To see the other types of publications on this topic, follow the link: Counting-set automata.
Journal articles on the topic 'Counting-set automata'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Counting-set automata.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Turoňová, Lenka, Lukáš Holík, Ondřej Lengál, Olli Saarikivi, Margus Veanes, and Tomáš Vojnar. "Regex matching with counting-set automata." Proceedings of the ACM on Programming Languages 4, OOPSLA (November 13, 2020): 1–30. http://dx.doi.org/10.1145/3428286.
Full text
2
SCHEICHER, KLAUS, and JÖRG M. THUSWALDNER. "Canonical number systems, counting automata and fractals." Mathematical Proceedings of the Cambridge Philosophical Society 133, no. 1 (July 2002): 163–82. http://dx.doi.org/10.1017/s0305004102005856.
Full textAbstract:
In this paper we study properties of the fundamental domain [Fscr ]β of number systems, which are defined in rings of integers of number fields. First we construct addition automata for these number systems. Since [Fscr ]β defines a tiling of the n-dimensional vector space, we ask, which tiles of this tiling ‘touch’ [Fscr ]β. It turns out that the set of these tiles can be described with help of an automaton, which can be constructed via an easy algorithm which starts with the above-mentioned addition automaton. The addition automaton is also useful in order to determine the box counting dimension of the boundary of [Fscr ]β. Since this boundary is a so-called graph-directed self-affine set, it is not possible to apply the general theory for the calculation of the box counting dimension of self similar sets. Thus we have to use direct methods.
3
HOLZER, MARKUS, and SEBASTIAN JAKOBI. "FROM EQUIVALENCE TO ALMOST-EQUIVALENCE, AND BEYOND: MINIMIZING AUTOMATA WITH ERRORS." International Journal of Foundations of Computer Science 24, no. 07 (November 2013): 1083–97. http://dx.doi.org/10.1142/s0129054113400327.
Full textAbstract:
We introduce E-equivalence, which is a straightforward generalization of almost-equivalence. While almost-equivalence asks for ordinary equivalence up to a finite number of exceptions, in E-equivalence these exceptions or errors must belong to a (regular) set E. The computational complexity of deterministic finite automata (DFAs) minimization problems and their variants w.r.t. almost- and E-equivalence are studied. We show that there is a significant difference in the complexity of problems related to almost-equivalence, and those related to E-equivalence. Moreover, since hyper-minimal and E-minimal automata are not necessarily unique (up to isomorphism as for minimal DFAs), we consider the problem of counting the number of these minimal automata.
4
Marchant, Ross, Martin Tetard, Adnya Pratiwi, Michael Adebayo, and Thibault de Garidel-Thoron. "Automated analysis of foraminifera fossil records by image classification using a convolutional neural network." Journal of Micropalaeontology 39, no. 2 (October 15, 2020): 183–202. http://dx.doi.org/10.5194/jm-39-183-2020.
Full textAbstract:
Abstract. Manual identification of foraminiferal morphospecies or morphotypes under stereo microscopes is time consuming for micropalaeontologists and not possible for nonspecialists. Therefore, a long-term goal has been to automate this process to improve its efficiency and repeatability. Recent advances in computation hardware have seen deep convolutional neural networks emerge as the state-of-the-art technique for image-based automated classification. Here, we describe a method for classifying large foraminifera image sets using convolutional neural networks. Construction of the classifier is demonstrated on the publicly available Endless Forams image set with a best accuracy of approximately 90 %. A complete automatic analysis is performed for benthic species dated to the last deglacial period for a sediment core from the north-eastern Pacific and for planktonic species dated from the present until 180 000 years ago in a core from the western Pacific warm pool. The relative abundances from automatic counting based on more than 500 000 images compare favourably with manual counting, showing the same signal dynamics. Our workflow opens the way to automated palaeoceanographic reconstruction based on computer image analysis and is freely available for use.
5
Ying, Yu Ming, and Xiao Hong Yang. "Automatic Counting System Based on MCU." Applied Mechanics and Materials 273 (January 2013): 547–50. http://dx.doi.org/10.4028/www.scientific.net/amm.273.547.
Full textAbstract:
For the low accuracy and low efficiency of artificial counting problem, we introduced a set of automatic counting system which can be applied in the particulate workpiece counting. With infrared transmitting and receiving module as sensor, when a workpiece passes through the surveyed area, the light will be blocked by the workpiece and the receiving module will emit a pulse signal, the counting for the passing workpiece just is the workpiece number. This text make detailed introduction to the hardware circuit and software design and An on-line type automatic control photoelectric counter system is developed based on this photoelectric detection method. The experiments show that the instrument has the advantages of precision counting, fast detection speed and strong practicability.
6
Fernandez-Gallego, Jose, Ma Buchaillot, Nieves Aparicio Gutiérrez, María Nieto-Taladriz, José Araus, and Shawn Kefauver. "Automatic Wheat Ear Counting Using Thermal Imagery." Remote Sensing 11, no. 7 (March 28, 2019): 751. http://dx.doi.org/10.3390/rs11070751.
Full textAbstract:
Ear density is one of the most important agronomical yield components in wheat. Ear counting is time-consuming and tedious as it is most often conducted manually in field conditions. Moreover, different sampling techniques are often used resulting in a lack of standard protocol, which may eventually affect inter-comparability of results. Thermal sensors capture crop canopy features with more contrast than RGB sensors for image segmentation and classification tasks. An automatic thermal ear counting system is proposed to count the number of ears using zenithal/nadir thermal images acquired from a moderately high resolution handheld thermal camera. Three experimental sites under different growing conditions in Spain were used on a set of 24 varieties of durum wheat for this study. The automatic pipeline system developed uses contrast enhancement and filter techniques to segment image regions detected as ears. The approach is based on the temperature differential between the ears and the rest of the canopy, given that ears usually have higher temperatures due to their lower transpiration rates. Thermal images were acquired, together with RGB images and in situ (i.e., directly in the plot) visual ear counting from the same plot segment for validation purposes. The relationship between the thermal counting values and the in situ visual counting was fairly weak (R2 = 0.40), which highlights the difficulties in estimating ear density from one single image-perspective. However, the results show that the automatic thermal ear counting system performed quite well in counting the ears that do appear in the thermal images, exhibiting high correlations with the manual image-based counts from both thermal and RGB images in the sub-plot validation ring (R2 = 0.75–0.84). Automatic ear counting also exhibited high correlation with the manual counting from thermal images when considering the complete image (R2 = 0.80). The results also show a high correlation between the thermal and the RGB manual counting using the validation ring (R2 = 0.83). Methodological requirements and potential limitations of the technique are discussed.
7
Gallardo-Caballero, Ramón, Carlos J. García-Orellana, Antonio García-Manso, Horacio M. González-Velasco, Rafael Tormo-Molina, and Miguel Macías-Macías. "Precise Pollen Grain Detection in Bright Field Microscopy Using Deep Learning Techniques." Sensors 19, no. 16 (August 17, 2019): 3583. http://dx.doi.org/10.3390/s19163583.
Full textAbstract:
The determination of daily concentrations of atmospheric pollen is important in the medical and biological fields. Obtaining pollen concentrations is a complex and time-consuming task for specialized personnel. The automatic location of pollen grains is a handicap due to the high complexity of the images to be processed, with polymorphic and clumped pollen grains, dust, or debris. The purpose of this study is to analyze the feasibility of implementing a reliable pollen grain detection system based on a convolutional neural network architecture, which will be used later as a critical part of an automated pollen concentration estimation system. We used a training set of 251 videos to train our system. As the videos record the process of focusing the samples, this system makes use of the 3D information presented by several focal planes. Besides, a separate set of 135 videos (containing 1234 pollen grains of 11 pollen types) was used to evaluate detection performance. The results are promising in detection (98.54% of recall and 99.75% of precision) and location accuracy (0.89 IoU as the average value). These results suggest that this technique can provide a reliable basis for the development of an automated pollen counting system.
8
Becker, D. E. "Algorithms for automated montage synthesis of images from laser-scanning confocal microscopes." Proceedings, annual meeting, Electron Microscopy Society of America 53 (August 13, 1995): 650–51. http://dx.doi.org/10.1017/s0424820100139627.
Full textAbstract:
An efficient, robust, and widely-applicable technique is presented for computational synthesis of high-resolution, wide-area images of a specimen from a series of overlapping partial views. This technique can also be used to combine the results of various forms of image analysis, such as segmentation, automated cell counting, deblurring, and neuron tracing, to generate representations that are equivalent to processing the large wide-area image, rather than the individual partial views. This can be a first step towards quantitation of the higher-level tissue architecture. The computational approach overcomes mechanical limitations, such as hysterisis and backlash, of microscope stages. It also automates a procedure that is currently done manually. One application is the high-resolution visualization and/or quantitation of large batches of specimens that are much wider than the field of view of the microscope.The automated montage synthesis begins by computing a concise set of landmark points for each partial view. The type of landmarks used can vary greatly depending on the images of interest. In many cases, image analysis performed on each data set can provide useful landmarks. Even when no such “natural” landmarks are available, image processing can often provide useful landmarks.
