Automatic Acquisition Research Articles

Automatic Data Acquisition and Monitoring Device to Indicate the Freshness of Milk during Transportation

Abstract: Milk is a nutrient-rich liquid food and it is the primary source of nutrition and a cheap source of protein for large vegetarian population living in India. Dairy industry in India is the world's largest milk producer and dominates about 13% of world milk production. Milk contains several groups of nutrients & considerable amount of organic substances and functional elements such as traces of vitamins, enzymes & dissolved gases, dissolved salts, calcium, water, carbohydrates, proteins, fats, complex & simple lipids, minerals, vitamins , etc.,. Milk transportation has shown to contribute to a greater extent to milk spoilage. Most of the milk which has been rejected by milk processing plants had samples which indicate milk of good quality at farm level before transportation. Milk processors request that milk must be cooled to 2°C to 4°C within 2 to 3 h of milking. The monitoring system that we have implied here is to check the temperature throughout the transportation using micro-controller and to ensure the quality of the milk. This monitoring device consist of NTC Temperature sensor to indicate the exposure to excessive temperature and controlled temperature like cold storage and a gas sensor is used to detect the spoilage of milk while transportation. The RFID tags are used to record the information of the vendor, temperature and how much litre they are giving to the society and hereby, the complete record of this is maintained separately by data acquisition system with the open source software cayenne. In this monitoring device, the temperature of the milk is continuously monitored using microcontroller and an immediate alert message is given to the driver and admin when there is raise in temperature. Keywords: Milk, cayenne, data acquisition, RFID, NTC

Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Automatic acquisition of the canopy volume parameters of the Citrus reticulate Blanco cv. Shatangju tree is of great significance to precision management of the orchard. This research combined the point cloud deep learning algorithm with the volume calculation algorithm to segment the canopy of the Citrus reticulate Blanco cv. Shatangju trees. The 3D (Three-Dimensional) point cloud model of a Citrus reticulate Blanco cv. Shatangju orchard was generated using UAV tilt photogrammetry images. The segmentation effects of three deep learning models, PointNet++, MinkowskiNet and FPConv, on Shatangju trees and the ground were compared. The following three volume algorithms: convex hull by slices, voxel-based method and 3D convex hull were applied to calculate the volume of Shatangju trees. Model accuracy was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The results show that the overall accuracy of the MinkowskiNet model (94.57%) is higher than the other two models, which indicates the best segmentation effect. The 3D convex hull algorithm received the highest R2 (0.8215) and the lowest RMSE (0.3186 m3) for the canopy volume calculation, which best reflects the real volume of Citrus reticulate Blanco cv. Shatangju trees. The proposed method is capable of rapid and automatic acquisition for the canopy volume of Citrus reticulate Blanco cv. Shatangju trees.

"3-D Dental Measurement Using A Non-Contact Optical Technique"

This research is aimed at creating a system of automatic acquisition of three-dimensional data with one or more teeth...

Surrogate model\u2013based inverse parameter estimation in deep drawing using automatic knowledge acquisition

In this paper, we propose a new approach for the simulation-based support of tryout operations in deep drawing which can be schematically classified as automatic knowledge acquisition. The central idea is to identify information maximising sensor positions for draw-in as well as local blank holder force sensors by solving the column subset selection problem with respect to the sensor sensitivities. Inverse surrogate models are then trained using the selected sensor signals as predictors and the material and process parameters as targets. The final models are able to observe the drawing process by estimating current material and process parameters, which can then be compared to the target values to identify process corrections. The methodology is examined on an Audi A8L side panel frame using a set of 635 simulations, where 20 out of 21 material and process parameters can be estimated with an R2 value greater than 0.9. The result shows that the observational models are not only capable of estimating all but one process parameters with high accuracy, but also allow the determination of material parameters at the same time. Since no assumptions are made about the type of process, sensors, material or process parameters, the methodology proposed can also be applied to other manufacturing processes and use cases.

