machine-learning algorithm to distinguish among the various patterns of activity evoked by different stimuli. For example, we might ask if imagining the sound of a bell produces different patterns of activity in auditory cortex compared with imagining the sound of a chainsaw, or the sound of a violin. If our classifier learns to tell apart the brain activity patterns produced by these three stimuli, then we can conclude that the auditory cortex is activated in a distinct way by each stimulus. One way to think of this kind of experiment is that instead of asking a question simply about the activity of a brain region, we ask a question about the information content of that region. 
In this experiment, based on Meyer et al., 2010,4 we will cue participants to imagine several sounds by presenting them with silent videos that are likely to evoke auditory imagery. Since we are interested in measuring the subtle patterns evoked by imagination in auditory cortex, it is preferable if the stimuli are presented in complete silence, without interference from the loud noises made by the fMRI scanner. To achieve this, we will use a special kind of functional MRI sequence known as sparse temporal sampling. In this approach, a single fMRI volume is acquired 4-5 s after each stimulus, timed to capture the peak of the hemodynamic response.

Source: Laboratories of Jonas T. Kaplan and Sarah I. Gimbel&#8212;University of Southern California
Imagine the sound of a bell ringing. What is happening ...

JoVE Science Education

Psychology

Neuropsychology

Vibrating Concrete

Mechanical vibrators are instrumental in compacting newly poured concrete within formwork and around reinforcements. This process is essential to eliminate trapped air pockets and establish a dense concrete mass. One widely used method is vibrating by internal vibrators, often referred to as a poker vibrator or immersion vibrator. It is rapidly inserted through the full depth of the freshly laid concrete and slightly extends into the layer below it (which remains in a plastic state). Consistent vibrations are applied across the concrete surface at intervals of every 2 to 3 feet for a period of 5 seconds to 2 minutes, depending on the consistency of the concrete mix. As the vibrator is slowly withdrawn, the hole left behind is naturally sealed, preventing the formation of voids.
Another method employs external vibrators that are attached to the formwork to vibrate the formwork and the concrete simultaneously. This is used for precast elements or thinner sections of concrete. In contrast to internal vibrators that directly vibrate the concrete, external vibrators do additional work by vibrating the formworks, making them less efficient than the internal vibrators. Occasionally, external vibrators have to be shifted from place to place depending on the placement of the concrete. For precast concrete units, a vibrating table is used, wherein the formwork is fixed directly onto the platform to achieve a uniform vibration throughout the unit.