9
Marin, Ambroise, Emmanuel Denimal, Stéphane Guyot, Ludovic Journaux, and Paul Molin. "A Robust Generic Method for Grid Detection in White Light Microscopy Malassez Blade Images in the Context of Cell Counting." Microscopy and Microanalysis 21, no. 1 (December 16, 2014): 239–48. http://dx.doi.org/10.1017/s1431927614013671.
Full textAbstract:
AbstractIn biology, cell counting is a primary measurement and it is usually performed manually using hemocytometers such as Malassez blades. This work is tedious and can be automated using image processing. An algorithm based on Fourier transform filtering and the Hough transform was developed for Malassez blade grid extraction. This facilitates cell segmentation and counting within the grid. For the present work, a set of 137 images with high variability was processed. Grids were accurately detected in 98% of these images.
10
Kuske, Dietrich, and Markus Lohrey. "First-order and counting theories of ω-automatic structures." Journal of Symbolic Logic 73, no. 1 (March 2008): 129–50. http://dx.doi.org/10.2178/jsl/1208358745.
Full textAbstract:
AbstractThe logic extends first-order logic by a generalized form of counting quantifiers (“the number of elements satisfying … belongs to the set C”). This logic is investigated for structures with an injectively ω-automatic presentation. If first-order logic is extended by an infinity-quantifier, the resulting theory of any such structure is known to be decidable [6]. It is shown that, as in the case of automatic structures [21], also modulo-counting quantifiers as well as infinite cardinality quantifiers (“there are many elements satisfying …”) lead to decidable theories. For a structure of bounded degree with injective ω-automatic presentation, the fragment of that contains only effective quantifiers is shown to be decidable and an elementary algorithm for this decision is presented. Both assumptions (ω-automaticity and bounded degree) are necessary for this result to hold.
11
Bélisle, François, Nicolas Saunier, Guillaume-Alexandre Bilodeau, and Sebastien le Digabel. "Optimized Video Tracking for Automated Vehicle Turning Movement Counts." Transportation Research Record: Journal of the Transportation Research Board 2645, no. 1 (January 2017): 104–12. http://dx.doi.org/10.3141/2645-12.
Full textAbstract:
This paper proposes a new method for automatically counting vehicle turning movements based on video tracking, expanding on previous work on optimization of parameters for road user trajectory extraction and on automated trajectory clustering. The counting method is composed of three main steps: an automated tracker that extracts vehicle trajectories from video data, an automated trajectory clustering algorithm, and an optimization algorithm. The proposed method was applied to obtain turning movement counts in three typical traffic engineering case studies in Canada representing industry-type conditions. These exhibited varying levels of tracking difficulty, ranging from a single-lane off-ramp to a six-movement intersection with a stop and a right-turn channel. Because of a limitation of the data set, giving flows per movement and not per lane, all sites were chosen with a single lane per movement. The 3-h morning peak period was used in the case studies. The results show an average weighted generalization error of 12% for more than 3,700 vehicles automatically analyzed for more than 8 h of video, ranging from 9.5% to 19.5%. The generalization error is on average 8.6% (and as low as 6.0% per movement) for the 3,084 uninterrupted vehicles that are in plain view of the camera. This paper describes in detail the methodology used and discusses the factors that affect counting performance and how to improve counting accuracy in further research.
12
Okunev, Alexey G., Mikhail Yu Mashukov, Anna V. Nartova, and Andrey V. Matveev. "Nanoparticle Recognition on Scanning Probe Microscopy Images Using Computer Vision and Deep Learning." Nanomaterials 10, no. 7 (June 30, 2020): 1285. http://dx.doi.org/10.3390/nano10071285.
Full textAbstract:
Identifying, counting and measuring particles is an important component of many research studies. Images with particles are usually processed by hand using a software ruler. Automated processing, based on conventional image processing methods (edge detection, segmentation, etc.) are not universal, can only be used on good-quality images and need to set a number of parameters empirically. In this paper, we present results from the application of deep learning to automated recognition of metal nanoparticles deposited on highly oriented pyrolytic graphite on images obtained by scanning tunneling microscopy (STM). We used the Cascade Mask-RCNN neural network. Training was performed on a dataset containing 23 STM images with 5157 nanoparticles. Three images containing 695 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in the verification set with 0.93 precision and 0.78 recall. Predicted contour refining with 2D Gaussian function was a proposed option. The accuracies for mean particle size calculated from predicted contours compared with ground truth were in the range of 0.87–0.99. The results were compared with outcomes from other generally available software, based on conventional image processing methods. The advantages of deep learning methods for automatic particle recognition were clearly demonstrated. We developed a free open-access web service “ParticlesNN” based on the trained neural network, which can be used by any researcher in the world.
13
Fedorenko, V. F., V. V. Kirsanov, and N. P. Mishurov. "Analysis of different options of use of milking robots in dairy livestock." Machinery and Equipment for Rural Area, no. 7 (July 26, 2021): 33–37. http://dx.doi.org/10.33267/2072-9642-2021-7-33-37.
Full textAbstract:
It has been established that currently there are about 700 milking robots in dairy farming in Russia, with a predominance of mono-box models. In flowconveyor robotic milking, it is possible to significantly reduce the number of automatic handlers and reduce the cost of a set of equipment due to the separate performing process steps for connecting the teatcups and the milking process itself compared to mono-boxes (one robot – one cow). It is noted that the latter are more expedient to use on small farms counting for up to 200-250 heads. For those farms that have 400 cows and more, it is more rational to build Yolochka milking parlors equipped with quarter-milking handlers and serviced by operators, which can then be robotized while keeping the milking trench for training animals in robotic milking. For those farms that have 800 heads and more, it is advisable to use automated rotating milking parlors, also along with their gradual transfer to robotic systems.
14
Zhou, Wenjing, Xueyan Zhu, Mengmeng Gu, and Fengjun Chen. "Spruce Counting Based on Lightweight Mask R-CNN with UAV Images." International Journal of Circuits, Systems and Signal Processing 15 (July 20, 2021): 634–42. http://dx.doi.org/10.46300/9106.2021.15.70.
Full textAbstract:
To achieve rapid and accurate counting of seedlings on mobile terminals such as Unmanned Aerial Vehicle (UAV), we propose a lightweight spruce counting model. Given the difficulties of spruce adhesion and complex environment interference, we adopt the Mask R-CNN as the basic model, which performs instance-level segmentation of the target. To successfully apply the basic model to the mobile terminal applications, we modify the Mask R-CNN model in terms of the light-weighted as follows: the feature extraction network is changed to MobileNetV1 network; NMS is changed to Fast NMS. At the implementation level, we expand the 403 spruce images taken by UAV to the 1612 images, where 1440 images are selected as the training set and 172 images are selected as the test set. We evaluate the lightweight Mask R-CNN model. Experimental results indicate that the Mean Counting Accuracy (MCA) is 95%, the Mean Absolute Error (MAE) is 8.02, the Mean Square Error (MSE) is 181.55, the Average Counting Time (ACT) is 1.514 s, and the Model Size (MS) is 90Mb. We compare the lightweight Mask R-CNN model with the counting effects of the Mask R-CNN model, the SSD+MobileNetV1 counting model, the FCN+Hough circle counting model, and the FCN+Slice counting model. ACT of the lightweight Mask R-CNN model is 0.876 s, 0.359 s, 1.691 s, and 2.443 s faster than the other four models, respectively. In terms of MCA, the lightweight Mask R-CNN model is similar to the Mask R-CNN model. It is 4.2%, 5.2%, and 9.3% higher than the SSD+MobileNetV1 counting model, the FCN+Slice counting model, and the FCN+Hough circle counting model, respectively. Experimental results demonstrate that the lightweight Mask R-CNN model achieves high accuracy and real-time performance, and makes a valuable exploration for the deployment of automatic seedling counting on the mobile terminal.
15
Ranefall, Petter, Kenneth Wester, Christer Busch, Per-Uno Malmström, and Ewert Bengtsson. "Automatic Quantification of Microvessels Using Unsupervised Image Analysis." Analytical Cellular Pathology 17, no. 2 (1998): 83–92. http://dx.doi.org/10.1155/1998/490585.
Full textAbstract:
An automatic method for quantification of images of microvessels by computing area proportions and number of objects is presented. The objects are segmented from the background using dynamic thresholding of the average component size histogram.To be able to count the objects, fragmented objects are connected, all objects are filled, and touching objects are separated using a watershed segmentation algorithm.The method is fully automatic and robust with respect to illumination and focus settings.A test set consisting of images grabbed with different focus and illumination for each field of view, was used to test the method, and the proposed method showed less variation than the intraoperator variation using manual threshold.Further, the method showed good correlation to manual object counting (r= 0.80) on an other test set.
16
Prabhu, Ghanashyama, Noel E. O’Connor, and Kieran Moran. "Recognition and Repetition Counting for Local Muscular Endurance Exercises in Exercise-Based Rehabilitation: A Comparative Study Using Artificial Intelligence Models." Sensors 20, no. 17 (August 25, 2020): 4791. http://dx.doi.org/10.3390/s20174791.