Fuzzy Cloud Evaluation of Service Quality Based on DP-FastText

This study proposes a service quality evaluation model framework which integrates automatic data acquisition, intelligent data processing and real-time data analysis with online comment data as data sources by introducing natural language processing technology based on management methods to break the traditional idea of over-reliance on human resources for service quality evaluation. The framework is mainly divided into text data preparation, fine-grained sentiment analysis and fuzzy cloud evaluation models. Data preparation module is responsible for preparing the initial data, and the fine-grained sentiment analysis module is responsible for pre-training a fine-grained sentiment classification model. The fuzzy cloud evaluation module uses the data obtained from the first two modules to evaluate service quality. By applying the model into catering industry, the feasibility of the model is proved and individuality, efficiency, dynamicity and intelligence of the model give it more advantage in the practice of service quality evaluation

Three Dimensions Reconstruction of Single-spectrum Multi-X-ray Views of Contraband Based on Space Carving Method

In consideration of imaging principle and sampling process of the X-ray imager, the collected images often appear blurry and noisy. We propose to add image processing in the reconstruction process to optimize the 3D reconstruction surface results of X-ray images in this paper. This paper proposes an automatic image data acquisition method to acquire images. According to the characteristics of X-ray images, an image processing method is drawn up. In this paper, the original image and the processed X-ray image are divided into two groups, and three-dimensional reconstruction is performed respectively, and the visualization effect and reconstruction time of the reconstruction result is compared. Experiments show that the running speed of the program is improved, and the visualization results show that the surface texture refinement and the reconstruction structure of the reconstruction effect after image processing have also been well optimized.

Automatic Hologram Acquisition of Pt Catalyst Nanoparticles on TiO2 Using Particle Detection with Image Processing and AI Classification

Automatic Hologram Acquisition of Pt Catalyst Nanoparticles on TiO₂ Using Particle Detection with Image Processing and AI Classification

User-friendly, High-throughput, and Fully Automated Data Acquisition Software for Single-particle Cryo-electron Microscopy

Single-particle cryo-electron microscopy demands a suitable software package and user-friendly pipeline for high-throughput automatic data acquisition. Here, we present the application of a fully automated image acquisition software package, Latitude-S, and a practical pipeline for data collection of vitrified biomolecules under low-dose conditions.

AGTOC: A novel approach to winter wheat mapping by automatic generation of training samples and one-class classification on Google Earth Engine

Accurate and timely acquisition of crop spatial distribution is a prerequisite for growth monitoring and yield forecasting. Currently, the automatic acquisition of crop distribution at large scales is still a challenge due to the time-consuming processing of remotely sensed imagery and manual collection of sufficient training samples. Although the advent of cloud computing platforms has proved to improve the efficiency and automation of crop type classification, how to obtain sufficient training samples in an efficient and cost-effective way remains unclear. In this research, we developed a new approach integrating the automatic generation of training samples and one-class machine learning classification (AGTOC) for mapping winter wheat over Jiangsu Province, China on Google Earth Engine (GEE). After extracting spatial objects from Sentinel-2 imagery in the season of 2017–2018, this method performed recognition of winter wheat objects based on the unique phenology and spectral features of winter wheat. Then the generated winter wheat objects were further refined and regarded as training samples for provincial winter wheat classification with one-class support vector machine (OCSVM). Furthermore, the transferability of AGTOC was evaluated by applying the classification approach to different seasons (2016–2017 & 2019–2020) and a different sensor (Landsat-8 OLI). According to independent ground truth data, the winter wheat mapping with AGTOC achieved an overall accuracy (OA) of 92.61%. When compared with agricultural census data, the winter wheat area accounted for 99% and 90% of the variability at the municipal and county levels. Furthermore, the OA achieved 88.94% and 90.17% while transferring the AGTOC from 2017–2018 to 2016–2017 and 2019–2020. The transferability of the AGTOC model to Landsat-8 OLI imagery of the same season yielded an OA of 85.98%. These results demonstrated that AGTOC exhibited high efficiency and accuracy across the province, different seasons and sensors without the need of extensive field visits for training sample collection. This proposed approach has great potential in the automatic mapping of winter wheat on GEE at country or global levels.