Full textAbstract:
Exercise-based cardiac rehabilitation requires patients to perform a set of certain prescribed exercises a specific number of times. Local muscular endurance exercises are an important part of the rehabilitation program. Automatic exercise recognition and repetition counting, from wearable sensor data, is an important technology to enable patients to perform exercises independently in remote settings, e.g., their own home. In this paper, we first report on a comparison of traditional approaches to exercise recognition and repetition counting (supervised ML and peak detection) with Convolutional Neural Networks (CNNs). We investigated CNN models based on the AlexNet architecture and found that the performance was better than the traditional approaches, for exercise recognition (overall F1-score of 97.18%) and repetition counting (±1 error among 90% observed sets). To the best of our knowledge, our approach of using a single CNN method for both recognition and repetition counting is novel. Also, we make the INSIGHT-LME dataset publicly available to encourage further research.
17
Дубровский, В. А., И. В. Забенков, Е. П. Карпочева, and С. О. Торбин. "Идентификация и счет эритроцитов нативной донорской крови человека методом цифровой оптической микроскопии с использованием спектрально фильтрованного освещения." Оптика и спектроскопия 129, no. 3 (2021): 327. http://dx.doi.org/10.21883/os.2021.03.50660.208-20.
Full textAbstract:
The possibility of identification and counting of native donor blood erythrocytes based by static, non-flow digital optical microscopy was studied. The object of study was the whole donor blood diluted by saline and placed into Goryaev's counting chamber. The sample was examined in transmitted light by a Lumam P-8 digital optical microscope equipped by a Basler acA920-40um camera. In order to identify erythrocytes by spectral characteristics two sets of micrographs of 20 pieces in each were obtained. In the first set there was no optical filter in the illumination channel of the microscope and in the second set an interference filter for a 420 nm wavelength with a 10 nm bandwidth was used. The characteristics of the interference filter were chosen to come more close to the Soret band of the RBC hemoglobin to obtain the best contrast for photographic images. The technique for automated analysis of micrographs using the OpenCV software was developed to recognize erythrocytes and to carry out their counting. The results of the computer RBC counting were compared with the manually counted red blood cells. It was found that for computer approach accepted the proportion of the erythrocytes identified and counted in averages was 97-98%.
18
Kurzin, Nikolay N., Dmitriy V. Lebedev, Evgeniy A. Rozhkov, and Vadim A. Bezverkhiy. "The Optoelectronic Installation for Counting the Seeds of Agricultural Crops." Elektrotekhnologii i elektrooborudovanie v APK, no. 3 (September 20, 2020): 115–19. http://dx.doi.org/10.22314/2658-4859-2020-67-3-115-119.
Full textAbstract:
Modern laboratory devices for counting the seeds are widely used in grain-cleaning enterprises and in research and agricultural centers, but they have disadvantages. (Research purpose) The research purpose is in design an innovative compact automatic optical-electronic plant for counting the seeds, which will have a minimum size and function according to a pre-set algorithm. (Materials and methods) The article describes the determined parameters of an optoelectronic device for counting the number of grains, taking into account the requirements for laboratory devices for counting the seeds of various agricultural crops. Authors have studied the operation of a device for counting the seeds of various agricultural crops using a designed algorithm. The installation has been modernized. The feeding mechanism has been changed and modern optoelectronic elements have been added to the recognition system, which make it possible to perform high-quality seed counting. (Results and discussion) It was found that the optocouplers added to the design after an experimental study of 10.000 seeds of wheat, corn, sunflower, rice, and oats showed deviations in time depending on the culture of 5-10 percent. (Conclusions) It was found that the design of an automatic optoelectronic plant for counting the number of seeds provides an effective process of working according to a predetermined algorithm with high accuracy of estimating the number of seeds (an error of about 1.8 percent). The device has a minimum overall size (3-5 kilograms). It was found that using a DC motor allows to create vibration on the plane for feeding seeds to the analysis zone. The developed installation has a minimum number of elements, which makes it possible to increase the reliability of its operation and durability to several decades.
19
Yu, Ta-Chuan, Wen-Chien Chou, Chao-Yuan Yeh, Cheng-Kun Yang, Sheng-Chuan Huang, Feng Ming Tien, Chi-Yuan Yao, et al. "Automatic Bone Marrow Cell Identification and Classification By Deep Neural Network." Blood 134, Supplement_1 (November 13, 2019): 2084. http://dx.doi.org/10.1182/blood-2019-125322.
Full textAbstract:
Purpose Differential counting of blood cells is the basis of diagnostic hematology. In many circumstances, identification of cells in bone marrow smears is the golden standard for diagnosis. Presently, methods for automatic differential counting of peripheral blood are readily available commercially. However, morphological assessment and differential counting of bone marrow smears are still performed manually. This procedure is tedious, time-consuming and laden with high inter-operator variation. In recent years, deep neural networks have proven useful in many medical image recognition tasks, such as diagnosis of diabetic retinopathy, and detection of cancer metastasis in lymph nodes. However, there has been no published work on using deep neural networks for complete differential counting of entire bone marrow smear. In this work, we present the results of using deep convolutional neural network for automatic differential counting of bone marrow nucleated cells. Materials & Methods The bone marrow smears from patients with either benign or malignant disorders in National Taiwan University Hospital were recruited in this study. The bone marrow smears are stained with Liu's stain, a modified Romanowsky stain. Digital images of the bone marrow smears were taken using 1000x oil immersion lens and 20MP color CCD camera on a single microscope with standard illumination and white-balance settings. The contour of each nucleated cell was artificially defined. These cells were then divided into a training/validation set and a test set. Each cell was then classified into 1 of the 11 categories (blast, promyelocyte, neutrophilic myelocyte, neutrophilic metamyelocyte, neutrophils, eosinophils and precursors, basophil, monocyte and precursors, lymphocyte, erythroid lineage cells, and invalid cell). In training/validation set, the classification of each cell was annotated once by experienced medical technician or hematologist. The annotated dataset was used to train a Path-Aggregation Network for instance segmentation task. In test set, cell classification was annotated by three medical technicians or hematologists; only over 2/3 consensus was regarded as valid. After the neural network model was fully trained, the ability of the model to classify and detect bone marrow nucleated cells was evaluated in terms of precision, recall and accuracy. During the model training, we used group normalization and stochastic gradient descent optimizer for training. Random noise, Gaussian blur, rotation, contrast and color shift were also used as means for data augmentation. Results The digital images of 150 bone marrow aspirate smears were taken for this study. They included 61 for acute leukemia, 39 for lymphoma, 2 for myelodysplastic syndrome (MDS), 2 for myeloproliferative neoplasm (MPN), 10 for MDS/MPN, 12 for multiple myeloma, 4 for hemolytic anemia, 9 for aplastic anemia, 8 for infectious etiology and 3 for solid cancers. The final data contained 5927 images and 187730 nucleated bone marrow cells, which were divided into 2 sets: 5630 images containing 170966 cells as the training/validation set, and 297 images containing 16764 cells as the test set. Among the 16764 cells annotated in test set, 15676 cells (93.6 %) reached over 2/3 consensus. The trained neural network achieved 0.832 recall and 0.736 precision for cell detection task, 0.79 mean intersection over union (IOU) for cell segmentation task, mean average precision of 0.659 and accuracy of 0.801 for cell classification. For individual cell categories, the model performs the best with "erythroid-lineage-cells" (0.971 recall, 0.935 precision) and the worst with "monocyte-and-precursors" (0.825 recall, 0.337 precision). Conclusions We have created the largest and the most comprehensive annotated bone marrow smear image dataset for deep neural network training. Compared with previous works, our approach is more practical for clinical application because it is able to take in an entire field of smear and generate differential counts without any other preprocessing steps. Current results are highly encouraging. With continued expansion of dataset, our model would be more precise and clinically useful. Figure Disclosures Yeh: aether AI: Other: CEO and co-founder. Yang:aether AI: Employment. Tien:Novartis: Honoraria; Daiichi Sankyo: Honoraria; Celgene: Research Funding; Roche: Honoraria; Johnson &Johnson: Honoraria; Alexion: Honoraria; BMS: Honoraria; Roche: Research Funding; Celgene: Honoraria; Pfizer: Honoraria; Abbvie: Honoraria. Hsu:aether AI: Employment.
20
Beitel, David, Spencer McNee, Fraser McLaughlin, and Luis F. Miranda-Moreno. "Automated Validation and Interpolation of Long-Duration Bicycle Counting Data." Transportation Research Record: Journal of the Transportation Research Board 2672, no. 43 (July 1, 2018): 75–86. http://dx.doi.org/10.1177/0361198118783123.
Full textAbstract:
Bicycle flow data is crucial for transportation agencies to evaluate and improve cycling infrastructure. Average annual daily bicyclists (AADB) is commonly used in research and practice as a metric for cycling studies such as ridership analysis, infrastructure planning, and injury risk. AADB is estimated by averaging the daily cyclist totals measured throughout the year using a long-term automated bicycle counter, or by using long-term bicycle counting data to extrapolate data from a short-term counting site. Extrapolation of a short-term bicycle counting site requires an accurate and complete set of daily factors from a group of references: long-term bicycle counters. In practice, validation of reference data is done manually, an exercise that is time-consuming but crucial as significant error can be introduced into AADB extrapolation if reference data are not validated. This paper proposes an automated method to validate long-term bicycle count data and interpolate anomalous portions of data. As part of this work, the methods are validated using a relatively large dataset of automated bicycle counts. For validation of our approach, data anomalies are created artificially in a way that removes data (first trial), or reduces counts to 25% or 40% of the measured bicycle counts (second and third trials), for 6 hours, 12 hours, and full days. Of the more than 100 generated anomalies, the validation process flagged approximately 90% in the first and second trials and 80% in the third trial. The average absolute relative error of the interpolated daily values was approximately 10% for all three trials.
21
Ojieabu, Clement E. "Developed Automated Vehicle Traffic Light Controller System for Cities in Nigeria." Journal of Advances in Science and Engineering 1, no. 1 (April 30, 2018): 19–25. http://dx.doi.org/10.37121/jase.v1i1.6.
Full textAbstract:
This paper presents a research work that was carried out to resolve challenges of traffic light system. This work employs the use of a microcontroller, an inductive loop which acts as the vehicle detector and LED’s (light emitting diodes) for simulating the red, yellow and green light in a traffic light. The inductive loop is embedded in pavement along the road which senses the presence of vehicle. When a vehicle passes across the loop, the magnetic field changes and the inductance of the coil is decreased resulting in a frequency change of the oscillator which is detected by the controller. The interrupt is set to make the traffic light allow the movement of vehicles on the lane with many vehicles on it according to information on the counter. This means that when the system discovers the lane with many vehicles by the number on the counter, the interrupt function comes into operation by interrupting the counting process and allowing the system to allow movement in that lane. Then the system resumes back to counting after this process is done. The test results show that the system can be physically and successfully implemented.
22
Friel, J. J., and E. B. Prestridge. "Image Analysis—Turning Images Into Data." Microscopy and Microanalysis 4, S2 (July 1998): 58–59. http://dx.doi.org/10.1017/s1431927600020419.
Full textAbstract:
Image analysis is the process of quantifying some aspect of an image—its particle size distribution, for example. Manual methods were in use long before computers made image analysis much faster and more reproducible. Linear measurements of diameter, point counting to measure volume fraction, and intercept counting to determine grain size have been used for over 100 years. Automatic image analysis (AIA), however, can make more measurements, and even calculate derived measurements, such as aspect ratio or circularity. AIA of a specimen or micrograph, of course, is only as good as the contrast mechanism used, so the imaging signal must be chosen carefully to reveal to the computer what is to be measured. Obtaining sufficient contrast is often the limiting task.Once an imaging signal is chosen and the digital resolution set, the computer can analyze the image. The feature descriptors can be generic:
23
Kermanidis, Katia Lida, Nikos Fakotakis, and George Kokkinakis. "Automatic acquisition of verb subcategorization information by exploiting mininal linguistic resources." International Journal of Corpus Linguistics 9, no. 1 (April 29, 2004): 1–28. http://dx.doi.org/10.1075/ijcl.9.1.01ker.
Full textAbstract:
A set of well known statistical filtering methods (binomial hypothesis testing, log-likelihood ratio, t-test, thresholds on relative frequencies) is used on Modern Greek and English corpora in order to automatically acquire verb subcategorization frames that are not limited in number and are not known beforehand. As sophisticated linguistic resources and tools are not available for most languages (including Modern Greek), pre-processing of our corpora reaches merely the stage of elementary, intrasentential, non-embedded phrase chunking. By forming, permutating and counting subsets of the verb's neighboring set of phrases, and by applying the statistical filters mentioned previously, valid syntactic frames of verbs are detected. The results achieved were comparable to and, in several cases, better than the ones of previous approaches, even approaches utilizing richer resources. Incorporating the extracted list of frames into a shallow parser, the performance of the latter increases by almost 6%, showing thereby the importance of the acquired knowledge.
24
JIJI, G. WISELIN, HENRY SELVARAJ, and G. EVELIN SUJI. "SUPERVISED CLASSIFICATION OF WHITE BLOOD CELLS BY FUSION OF COLOR TEXTURE FEATURES AND NEURAL NETWORK." International Journal of Computational Intelligence and Applications 10, no. 04 (December 2011): 471–80. http://dx.doi.org/10.1142/s1469026811003197.
Full textAbstract:
Nucleus segmentation is one of important steps in the automatic white blood cell differential counting. In this paper, we proposed a technique to segment images of the nucleus. We analyze a set of white-blood-cell-nucleus-based features using color fuzzy texture spectrum (Base 5). We applied artificial neural network for classification. We compared the results with moment based features. The classification performances are evaluated by class wise classification rates. The results show that the features using nucleus alone could be utilized to achieve a classification rate of 99.05% on the test sets.
25
Petra, Hlaváčková, Slováčková Hana, Březina David, and Michal Jakub. "Comparison of results of visitor arrival monitoring using regression analysis." Journal of Forest Science 64, No. 7 (August 1, 2018): 303–12. http://dx.doi.org/10.17221/20/2018-jfs.
Full textAbstract:
Monitoring of visitor arrivals is one of the tools which help to ensure good-quality and suitable management of the respective area. This paper is aimed at the monitoring of visitor arrivals when the visitors are counted automatically using a field counting device, namely a pyroelectric sensor. In 2015, visitor arrival monitoring using a pyro sensor was conducted on the selected forest roads in the Křtiny Training Forest Enterprise of Masaryk Forest. Since this method should be employed in another project, it was necessary to find out whether the pyroelectric sensor is a reliable tool and whether it can be used for further research. The aim of this paper is to perform a regression analysis of the data collected at the selected site in order to determine whether the pyroelectric sensor provides relevant information. Two data sets acquired during the first week of the monitoring of visitor arrivals at the single site will be compared. The one set includes data obtained by automatic monitoring using the pyro sensor, the other set contains data gained by means of manual counting by students of the Faculty of Forestry and Wood Technology. Two directions of visitor flows were monitored – in and out. The data were statistically processed using the ADSTAT software. Results of the regression analysis show that the results of the visitor arrival monitoring carried out using a pyro sensor differ just slightly from those gained by manual counting.
26
Beitel, David, Spencer McNee, and Luis F. Miranda-Moreno. "Quality Measure of Short-Duration Bicycle Counts." Transportation Research Record: Journal of the Transportation Research Board 2644, no. 1 (January 2017): 64–71. http://dx.doi.org/10.3141/2644-08.
Full textAbstract:
The average annual daily bicyclists (AADB) measure is commonly used in research and practice as a metric for cycling studies, such as bike ridership analysis, infrastructure planning, and injury risk. It is estimated in one of two ways: by averaging the daily cyclist totals measured throughout the year with a long-term automated bicycle counter, or by using a long-term bicycle counter to extrapolate data from a short-term counting site. Unfortunately, extrapolation of a short-term bicycle counting site can produce inaccurate AADB estimates as a result of different error sources; the range of possible error is highly correlated to several characteristics of the short-term count, such as the counting period, flow intensity, and time of year. This paper proposes a simple method to estimate the quality of a short-term count through a single metric combining five factors associated with the count variation: duration, average demand, time of year, stability, and correlation with the reference count. The method is validated with the use of a relatively large data set of automated bicycle counts. The quality measure, with a range from 0 to 10, is negatively correlated with the absolute relative error (ARE) of the AADB estimation. Results show distinct ARE distributions for different quality measure classes. The average ARE for the lowest quality class is 13.5% compared with an average ARE of 3.0% for the highest quality class. The maximum ARE (95% confidence) is 35% for the lowest quality class compared with 7.5% for the highest quality class.
27
Zhou, Chengquan, Hongbao Ye, Jun Hu, Xiaoyan Shi, Shan Hua, Jibo Yue, Zhifu Xu, and Guijun Yang. "Automated Counting of Rice Panicle by Applying Deep Learning Model to Images from Unmanned Aerial Vehicle Platform." Sensors 19, no. 14 (July 13, 2019): 3106. http://dx.doi.org/10.3390/s19143106.
Full textAbstract:
The number of panicles per unit area is a common indicator of rice yield and is of great significance to yield estimation, breeding, and phenotype analysis. Traditional counting methods have various drawbacks, such as long delay times and high subjectivity, and they are easily perturbed by noise. To improve the accuracy of rice detection and counting in the field, we developed and implemented a panicle detection and counting system that is based on improved region-based fully convolutional networks, and we use the system to automate rice-phenotype measurements. The field experiments were conducted in target areas to train and test the system and used a rotor light unmanned aerial vehicle equipped with a high-definition RGB camera to collect images. The trained model achieved a precision of 0.868 on a held-out test set, which demonstrates the feasibility of this approach. The algorithm can deal with the irregular edge of the rice panicle, the significantly different appearance between the different varieties and growing periods, the interference due to color overlapping between panicle and leaves, and the variations in illumination intensity and shading effects in the field. The result is more accurate and efficient recognition of rice-panicles, which facilitates rice breeding. Overall, the approach of training deep learning models on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a global scale.
28
Grosjean, Philippe, Marc Picheral, Caroline Warembourg, and Gabriel Gorsky. "Enumeration, measurement, and identification of net zooplankton samples using the ZOOSCAN digital imaging system." ICES Journal of Marine Science 61, no. 4 (January 1, 2004): 518–25. http://dx.doi.org/10.1016/j.icesjms.2004.03.012.