BIMBased Automatic Acquisition andIntelligent Control Method for PipelineInstallation Schedule for Auxiliary Works of Subway Station

BIMBased Automatic Acquisition andIntelligent Control Method for PipelineInstallation Schedule for Auxiliary Works of Subway Station

Array Tomography Workflow for the Targeted Acquisition of Volume Information using Scanning Electron Microscopy

Electron microscopy is applied in biology and medicine for imaging of cellular and structural details at nanometer resolution. Historically, Transmission Electron Microscopy (TEM) provided insight into cell ultrastructure, but in the recent decade, the development of modern Scanning Electron Microscopes (SEM) has changed the way of looking inside the cells. Even though the resolution of TEM is superior when protein-level structural details are needed, SEM-resolution is sufficient for the majority of the organelle-level cell biology-related questions. The advancement in technology enabled automatic volume acquisition solutions such as Serial block-face imaging (SBF-SEM) and Focused ion beam SEM (FIB-SEM). Nevertheless, to this day, these methods remain inefficient when the identification and navigation to areas of interest are crucial. Without the means for precise localization of target areas before imaging, operators need to acquire much more data than they need (in SBF-SEM), or, even worse, prepare many grids and image them all (in TEM). We propose the strategy of "lateral screening" using Array Tomography in SEM, which facilitates the localization of areas of interest, followed by automated imaging of the relevant fraction of the total sample volume. Array tomography samples are conserved during imaging, and they can be arranged into section libraries ready for repeated imaging. Several examples are shown in which lateral screening enables us to analyze structural details that are incredibly challenging to access with any other method.

Array Tomography Workflow for the Targeted Acquisition of Volume Information using Scanning Electron Microscopy.

Electron microscopy is applied in biology and medicine for imaging of cellular and structural details at nanometer resolution. Historically, Transmission Electron Microscopy (TEM) provided insight into cell ultrastructure, but in the recent decade, the development of modern Scanning Electron Microscopes (SEM) has changed the way of looking inside the cells. Even though the resolution of TEM is superior when protein-level structural details are needed, SEM-resolution is sufficient for the majority of the organelle-level cell biology-related questions. The advancement in technology enabled automatic volume acquisition solutions such as Serial block-face imaging (SBF-SEM) and Focused ion beam SEM (FIB-SEM). Nevertheless, to this day, these methods remain inefficient when the identification and navigation to areas of interest are crucial. Without the means for precise localization of target areas before imaging, operators need to acquire much more data than they need (in SBF-SEM), or, even worse, prepare many grids and image them all (in TEM). We propose the strategy of "lateral screening" using Array Tomography in SEM, which facilitates the localization of areas of interest, followed by automated imaging of the relevant fraction of the total sample volume. Array tomography samples are conserved during imaging, and they can be arranged into section libraries ready for repeated imaging. Several examples are shown in which lateral screening enables us to analyze structural details that are incredibly challenging to access with any other method.

Automatic data acquisition for deep learning

Deep learning (DL) has widespread applications and has revolutionized many industries. Although automated machine learning (AutoML) can help us away from coding for DL models, the acquisition of lots of high-quality data for model training remains a main bottleneck for many DL projects, simply because it requires high human cost. Despite many works on weak supervision ( i.e. , adding weak labels to seen data) and data augmentation ( i.e. , generating more data based on seen data), automatically acquiring training data, via smartly searching a pool of training data collected from open ML benchmarks and data markets, is not explored. In this demonstration, we demonstrate a new system, automatic data acquisition (AutoData), which automatically searches training data from a heterogeneous data repository and interacts with AutoML. It faces two main challenges. (1) How to search high-quality data from a large repository for a given DL task? (2) How does AutoData interact with AutoML to guide the search? To address these challenges, we propose a reinforcement learning (RL)-based framework in AutoData to guide the iterative search process. AutoData encodes current training data and feedbacks of AutoML, learns a policy to search fresh data, and trains in iterations. We demonstrate with two real-life scenarios, image classification and relational data prediction, showing that AutoData can select high-quality data to improve the model.