Full textAbstract:
Abstract Identifying and counting zooplankton are labour-intensive and time-consuming processes that are still performed manually. However, a new system, known as ZOOSCAN, has been designed for counting zooplankton net samples. We describe image-processing and the results of (semi)-automatic identification of taxa with various machine-learning methods. Each scan contains between 1500 and 2000 individuals <0.5 mm. We used two training sets of about 1000 objects each divided into 8 (simplified) and 29 groups (detailed), respectively. The new discriminant vector forest algorithm, which is one of the most efficient methods, discriminates between the organisms in the detailed training set with an accuracy of 75% at a speed of 2000 items per second. A supplementary algorithm tags objects that the method classified with low accuracy (suspect items), such that they could be checked by taxonomists. This complementary and interactive semi-automatic process combines both computer speed and the ability to detect variations in proportions and grey levels with the human skills to discriminate animals on the basis of small details, such as presence/absence or number of appendages. After this checking process, total accuracy increases to between 80% and 85%. We discuss the potential of the system as a standard for identification, enumeration, and size frequency distribution of net-collected zooplankton.
29
Kruchak, Liudmyla, and Volodymyr Muravskyi. "Automation of receivables accounting based on an integrated database of counterparties." Herald of Ternopil National Economic University, no. 1(83) (February 22, 2017): 109–18. http://dx.doi.org/10.35774/visnyk2017.01.109.
Full textAbstract:
The development of information and communication technology has led to the introduction of electronic communication channels to accounting processes. Electronic communications provide information interaction of all debtors and creditors of a company, through which collec- tion, processing and storage of data on payments to counterparties take place in a consoli- dated database. The received primary information can be used to automate receivables ac- counting. Theoretical and practical issues related to automation of receivables accounting are identified. The purpose of the article is to theoretically justify and practically introduce the possibilities of setting up a consolidated database on counterparties of a company; to study communication and organizational aspects of automation of receivables accounting in terms of modern information technology. The subject matter of the study is automation of receivables accounting in a company. The scope of the study is a set of theoretical, methodological and practical aspects of automated accounting of receivables through the introduction of a consolidated database of counterparties. Methods of analysis and synthesis are used to structure the area of research through identification and formalization of automation of receivables accounting facilitated by information and communication technology. The article considers a matter related to automation of receivables accounting and proposes recommendations on the introduction of an automated system for settlement with debtors in a company. The authors have developed an information model of a consolidated database which contains information on counterparties, contract relations, and settlement of receivables. A consolidated database acts as an information environment for electronic interactions of all participanys of financial transactions. There is an information exchange between suppliers, customers, banking institutions, legal and factoring organizations, state fiscal and statistics services. However, public access to a consolidated database can lead to a loss of confidential information, which means the need for valid methods of information protection of a company’s accounting system.
30
Xu, Qiaoji, Lingling Jin, James H. Leebens-Mack, and David Sankoff. "Validation of Automated Chromosome Recovery in the Reconstruction of Ancestral Gene Order." Algorithms 14, no. 6 (May 21, 2021): 160. http://dx.doi.org/10.3390/a14060160.
Full textAbstract:
The RACCROCHE pipeline reconstructs ancestral gene orders and chromosomal contents of the ancestral genomes at all internal vertices of a phylogenetic tree. The strategy is to accumulate a very large number of generalized adjacencies, phylogenetically justified for each ancestor, to produce long ancestral contigs through maximum weight matching. It constructs chromosomes by counting the frequencies of ancestral contig co-occurrences on the extant genomes, clustering these for each ancestor and ordering them. The main objective of this paper is to closely simulate the evolutionary process giving rise to the gene content and order of a set of extant genomes (six distantly related monocots), and to assess to what extent an updated version of RACCROCHE can recover the artificial ancestral genome at the root of the phylogenetic tree relating to the simulated genomes.
31
Humaira, Fitrah Maharani, Tengku Musri, Sarimuddin Sarimuddin, Dwi Samsuifin Alham, and Aurista Miftahatul Ilmah. "Analisis Robustness Teks Captcha Paypal HIP Menggunakan Template Matching." JOURNAL OF APPLIED INFORMATICS AND COMPUTING 2, no. 2 (December 5, 2018): 29–33. http://dx.doi.org/10.30871/jaic.v2i2.1039.
Full textAbstract:
CAPTCHA refer to Completely Automated Public Turing test to tell Computers and Humans Apart. CAPTCHA are used to ensure that the operators are human not robots. The basic idea of using CAPTCHA is segmentation and recognition. Random characters, graphic images, or CAPTCHA audio become possible solutions to improve security and resilience for protection systems. In this paper used CAPTCHA random characters. However the CAPTCHA text needs to be analyzed again whether it is still solved by the computer or not it needs to be analyzed, improved, and developed to avoid automatic interference. Data set of text CAPTCHA paypal or so-called paypal HIP with 20 pieces of training data to get the template as much as 36 images that is from the numbers 0-9 and the letter A-Z. This particular paypal HIP data is limited by not using numbers 0 and 1 with the letters O and Q because of the similarity between the data. The method used starts from pre-processing, segmentation, and classification. Pre-processing techniques used consist of removing noise by tresholding and using cleaning techniques. We use bounding box and padding for segmentation method. And then for classification used counting pixel, vertical projections, horizontal projections, dan template correlation. By using these methods will be known which method can recognize CAPTCHA text accurately so as to affect the robustness of the CAPTCHA text.
32
Becker, D. E., H. Ancin, B. Roysam, and J. N. Turner. "Fast automated mosaic synthesis method for 2-D/3-D image analysis of specimens much wider than the field of view." Proceedings, annual meeting, Electron Microscopy Society of America 52 (1994): 224–25. http://dx.doi.org/10.1017/s0424820100168852.
Full textAbstract:
We present an efficient, robust, and widely-applicable technique for computational synthesis of wide-area images from a series of overlapping partial views. The synthesized image is the set union of the areas covered by the partial views, and is called the “mosaic”. One application is the laser-scanning confocal microscopy of specimens that are much wider than the field of view of the microscope. Another is imaging of the retinal periphery using a standard fundus imager. This technique can also be used to combine the results of various forms of image analysis, such as cell counting and neuron tracing, to generate large representations that are equivalent to processing the total mosaic, rather than the individual partial views.The synthesis begins by computing a concise set of landmark points for each partial view. The type of landmarks used can vary greatly depending on the application. For instance, in the retinal imaging application, the vascular branching and crossover points are a natural choice. Likewise, the locations of cells in Figs. 1 and 2 provide a natural set of landmarks for joining these images.
33
Rasmussen, Sune Olander, Katrine Krogh Andersen, Marie-Louise Siggaard-Andersen, and Henrik B. Clausen. "Extracting the annual signal from Greenland ice-core chemistry and isotopic records." Annals of Glaciology 35 (2002): 131–35. http://dx.doi.org/10.3189/172756402781817310.
Full textAbstract:
AbstractStratigraphic dating of ice cores by identification and counting of annual cycles in, for example, chemical measurements requires skill and experience. the work presented here investigates a method of data enhancement which is a first step towards an automated and more objective method of annual-layer counting. the method of dynamical decorrelation is briefly introduced and is applied to data from Site D and NorthGRIP in central Greenland. With this method the measured data series are decomposed into a number of independent source series, one of which exhibits a more pronounced annual variation than the input data themselves. the annual variation is more regular in that (1) some double and triple peaks in the measured series are replaced by single peaks in the extracted signal, and (2) the resulting annual peaks have a much more uniform height. A simple method of determining the number of annual peaks in a series is set up. Using this method, it is shown that it is easier to determine the number of annual peaks in the series produced by dynamical decorrelation than in the original data series. Dynamical decorrelation may thus be used to improve data series prior to dating.
34
Ward, Charlotte, Kevin Baker, Sarah Marks, Dawit Getachew, Tedila Habte, Cindy McWhorter, Paul Labarre, et al. "Determining the Agreement Between an Automated Respiratory Rate Counter and a Reference Standard for Detecting Symptoms of Pneumonia in Children: Protocol for a Cross-Sectional Study in Ethiopia." JMIR Research Protocols 9, no. 4 (April 2, 2020): e16531. http://dx.doi.org/10.2196/16531.
Full textAbstract:
Background Acute respiratory infections (ARIs), primarily pneumonia, are the leading infectious cause of under-5 mortality worldwide. Manually counting respiratory rate (RR) for 60 seconds using an ARI timer is commonly practiced by community health workers to detect fast breathing, an important sign of pneumonia. However, correctly counting breaths manually and classifying the RR is challenging, often leading to inappropriate treatment. A potential solution is to introduce RR counters, which count and classify RR automatically. Objective This study aims to determine how the RR count of an Automated Respiratory Infection Diagnostic Aid (ARIDA) agrees with the count of an expert panel of pediatricians counting RR by reviewing a video of the child’s chest for 60 seconds (reference standard), for children aged younger than 5 years with cough and/or difficult breathing. Methods A cross-sectional study aiming to enroll 290 children aged 0 to 59 months presenting to pediatric in- and outpatient departments at a teaching hospital in Addis Ababa, Ethiopia, was conducted. Enrollment occurred between April and May 2017. Once enrolled, children participated in at least one of three types of RR evaluations: (1) agreement—measure the RR count of an ARIDA in comparison with the reference standard, (2) consistency—measure the agreement between two ARIDA devices strapped to one child, and (3) RR fluctuation—measure RR count variability over time after ARIDA attachment as measured by a manual count. The agreement and consistency of expert clinicians (ECs) counting RR for the same child with the Mark 2 ARI timer for 60 seconds was also measured in comparison with the reference standard. Results Primary outcomes were (1) mean difference between the ARIDA and reference standard RR count (agreement) and (2) mean difference between RR counts obtained by two ARIDA devices started simultaneously (consistency). Conclusions Study strengths included the design allowing for comparison between both ARIDA and the EC with the reference standard RR count. A limitation is that exactly the same set of breaths were not compared between ARIDA and the reference standard since ARIDA can take longer than 60 seconds to count RR. Also, manual RR counting, even when aided by a video of the child’s chest movements, is subject to human error and can result in low interrater reliability. Further work is needed to reach global consensus on the most appropriate reference standard and an acceptable level of agreement to provide ministries of health with evidence to make an informed decision on whether to scale up new automated RR counters. Trial Registration ClinicalTrials.gov NCT03067558; https://clinicaltrials.gov/ct2/show/NCT03067558 International Registered Report Identifier (IRRID) RR1-10.2196/16531
35
Ascari, Lorenzo, Cristina Novara, Virginia Dusio, Ludovica Oddi, and Consolata Siniscalco. "Quantitative methods in microscopy to assess pollen viability in different plant taxa." Plant Reproduction 33, no. 3-4 (October 29, 2020): 205–19. http://dx.doi.org/10.1007/s00497-020-00398-6.