Research and application of a new type of aqueduct concrete non-destructive inspection robot based on the principle of coherent frequency

The concrete aqueduct has some quality problems such as lacuna and cavity during construction or operation, which seriously affects the safety of aqueduct operation. How to quickly detect the defects of aqueduct is of great significance to provide the basis for the repair and reinforcement of aqueduct. In this paper, based on the coherent frequency method, the automatic walking robot device for concrete nondestructive testing is integrated and assembled. Through wireless communication, the automatic excitation, acquisition and imaging of elastic wave are completed, so as to realize the rapid detection of uniformity and compactness defects of aqueduct concrete structure. Through the test and engineering demonstration application, the detection results are reliable, and the detection efficiency is improved by more than 50%. And the follow-up improvement plan of the system hardware should strengthen the maneuverability of the car, realize precise positioning, strengthen the energy of the seismic source, and improve the overall reliability of the system.

Adaptive preprocessing of character recognition image based on neural network

Words in natural scenes contain abundant information. Automatic acquisition of text information in images can help people understand images more effectively and further process images such as storage, compression and retrieval. Pattern recognition technology is to use machines to simulate people’s various recognition abilities. At present, it mainly simulates people’s visual and auditory abilities. Based on BP neural network in deep learning, a text positioning BP neural network is proposed, which automatically extracts the text features in the image and avoids the defect of using manual design features This paper studies the preprocessing algorithm of Chinese character recognition in natural scenes, including binarization of text regions, extraction of character colors, clustering analysis of colors, segmentation of characters, etc., and designs the rules for merging text regions after positioning. Experimental results show that the algorithm can solve the problem of insufficient recognition ability for text images and long-sequence text images with complex background noise between characters when the background and text gray level are similar.

Loss of nitrogen and phosphorus from farmland runoff and the interception effect of an ecological drainage ditch in the North China Plain—A field study in a modern agricultural park

Agricultural non-point source pollution caused by excessive fertilization is a problem in the North China Plain. The experimental site was at a modern high-tech agricultural park in Dezhou City of Shandong Province that is located within the lower Yellow River impact plain. The fertilization, irrigation, and crop management in the modern agricultural park were investigated to determine the proportion of nitrogen and phosphorus loss of the total input. An ecological drainage ditch was constructed in the modern agricultural park in 2016. At the same time, a Doppler flowmeter and a runoff automatic acquisition instrument were installed in the inlet and outlet of the ecological drainage ditch for monitoring the flow of runoff and collecting runoff samples under natural rainfall in 2018 and 2019. The nitrogen, phosphorus, and sediment runoff contents were determined in the laboratory in order to calculate the loss of nitrogen and phosphorus from farmland runoff and the nitrogen and phosphorus interception rate of the ecological drainage ditch. The results showed that there were a total of 13 runoff events in 2018 and 2019 and that the average concentration of total nitrogen and phosphorus in farmland runoff was 2.63–18.84 mg·L−1and 0.81–13.14 mg·L−1 in both years combined, respectively. The main forms of nitrogen found in runoff were NO3−-N, and the main form of phosphorus found in runoff was particulate phosphorus. The amount of nitrogen and phosphorus lost through runoff was 2.90% and 5.07%, respectively, of the average nitrogen and phosphorus input from both years combined. Runoff was generated when daily precipitation was above 17.4 mm and daily maximum precipitation intensity was above 5.1 mm·h−1. There was a linear relationship between daily precipitation, daily maximum precipitation intensity, and the amount of runoff after natural rainfall. A linear regression equation was established to predict the amount of runoff in the study area. The results indicated that ecological ditches in the watersheds of modern agricultural parks could be used to intercept nitrogen and phosphorus from farmland runoff effectively.