Full textAbstract:
AbstractHigh-quality pollen is a prerequisite for plant reproductive success. Pollen viability and sterility can be routinely assessed using common stains and manual microscope examination, but with low overall statistical power. Current automated methods are primarily directed towards the analysis of pollen sterility, and high throughput solutions for both pollen viability and sterility evaluation are needed that will be consistent with emerging biotechnological strategies for crop improvement. Our goal is to refine established labelling procedures for pollen, based on the combination of fluorescein (FDA) and propidium iodide (PI), and to develop automated solutions for accurately assessing pollen grain images and classifying them for quality. We used open-source software programs (CellProfiler, CellProfiler Analyst, Fiji and R) for analysis of images collected from 10 pollen taxa labelled using FDA/PI. After correcting for image background noise, pollen grain images were examined for quality employing thresholding and segmentation. Supervised and unsupervised classification of per-object features was employed for the identification of viable, dead and sterile pollen. The combination of FDA and PI dyes was able to differentiate between viable, dead and sterile pollen in all the analysed taxa. Automated image analysis and classification significantly increased the statistical power of the pollen viability assay, identifying more than 75,000 pollen grains with high accuracy (R2 = 0.99) when compared to classical manual counting. Overall, we provide a comprehensive set of methodologies as baseline for the automated assessment of pollen viability using fluorescence microscopy, which can be combined with manual and mechanized imaging systems in fundamental and applied research on plant biology. We also supply the complete set of pollen images (the FDA/PI pollen dataset) to the scientific community for future research.
36
Albano, Maria S., William Rothman, Andromachi Scaradavou, Devin P. Blass, John D. McMannis, and Pablo Rubinstein. "Automated Counting of Colony Forming Units (CFU): Towards Standardization of the Measurement of Potency in Cord Blood Cell Therapy Products." Blood 118, no. 21 (November 18, 2011): 485. http://dx.doi.org/10.1182/blood.v118.21.485.485.
Full textAbstract:
Abstract Abstract 485 CFU content of a cord blood (CB) graft is a potency indicator that evaluates the number, viability, functionality and repopulation capability of its hematopoietic progenitor cells (HPC). However, the CFU assay has not yet been amenable to standardization necessary for potency comparisons between CB units from different CB banks. As a result, this key graft attribute cannot be used widely in CB unit selection. One of the critical steps of the CFU assay is CFU counting, which, together with dish plating, contributes to the 14–36% of variability in CFU counts, as evaluated in the NCBP laboratory in a set of 64 CB samples that were plated and 240 CFU dishes independently red and counted by three operators. Our goal is to establish a method to determine HPC potency able to replace the manual CFU counting, that can be standardized, proving accurate high-throughput performance. Our technology includes traditional, manual CFU assay and High Resolution Digital Imaging of stained colonies (CFU-HRDI) [work in progress presented at ASH 2008 and 2009; abstracts 2306 and 2160]. After 14 days of CB culture in Stem Cell Technologies media, culture dishes contents were stained with MTT (3-[4,5-dimethylthiazol-2yl]-2,5-diphenyltetrazolium bromide). A high resolution image of each dish was captured which allowed a clear view of HPC colonies in a color different for CFU-M/GM than for CFU-E. The image also included the dish's barcoded ID. CFU manual counting on the HRDI images showed good correlation with microscope counts (R2 = 0.95; p<0.01; n=151). To improve consistency, eliminate the variability of manual CFU counting and allow high-throughput performance that can be applied widely with acceptable ruggedness, we developed and validated a system that performs automated counting of CFU [ACC] imaged with HRDI. Algorithms were designed to count objects within a specific region of the dish, defined as a “CFU” based on size, optical density and separateness from other objects and also, to read a barcode ID label on the culture dish. The ACC required 20 seconds per image to complete the capture and counting of CFU. The system produces a batch report with CFU counts/dish including the CB unit ID, date and other desired data such as technologist ID, time or lot numbers. A total of N= 12,263 CB samples were tested in duplicate CFU assays. CFU were counted manually and using HRDI-ACC over a period of 24 months. Thus, N= 24,486 CFU culture dishes were evaluated. Assays and manual counting were performed by 8 operators. ACC and manual CFU counts correlated well (R2 = 0.85, slope 1.14, intercept 2.0). An average of n=490 CB samples were evaluated per month. Monthly correlations between manual CFU counts and ACC were consistent (range R2 =0.81–0.89; SD=0.024). In addition, CFU counts by operator and ACC correlated, with R2= between 0.8–0.9 (mean=0.84 and slope 1.11; range 0.92–1.21). ACC was highly reproducible: CFU counts of the same dish were within 1–2%, with n=50 culture dishes each read 10 times. To evaluate the inter-laboratory reproducibility of results and their stability despite operational and environmental variables the ruggedness of the CFU-HRDI-ACC system was evaluated by the NCBP and MDA teams in their respective laboratories. Aliquots of the same unprocessed CB units (n=173) were tested for CFU in duplicate and in parallel by two laboratories following a jointly-developed protocol. Automated CFU counts (ACC) per culture dish were comparable between laboratories. The CB units evaluated had CFU counts in the range of 3 to 93 and 4 to 88 CFU/culture dish in each lab respectively with a highly significant linear correlation (R2 = 0.62, slope 0.8, intercept 6). Manual CFU counts of the same culture dishes using HRDI images were also comparable between both labs (R2=0.67, slope 0.8, intercept 3). Conclusion: CFU is a potency assay that should evaluate the potency of the HPC in a CB graft more completely than the TNC or CD34 counts. The introduction of automated counting (ACC) with the CFU-HRDI system improves the reliability, reproducibility and ruggedness by eliminating the variability of manual CFU counting with contrast phase microscopy and importantly, supports high-throughput implementation and standardization as shown by the consistency achieved in different laboratories. Thus, the CFU content can be used for clinical CB unit selection. Although not described, CFU assessments can be performed before and after cryopreservation and thaw. Disclosures: No relevant conflicts of interest to declare.
37
Jiang, Wang, Zhuang, Li, Li, and Gong. "Leaf Counting with Multi-Scale Convolutional Neural Network Features and Fisher Vector Coding." Symmetry 11, no. 4 (April 10, 2019): 516. http://dx.doi.org/10.3390/sym11040516.
Full textAbstract:
The number of leaves in maize plant is one of the key traits describing its growth conditions. It is directly related to plant development and leaf counts also give insight into changing plant development stages. Compared with the traditional solutions which need excessive human interventions, the methods of computer vision and machine learning are more efficient. However, leaf counting with computer vision remains a challenging problem. More and more researchers are trying to improve accuracy. To this end, an automated, deep learning based approach for counting leaves in maize plants is developed in this paper. A Convolution Neural Network(CNN) is used to extract leaf features. The CNN model in this paper is inspired by Google Inception Net V3, which using multi-scale convolution kernels in one convolution layer. To compress feature maps generated from some middle layers in CNN, the Fisher Vector (FV) is used to reduce redundant information. Finally, these encoded feature maps are used to regress the leaf numbers by using Random Forests. To boost the related research, a relatively single maize image dataset (Different growth stage with 2845 samples, which 80% for train and 20% for test) is constructed by our team. The proposed algorithm in single maize data set achieves Mean Square Error (MSE) of 0.32.
38
Mekhalfi, Mohamed Lamine, Carlo Nicolò, Yakoub Bazi, Mohamad Mahmoud Al Rahhal, and Eslam Al Maghayreh. "Detecting Crop Circles in Google Earth Images with Mask R-CNN and YOLOv3." Applied Sciences 11, no. 5 (March 3, 2021): 2238. http://dx.doi.org/10.3390/app11052238.