Enhancement of Machinery Activity Recognition in a Mining Environment with GPS Data

Fast-growing methods of automatic data acquisition allow for collecting various types of data from the production process. This entails developing methods that are able to process vast amounts of data, providing generalised knowledge about the analysed process. Appropriate use of this knowledge can be the basis for decision-making, leading to more effective use of the company’s resources. This article presents the approach for data analysis aimed at determining the operating states of a wheel loader and the place where it operates based on the recorded data. For this purpose, we have used several methods, e.g., for clustering and classification, namely: DBSCAN, CART, C5.0. Our approach has allowed for the creation of decision rules that recognise the operating states of the machine. In this study, we have taken into account the GPS signal readings, and thanks to this, we have indicated the differences in machine operation within the designated states in the open pit and at the mine base area. In this paper, we present the characteristics of the selected clusters corresponding to the machine operation states and emphasise the differences in the context of the operation area. The knowledge obtained in this study allows for determining the states based on only a few selected most essential parameters, even without consideration of the coordinates of the machine’s workplace. Our approach enables a significant acceleration of subsequent analyses, e.g., analysis of the machine states structure, which may be helpful in the optimisation of its use.

Semi-automated extraction of surface water based on ZhuHai-1 hyperspectral satellite images

ABSTRACT Surface water, as the most important land resource, profoundly affects the balance of the ecosystem and the development of social economy. The rapid development of remote-sensing technology provides the possibility of dynamic monitoring and real-time automatic extraction of surface water. Based on the index of ZhuHai-1 Orbita-hyperspectral (OHS) pixels, this paper proposes a supervised learning method for semi-automatic surface water extraction. The method first uses a threshold method to segment the cosine distance between pixel spectra, realizes automatic acquisition of training set labels required for supervised classification and effectively improves work efficiency. We then combine the extraction results of the support vector machine (SVM), which only considers spectral information, and the variant full convolutional neural network (VFCN), which only considers spatial information, to obtain more accurate surface water information. In this paper, the analysis of typical waterbodies in four regions showed that the performance of the surface water extraction for all scenes when using this method in this paper is better than that when using the water index (WI), VFCN or SVM. The overall accuracy of this method is above 98.822%, and the kappa coefficients are above 0.9019.

A novel circle center location method for a large-scale wafer

The high-precision circle center location of a wafer can implement the automatic acquisition of the special die, which is one of the most significant steps in wafer surface defect detection. Due to the larger scale of the wafer and the smaller field of view of the camera, the circular arc edge captured is an approximate line segment and has less arc information. The existing methods are mainly used to locate the circle center of the full or more than half of the circular arc captured by a large field of view camera, and it is extremely difficult to accurately locate the circle center of the wafer. To solve this problem, we propose a novel circle center location method for the large-scale wafer. A method for measuring the system angle in the horizontal plane by calibration is presented. Throughthe analysis of multiple error sources and the compensation of systemangle, the system angle inthe horizontal plane is the main source of error that causes the positioningerror of the inspection system. Based on the distance constraint and the system angle compensation in the horizontal plane, the edge point set coordinates of multi-segment circular arc images are accurately extracted and transformed in the reference coordinate system. A new hierarchical Bayesian model, which takes the initial circle parameter obtained by an improved method as a priori constraint, is utilized to accurately estimate the circle center and radius of the wafer. The effectiveness of the proposed method is verified by various experiments, which are conducted with real 8-inch and 12-inch wafers using the inspection equipment developed.

The Development of Automated Testing Acquisition Terminal

With the mature of single phase intelligent electric meter automation detection technology, concentrator and shift acquisition terminal also need to implement automated testing. The current domestic reality for some measuring equipment in the production of automated verification or a link in the test, which still have some technical problems. It combined with the necessary human intervention, virtually increased the cost and certain security hidden danger, make the lost of the role of automation and automated verification or testing is true meaning. However, how to realize the automation of collection terminal detection is mainly to solve the problem. For intelligent electricity information collection system construction, the problems arising from the use and application, put forward to realize the automatic acquisition terminal detection scheme, for the domestic intelligent electricity information acquisition terminal test provide beneficial guidance and reference.