Full textAbstract:
Automatic detection and counting of crop circles in the desert can be of great use for large-scale farming as it enables easy and timely management of the farming land. However, so far, the literature remains short of relevant contributions in this regard. This letter frames the crop circles detection problem within a deep learning framework. In particular, accounting for their outstanding performance in object detection, we investigate the use of Mask R-CNN (Region Based Convolutional Neural Networks) as well as YOLOv3 (You Only Look Once) models for crop circle detection in the desert. In order to quantify the performance, we build a crop circles dataset from images extracted via Google Earth over a desert area in the East Oweinat in the South-Western Desert of Egypt. The dataset totals 2511 crop circle samples. With a small training set and a relatively large test set, plausible detection rates were obtained, scoring a precision of 1 and a recall of about 0.82 for Mask R-CNN and a precision of 0.88 and a recall of 0.94 regarding YOLOv3.
39
MARTIS, ROSHAN JOY, HARI PRASAD, CHANDAN CHAKRABORTY, and AJOY KUMAR RAY. "AUTOMATED DETECTION OF ATRIAL FLUTTER AND FIBRILLATION USING ECG SIGNALS IN WAVELET FRAMEWORK." Journal of Mechanics in Medicine and Biology 12, no. 05 (December 2012): 1240023. http://dx.doi.org/10.1142/s0219519412400234.
Full textAbstract:
In this paper, an electrocardiogram (ECG)-based pattern analysis methodology is presented for the detection of artrial flutter and atrial fibrillation using fractal dimension (FD) of continuous wavelet transform (CWT) coefficients of raw ECG signals, sample entropy of heart beat interval time series, and mean heart beat interval features. Accurate diagnosis of atrial tachyarrhythmias is important, as they have different therapeutic options and clinical decisions. In view of this, we have made an attempt to develop a discrimination mechanism between artrial flutter and atrial fibrillation. The methodology consists of mean heart beat interval detection using Pan Tompkins algorithm, calculation of sample entropy of heart beat interval time series, computation of box counting FD from CWT coefficients of raw ECG, statistical significance test, and subsequent pattern classification using different classifiers. Different wavelet basis functions like Daubechies-4, Daubechies-6, Symlet-2, Symlet-4, Symlet-6, Symlet-8, Coiflet-2, Coiflet-5, Biorthogonal-1.3, Biorthogonal-3.1, and Mayer wavelet have been used to compute CWT coefficients. Features are evaluated using statistical analysis and subsequently two-class pattern classification is done using unsupervised (k-means, fuzzy c-means, and Gaussian mixture model) and supervised (error back propagation neural network and support vector machine) techniques. In order to reduce the bias in choosing the training and testing set, k-fold cross validation is used. The obtained results are compared and discussed. It is found that the supervised classifiers provide higher accuracy in comparison to the set of unsupervised classifiers.
40
Leonard, Robert, Matthew Conrad, Edward Van Brunt, Jeffrey Giles, Ed Hutchins, and Elif Balkas. "From Wafers to Bits and Back again: Using Deep Learning to Accelerate the Development and Characterization of SiC." Materials Science Forum 1004 (July 2020): 321–27. http://dx.doi.org/10.4028/www.scientific.net/msf.1004.321.
Full textAbstract:
A non-destructive, fast and accurate extended defect counting method on large diameter SiC wafers is presented. Photoluminescence (PL) signals from extended defects on 4H-SiC substrates were correlated to the specific etch features of Basal Plane Dislocations (BPDs), Threading Screw Dislocations (TSDs), and Threading Edge Dislocations (TED). For our non-destructive technique (NDT), automated defect detection was developed using modern deep convolutional neural networks (DCNN). To train a robust network, we used our large volume data set from our selective etch method of 4H-SiC substrates, already established based on definitive correlations to Synchrotron X-Ray Topography (SXRT) [1]. The defect locations, classifications and counts determined by our DCNN correlate with the subsequently etch-delineated features and counts. Once our network is sufficiently trained we will no longer need destructive methods to characterize extended defects in 4H-SiC substrates.
41
Nordhaug Myhre, Jonas, Miguel Tejedor, Ilkka Kalervo Launonen, Anas El Fathi, and Fred Godtliebsen. "In-Silico Evaluation of Glucose Regulation Using Policy Gradient Reinforcement Learning for Patients with Type 1 Diabetes Mellitus." Applied Sciences 10, no. 18 (September 11, 2020): 6350. http://dx.doi.org/10.3390/app10186350.
Full textAbstract:
In this paper, we test and evaluate policy gradient reinforcement learning for automated blood glucose control in patients with Type 1 Diabetes Mellitus. Recent research has shown that reinforcement learning is a promising approach to accommodate the need for individualized blood glucose level control algorithms. The motivation for using policy gradient algorithms comes from the fact that adaptively administering insulin is an inherently continuous task. Policy gradient algorithms are known to be superior in continuous high-dimensional control tasks. Previously, most of the approaches for automated blood glucose control using reinforcement learning has used a finite set of actions. We use the Trust-Region Policy Optimization algorithm in this work. It represents the state of the art for deep policy gradient algorithms. The experiments are carried out in-silico using the Hovorka model, and stochastic behavior is modeled through simulated carbohydrate counting errors to illustrate the full potential of the framework. Furthermore, we use a model-free approach where no prior information about the patient is given to the algorithm. Our experiments show that the reinforcement learning agent is able to compete with and sometimes outperform state-of-the-art model predictive control in blood glucose regulation.
42
Zhang, Haocheng, Jonathan Li, Ming Cheng, and Cheng Wang. "RAPID INSPECTION OF PAVEMENT MARKINGS USING MOBILE LIDAR POINT CLOUDS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B1 (June 6, 2016): 717–23. http://dx.doi.org/10.5194/isprsarchives-xli-b1-717-2016.
Full textAbstract:
This study aims at building a robust semi-automated pavement marking extraction workflow based on the use of mobile LiDAR point clouds. The proposed workflow consists of three components: preprocessing, extraction, and classification. In preprocessing, the mobile LiDAR point clouds are converted into the radiometrically corrected intensity imagery of the road surface. Then the pavement markings are automatically extracted with the intensity using a set of algorithms, including Otsu’s thresholding, neighbor-counting filtering, and region growing. Finally, the extracted pavement markings are classified with the geometric parameters using a manually defined decision tree. Case studies are conducted using the mobile LiDAR dataset acquired in Xiamen (Fujian, China) with different road environments by the RIEGL VMX-450 system. The results demonstrated that the proposed workflow and our software tool can achieve 93% in completeness, 95% in correctness, and 94% in F-score when using Xiamen dataset.
43
Zhang, Haocheng, Jonathan Li, Ming Cheng, and Cheng Wang. "RAPID INSPECTION OF PAVEMENT MARKINGS USING MOBILE LIDAR POINT CLOUDS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B1 (June 6, 2016): 717–23. http://dx.doi.org/10.5194/isprs-archives-xli-b1-717-2016.
Full textAbstract:
This study aims at building a robust semi-automated pavement marking extraction workflow based on the use of mobile LiDAR point clouds. The proposed workflow consists of three components: preprocessing, extraction, and classification. In preprocessing, the mobile LiDAR point clouds are converted into the radiometrically corrected intensity imagery of the road surface. Then the pavement markings are automatically extracted with the intensity using a set of algorithms, including Otsu’s thresholding, neighbor-counting filtering, and region growing. Finally, the extracted pavement markings are classified with the geometric parameters using a manually defined decision tree. Case studies are conducted using the mobile LiDAR dataset acquired in Xiamen (Fujian, China) with different road environments by the RIEGL VMX-450 system. The results demonstrated that the proposed workflow and our software tool can achieve 93% in completeness, 95% in correctness, and 94% in F-score when using Xiamen dataset.
44
Corkidi, G., R. Diaz-Uribe, J. L. Folch-Mallol, and J. Nieto-Sotelo. "COVASIAM: an Image Analysis Method That Allows Detection of Confluent Microbial Colonies and Colonies of Various Sizes for Automated Counting." Applied and Environmental Microbiology 64, no. 4 (April 1, 1998): 1400–1404. http://dx.doi.org/10.1128/aem.64.4.1400-1404.1998.
Full textAbstract:
ABSTRACT In this work we introduce the confluent and various sizes image analysis method (COVASIAM), an automated colony count technique that uses digital imaging technology for detection and separation of confluent microbial colonies and colonies of various sizes growing on petri dishes. The proposed method takes advantage of the optical properties of the surfaces of most microbial colonies. Colonies in the petri dish are epi-illuminated in order to direct the reflection of concentrated light coming from a halogen lamp towards an image-sensing device. In conjunction, a multilevel threshold algorithm is proposed for colony separation and counting. These procedures improved the quantification of colonies showing confluence or differences in size. We tested COVASIAM with a sample set of microorganisms that form colonies with contrasting physical properties:Saccharomyces cerevisiae, Aspergillus nidulans,Escherichia coli, Azotobacter vinelandii,Pseudomonas aeruginosa, and Rhizobium etli. These physical properties range from smooth to hairy, from bright to opaque, and from high to low convexities. COVASIAM estimated an average of 95.47% (ς = 8.55%) of the manually counted colonies, while an automated method based on a single-threshold segmentation procedure estimated an average of 76% (ς = 16.27) of the manually counted colonies. This method can be easily transposed to almost every image-processing analyzer since the procedures to compile it are generically standard.
45
Calvario, Gabriela, Teresa E. Alarcón, Oscar Dalmau, Basilio Sierra, and Carmen Hernandez. "An Agave Counting Methodology Based on Mathematical Morphology and Images Acquired through Unmanned Aerial Vehicles." Sensors 20, no. 21 (November 2, 2020): 6247. http://dx.doi.org/10.3390/s20216247.
Full textAbstract:
Blue agave is an important commercial crop in Mexico, and it is the main source of the traditional mexican beverage known as tequila. The variety of blue agave crop known as Tequilana Weber is a crucial element for tequila agribusiness and the agricultural economy in Mexico. The number of agave plants in the field is one of the main parameters for estimating production of tequila. In this manuscript, we describe a mathematical morphology-based algorithm that addresses the agave automatic counting task. The proposed methodology was applied to a set of real images collected using an Unmanned Aerial Vehicle equipped with a digital Red-Green-Blue (RGB) camera. The number of plants automatically identified in the collected images was compared to the number of plants counted by hand. Accuracy of the proposed algorithm depended on the size heterogeneity of plants in the field and illumination. Accuracy ranged from 0.8309 to 0.9806, and performance of the proposed algorithm was satisfactory.
46
Zeder, Michael, Silke Van den Wyngaert, Oliver K�ster, Kathrin M. Felder, and Jakob Pernthaler. "Automated Quantification and Sizing of Unbranched Filamentous Cyanobacteria by Model-Based Object-Oriented Image Analysis." Applied and Environmental Microbiology 76, no. 5 (January 4, 2010): 1615–22. http://dx.doi.org/10.1128/aem.02232-09.
Full textAbstract:
ABSTRACT Quantification and sizing of filamentous cyanobacteria in environmental samples or cultures are time-consuming and are often performed by using manual or semiautomated microscopic analysis. Automation of conventional image analysis is difficult because filaments may exhibit great variations in length and patchy autofluorescence. Moreover, individual filaments frequently cross each other in microscopic preparations, as deduced by modeling. This paper describes a novel approach based on object-oriented image analysis to simultaneously determine (i) filament number, (ii) individual filament lengths, and (iii) the cumulative filament length of unbranched cyanobacterial morphotypes in fluorescent microscope images in a fully automated high-throughput manner. Special emphasis was placed on correct detection of overlapping objects by image analysis and on appropriate coverage of filament length distribution by using large composite images. The method was validated with a data set for Planktothrix rubescens from field samples and was compared with manual filament tracing, the line intercept method, and the Uterm�hl counting approach. The computer program described allows batch processing of large images from any appropriate source and annotation of detected filaments. It requires no user interaction, is available free, and thus might be a useful tool for basic research and drinking water quality control.
47
Roysam, B., A. Can, H. Shen, K. Al-Kofahi, and J. N. Turner. "From 3-D Light Microscopic Images to Quantitative Insight." Microscopy and Microanalysis 5, S2 (August 1999): 524–25. http://dx.doi.org/10.1017/s1431927600015944.
Full textAbstract:
This presentation will describe a common core set of widely applicable image analysis techniques for automated quantitative analysis of volumetric microscope image data. Volumetric (as distinct from stereoscopic) three-dimensional (3-D) Microscopy is a rapidly maturing field offering the ability to image thick (compared to the depth of field) specimens using a variety of instrumentation techniques, and producing arrays of brightness values in three spatial dimensions. Also well developed are methods to correct the acquired images for a variety of physical effects including blur and attenuation.Commonly, what is of interest is the best-possible visualization of thick specimens. The next step, increasingly being considered in view of growing computational resources, and progress in image analysis techniques, seeks to quantify many of the processes and effects being studied. In some mainstream fields, such quantitation is essential. For instance, various assays for substance testing in pharmaceutical and chemical industries involve quantitative end points. As an illustration, the Draize assay for ocular irritancy testing of drugs and biochemical products for human use requires counting of live and dead cells that stain differently. Another example is the mouse lymphoma test that requires a 3-D counting of bacterial colonies. Neurobiological assays require morphometry, as well as quantification of changes in neurons as a function of time and various applied stimuli such as drugs, heat, and radiation. Angiogenesis assays require quantification of changes in vascular morphometry. Computerized image analysis is a powerful tool for extracting quantitative data from 3-D images for statistical analysis.
48
Mekhalfi, Mohamed Lamine, Carlo Nicolò, Ivan Ianniello, Federico Calamita, Rino Goller, Maurizio Barazzuol, and Farid Melgani. "Vision System for Automatic On-Tree Kiwifruit Counting and Yield Estimation." Sensors 20, no. 15 (July 29, 2020): 4214. http://dx.doi.org/10.3390/s20154214.
Full textAbstract:
Yield estimation is an essential preharvest practice among most large-scale farming companies, since it enables the predetermination of essential logistics to be allocated (i.e., transportation means, supplies, labor force, among others). An overestimation may thus incur further costs, whereas an underestimation entails potential crop waste. More interestingly, an accurate yield estimation enables stakeholders to better place themselves in the market. Yet, computer-aided precision farming is set to play a pivotal role in this respect. Kiwifruit represents a major produce in several countries (e.g., Italy, China, New and Zealand). However, up to date, the relevant literature remains short of a complete as well as automatic system for kiwifruit yield estimation. In this paper, we present a fully automatic and noninvasive computer vision system for kiwifruit yield estimation across a given orchard. It consists mainly of an optical sensor mounted on a minitractor that surveys the orchard of interest at a low pace. Afterwards, the acquired images are fed to a pipeline that incorporates image preprocessing, stitching, and fruit counting stages and outputs an estimated fruit count and yield estimation. Experimental results conducted on two large kiwifruit orchards confirm a high plausibility (i.e., errors of 6% and 15%) of the proposed system. The proposed yield estimation solution has been in commercial use for about 2 years. With respect to the traditional manual yield estimation carried out by kiwifruit companies, it was demonstrated to save a significant amount of time and cut down on estimation errors, especially when speaking of large-scale farming.
49
Brucher, Rainer, and David Russell. "A NEW METHOD FOR AUTOMATIC DIFFERENTIATION BETWEEN CEREBRAL EMBOLI AND ARTEFACTS." Stroke 32, suppl_1 (January 2001): 344. http://dx.doi.org/10.1161/str.32.suppl_1.344-b.
Full textAbstract:
P29 Introduction: Cerebral embolus monitoring systems suitable for routine clinical use must have the ability to automatically recognise and differentiate between artefacts and emboli. This has to date proven to be an extremely difficult problem to solve. Methods: In this study we present a new advancement with regard to the automatic recognition of cerebral emboli and differentiation from artefacts based on a binary decision tree which includes a completely new parameter. This is the 1/4 Doppler shift for the maximum power reflection of an embolic event at 2.5 MHz insonation frequency compared to 2.0 MHz. A new multifrequency transcranial Doppler system together with this software was used in this study of 2000 artefacts and 100 embolic events in one heart valve patient. The level for event recognition was set at 5db above background Doppler power. The artefacts in 2 healthy controls consisted of 200: tapping the probe, 200: tapping the skull, 200: talking (counting), 200: swallowing, 400: coughing, 200: wrinkling the forehead, 200: clenching the teeth, 400: movement of the skin near the probe. Results: Only two (skin movements near the probe) of the 2000 artefacts were recognised as embolic events. All 100 heart valve emboli were detected and 98 (98%) were correctly classified (specificity 98%). Conclusion: This study suggests that a binary decision tree including 1/4 Doppler shift assessment at 2.0 and 2.5 MHz insonation frequencies will greatly improve the ability to carry out automatic differentiation between artefacts and cerebral emboli during monitoring in routine clinical situations.
50
Balestra, Noah, Gaurav Sharma, Linda M. Riek, and Ania Busza. "Automatic Identification of Upper Extremity Rehabilitation Exercise Type and Dose Using Body-Worn Sensors and Machine Learning: A Pilot Study." Digital Biomarkers 5, no. 2 (July 2, 2021): 158–66. http://dx.doi.org/10.1159/000516619.
Full textAbstract:
<b><i>Background:</i></b> Prior studies suggest that participation in rehabilitation exercises improves motor function poststroke; however, studies on optimal exercise dose and timing have been limited by the technical challenge of quantifying exercise activities over multiple days. <b><i>Objectives:</i></b> The objectives of this study were to assess the feasibility of using body-worn sensors to track rehabilitation exercises in the inpatient setting and investigate which recording parameters and data analysis strategies are sufficient for accurately identifying and counting exercise repetitions. <b><i>Methods:</i></b> MC10 BioStampRC® sensors were used to measure accelerometer and gyroscope data from upper extremities of healthy controls (<i>n</i> = 13) and individuals with upper extremity weakness due to recent stroke (<i>n</i> = 13) while the subjects performed 3 preselected arm exercises. Sensor data were then labeled by exercise type and this labeled data set was used to train a machine learning classification algorithm for identifying exercise type. The machine learning algorithm and a peak-finding algorithm were used to count exercise repetitions in non-labeled data sets. <b><i>Results:</i></b> We achieved a repetition counting accuracy of 95.6% overall, and 95.0% in patients with upper extremity weakness due to stroke when using both accelerometer and gyroscope data. Accuracy was decreased when using fewer sensors or using accelerometer data alone. <b><i>Conclusions:</i></b> Our exploratory study suggests that body-worn sensor systems are technically feasible, well tolerated in subjects with recent stroke, and may ultimately be useful for developing a system to measure total exercise “dose” in poststroke patients during clinical rehabilitation or clinical trials.